阅读说明：本技术 颗粒捕捉系统处理方法及设备 (Particle capture system processing method and apparatus ) 是由 孙凯信 张海瑞 张博强 于 2021-08-31 设计创作，主要内容包括：本申请提供一种颗粒捕捉系统处理方法及设备。该方法包括：获取当前预警监测周期内车辆运行过程中的基础行驶数据以及车辆的颗粒捕捉系统的系统运行数据；根据基础行驶数据以及系统运行数据,确定当前预警监测周期的累碳特征以及再生特征；根据当前预警监测周期的累碳特征以及再生特征,确定颗粒捕捉系统的运行是否存在异常。本申请的方法,可以在颗粒捕捉系统发生故障之前确定颗粒捕捉系统的运行是否存在异常,避免颗粒捕捉系统发生故障而影响车辆的性能以及颗粒物的排放。(The application provides a particle capture system processing method and device. The method comprises the following steps: acquiring basic running data of a vehicle in the running process and system running data of a particle capture system of the vehicle in a current early warning monitoring period; determining carbon accumulation characteristics and regeneration characteristics of the current early warning monitoring period according to the basic driving data and the system operation data; and determining whether the operation of the particle capture system is abnormal or not according to the accumulated carbon characteristic and the regeneration characteristic of the current early warning monitoring period. The method can determine whether the operation of the particle capture system is abnormal or not before the particle capture system is in failure, and avoids the condition that the performance of a vehicle and the emission of particulate matters are influenced due to the failure of the particle capture system.)

1. A method of processing a particle capture system, comprising:

acquiring basic running data of a vehicle in a running process and system running data of a particle capture system of the vehicle in a current early warning monitoring period;

determining carbon accumulation characteristics and regeneration characteristics of the current early warning monitoring period according to the basic driving data and the system operation data;

and determining whether the operation of the particle capture system is abnormal or not according to the accumulated carbon characteristic and the regeneration characteristic of the current early warning monitoring period.

2. The method according to claim 1, wherein determining the carbon accumulation characteristic and the regeneration characteristic of the current early warning monitoring period according to the basic driving data and the system operation data specifically comprises:

sequencing basic driving data and the system operation data in the current early warning monitoring period according to a data acquisition time sequence;

segmenting the sorted basic driving data and the system operation data according to the cycle period of the particle capture system to obtain segmented sample data;

and extracting the accumulated carbon characteristic and the regeneration characteristic from each section of sample data.

3. The method of claim 2, wherein before segmenting the sorted basic driving data and the system operation data according to the cycle period of the particle capture system to obtain each segmented sample data, the method further comprises:

and acquiring state change information of the state of the particle capture system switched from the engine working mode, and determining the cycle period of the particle capture system according to the state change information.

4. The method of any of claims 1-3, wherein the base travel data includes at least one of vehicle speed, accumulated run time, accumulated run mileage, and engine speed;

the system operational data of the particle capture system includes at least one of a particle capture system carbon load, an exhaust gas flow, a temperature upstream of the particle capture system, and a temperature downstream of the particle capture system.

5. The method of any of claims 1-3, wherein the carbon buildup characteristic comprises at least one of an operating condition index, a running average vehicle speed, a vehicle speed zero ratio, a carbon buildup duration, a total exhaust flow value, and a high engine speed ratio, and the regeneration characteristic comprises at least one of a regeneration duration, a maximum carbon loading window value, a minimum carbon loading window value, an average particle capture system upstream temperature, and an average particle capture system downstream temperature;

wherein, the operation condition index R ═ S_C/S_ZThe ∞ represents a condition coefficient set according to the vehicle speed, S_CRepresents the running mileage of the carbon accumulation process in each cycle period, and S_ZRepresenting the running mileage of each cycle period;

average speed of vehicleThe T is_iRepresenting the length of time that the vehicle has traveled at the ith vehicle speed greater than zero in each cycle periodThe sum of the running time lengths of the vehicle running at the vehicle speed greater than zero in each cycle period is represented, and N represents the number of the vehicle speeds greater than zero in each cycle period;

vehicle speed zero-proportion B ═ T_a/T_ZSaid T is_aRepresenting the duration of time during each cycle when the vehicle speed is zero, T_ZIndicating the duration of each cycle period;

duration of accumulated carbon T_C＝T_SK-T_SJSaid T is_SKIndicates the time, T, at which the regeneration process begins in the current cycle_SJIndicating the time when the regeneration process was ended in the previous cycle period;

total exhaust gas flow L ═ Σ L_tSaid L is_tAn instantaneous value representing the exhaust gas flow rate for each cycle period;

high speed ratio P ═ T of engine_f/T_FSaid T is_fIndicating the length of time that the engine speed exceeds a threshold value in each cycle period, T_FIndicating the length of time the engine is operating in each cycle;

regeneration duration T_S＝T_SH-T_SKSaid T is_SHIndicating the time when the regeneration process is finished in the current cycle period;

maximum carbon loading windowCarbon loading window minimumThe G is_jRepresents the jth carbon loading in the sliding window, said M represents the number of carbon loadings in the sliding window, saidRepresents the sum of the carbon loadings in the sliding window;

temperature mean upstream of particle capture systemSaid C is_{Upper x}Represents the upstream temperature of the X-th particle capture system in each cycle period, wherein X represents the number of the upstream temperatures of the particle capture systems in each cycle period; the above-mentionedRepresenting the sum of the temperatures upstream of the particle capture system during each cycle;

mean downstream temperature of particle capture systemSaid C is_{Lower y}Indicating the temperature downstream of the Y-th particle capture system in each cycle period, wherein Y indicates the number of temperatures downstream of the particle capture system in each cycle period; the above-mentionedRepresenting the sum of the temperatures downstream of the particle capture system during each cycle.

