阅读说明：本技术 具有耦合子系统模型和数字孪生的操作优化分配控制系统 (Operation optimization distribution control system with coupled subsystem model and digital twinning ) 是由 克里斯托弗·约翰森 洛伦佐·埃斯克里切 迪纳卡尔·德什穆克 迈克尔·阿尔圭洛 奥图格·拜拉姆 于 2021-05-07 设计创作，主要内容包括：公开了用于优化业务操作和资产系统的优化系统和方法。系统包括对应于资产系统的数字孪生；与业务操作相对应的业务模型；和电子控制单元(ECU)。ECU编程为：实施资产优化器模块,其中实施资产优化器模块将多个数字孪生互连以用于优化；执行资产优化器模块,其中,资产优化器模块优化数字孪生,以获得资产系统的一个或多个优化参数；实施系统优化器模块,其中,系统优化器模块接收一个或多个优化参数和业务模型；执行系统优化器模块,其中,系统优化器模块生成业务模型的操作协议；以及向用户输出操作协议以在现实世界资产系统中实施。(An optimization system and method for optimizing business operations and asset systems is disclosed. The system includes a digital twin corresponding to the asset system; a business model corresponding to the business operation; and an Electronic Control Unit (ECU). The ECU is programmed to: an implementation asset optimizer module, wherein the implementation asset optimizer module interconnects the plurality of digital twins for optimization; executing an asset optimizer module, wherein the asset optimizer module optimizes the digital twin to obtain one or more optimized parameters of the asset system; implementing a system optimizer module, wherein the system optimizer module receives one or more optimization parameters and a business model; executing a system optimizer module, wherein the system optimizer module generates an operating protocol of the business model; and outputting the operating protocol to the user for implementation in the real-world asset system.)

1. A system, comprising:

a plurality of digital twins corresponding to one or more asset systems of an asset;

one or more business models corresponding to one or more business operations; and

an Electronic Control Unit (ECU), wherein the ECU is programmed to:

implementing an asset optimizer module, wherein implementing the asset optimizer module interconnects the plurality of digital twins for optimization over a time horizon, wherein the asset optimizer module selects the plurality of digital twins for optimization based on at least one of accuracy, time coverage, computation time, or contribution to variance;

executing the asset optimizer module over the time horizon, wherein the asset optimizer module optimizes one or more parameters of the plurality of digital twins to obtain one or more key process indicators for the one or more asset systems;

implementing a system optimizer module, wherein the system optimizer module receives the one or more optimization parameters and the one or more business models;

executing the system optimizer module, wherein the system optimizer module generates one or more operating protocols for the one or more business models; and

outputting the one or more operating protocols to a user for implementation in a real-world asset system.

2. The system of claim 1, wherein the ECU is further programmed to:

outputting an indication of one or more optimization statuses, wherein the indication defines an optimization level of at least one of the plurality of digital twins or the one or more business models.

3. The system of claim 1, wherein the ECU is further programmed to:

feeding back the one or more operating protocols into one or more of the plurality of digital twins such that the ECU executes another instance of at least one of the asset optimizer module or the system optimizer module to generate an updated set of the one or more operating protocols for implementation in the real-world asset system.

4. The system of claim 1, wherein the system optimizer module is configured to optimize each of the one or more business models based on interactions between the one or more business models and one or more optimization parameters.

5. The system of claim 1, wherein the ECU is further programmed to:

selecting one or more of the plurality of digital twins having a calculation time less than or equal to the time range in the simulated future period of time according to a limit on the calculation duration.

6. The system of claim 1, wherein the ECU is further programmed to:

selecting one or more of the plurality of digital twins having a calculation time less than or equal to the time horizon of a simulated future period, while optimizing a predicted KPI objective of operation, according to a desired predicted rate of variability reduction per unit of calculation time.

7. The system of claim 1, wherein the asset is an aircraft.

8. The system of claim 1, wherein one or more of the plurality of digital twins comprises one or more first sub-level digital twins corresponding to one or more asset subsystems of the one or more asset systems.

9. The system of claim 8, wherein the one or more first sub-level digital twins comprise one or more component level digital twins corresponding to one or more components of the one or more asset subsystems.

10. The system of claim 1, wherein the one or more business models comprise at least one of:

the model of the fuel management is a model of the fuel management,

a model of the operation of the flight is described,

an asset maintenance planning model is created for the asset,

personnel scheduling models, or

A financial model.

Technical Field

The present application relates to systems and methods for performing optimization and controlling resource allocation using Digital Twins (DTs), and more particularly, to systems and methods for capturing interactions between physical flows between DTs and traffic state flows experienced by controlled objects in the real world using DTs.

Background

The Digital Twin (DT) is a digital version of the machine in the disclosed embodiment. Once created, the DT can be used to represent the machine in a digital representation of the real-world system (which itself can be described as a DT of the process implemented by the system). The DT is created to reflect the form and behavior of the corresponding machine in terms of operational capability, reliability and efficiency. In addition, the DT can reflect the state of machines in a larger system (e.g., a physical and/or business system). For example, sensors may be placed on the machine to capture real-time (or near real-time) data from physical objects relayed to the remote DT. The remote DT may then make any changes necessary to maintain its correspondence with the twin asset. For example, the optimal control allocation may then alter the specified operating duty cycle and maintenance actions to achieve the business system key process index probabilities at selected time intervals.

The design focus of conventional DT implementations is object level behavior. The current focus of DT technology is to create a digital correspondence of an object that can be used to identify opportunities to improve the efficiency of the object in its physical energy conversion and reliability in operational use. For example, it has been demonstrated that the DT of a wind turbine can provide up to 20% more energy capacity than a wind turbine without DT. This is accomplished by collecting, visualizing, and analyzing data from the wind turbines, using predictive analysis to assist in operational strategy planning and dynamic control (subject to life and physical constraints) in operation. This is the object level space DT, since it only captures objects during operation.

Other conventional systems employ a broad field of view with object-level spatiotemporal DT. The DT captures the characteristics of the object from a design, engineering, production, operation, service, maintenance, end-of-life, and financial perspective. To capture spatiotemporal aspects, some systems use an integral representation approach in which a digital representation of the object summarizes all aspects and data required for different lifecycle stages. This approach, known as a mechatronic object, may not be effective because the aggregation of all necessary data and analysis causes the resulting object to quickly become inflated. Furthermore, such DTs cannot capture the interaction flow between different DTs or the traffic flow experienced by the object in the real world.

Therefore, there is a need for systems and methods that dynamically and optimally derive DTs, and then use them to capture the interaction flow between multiple DTs and the traffic that the object is subjected to in the real world.

Disclosure of Invention

In one embodiment, a system comprises: a plurality of digital twins, the plurality of digital twins corresponding to one or more asset systems; one or more business models corresponding to one or more business operations; and an Electronic Control Unit (ECU). The ECU is programmed to: an asset optimizer module, wherein the asset optimizer module interconnects the plurality of digital twins for optimization over a time horizon, wherein the asset optimizer module selects the plurality of digital twins for optimization based on at least one of accuracy, time coverage, computation time, or contribution to variance; executing an asset optimizer module over a time horizon, wherein the asset optimizer module optimizes one or more parameters of the plurality of digital twins to obtain one or more key process indicators for one or more asset systems; implementing a system optimizer module, wherein the system optimizer module receives one or more optimization parameters and one or more business models; executing a system optimizer module, wherein the system optimizer module generates one or more operating protocols for the one or more business models; and outputting one or more operational protocols to the user for implementation in the dynamically controlled real-world asset system.

