Controller testing method, device, equipment and medium

By obtaining and processing the running data of entity objects, generating training and testing data, and training the physical model of the controlled object, it solves the problems of low accuracy and high cost of vehicle controller testing in the prior art, and achieves high precision and efficiency Controller test.

CN115391167BActive Publication Date: 2025-01-17BYD CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202110572077.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-05-25
Publication Date
2025-01-17
Estimated Expiration
2041-05-25

AI Technical Summary

Technical Problem

Due to the lack of standard controllers, the test results are not accurate, and the test cycle is long and costly, so multiple real vehicles are required to collect information.

Method used

By obtaining the running data of the entity object under various working conditions, performing classification processing, generating training data and test data, testing the controller under test based on these data, and using the training data to train the physical model of the controlled object to achieve the goal of the control. High-precision testing of the controller.

Benefits of technology

It improves the accuracy and environmental authenticity of controller testing, shortens test time, reduces test costs, and supports HIL testing of multiple controllers at the same time.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115391167B_ABST
    Figure CN115391167B_ABST
Patent Text Reader

Abstract

The present application discloses a controller testing method, device, equipment and medium, the method comprising: obtaining operating data collected by a physical object; classifying and processing the operating data to obtain training data and test data corresponding to at least one controller under test, the test data being used to test at least one controller under test; training the physical model of at least one controlled object based on the training data, the controller under test and the controlled object being used to be configured on physical equipment of the same type as the physical object. The data processing server of the embodiment of the present application classifies and processes the acquired operating data to obtain training data and test data, so that the test data can test the controller under test, and uses the training data to train the corresponding controlled object model, so that the controlled object model test accuracy is improved, the authenticity of the controller test environment is improved, and ultimately the accuracy of the controller test results is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates generally to the field of computer technology, and more particularly to vehicle controller testing methods, devices, equipment and media. Background Art

[0002] With the development of artificial intelligence, the autonomous driving technology of automobiles has been gradually used. In the production process of autonomous vehicles, it is necessary to perform performance tests on various controllers of the vehicle to determine whether the performance of the controller is qualified, and then continuously optimize the controller control parameters and improve the control accuracy.

[0003] At present, in the process of controller performance testing, a standard controller is installed on an actual vehicle, and the information perceived and planned by the actual vehicle in operation on the road is used as data input for simulation testing. Finally, the controller test results are compared with the actual vehicle execution results to implement controller performance testing based on the comparison results.

[0004] Regarding the testing methods in the prior art, since the current controller is a process of gradual deepening and refinement from system requirements to hardware and software, its functions and performance are gradually improved, and there is no standard controller to refer to, so the method of comparing the processing results of the standard controller with the processing results of the test control makes the test results not accurate; and since the development and testing of each controller requires the use of one or more real vehicles to collect information, the testing cycle is long and the testing cost is high. Summary of the invention

[0005] In view of the above-mentioned defects or deficiencies in the prior art, it is desired to provide a vehicle controller testing method, device, equipment and medium, which can improve the accuracy of vehicle controller testing and reduce testing costs by processing, analyzing and reusing the data collected from actual vehicle test vehicles.

[0006] In a first aspect, an embodiment of the present application provides a controller testing method, the method comprising:

[0007] Acquire operation data collected by the entity object, where the operation data is information collected when the entity object is running under various working conditions;

[0008] Classify and process the operation data to obtain training data and test data corresponding to at least one controller under test, wherein the test data is used to test at least one controller under test;

[0009] The physical model of at least one controlled object is trained based on the training data. The controller under test corresponds to the controlled object one-to-one and is used to control the controlled object. The controller under test and the controlled object are used to be configured on a physical device of the same type as the physical object.

[0010] In a second aspect, an embodiment of the present application provides a controller testing device, the device comprising:

[0011] An acquisition module, used to acquire operation data collected by the entity object, where the operation data is information collected when the entity object operates under various working conditions;

[0012] A processing module, used for classifying and processing the operation data to obtain training data and test data corresponding to at least one controller under test, wherein the test data is used for testing at least one controller under test;

[0013] A training module is used to train a physical model of at least one controlled object based on the training data. The controller under test corresponds to the controlled object one-to-one and is used to control the controlled object. The controller under test and the controlled object are used to be configured on a physical device of the same type as the physical object.

