Vehicle fault diagnosis method and device and computer program product

Abstract

The invention discloses a vehicle fault diagnosis method and device and a computer program product, and the method comprises the steps: configuring a state variable according to a selected bus message and a selected bus signal, constructing a signal and message event processing logic based on the state variable, and obtaining a decision script; and calling the decision script to execute decision analysis on the extracted bus message and the bus signal according to a fault vehicle and a fault occurrence time period, triggering to execute the signal and message event processing logic when detecting that the bus message or the bus signal jumps, and outputting a diagnosis result. According to the method, based on decision analysis of an event mechanism, bus messages and signals are regarded as event streams, event decision analysis is triggered only during jumping, the number of jumping times of vehicle end signals is small, and analysis time is greatly shortened; in the aspect of resource consumption, messages / signals do not need to be aligned, each message / signal independently triggers an event at a jump edge, a state variable automatically memorizes a current value, and memory consumption and alignment time are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent connected vehicles, and particularly relates to a vehicle fault diagnosis method, device and computer program product. Background Art

[0002] With the development of vehicle networking technology, a vehicle remote diagnosis system based on a cloud platform has realized the cloud storage and intelligent analysis of vehicle bus data and diagnostic messages. Through semi-automated / automated means such as time series visualization, log feature parsing, and decision tree algorithms, the positioning efficiency of vehicle electrical faults has been significantly improved. Among them, as a mainstream technical solution, the construction method of the multi-layer decision tree model based on configuration rules includes the following technical features:

[0003] 1. Basic rule construction: Establish atomic judgment rules based on bus signal values (including numerical relationships such as equal to / not equal to / greater than / less than / jump, etc.) and diagnostic parameter parsing rules (numerical matching relationships for specific Byte / Bit positions)

[0004] 2. Composite condition generation: Combine atomic rules through logical operators (AND / OR / NOT) to form complex judgment conditions;

[0005] 3. Tree structure construction: Establish a multi-layer decision-making process using a node-edge architecture. Each decision node is configured with a rule filtering condition, and the decision path is transferred through edge connection;

[0006] 4. Dynamic decision-making process: Data flows through the upper-layer node rule filtering and enters the lower-layer node, and finally reaches the leaf node containing the fault cause and repair suggestion;

[0007] 5. Time-series data processing: The execution process includes key steps such as bus signal extraction, multi-cycle signal timestamp alignment (the minimum alignment granularity reaches the millisecond level), and hierarchical filtering analysis.

[0008] This model has the following technical defects in practical applications:

[0009] (1) Limited applicable scenarios: All configuration rules are obtained by configuring the rules in the rule library and forming combined configuration rules through AND / OR / NOT. Rules beyond the configuration rule library cannot be configured, so it is difficult to implement decision-making analysis for complex scenarios.

[0010] (2) High redundancy of decision logic for complex scenarios: Due to the limitation of the tree structure of the decision tree, branches are not allowed to cross. When implementing complex logical jumps, the entire branch needs to be copied for reuse, resulting in a large redundancy of decision logic and difficult maintenance.

[0011] (3) Stateless memory, unable to simulate the vehicle-end state machine: The decision tree makes decisions layer by layer, and the decision analysis at the next moment does not depend on the data at the previous moment. It is difficult to analyze abnormal scenarios with dependencies between the front and back in the bus signal flow. These similar scenarios are difficult to cover using decision tree rules.

[0012] (4) High memory consumption: When performing decision analysis, it is necessary to align all signal timestamps used, consuming a large amount of memory.

[0013] (5) Long analysis time: When performing decision analysis, the aligned signal values are injected one by one in each decision rule to implement the judgment of combined conditions. After meeting the conditions, it enters the next layer. For the multi-layer decision analysis of complex problems, the time is usually up to dozens of minutes or even several hours, resulting in poor user experience.

[0014] In the context of the continuous improvement of the intelligence level of new energy vehicles, the above technical defects seriously restrict the application efficiency of the remote diagnosis system in complex electrical fault scenarios. Summary of the Invention

[0015] The technical problem to be solved by the embodiments of the present invention is to provide a vehicle fault diagnosis method, device and computer program product to shorten the fault analysis time.