6. The method according to any one of claims 1-3, wherein determining whether there is an abnormality in the operation of the particle capture system based on the carbon buildup characteristic and the regeneration characteristic of the current early warning monitoring period comprises:

performing single classification on the accumulated carbon characteristic and the regeneration characteristic of the current early warning monitoring period by adopting a characteristic single classification model to obtain a single classification result; if the single classification result has abnormal features, determining that the operation of the particle capture system is abnormal; if the single classification result does not have abnormal features, determining that the operation of the particle capture system is not abnormal; the characteristic single classification model is obtained by training the system state of the particle capture system acquired in the normal state of the vehicle;

alternatively, the first and second electrodes may be,

judging whether the accumulated carbon characteristics or the regeneration characteristics exist in a preset abnormal characteristic library; determining that there is an anomaly in operation of the particle capture system if the accumulated carbon feature or the regeneration feature is present in the anomaly feature library; determining that there is no anomaly in operation of the particle capture system if the accumulated carbon characteristic and the regeneration characteristic are not present in the anomaly characteristic library.

7. The method of claim 6, wherein the feature single classification model is obtained by:

acquiring carbon accumulation characteristics and regeneration characteristics within a preset time before the current early warning monitoring period;

judging whether abnormal features exist in the accumulated carbon features and the regeneration features within the preset time length or not;

if no abnormal feature exists, training a feature single classification model used in a previous early warning monitoring period of the current early warning monitoring period by using the accumulated carbon feature and the regeneration feature within the preset time as a training set to obtain the feature single classification model used in the current early warning monitoring period;

if the abnormal features exist and the corresponding fault information exists in the abnormal features, taking a feature single classification model used in a previous early warning monitoring period of the current early warning monitoring period as the feature single classification model used in the current early warning monitoring period;

and if the abnormal features exist and the corresponding fault information does not exist in the abnormal features, rejecting the abnormal features, taking the remaining accumulated carbon features and the regeneration features in the preset duration as a training set, and training a feature list classification model used in a previous early warning monitoring period of the current early warning monitoring period to obtain the feature list classification model used in the current early warning monitoring period.

8. A particle capture system processing device comprising a memory, a processor;

a memory; a memory for storing the processor-executable instructions;

wherein the processor is configured to invoke executable instructions stored in the memory to perform the method of any of claims 1 to 7.

9. A computer-readable storage medium having computer-executable instructions stored therein, which when executed by a processor, are configured to implement the method of any one of claims 1 to 7.

10. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-7.

Technical Field

The present application relates to the field of vehicle technologies, and in particular, to a method and an apparatus for processing a particle capture system.

Background

Conventional vehicles can be broadly classified into two major types, i.e., diesel vehicles and gasoline vehicles. The diesel vehicle is more and more favored by people due to the advantages of low oil consumption, quick acceleration, low price, long service life, high reliability and the like.

A Particulate trap system (DPF), an important component of a Diesel exhaust gas treatment system, is a ceramic Filter installed in the Diesel exhaust gas treatment system, which traps Particulate emissions before they enter the atmosphere. When the accumulated particles in the particle capture system reach a certain value, in order to avoid the performance degradation of the diesel vehicle, the particle capture system needs to remove the accumulated particles through a regeneration process to ensure that the particle capture system can continue to work normally. If the particle capture system fails, it may result in the particle capture system failing the regeneration process or having fewer particles removed by the regeneration process, resulting in excessive accumulation of particles in the particle capture system, which may severely affect the performance of the diesel vehicle and the emission of particulate matter.

However, in the prior art, when the particle capture system is processed, it can only be determined whether the particle capture system is operating normally or has a fault, and it cannot be found that the operation of the particle capture system is abnormal before the fault occurs to perform early warning, so that when the fault of the particle capture system is reported, some adverse effects caused by the abnormal operation of the particle capture system are often generated, thereby affecting the performance of the vehicle and the emission of particulate matters.

Disclosure of Invention

The application provides a particle capture system processing method and device, which are used for solving the problem that the prior art cannot find abnormal operation before the particle capture system breaks down in time.

In one aspect, the present application provides a particle capture system processing method, including:

acquiring basic running data of a vehicle in a running process and system running data of a particle capture system of the vehicle in a current early warning monitoring period;

determining carbon accumulation characteristics and regeneration characteristics of the current early warning monitoring period according to the basic driving data and the system operation data;

and determining whether the operation of the particle capture system is abnormal or not according to the accumulated carbon characteristic and the regeneration characteristic of the current early warning monitoring period.

