Large model-based vehicle body fault analysis method, apparatus and device, and medium

Abstract

The invention discloses a vehicle body fault analysis method and device based on a large model, equipment and a medium, and belongs to the technical field of vehicles. The method comprises the following steps: if a control signal for controlling a vehicle body system to execute a task is received, acquiring a state signal related to the task, a timestamp of the control signal and a timestamp of the state signal, the state signals comprise an execution part state signal, a controller state signal and a task execution state signal of the vehicle body system; generating a data string of the task according to the control signal, the state signal and a corresponding timestamp; according to the data string, judging whether the vehicle body system has a fault or not; and if the vehicle body system has a fault, determining a fault reason according to the data string. According to the method, the vehicle body fault analysis is more timely, and whether a fault exists or not and the fault reason can be judged more accurately.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a vehicle body fault analysis method, device, equipment and medium based on a large model. Background Art

[0002] As the central controller has more and more functions and the network becomes more and more complex, the links caused by body failures are getting longer and longer, making body failure analysis more difficult.

[0003] In related technologies, the vehicle's local data or cloud data will be downloaded, and the downloaded data will be analyzed to find out what problems there are with the vehicle body.

[0004] However, the above method is a body fault analysis method used when the vehicle is under maintenance, and it is unable to analyze the body fault in real time while the vehicle is running, resulting in a serious lag in fault analysis. Summary of the invention

[0005] In view of the above problems, the present invention is proposed to provide a large-model based vehicle body fault analysis method, device, equipment and medium to solve the above problems. According to the control signals and status signals of the vehicle body system collected in real time, and the corresponding timestamps, a data string for characterizing the changes in various states of the vehicle body system during the entire task execution process is generated. Then, according to the data string, it can be judged whether the vehicle body system has a fault, and the cause of the fault can be determined, so that the analysis of the vehicle body fault is more timely, and whether there is a fault and the cause of the fault can be judged more accurately.

[0006] In a first aspect, the present invention provides a method for analyzing vehicle body failure based on a large model, the method comprising:

[0007] If a control signal for controlling the vehicle body system to execute a task is received, a status signal related to the task, as well as a timestamp of the control signal and a timestamp of the status signal are acquired, wherein the status signal includes an actuator status signal, a controller status signal and a task execution status signal of the vehicle body system;

[0008] generating a data string of the task according to the control signal, the state signal and the corresponding timestamp;

[0009] determining whether the vehicle body system has a fault according to the data string;

[0010] If the vehicle body system has a fault, the cause of the fault is determined based on the data string.

[0011] Optionally, generating the data string of the task according to the control signal, the state signal and the corresponding timestamp includes:

[0012] Determine the actuator number, controller number and control source number corresponding to the control signal;

[0013] Determine first data according to the execution component number, the execution component status signal and the corresponding timestamp;

[0014] Determining second data according to the controller number, the controller status signal and the corresponding timestamp;

[0015] Determine third data according to the control source number, the task execution status signal and the corresponding timestamp;

[0016] A data string of the task is determined according to the control signal, the first data, the second data, and the third data.

[0017] Optionally, determining the data string of the task according to the control signal, the first data, the second data and the third data includes:

[0018] The control signal, the first data, the second data and the third data are arranged in chronological order to obtain a data string for the task.

[0019] Optionally, the vehicle body system includes a plurality of subsystems, and determining the data string of the task according to the control signal, the first data, the second data and the third data further includes:

[0020] Determine the corresponding subsystem number according to the control signal;

[0021] A data string of the task is determined according to the subsystem number, the control signal, the first data, the second data, and the third data.

[0022] Optionally, determining the third data according to the control source number, the task execution status signal and the corresponding timestamp includes:

[0023] Get the vehicle's power mode;

[0024] The third data is determined according to the power mode, the control source number, the task execution status signal and the corresponding timestamp.

[0025] Optionally, determining the fault cause according to the data string includes:

[0026] Determine the previous data of the data string representing the task execution status;

[0027] The cause of the fault is determined according to the previous data.

[0028] Optionally, judging whether the vehicle body system is faulty according to the data string includes:

[0029] If the data representing the task execution status signal in the data string indicates that the task execution status is successful, it is determined that the vehicle body system has no fault;

[0030] If the data representing the task execution status signal in the data string indicates that the task execution status is execution failure, it is determined that the body system has a fault.