In one embodiment, a method comprises: implementing an asset optimizer module with the computing device, wherein the implementing asset optimizer module interconnects the plurality of digital twins for optimization over a time horizon, wherein the asset optimizer module selects the plurality of digital twins for optimization based on at least one of accuracy, time coverage, computation time, or contribution to variance; executing, with a computing device, an asset optimizer module, wherein the asset optimizer module optimizes one or more parameters of one or more of the plurality of digital twins to obtain one or more key process indicators for one or more asset systems of the asset; implementing a system optimizer module with a computing device, wherein the system optimizer module receives one or more optimization parameters and one or more business models corresponding to one or more business operations; executing, with a computing device, a system optimizer module, wherein the system optimizer module generates one or more operating protocols for one or more business models; and outputting, with the computing device, the one or more operating protocols to a user (or an automated control system) for implementation in the real-world asset system.

In one embodiment, a non-transitory machine-readable medium containing a set of instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising: implementing an asset optimizer module with the computing device, wherein the implementing asset optimizer module interconnects the plurality of digital twins for optimization over a time horizon, wherein the asset optimizer module selects the plurality of digital twins for optimization based on at least one of accuracy, time coverage, computation time, or contribution to variance; executing, with a computing device, an asset optimizer module, wherein the asset optimizer module optimizes one or more parameters of one or more of the plurality of digital twins to obtain one or more key process indicators for one or more asset systems of the asset; implementing a system optimizer module with a computing device, wherein the system optimizer module receives one or more optimization parameters and one or more business models corresponding to one or more business operations; executing, with a computing device, a system optimizer module, wherein the system optimizer module generates one or more operating protocols for one or more business models; and outputting, with the computing device, the one or more operating protocols to the user for implementation in the real-world asset system.

These and other features of the present technology, as well as the methods of operation and functions of the related elements of structure and the combination of parts and economies of manufacture, will become more apparent upon consideration of the following description and the appended claims with reference to the accompanying drawings, all of which form a part of this specification, wherein like reference numerals designate corresponding parts in the various figures. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the application. As used in the specification and in the claims, the singular form of "a", "an", and "the" include plural referents unless the context clearly dictates otherwise.

Drawings

The embodiments set forth in the drawings are illustrative and exemplary in nature and are not intended to limit the subject matter defined by the claims. The following detailed description of illustrative embodiments can be understood when read in conjunction with the following drawings, where like structure is indicated with like reference numerals, and in which:

FIG. 1A schematically depicts an example computing network for system optimization for asset and business operations with Digital Twins (DTs), according to one or more embodiments shown and described herein;

FIG. 1B schematically depicts an example computing device for system optimization for asset and business operations using DTs, according to one or more embodiments shown and described herein;

FIG. 2 depicts an illustrative block diagram of an example system hierarchy for optimization at various levels in accordance with one or more embodiments shown and described herein;

FIG. 3A depicts an illustrative example of asset optimization for the system hierarchy block diagram of the optimization of FIG. 2 in accordance with one or more embodiments shown and described herein;

FIG. 3B depicts an illustrative example of system optimization continuing from FIG. 3A in accordance with one or more embodiments shown and described herein;

FIG. 4 depicts an example high-level block diagram of a DT system according to one or more embodiments shown and described herein;

FIG. 5 illustrates an example DT having six modules in accordance with one or more embodiments shown and described herein;

FIG. 6 depicts a flow diagram of an illustrative method for optimizing asset and business operations in accordance with one or more embodiments shown and described herein; and

FIG. 7 depicts an illustrative time diagram depicting the utilization and selection of a plurality of asset DTs to be used in a system simulation with optimization over a time horizon.

Detailed Description

Referring to the drawings, embodiments of the present application are generally directed to optimization systems and methods that configure and operate DT models of underlying asset systems and business elements to help drive operational optimization. In general, the systems and methods described herein provide the ability to manage business level optimization through the use of business models coupled through a business integration system that allows feedback from one business element to the next. The system may provide real-time optimization. For example, the system utilizes the historical, current and specified future time domains to optimize a plurality of resource allocations to achieve a plurality of goals required for the optimization operation in the current (true) time domain. In addition, the system provides management of the optimization status by tracking key business parameters that indicate the business optimization status.

In certain embodiments, the DT models are coupled to each other by a main system inside the business element, and then optimized across multiple elements. In other words, the system provides optimization through real-time operation of the optimization tool and/or optimization with offline and application operation tracking to ensure that the system operates within optimization limits or for hypothetical planning phases, such as designing complex asset systems. In addition, the system can manage multiple optimization threads that can be independent within a business unit, or aggregate optimization that results in overall optimization of business unit and asset operations.

In general, without the systems and methods described herein, optimization and physical control is a difficult process across complex business management and delivery because optimization can quickly exceed current computing capabilities relative to time constants required for computation, e.g., the present disclosure contemplates a system that optimizes one, hundreds or thousands of potential futures across the next deterministic time step or transition states or events across multiple physical assets through millions of operational increments and completes the optimization with the required accuracy and/or deadline. The systems and methods described herein provide a method for providing optimizations within current computing capabilities. In some embodiments, this is accomplished by utilizing a hierarchical system structure of DT models of components, sub-systems and/or asset systems, and models of business units. In such embodiments, the system may calculate local differential sensitivities, may learn how adjustments to a particular model will affect changes in other models, and how dynamic changes in one time interval will affect other future time intervals relative to asset and system dynamics, thereby minimizing the need to optimize the computational space and recalculate and/or reconstruct the entire optimization.

The system may be modeled as a subsystem model, such as a DT model. The DT models are coupled together to provide their relevant inputs through a system hierarchy that allows any and/or all levels of optimization, as well as the ability to examine sub-optimization functions. As described in more detail herein, the DT model includes its associated fleet management protocols, which provide a hierarchy of systems. For example, a fleet may refer to a fleet of aircraft, vehicles, ships, etc., that engage in activities such as cargo or personnel transportation. Additionally, in some embodiments, the system may be driven in a simulated environment to allow tuning and "what if" calculations.

DT in the disclosed embodiments differs to some extent from simulation. Simulations provide an understanding of what may happen in the future real world when presenting generated external conditions or simulating with historical data. In one embodiment, DT may be stateless with respect to time and therefore may be used in the current time domain to reconcile hidden variables or may be used to calculate a very recent physical output from existing sensor data. In another embodiment, DT may be invoked by a simulator that traverses the time domain. Currently, there is an unmet need to call from multiple DTs for a simulation system, however, this is addressed by the systems and methods disclosed herein. Thus, a need not met by the current art is to invoke an optimal DT from a feasible set of DTs for one or more time periods and to invoke one or more state computation methods based on analysis, decision support or automated system variables computed for use in the complex business physical system of the system.

In the current temporal context, like simulation, DT can help to understand what may happen in the real world over time. However, DT also provides insight into what physically occurs, i.e. the way assets or business units behave in the real world and the causal understanding, for example, by tuning down and physical dynamics that may not be directly measured but can be inferred or calculated as the only possible internal dynamics, on the premise that the physical system is modeled in simulation and compared to real-time signals. This is accomplished by providing a continuous stream of information to the DT and reconciling between its calculated physical state and the empirically observed physical state to estimate what the missing internal values must be. The present embodiment takes advantage of this feature and further steps by integrating multiple DTs and optionally other types of models together in a system hierarchy where optimization processes are implemented at various levels in the hierarchy to implement real-time or near real-time optimization parameters (as output of level optimization) and/or operating protocols and/or insights into physical constraints that manifest themselves as operational limitations. The operating protocol includes events, activities, and/or threshold ranges that should be implemented or maintained to achieve a desired goal, such as to achieve and/or maintain operation of the system in an optimized state. Hidden constraints may include the internal physical dynamics of complex engineering assets (e.g., turbines) whose internal pressure or temperature or flow signals may not be directly measurable by physical sensors and whose operation is or should be limited. For example, the ignition temperature should be limited so that it does not exceed the material properties of the engine, which may have reduced thermal properties due to wear from previous operations.

