阅读说明：本技术 测试方法、装置、电子设备及计算机可读存储介质 (Test method, test device, electronic equipment and computer readable storage medium ) 是由 樊翔 秦尧 张亮亮 姚望 桂皓 陈立 黄建涛 蔡笑驰 刘梦园 汤瑾璟 顾一清 于 2020-07-29 设计创作，主要内容包括：本发明提供了一种测试方法、装置、电子设备及计算机可读存储介质,包括：获取初始测试参数；其中,初始测试参数包括虚拟环境参数、虚拟船舶参数、实际环境参数和实际船舶参数；基于初始测试参数对预先建立的综合决策模型进行测试,得到测试结果；其中,综合决策模型为基于环境参数和船舶参数进行船舶航行决策的算法模型。本发明可以提供更加智能更加完善的船舶航行决策测试方法,提升船舶综合决策的准确度。(The invention provides a test method, a test device, electronic equipment and a computer readable storage medium, comprising the following steps: acquiring initial test parameters; the initial test parameters comprise virtual environment parameters, virtual ship parameters, actual environment parameters and actual ship parameters; testing a pre-established comprehensive decision model based on the initial test parameters to obtain a test result; the comprehensive decision model is an algorithm model for making ship navigation decision based on the environmental parameters and the ship parameters. The invention can provide a more intelligent and more perfect ship navigation decision test method and improve the accuracy of the comprehensive decision of the ship.)

1. A method of testing, comprising:

acquiring initial test parameters; the initial test parameters comprise virtual environment parameters, virtual ship parameters, actual environment parameters and actual ship parameters;

testing a pre-established comprehensive decision model based on the initial test parameters to obtain a test result; the comprehensive decision model is an algorithm model for making ship navigation decision based on environmental parameters and ship parameters.

2. The method of claim 1, wherein the step of obtaining initial test parameters comprises:

acquiring virtual environment parameters and virtual ship parameters based on a pre-established test environment model; wherein the test environment model comprises: the system comprises a marine environment simulation model, a real sea scene digital reconstruction model and a shipborne equipment simulation model.

3. The method of claim 1, wherein the step of testing a pre-established integrated decision model based on the initial test parameters to obtain a test result comprises:

testing a pre-established comprehensive decision model based on the virtual environment parameters and the virtual ship parameters to obtain a first test result;

and/or testing the comprehensive decision model based on the actual environment parameters and the virtual ship parameters to obtain a second test result;

and/or testing the comprehensive decision model based on the virtual environment parameters and the actual ship parameters to obtain a third test result;

and/or testing the comprehensive decision model based on the actual environment parameters and the actual ship parameters to obtain a fourth test result.

4. The method of claim 1, wherein the initial test parameters further comprise a navigation task comprising: the coordinates of a starting point of the flight path, the coordinates of a terminal point of the flight path and the navigation duration;

the step of testing the pre-established comprehensive decision model based on the initial test parameters to obtain a test result comprises the following steps:

executing test operation based on the initial test parameters and a pre-established comprehensive decision model to obtain navigation information of the ship; the navigation information at least comprises navigation speed, ship attitude and course;

repeating the test operation based on the sailing information until the ship completes the sailing task;

determining a test result according to the comprehensive index corresponding to the navigation information and the comprehensive index corresponding to the navigation task; the comprehensive index is a parameter for representing the navigation decision performance of the ship.

5. The method of claim 4, wherein the testing operation comprises:

determining a decision instruction based on the initial test parameters and a pre-established comprehensive decision model;

determining navigation information of a ship based on the decision instruction, the shipborne equipment simulation model and a pre-established numerical pool model, and sending the navigation information to the comprehensive decision model for storage; the numerical pool model is used for simulating the movement track and the posture of the ship.

6. The method according to claim 4, wherein the step of determining the test result according to the comprehensive index corresponding to the navigation information and the comprehensive index corresponding to the navigation task comprises:

acquiring a plurality of preset navigation information corresponding to the navigation task;

respectively determining a comprehensive index corresponding to the navigation information and a comprehensive index corresponding to the preset navigation information according to a comprehensive index calculation module in the comprehensive decision-making model;

and when the comprehensive indexes corresponding to the preset navigation information are all smaller than the comprehensive indexes corresponding to the navigation information, determining that the test result is that the comprehensive decision model is effective.

