Vehicle FMEA data updating method and device, equipment and storage medium

Abstract

The invention relates to a vehicle FMEA data updating method and device, equipment and a storage medium. The method comprises the steps of obtaining an FMEA file corresponding to a target vehicle, and determining a vehicle fault signal associated with a potential failure mode according to the vehicle FMEA file; according to a real-time fault signal reported by the target vehicle in the driving process, determining a fault occurrence rate corresponding to a fault type to which the real-time fault signal belongs and a supplementary potential failure reason corresponding to the real-time fault signal; determining a supplementary potential failure reason corresponding to the potential failure mode according to a vehicle fault signal associated with the potential failure mode, a real-time fault signal matched with the associated vehicle fault signal and a supplementary potential failure reason corresponding to the matched real-time fault signal; and updating the FMEA file according to the supplementary potential failure reason corresponding to the potential failure mode and the fault occurrence rate corresponding to the fault type. The problems occurring in the driving process are more real and more comprehensive, so that the updated FMEA file is more comprehensive and more real.

Description

Technical Field

[0001] This application relates to the field of automotive technology, and in particular to a method, apparatus, device, and storage medium for updating vehicle FMEA (Failure Mode and Effects Analysis) data. Background Technology

[0002] FEMA is a systematic, preventative failure analysis method commonly used in engineering, manufacturing, quality management, and risk assessment.

[0003] In the vehicle R&D and manufacturing process, FMEA documents can be applied to many aspects, including but not limited to: body structure design, engine system, transmission system, vehicle electrical system, and manufacturing process, to ensure the reliability and safety of the vehicle during design, production, and use. By effectively applying FMEA documents, automotive manufacturers can identify and resolve potential problems early, improving product quality and customer satisfaction.

[0004] Traditional vehicle FMEA data management relies heavily on experience-based design. This involves R&D personnel manually analyzing potential failure modes and their corresponding causes, referencing a fault description library and considering the specifications of the vehicle under development. However, due to the limitations of manual analysis, incomplete analysis of potential failure causes is a common problem. Summary of the Invention

[0005] This application provides a method, apparatus, device, and storage medium for updating vehicle FMEA data, in order to solve the problem that traditional vehicle FMEA data management methods rely mainly on experience-based design, which can easily lead to incomplete analysis of potential failure causes.

[0006] To address the aforementioned technical problems, the technical solution of this application is provided through the following embodiments:

[0007] This application provides a method for updating vehicle FMEA data, including: acquiring a vehicle fault mode and impact analysis (FMEA) file corresponding to a target vehicle; determining vehicle fault signals associated with potential failure modes based on the vehicle FMEA file; determining the fault occurrence rate corresponding to the fault type of the real-time fault signal and determining the supplementary potential failure cause corresponding to the real-time fault signal based on the real-time fault signal reported by the target vehicle during driving; determining supplementary potential failure causes corresponding to the potential failure modes based on the vehicle fault signals associated with the potential failure modes, the real-time fault signals matched by the associated vehicle fault signals, and the supplementary potential failure causes corresponding to the matched real-time fault signals; and updating the FMEA file based on the supplementary potential failure causes corresponding to the potential failure modes and the fault occurrence rate corresponding to the fault type.

[0008] The step of determining the vehicle fault signals associated with potential failure modes based on the vehicle FMEA file includes: preprocessing the vehicle FMEA file to obtain FMEA data; using a preset natural language processing tool to extract feature values ​​of each potential failure mode from the preprocessed FMEA data; extracting each vehicle fault signal from the preprocessed FMEA data; performing word vector parsing on each potential failure mode feature value and each vehicle fault signal to obtain a potential failure mode vector corresponding to each potential failure mode feature value and a vehicle fault signal vector corresponding to each vehicle fault signal; calculating the correlation degree between each potential failure mode vector and each vehicle fault signal vector; obtaining a preset number of vehicle fault signal vectors in descending order of correlation degree, and associating the vehicle fault signal corresponding to each obtained vehicle fault signal vector with the potential failure mode feature value corresponding to the potential failure mode vector.