In one possible design, the determining, according to the basic driving data and the system operation data, a carbon accumulation characteristic and a regeneration characteristic of a current early warning monitoring period specifically includes:

sequencing basic driving data and the system operation data in the current early warning monitoring period according to a data acquisition time sequence;

segmenting the sorted basic driving data and the system operation data according to the cycle period of the particle capture system to obtain segmented sample data;

and extracting the accumulated carbon characteristic and the regeneration characteristic from each section of sample data.

In a possible design, before segmenting the sorted basic driving data and the system operation data according to the cycle period of the particle capture system to obtain sample data of each segment, the method further includes:

and acquiring state change information of the state of the particle capture system switched from the engine working mode, and determining the cycle period of the particle capture system according to the state change information.

In one possible design, the base travel data includes at least one of a vehicle speed, an accumulated operating time, an accumulated operating mileage, and an engine speed;

the system operational data of the particle capture system includes at least one of a particle capture system carbon load, an exhaust gas flow, a temperature upstream of the particle capture system, and a temperature downstream of the particle capture system.

In one possible design, the carbon accumulation characteristic comprises at least one of an operating condition index, a running average vehicle speed, a vehicle speed zero proportion, a carbon accumulation duration, an exhaust gas flow total value and an engine high speed proportion, and the regeneration characteristic comprises at least one of a regeneration duration, a carbon loading window maximum value, a carbon loading window minimum value, a particle capture system upstream temperature average value and a particle capture system downstream temperature average value;

wherein, the operation condition index R ═ S_C/S_ZThe ∞ represents a condition coefficient set according to the vehicle speed, S_CRepresents the running mileage of the carbon accumulation process in each cycle period, and S_ZRepresenting the running mileage of each cycle period;

average speed of vehicleThe T is_iRepresenting the length of time that the vehicle has traveled at the ith vehicle speed greater than zero in each cycle periodThe sum of the running time lengths of the vehicle running at the vehicle speed greater than zero in each cycle period is represented, and N represents the number of the vehicle speeds greater than zero in each cycle period;

vehicle speed zero-proportion B ═ T_a/T_ZSaid T is_aRepresenting the duration of time during each cycle when the vehicle speed is zero, T_zIndicating the duration of each cycle period;

duration of accumulated carbon T_C＝T_SK-T_SJSaid T is_SKIndicates the time, T, at which the regeneration process begins in the current cycle_SJIndicating the time when the regeneration process was ended in the previous cycle period;

total exhaust gas flow L ═ Σ L_tSaid L is_tAn instantaneous value representing the exhaust gas flow rate for each cycle period;

high speed ratio P ═ T of engine_f/T_FSaid T is_fIndicating the length of time that the engine speed exceeds a threshold value in each cycle period, T_FIndicating the length of time the engine is operating in each cycle;

regeneration duration T_S＝Y_SH-T_SKSaid T is_SHIndicating the time when the regeneration process is finished in the current cycle period;

maximum carbon loading windowCarbon loading window minimumThe G is_jRepresents the jth carbon loading in the sliding window, said M represents the number of carbon loadings in the sliding window, saidRepresents the sum of the carbon loadings in the sliding window;

temperature mean upstream of particle capture systemSaid C is_{Upper x}Represents the upstream temperature of the X-th particle capture system in each cycle period, wherein X represents the number of the upstream temperatures of the particle capture systems in each cycle period; the above-mentionedRepresenting the sum of the temperatures upstream of the particle capture system during each cycle;

mean downstream temperature of particle capture systemSaid C is_{Lower y}Indicating the temperature downstream of the Y-th particle capture system in each cycle period, wherein Y indicates the number of temperatures downstream of the particle capture system in each cycle period; the above-mentionedRepresenting the sum of the temperatures downstream of the particle capture system during each cycle.

In one possible design, the determining whether there is an abnormality in the operation of the particle capture system according to the carbon accumulation characteristic and the regeneration characteristic of the current warning monitoring period specifically includes:

performing single classification on the accumulated carbon characteristic and the regeneration characteristic of the current early warning monitoring period by adopting a characteristic single classification model to obtain a single classification result; if the single classification result has abnormal features, determining that the operation of the particle capture system is abnormal; if the single classification result does not have abnormal features, determining that the operation of the particle capture system is not abnormal; the characteristic single classification model is obtained by training the system state of the particle capture system acquired in the normal state of the vehicle;

alternatively, the first and second electrodes may be,

judging whether the accumulated carbon characteristics or the regeneration characteristics exist in a preset abnormal characteristic library; determining that there is an anomaly in operation of the particle capture system if the accumulated carbon feature or the regeneration feature is present in the anomaly feature library; determining that there is no anomaly in operation of the particle capture system if the accumulated carbon characteristic and the regeneration characteristic are not present in the anomaly characteristic library.