7. The method of claim 1, further comprising:

and optimizing the comprehensive decision-making model according to the test result.

8. A test apparatus, comprising:

the parameter acquisition module is used for acquiring initial test parameters; the initial test parameters comprise virtual environment parameters, virtual ship parameters, actual environment parameters and actual ship parameters;

the testing module is used for testing a pre-established comprehensive decision model based on the initial testing parameters to obtain a testing result; the comprehensive decision model is an algorithm model for decision making based on environmental parameters and ship parameters.

9. An electronic device comprising a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to perform the steps of the method of any one of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of the claims 1 to 7.

Technical Field

The invention relates to the technical field of intelligent decision making of ships, in particular to a testing method, a testing device, electronic equipment and a computer-readable storage medium.

Background

The comprehensive decision of the ship refers to the optimal operation instruction made by the computer on the basis of sensing the surrounding environment to comprehensively synthesize the performance of the ship body and the performance of each device on the ship base and comprehensively meet the requirements of the safety, the economy and the healthy operation and maintenance of the device. The accuracy of the ship comprehensive decision is improved by testing the intelligent ship comprehensive decision function, but no existing test method exists for the intelligent ship comprehensive decision function at present, and the comprehensive decision function cannot be tested.

Disclosure of Invention

In view of the above, the present invention provides a testing method, a testing apparatus, an electronic device and a computer-readable storage medium, so as to provide a more intelligent and more complete ship navigation decision testing method and improve the accuracy of a comprehensive decision of a ship.

In a first aspect, an embodiment of the present invention provides a testing method, including: acquiring initial test parameters; the initial test parameters comprise virtual environment parameters, virtual ship parameters, actual environment parameters and actual ship parameters; testing a pre-established comprehensive decision model based on the initial test parameters to obtain a test result; the comprehensive decision model is an algorithm model for making ship navigation decision based on the environmental parameters and the ship parameters.

In one embodiment, the step of obtaining initial test parameters comprises: acquiring virtual environment parameters and virtual ship parameters based on a pre-established test environment model; wherein, the test environment model includes: the system comprises a marine environment simulation model, a real sea scene digital reconstruction model and a shipborne equipment simulation model.

In one embodiment, the step of testing the pre-established comprehensive decision model based on the initial test parameters to obtain the test result includes: testing a pre-established comprehensive decision model based on the virtual environment parameters and the virtual ship parameters to obtain a first test result; and/or testing the comprehensive decision model based on the actual environment parameters and the virtual ship parameters to obtain a second test result; and/or testing the comprehensive decision model based on the virtual environment parameters and the actual ship parameters to obtain a third test result; and/or testing the comprehensive decision model based on the actual environment parameters and the actual ship parameters to obtain a fourth test result.

In one embodiment, the initial test parameters further include a navigation mission comprising: the coordinates of a starting point of the flight path, the coordinates of a terminal point of the flight path and the navigation duration; the method comprises the following steps of testing a pre-established comprehensive decision model based on initial test parameters to obtain a test result, wherein the steps comprise: executing test operation based on the initial test parameters and a pre-established comprehensive decision model to obtain navigation information of the ship; the navigation information at least comprises navigation speed, ship attitude and course; repeating the test operation based on the navigation information until the ship completes the navigation task; determining a test result according to the comprehensive index corresponding to the navigation information and the comprehensive index corresponding to the navigation task; the comprehensive index is a parameter for representing the navigation decision performance of the ship.

In one embodiment, the testing operation includes: determining a decision instruction based on the initial test parameters and a pre-established comprehensive decision model; determining navigation information of the ship based on the decision instruction, the shipborne equipment simulation model and a pre-established numerical pool model, and sending the navigation information to the comprehensive decision model for storage; the numerical pool model is used for simulating the movement track and the posture of the ship.

In one embodiment, the step of determining the test result according to the comprehensive index corresponding to the navigation information and the comprehensive index corresponding to the navigation task includes: acquiring a plurality of preset navigation information corresponding to the navigation task; respectively determining a comprehensive index corresponding to the navigation information and a comprehensive index corresponding to the preset navigation information according to a comprehensive index calculation module in the comprehensive decision model; and when the comprehensive indexes corresponding to the preset navigation information are all smaller than the comprehensive indexes corresponding to the navigation information, determining that the test result is that the comprehensive decision model is effective.