In the context of predicted future times, there are no physical measurement signals from field operations, so instead DT depends on calculated estimates and exogenous conditions determined from the system model. These future temporal contexts are operationally valuable because, given previous choices and influences and feasible future operational choices, it can optimize operation in the current time domain, allowing a practical system to operate optimally in one or more time domains. However, many simulated futures with replication functionality to estimate probabilities can consume significant computing resources. The method not only rationalizes the optimal DT for one or more time domains, but also achieves the calculated system response specificity and the calculated duration.

Now, an optimization system and method for optimizing asset-related business operations by utilizing a DT model in a hierarchical system structure will be described below. Various systems and methods will now be described in more detail herein with particular reference to the accompanying drawings.

Referring now to the drawings, FIG. 1A depicts an exemplary network 100 showing components of a system for system optimization for asset and business operations utilizing DTs according to one or more embodiments shown and described herein. As shown in fig. 1A, network 100 may include a wide area network (e.g., the internet), a Local Area Network (LAN), a mobile communication network, a Public Service Telephone Network (PSTN), and/or other networks, and may be configured to electronically and/or communicatively connect user computing device 102, computing device 103 (also referred to herein as an electronic control unit or ECU), and administrator computing device 104.

The user computing device 102 may include a display 102a, a processing unit 102b, and an input device 102c, each of which may be communicatively coupled together and/or to the network 100. The user computing device 102 may be used to interface with a user that may manipulate and/or configure DT models, business models, optimization processes, and the like. Additionally, an administrator computing device 104 is included in FIG. 1A. In the event that the computing device 103 requires supervision, updating, or correction, the administrator computing device 104 may be configured to provide the desired supervision, updating, and/or correction.

It should be understood that although the user computing device 102 and the administrator computing device 104 are depicted as personal computers and the computing device 103 is depicted as a server, these are merely examples. More specifically, in some embodiments, any type of computing device (e.g., mobile computing device, personal computer, server, etc.) may be used for any of these components. In addition, although each of these computing devices is illustrated in fig. 1 as a single piece of hardware, this is also an example. More specifically, each of the user computing device 102, the computing device 103 (optionally used to perform optimization by one or more of the processes described herein), and the administrator computing device 104 may represent a plurality of computers, servers, databases, etc. For example, each of the user computing device 102, the computing device 103, and the administrator computing device 104 may form a distributed or grid computing framework for implementing the methods described herein.

Turning now to fig. 1B, fig. 1B depicts an example computing device 103 for system optimization for asset and business operations utilizing DTs in accordance with one or more embodiments shown and described herein. In particular, FIG. 1B depicts the computing device 103 from FIG. 1, while also showing a system for system optimization for asset and business operations utilizing DTs. According to embodiments shown and described herein, the computing device 103 may utilize hardware, software, and/or firmware. Although in some embodiments the computing device 103 may be configured as a general purpose computer with the necessary hardware, software, and/or firmware, in some embodiments the computing device 103 may be configured as a special purpose computer specifically designed to perform the functions described herein.

As also shown in FIG. 1B, the computing device 103 may include a processor 130, input/output hardware 132, network interface hardware 134, a data storage component 136, and a memory component 140. The data storage component 136 stores the DTs 138a, business models 138b, optimization parameters 138c, and operating protocols 138 d. The memory component 140 can be a machine-readable memory (also can be referred to as a non-transitory processor-readable memory). The memory component 140 may be configured as volatile and/or non-volatile memory, and thus may include random access memory (including SRAM, DRAM, and/or other types of random access memory), flash memory, registers, Compact Discs (CDs), Digital Versatile Discs (DVDs), and/or other types of storage components. Additionally, the memory component 140 may be configured to store operating logic 142 and logic for implementing an asset optimizer module 144a and a system optimizer module 144b (each of the asset optimizer module 144a and the system optimizer module 144b may be embodied as a computer program, firmware, or hardware, as examples).

Operating logic 142 may include an operating system and/or other software for managing components of computing device 103. The asset optimizer module 144a may include logic configured to optimize one or more DTs that define an asset or assets, as will be described in detail below. The system optimizer module 144b may include logic configured to optimize business operations in conjunction with optimization parameters received from optimization of an asset and/or assets, as will be described in detail below. The asset optimizer module 144a and the system optimizer module 144b will be described in more detail with reference to the following figures.

A local interface 146 is also included in fig. 1B and may be implemented as a bus or other interface to facilitate communication among the components of the computing device 103.

Processor 130 may include any processing component configured to receive and execute programming instructions (e.g., from data storage component 136 and/or memory component 140). The instructions may be in the form of a set of machine-readable instructions stored in the data storage component 136 and/or the memory component 140. Input/output hardware 132 may include a monitor, keyboard, mouse, printer, camera, microphone, speaker, and/or other devices for receiving, transmitting, and/or presenting data. The network interface hardware 134 may include any wired or wireless network hardware, such as a modem, a LAN port, a Wi-Fi card, a WiMAX card, mobile communication hardware, and/or other hardware for communicating with other networks and/or devices.

It should be understood that the data storage component 136 can reside locally to the computing device 103 and/or remotely from the computing device 103 and can be configured to store one or more pieces of data for access by the computing device 103 and/or other components. As shown in fig. 1B, the data storage component 136 stores a DT 138 a. DT 138a is a digital copy of a physical entity, either animate or inanimate. That is, a DT is a digital version of a machine (also referred to as an "asset"). Once created, the DT can be used to represent the machine in a digital representation of a real-world system. The DT is created such that it computationally reflects the behavior of the corresponding machine. Further, the DT may reflect the state of the machine in a larger system. For example, sensors may be placed on the machine to capture real-time (or near real-time) data from the physical object to relay it back to the remote DT. The DT may then make any changes necessary to maintain its correspondence with the twin asset to provide operational instructions, diagnostics, insight into unmeasurable internal physical dynamics, insight into efficiency and reliability.

The data storage component 136 can also include a business model 138b, which can be constructed as a DT or other type of virtual model of a business operation that contains one or more physical state estimates DT operatively linked via the business operation. Business model 138b can include any model that represents a business unit or business objective. For example, business models 138B may include fuel models 352 (FIG. 3B), flight operations models 354 (FIG. 3B), asset scheduling maintenance models 356 (FIG. 3B), personnel scheduling models 358 (FIG. 3B), financial models 360 (FIG. 3B), and/or other business models 362 (FIG. 3B). The foregoing business models are merely illustrative and may be replaced or supplemented with other business models depending on the type of business and the operation that the user seeks to optimize. The business model will be described in more detail below with reference to FIG. 3B.

Still referring to FIG. 1B, the data storage component 136 can also include optimization parameters 138 c. The optimization parameters 138c include intermediate parameters of the optimization process that occur at various levels of the system hierarchy. (an example system hierarchy is depicted and described below with reference to FIG. 2). The optimization parameters 138c may be generated by an optimization process and then stored in the data storage component 136 until a subsequent process requires the optimization parameters 138 c. However, in some embodiments, the optimization parameters 138c may not be stored in the data storage component 136, but may be directly input into subsequent models or processes.