[0009] The step of determining the fault occurrence rate corresponding to the fault type of the real-time fault signal includes: reading the fault type and reporting timestamp in the real-time fault signal; if the difference between the reporting timestamp of the current real-time fault signal and the reporting timestamp of the previous real-time fault signal of the same fault type is greater than a preset time length, then the number of fault occurrences corresponding to the fault type is accumulated; and the fault occurrence rate corresponding to the fault type is determined based on the number of fault occurrences corresponding to the fault type.

[0010] The step of determining the supplementary potential failure cause corresponding to the real-time fault signal includes: reading the fault type in the real-time fault signal; querying the supplementary potential failure cause corresponding to the fault type in the real-time fault signal in a preset signal fault association table; wherein the signal fault association table is used to record at least the association relationship between fault type and supplementary potential failure cause.

[0011] The step of determining the supplementary potential failure cause corresponding to the potential failure mode based on the vehicle fault signal associated with the potential failure mode, the real-time fault signal matched by the associated vehicle fault signal, and the supplementary potential failure cause corresponding to the matched real-time fault signal includes: for the vehicle fault signal associated with the potential failure mode, determining the real-time fault signal matched by the vehicle fault signal from the real-time fault signals reported by the target vehicle; for the real-time fault signal matched by the vehicle fault signal, determining the supplementary potential failure cause corresponding to the real-time fault signal as the supplementary potential failure cause corresponding to the vehicle fault signal; and for the vehicle fault signal associated with the potential failure mode, determining the supplementary potential failure cause corresponding to the potential failure mode based on the supplementary potential failure cause corresponding to the vehicle fault signal.

[0012] The step of determining the supplementary potential failure cause corresponding to the potential failure mode based on the supplementary potential failure cause corresponding to the vehicle fault signal includes: if the potential failure mode is associated with at least two vehicle fault signals, then the supplementary potential failure causes corresponding to the at least two vehicle fault signals are merged into one supplementary potential failure cause, which is used as the supplementary potential failure cause corresponding to the potential failure mode.

[0013] The step of updating the FMEA file based on the supplementary potential failure causes corresponding to the potential failure mode and the failure occurrence rate corresponding to the failure type includes: determining the original potential failure causes corresponding to the potential failure mode and the original failure occurrence rate corresponding to the failure type in the FMEA file; aggregating the original potential failure causes and supplementary potential failure causes corresponding to the potential failure mode to obtain the potential failure causes corresponding to the potential failure mode; updating the original potential failure causes corresponding to the potential failure mode to the potential failure causes corresponding to the potential failure mode in the FMEA file, and updating the original failure occurrence rate corresponding to the failure type to the failure occurrence rate corresponding to the failure type.

[0014] This application embodiment also provides a vehicle FMEA data updating device, including: an acquisition and determination module, configured to acquire a vehicle FMEA file corresponding to a target vehicle, and determine vehicle fault signals associated with potential failure modes based on the vehicle FMEA file; a first determination module, configured to determine the fault occurrence rate corresponding to the fault type of the real-time fault signal and determine the supplementary potential failure cause corresponding to the real-time fault signal based on the real-time fault signal reported by the target vehicle during driving; a second determination module, configured to determine the supplementary potential failure cause corresponding to the potential failure mode based on the vehicle fault signal associated with the potential failure mode, the real-time fault signal matched by the associated vehicle fault signal, and the supplementary potential failure cause corresponding to the matched real-time fault signal; and a file updating module, configured to update the FMEA file based on the supplementary potential failure cause corresponding to the potential failure mode and the fault occurrence rate corresponding to the fault type.

[0015] This application also provides a vehicle FMEA data updating device, including: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is configured to execute an update program for vehicle FMEA data stored in the memory to implement the vehicle FMEA data updating method described in any of the above claims.

[0016] This application also provides a computer-readable storage medium storing computer-executable instructions, which are executed to implement the vehicle FMEA data update method described in any of the above claims.