In one embodiment, the aforementioned method further comprises: and optimizing the comprehensive decision model according to the test result.

In a second aspect, an embodiment of the present invention provides a testing apparatus, including: the parameter acquisition module is used for acquiring initial test parameters; the initial test parameters comprise virtual environment parameters, virtual ship parameters, actual environment parameters and actual ship parameters; the testing module is used for testing the pre-established comprehensive decision model based on the initial testing parameters to obtain a testing result; the comprehensive decision model is an algorithm model for making ship navigation decision based on the environmental parameters and the ship parameters.

In a third aspect, an embodiment of the present invention provides an electronic device, which includes a processor and a memory, where the memory stores computer-executable instructions capable of being executed by the processor, and the processor executes the computer-executable instructions to implement the steps of any one of the methods provided in the first aspect.

In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of any one of the methods provided in the first aspect.

The testing method, the testing device, the electronic equipment and the computer readable storage medium provided by the embodiment of the invention can acquire initial testing parameters (virtual environment parameters, virtual ship parameters, actual environment parameters and actual ship parameters); and then testing a pre-established comprehensive decision model (the comprehensive decision model is an algorithm model for making ship navigation decisions based on the environmental parameters and the ship parameters) based on the initial test parameters to obtain a test result. The method can test the comprehensive decision-making model by combining virtual and real scenes of the environment and the ship based on the virtual environment parameters, the virtual ship parameters, the actual environment parameters and the actual ship parameters, so that a more intelligent and more complete ship navigation decision-making test method is provided, a more comprehensive ship application scene is considered, and the accuracy of comprehensive decision-making is improved.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.

FIG. 1 is a flow chart of a testing method according to an embodiment of the present invention;

FIG. 2 is a flow chart of another testing method provided by the embodiment of the invention;

fig. 3 is a schematic structural diagram of a testing apparatus according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

At present, no existing test method exists for the comprehensive decision function of the intelligent ship, and the comprehensive decision function cannot be tested. Based on this, the test method, the test device, the electronic device and the computer readable storage medium provided by the embodiment of the invention can provide a more intelligent and more complete ship navigation decision test method, and improve the accuracy of a comprehensive decision of a ship.

To facilitate understanding of the present embodiment, first, a detailed description is given of a testing method disclosed in the present embodiment, referring to a flowchart of a testing method shown in fig. 1, where the method may be executed by an electronic device and mainly includes the following steps S102 to S104:

step S102: initial test parameters are obtained.

The initial test parameters comprise virtual environment parameters, virtual ship parameters, actual environment parameters and actual ship parameters. The environmental parameters may include: wave current (especially wave current in severe weather such as typhoon and cold tide), sea fixed targets such as landform and buoy, sea moving targets such as ship, shore buildings such as wharf spur dike, etc.; the ship parameters can comprise the ship parameters and other ship parameters, and the ship parameters comprise: ship type, size, draft, onboard equipment parameters (such as turbine parameters, steering engine parameters, etc.), etc.; other vessel parameters include: ship type, size, draft, other ship navigation parameters (such as speed, heading, drift angle, steering angle, etc.), etc. In one embodiment, the virtual environment parameters and the virtual ship parameters may be obtained according to a simulation model, and the actual environment parameters and the actual ship parameters may be obtained by measurement with a measuring instrument, or the actual environment parameters and the actual ship parameters may be obtained through information and a ship design manual recorded by a maritime office, a channel office, a port office, and the like.

Step S104: and testing the pre-established comprehensive decision model based on the initial test parameters to obtain a test result.

The comprehensive decision model is an algorithm model for making ship navigation decision based on the environmental parameters and the ship parameters. In one embodiment, the comprehensive decision model includes a comprehensive index calculation module, an index optimization calculation module, a decision instruction generation module, and the like, and specifically, a ship navigation decision instruction may be generated by the decision instruction generation module in the comprehensive decision model according to the initial test parameter, then a comprehensive index corresponding to the generated ship navigation decision instruction is calculated by the comprehensive index calculation module and the index optimization calculation module, and a test result of the comprehensive decision performance of the ship is obtained based on the comprehensive index.