In one possible design, the feature single classification model is obtained by:

acquiring carbon accumulation characteristics and regeneration characteristics within a preset time before the current early warning monitoring period;

judging whether abnormal features exist in the accumulated carbon features and the regeneration features within the preset time length or not;

if no abnormal feature exists, training a feature single classification model used in a previous early warning monitoring period of the current early warning monitoring period by using the accumulated carbon feature and the regeneration feature within the preset time as a training set to obtain the feature single classification model used in the current early warning monitoring period;

if the abnormal features exist and the corresponding fault information exists in the abnormal features, taking a feature single classification model used in a previous early warning monitoring period of the current early warning monitoring period as the feature single classification model used in the current early warning monitoring period;

and if the abnormal features exist and the corresponding fault information does not exist in the abnormal features, rejecting the abnormal features, taking the remaining accumulated carbon features and the regeneration features in the preset duration as a training set, and training a feature list classification model used in a previous early warning monitoring period of the current early warning monitoring period to obtain the feature list classification model used in the current early warning monitoring period.

In another aspect, the present application provides a particle capture system processing apparatus comprising: a memory, a processor;

a memory; a memory for storing the processor-executable instructions;

wherein the processor is configured to call executable instructions stored in the memory to perform the above-described method.

In a third aspect, the present application provides a computer-readable storage medium having stored thereon computer-executable instructions for implementing the above-mentioned method when executed by a processor.

In a fourth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the method described above.

According to the particle capture system processing method, the carbon accumulation characteristic and the regeneration characteristic of the current early warning monitoring period can be determined according to basic driving data in the vehicle running process and system running data of the particle capture system of the vehicle in the current early warning monitoring period. And then, determining whether the operation of the particle capture system is abnormal in the current early warning monitoring period according to the carbon accumulation characteristic and the regeneration characteristic. The operation process of particle capture system can be divided into carbon accumulation process and regeneration process, through the regeneration characteristic who acquires the carbon accumulation characteristic of carbon accumulation process and regeneration process respectively, can accurate sign particle capture system's running state, whether the operation of further judging particle capture system through carbon accumulation characteristic and regeneration characteristic in the current early warning monitoring cycle exists unusually, thereby confirm whether particle capture system's operation exists unusually before particle capture system breaks down, when particle capture system's operation exists unusually, can carry out the early warning in order to indicate the user in time to overhaul the vehicle to the user, avoid particle capture system to break down and influence the performance of vehicle and the emission of particulate matter.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.

Fig. 1a is an application scenario diagram provided in an embodiment of the present application;

FIG. 1b is a diagram of an application scenario provided by another embodiment of the present application;

FIG. 2 is a schematic flow chart of a particle capture system processing method according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of a training set determination of a feature classification model according to an embodiment of the present application;

FIG. 4 is a schematic flow chart illustrating a particle capture system processing method according to another embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of a particle capture system processing device according to an embodiment of the present disclosure.

With the above figures, there are shown specific embodiments of the present application, which will be described in more detail below. These drawings and written description are not intended to limit the scope of the inventive concepts in any manner, but rather to illustrate the inventive concepts to those skilled in the art by reference to specific embodiments.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

As shown in fig. 1a, the server 2 obtains various system operation data generated by the particle capture system during the operation of the vehicle 1, and determines whether there is fault data in the system operation data. For example, the vehicle 1 may generate a fault code when a fault occurs, and the fault code may indicate the type of the fault occurred. The server 2 may determine that the particle capture system of the vehicle 1 has failed after acquiring the fault code corresponding to the particle capture system, and send fault information to the vehicle 1, so that the vehicle 1 outputs an alarm signal after receiving the fault information, so that a user can maintain the particle capture system of the vehicle 1 after receiving the alarm signal.

However, when the vehicle outputs an alarm signal to a user after receiving the failure information, the particle capture system of the vehicle has failed, and the particle capture system may have abnormal operation for a while before the failure occurs, so that some adverse effects caused by the abnormal operation and the failure of the particle capture system are often generated at this time, thereby affecting the performance of the vehicle and the emission of particulate matters.

The present application provides a particle capture system processing method, which aims to solve the above technical problems in the prior art. The method can determine whether the operation of the particle capture system is abnormal or not before the particle capture system fails, and when the operation of the particle capture system is abnormal, the method can give an early warning to a user to prompt the user to overhaul the vehicle in time, so that the influence on the performance of the vehicle and the emission of particles caused by the failure of the particle capture system is avoided.

The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.

Fig. 1b is an application scenario diagram according to an embodiment of the present application, where the server 2 obtains basic driving data generated during the operation of the vehicle 1 in the current early warning monitoring period and system operation data of the particle capture system of the vehicle 1, and determines the carbon accumulation feature and the regeneration feature according to the basic driving data and the system operation data. Then, the server 2 judges whether abnormal features exist in the accumulated carbon features and the regeneration features according to a preset feature single classification model, if the abnormal features exist in the single classification result, the operation of the particle capture system is abnormal, and the server 2 sends an abnormal message to the vehicle 1. The vehicle 1 outputs the early warning signal after receiving the abnormal information, so that the user can conveniently overhaul the particle capture system of the vehicle 1 after receiving the early warning signal, and the influence on the performance of the vehicle 1 and the emission of particulate matters caused by the failure of the particle capture system is avoided.