[0017] Compared with the prior art, the technical solution provided in this application has the following advantages: The method provided in this application can obtain the vehicle fault mode and impact analysis (FMEA) file corresponding to the target vehicle, and, based on the vehicle FMEA file, determine the vehicle fault signals associated with potential failure modes; based on the real-time fault signals reported by the target vehicle during driving, determine the fault occurrence rate corresponding to the fault type of the real-time fault signal and determine the supplementary potential failure causes corresponding to the real-time fault signal; based on the vehicle fault signals associated with the potential failure modes, the real-time fault signals matched by the associated vehicle fault signals, and the supplementary potential failure causes corresponding to the matched real-time fault signals, determine the supplementary potential failure causes corresponding to the potential failure modes; and update the FMEA file based on the supplementary potential failure causes corresponding to the potential failure modes and the fault occurrence rate corresponding to the fault type. In this embodiment of the application, based on the vehicle dynamic data represented by the real-time fault signals of the target vehicle, the potential failure causes and failure rates that may occur during the driving process of the target vehicle are analyzed. The potential failure causes and failure rates that may occur during the driving process of the target vehicle are used to improve the original potential failure causes and failure rates in the FMEA file. Since the problems that occur during the driving process of the target vehicle are more realistic and more comprehensive, and are no longer limited to the thinking and analysis of the R&D personnel, the potential failure causes and failure rates in the updated FMEA file are more comprehensive and more in line with the real vehicle. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0021] Figure 1 This is a flowchart of a method for updating vehicle FMEA data according to an embodiment of this application;

[0022] Figure 2This is a flowchart illustrating the steps for determining a vehicle fault signal associated with a potential failure mode according to an embodiment of this application.

[0023] Figure 3 This is a structural diagram of a vehicle FMEA data updating device according to an embodiment of this application;

[0024] Figure 4 This is a structural diagram of a vehicle FMEA data updating device according to an embodiment of this application. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] The following disclosure provides numerous different embodiments or examples for implementing various structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0027] This application provides a method for updating vehicle FMEA data. For example... Figure 1 The diagram shown is a flowchart of a method for updating vehicle FMEA data according to an embodiment of this application.

[0028] Step S110: Obtain the vehicle FMEA file corresponding to the target vehicle, and determine the vehicle fault signals associated with potential failure modes based on the vehicle FMEA file.

[0029] The vehicle FMEA file is a vehicle-related FMEA file. In this embodiment, the vehicle FMEA file is the FMEA file corresponding to the vehicle specifications of the target vehicle.

[0030] Potential failure modes refer to situations where a component, subsystem, or system of a vehicle may fail to achieve or be unable to perform the expected function described in the item / function column.

[0031] Potential failure causes refer to the reasons that lead to potential failure modes.

[0032] Vehicle malfunction signals are signals emitted when a vehicle malfunctions.

[0033] Specifically, vehicle FMEA files are released periodically. A vehicle FMEA file includes: at least one vehicle fault signal, the original fault occurrence rate corresponding to at least one fault type, at least one potential failure mode, and the original potential failure cause corresponding to each potential failure mode. The vehicle fault signal and fault occurrence rate are located in the first data section, while the potential failure modes and their potential failure causes are located in the second data section. The first and second data sections are separate and unrelated.

[0034] In the vehicle FMEA file, at least one vehicle fault signal and at least one potential failure mode are extracted. For each potential failure mode, among the at least one vehicle fault signal, the vehicle fault signal associated with that potential failure mode is identified. The specific methods for obtaining potential failure modes and vehicle fault signals from the FMEA file, and for determining the association between them, will be described later and will not be elaborated upon here.

[0035] Step S120: Based on the real-time fault signals reported by the target vehicle during driving, determine the fault occurrence rate corresponding to the fault type of the real-time fault signal and determine the supplementary potential failure causes corresponding to the real-time fault signal.

[0036] The failure rate refers to the number of failures that occur within a preset statistical period. The statistical period can be an empirical value or a value obtained through experiments.

[0037] Supplementary potential failure causes refer to potential failure causes used to supplement the original potential failure causes. The original potential failure causes are those described in the FMEA document.

[0038] The target vehicle reports a real-time signal every preset time interval during its operation. For each real-time signal, it is identified whether the real-time signal is a real-time fault signal. If the real-time signal is a real-time fault signal, the fault occurrence rate corresponding to the fault type of the real-time fault signal is determined, and the supplementary potential failure cause corresponding to the real-time fault signal is queried in the preset signal fault association table. The signal fault association table is used to record at least the association between fault type and supplementary potential failure cause.