[0016] To solve the above technical problem, the present invention provides a vehicle fault diagnosis method, including the following steps:

[0017] Configure state variables according to the selected bus messages and bus signals, and construct signal and message event processing logic based on the state variables to obtain a decision script;

[0018] According to the faulty vehicle and the time period when the fault occurs, call the decision script to perform decision analysis on the extracted bus messages and bus signals, and trigger the execution of the signal and message event processing logic when a jump in the bus message or bus signal is detected, and output a diagnosis result.

[0019] Preferably, the configuring state variables according to the selected bus messages and bus signals specifically includes:

[0020] Configure state variables to memorize message and signal timestamps, message and signal values, and system state values.

[0021] Preferably, the constructing signal and message event processing logic based on the state variables specifically includes:

[0022] Write logic code in the message and signal events, and the logic code includes:

[0023] Memorize and update the timestamp triggered by the current message and signal event;

[0024] Remember and update the latest value of the signals in the current message and the signal event message;

[0025] Retrieve the timestamp and signal value of the message signal event of the previous event;

[0026] Calculate the time difference between the current message and signal event and the previous event;

[0027] Perform calculations and judgments by combining the status variables of the current event and the variable values of the previous event, and update the status variables. If it is determined that the vehicle has a fault, print the cause of the fault and repair suggestions.

[0028] Preferably, when constructing the signal and message event processing logic based on the status variables, if there is a common decision logic, abstract it into a common function. In the signal and message events, when it is determined that the condition for entering the execution of the common function is met, call the common function.

[0029] Preferably, triggering the execution of the signal and message event processing logic when detecting a jump in the bus message or bus signal specifically includes:

[0030] Initialize the status variables used in the decision script;

[0031] Judge the transition edge of each signal and message, and record the transition moment;

[0032] At the transition moment of each signal and message, trigger the corresponding signal and message event, and execute the logic of the signal and message event, including updating the signal and message timestamps, updating the signal and variable values, retrieving the previous moment timestamp and signal value, performing calculations and judgments on the signal, and printing the cause of the fault and repair suggestions.

[0033] Preferably, after obtaining the decision script, it further includes:

[0034] Release the decision script to the cloud platform, and perform syntax checking and compilation on the decision script on the cloud platform;

[0035] Test the decision script that passes the compilation;

[0036] Publish the decision script that passes the test to the cloud platform and enable it.

[0037] Preferably, after outputting the diagnostic result, it further includes:

[0038] Optimize the decision script based on the matching degree score between the diagnostic result and the actual fault.

[0039] The present invention also provides a vehicle fault diagnosis device, including:

[0040] A decision script construction module, configured to configure state variables according to selected bus messages and bus signals, and construct signal and message event processing logic based on the state variables to obtain a decision script;

[0041] A fault diagnosis module, configured to call the decision script to perform decision analysis on the extracted bus messages and bus signals according to the faulty vehicle and the time period when the fault occurs, trigger the execution of the signal and message event processing logic when a jump in the bus message or bus signal is detected, and output a diagnosis result.

[0042] The present invention also provides a vehicle fault diagnosis device, including:

[0043] One or more processors;

[0044] A memory;

[0045] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to execute the vehicle fault diagnosis method described above.

[0046] The present invention also provides a computer program product, including computer instructions, and the computer instructions instruct a computer device to perform the operations corresponding to the method.

[0047] Implementing the present invention has the following beneficial effects: Based on the decision analysis of the event mechanism, in terms of analysis efficiency, the bus messages and signals are regarded as an event stream, and the event decision analysis is only triggered at the jump, and the number of signal jumps at the vehicle end is small, greatly shortening the analysis time; in terms of resource consumption, there is no need to align the messages / signals, each message / signal triggers an event separately at the jump edge, and the state variable automatically remembers the current value, greatly reducing the memory consumption and alignment time during combined judgment; in terms of fault judgment, the state variable is used to implement state memory and simulate the vehicle end state machine, solving the problem that the traditional decision tree cannot accurately judge faults when there is a dependency between the front and rear states; in terms of function expansion, it supports signal combination calculation and branch jump, meets the requirements of complex decision judgment, and also effectively solves the problem of logical redundancy by defining common functions, comprehensively improving the performance and efficiency of vehicle fault diagnosis. Description of the Drawings

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0049] Figure 1It is a schematic flowchart of a method for optimizing vehicle fault diagnosis according to Embodiment 1 of the present invention.