The test method provided by the embodiment of the invention can test the comprehensive decision-making model by combining virtual environment parameters, virtual ship parameters, actual environment parameters and actual ship parameters according to the environment and the virtual and real scenes of the ship, thereby providing a more intelligent and more complete ship navigation decision-making test method, considering more comprehensive ship application scenes and improving the accuracy of comprehensive decision-making.

For convenience of understanding, the embodiment of the present invention provides a specific example of obtaining the initial test parameters, that is, for the step S102, the following steps may be implemented: and acquiring virtual environment parameters and virtual ship parameters based on a pre-established test environment model. Wherein, the test environment model includes: the system comprises a marine environment simulation model, a real sea scene digital reconstruction model and a shipborne equipment simulation model.

In one embodiment, the marine environment simulation model may use Delft3D (3-dimensional hydrodynamic-water quality model system), SWAN (simulation Waves sea wave numerical simulation), AERMOD (atmospheric prediction software system), WAVEWATCH III (third generation sea wave numerical prediction mode), and other software. The marine environment simulation model can be used for accurately simulating parameters of wind, wave, flow, water temperature, salinity and the like influencing the safety of the ship, particularly parameters under extreme weather conditions such as typhoon, cold tide and the like, and providing input parameters (namely initial test parameters) for the comprehensive decision model.

The digital reconstruction model of the real sea area scene comprises Automatic identification system (Automatic identification system) data of a ship, electronic chart data and the like, and can be provided by a maritime office. The ship AIS data contains information such as ship type, ship name, ship number, estimated arrival time of the ship, ship starting time, ship berthing port information, ship position (longitude and latitude), ship maximum draft, ship sailing speed, transit area and the like. The real sea-area scene digital reconstruction model may be used to provide input parameters for the integrated decision model.

The ship-borne equipment simulation model comprises a turbine simulation model and a steering engine simulation model and can be provided by equipment manufacturers. The simulation of the shipborne equipment can be used for simulating the states of equipment such as a main engine, a steering engine and the like in the navigation operation process of the ship, such as the rotating speed of the main engine, the pressure of an air cylinder, the temperature and the base of an oil tank, the power of an auxiliary engine, the transmission efficiency of the steering engine, the stress of transmission equipment and the like, setting reasonable boundary conditions for the ship operation instruction in a numerical pool, and providing input parameters for a comprehensive decision model.

In order to verify the accuracy of the ship decision model, in this embodiment, the comprehensive decision model may be tested in a manner of combining virtual and real scenarios, such as testing a full virtual environment (i.e., a virtual environment and a virtual ship), testing a real scenario (i.e., a real environment) and a virtual ship, testing a virtual scenario and a real ship in combination, and testing a real scenario and a real ship in combination. Based on this, the step of obtaining the test result by testing the pre-established comprehensive decision model based on the initial test parameters, that is, the step S104 may be implemented according to the following steps (1) to (4):

step (1): and testing the pre-established comprehensive decision model based on the virtual environment parameters and the virtual ship parameters to obtain a first test result.

Step (2): and testing the comprehensive decision model based on the actual environment parameters and the virtual ship parameters to obtain a second test result.

And (3): and testing the comprehensive decision model based on the virtual environment parameters and the actual ship parameters to obtain a third test result.

And (4): and testing the comprehensive decision model based on the actual environment parameters and the actual ship parameters to obtain a fourth test result.

It can be understood that there is no limitation on the execution sequence of the steps (1) to (4), and in practical applications, one or more of the four manners may be arbitrarily selected for testing according to actual requirements, which is not limited herein.

Further, the initial test parameters further include a navigation task, and the navigation task includes: the embodiment of the invention also provides a specific implementation mode for testing a pre-established comprehensive decision model based on initial test parameters to obtain a test result, which mainly comprises the following steps 1 to 3:

step 1: and executing test operation based on the initial test parameters and a pre-established comprehensive decision model to obtain the navigation information of the ship.