[0039] Step S130: Based on the vehicle fault signal associated with the potential failure mode, the real-time fault signal matched by the associated vehicle fault signal, and the supplementary potential failure cause corresponding to the matched real-time fault signal, determine the supplementary potential failure cause corresponding to the potential failure mode.

[0040] Since there may be more than two potential failure modes, each potential failure mode is used as a starting point to determine the corresponding supplementary potential failure cause.

[0041] Specifically, for each potential failure mode, the following steps are performed: For each vehicle fault signal associated with the potential failure mode, among the real-time fault signals reported by the target vehicle, determine the real-time fault signal that matches the vehicle fault signal; since the real-time fault signal has a corresponding supplementary potential failure cause, the supplementary potential failure cause corresponding to the real-time fault signal is used as the supplementary potential failure cause corresponding to the vehicle fault signal; since the vehicle fault signal is associated with the potential failure mode, the supplementary potential failure cause corresponding to the vehicle fault signal is used as the supplementary potential failure cause corresponding to the potential failure mode. In this way, one potential failure mode can correspond to at least two supplementary potential failure causes corresponding to each vehicle fault signal.

[0042] Step S140: Update the FMEA file based on the supplementary potential failure causes corresponding to the potential failure modes and the failure occurrence rate corresponding to the failure types.

[0043] In the FMEA file, the original potential failure causes corresponding to the potential failure mode and the original failure occurrence rate corresponding to the failure type are determined; the original potential failure causes and supplementary potential failure causes corresponding to the potential failure mode are aggregated to obtain the potential failure causes corresponding to the potential failure mode; in the FMEA file, the original potential failure causes corresponding to the potential failure mode are updated to the potential failure causes corresponding to the potential failure mode, and the original failure occurrence rate corresponding to the failure type is updated to the failure occurrence rate corresponding to the failure type.

[0044] In this embodiment, a Vehicle Fault Mode and Effects Analysis (FMEA) file corresponding to the target vehicle is obtained. Based on the FMEA file, vehicle fault signals associated with potential failure modes are determined. Based on real-time fault signals reported by the target vehicle during operation, the failure incidence rate corresponding to the fault type of the real-time fault signal and the supplementary potential failure cause corresponding to the real-time fault signal are determined. Based on the vehicle fault signals associated with the potential failure modes, the real-time fault signals matched by the associated vehicle fault signals, and the supplementary potential failure causes corresponding to the matched real-time fault signals, supplementary potential failure causes corresponding to the potential failure modes are determined. The FMEA file is updated based on the supplementary potential failure causes corresponding to the potential failure modes and the failure incidence rate corresponding to the fault type. In this embodiment, based on vehicle dynamic data represented by real-time fault signals of the target vehicle, the potential causes and failure rates of the target vehicle during operation are analyzed. These potential causes and failure rates are then used to refine the original potential causes and failure rates in the FMEA file. Because the problems encountered by the target vehicle during operation are more realistic and comprehensive, no longer limited to the thinking and analysis of the R&D personnel, the potential causes and failure rates in the updated FMEA file are more comprehensive and more closely reflect real vehicles. Furthermore, the updated FMEA file is more valuable for R&D personnel, and with its use, potential faults can be detected and addressed promptly, improving fault handling efficiency and accuracy, and ensuring the stability and safety of vehicle operation.

[0045] The process of identifying vehicle fault signals associated with potential failure modes is described below, such as... Figure 2 The diagram shown is a flowchart illustrating the steps for determining a vehicle fault signal associated with a potential failure mode according to an embodiment of this application.

[0046] Step S210: Preprocess the vehicle FMEA file to obtain FMEA data.

[0047] The published FMEA files are converted into Data Frames using the Lang Chain framework. Data Frames are tabular data structures. Potential failure modes and vehicle fault signals are segmented from the Data Frames to obtain FMEA data.

[0048] Furthermore, potential failure modes and vehicle malfunction signals can be segmented from DataFrame data by row, column, value, group by, or Boolean index.

[0049] Furthermore, to ensure the quality and accuracy of the segmented data, the segmented data portions can be cleaned. This includes tasks such as noise removal, simplified / traditional character conversion, removal of special markers, removal of invalid characters, standardization of naming, and numerical range processing.