[0050] Figure 2 It is a specific flowchart of a vehicle fault diagnosis method according to Embodiment 1 of the present invention.

[0051] Figure 3 It is a schematic diagram of a vehicle speed locking failure state machine exemplified in the embodiment of the present invention.

[0052] Figure 4 It is a schematic flowchart of diagnosing vehicle speed locking failure by using the vehicle fault diagnosis method according to the embodiment of the present invention. Detailed implementation manners

[0053] The descriptions of the following embodiments refer to the accompanying drawings to exemplify specific embodiments in which the present invention can be implemented.

[0054] Please refer to Figure 1 As shown, Embodiment 1 of the present invention provides a vehicle fault diagnosis method, including the following steps:

[0055] Configure state variables according to the selected bus messages and bus signals, and construct signal and message event processing logic based on the state variables to obtain a decision script;

[0056] According to the faulty vehicle and the time period when the fault occurs, call the decision script to perform decision analysis on the extracted bus messages and bus signals, trigger the execution of the signal and message event processing logic when a jump in the bus message or bus signal is detected, and output a diagnosis result.

[0057] From the above steps, it can be seen that in the embodiment of the present invention, by configuring state variables, the complex calculation of aligning multi-source time-series data in the traditional method is dynamically avoided, improving the data processing efficiency; the jump trigger mechanism is used to replace periodic polling, reducing the consumption of invalid computing resources and achieving real-time response, significantly improving the accuracy of vehicle fault diagnosis and the utilization rate of system resources.

[0058] Specifically, please also refer to Figure 2 As shown, the embodiment of the present invention first constructs a decision script, mainly including the following processes:

[0059] Select the bus signals and bus messages required for decision analysis;

[0060] Configure state variables for storing the timestamps and values of the bus messages and bus signals, and system status values;

[0061] Construct signal and message event processing logic based on the state variables.

[0062] Among them, by configuring custom status variables to record timestamps, signal values, and system status values in real time, a dynamic data storage framework is constructed, replacing the complex time-series synchronization logic required for traditional multi-source data alignment. Data fusion is directly achieved through the time-series correlation between variables, providing a structured data foundation for subsequent event triggering and calculation.

[0063] Constructing the signal and message event processing logic based on the status variables specifically includes the following aspects:

[0064] (1) Storing and updating the timestamps triggered by the current message and signal events: Each time a message and signal event is triggered, the system records the time point when the event occurs and updates the timestamp information to track the order and time interval of event occurrences, providing data support in the time dimension for subsequent analysis. For example, by recording the timestamps of a series of fault-related events, the sequence of fault occurrences and the time interval pattern between events can be analyzed, thus assisting in judging the process and cause of fault generation.

[0065] (2) Storing and updating the latest values of the signals of the current message and signal events: Similarly, whenever a new message or signal event occurs, the signal values carried by these events are updated and saved. These signal values may represent various state information of the vehicle, such as speed, temperature, pressure, etc. The changes in vehicle bus signals often reflect the operating states of various vehicle components. For example, a sudden change in the signal value of a certain sensor may indicate an abnormality in the corresponding component. By continuously recording the latest values, these changes can be captured in a timely manner.

[0066] (3) Retrieving the timestamps and signal values of the previous message or signal event: To compare and analyze the changes and trends between events, it is necessary to be able to access the timestamps and signal values of the previous message or signal event. For example, by comparing the signal values of two consecutive events, it can be determined whether the signal changes gradually or suddenly.

[0067] (4) Calculating the time difference between the current message and signal event and the previous event: By calculating the time difference between the current event and the previous event, the frequency and rhythm of signal changes can be understood. When different vehicle components are operating normally, their signal changes usually have a certain time pattern. For example, the change frequency and time interval of the engine speed signal are relatively stable during normal driving. If the calculated time difference does not match the normal situation, it may indicate that there is a fault in the vehicle.

[0068] (5) Calculate and make judgments by combining the state variables of the current event and the state variables of the previous event, and update the state variables: Combine the state variables of the current event and the state variables of the previous event for calculation and judgment. As mentioned above, the state variables record the signal and message event timestamps, signal values, and system state values in real time. By making logical judgments based on the parameters recorded in the combined state variables, it is possible to determine whether a vehicle failure has occurred. Once a failure is determined, the cause of the failure and repair suggestions will be printed to provide clear fault diagnosis information and solutions for maintenance personnel.