Example one

Fig. 2 is a flowchart of a processing method of a particle capture system according to an embodiment of the present application, an execution subject of the processing method of the particle capture system according to the embodiment of the present application may be a server, or may be a controller of a vehicle, and the embodiment describes the processing method of the particle capture system with the execution subject as the server. As shown in fig. 2, the particle capture system processing method may include the steps of:

s101: and acquiring basic running data of the vehicle in the running process and system running data of a particle capture system of the vehicle in the current early warning monitoring period.

In this embodiment, there are many data generated during the operation of the vehicle and many data generated during the operation of the particle capture system of the vehicle, in this embodiment, the basic driving data and the system operation data related to the abnormal operation of the particle capture system may be obtained, and specific data may be flexibly set by those skilled in the art according to experience, which is not limited herein. In addition, a person skilled in the art can flexibly set the early warning monitoring period as needed, for example, the early warning monitoring period may be one day or one week, which is not limited herein.

In this embodiment, after the basic driving data and the system operation data in the current early warning monitoring period are acquired, null values or abnormal values and the like in the data can be subjected to data cleaning, so that the influence of invalid calculation caused by the null values and accidental errors such as the abnormal values on subsequent characteristic determination is avoided.

In one embodiment, the base travel data includes at least one of vehicle speed, accumulated run time, accumulated mileage, and engine speed; the system operation data of the particle capture system includes at least one of a carbon loading of the particle capture system, an exhaust gas flow, a temperature upstream of the particle capture system, and a temperature downstream of the particle capture system.

In this embodiment, the current operating state of the vehicle can be accurately represented by the basic driving data, and the operating state of the particle capture system in the current early warning monitoring period can be accurately represented by the system operating data, so that the accuracy of feature determination in the subsequent steps according to the basic driving data and the system operating data is improved.

In this embodiment, the carbon loading of the particle capture system refers to the amount of particles accumulated in the particle capture system, and is often referred to simply as carbon loading because of the high carbon content of these particles. The carbon loading of the particle capture system can be calculated by the existing back pressure model of the particle capture system, and the specific calculation method is not described herein. Exhaust gas flow refers to the flow of exhaust gas into the exhaust gas treatment system. The temperature upstream of the particle capture system refers to the temperature at the front end of the particle capture system and the temperature downstream of the particle capture system refers to the temperature at the back end of the particle capture system. Of course, the basic driving data may also include data generated when other vehicles are running, such as engine output torque, engine cycle fuel injection amount, and the like; the system operational data may also include data generated by other particle capture systems operating, such as, but not limited to, particle capture system pressure differentials, etc.

S102: and determining the carbon accumulation characteristic and the regeneration characteristic of the current early warning monitoring period according to the basic driving data and the system operation data.

In this embodiment, the operation process of the particle capture system can be divided into a carbon accumulation process and a regeneration process, the operation emphasis of the particle capture system in the carbon accumulation process and the regeneration process is different, and different features need to be extracted according to different processes. Therefore, the carbon accumulation characteristic of the carbon accumulation process and the regeneration characteristic of the regeneration process can be respectively determined according to the basic driving data and the system operation data, and the operation state of the particle capture system in the current early warning monitoring period can be accurately represented through the carbon accumulation characteristic and the regeneration characteristic.

In one embodiment, the carbon accumulation characteristic comprises at least one of an operating condition index, a running average vehicle speed, a vehicle speed zero proportion, a carbon accumulation duration, an exhaust gas flow total value and an engine high speed proportion, and the regeneration characteristic comprises at least one of a regeneration duration, a carbon loading window maximum value, a carbon loading window minimum value, a particle capture system upstream temperature mean value and a particle capture system downstream temperature mean value.

In the present embodiment, the operation condition index R ═ S_C/S_ZAnd oc represents an operating condition coefficient set according to the vehicle speed, S_CRepresents the running mileage of the carbon accumulation process in each cycle period, S_ZRepresenting the operating range of each cycle. The operating condition coefficient oc is set according to the vehicle speed, and the specific setting mode can be flexibly set by a person skilled in the art. For example, the vehicle speed is less than 40km/h, which is the urban condition; the vehicle speed is more than or equal to 40km/h, and less than or equal to 80km/h is suburban working condition; the vehicle speed is greater than 80km/h, and the high-speed working condition is adopted; the urban working condition coefficient is oc ═ 0; the suburban working condition coefficient oc is 0.6; the high-speed operating condition coefficient oc ═ 1.

Average speed of vehicleT_iIndicating the length of time the vehicle travels at the ith vehicle speed greater than zero in each cycle,represents the sum of the periods during which the vehicle is traveling at a vehicle speed greater than zero for each cycle, and N represents the number of vehicle speeds greater than zero for each cycle.

Vehicle speed zero-proportion B ═ T_a/T_z，T_aIndicating the duration of time during each cycle when the vehicle speed is zero, T_zIndicating the duration of each cycle period.