[0014] In a third aspect, an embodiment of the present application provides a processing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the controller testing method as described in the first aspect above is implemented.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is used to implement the controller testing method as described in the first aspect above.

[0016] The controller testing method, apparatus, equipment and medium provided in the embodiments of the present application, the data processing server obtains the operating data collected by the actual object under various working conditions, and then classifies and processes the obtained operating data to obtain training data and test data of at least one controller, so that the test data can be used to test the controller under test, and the training data is used to train the corresponding controlled object model, so that the testing accuracy of the controlled object model is improved, the authenticity of the controller testing environment is improved, and ultimately the accuracy of the controller testing results is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0018] Figure 1 Shown is a schematic diagram of the framework structure of the control test of an embodiment of the present application;

[0019] Figure 2 A schematic diagram of the structure of a controller testing system according to an embodiment of the present application;

[0020] Figure 3 A flowchart of a controller testing method according to an embodiment of the present application;

[0021] Figure 4 A schematic diagram of the structure of a controller testing device according to an embodiment of the present application;

[0022] Figure 5 A schematic diagram of the structure of a computer of a processing device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant disclosure, rather than to limit the disclosure. It should also be noted that, for ease of description, only the parts related to the disclosure are shown in the accompanying drawings.

[0024] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0025] It is understandable that during the development and testing process of the unmanned vehicle controller, the developed and designed controller needs to be tested to detect whether its functions are qualified, such as the engine controller, steering wheel controller, etc.

[0026] Considering that in the prior art each controller needs to be compared with the standard controller of the actual vehicle to implement controller testing, which results in a long testing cycle, high cost and low test accuracy, the controller can be tested through hardware-in-the-loop (HIL), that is, by replacing the rest of the physical parts of the vehicle with a virtual model to test the controller, so that the system software and mechanical hardware structure can be designed in parallel during the controller development process, shortening the production cycle, reducing testing costs and improving test accuracy.

[0027] In the embodiment of the present application, in order to improve the test accuracy and reduce the test cost, a hardware system and a software system for controller testing are constructed, such as Figure 1 and Figure 2 As shown, by utilizing the constructed platform, it is possible to obtain the actual measured data of each vehicle type under various working conditions, and then the obtained data can be analyzed and processed by the software system running in the data processing server to train the physical model of the controlled object of each controller to obtain a realistic virtual model of the controlled object; at the same time, part of the data can be directly imported into the HIL test system to realize the test of the controller under test.

[0028] It can be understood that the controller testing method provided in the embodiment of the present application can also be used for testing controllers in other machines and equipment, such as controllers in drones, or controllers in industrial production, etc.

[0029] Figure 1 A schematic diagram of the hardware system architecture of the controller test provided in the embodiment of the present application, such as Figure 1 As shown, the system may include an actual object (such as an actual vehicle, etc.), a cloud server, a data processing server, a HIL test device and a controller under test. The actual object is connected to the cloud server through an intelligent network system to achieve data transmission; the data processing server is connected to the cloud server through a laboratory intelligent network system to achieve data transmission. The data processing server is connected to the HIL test device and the controller under test respectively to achieve data transmission.

[0030] The actual object is equipped with sensors for collecting the operating status of the actual object and external environment information, and is equipped with an intelligent network connection system. The actual object can transmit the object operating status parameter information, environmental information, location information and bus information collected by the sensors and navigation system to the cloud server for storage through the intelligent network connection system.

[0031] The data processing server manages and processes data. In practice, it can download the information collected by the actual object from the cloud server, analyze, classify and process it, and use the downloaded data to train the physical model of the controlled object. In addition, the downloaded data can also be sent to the HIL device to test various controllers.

[0032] The data processing server runs the software of the data management system, which can classify and process the collected information through the data processing program, such as classifying the data for different controllers, or extracting the dynamic and economic data to train the physical model of the HIL system to improve its accuracy. At the same time, different data information can be downloaded to the corresponding controller HIL device, combined with the high-precision physical model for HIL testing, and the vehicle model and environmental information can be truly simulated, making the test process and test results more realistic and reliable.

[0033] The host computer, that is, the terminal device used by the tester, can run the front-end interface of the data management system, such as the account login interface and the data interaction interface.