[0069] It should be noted that the parameters involved in the above processing logic include: the signal names used in the fault decision conditions, the signal change times, the fault occurrence discrimination conditions, and the fault information output content, which are described separately below:

[0070] The signal names used in the fault decision conditions are specifically the specific bus signal identifiers involved in fault judgment (such as "BMS_BatteryVoltage"), which mainly focus the diagnostic logic on key parameters and avoid interference from irrelevant signals (for example, only monitoring temperature signals related to overheating faults), thereby improving the judgment efficiency.

[0071] The signal change time is used to record the timestamp when the signal value changes, to judge the timeliness of the signal change. By combining the time difference and the signal value change (such as the temperature rising suddenly by 10°C within 2 seconds), it is possible to identify abnormal mutations (such as the cooling system failure), and solve the problem of missed / misjudgment caused by the fixed time window in traditional methods (for example, periodic polling may miss instantaneous abnormalities).

[0072] The fault occurrence discrimination conditions include the judgment types (i.e., equal to, not equal to, less than, less than or equal to, greater than, greater than or equal to, contains, does not contain, similar to, not similar to, etc.) and the corresponding judgment standard values. The judgment types are used to define the logical relationship between the signal values and the system states, such as "the battery voltage is less than 11.5V" or "the engine speed has been greater than the red line threshold for 5 seconds". The judgment standard values include dynamic thresholds (such as the temperature threshold is adaptively adjusted according to the ambient temperature), or static thresholds (such as the lower limit of the safety voltage). By combining the judgment types and the standard values, multi-dimensional condition nesting can also be supported (for example, "temperature > 100°C and the fan speed = 0"), making the diagnostic rules flexible and adaptable to scenarios, and directly solving the problem of high false alarm rate of traditional fixed rules (such as a single threshold).

[0073] The specific content of the fault information output includes: Fault location: Locate the faulty component (such as "ECU module A - cooling circuit") and map it to the vehicle's electronic architecture; Fault cause: The root cause deduced based on state variables (such as "coolant pump not started"); Repair suggestion: Repair guidance associated with the knowledge base (such as "check fuse F23 or replace the water pump"). Finally, a closed-loop diagnosis - repair link is formed to reduce the manual troubleshooting time through accurate information output.

[0074] In addition, it can be understood that during the initialization process, initialization assignment operations are performed on all state variables to be used to ensure that each variable has an initial and definite state before the start of the diagnostic process. For example, some system state variables may be set to the vehicle's default state during initialization, the timestamp variable may be initialized to a certain starting time point, and the signal value variable may be initialized to the initial reading or default value of the corresponding sensor.

[0075] In the embodiment of the present invention, by constructing a programmable decision script, the state management, event triggering, and diagnostic logic are decoupled, while improving the data processing efficiency, realizing the collaborative optimization of resource consumption, real-time performance, and diagnostic accuracy.

[0076] It should also be noted that during the process of constructing the decision script above, if some decision logics repeatedly appear in different signal and message events, for example, the logic for validating the effectiveness of a certain type of sensor signal may be required in the processing of multiple different signal and message events. To avoid repeatedly writing the same code and improve the development efficiency, the embodiment of the present invention extracts these common decision logics and encapsulates them into an independent common function. In this way, when this part of the common decision logic needs to be modified, only one modification needs to be made in the common function, and all places where the common function is called will automatically apply the modified logic, without having to modify each code segment using this logic one by one, thereby reducing the maintenance cost and improving the consistency and reliability of the code.

[0077] Meanwhile, when constructing the signal and message event processing logic, specific conditions will be set. When the running state of a certain signal and message event meets these pre-set conditions for entering the execution of the common function, the previously abstracted common function will be called. For example, in the message event of processing the engine speed signal, when it is detected that the engine speed exceeds a certain normal range and the vehicle is in a specific driving mode (i.e., the set specific conditions), the common function for further analyzing the engine abnormality is called. This common function contains more complex calculation and judgment logics, which can further determine the specific reason for the engine speed abnormality, such as whether it is a sensor failure, an oil circuit problem, or other mechanical failures, etc.

[0078] After the decision-making script is constructed, it also needs to go through processes such as uploading, checking, testing, and releasing to ensure the quality and usability of the script.