The data storage component 136 may also include an operating protocol 138 d. The operating protocol 138d may include events, activities, and/or threshold ranges that should be implemented or maintained to achieve a desired goal, such as to bring and/or maintain the operation of the system to an optimized state. The operating protocol 138d may be determined by an optimization system.

Turning now to FIG. 2, an illustrative block diagram of an example system hierarchy for optimization at various levels is depicted. The system hierarchy depicted in FIG. 2 includes an asset optimization level 200 and a business model optimization level, where the business model 210 is optimized with inputs from the optimization of the asset optimization level 200. In some embodiments, the asset optimization level 200 includes one or more assets that may be optimized, for example, an aircraft fleet. Considering a single asset, one or more DTs may be created and used to optimize the asset. In some embodiments, an asset may be defined by one or more component DTs 201 for components of the asset. In some embodiments, an asset may be defined by one or more subsystems DT 202, which subsystems DT 202 may include one or more DTs defining the subsystem of the asset or a combination of one or more component DTs 201. In some embodiments, the assets may be defined by system level DTs 203. It should also be understood that an asset may be defined by a combination of DTs at various levels (e.g., at the component, subsystem, and/or system level).

The asset optimizer module 144a (fig. 1B) may be implemented to generate optimization parameters for the asset to optimize the asset for an intended or desired function or operation. For example, a user may desire an asset that is capable of transporting cargo with low offline maintenance time and high long haul flight fuel efficiency. The asset optimizer module 144a (fig. 1B) may be configured with these requirements and optimize the asset, generating optimization parameters that define the components and/or subsystems of the asset and operating conditions such as anticipated maintenance. The DT or DTs defining the asset may be further configured to receive real-time information (e.g., sensor data from the operation of the asset), enabling the asset optimizer module 144a (fig. 1B) to provide optimization parameters for a predefined time period (e.g., a user-defined time period) or prediction of a future time to determine future economics and/or operation of the asset (e.g., when maintenance may be required).

Turning briefly to fig. 3A, a more detailed example of an asset defined by a plurality of subsystems DT at the asset optimization level 200 (fig. 2) is depicted in a block diagram 300. For illustrative purposes, the assets described herein are aircraft. However, it should be understood that an asset may be any object, such as a vehicle, a facility, or other tangible object, such as an aircraft and/or its engines, and within an engine and/or its modules. The object may be a component of the business system that is constrained by contractual terms, fleet membership, or components in an entity financial statement. An aircraft includes many components that form many systems and subsystems. For example, an aircraft may include one or more engines, fuel systems, hydraulics, avionics, braking systems, Auxiliary Power Units (APUs), customer interiors that define cargo spaces of the aircraft, and/or other systems and components. The fleet may be subject to long-term service agreements or financing terms and billed in one or more financial statements. The system may evolve over time, wherein the mix of assets and their performance also change as a result of intent or in response to external forces or responsibility changes. In an embodiment, a DT may be generated for each component and/or subsystem of an aircraft system. For example, an aircraft may be defined by a DT 302 for a fuel system, one or more DTs 304 for one or more engines, a DT 306 for hydraulics, a DT 308 for avionics, a DT 310 for a braking system, a DT312 for an APU, a DT 314 for customer internals, and/or other DTs for other systems and components. Each DT may be interconnected to each other through an asset optimizer 320. The asset optimizer 320 implements an asset optimizer module 144a so that assets can be optimized and optimization parameters can be generated. The asset optimizer 320 effectively creates a network of DTs for an aircraft so that adjustments to one DT can be implemented within other connected DTs as in real-world aircraft. FIG. 3A

Referring back to FIG. 2, optimization parameters obtained from optimizing assets at a first level of the system hierarchy may be included in business model 210 and subsequently input to system optimizer unit 240. In some embodiments, the system optimizer unit may also be connected to other business models 220, which other business models 220 may not be linked to the assets, but may be related to the overall business operation. Additionally, in some embodiments, an optimizer management tool 230, for example implemented by the user computing device 102 (fig. 1A), may be communicatively coupled with the system optimizer unit 240. The optimizer management tool 230 may provide parameters to the system optimizer unit such as the desired goals that should be achieved by the optimization, the ability to track key elements of the optimization, and/or provide updates to the system optimizer module 144b (FIG. 1A) implemented and executed by the system optimizer unit 240.

The system optimizer unit 240 generates and outputs an indication of a set of operating protocols 250 and/or an optimization status 260 of the system via the system optimizer module 144 b. The operating protocol 250 includes events, activities, and/or threshold ranges that should be implemented or maintained to achieve a desired goal, such as to bring and/or maintain the operation of the system to an optimized state. The optimization state 260 can include tracking key elements that provide an indication as to how to optimize the system or whether certain optimization parameters are approaching their desired limits. For example, if the financial transaction unit includes a range defining expected revenue or expenditure, and the optimization seeks to obtain a result within that range but near one of the extremes, the status may indicate the same. In some embodiments, the aforementioned ranges may be identified by a user as key elements for tracking purposes and thus displayed on a display device (e.g., display device 102a, fig. 1A) for tracking purposes.

Turning briefly to fig. 3B, a more detailed example of a business unit related to an asset defined by a plurality of subsystems DT is depicted in block 350. More specifically, FIG. 3B is a continuation of the block diagram 300 depicted in FIG. 3A. FIG. 3B depicts a subsequent level of the system hierarchy. In this example embodiment, the subsequent level of the system hierarchy is the business unit optimization level. The level includes optimization parameters from an asset optimization level and a business model. For example, the business models depicted in FIG. 3B include a fuel model 352, a flight operations model 354, an asset scheduling maintenance model 356, a personnel scheduling model 358, a financial model 360, and/or other business models 362. The foregoing business models are merely illustrative and may be replaced or supplemented with other business models depending on the type of business and the operation that the user seeks to optimize.

The fuel model 352 may be a DT or another model defining business operations associated with fuel purchase, distribution, refinement, sale, and the like. In some embodiments, these activities may be closely related to the operation of the asset and the desire of the customer to maintain the fuel costs within a defined range or reduce the fuel costs. The flight operations model 354 may be a model that defines a flight schedule, route plan, etc. The asset scheduling maintenance model 356 may be a model that defines maintenance requirements and future predictive maintenance based on current operating activities, optimization objectives defined by other business models, and/or asset configurations communicated by optimization parameters from the asset optimizer 320.

The business units being modeled may include a personnel scheduling model 358 configured to model personnel needs, associated costs, and the like in response to asset and other business unit activities. The personnel scheduling model 358 may also provide constraints to the system by the total number of personnel to be employed, the total amount of capital allocated to the personnel, definitions of field and service shop maintenance, material usage, manner of operation limits or permits, and the like. In some embodiments, the business units may be further defined by a financial model 360, and the financial model 360 may define the financial model of the business units using parameters that are adjustable during the optimization process. Further, business units can be defined by other business models 362, other business models 362 not disclosed herein but may be apparent to those interacting with a particular business unit.

The system optimizer 370 effectively creates a network of DTs and/or other types of models for business operations defining a business unit so that one DT can be adjusted within other connected DTs as in a real world business unit. As discussed with reference to fig. 2, the system optimizer 370 (corresponding to the system optimizer unit 240 depicted in fig. 2) generates a set of outputs 380, e.g., a set of operating protocols 250 (fig. 2) and/or an indication of the optimization status 260 (fig. 2) of the system, via the system optimizer module 144 b.