In one embodiment, the initial test parameters may be input into a pre-established comprehensive decision model according to actual test requirements, and then a test operation is performed according to an output result of the comprehensive decision model to obtain navigation information of the ship, where the navigation information at least includes a speed, a posture and a heading of the ship. Taking a full-virtual environment test as an example, a navigation task, virtual environment parameters and virtual ship parameters can be input into a comprehensive decision model, the virtual environment parameters comprise marine environment information such as wind, wave and current acquired through a marine environment simulation model, electronic chart information and other ship information acquired through a real sea area scene digital reconstruction model, and the virtual ship parameters comprise ship-borne equipment parameters and ship parameters acquired through a ship-borne equipment simulation model; and then, executing test operation according to the output result of the comprehensive decision model to obtain the navigation information of the ship. It can be understood that the principles of the other three test modes are the same as the methods and principles of the full virtual environment test described above, and are not described herein again.

Further, the above test operation mainly includes the following steps 1.1 to 1.2:

step 1.1: and determining a decision instruction based on the initial test parameters and a pre-established comprehensive decision model.

Step 1.2: determining the navigation information of the ship based on the decision instruction, the shipborne equipment simulation model and the pre-established numerical pool model, and sending the navigation information to the comprehensive decision model for storage.

The numerical pool model is used for simulating the movement track and the attitude of the ship, CFD calculation software such as Fluent and STAR CCM + can be adopted, ship control software such as Mooring and Seaman can be adopted, and a self-compiled numerical simulation model can be adopted. The numerical pool model can be used for simulating the motion trail and posture of the ship after the ship receives the intelligent decision instruction, and comprises the following steps: speed, heading, draft, trim, heel, rudder angle, propeller thrust, etc. The ship-borne equipment simulation model comprises a turbine simulation model and a steering engine simulation model.

In one embodiment, the integrated decision model may output decision instructions to the turbine simulation model, the steering engine simulation model, and the digital pool model; the turbine simulation model and the steering engine simulation model output parameters such as propeller rotating speed, rudder angle and the like to the numerical pool model according to the received decision instruction, and meanwhile, state parameters of the turbine and the steering engine are fed back to the comprehensive decision model; the numerical value pool model calculates navigation information of the ship according to parameters such as the received decision instruction, the propeller rotating speed and the rudder angle, such as: the navigation speed, the ship attitude, the course, the navigation track, the motion response, the stress and the like, and the obtained navigation information is fed back to the comprehensive decision-making model for recording and storing.

Step 2: and repeating the test operation based on the navigation information until the ship finishes the navigation task.

In one embodiment, after the first navigation information is obtained, the integrated decision-making model may make a decision-making instruction again according to the current marine environment information, the electronic chart information, the navigation information of the ship (calculation result of the numerical pool model), the equipment information onboard the ship, the navigation state of the ship, the information of other ships, the navigation state information of other ships, and the like, and repeat the above-described test operation until the ship completes the navigation task. Specifically, the updated calculation times can be set according to the calculation capability of the computer, and the navigation information of the ship obtained by each calculation, namely the speed, the navigation attitude and the course of the ship, is recorded.

And step 3: and determining a test result according to the comprehensive index corresponding to the navigation information and the comprehensive index corresponding to the navigation task.

The comprehensive index is a parameter for representing the navigation decision performance of the ship. In one embodiment, a plurality of preset navigation information corresponding to a navigation task may be obtained first; then respectively determining a comprehensive index corresponding to the navigation information and a comprehensive index corresponding to the preset navigation information according to a comprehensive index calculation module in the comprehensive decision model; and when the comprehensive indexes corresponding to the preset navigation information are all smaller than the comprehensive indexes corresponding to the navigation information, determining that the test result is that the comprehensive decision model is effective.

Specifically, because the navigational speed and the navigational attitude of the ship both have the maximum value and the minimum value, a plurality of preset navigational information corresponding to the navigational task can be generated by taking the navigational speed and the navigational attitude both have the maximum value and the minimum value as constraint conditions; then, the navigation information and the preset navigation information are respectively input into a comprehensive index calculation module in a comprehensive decision model to obtain a comprehensive index corresponding to the navigation information and a comprehensive index corresponding to the preset navigation information, when the comprehensive indexes corresponding to the preset navigation information are all smaller than the comprehensive index corresponding to the navigation information, the comprehensive decision model is determined to be effective, namely when the comprehensive indexes corresponding to the navigation tasks are all smaller than the comprehensive index corresponding to the navigation information calculated in the step 1 and the step 2, the comprehensive decision model is determined to play an application function, namely when the comprehensive index formed when the ship navigates according to the control instruction generated by the comprehensive decision model is superior to the comprehensive index corresponding to the ship navigates according to any other control instruction, the test result is determined to be effective, and particularly, the ship navigates according to the control instruction generated by the comprehensive decision model, namely, the ship navigates according to the navigation instruction pair determined by the comprehensive decision model The ship navigates according to the navigation information, and the ship navigates according to other control instructions, namely, the ship navigates according to the preset navigation information corresponding to the navigation task.