[0079] After the decision-making script is uploaded to the cloud platform, the cloud platform performs syntax checking and compilation on the decision-making script. If problems are found during the compilation process, such as missing dependency libraries or incorrect function definitions, the compilation will not pass. At this time, the cloud platform will feedback the compilation error information to the script editing end. According to these error messages, the script editing end re-edits and modifies the decision-making script, and after correcting the errors, releases it to the cloud platform again for syntax checking and compilation until the compilation passes.

[0080] After that, the script testing end tests the decision-making script, aiming to verify whether the functions of the script in the actual application scenario are correct and whether the expected fault diagnosis effect can be achieved. If problems are found in the script during the testing process, such as inaccurate judgment results or incorrect output information, the script testing end will feedback the problems to the script editing end. The script editing end re-edits the script according to the feedback information and modifies the logical errors or imperfections in it. After the modification is completed, the script is released to the cloud platform again, repeating the previous syntax checking, compilation, and testing processes until the testing passes.

[0081] When the decision-making script passes all processes such as syntax checking, compilation, and testing, it is officially released to the cloud platform through the script release end. The released decision-making script will be enabled on the cloud platform. By selecting the corresponding decision-making script on the operation interface of the cloud platform through the maintenance diagnosis end, fault diagnosis and analysis are carried out for the faulty vehicle. At this time, the decision-making script is ready to receive the bus data of the vehicle and processes it according to the preset signal and message event processing logic, providing fault diagnosis results and maintenance suggestions for the maintenance personnel to help the maintenance personnel carry out vehicle maintenance work more efficiently.

[0082] When facing a faulty vehicle, the maintenance personnel first need to identify the specific faulty vehicle, determine the time period when the fault occurred, and associate the corresponding decision-making script. This can limit the diagnosis scope, ensure that the analysis data matches the fault scenario, and avoid wasting resources in processing all data.

[0083] Then the cloud platform retrieves the bus data and performs decision analysis, which specifically includes the following steps:

[0084] (1) Initialize state variables: The cloud platform extracts the original bus messages and signal data (such as CAN / LIN messages) during the fault time period from the database and assigns initial values to the state variables (such as timestamp, signal value, system status value) according to the definition of the decision-making script (for example, initial temperature = 25°C).

[0085] (2) Determine the signal and message transition edges and record the time: Real-time parse the bus data stream, detect the transition edges (rising edge / falling edge) of the signal value or message, and record the time when the transition occurs (such as the timestamp when the vehicle speed jumps from 0 to 20 km / h). By determining the transition edges of the signal and message, key state change points can be captured. Recording these transition times facilitates subsequent analysis of the signal change sequence, frequency, and the association with other signal changes.

[0086] (3) Trigger the execution of the signal and message event handling logic: At each signal and message transition time, the corresponding signal and message event handling logic is triggered for execution, that is, perform operations according to the pre-written logic, including: storing and updating the timestamp triggered by the current message and signal event, storing and updating the latest value of the signal of the current message and signal event, retrieving the timestamp and signal value of the previous event's message or signal event, calculating the time difference between the current message and signal event and the previous event, calculating and judging by combining the state variables of the current event and the previous event, and updating the state variables, etc.

[0087] Meanwhile, if there is common decision-making logic (abstracted as a common function), call these common functions when the conditions are met to avoid logical redundancy.

[0088] As a further improvement of the embodiment of the present invention, after outputting the diagnostic result, the decision-making script is further optimized based on the matching degree score between the diagnostic result and the actual fault. After the maintenance diagnosis terminal views the fault cause and maintenance suggestions printed by the decision-making script, combined with the actual vehicle's real fault situation, the accuracy of the conclusion obtained by the decision-making script is scored. Through scoring, possible deviations or inaccuracies in the decision-making script during the diagnostic process can be found.

[0089] Finally, collect the scores given by the maintenance diagnosis terminal and analyze these score data. If it is found that the score is low, it indicates that there may be some problems with the decision-making script, such as imperfect diagnostic logic, insufficient consideration of certain fault scenarios, etc. Based on these analysis results, update and optimize the logic of the decision-making script at the script editing end. This is an iterative process. Through continuous optimization, the decision-making script can diagnose vehicle faults more accurately and improve the performance and reliability of the entire diagnostic system.