[0050] Step S220: Using a preset NLP (Natural Language Processing) tool, extract feature values ​​of each potential failure mode from the preprocessed FMEA data.

[0051] For the segmented potential failure modes, feature values ​​of the potential failure modes are extracted. These feature values ​​can be used to represent the potential failure modes. For example, the feature value "large engine speed fluctuation" is extracted from the potential failure mode "the engine speed fluctuates greatly during vehicle operation".

[0052] Specifically, the following steps can be used to extract the feature values ​​of potential failure modes.

[0053] Step S1: Segment the potential failure mode into words. The sentence containing the potential failure mode is broken down into individual words or phrases. For example: “car”, “in”, “driving”, “in process”, “,”, “engine”, “speed”, “fluctuation”, “very large”.

[0054] Step S2 involves tagging the potential failure modes after word segmentation, assigning a part-of-speech tag to each word or phrase. For example, tagging each word or phrase as a noun, verb, adjective, etc., helps in understanding the role of the words in a sentence.

[0055] Step S3: Extract key information from the word segmentation after part-of-speech tagging. Based on the sentence structure and semantics, identify and extract key information. For example, "engine speed" is the subject, and "fluctuates greatly" is the key feature describing this subject.

[0056] Step S4: Reconstruct the potential failure mode feature values ​​using the extracted key information. The extracted key information is reconstructed into a concise feature value description. For example, the reconstructed potential failure mode feature value is "large engine speed fluctuations".

[0057] Step S230: Extract the fault signals of each vehicle from the preprocessed FMEA data.

[0058] Step S240: Perform word vector parsing for each potential disappearance mode feature value and each vehicle fault signal to obtain the potential failure mode vector corresponding to each potential disappearance mode feature value and the vehicle fault signal vector corresponding to each vehicle fault signal.

[0059] The pre-trained vector model of the automotive industry is called to perform word vector parsing on each potential disappearance mode feature value and each vehicle fault signal to obtain the potential failure mode vector corresponding to each potential disappearance mode feature value and the vehicle fault signal vector corresponding to each vehicle fault signal.

[0060] The potential failure mode vector and the vehicle fault signal vector have the same dimension. The dimension of the vector can be set according to requirements. For example, the dimension of the vector can be 4.

[0061] For example: Potential failure mode feature value 1 is "large engine speed fluctuation", potential failure mode feature value 2 is "excessive fuel consumption", vehicle fault signal 1 is "engine cold start vibration" and vehicle fault signal 2 is "abnormal engine noise". After word vector parsing, the potential failure mode vector v1 corresponding to potential failure mode feature value 1 is [0.2,0.5,-0.1,0.3], the potential failure mode vector v2 corresponding to potential failure mode feature value 2 is [0.1,0.1,0.1,0.2], the vehicle fault signal vector u1 corresponding to vehicle fault signal 1 is [0.2,0.4,0.5,0.1], and the vehicle fault signal vector u2 corresponding to vehicle fault signal 1 is [0.1,0.4,-0.2,0.2].

[0062] Step S250: For each potential failure mode vector, calculate the correlation degree between the potential failure mode vector and each vehicle fault signal vector; obtain a preset number of vehicle fault signal vectors in descending order of correlation degree, and associate the vehicle fault signal corresponding to each obtained vehicle fault signal vector with the potential failure mode feature value corresponding to the potential failure mode vector.

[0063] The degree of association can be measured by cosine similarity. The higher the cosine similarity, the higher the degree of association; the lower the cosine similarity, the lower the degree of association.

[0064] Furthermore, the potential failure mode vector v can be calculated using the following formula. n and vehicle fault signal vector u n Cosine similarity between them:

[0065] Where n is a positive integer.

[0066] Based on the potential failure mode vector, calculate cos(v1,u1), cos(v1,u2), ..., cos(v1,u1), ... n ), thus obtaining v1 and u1 to u n The cosine similarity of each vector in the vector is calculated. Similarly, cos(v) can be calculated. n ,u1),cos(v n,u2), ...,cos(v n ,u n ), thus obtaining v1 and u1 to u n The cosine similarity of each vector in the vector.