Further, the test method provided by the embodiment of the invention further comprises the following steps: and optimizing the comprehensive decision model according to the test result. Specifically, the comprehensive decision model may be optimized and upgraded according to the full virtual environment test result obtained in the foregoing steps 1 to 3, the test result of combining the real scene with the virtual ship, the test result of combining the virtual scene with the actual ship, and the test result of combining the real scene with the actual ship.

In order to verify the accuracy of the comprehensive decision model in an ideal state, taking a full virtual environment test as an example, the embodiment of the present invention further provides another test method, which is shown in a flowchart of another test method shown in fig. 2, and mainly includes the following steps S202 to S212:

step S202: and inputting the obtained initial test parameters into the comprehensive decision-making model.

In one embodiment, the initial data parameters include virtual environment parameters and virtual ship parameters, and may be obtained through numerical simulation, that is, through a pre-established environment test model. Specifically, the initial test parameters may include: sea environment parameters such as wind, wave and current, electronic chart information, ship parameters, ship-mounted equipment parameter import of the ship, ship information, ship navigation parameters, navigation tasks and the like. The parameters can be selected from various options, such as marine environment parameters, low sea condition scenes favorable for ship navigation, typhoon cold tides and other extreme sea condition fields; the electronic chart can be selected from open water areas, port water areas and the like; the ship parameters comprise ship type, size, draught and the like, and can be selected according to different ship types; the ship-borne equipment parameters of the ship comprise turbine parameters, steering engine parameters and the like, and the ship-borne equipment cannot change after being installed on the ship, so that the ship-borne equipment parameters can be automatically imported after the ship-borne equipment parameters are imported; the ship information mainly comprises: the ship type, the size and the draught can be randomly selected within a reasonable range; the navigation parameters of other ships comprise: the navigation speed, the course, the drift angle, the steering angle and the like can be randomly selected in a reasonable range according to the information of other ships; the navigation tasks include: the starting point coordinate, the ending point coordinate, the navigation duration and the like of the air route can also be randomly selected within a reasonable range.

Step S204: and the comprehensive decision algorithm model makes decision instructions according to the input initial test parameters and outputs the decision instructions to the turbine simulation model, the steering engine simulation model and the numerical pool model.

In one embodiment, the decision instruction may include a speed command, a heading command, and a gesture command, and the integrated decision model (integrated decision algorithm model) may output the speed command to the turbine simulation model (turbine simulator), the heading command to the steering engine simulation model (steering engine simulator), and the gesture command to the numerical pool model.

Step S206: the turbine simulation model and the steering engine simulation model respectively output a rotating speed command and a steering angle command to the numerical pool model, and the turbine state parameters and the steering engine state parameters are fed back to the comprehensive decision model.

Specifically, the turbine simulation model can output the rotating speed of the propeller to the numerical pool model, and the steering engine simulation model can output parameters such as a rudder angle to the numerical pool model.

Step S208: and the numerical pool model determines the navigation information of the ship according to the received rotating speed command, rudder angle command and attitude command, and feeds the navigation information back to the comprehensive decision model for storage and recording. Specifically, the navigation information of the ship includes: navigational speed, trajectory, motion response, force, etc.

Step S210: and the comprehensive decision-making model makes a decision-making instruction according to the received navigation information and the initial test parameters, and returns to the step S206.

In an embodiment, the integrated decision model may make a decision again according to the current marine environment information, the electronic chart information, the navigation information (calculation result of the numerical pool model) of the ship, the onboard equipment information of the ship, the navigation state of the ship, the information of other ships, the navigation state information of other ships, and the like, and repeat the above steps S206 to S208 until the ship completes the navigation task. Specifically, the updated calculation times can be set according to the calculation capability of the computer, and the navigation information of the ship obtained by each calculation, namely the speed, the navigation attitude and the course of the ship, is recorded.