[0090] The vehicle fault diagnosis method applying the embodiment of the present invention will be further introduced below by taking the decision analysis of vehicle speed locking failure as an example.

[0091] As Figure 3 shown, the decision analysis of vehicle speed locking failure uses 2 bus signals:

[0092] The bus signal SpeedLockEnable indicates whether the vehicle speed locking function is enabled on the host. It can take the values Disable and Enable, representing the disabled and enabled vehicle speed locking functions respectively;

[0093] The bus signal Bcs_VehSpd represents the vehicle speed.

[0094] The state machine has three states: the initial state Init, representing the state when the vehicle has just started; the Standby state, representing that the user has activated the vehicle speed locking function, but the vehicle speed has not reached 20 km / h and the vehicle locking state has not been triggered; the Active state, representing that the user has activated the vehicle speed locking and the vehicle speed is greater than or equal to 20 km / h, triggering the vehicle's automatic door locking state.

[0095] Configure the following state variables to record the signal update time, the updated signal value, and the current state of the system:

[0096] Sig_SpeedLockEnable: Represents the latest value of the bus signal SpeedLockEnable;

[0097] Sig_Bcs_VehSpd: Represents the latest value of the bus signal Bcs_VehSpd;

[0098] State: Represents the system state, which can take three values: Init, Standby, Active;

[0099] T_SpeedLockEnable: Represents the current update time of the bus signal SpeedLockEnable;

[0100] T_Bcs_VehSpd: Represents the current update time of the bus signal Bcs_VehSpd.

[0101] Again Figure 4 As shown, the decision analysis process for the failure of the vehicle speed lock is as follows, including initialization, signal judgment, event handling, and state update:

[0102] (1) Initialization phase:

[0103] Initialize Sig_SpeedLockEnable to Disable, indicating that the vehicle speed locking function is disabled in the initial state;

[0104] Initialize Sig_Bcs_VehSpd to 0, that is, the initial vehicle speed is 0;

[0105] Initialize T_SpeedLockEnable to 0 to record the initial update time of the vehicle speed locking function signal;

[0106] Initialize T_Bcs_VehSpd to 0 and record the initial update time of the vehicle speed signal;

[0107] Initialize State to Init, indicating that the vehicle is in the initial state when it just starts.

[0108] (2) Signal edge confirmation stage

[0109] Respectively confirm the edges of the two bus signals SpeedLockEnable and Bcs_VehSpd:

[0110] First, judge whether the edge of Bcs_VehSpd is reached (that is, whether the vehicle speed has changed). If not (the vehicle speed has not changed), then continue to judge whether the edge of SpeedLockEnable is reached (that is, whether the vehicle speed locking function has an enable or disable operation).

[0111] If the edges of SpeedLockEnable and Bcs_VehSpd are respectively reached, enter the corresponding signal change event handling stage respectively. If neither of the two signals reaches the edge, replay the next edge signal, and then make the above judgment again. If the replay of all signals ends, the decision analysis ends.

[0112] (3) Signal change event handling stage

[0113] Signal Bcs_VehSpd change event: When the signal Bcs_VehSpd changes, set Sig_Bcs_VehSpd to the current vehicle speed, and at the same time set T_Bcs_VehSpd to the current update time, recording the time of the vehicle speed change and the new vehicle speed value.

[0114] Signal SpeedLockEnable change event: When the signal SpeedLockEnable changes, set Sig_SpeedLockEnable to the current vehicle speed locking configuration value (Enable or Disable), set T_SpeedLockEnable to the current update time, recording the time of the vehicle speed locking function state change and the new state value.

[0115] (4) Update state variable stage

[0116] First, judge whether Sig_SpeedLockEnable is Disable. If so, update the system state State to Init, and print the relevant current update times T_Bcs_VehSpd and T_SpeedLockEnable, and the process ends.

[0117] If Sig_SpeedLockEnable is not "Disable", then continue to determine whether the state State is "Init":

[0118] If it is "Init", then further determine whether Sig_SpeedLockEnable is "Enable" and whether Sig_Bcs_VehSpd is less than 20 (i.e., whether the vehicle speed is less than 20 km / h). If so, update the system state State to "Standby", and print the relevant current update times T_Bcs_VehSpd and T_SpeedLockEnable, and the process ends. If not, then directly end.