Duration of accumulated carbon T_C＝T_SK-T_SJ，T_SKIndicates the time, T, at which the regeneration process begins in the current cycle_SJIndicating the time at which the regeneration process was completed in the previous cycle.

Total exhaust gas flow rate L ═ Σ L_t，L_tRepresenting the exhaust gas flow transient for each cycle period.

High speed ratio P ═ T of engine_f/T_F，T_fIndicating the length of time, T, during each cycle that the engine speed exceeds a threshold_FIndicating the length of time the engine is operating in each cycle.

Regeneration duration T_s＝T_SH-T_SK，T_SHIndicates the time when the regeneration process ends in the present cycle.

Maximum carbon loading windowCarbon loading window minimumG_jRepresents the jth carbon loading in the sliding window, M represents the number of carbons loaded in the sliding window,representing the sum of the carbon loadings in the sliding window. The carbon load window refers to the calculation of the sum of the carbon loads in the window by intercepting the carbon loads through a sliding window.

Temperature mean upstream of particle capture systemC_{Upper x}Represents the upstream temperature of the X-th particle capture system in each cycle period, and X represents the number of upstream temperatures of the particle capture system in each cycle period;representing the sum of the temperatures upstream of the particle capture system during each cycle.

Mean downstream temperature of particle capture systemC_{Lower y}Indicating the temperature downstream of the Y-th particle capture system during each cycle, YRepresenting the number of temperatures downstream of the particle capture system in each cycle;representing the sum of the temperatures downstream of the particle capture system during each cycle.

In the embodiment, when the particle capture system is in the carbon accumulation process, particles generated in the driving process of the vehicle are mainly captured, in the process, the influence of basic driving data on the operation state of the particle capture system is large, and the influence of system operation data on the operation state of the particle capture system is small, so that the basic driving data is emphasized when the carbon accumulation characteristic in the carbon accumulation process is extracted. When the particle capture system is in the regeneration process, particles captured in the carbon accumulation process are combusted mainly through the regeneration process, in the process, the influence of system operation data on the operation state of the particle capture system is large, and the influence of basic driving data on the operation state of the particle capture system is small, so that the system operation data is emphasized when the regeneration characteristics in the regeneration process are extracted.

In the embodiment, the running state of the particle capture system in the carbon accumulation process can be accurately represented by carbon accumulation characteristics such as running condition indexes, running average speed, zero vehicle speed ratio, carbon accumulation duration, total exhaust gas flow rate, high engine speed ratio and the like; the running state of the particle capture system in the regeneration process can be accurately represented through regeneration characteristics such as regeneration duration, the maximum value of a carbon loading window, the minimum value of the carbon loading window, the average value of the upstream temperature of the particle capture system and the downstream temperature of the particle capture system, and the accuracy of judgment can be improved when the carbon accumulation characteristic and the regeneration characteristic of the current early warning monitoring period are used for judging whether the running of the particle capture system is abnormal or not in the subsequent steps.

In this embodiment, after the carbon accumulation feature and the regeneration feature are extracted, because the number of features is large and the subsequent calculation amount is large, the extracted features can be subjected to dimensionality reduction, the specific dimensionality reduction can be flexibly set by a person skilled in the art, and the specific dimensionality reduction process can adopt algorithms such as PCA in the prior art, which is not described herein in detail.

S103: and determining whether the operation of the particle capture system is abnormal or not according to the accumulated carbon characteristic and the regeneration characteristic of the current early warning monitoring period.

In this embodiment, when there is the anomaly in the operation of particle capture system, can control the vehicle and output early warning information in order to remind user's particle capture system to take place the anomaly, continue to travel and probably break down to the user overhauls in time, prevents that particle capture system from breaking down and influencing the performance of vehicle and the emission of particulate matter.

In one possible embodiment, the step S103 of determining whether there is an abnormality in the operation of the particle capture system according to the carbon accumulation characteristic and the regeneration characteristic of the current early warning monitoring period may include: judging whether the carbon accumulation characteristics or the regeneration characteristics exist in a preset abnormal characteristic library; if the accumulated carbon characteristics or the regeneration characteristics exist in the abnormal characteristic library, the operation of the particle capture system is abnormal; if the accumulated carbon characteristic and the regeneration characteristic do not exist in the abnormal characteristic library, the operation of the particle capture system is not abnormal.

In this embodiment, an abnormal feature library may be created in advance according to a test before the vehicle leaves a factory, an abnormal feature generated in an actual driving process of the vehicle, and the like, and after the carbon accumulation feature and the regeneration feature of the current early warning monitoring period are extracted, it may be determined whether the carbon accumulation feature or the regeneration feature exists in the abnormal feature library, and if the carbon accumulation feature or the regeneration feature of the current early warning monitoring period exists in the abnormal feature library, the operation of the particle capture system is abnormal. Through such setting, whether abnormal characteristics exist in the accumulated carbon characteristics and the regeneration characteristics of the current early warning monitoring period can be simply and conveniently determined, so that whether the operation of the particle capture system is abnormal or not is further judged, and the efficiency of judging the abnormal operation is improved.