Step S212: and testing the comprehensive decision model according to the navigation information.

In one embodiment, M sets of voyage missions may be randomly generated within a reasonable range, keeping the initial test parameters in step S202 the same. Because the navigational speed and the attitude of the ship have the maximum value and the minimum value, the reasonable range can be determined according to the navigational speed and the maximum value and the minimum value of the attitude of the ship, and the navigational speed and the maximum value and the minimum value of the attitude of the ship can be searched from a loading manual of the ship. In addition, the generated voyage task should also satisfy that the planned voyage time of the whole voyage is the same as the target voyage time. Further, navigation tasks are generated with simple random combinations under these constraints, such as: specific task parameters such as navigational speed, course, attitude and the like.

And (4) bringing the generated navigation tasks into a comprehensive index calculation module in the comprehensive decision model to calculate comprehensive indexes, and meanwhile, guiding the final navigation tasks (namely navigation information) stored in the step (S208) into the comprehensive index calculation module to calculate the comprehensive indexes. The calculation of the comprehensive index is a part of a comprehensive decision algorithm model, and is embedded and established in the comprehensive decision model. And when the comprehensive indexes of the M groups of navigation tasks are all smaller than the comprehensive index of the final navigation task stored in the step S208, the comprehensive decision-making model is considered to play due functions. Wherein, the determination process of the comprehensive index comprises the following steps: the speed, the attitude and the course are taken as parameters required for calculating the comprehensive index, and the comprehensive index is calculated by inputting the speed, the attitude and the course to the comprehensive index calculation module.

Further, in order to test the capability of the comprehensive decision-making model to adapt to a real scene and verify the reliability of the comprehensive decision-making model, the real scene and the virtual ship can be combined for testing, and specifically, sea environment parameters such as stormy waves and currents, topographic information, other ship information and other ship navigation parameters are information under the real scene, wherein the sea environment parameters can be measured by a conventional measuring instrument and can also be obtained from a maritime office; the topographic information can be provided by units such as a maritime bureau, a channel bureau, a port bureau and the like; the information of other ships is provided by AIS data, and the navigation parameters of other ships can be measured by conventional equipment and can also be obtained from a maritime office. The setting of the own ship parameters, the own ship onboard equipment parameters, the own ship navigation parameters and the like is the same as in the above step S202. The subsequent testing process and principle are also the same as those of the above steps S204 to S212, and are not described herein again.

Further, in order to test whether the decision made by the comprehensive decision model when applied to the real ship is still accurate, the virtual scene and the real ship can be combined for testing, and specifically, the ship information and the ship-mounted equipment information of the ship are actually determined quantities and can be determined according to the ship of the test ship; the ship route parameter and the equipment state parameter are actual measured values of the equipment; the sea environment parameters such as wind, wave and current, the terrain information, the information of other ships and the navigation parameters of other ships are virtual quantities, which can be set according to different scene requirements, and the setting method is the same as the method in the step S202. The subsequent testing process and principle are also the same as those of the above steps S204 to S212, and are not described herein again.

Further, in order to test the reliability and accuracy of the comprehensive decision-making model applied to all real scenes, the real scenes can be combined with the actual ship for testing, and specifically, marine environment parameters such as ship information, ship-mounted equipment information of the ship, storm flow and the like, terrain information, other ship information and other ship navigation parameters are all actual measurement values. The testing process and principle are also the same as those of the above steps S204 to S212, and are not described herein again.

The testing method provided by the embodiment of the invention can test the comprehensive decision-making model by combining virtual and real scenes of the environment and the ship based on the virtual environment parameters, the virtual ship parameters, the actual environment parameters and the actual ship parameters, thereby providing a feasible intelligent ship testing scheme, testing and evaluating the intelligent decision-making function of the intelligent ship on the premise of controllable risk and cost, and improving the accuracy of comprehensive decision-making.

For the test method provided by the foregoing embodiment, an embodiment of the present invention further provides a test apparatus, referring to a schematic structural diagram of a test apparatus shown in fig. 3, where the test apparatus may include the following components:

a parameter obtaining module 301, configured to obtain an initial test parameter; the initial test parameters comprise virtual environment parameters, virtual ship parameters, actual environment parameters and actual ship parameters.