Turning to fig. 4, a high-level architecture of a system 400 according to some embodiments is depicted. The system 400 includes a computer data store 410 (e.g., a data store of the user computing device 102, the computing device 103, and/or the administrator computing device 104 as shown in fig. 1A) that provides information to the DT 450 of the twin physical asset or system 420. The data in computer data store 410 may include, for example, information about twin physical assets or systems 420, such as historical engine sensor information (e.g., outside temperature, exhaust temperature, engine model, landing gear, etc.) about a number of different aircraft engines and prior aircraft flights.

According to some embodiments, the DT 450 may access the computer data store 410 and utilize a probabilistic model creation unit to automatically create a predictive model that may be used by the DT modeling software and the processing platform to create predictions and/or results that may be suitably transmitted to the respective user platform 470 (e.g., displayed to a user). As used herein, the term "automatically" may refer to an action that may be taken with little or no human intervention, for example.

As used herein, devices, including those associated with system 100 and any other devices described herein, may exchange information via any communication network, which may be one or more of a local area network ("LAN"), a metropolitan area network ("MAN"), a wide area network ("WAN"), a proprietary network, a public switched telephone network ("PSTN"), a wireless application protocol ("WAP") network, a bluetooth network, a wireless LAN network, and/or an internet protocol ("IP") network (e.g., the internet, an intranet, or an extranet). Note that any of the devices described herein may communicate via one or more such communication networks.

The DT 450 may store and/or retrieve information from various data sources, such as the computer data store 410 and/or the user platform 470. The various data sources may be stored locally or may reside remotely from the DT 450. Although a single DT 450 of a twin physical asset or system 420 is shown in fig. 4, any number of such DTs may be included. Furthermore, various devices described herein may be combined in accordance with embodiments of the present invention. For example, in some embodiments, the DT 450 and one or more data sources of the twin physical asset or system 420 may comprise a single device. DT software functions may be performed by a set of networked devices in a distributed processing or cloud-based architecture.

A user may access the system 400 via one of the user platforms 470 (e.g., the user computing device 102 or the computing device 103 as shown in fig. 1A, which may be a personal computer, a tablet, or a smartphone) to view information about DTs and/or manage DTs according to any of the embodiments described herein. According to some embodiments, the interactive graphical display interface may allow an operator to define and/or adjust certain parameters, and/or provide or receive automatically generated recommendations or results.

Fig. 5 now depicts a more detailed embodiment of a DT with six modules. DT can have two functions: twin physical systems are monitored and predicted. Another function of the DT may include limited or full control of the twin physical system. In one embodiment, the DT of the twin physical system includes (1) one or more sensors that sense values of specified parameters of the twin physical system, and (2) a realistic computer model of the multiple elements of all subject systems and their interactions under a range of conditions. This may be implemented using computer models with a large number of degrees of freedom and may be associated with the integration of complex physical models including, for example, computational fluid dynamics, structural dynamics, thermodynamic modeling, stress analysis modeling, and/or fatigue crack models. Such methods may be associated with, for example, a unified physical model ("UPM"). Furthermore, embodiments described herein can solve the resulting system of partial differential equations used in applying random finite element methods, utilize high performance computing resources that can scale up to trillion times per second, and are implemented in a useful manner. The computing system used to derive the states and responses requires operational control, which will be described in more detail in this application.

Consider, for example, fig. 5, which shows a DT 550 including such a Unified Physical Model (UPM) 551. The DT 550 may use an algorithm (such as, but not limited to, an extended kalman filter) to compare the model prediction with the measurement data from the twinned physical system. The difference between the predicted and actual sensor data (called variance or innovation) can be used to tune the internal model parameters to match the DT 550 to the physical system. The UPM 551 of the DT may be configured so that it can adapt to changing environmental or operating conditions seen by an actual twin asset. Potential physics-based formulas may be adapted to reflect the new realities experienced by physical systems.

The DT 550 also includes a component dimension value ("CDV") table 552, which table 552 may include a list of all physical components of the twin physical system. Each component may be tagged with a unique identifier, such as an internet protocol version 6 ("IPv 6") address. Each component in the CDV table 552 may be associated or linked with a value for its size, which is the most important variable for the conditional size of the component. The product lifecycle management ("PLM") infrastructure, if utilized efficiently, can be inherently consistent with the CDV tables 552, enabling the lifecycle asset performance states computed by the DTs 550 to be closed-loop model validation support for size and performance calculations and assumptions. The number of component sizes and their values may be extended to accommodate the storage and updating of values of exogenous variables found during DT operations.

The DT 550 may also include a system architecture 553, which system architecture 553 specifies the components of the twin physical system and how those components are connected or interact with each other. The system architecture 553 may also specify how the components react to input conditions including environmental data, operational controls, and/or externally applied forces.

The DTs 550 may also include economic operation optimizations 554 that control use and consumption of the industrial system to create operations and/or critical process results that result in financial rewards of users and service providers of the industrial system over a period of time and risks of those projected rewards. Similarly, the DT 550 may include an ecosystem simulator 555, which ecosystem simulator 555 may allow all contributors to interact, not only at the physical level, but actually across time, operational efforts, and/or economic realms. The part supplier or anyone with special knowledge can supply the DT model to be operated in an ecosystem and to interact in a reciprocal and profitable way. The models may be connected directly or indirectly, for example, through a data service or via parameter exchange in digital form. The DT 550 may further include a supervisory computer control 556 that controls the overall function of the DT 550, accepts inputs and produces outputs. Monitoring computer controls 556 can orchestrate the data flow, data storage, computation results and/or calculations required for computation state, and subsequent use of performance and state-of-life estimates for operation and PLM closed-loop design, such that digital thread connections are designed, manufactured and/or operated.

As used herein, the term "in operation" may refer to an operating state in which both the twin physical system and the DT 550 are operating. The term "non-operational state" may refer to an operational state in which the twin physical system is not operating but the DT 550 continues to operate. The phrase "black box" may refer to a subsystem, which may be defined by the DT 550, for recording and saving information obtained in the operation of the twin physical system for analyzing the non-operational state of the twin physical system. The phrase "tolerance envelope" may refer to the residual or magnitude that a reading of a sensor may deviate from its predicted value without initiating other actions (e.g., an alarm or diagnostic routine). The term "tuning" may refer to the adjustment of DT software or component values or other parameters. The operating state may be a non-running state or in operation. The term "mode" may refer to the allowable operating protocols of the DT 550 and its twin physical system. According to some embodiments, there may be a primary mode and a secondary mode associated with the primary task.

Still referring to fig. 5, the inputs to the DT 550 may include conditions 510, which conditions 510 include environmental data (such as weather-related quantities) and operational controls (such as requirements for a twin physical system to achieve a particular operation, for example, in the case of aircraft control). The input may also include data from a sensor 520, the sensor 520 being placed on and within the twin physical system. A sensor suite embedded within the twinned physical system may provide an information bridge to the DT software. Other inputs may include a tolerance envelope 530 that may specify time and amplitude regions that are acceptable regions of differences between actual sensor values and their predictions by DT. Other inputs to the system may include maintenance inspection data, manufacturing design data, and/or hypothetical exogenous data (e.g., weather, fuel costs, and defined solutions, such as candidate designs, data allocation and maintenance, and/or work scope). The economic data request 540 may also be input into the DT 550. For example, the economic data request may include a target and/or a range of economic operation for the DT modeled system or asset.