[0034] It can be understood that in actual use, the tester can log in to the test management system through the front-end web page of the operation data management system software on the host computer, and send a request message to the data processing server to request to obtain data or process data, such as requesting the trained controlled object model to be downloaded to the real-time simulation platform of the HIL device, or requesting the collected raw data to be input into the controller under test.

[0035] HIL test equipment (HIL system) may include a real-time simulation platform, a programmable power supply, an IO and communication board, a signal conditioning board and a fault injection board. The real-time simulation platform runs a trained physical model of the controlled object and is the core of the hardware-in-the-loop device. The programmable power supply is used to simulate the power supply, such as simulating the power supply on the vehicle. The IO and communication board is used to interact with the controller under test. The signal conditioning board is used to condition the input and output signals of the controller under test. The fault injection board is used to simulate various faults in the real environment.

[0036] The controller under test is the object under test, such as a controller in an unmanned vehicle, or a controller in a drone, such as an engine controller.

[0037] The HIL test equipment exchanges data with the controller under test to implement function testing and performance testing of the controller under test.

[0038] The physical model of the controlled object is a virtual model of the control object of the controller under test constructed by the data processing server, such as a virtual model of an engine or a virtual model of a steering wheel, that is, the controller under test is an engine controller, which controls the engine virtual model to achieve realistic engine operation.

[0039] In order to better understand and illustrate the controller testing method, device, system and medium provided in the embodiments of the present application, an unmanned vehicle is taken as an example. Figures 3 to 5 Elaborate in detail.

[0040] Figure 3 A flow chart of a controller testing method provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the method may be executed by a data processing server, and the method may include:

[0041] S310, acquiring operation data of the entity object, where the operation data is information collected when the entity object operates under various working conditions;

[0042] S320, classifying and processing the operation data to obtain training data and test data, where the test data is used to test at least one controller under test;

[0043] S330, training a physical model of at least one controlled object based on training data, wherein the controller under test corresponds to the controlled object one-to-one, the controller under test is used to control the controlled object, and the controller under test and the controlled object are used on physical equipment of the same type as the physical object.

[0044] Specifically, in the embodiment of the present application, an unmanned vehicle is taken as an example for explanation, that is, the entity object is an actual vehicle, and the data processing server can obtain various operating data collected and reported when the actual vehicle is running under various working conditions.

[0045] It can be understood that in practice, in order to ensure the accuracy of the test results, the operating data collected by the actual vehicle is used to construct the training of the physical model of the controlled object of the same type as the controller and controlled object configured on the actual vehicle, as well as the testing of the controller under test.

[0046] The operating data can be collected under various operating conditions such as urban areas, mountain roads, straight driving, turning, and side parking, including vehicle operating status parameter information, environmental information, location information, and bus information collected by on-board sensors and navigation systems.

[0047] The actual vehicle's operating status parameter information may include vehicle speed, steering wheel angle, cooling water temperature and fuel tank pressure, etc.; the environmental information may include outside temperature, road slope, traffic information and surrounding information, etc.; the location information may include collected landmark information, etc.; the bus information may include vehicle door switch status, steering wheel data torque, etc.

[0048] For example, Figure 2 As shown, the actual vehicle can upload the collected operation data to the cloud server through the Internet for storage. Then the test engineer can send a data request message to the data processing server by operating the operation interface of the data management system running on the terminal, so that the data processing server responds to the data request message and downloads the operation data to the cloud.

[0049] Specifically, after the data processing server obtains the running data, the tester can operate the data management system to run on the terminal, such as Figure 1 The operation interface on the upper computer shown in the figure inputs the operation instruction, so that the terminal responds to the operation instruction and sends a data acquisition request message to the backend server of the operation data management system, that is, the data processing server. After receiving the data acquisition request message, the data processing server can respond to the request message and download the required data from the cloud.

[0050] For example, the operator can enable the data processing server to download the operation data collected during the operation of the corresponding vehicle model from the cloud according to the vehicle model corresponding to the controller to be trained and tested.

[0051] Furthermore, after downloading the operation data to the local server, i.e., the data processing server, the operator may further input an operation instruction to send a data processing request message to the data processing server. After receiving the request message, the data processing server may respond to the data processing request message and process the downloaded operation data.