In another possible embodiment, the S103 determines whether there is an abnormality in the operation of the particle capture system according to the carbon accumulation characteristic and the regeneration characteristic of the current early warning monitoring period, and may further include: performing single classification on the accumulated carbon characteristic and the regeneration characteristic of the current early warning monitoring period by adopting a characteristic single classification model to obtain a single classification result; if the single classification result has abnormal features, determining that the operation of the particle capture system is abnormal; if the single classification result does not have abnormal features, determining that the operation of the particle capture system is not abnormal; wherein the feature single classification model is obtained by training the system state of the particle capture system acquired under the normal state of the vehicle.

In this embodiment, the system operation data of the particle capture system in the normal state of the vehicle and the basic driving data of the vehicle may be collected in advance, the corresponding features may be determined according to the system operation data of the particle capture system in the normal state of the vehicle and the basic driving data of the vehicle by using the method in step S102, and the feature list classification model may be obtained according to the feature training. And after the accumulated carbon characteristic and the regeneration characteristic of the current early warning monitoring period are determined, performing single classification on the accumulated carbon characteristic and the regeneration characteristic of the current early warning monitoring period by using the characteristic single classification model, and determining that the operation of the particle capture system is abnormal if abnormal characteristics exist in a single classification result. Through the arrangement, the accuracy of judging the abnormal operation of the particle capture system in the current early warning monitoring period can be improved.

In a specific embodiment, the feature single classification model may be obtained by training according to a Class-One support vector machine (One Class-SVM) algorithm model, and the Class-One support vector machine algorithm model may be trained and fitted to a hyperplane according to the features extracted in the normal state of the vehicle, so as to distinguish the normal features from the abnormal features through the hyperplane. After the accumulated carbon characteristic and the regeneration characteristic of the current early warning monitoring period are input into a trained characteristic single classification model for testing, if the characteristic exceeding the hyperplane exists, the characteristic is an abnormal characteristic.

In one embodiment, the feature single classification model may be obtained by: acquiring carbon accumulation characteristics and regeneration characteristics within a preset time before a current early warning monitoring period; and judging whether abnormal characteristics exist in the accumulated carbon characteristics and the regeneration characteristics within the preset time length.

And if the abnormal features do not exist, training a feature single classification model used in a previous early warning monitoring period of the current early warning monitoring period by using accumulated carbon features and regeneration features within a preset time length as a training set to obtain the feature single classification model used in the current early warning monitoring period.

And if the abnormal features exist and the corresponding fault information exists in the abnormal features, taking the feature single classification model used in the early warning monitoring period before the current early warning monitoring period as the feature single classification model used in the current early warning monitoring period.

And if the abnormal features exist and the corresponding fault information does not exist in the abnormal features, rejecting the abnormal features, taking the accumulated carbon features and the regeneration features remaining in the preset time as a training set, and training a feature single classification model used in a previous early warning monitoring period of the current early warning monitoring period to obtain the feature single classification model used in the current early warning monitoring period.

In this embodiment, because differences exist among different vehicles, differences exist among different drivers, differences exist among different operating conditions, and the like, system operating data and corresponding system operating states generated after different vehicles leave a factory are different, and system operating data and corresponding system operating states generated by the same vehicle at different periods are also different. Some system operation data correspond to normal system operation states when the vehicle leaves a factory, but the system operation states corresponding to the system operation data may be abnormal after the vehicle runs for a period of time. In order to solve the problems, the method and the device train the characteristic single classification model used in the previous early warning monitoring period by utilizing the accumulated carbon characteristic and the regeneration characteristic in the preset time before the current early warning monitoring period, and enable the single classification result of the characteristic single classification model to be more fit with the running state of the current particle capture system through continuously updating the model, so that the single classification result is more accurate, and the accuracy of the abnormal running judgment is further improved.

Further, when the carbon accumulation characteristic and the regeneration characteristic in the preset time length before the current early warning monitoring period are used for updating the model of the characteristic single classification model used in the previous early warning monitoring period, whether the model needs to be updated or not is determined by judging whether the carbon accumulation characteristic and the regeneration characteristic in the preset time length have abnormal characteristics or not. And if the abnormal features exist, further determining whether the model is to be updated and a specific training set according to whether the abnormal features exist or not and corresponding fault information. Through the arrangement, the training set of the model is always the normal features within the preset time length before the current early warning monitoring period, the timeliness and the accuracy of the training set features are improved, and the accuracy of the single classification result of the feature single classification model is further improved.

In this embodiment, a person skilled in the art can flexibly set the preset time period, for example, the preset time period may be one week or one month, which is not limited herein. In addition, in order to ensure the number of samples in the model training set so as to improve the model classification effect, the preset time length can be more than or equal to the early warning monitoring period. The fault information can be a fault code or a fault state code of the particle capture system, whether the particle capture system has a fault or not can be judged through the fault code, and whether the fault occurs or not and the fault degree can be judged through the fault state code. If a certain abnormal feature corresponds to a fault code, the abnormal feature corresponds to fault information, and of course, it may also be determined whether the abnormal feature corresponds to the fault information through other data, which is not limited herein.