"economic operation" can be used to create a demonstrable business value. For example, an economic operation may be assigned to operate with and track an asset over the life cycle of the asset or the duration of a maintenance/performance contract. The economic operation DT software model may include an economic operation optimization module for creating economic data and using it in modeling to coordinate optimal operational control of the twin physical system with economic considerations related to the physical system (e.g., inspection scheduling, related logistics, assessment and mitigation of financial risk, etc.).

The output from the DT 550 may include a continuously updated estimate of the remaining useful life ("RUL") 560 of the twin physical system. It is often desirable to evaluate and/or predict the operation of real-world physical systems, such as electromechanical systems. For example, predicting the remaining useful life ("RUL") of an electromechanical system, such as an aircraft engine, may help to plan when the system should be replaced. Likewise, an owner or operator of a system may wish to monitor the condition of the system or a portion of the system to assist in making maintenance decisions, budget predictions, and the like. However, even with improvements in sensor and computer technology, accurately making such evaluations and/or predictions can be a difficult task. For example, events that occur when the system is not operating may affect the RUL and/or system conditions, but are generally not considered by typical methods of system evaluation and/or prediction processing.

Other outputs from the DT 550 may include alarms and diagnostics 570. For example, an alert of a possible twin physical system component failure may be output. Results of the DT diagnostic work and/or performance estimates of critical components within the twinned physical system may also be output. For example, using the DT 550, an operator may be able to see how critical section performance of the gas turbine is degraded. This may be an important consideration for maintenance scheduling, optimal control, and other objectives. According to some embodiments, information may be recorded and saved in a black box about the in-operation information of the twin physical system for analyzing the non-operational state of the twin physical system. The DT 550 may also include outputting economic data and modeling results 580. The economic data and/or the modeling results 580 may be the optimization parameters 138c (FIG. 1B) used as inputs to the subsequent DT and model of the optimization system. In particular, for example, economic data and modeling results may include considerations of particular assets (such as aircraft engines), such as inspection schedules, associated logic, assessment and mitigation of financial risk, and the like.

Fig. 6 illustrates a method depicted in a flow chart 600, which may be performed by some or all of the elements of the system shown and described herein. The flow charts described herein do not imply a fixed order to the steps and embodiments of the present invention may be practiced in any order that is practicable. Note that any of the methods described herein can be performed by hardware, software, or any combination of these methods. For example, a computer-readable storage medium may store instructions thereon that when executed by a machine result in the performance of any of the embodiments described herein. Additionally, the method described in flowchart 600 is described with respect to computing device 103 (fig. 1A and 1B). However, this is merely an example.

In some embodiments, at block 602, the computing device 103 (fig. 1A and 1B) may generate one or more DTs that define one or more asset systems of an asset (such as an aircraft), an intentional combination of the DTs being a subsystem or system's DT. For example, but not limiting of, the asset may be an aircraft and one of the asset systems may be an engine of the aircraft. For example, a DT (e.g., DT 304 (fig. 3A)) defining an engine may be generated to numerically model the engine. Then, at block 604, the computing device implements an asset optimizer module, which may receive input parameters obtained from a user at block 606. In some embodiments, the input parameters may include conditions 510, sensors 520 (e.g., sensor values obtained from a real-world asset system), tolerance envelopes 530, and/or economic data requests 540 (e.g., defining economic targets for an asset system, which may be an aircraft engine). In some embodiments, the input parameters may be input parameters obtained from a user by the user computing device 102 (fig. 1A). Referring back to the example of an aircraft engine, the input parameters may include a fuel flow function, an operating altitude, an operating temperature, and/or an ambient pressure, etc. that define the aircraft engine so that it may be accurately modeled in a digital system. Implementing the asset optimizer module at block 604 causes the DTs to be interconnected such that the inputs and outputs from the respective DTs are linked together. For example, as shown in FIG. 3A, the DTs 302-314 are interconnected by an asset optimizer 320 that implements an asset optimizer module. That is, when the asset optimizer module is executed by the computing device at block 608, the DT (e.g., DT 302 and 314 of fig. 3A) is optimized and optimized parameters for one or more assets are generated. Optimization parameters may be input to block 610, at which block 610 the computing device implements a system optimizer module. The system optimizer module may receive one or more business models generated at block 612, such as business model 352 and 362 (see FIG. 3B). The one or more business models correspond to the operation of the business unit to be optimized. A business unit may be an airline that manages one or more aircraft (i.e., assets) and seeks to optimize the operation of the assets in connection with business operations, such as flight scheduling, personnel scheduling, and other business operations.

At block 614, the computing device executes a system optimizer module that optimizes one or more business models in conjunction with optimization parameters generated by the asset optimizer module from a resource layer of the system hierarchy (e.g., asset optimization level 200 depicted in fig. 2). For example, the computing device is configured with a system optimizer unit 240 (fig. 2) that implements the system optimizer module 144B (fig. 1B). The execution may be limited by the response time or available computational resources, and therefore the computational processing needs to be directly controlled within a certain computational envelope, for the duration of the operation time, to achieve the required level of specificity. At block 616, the computing device outputs an operating protocol (e.g., operating protocol 250 described with reference to fig. 2) that may be implemented in a real-world setting to implement the optimization system defined by the computing device implemented methods described herein. For example, an operating protocol may be that a particular engine on a particular aircraft is flown over a defined set of routes to minimize required maintenance time while maximizing its operating costs and maintaining fuel economy targets. Additionally, in some embodiments, at block 618, the computing device may output an indication of the optimization status of the system. The indication of the optimization status may include a trace element indicating a level of optimization and/or a correlation of optimization parameters and/or operating protocols with respect to defined or desired operating limits.

In some embodiments, at block 614, the operating parameters and/or operating protocols generated from the execution of the system optimizer module are fed back to block 604 and integrated with the DT of the asset. For example, referring briefly to FIG. 2, an operational protocol 250 may be fed back into the DT at the asset optimization level 200 for additional refinement/optimization activities. This is just one example of a feedback optimization parameter. Feedback of optimization parameters may be implemented between any stage of the system hierarchy (e.g., between the system optimizer unit 240 and the business model, between the operating agreement 250 and the asset optimization level 200 of the system output) so that optimization of the asset system and business unit operations may be interconnected. In the event that a set of optimization parameters is received at block 604, the computing device may perform a second iteration of the method depicted and described herein to update the optimization of the system. For example, in some cases, when optimizing a system in view of financial model 260 at a business operations optimization level (e.g., including system modules 210, 220, 230, 240 shown in FIG. 2), the asset configuration (e.g., selection of components in the asset) may need to be adjusted or redefined to satisfy the optimization protocol driven by financial model 260 (FIG. 2). Thus, the system is re-optimized using the adjusted components of the asset by feeding back the optimization results due to the inclusion of the business model.

In some embodiments, the utilization of multiple physical assets DT over a time horizon by coordinating to interact and compute key process indicators for a desired system that takes into account system behavior may include simulated utilization. The simulation may be a continuous time simulation or a discrete time simulation. The entity being simulated may be instructed to take action by the central analytic inference engine, or may have an autonomic behavioral response computed by each physical asset, while system dynamics occur with agent behavior. The time range may be historical (e.g., based on past sensor readings, events, and/or results), current, or future. The entities in the system simulation may be physical, informational, or economic in nature. The simulated scene may be deterministic or probabilistic and may be traversed in a directed graph or undirected graph mode over time. Where the simulation is configured to explore probabilistic paths, the replication is made through a definable time horizon, which may be controlled by the disclosed system, the replication includes multiple DTs that may be optimally invoked to describe elements of the system. In some embodiments, the interval for calculation may be specified to have a limit set by a time limit or accuracy.