[0031] In a second aspect, the present invention provides a vehicle body fault analysis device based on a large model, the device comprising:

[0032] an acquisition module, configured to acquire a status signal related to the task, as well as a timestamp of the control signal and a timestamp of the status signal if a control signal for controlling the vehicle body system to execute a task is received, wherein the status signal includes an actuator status signal, a controller status signal and a task execution status signal of the vehicle body system;

[0033] A generating module, used for generating a data string of the task according to the control signal, the state signal and the corresponding timestamp;

[0034] A judgment module, used for judging whether the vehicle body system has a fault according to the data string;

[0035] A determination module is used to determine the cause of the fault according to the data string if the body system has a fault.

[0036] Optionally, the generation module includes:

[0037] A first determining unit, used to determine an actuator number, a controller number and a control source number corresponding to the control signal;

[0038] A second determining unit, configured to determine first data according to the execution component number, the execution component status signal and a corresponding timestamp;

[0039] a third determining unit, configured to determine second data according to the controller number, the controller state signal and a corresponding timestamp;

[0040] a fourth determining unit, configured to determine third data according to the control source number, the task execution state signal and a corresponding timestamp;

[0041] A fifth determining unit is used to determine a data string of the task according to the control signal, the first data, the second data and the third data.

[0042] Optionally, Unit 5 is also used to:

[0043] The control signal, the first data, the second data and the third data are arranged in chronological order to obtain a data string for the task.

[0044] Optionally, the vehicle body system includes a plurality of subsystems, and the fifth unit is further used for:

[0045] Determine the corresponding subsystem number according to the control signal;

[0046] A data string of the task is determined according to the subsystem number, the control signal, the first data, the second data, and the third data.

[0047] Optionally, the fourth determining unit is further configured to:

[0048] Get the vehicle's power mode;

[0049] The third data is determined according to the power mode, the control source number, the task execution status signal and the corresponding timestamp.

[0050] Optionally, the determination module is further configured to:

[0051] Determine the previous data of the data string representing the task execution status;

[0052] The cause of the fault is determined according to the previous data.

[0053] Optionally, the judgment module is also used to:

[0054] If the data representing the task execution status signal in the data string indicates that the task execution status is successful, it is determined that the vehicle body system has no fault;

[0055] If the data representing the task execution status signal in the data string indicates that the task execution status is execution failure, it is determined that the body system has a fault.

[0056] In a third aspect, the present invention provides an electronic device comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method described in the first aspect by executing the computer instructions.

[0057] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method described in the first aspect.

[0058] The technical solution provided in the embodiments of the present invention has at least the following technical effects or advantages:

[0059] The embodiment of the present invention provides a method, device, equipment and medium for analyzing vehicle body faults based on a large model. If a control signal for controlling the vehicle body system to execute a task is received, indicating that the vehicle body system task needs to be executed, then a status signal related to the task, as well as a timestamp of the control signal and a timestamp of the status signal are obtained. The status signal includes an actuator status signal of the vehicle body system, a controller status signal and a task execution status signal. The status signal reflects the execution of the task; a data string of the task is generated according to the control signal, the status signal and the corresponding timestamp, and the data related to the task execution are formed into a data string; according to the data string, it is determined whether the vehicle body system has a fault. The data string can reflect the status of each step in the task execution process, so it can reflect whether the task execution is successful, and whether the vehicle body system has a fault; if the vehicle body system has a fault, the cause of the fault is determined according to the data string. The data string contains all relevant data in the task execution process, so the cause of the fault can be located according to these data. This method is more timely in analyzing vehicle body faults, and can more accurately determine whether there is a fault and the cause of the fault.

[0060] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0062] Figure 1 is a flow chart of a vehicle body fault analysis method based on a large model provided by an embodiment of the present invention;

[0063] Figure 2 is a structural block diagram of a vehicle body fault analysis device provided by an embodiment of the present invention;

[0064] Figure 3 It is a structural block diagram of a large fault analysis model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solutions and advantages of the present application clearer, the implementation mode of the present application will be further described in detail below in conjunction with the accompanying drawings. It should be understood that the embodiments of the present disclosure and the specific features in the embodiments are detailed descriptions of the technical solutions of the present application, rather than limitations on the technical solutions of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0066] Figure 1 is a flow chart of a method for analyzing vehicle body failure based on a large model provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes:

[0067] Step S110: If a control signal for controlling the vehicle body system to execute a task is received, a status signal related to the task, as well as a timestamp of the control signal and a timestamp of the status signal are obtained.