In a specific embodiment, as shown in fig. 3, fig. 3 shows a training set determination diagram of a feature single classification model. The middle square represents the accumulated carbon characteristic and the regeneration characteristic generated in each early warning monitoring period, and the dashed line frame represents the training set of the characteristic single classification model. The box 5 in the left graph represents the characteristics of the previous early warning monitoring period of the current early warning monitoring period, and the boxes 1-4 in the dotted line frame represent the carbon accumulation characteristics and regeneration characteristics within four weeks before the previous early warning monitoring period. The feature list classification model used in the previous early warning monitoring period is obtained by utilizing feature training in squares 1-4. When the feature single classification model of the current early warning monitoring period is obtained, features in the four weeks before the current early warning monitoring period, namely the features in the squares 2-5, are used, and at this time, whether abnormal features exist in the features in the squares 2-5 or not needs to be judged. Since the features in the squares 2-4 are already used in training the used feature list classification model of the previous early warning monitoring period, and are normal features, it is only necessary to judge whether there is an abnormal feature in the features in the square 5. In the right diagram, scheme one: and if the abnormal features do not exist in the features in the square 5, training the feature single classification model used in the previous early warning monitoring period by using the features in the squares 2-5 as a training set to obtain the feature single classification model of the current early warning monitoring period. Scheme II: if the abnormal features exist in the features in the square 5 and the corresponding fault information exists in the abnormal features, the model is not updated, and the feature single classification model used in the early warning monitoring period before the current early warning monitoring period is used as the feature single classification model used in the current early warning monitoring period. Scheme II: and if the abnormal features exist in the features in the square 5 and the corresponding fault information does not exist in the abnormal features, rejecting the abnormal features, taking the residual accumulated carbon features and the regeneration features in the square 2-5 as a training set, and training a feature single classification model used in a previous early warning monitoring period of the current early warning monitoring period to obtain the feature single classification model used in the current early warning monitoring period.

Example two

Fig. 4 is a flowchart of a processing method of a particle capture system according to an embodiment of the present disclosure. As shown in fig. 4, the step S102 of determining the carbon accumulation characteristic and the regeneration characteristic of the current warning monitoring period according to the basic driving data and the system operation data may include the following steps:

s201: and sequencing the basic driving data and the system operation data in the current early warning monitoring period according to the data acquisition time sequence.

S202: and segmenting the sorted basic driving data and system operation data according to the cycle period of the particle capture system to obtain segmented sample data.

S203: and extracting the accumulated carbon characteristic and the regeneration characteristic from each section of sample data.

In this embodiment, the operation of the particle capture system includes a carbon accumulation process and a regeneration process, and one cycle of the particle capture system may include one carbon accumulation process and one regeneration process. By segmenting the cycle period of the particle capture system and extracting the carbon accumulation characteristic and the regeneration characteristic corresponding to the cycle period of each particle capture system, the running state of the particle capture system can be more accurately characterized by the carbon accumulation characteristic and the regeneration characteristic.

In an embodiment, before segmenting the sorted basic driving data and the system operation data according to the cycle period of the particle capture system in step S202 to obtain sample data of each segment, the method may further include:

s204: and acquiring state change information of the state of the particle capture system switched from the engine working mode, and determining the cycle period of the particle capture system according to the state change information.

In the present embodiment, when the particle capture system switches from the carbon accumulation process to the regeneration process, the engine operating mode is switched to the particle capture system state; when the particle capture system is switched from a regeneration process to a carbon accumulation process, the engine working mode can close the state of the particle capture system, so that the time period from the last time when the engine working mode is switched to the state of the particle capture system to the current time when the engine working mode is switched to the state of the particle capture system is a particle capture system cycle period.

Fig. 5 is a schematic structural diagram of a particle capture system processing apparatus according to an embodiment of the present application, and as shown in fig. 5, the particle capture system processing apparatus includes: a processor 101 and a memory 102; the memory 102 stores a computer program; the processor 101 executes the computer program stored in the memory to implement the steps of the particle capture system processing method in the above-described method embodiments.

The particle capture system processing device may be stand alone or part of a vehicle, and the processor 101 and memory 102 may employ existing hardware within the vehicle.

In the particle capture system processing device described above, the memory 102 and the processor 101 are electrically connected, directly or indirectly, to enable the transfer or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines, such as a bus. The memory 102 stores computer-executable instructions for implementing the data access control method, including at least one software functional module that can be stored in the memory 102 in the form of software or firmware, and the processor 101 executes various functional applications and data processing by running software programs and modules stored in the memory 102.

The Memory 102 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 102 is used for storing programs, and the processor 101 executes the programs after receiving the execution instructions. Further, the software programs and modules within the memory 102 may also include an operating system, which may include various software components and/or drivers for managing system tasks (e.g., memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components.

The processor 101 may be an integrated circuit chip having signal processing capabilities. The Processor 101 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and so on. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

An embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored, and the computer-executable instructions are executed by a processor to implement the steps of the method embodiments of the present application.

An embodiment of the present application also provides a computer program product comprising a computer program that, when being executed by a processor, performs the steps of the method embodiments of the present application.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.