[0052] For example, after acquiring the operating data, the data processing server can classify the operating data using a pre-stored processing program, such as classifying the data according to the type of controller configured in the vehicle, and obtaining training data corresponding to the controlled objects of different controllers. For example, the training data corresponding to the engine controller or the training data of the steering wheel controller object can be obtained.

[0053] It can be understood that data related to vehicle performance, such as power, economy, etc., are used to train the physical model of the controlled object in the HIL system, so as to optimize the physical model of the controlled object, especially to update and upgrade the nonlinear part model (such as tire model, brake model, etc.) to make its performance closer to the actual vehicle and make the vehicle environment of the controller under test more realistic.

[0054] At the same time, some operating data can be directly extracted as test data to be imported into the HIL device to test the controller under test. For example, the steering wheel angle in the collected bus data can be used to test the torque output by the controller.

[0055] For example, the vehicle's environmental information and bus signals can be extracted and directly used for HIL testing of the corresponding controller. In practice, for example, the signals (bus signals and hard-wired signals) that interact with the vehicle controller VCU are extracted to perform cycle and working condition tests on the VCU, and the environmental data during the vehicle parking process is extracted and then input into the HIL test animation software. The automatic parking controller APA is tested in HIL in combination with the physical model, and the effect of the APA can be verified through the animation software and test data.

[0056] It can be understood that in this method, multiple controllers of the same type or different types can be tested at the same time based on the collected operating data, such as testing different functions of multiple controllers of the same type at the same time. Finally, the test results can be automatically sorted out and reported, thereby shortening the controller test time and reducing the test cost.

[0057] It can also be understood that in the embodiment of the present application, the requirement for the actual vehicle test vehicle, that is, the actual vehicle, is one of the same model. The actual vehicle test vehicle collects data on all roads and working conditions, transmits the data to the laboratory through the intelligent network connection system, and relies on the test management system to process, analyze and reuse the data, thereby reducing the cost of collecting environmental data on the actual vehicle, and also laying the foundation for subsequent controller development and testing.

[0058] For a better understanding, the following Figure 1 and Figure 2 The whole process of controller testing method is elaborated in detail.

[0059] Vehicle sensors, environmental perception devices, navigation systems, etc. are installed on actual vehicles and put into operation on the road to collect vehicle operating status parameters, traffic information, and location information. After processing by the corresponding controller, the collected information and bus signals are transmitted to the cloud by the intelligent network system. After the actual vehicle has finished collecting information, the tester uses the laboratory intelligent network system to download the actual vehicle operation data and perception information to the local and import it into the test management system for classification and processing. At this time, the information data has two uses: data related to vehicle performance, such as power, economy and other data, is used to train the physical model in the HIL system to optimize the controlled object, especially to update and upgrade the nonlinear part model (such as tire model, brake model, etc.) to make its performance closer to the actual vehicle and make the vehicle environment of the controller under test more realistic; in addition, the vehicle's environmental information and bus signals can be extracted and directly used for HIL testing of the corresponding controller, such as extracting signals (bus signals and hard-wired signals) that interact with the vehicle controller VCU to perform cycle and operating condition tests on the VCU, extracting environmental data during the vehicle parking process, and inputting it into the HIL test animation software, and combining the physical model to perform HIL testing on the automatic parking controller APA. The effect of APA can be verified through animation software and test data.

[0060] It can be understood that in this process, model training improves the accuracy of the physical model, and the high-precision model is integrated into the controller test environment, thereby improving the authenticity of the controller test environment and ultimately improving the accuracy of the controller test results. This test method supports simultaneous HIL testing of multiple controllers of the same or different types, automatically sorting out and reporting the test results, shortening the controller test time, and reducing the test cost.

[0061] It can be understood that in the embodiment of the present application, the physical model in the HIL system is trained so that the physical model is continuously iterated and optimized, making its functions and performance closer to the actual vehicle.

[0062] In terms of the application of information transmitted by the intelligent connected system, that is, the information transmitted by the system is not only used for controller testing. After processing and classification of the information, the vehicle-related information is used to train the physical model of the HIL system, so as to continuously improve the accuracy of the physical model and realize the dual iteration and synchronous optimization of the physical and controller algorithms.