[0068] The status signal includes an actuator status signal of the vehicle body system, a controller status signal and a task execution status signal.

[0069] In this embodiment, the body system refers to the body structure of the car and its related electronic control system. The control signal refers to a signal for controlling the body system. When the body system receives the control signal, the body system will perform the task corresponding to the control signal. For example, when receiving a control signal for opening a window, the body system performs the task of opening the window.

[0070] Among them, the body system includes an actuator and a controller, and the controller controls the actuator to perform tasks. The actuator includes a hardware structure and a driving mechanism, and the driving mechanism is used to drive the hardware structure to move to complete the task. For example, the window driving mechanism is used to drive the window to open or close. The body system can include multiple subsystems such as the window subsystem, rearview mirror system, door lock subsystem and lighting subsystem. Each subsystem includes one or more actuators. For example, the window subsystem includes a left front window actuator, a right front window actuator, a left rear window actuator and a right rear window actuator.

[0071] In this embodiment, the actuator state signal is used to represent the current state of the actuator, the controller state signal is used to represent the current state of the controller, and the task execution state signal is used to represent the current state of the task execution. When each state signal is acquired, a timestamp representing the time of the current state signal is synchronously acquired, and the current state can be determined based on the corresponding timestamp.

[0072] Among them, the actuator status signal may include signals such as the actuator's fault status, position status and motion status, the controller status signal may include signals such as sleep, waiting for wake-up, initialization, wake-up interrupt, wake-up, wake-up success and wake-up failure, and the task execution status signal may include signals such as not meeting the execution conditions, waiting for execution, execution interrupt, execution, execution success and execution failure.

[0073] In this embodiment, the car includes a central control unit, and the central control unit includes a data acquisition module for acquiring control signals, status signals and timestamps. The control signal and the corresponding timestamp can be sent to the central control unit by the in-vehicle infotainment system (IVI) or the telematics box (Tbox) control unit on the car, or can be generated by the remote control app and sent to the telematics control unit, and then forwarded to the central control unit through the telematics control unit. The in-vehicle infotainment system includes a car touch screen, and the control signal can be generated when the touch screen is operated.

[0074] Among them, the actuator status signal can be collected by sensors. For example, the vehicle body can be divided into four areas: left front, left rear, right front and right rear. Each area is equipped with a door module. Each door module includes multiple sensors for collecting actuator status signals. The door module can also include a switch, which can generate a control signal when the switch is pressed; the controller status signal is the internal state of the controller, and the controller can actively send it to the central control unit; the task execution status signal can be generated by the sensor and the controller and sent to the central control unit. Among them, the actuator status signal is sent periodically; the controller status signal and the task execution status are sent in a triggered manner, and the message is an event message.

[0075] The central control unit is connected to the door module through the CANFD bus. The central control unit communicates with the IVI / Tbox through the Ethernet protocol. The sensor and its corresponding door module are connected through a hard line. The door module converts the collected signal into a CANFD signal and sends it to the central control unit.

[0076] Step S120: Generate a data string of the task according to the control signal, the state signal and the corresponding timestamp.

[0077] In this embodiment, when a control signal is received, it means that the vehicle body system can start to execute the corresponding task. The status signal will change during the execution of the task, so the control signal and the status signal together reflect the process of task execution. Combined with the corresponding timestamp, it can just reflect the execution status of the task over time. The control signal and status signal with timestamp are converted into character format data through the data processing module of the central control unit, and these data are synthesized into a data string.

[0078] For example, during the process of executing the task of opening the window, after receiving the control signal for opening the window, the controller corresponding to the window is awakened. After the controller status signal becomes a wake-up success signal, the controller will control the window drive mechanism to drive the window to open. If the window is successfully opened, the position state of the window acquired at this time should be the open state. Therefore, the control signal for opening the window is converted into data 01 in character format, the controller's wake-up success state is converted into data 02 in character format, and the window opening state is converted into data 03 in character format. Based on the data 01, 02 and 03, a data string representing the execution process of the task of opening the window is generated.