[0119] If it is not "Init", first determine whether it is "Standby": If so, then further determine whether Sig_Bcs_VehSpd is greater than or equal to 20 (i.e., whether the vehicle speed is higher than or equal to 20 km / h). If so, update the system state State to "Active", and print the relevant current update times T_Bcs_VehSpd and T_SpeedLockEnable; if Sig_Bcs_VehSpd is not greater than or equal to 20 (i.e., less than 20), then directly end. If the system state is not "Standby", then determine whether it is "Active". If so, further determine whether Sig_Bcs_VehSpd is less than 20 (i.e., whether the vehicle speed is less than 20 km / h). If so, update the system state State to "Standby", and print the relevant current update times T_Bcs_VehSpd and T_SpeedLockEnable; if Sig_Bcs_VehSpd is not less than 20 (i.e., greater than or equal to 20), then directly end; if the state is not "Active", also directly end.

[0120] From the above process, it can be seen that according to the vehicle fault diagnosis method of the embodiment of the present invention, the system state can be updated in real time according to the vehicle speed and the state change of the vehicle speed locking function, and it can be determined whether the vehicle speed locking function works properly, so as to realize the decision-making analysis of the vehicle speed locking failure.

[0121] According to the foregoing description of the specific embodiments of the present invention, the embodiments of the present invention regard bus messages and signals as event streams, and only trigger corresponding message / signal events for decision-making analysis when the messages / signals change. Since vehicle-end bus signals are generally regular message / signal event streams, and the number of message / signal transitions is much smaller than the total number of messages / signals, the total number of times that need to be analyzed for decision-making in the embodiments of the present invention is much smaller than that of traditional decision tree decision-making, and the analysis time is reduced from dozens of minutes to several hours to seconds to minutes. Moreover, for decision-making analysis, it is not necessary to align the messages / signals. Each message / signal triggers a corresponding event separately at its own transition edge, greatly reducing the memory and time required for signal alignment. Second, in the message and signal events, the time stamps of the trigger moments and the message values and signal values at the trigger moments are memorized for the next judgment. In the next message and signal events, the time difference between the current event and the previous message and signal event trigger can be calculated, and the signal values at the previous moment and the current moment are used for combined judgment to update the system state variables, realizing state memory and state jump, so as to simulate the vehicle-end functional logic. Third, public functions are defined in the message and signal events, and the decision-making logic is reused by defining public functions, avoiding logical redundancy.

[0122] Corresponding to the vehicle fault diagnosis method described in the first embodiment of the present invention, the second embodiment of the present invention further provides a vehicle fault diagnosis device, including:

[0123] A decision script construction module, configured to configure state variables according to selected bus messages and bus signals, and construct signal and message event processing logic based on the state variables to obtain a decision script;

[0124] A fault diagnosis module, configured to call the decision script to perform decision-making analysis on the extracted bus messages and bus signals according to the faulty vehicle and the time period when the fault occurs, trigger the execution of the signal and message event processing logic when it detects that a bus message or bus signal changes, and output a diagnosis result.

[0125] Corresponding to the vehicle fault diagnosis method described in the first embodiment of the present invention, the third embodiment of the present invention further provides a vehicle fault diagnosis device, including:

[0126] One or more processors;

[0127] A memory;

[0128] One or more applications, wherein the one or more applications are stored in the memory and are configured to be executed by the one or more processors, and the one or more applications are configured to execute the vehicle fault diagnosis method described in the first embodiment of the present invention.

[0129] Corresponding to the vehicle fault diagnosis method described in the first embodiment of the present invention, the fourth embodiment of the present invention further provides a computer program product, including computer instructions, and the computer instructions direct a computer device to perform operations corresponding to the vehicle fault diagnosis method described in the first embodiment of the present invention.

[0130] Preferably, the processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor. The processor is the control center of the device and connects various parts of the device through various interfaces and lines.

[0131] The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function, etc., and the data storage area can store relevant data, etc. In addition, the memory may be a high-speed random access memory, or may also be a non-volatile memory, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., or the memory may also be other volatile solid-state storage devices.

[0132] It should be noted that the above device may include but is not limited to a processor and a memory, which can be understood by those skilled in the art.

[0133] Regarding the working principle and process of the above embodiments, refer to the description of the first embodiment of the present invention, which will not be elaborated here.