The testing module 302 is configured to test a pre-established comprehensive decision model based on the initial testing parameters to obtain a testing result; the comprehensive decision model is an algorithm model for making ship navigation decision based on the environmental parameters and the ship parameters.

The testing device provided by the embodiment of the invention can test the comprehensive decision-making model by combining virtual environment parameters, virtual ship parameters, actual environment parameters and actual ship parameters according to the environment and the virtual and real scenes of the ship, thereby providing a more intelligent and more complete ship navigation decision-making testing method, considering more comprehensive ship application scenes and improving the accuracy of comprehensive decision-making.

In an embodiment, the parameter obtaining module 301 is further configured to obtain a virtual environment parameter and a virtual ship parameter based on a pre-established test environment model; wherein, the test environment model includes: the system comprises a marine environment simulation model, a real sea scene digital reconstruction model and a shipborne equipment simulation model.

In an embodiment, the testing module 302 is further configured to test a pre-established comprehensive decision model based on a virtual environment parameter and a virtual ship parameter to obtain a first testing result; and/or testing the comprehensive decision model based on the actual environment parameters and the virtual ship parameters to obtain a second test result; and/or testing the comprehensive decision model based on the virtual environment parameters and the actual ship parameters to obtain a third test result; and/or testing the comprehensive decision model based on the actual environment parameters and the actual ship parameters to obtain a fourth test result.

In one embodiment, the initial test parameters further include a navigation mission comprising: the coordinates of a starting point of the flight path, the coordinates of a terminal point of the flight path and the navigation duration; the test module 302 is further configured to execute a test operation based on the initial test parameters and a pre-established comprehensive decision model to obtain navigation information of the ship; the navigation information at least comprises navigation speed, ship attitude and course; repeating the test operation based on the navigation information until the ship completes the navigation task; determining a test result according to the comprehensive index corresponding to the navigation information and the comprehensive index corresponding to the navigation task; the comprehensive index is a parameter for representing the navigation decision performance of the ship.

In one embodiment, the test module 302 is further configured to determine a decision instruction based on the initial test parameters and a pre-established comprehensive decision model; determining navigation information of the ship based on the decision instruction, the shipborne equipment simulation model and a pre-established numerical pool model, and sending the navigation information to the comprehensive decision model for storage; the numerical pool model is used for simulating the movement track and the posture of the ship.

In an embodiment, the test module 302 is further configured to obtain a plurality of preset navigation messages corresponding to the navigation task; respectively determining a comprehensive index corresponding to the navigation information and a comprehensive index corresponding to the preset navigation information according to a comprehensive index calculation module in the comprehensive decision model; and when the comprehensive indexes corresponding to the preset navigation information are all smaller than the comprehensive indexes corresponding to the navigation information, determining that the test result is that the comprehensive decision model is effective.

In an embodiment, the apparatus further includes an optimization module configured to optimize the comprehensive decision model according to the test result.

The device provided by the embodiment of the present invention has the same implementation principle and technical effect as the method embodiments, and for the sake of brief description, reference may be made to the corresponding contents in the method embodiments without reference to the device embodiments.

The embodiment of the invention also provides electronic equipment, which specifically comprises a processor and a storage device; the storage means has stored thereon a computer program which, when executed by the processor, performs the method of any of the above embodiments.

Fig. 4 is a schematic structural diagram of an electronic device 100 according to an embodiment of the present invention, where the electronic device 100 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43, wherein the processor 40, the communication interface 43 and the memory 41 are connected through the bus 42; the processor 40 is arranged to execute executable modules, such as computer programs, stored in the memory 41.

The Memory 41 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 43 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, etc. may be used.

The bus 42 may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 4, but that does not indicate only one bus or one type of bus.

The memory 41 is used for storing a program, the processor 40 executes the program after receiving an execution instruction, and the method executed by the apparatus defined by the flow disclosed in any of the foregoing embodiments of the present invention may be applied to the processor 40, or implemented by the processor 40.

The processor 40 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 40. The Processor 40 may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory 41, and the processor 40 reads the information in the memory 41 and completes the steps of the method in combination with the hardware thereof.

The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer readable storage medium storing a program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiment, and specific implementation may refer to the foregoing method embodiment, which is not described herein again.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.