[0079] In this embodiment, a fault analysis model can be established in advance, and then the control signal, status signal, and corresponding timestamps can be packaged into a data packet, and then the data packet is input into the fault analysis model. The data in the data packet is processed by the fault analysis model to generate a data string for the task.

[0080] Among them, the fault analysis model can be deployed on the cloud platform, and the central control unit communicates with the cloud platform through the Ethernet protocol. The central control unit packages the acquired control signals and status signals, as well as the corresponding timestamps, into data packets, and then sends the data packets to the fault analysis model on the cloud platform.

[0081] Step S130: Determine whether the vehicle body system has a fault based on the data string.

[0082] In this embodiment, because the data string reflects the execution of the task over time, whether the task is successfully executed can be reflected by the data in the data string. If the execution is successful, the body system is not faulty. If the execution fails, there may be a fault, or the execution failure may be caused by other reasons. The specific judgment should be made based on the data string. Similarly, the data string can also be analyzed by the fault analysis model to directly output the analysis result of whether the body system is faulty.

[0083] Step S140: If there is a fault in the vehicle body system, determine the cause of the fault based on the data string.

[0084] In this embodiment, if the vehicle body system has a fault, the cause of the fault can be analyzed by analyzing the data string. Therefore, the method in this embodiment can not only analyze in real time whether the vehicle body system has a fault, but also accurately locate the cause of the fault.

[0085] Optionally, step S120 includes:

[0086] The first step is to determine the actuator number, controller number and control source number corresponding to the control signal.

[0087] In this embodiment, the body system includes multiple actuators, each of which can perform different tasks; the body system may also include one or more controllers, each of which can control one or more actuators; the control source is hardware or software that generates and sends control signals, and may be one or more, such as switches on the vehicle, car keys, IVI, or mobile phone APPs. In order to distinguish between multiple actuators, multiple controllers, and multiple control sources, each actuator, controller, and control source is assigned a different number, and the actuator, controller, or control source can be found according to the number.

[0088] In this embodiment, the state signal is divided into three types of data: actuator, controller and control source according to the actuator number, controller number and control source number through the data processing module.

[0089] The second step is to determine the first data according to the execution part number, the execution part status signal and the corresponding timestamp.

[0090] It can be understood that the number, state signal and time stamp of the actuator are combined together to obtain a comprehensive data, which is recorded as the first data. The static situation of the actuator can be reflected through the first data.

[0091] If there are multiple executables, the first data of each executable can be separated by a separator and then combined together. For example, the first data of two executables are separated by 0xFF, that is, the data between two 0xFFs is the first data of one executable.

[0092] Exemplarily, the first data of the window subsystem may be: the number of the window actuator 1 + the fault status of the window actuator 1 + 0xFF + the number of the window actuator 2 + the fault status of the window actuator 2 + the timestamp.

[0093] Step 3: Determine the second data according to the controller number, the controller status signal and the corresponding timestamp.

[0094] It can be understood that the serial number, state signal and timestamp of the controller are combined together to obtain a comprehensive data, which is recorded as the second data. The state of the controller can be reflected through the second data.

[0095] Exemplarily, the second data of the vehicle window subsystem may be: the number of the vehicle window controller+waking up+time stamp.

[0096] In this embodiment, a controller target state signal may also be acquired, and the second data may be determined according to the controller target state signal, the controller number, the controller state signal and the corresponding timestamp.

[0097] Step 4: Determine the third data according to the control source number, the task execution status signal and the corresponding timestamp.

[0098] It can be understood that the control source number, the task execution status signal and the timestamp are combined together to obtain a comprehensive data, which is recorded as the third data. The execution status of the task can be reflected through the third data.

[0099] Optionally, the fourth step includes:

[0100] Obtain the power mode of the vehicle; and determine the third data according to the power mode, the control source number, the task execution status signal and the corresponding timestamp.

[0101] Among them, the vehicle's power modes include Abdandon mode, Convenient mode, Driving mode and SystemUpdate mode. Among them, in Abdandon mode, the vehicle power is not powered on, and the CAN network (Controller Area Network) of the whole vehicle is generally in a dormant state. In Convenient mode, the whole vehicle is powered on, the CAN network will also wake up and start transmitting signals, but the engine is not started, and the whole vehicle is basically connected to a low-voltage power supply. For example, in Convenient mode, the windows are available and the air conditioner can be turned on, but because the generator is not turned on, the air conditioning cooling and heating functions cannot be used. In Driving mode, the engine is in running mode, and the generator is also running and charging the battery, and the air conditioning cooling and heating are available. In SystemUpdate mode, the vehicle is in a software upgrade state, and most of the vehicle functions are disabled.