Turning now to FIG. 7, an illustrative time diagram 700 is depicted depicting utilization of a plurality of assets DT over a time horizon. More specifically, the method for controlling the intentional selection of DTs used in system simulations, the time range of certain DTs, the contribution to the prediction variance, and the limit on the computation duration is controlled by the disclosed system. The continuous operation time 705 contains a range of historical time 715, current time 710, and future time 720 at which the physical asset and business system is operating.

As previously disclosed, assets and operations are modeled using mathematical abstractions disclosed as DTs, which models may be first principles in nature, such as engineering thermodynamic models or statistical models, such as Weibull distributions or artificial intelligence models, such as representations based on machine learning or a set of regular or closed form expressions, or even observed historical trajectories. These models may have different accuracies for converting their externality into their response. In this figure, blocks 725,730,735, and 740 represent different DTs of the same asset in one embodiment, and a mix of assets in another embodiment. These DTs may have different calculation durations.

For decision support, analysis, or automation that the disclosed system results in, the potential computation time 780 may or may not be short enough. At a time t from the start₀785 requires a certain response time t_c790, the system may invoke certain of the DTs 725,730,735,740 based on the calculated speed of DT 725,730,735,740 to provide a particular response time t_cAnd 790 for the most complete calculation. In the event that certain computational variance guarantees are required (e.g., as represented by equation 1 below) for a certain time interval 790, the system may invoke certain DTs in DT 725,730,735,740 based on the speed of calculation of DT 725,730,735,740 on an absolute basis or according to the rate of contribution of DTs to the variance 775 per unit time, as calculated by equation 2.

Wherein W_kIs a weighted percentage of DT of the selected k_kA partial distribution Y representing the increment of X in a time interval n, n being from an initial t_niTo the rear t_nThe index of the time step of.

In equation 2, the Δ calculation time is the time variation of the running DT and the simulation scene, and the Δ sensitivity is the variation of Y of X in equation 1. When learning is performed at a rate greater than the threshold rate for each calculation time interval, the learning process will continue. When the rate of change learning (i.e., the sensitivity change per calculation interval) is below a threshold, then learning may be stopped. For example, for a given set of DTs, if learning is desired to reduce the change in a particular aspect calculated by twinning by 1% per minute of calculation time, the change in the 1 standard deviation of the Net Present Value (NPV) per minute of calculation time is 2%, and the learning may run for 2 minutes. However, the desired learning rate may be possible for a first combination of DTs, but may not be possible for another selected combination of DTs. In some embodiments, the desired rate of change reduction may be achieved, but the calculation with a particular combination of DTs takes too long. That is, for example, the combination of DTs may be a complex model, such as a finite element model, that utilizes a large amount of computation time.

A given DT method may include many model types. In an example embodiment, first principles, statistics, machine learning, historical observations, rules, and/or heuristics define DT model types 725,730,735,740. The operating scheme should include future prediction means, e.g. with hopes that future time period t will be affected_+nCurrent time t of 720₀710 as is the case with the current action taken, four candidate models as shown in fig. 7 may be selected. DT models 725,730, and 735 overlap in their time ranges. Each DT model may have certain advantages over other models, such as computation time or accuracy, or the ability to interpret system dynamics with respect to changing input assumptions. In one embodiment, the sum of the interpretations of the cumulative velocity, accuracy, variance is the target of equation 1, which can be maximized or minimized. There may be multiple criteria, for example, in one embodiment, minimizing one or more model output changes per unit of change in one or more DT model inputs and calculating time t_cThe ratio of 790 or contribution sensitivity change to calculation time change is minimal, equation 2. In a time region, for example, as depicted along continuous operation time 705, more or less contribution may be made to the modeled key process indicators. For example, in economic computing, where use is made ofRisk adjusted discount rate will be t in the future_+n720 cash flow is converted to current t₀710 values (e.g., net present values), the per unit contribution of KPI variation from model DT 4740 will not be as great as from DT 1725. The future simulated complete path may utilize each DT in part as needed to meet the criteria of variation, length of time of operation, length of time of computation, and accuracy.

DT is invoked to achieve the computation goals and limits, and may ultimately form a compilation of model activations to complete the trajectory for the entire time, e.g., from the current time t₀710 to future time t_+n,720. For example, but not limiting of, DT 1725 in fig. 7 is the only viable DT model for whatever reason (computation speed, accuracy, prediction interval, etc.) is viable from start time to time 745, with only DT 3735 viable during the time 745 interval, until time 760, at which time 760 both DTs 730 and 735 have a candidate qualification. Selecting DTs according to one or more objectives or constraints_K. DT 1725 may be used optimally from start times 710 to 745, e.g., DT 3735 is called for interval spans 745 to 760, DT2 is then utilized from 760 to 765, and DT4 may be utilized from 765 to 770.

There may be the following: the combination of the asset's DT models 725,730,735,740 improves prediction accuracy by performing independent calculations throughout the operating time ranges 710, 720 and having a weighted percentage W of each DT output_kAnd forming comprehensive prediction. Weighted percentage of each DT output W_kPossibly at a time limit t_niTo t_nIntra prediction interval. Thus, DT is weighted in time by the computational optimizations 775, 793 for use as a key process indicator for KPI optimizer prediction and optimization. These optimization capabilities are nested in that the operation of the system of system 705 is optimized and the computational control of DT selection that satisfies the computation time constraints (e.g., represented by equation 3 below) and/or the contribution to variance or accuracy 775 is satisfied.

∑t_Computing<t_cEquation 3

It should be understood that DTs may be calculated or operated in parallel with other DTs, and may be purposefully composed by methods disclosed from other DTs. However, the calculations should be completed when the time constant required for decision support or automation is reached. Alternatively, when operating in the change reduction mode, i.e., solving equations 1 and 2, the system may be run until the learning threshold is met. Also, in some embodiments, these constraints may be nested. That is, the change pattern may operate as an inner loop and the total computation time may operate as an outer loop, or vice versa. A predetermined computation time duration may be defined for the combination of DTs, which then yields a learning rate or level of change that satisfies a computation time constraint or learning threshold.

The functional blocks and/or flowchart elements described herein may be translated into machine-readable instructions. By way of non-limiting example, the machine-readable instructions may be written using any programming protocol, such as: descriptive text to be parsed (e.g., hypertext markup language, extensible markup language, etc.), (ii) assembly language, (iii) object code generated by a compiler from source code; (iv) source code written using syntax from any suitable programming language for execution by an interpreter; (v) source code for compilation and execution by a just-in-time compiler, and so on. Alternatively, the machine-readable instructions may be written in a Hardware Description Language (HDL) such as logic implemented via a Field Programmable Gate Array (FPGA) configuration or Application Specific Integrated Circuit (ASIC) or equivalent thereof. Thus, the functions described herein can be implemented in any conventional computer programming language, as preprogrammed hardware elements, or as a combination of hardware and software components.

It should now be appreciated that the systems and methods described herein disclose the optimization of business unit operations and related assets organized in a system hierarchy using interconnected DTs, wherein the DTs are optimally selected based on varying and/or computing time objectives. For example, the systems and methods provide the ability to manage business level optimizations by using business models coupled through a business integration system that allows feedback from one business element to the next. The system may provide near or real time optimization in physical asset control embodiments. In addition, the system provides for management of optimization states by tracking key business parameters that indicate the state of present or simulated future business optimizations.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the application. Since modifications, combinations, sub-combinations and variations of the disclosed embodiments incorporating the spirit and substance of the application may occur to persons skilled in the art, the application should be construed to include everything within the scope of the appended claims and their equivalents.