[0067] Taking the calculation of cos(v1,u2), where v1 = [0.2,0.5,-0.1,0.3] and u2 = [0.1,0.4,-0.2,0.2] as an example:

[0068] v1·u2=0.2×0.1+0.5×0.4+(-0.1)×(-0.2)+0.3×0.2;

[0069]

[0070] Finally, the cosine similarity cos(v1,u2) is obtained as 0.8869025492.

[0071] Furthermore, the cosine similarity between two vectors ranges from -1 to 1. Here, -1 indicates that the two vectors point in opposite directions, 1 indicates that the two vectors point in exactly the same direction, and 0 indicates that the two vectors are independent.

[0072] After calculating the cosine similarity between each potential failure mode vector and each vehicle fault signal vector, vehicle fault signal vectors with a cosine similarity greater than 0 can be selected. These selected vectors are then sorted in descending order of cosine similarity, starting with the vector with the highest similarity. A predetermined number of vehicle fault signal vectors are obtained; if the sorted sequence is less than this predetermined number, all vehicle fault signal vectors are directly acquired. The acquired vehicle fault signal vectors are then associated with the current potential failure mode vector. Since each vehicle fault signal vector corresponds to a vehicle fault signal, and each potential failure mode vector corresponds to a potential failure mode feature value, associating the acquired vehicle fault signal vectors with the current potential failure mode vector allows for the association of each acquired vehicle fault signal vector with the potential failure mode feature value corresponding to the potential failure mode vector.

[0073] The preset quantity can be an empirical value or a value obtained through experiments.

[0074] For example: filter out all vehicle fault signal vectors with a cosine similarity between 0 and 1 (excluding 0). If there are more than 5 (preset number), filter out the top 5 u vectors with the highest cosine similarity to the v vector and associate them with the vehicle fault signals corresponding to the u vectors; if there are fewer than 5 u vectors, associate them with the vehicle fault signals corresponding to all u vectors.

[0075] After identifying the vehicle fault signals associated with potential failure modes, the failure rates of each fault type in the FMEA file can be updated based on the vehicle's dynamic data. Furthermore, the original potential failure causes corresponding to the potential failure modes in the FMEA file can be supplemented. Before supplementing, it is necessary to determine the failure rate of each fault type and identify the supplementary potential failure causes corresponding to the potential failure modes.

[0076] Specifically, the target vehicle will continuously report real-time fault signals while driving.

[0077] Furthermore, after the target vehicle is powered on, it reports a real-time signal at preset time intervals (e.g., 10 seconds), with at least one real-time signal reported each time. The real-time signal carries a signal name and a reporting timestamp. The reporting timestamp can be used to indicate the time the target vehicle reported the signal.

[0078] Furthermore, if the vehicle's network connectivity is poor, preventing the normal reporting of real-time signals, the real-time signals can be stored in the vehicle's telematics processor T-BOX and uploaded after the vehicle's network connectivity is restored.

[0079] Real-time signals include, but are not limited to, real-time fault signals. Real-time fault signals carry the fault type and reporting timestamp. The fault type can be either the signal name or the fault name.

[0080] Specifically, if the fault type is a signal name, the real-time signal can be identified as a real-time fault signal based on its normal range or abnormal condition. If the real-time signal is found to be outside its normal range or exhibiting an abnormal condition, it is determined to be a real-time fault signal.

[0081] Further, determining the fault occurrence rate corresponding to the fault type to which the real-time fault signal belongs includes: reading the fault type and reporting timestamp in the real-time fault signal; if the difference between the reporting timestamp of the current real-time fault signal and the reporting timestamp of the previous real-time fault signal of the same fault type is greater than a preset time length (e.g., 30 minutes), then the number of fault occurrences corresponding to the fault type is accumulated; based on the number of fault occurrences corresponding to the fault type, the fault occurrence rate corresponding to the fault type is determined.

[0082] For example, if the statistical duration is 1000 hours, and each frame is 10 seconds, then 1000 hours would consist of 360,000 frames. The goal is to determine the number of times a fault type occurs within 1000 hours. When a fault occurs, the target vehicle continuously sends real-time fault signals to the cloud. The target vehicle only stops uploading fault signals after the fault is resolved. If, within 30 minutes after a real-time fault signal stops uploading, the target vehicle does not report the same real-time fault signal again, it is counted as one fault. If, within 30 minutes after a real-time fault signal stops uploading, the target vehicle reports the same fault signal again, it indicates that the fault has not been resolved. The timer is reset from the reporting timestamp of this real-time fault signal until the target vehicle stops reporting the real-time fault signal for 30 minutes, at which point it is counted as one fault.