[0102] In this embodiment, the body system can perform different tasks in different power modes, so considering the power mode can better determine the reason for the failure of task execution. For example, in RUN mode, the mobile phone APP cannot control the body system, so when the mobile phone APP sends a control signal, the body system does not execute the corresponding task. At this time, the reason for the failure of task execution is the power mode, not because of a fault in the body system. In other words, the task execution status signal will be affected by the power mode.

[0103] Exemplarily, the third data of the vehicle window subsystem may be: mobile phone APP number+ACC mode+execution completion signal+time stamp.

[0104] Step 5: Determine the data string of the task according to the control signal, the first data, the second data and the third data.

[0105] In this embodiment, the data string of the task is determined according to the indication signal of the task start and the task execution process, so that the data string can accurately reflect the execution status of the task as time goes by.

[0106] Optionally, the vehicle body system includes a plurality of subsystems, and the plurality of actuators are arranged in different subsystems. The fifth step includes:

[0107] According to the control signal, the corresponding subsystem number is determined; according to the subsystem number, the control signal, the first data, the second data and the third data, the data string of the task is determined.

[0108] In this embodiment, in order to better distinguish each subsystem, a different number is configured for each subsystem. Therefore, according to the control signal, it can be known which numbered subsystem is to be controlled to perform the task, and then the subsystem corresponding to the control number is controlled to perform the task. During fault analysis, the data string includes the subsystem number data, so during fault analysis, the name of the faulty subsystem can be inferred based on the number data.

[0109] Specifically, the subsystem number, the control signal, the first data, the second data and the third data are combined to obtain a data group; and the data string of the task is determined according to the data group.

[0110] Exemplarily, the data group may be a subsystem number+control signal+first data+second data+third data.

[0111] Optionally, the fifth step also includes:

[0112] Arrange the control signal, the first data, the second data and the third data in chronological order to obtain a data string of the task.

[0113] In this embodiment, each data has a corresponding timestamp, that is, the collection time of each data is recorded. As the task is executed, the time indicated by the timestamps of these data becomes later, which also represents that the task is being executed step by step. Therefore, in order to easily analyze the data string, all data are arranged in the order of the time indicated by the timestamps, and the arranged data are combined to obtain a data string, which can reflect the change process of the state of the vehicle body system during the execution of the task.

[0114] Optionally, step S130 includes:

[0115] If the data representing the task execution status signal in the data string indicates that the task execution status is successful, it is determined that the body system has no fault;

[0116] If the data representing the task execution status signal in the data string indicates that the task execution status is execution failure, it is determined that the body system has a fault.

[0117] In this embodiment, the task execution status signal is converted into data in character data format before generating the data string, so the data representing the task execution status signal in the data string will be different due to different task execution states. That is, different task execution status signals in the data string are represented by different character data. Therefore, if the data representing the task execution status signal in the data string indicates that the task execution status is successful, it means that the task is successfully executed, and it is determined that there is no fault in the body system; if the data representing the task execution status signal in the data string indicates that the task execution status is failed, it means that the task execution failed, and it is determined that there is a fault in the body system; if the data representing the task execution status signal in the data string indicates that the task execution status is in execution, it means that the task is still in execution, and the status signal of the next cycle can be continued to be collected; if the data representing the task execution status signal in the data string indicates that the task execution status is interrupted, it means that the task execution process is interrupted by some factors, which may be due to a vehicle system failure or other reasons. At this time, it is necessary to further find the cause; if the data representing the task execution status signal in the data string indicates that the task execution status is waiting for execution, it means that the task has not been completed yet, you can continue to wait, and then obtain the status signal of the next cycle; if the data representing the task execution status signal in the data string indicates that the task execution status does not meet the execution conditions, it means that the task cannot be executed because the conditions are not met, not because of a body system failure.

[0118] In this embodiment, the standard data string for each task when it is successfully executed can be pre-stored, and then the current data string is compared with the standard data string. If the two are consistent, it means that the task is successfully executed without any faults; if the two are inconsistent, it means that the task has failed.