[0063] In addition, full utilization of virtual simulation (hardware-in-the-loop simulation), that is, the HIL system consists of a physical model, a real-time processor, and a controller under test. The high-precision physical model can truly reflect the vehicle's power, economy, smoothness, etc., and other control modules outside the controller under test are virtualized, which can truly reflect the signal interaction with the controller under test, so that the controller under test is in a test environment close to the real vehicle.

[0064] Figure 4 FIG. 1 is a schematic diagram of the structure of a controller testing device provided in an embodiment of the present application. Figure 4 As shown, the device 400 includes:

[0065] An acquisition module 410 is used to acquire operation data collected by the entity object, where the operation data is information collected when the entity object operates under various working conditions;

[0066] The processing module 420 is used to classify the operation data to obtain training data and test data corresponding to at least one controller under test, and the test data is used to test the at least one controller under test;

[0067] The training module 430 is used to train the physical model of at least one controlled object based on the training data. The controller under test corresponds to the controlled object one by one and is used to control the controlled object. The controller under test and the controlled object are used to be configured on a physical equipment of the same type as the physical object.

[0068] Optionally, the controller testing device of the embodiment of the present application further includes a transmission module 440, which is used to input the test data into a hardware-in-the-loop testing device so that the hardware-in-the-loop testing device tests the controller under test, and the physical model of the controlled object controlled by the controller under test runs in the hardware-in-the-loop testing device.

[0069] Optionally, in the controller testing device of the embodiment of the present application, the classification module is specifically used to respond to the data processing request message, classify the operating data according to the category of the controller under test, and obtain training data corresponding to at least one controller under test.

[0070] Optionally, in the controller testing device of the embodiment of the present application, the acquisition module is specifically used to respond to the data download request message and obtain the operating data collected by the physical object from the cloud.

[0071] Optionally, in the controller testing device of an embodiment of the present application, the entity object is an actual vehicle, and the operating data includes state parameters, environmental information, location information and bus information of the actual vehicle.

[0072] Optionally, in the controller testing device of an embodiment of the present application, the classification module is specifically used to respond to a data classification request message, classify the on-road data according to the controller category configured on the actual vehicle, and obtain training data corresponding to at least one controller.

[0073] On the other hand, an embodiment of the present application also provides a processing device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the controller testing method described in the above embodiment when executing the program.

[0074] Reference below Figure 5 , Figure 5 A schematic diagram of the structure of a computer electronic device which is a processing device of an embodiment of the present application.

[0075] like Figure 5 As shown, the computer electronic device 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage part 502 to the random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0076] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.

[0077] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a machine-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 509, and / or installed from a removable medium 511. When the computer program is executed by a central processing unit (CPU) 501, the above-mentioned functions defined in the electronic device of the present application are executed.

[0078] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electronic device, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction-executing electronic device, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction-executing electronic device, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0079] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the processing equipment, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the aforementioned module, program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based electronic device that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0080] The units or modules involved in the embodiments of the present application may be implemented by software or by hardware. The units or modules described may also be arranged in a processor, for example, they may be described as: a processor comprising: an acquisition module, a processing module and a training module. Among them, the names of these units or modules do not constitute limitations on the units or modules themselves under certain circumstances. For example, a training module may also be described as "used to train a physical model of at least one controlled object based on the training data, the controller under test corresponds one-to-one with the controlled object, and is used to control the controlled object, and the controller under test and the controlled object are used to be configured on a physical equipment of the same type as the physical object".

[0081] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable storage medium stores one or more programs, and when the above programs are used by one or more processors to execute the controller testing method described in the present application:

[0082] Acquiring operation data collected by the physical object, wherein the operation data is information collected when the physical object operates under various working conditions;

[0083] Classify and process the operating data to obtain training data and test data corresponding to at least one controller under test, wherein the test data is used to test at least one controller under test;

[0084] The physical model of at least one controlled object is trained based on the training data. The controller under test corresponds to the controlled object one-to-one and is used to control the controlled object. The controller under test and the controlled object are used to be configured on a physical equipment of the same type as the physical object.

[0085] In summary, the controller testing method, apparatus, equipment and medium provided in the embodiments of the present application, the data processing server obtains the operating data collected by the actual object under various working conditions, and then classifies and processes the obtained operating data to obtain training data and test data of at least one controller, so that the test data can be used to test the controller under test, and then the training data can be used to train the corresponding controlled object model, so that the testing accuracy of the controlled object model is improved, the authenticity of the controller testing environment is improved, and ultimately the accuracy of the controller testing results is improved.