[0083] Further, determining the supplementary potential failure cause corresponding to the real-time fault signal includes: reading the fault type in the real-time fault signal; and querying the supplementary potential failure cause corresponding to the fault type in the real-time fault signal in a preset signal fault association table.

[0084] For example, the signal fault association table is shown in Table 1. However, those skilled in the art should know that Table 1 is only for illustrating this embodiment and is not intended to limit this embodiment.

[0085]

[0086]

[0087] Table 1

[0088] After determining the fault occurrence rate corresponding to the fault type of the real-time fault signal and the supplementary potential failure causes corresponding to the real-time fault signal, we can begin to determine the supplementary potential failure causes corresponding to the potential failure modes.

[0089] Specifically, since the FMEA file includes multiple potential failure modes, for each potential failure mode, the supplementary potential failure cause corresponding to the potential failure mode can be determined based on the vehicle fault signal associated with the potential failure mode, the real-time fault signal that matches the associated vehicle fault signal, and the supplementary potential failure cause corresponding to the matching real-time fault signal.

[0090] Furthermore, for the vehicle fault signals associated with the potential failure mode, among the real-time fault signals reported by the target vehicle, a real-time fault signal matching the vehicle fault signal is determined; for the real-time fault signal matching the vehicle fault signal, the supplementary potential failure cause corresponding to the real-time fault signal is determined as the supplementary potential failure cause corresponding to the vehicle fault signal; for the vehicle fault signals associated with the potential failure mode, based on the supplementary potential failure cause corresponding to the vehicle fault signal, the supplementary potential failure cause corresponding to the potential failure mode is determined. Here, matching the vehicle fault signal and the real-time fault signal means that the vehicle fault signal and the real-time fault signal have the same fault type.

[0091] Furthermore, if the potential failure mode is associated with at least two vehicle fault signals, the supplementary potential failure causes corresponding to the at least two vehicle fault signals are merged into a single supplementary potential failure cause, which serves as the supplementary potential failure cause corresponding to the potential failure mode.

[0092] For example: a potential failure mode is associated with vehicle fault signal 1 and vehicle fault signal 2; the fault type of vehicle fault signal 1 is noise intensity; the fault type of vehicle fault signal 2 is exhaust oxygen content; the supplementary potential failure cause corresponding to vehicle fault signal 1 is "exhaust system leakage, piston ring damage, exhaust pipe damage"; the supplementary potential failure cause corresponding to vehicle fault signal 2 is "fuel supply problem, ignition system failure, exhaust system blockage"; using a preset language model, "exhaust system leakage, piston ring damage, exhaust pipe damage" and "fuel supply problem, ignition system failure, exhaust system blockage" are merged into "exhaust system failure, including sensor, oxygen sensor wiring, leakage, piston ring and exhaust pipe damage".

[0093] After determining the supplementary potential failure causes for each potential failure mode and the failure rate for each failure type, the corresponding data sections in the FMEA file are updated based on the supplementary potential failure causes for each potential failure mode and the failure rates for each failure type.

[0094] Further, in the FMEA file, the original potential failure causes corresponding to the potential failure mode and the original failure occurrence rate corresponding to the failure type are determined; the original potential failure causes and supplementary potential failure causes corresponding to the potential failure mode are aggregated to obtain the potential failure cause corresponding to the potential failure mode; in the FMEA file, the original potential failure causes corresponding to the potential failure mode are updated to the actual potential failure causes corresponding to the potential failure mode, and the original failure occurrence rate corresponding to the failure type is updated to the actual failure occurrence rate corresponding to the failure type. Specifically, when aggregating the original potential failure causes and supplementary potential failure causes corresponding to the potential failure mode, if there are identical original potential failure causes and supplementary potential failure causes, only one of them needs to be retained.

[0095] The embodiments of this application can process FMEA files in a fully automated manner, that is, by using the Lang Chain framework for file segmentation and data preprocessing, the rapid conversion and data cleaning of FMEA files are realized, which greatly improves the data processing efficiency.