[0119] Optionally, step S140 includes:

[0120] Determine the previous data of the data string indicating the task execution status; and determine the cause of the fault according to the previous data.

[0121] In this embodiment, if the task execution fails, the previous data in the data string representing the task execution status is determined. The previous data is the last step of the task execution, that is, the task execution stopped at this step, so the data corresponding to this step can reflect the reason for the execution failure.

[0122] In this embodiment, data representing the fault state signal of the actuator in the data string can also be determined, and based on the data, it can be determined whether the cause of the execution failure is a fault in the actuator. If the data indicates that the fault state of the actuator is a fault, the fault cause includes the actuator fault; if the data indicates that the fault state of the actuator is normal, the fault cause does not include the actuator fault.

[0123] Exemplarily, the data representing the task execution status signal in the data string of the task of opening the window indicates that the task execution status is successful, which means that the window subsystem has no faults; if it indicates that the execution conditions are not met, and the data representing the fault status signal of the actuator of the window subsystem indicates that the actuator is normal, then the cause of the fault is determined to be that the execution conditions are not met. At this time, it is possible to further analyze what specific conditions are not met, and the causes in the pre-established fault cause library can be referred to during the analysis; if it indicates that the execution failed, and the data preceding the execution failed is the data representing the controller status signal, the data representing the controller status signal indicates that the controller status is waiting for wake-up, and the data representing the fault status signal of the actuator indicates that the actuator is normal, then the cause of the fault can be determined to be that the actuator has not woken up; if the data representing the controller status signal indicates that the controller status is initialized, and the data representing the fault status signal of the actuator indicates that the actuator is normal, then the cause of the fault can be determined to be an actuator initialization failure fault or other corresponding causes in the fault cause library; if the data representing the controller status signal indicates that the controller status is waiting for execution or execution is interrupted, and the data representing the fault status signal of the actuator indicates that the actuator is normal, then the cause of the fault is determined to be a corresponding cause in the fault cause library.

[0124] Among them, the causes in the fault cause library may include message loss and software failure. The fault cause library can be arranged in the fault analysis big model. The fault analysis big model has an automatic training function. When the fault analysis big model performs fault analysis, if a new fault cause is analyzed, the fault analysis big model can be automatically trained according to the data corresponding to the fault cause, so as to obtain a new fault analysis big model. After the new fault analysis big model is verified, the original fault cause library is optimized. When the verification fails after more than 3 automatic trainings, the manual training mode is triggered, and the fault analysis big model is retrained manually.

[0125] In this embodiment, if there is a fault in the vehicle body system, an early warning is issued. For example, an early warning reminder is issued through email / text message / vehicle pop-up screen / vehicle language, etc., which facilitates the understanding of vehicle abnormalities, and after-sales service can better repair and handle the vehicle according to the prompt information, while reducing the workload of R&D personnel in manually analyzing problems.

[0126] The embodiment of the present invention can automatically identify vehicle body faults, locate the cause of the fault efficiently and quickly, reduce the difficulty and workload of fault troubleshooting, optimize the driving experience, and reduce the workload of maintenance personnel. It also provides intelligent prompts and warnings, so that users can take countermeasures according to the cause of the fault.

[0127] Based on the same inventive concept, the embodiment of the present invention also provides a vehicle body fault analysis device based on a large model. Figure 2 is a structural block diagram of a vehicle body fault analysis device based on a large model provided by an embodiment of the present invention, such as Figure 2 As shown, the device 200 includes an acquisition module 201 , a generation module 202 , a judgment module 203 and a determination module 204 .

[0128] The acquisition module 201 is used to acquire a status signal related to the task, as well as a timestamp of the control signal and a timestamp of the status signal if a control signal for controlling the body system to execute a task is received. The status signal includes an actuator status signal of the body system, a controller status signal, and a task execution status signal;

[0129] A generating module 202, for generating a data string of a task according to a control signal, a state signal and a corresponding timestamp;

[0130] A judgment module 203 is used to judge whether the vehicle body system has a fault according to the data string;

[0131] The determination module 204 is used to determine the cause of the fault according to the data string if there is a fault in the vehicle body system.

[0132] In this embodiment, the device 200 includes a pre-built fault analysis big model 205, and then the generation module 202, the judgment module 203 and the determination module 204 are all arranged in the fault analysis big model 205. The control signal, the status signal and the corresponding timestamp are analyzed by the fault analysis big model 205, and finally the analysis result is output. If there is a fault, the cause of the fault is also output.