[0086] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A controller testing method, characterized in that: The method is based on a controller test system, which includes: a physical object, a cloud server, a data processing server, a HIL test device and a controller under test, wherein the physical object is connected to the cloud server; the data processing server is connected to the cloud server; the data processing server is connected to the HIL test device and the controller under test respectively; the physical object is equipped with a sensor that collects the running status of the physical object and the external environment information, and the information collected by the sensor and the navigation system is transmitted to the cloud server for storage through the intelligent network connection system; the data processing server realizes data management and processing, downloads the information collected by the physical object from the cloud server, and performs analysis, classification and processing; the HIL test device supports HIL testing of multiple controllers of the same or different types at the same time in the HIL test laboratory, and the HIL test device includes a real-time simulation platform, an IO and communication board, and a signal conditioning board; a trained physical model of the controlled object is run on the real-time simulation platform, the IO and communication board is used to perform signal interaction with the controller under test, and the signal conditioning board is used to condition the signal input and output of the controller under test; wherein the physical model of the controlled object is a virtual model of the control object of the controller under test constructed by the data processing server; The method comprises: acquiring operation data collected by a physical object, wherein the operation data is information collected when the physical object is running under various working conditions; if the physical object is an actual vehicle, the operation data comprises state parameters, environmental information, location information and bus information of the actual vehicle; Classify the operation data, classify the operation data according to the type of controller, and obtain training data and test data corresponding to at least one controller under test, wherein the test data is used to test at least one controller under test; The physical model of at least one controlled object is trained based on the training data. The controller under test corresponds to the controlled object one-to-one and is used to control the controlled object. The controller under test and the controlled object are used to be configured on a physical equipment of the same type as the physical object.

2. The controller testing method according to claim 1, characterized in that: The method further comprises: The test data is input into a hardware-in-the-loop test device, so that the hardware-in-the-loop test device tests the controller under test. A physical model of a controlled object controlled by the controller under test runs in the hardware-in-the-loop test device.

3. The controller testing method according to claim 1, characterized in that: The classifying and processing the operation data comprises: In response to the data processing request message, the operating data is classified and processed according to the category of the controller under test to obtain training data corresponding to at least one controller under test.

4. The controller testing method according to claim 1, characterized in that: The acquisition of the operation data collected by the entity object includes: In response to the data download request message, the operation data collected by the physical object is obtained from the cloud.

5. A controller testing device, characterized in that: The device is used to execute the controller testing method according to any one of claims 1 to 4, and the device comprises: An acquisition module, used to acquire operating data collected by a physical object, wherein the operating data is information collected when the physical object is operating under various working conditions; if the physical object is an actual vehicle, the operating data includes state parameters, environmental information, location information and bus information of the actual vehicle; A processing module, used for classifying the operation data, classifying the operation data according to the type of the controller, and obtaining training data and test data corresponding to at least one controller under test, wherein the test data is used for testing at least one controller under test; A training module is used to train a physical model of at least one controlled object based on the training data. The controller under test corresponds to the controlled object one-to-one and is used to control the controlled object. The controller under test and the controlled object are used to be configured on a physical equipment of the same type as the physical object.

6. The controller testing device according to claim 5, characterized in that: It also includes a transmission module for inputting the test data into a hardware-in-the-loop test device so that the hardware-in-the-loop test device tests the controller under test. A physical model of a controlled object controlled by the controller under test runs in the hardware-in-the-loop test device.

7. The controller testing device according to claim 5, characterized in that: The acquisition module is specifically used to respond to the data download request message and obtain the operation data collected by the physical object from the cloud.

8. A processing device, characterized in that: The processing device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the controller testing method according to any one of claims 1 to 4 when executing the program.

9. A computer-readable storage medium having a computer program stored thereon, wherein the computer program is used to implement the controller testing method according to any one of claims 1 to 4.

Citation Information

Patent Citations

  • Real automobile in-the-loop simulation testing method, real-time simulation machine and system

    CN104460349A

  • Design method for HIL test system, and HIL test system

    CN109031977A

  • Training method, device and equipment for longitudinal kinetic model

    CN111931286A