[0134] As can be seen from the above description, compared with the prior art, the beneficial effects of the present invention are as follows: Based on the event mechanism for decision analysis, in terms of analysis efficiency, the bus messages and signals are regarded as event streams, and event decision analysis is only triggered at the jump. The number of signal jumps at the vehicle end is small, greatly shortening the analysis time. In terms of resource consumption, there is no need to align messages / signals. Each message / signal triggers an event independently at the jump edge, and the state variables automatically remember the current value, greatly reducing memory consumption and alignment time during combined judgment. In terms of fault judgment, state variables are used to implement state memory and simulate the vehicle end state machine, solving the problem that traditional decision trees cannot accurately judge faults when there is a dependency between the front and rear states. In terms of function expansion, it supports signal combination calculation and branch jump, meeting the requirements of complex decision-making judgment. It also effectively solves the problem of logical redundancy by defining common functions, comprehensively improving the performance and efficiency of vehicle fault diagnosis.

[0135] The above-disclosed are only the preferred embodiments of the present invention. Of course, the scope of the rights of the present invention cannot be limited thereby. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope covered by the present invention.

Claims

1. A vehicle fault diagnosis method, characterized in that: The following steps are involved: Configure state variables according to the selected bus message and bus signal, and construct signal and message event processing logic based on the state variables to obtain a decision script; According to the faulty vehicle and the time period in which the fault occurred, the decision script is called to perform decision analysis on the extracted bus messages and bus signals. When a jump in the bus message or bus signal is detected, the signal and message event processing logic is triggered to execute and the diagnosis result is output.

2. The method according to claim 1, characterized in that: The configuring state variables according to the selected bus message and bus signal specifically includes: Configuration state variables are used to store message and signal timestamps, message and signal values, and system state values.

3. The method according to claim 1, characterized in that The constructing of the signal and message event processing logic based on the state variable specifically includes: Write logic code in messages and signal events, the logic code includes: Memorize and update the timestamp of the message and signal event triggering; Memorize and update the latest value of the signal of this message and signal event message; Retrieve the timestamp and signal value of the message signal event of the previous event; Calculate the time difference between the current message and signal event and the previous event; The state variables of this event and the variable values ​​of the previous event are combined for calculation and judgment, and the state variables are updated. If it is determined that the vehicle has a fault, the cause of the fault and maintenance suggestions are printed.

4. The method according to claim 3, characterized in that When constructing the signal and message event processing logic based on the state variables, if there is a common decision logic, it is abstracted as a common function. In the signal and message events, when it is determined that the conditions for entering the execution of the common function are met, the common function is called.

5. The method according to claim 1, characterized in that The triggering and executing of the signal and message event processing logic when a bus message or bus signal jump is detected specifically includes: Initialize the state variables used in the decision script; Determine the transition edge of each signal and message, and record the transition time; At the moment of each signal and message transition, the corresponding signal and message events are triggered, and the logic of the signal and message events is executed, including updating the signal and message timestamps, updating the signal and variable values, retrieving the timestamp and signal value of the previous moment, calculating and judging the signal, and printing the cause of the fault and maintenance suggestions.

6. The method according to claim 1, characterized in that After obtaining the decision script, it also includes: Releasing the decision script to the cloud platform, and performing syntax checking and compiling on the decision script on the cloud platform; Test the compiled decision scripts; Publish the decision script that passes the test to the cloud platform and enable it.

7. The method according to claim 1, characterized in that After the diagnostic results are output, they also include: The decision script is optimized based on the matching score between the diagnosis result and the actual fault.

8. A vehicle fault diagnosis device, characterized in that: include: A decision script construction module, used to configure state variables according to selected bus messages and bus signals, and to construct signal and message event processing logic based on the state variables to obtain a decision script; The fault diagnosis module is used to call the decision script to perform decision analysis on the extracted bus messages and bus signals according to the faulty vehicle and the time period when the fault occurs, trigger the execution of the signal and message event processing logic when a jump in the bus message or bus signal is detected, and output the diagnosis result.

9. A vehicle fault diagnosis device, characterized in that: include: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and are configured to be executed by the one or more processors, and the one or more applications are configured to execute the vehicle fault diagnosis method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that It includes computer instructions, which instruct a computer device to execute operations corresponding to the vehicle fault diagnosis method as described in any one of claims 1 to 7.

Images