[0133] Figure 3 is a structural block diagram of a large fault analysis model provided by an embodiment of the present invention, such as Figure 3As shown, the fault analysis model 205 may include a fault cause library 2051, a fault handling module 2052, a training module 2053 and a verification module 2054. The fault cause library 2051 stores common reasons for the failure of each task execution; the fault handling module 2052 is used to give reasonable handling opinions according to the fault cause; the training module 2053 is used to automatically train the original fault analysis model to obtain a new fault analysis model. For example, when a new fault cause is analyzed, the fault analysis model can be automatically trained according to the data corresponding to the fault cause through the training model 2053 to obtain a new fault analysis model; the verification module 2054 is used to verify the new fault analysis model. After the verification is passed, the new fault analysis model is used for fault analysis and the original fault cause library is optimized. When the verification fails after more than 3 automatic trainings, the manual training mode is triggered, and the original fault analysis model is retrained manually.

[0134] In this embodiment, the device 200 further includes an early warning module, which is used to issue an early warning when a fault occurs. The early warning module and the fault analysis model can be arranged on a cloud platform.

[0135] Optionally, the vehicle body system includes multiple actuators, and the generating module 202 includes:

[0136] A first determining unit, used to determine an actuator number, a controller number and a control source number corresponding to a control signal;

[0137] A second determining unit, configured to determine the first data according to the execution part number, the execution part state signal and the corresponding timestamp;

[0138] a third determining unit, configured to determine second data according to the controller number, the controller state signal and the corresponding timestamp;

[0139] a fourth determining unit, configured to determine third data according to the control source number, the task execution state signal and the corresponding timestamp;

[0140] The fifth determining unit is used to determine the data string of the task according to the control signal, the first data, the second data and the third data.

[0141] Optionally, Unit 5 is also used to:

[0142] Arrange the control signal, the first data, the second data and the third data in chronological order to obtain a data string of the task.

[0143] Optionally, the vehicle body system includes a plurality of subsystems, and the plurality of actuators are arranged in different subsystems, and the fifth unit is further used for:

[0144] According to the control signal, determine the corresponding subsystem number;

[0145] A data string of the task is determined according to the subsystem number, the control signal, the first data, the second data and the third data.

[0146] Optionally, the fourth determining unit is further configured to:

[0147] Get the vehicle's power mode;

[0148] The third data is determined according to the power mode, the control source number, the task execution status signal and the corresponding timestamp.

[0149] Optionally, the determination module 204 is further configured to:

[0150] Determine the previous data of the data string representing the task execution status;

[0151] Determine the cause of the failure based on the previous data.

[0152] Optionally, the determination module 203 is further configured to:

[0153] If the data representing the task execution status signal in the data string indicates that the task execution status is successful, it is determined that the body system has no fault;

[0154] If the data representing the task execution status signal in the data string indicates that the task execution status is execution failure, it is determined that the body system has a fault.

[0155] It can be understood that the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0156] An embodiment of the present invention further provides an electronic device, which may include a processor and a memory, wherein the processor and the memory may be communicatively connected to each other via a bus or other means.

[0157] The processor may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application, or may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components and other chips, or a combination of the above-mentioned chips.

[0158] The memory may include a large capacity memory for data or instructions. By way of example and not limitation, the memory may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory may include a removable or non-removable (or fixed) medium. Where appropriate, the memory may be inside or outside the electronic device. In a particular embodiment, the memory may be a non-volatile solid-state memory.

[0159] In one example, the memory may be a read-only memory (ROM). In one example, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0160] The processor implements any one of the large-model-based vehicle body fault analysis methods in the above-mentioned embodiments by reading and executing computer program instructions stored in the memory.

[0161] In one example, the electronic device may further include a communication interface and a bus. Among them, the processor, memory, and communication interface are connected through a bus and communicate with each other. The communication interface is mainly used to realize the communication between the modules, devices, units and / or devices in the embodiment of the present application. Where appropriate, the bus may include one or more buses.

[0162] In addition, in combination with the large model-based vehicle body fault analysis method in the above embodiments, the present invention can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any of the large model-based vehicle body fault analysis methods in the above embodiments is implemented.