Further aspects of the invention are provided by the subject matter of the following clauses:

a system, comprising: a plurality of digital twins corresponding to one or more asset systems of an asset; one or more business models corresponding to one or more business operations; and an Electronic Control Unit (ECU). The ECU is programmed to: an asset optimizer module, wherein the asset optimizer module interconnects the plurality of digital twins for optimization over a time horizon, wherein the asset optimizer module selects the plurality of digital twins for optimization based on at least one of accuracy, time coverage, computation time, or contribution to variance; executing an asset optimizer module over a time horizon, wherein the asset optimizer module optimizes one or more parameters of the plurality of digital twins to obtain one or more key process indicators for one or more asset systems; implementing a system optimizer module, wherein the system optimizer module receives one or more optimization parameters and one or more business models; executing a system optimizer module, wherein the system optimizer module generates one or more operating protocols for the one or more business models; and outputting one or more operating protocols to the user for implementation in the real-world asset system.

The system of any preceding item, wherein the ECU is further programmed to: outputting an indication of one or more optimization statuses, wherein the indication defines an optimization level of at least one of the one or more digital twins or the one or more business models.

The system of any preceding item, wherein the ECU is further programmed to: feeding back the one or more operating protocols into one or more of the plurality of digital twins such that the ECU executes another instance of at least one of the asset optimizer module or the system optimizer module to generate an updated set of one or more operating protocols for implementation in the real-world asset system.

The system of any preceding item, wherein the system optimizer module is configured to optimize each of the one or more business models based on interactions between the one or more business models and the one or more optimization parameters.

The system of any preceding item, wherein the ECU is further programmed to: one or more of the plurality of digital twins having a calculation time less than or equal to the time range are selected in the simulated future period according to the limit of the calculation duration.

The system of any preceding item, wherein the ECU is further programmed to: one or more of the plurality of digital twins having a computation time less than or equal to the time horizon of the simulated future period are selected while optimizing the operational predicted KPI target according to the desired predicted variability reduction rate per unit of computation time.

The system of any preceding item, wherein the asset is an aircraft.

The system of any preceding claim, wherein one or more of the plurality of digital twins comprises one or more first sub-level digital twins corresponding to one or more asset subsystems of one or more asset systems.

The system of any preceding item, wherein the one or more first sub-level digital twins comprise one or more component level digital twins corresponding to one or more components of one or more asset subsystems.

The system of any preceding item, wherein one or more business models comprise at least one of: a fuel management model, a flight operations model, an asset maintenance planning model, a personnel scheduling model, or a financial model.

A method, comprising: implementing an asset optimizer module with the computing device, wherein the implementing asset optimizer module interconnects the plurality of digital twins for optimization over a time horizon, wherein the asset optimizer module selects the plurality of digital twins for optimization based on at least one of accuracy, time coverage, computation time, or contribution to variance; executing, with a computing device, an asset optimizer module, wherein the asset optimizer module optimizes one or more parameters of one or more of the plurality of digital twins to obtain one or more key process indicators for one or more asset systems of the asset; implementing a system optimizer module with a computing device, wherein the system optimizer module receives one or more optimization parameters and one or more business models corresponding to one or more business operations; executing, with a computing device, a system optimizer module, wherein the system optimizer module generates one or more operating protocols for one or more business models; and outputting, with the computing device, the one or more operating protocols to the user for implementation in the real-world asset system.

The method of any preceding clause, further comprising: outputting, with a computing device, an indication of one or more optimization statuses, wherein the indication defines an optimization level of at least one of the plurality of digital twins or the one or more business models.

The method of any preceding clause, further comprising: feeding back the one or more operating protocols into one or more of the plurality of digital twins such that the ECU executes another instance of at least one of the asset optimizer module or the system optimizer module to generate an updated set of one or more operating protocols for implementation in the real-world asset system.

The method of any preceding item, wherein the system optimizer module is configured to optimize each of the one or more business models based on interactions between the one or more business models and the one or more optimization parameters.

The method of any preceding clause, further comprising: one or more of the plurality of digital twins having a calculation time less than or equal to the time range are selected in the simulated future period according to the limit of the calculation duration.

The method of any preceding clause, further comprising: one or more of the plurality of digital twins having a computation time less than or equal to the time horizon of the simulated future period are selected while optimizing the operational predicted KPI target according to the desired predicted variability reduction rate per unit of computation time.

The method of any preceding item, wherein the asset is an aircraft.

The method of any preceding item, wherein one or more of the plurality of digital twins comprises one or more first sub-level digital twins corresponding to one or more asset subsystems of one or more asset systems.

The method of any preceding claim, wherein the one or more first sub-level digital twins comprise one or more component level digital twins corresponding to one or more components of one or more asset subsystems.

The method of any preceding item, wherein one or more business models comprise at least one of: a fuel management model, a flight operations model, an asset maintenance planning model, a personnel scheduling model, or a financial model.

A non-transitory machine-readable medium containing a set of instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising: implementing an asset optimizer module with the computing device, wherein the implementing asset optimizer module interconnects the plurality of digital twins for optimization over a time horizon, wherein the asset optimizer module selects the plurality of digital twins for optimization based on at least one of accuracy, time coverage, computation time, or contribution to variance; executing, with a computing device, an asset optimizer module, wherein the asset optimizer module optimizes one or more parameters of one or more of the plurality of digital twins to obtain one or more key process indicators for one or more asset systems of the asset; implementing a system optimizer module with a computing device, wherein the system optimizer module receives one or more optimization parameters and one or more business models corresponding to one or more business operations; executing, with a computing device, a system optimizer module, wherein the system optimizer module generates one or more operating protocols for one or more business models; and outputting, with the computing device, the one or more operating protocols to the user for implementation in the real-world asset system.

The non-transitory machine readable medium of any preceding item, wherein a set of instructions, when executed by one or more processors, further cause the one or more processors to perform operations comprising: outputting, with a computing device, an indication of one or more optimization statuses, wherein the indication defines an optimization level of at least one of the plurality of digital twins or the one or more business models.

The non-transitory machine readable medium of any preceding item, wherein a set of instructions, when executed by one or more processors, further cause the one or more processors to perform operations comprising: feeding back the one or more operating protocols into one or more of the plurality of digital twins such that the ECU executes another instance of at least one of the asset optimizer module or the system optimizer module to generate an updated set of one or more operating protocols for implementation in the real-world asset system.

The non-transitory machine-readable medium of any preceding clause, wherein: one or more of the plurality of digital twins comprises one or more first sub-level digital twins corresponding to one or more asset subsystems of one or more asset systems; and the one or more first sub-level digital twins comprise one or more component-level digital twins corresponding to one or more components of the one or more asset subsystems.

The non-transitory machine readable medium of any preceding item, wherein a set of instructions, when executed by one or more processors, further cause the one or more processors to perform operations comprising: one or more of the plurality of digital twins having a calculation time less than or equal to the time range are selected in the simulated future period according to the limit of the calculation duration.

The non-transitory machine readable medium of any preceding item, wherein a set of instructions, when executed by one or more processors, further cause the one or more processors to perform operations comprising: one or more of the plurality of digital twins having a computation time less than or equal to the time horizon of the simulated future period are selected while optimizing the operational predicted KPI target according to the desired predicted variability reduction rate per unit of computation time.