[0163] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0164] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0165] The embodiment of the present invention provides a method, device, equipment and medium for analyzing vehicle body faults based on a large model. If a control signal for controlling the vehicle body system to execute a task is received, indicating that the vehicle body system task needs to be executed, then a status signal related to the task, as well as a timestamp of the control signal and a timestamp of the status signal are obtained. The status signal includes an actuator status signal of the vehicle body system, a controller status signal and a task execution status signal. The status signal reflects the execution of the task; a data string of the task is generated according to the control signal, the status signal and the corresponding timestamp, and the data related to the task execution are formed into a data string; according to the data string, it is determined whether the vehicle body system has a fault. The data string can reflect the status of each step in the task execution process, so it can reflect whether the task execution is successful, and whether the vehicle body system has a fault; if the vehicle body system has a fault, the cause of the fault is determined according to the data string. The data string contains all relevant data in the task execution process, so the cause of the fault can be located according to these data. This method is more timely in analyzing vehicle body faults, and can more accurately determine whether there is a fault and the cause of the fault.

[0166] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0167] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0168] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "one" or "an" preceding a component does not exclude the presence of a plurality of such components. The present invention may be implemented by means of hardware comprising a number of different components and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

Claims

1. A vehicle body fault analysis method based on a large model, characterized in that: The method comprises: If a control signal for controlling the vehicle body system to execute a task is received, a status signal related to the task, as well as a timestamp of the control signal and a timestamp of the status signal are acquired, wherein the status signal includes an actuator status signal, a controller status signal and a task execution status signal of the vehicle body system; generating a data string of the task according to the control signal, the state signal and the corresponding timestamp; determining whether the vehicle body system has a fault according to the data string; If the vehicle body system has a fault, the cause of the fault is determined based on the data string.

2. The large model-based vehicle body fault analysis method according to claim 1, characterized in that: The step of generating a data string of the task according to the control signal, the state signal and the corresponding timestamp comprises: Determine the actuator number, controller number and control source number corresponding to the control signal; Determine first data according to the execution component number, the execution component status signal and the corresponding timestamp; Determining second data according to the controller number, the controller status signal and the corresponding timestamp; Determine third data according to the control source number, the task execution status signal and the corresponding timestamp; A data string of the task is determined according to the control signal, the first data, the second data, and the third data.

3. The large model-based vehicle body fault analysis method according to claim 2, characterized in that: Determining the data string of the task according to the control signal, the first data, the second data and the third data comprises: The control signal, the first data, the second data and the third data are arranged in chronological order to obtain a data string for the task.

4. The large model-based vehicle body fault analysis method according to claim 2, characterized in that: The vehicle body system includes a plurality of subsystems, and the data string of the task is determined according to the control signal, the first data, the second data and the third data, and further includes: Determine the corresponding subsystem number according to the control signal; A data string of the task is determined according to the subsystem number, the control signal, the first data, the second data, and the third data.

5. The large model-based vehicle body fault analysis method according to claim 2, characterized in that: The determining of the third data according to the control source number, the task execution status signal and the corresponding timestamp includes: Get the vehicle's power mode; The third data is determined according to the power mode, the control source number, the task execution status signal and the corresponding timestamp.

6. The large model-based vehicle body fault analysis method according to claim 1, characterized in that: Determining the cause of the fault according to the data string includes: Determine the previous data of the data string representing the task execution status; The cause of the fault is determined according to the previous data.

7. The large model-based vehicle body fault analysis method according to claim 1, characterized in that: The step of determining whether the vehicle body system has a fault according to the data string includes: If the data representing the task execution status signal in the data string indicates that the task execution status is successful, it is determined that the vehicle body system has no fault; If the data representing the task execution status signal in the data string indicates that the task execution status is execution failure, it is determined that the body system has a fault.

8. A vehicle body fault analysis device based on a large model, characterized in that: The device comprises: an acquisition module, configured to acquire a status signal related to the task, as well as a timestamp of the control signal and a timestamp of the status signal if a control signal for controlling the vehicle body system to execute a task is received, wherein the status signal includes an actuator status signal, a controller status signal and a task execution status signal of the vehicle body system; A generating module, used for generating a data string of the task according to the control signal, the state signal and the corresponding timestamp; A judgment module, used for judging whether the vehicle body system has a fault according to the data string; A determination module is used to determine the cause of the fault according to the data string if the body system has a fault.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 7.

Images