[0096] The embodiments of this application can accurately extract feature values. That is, by using NLP tools, the potential failure mode feature values ​​in the FMEA file can be accurately extracted, avoiding the tedious manual processing and ensuring the accuracy and consistency of the feature values.

[0097] This application employs word vector correlation analysis, which calculates the cosine similarity of word vectors to quickly and accurately identify vehicle fault signals associated with feature values, providing strong support for subsequent fault warning and diagnosis.

[0098] This application's embodiments employ vehicle fault attribution analysis, combined with real-time data, to identify abnormal CAN signals. This enables rapid and accurate location of fault causes, providing effective data support for fault repair and prevention, and improving the efficiency and accuracy of fault handling.

[0099] The embodiments of this application can regenerate vehicle FMEA data, that is, regenerate FMEA data based on the attribution analysis results, which provides an important basis for vehicle fault management, enables the timely detection of potential problems and the implementation of preventive measures, and improves the reliability and safety of vehicles.

[0100] The embodiments of this application can realize real-time monitoring and early warning. By combining real-time data acquisition and fault occurrence rate calculation, it can realize real-time monitoring and early warning of vehicle faults, timely detection and handling of potential faults, and ensure the stability and safety of vehicle operation.

[0101] This application also provides a device for updating vehicle FMEA data. For example... Figure 3 The diagram shown is a structural diagram of a vehicle FMEA data updating device according to an embodiment of this application.

[0102] The vehicle FMEA data update device includes:

[0103] The acquisition and determination module 310 is used to acquire the vehicle FMEA file corresponding to the target vehicle, and, based on the vehicle FMEA file, determine the vehicle fault signals associated with potential failure modes.

[0104] The first determining module 320 is used to determine the fault occurrence rate corresponding to the fault type of the real-time fault signal and to determine the supplementary potential failure cause corresponding to the real-time fault signal based on the real-time fault signal reported by the target vehicle during driving.

[0105] The second determining module 330 is used to determine the supplementary potential failure cause corresponding to the potential failure mode based on the vehicle fault signal associated with the potential failure mode, the real-time fault signal matched by the associated vehicle fault signal, and the supplementary potential failure cause corresponding to the matched real-time fault signal.

[0106] The file update module 340 is used to update the FMEA file based on the supplementary potential failure causes corresponding to the potential failure modes and the failure occurrence rate corresponding to the failure types.

[0107] The functions of the apparatus described in this application embodiment have been described in the above method embodiments. Therefore, for any parts not detailed in the description of this embodiment, please refer to the relevant descriptions in the foregoing embodiments, which will not be repeated here.

[0108] This application also provides a device for updating vehicle FMEA data, such as... Figure 4 The diagram shown is a structural diagram of a vehicle FMEA data updating device according to an embodiment of this application.

[0109] The device for updating vehicle FMEA data includes a processor 410, a communication interface 420, a memory 430, and a communication bus 440. The processor 410, communication interface 420, and memory 430 communicate with each other via the communication bus 440.

[0110] Memory 430 is used to store computer programs.

[0111] In one embodiment of this application, when the processor 410 executes a program stored in the memory 430, it implements the vehicle FMEA data update method provided in any of the foregoing method embodiments, including: acquiring a vehicle fault mode and impact analysis (FMEA) file corresponding to a target vehicle; and determining vehicle fault signals associated with potential failure modes based on the vehicle FMEA file; determining the fault occurrence rate corresponding to the fault type of the real-time fault signal and determining supplementary potential failure causes corresponding to the real-time fault signal based on the real-time fault signals reported by the target vehicle during driving; determining supplementary potential failure causes corresponding to the potential failure modes based on the vehicle fault signals associated with the potential failure modes, the real-time fault signals matched by the associated vehicle fault signals, and the supplementary potential failure causes corresponding to the matched real-time fault signals; and updating the FMEA file based on the supplementary potential failure causes corresponding to the potential failure modes and the fault occurrence rate corresponding to the fault type.

[0112] The step of determining the vehicle fault signals associated with potential failure modes based on the vehicle FMEA file includes: preprocessing the vehicle FMEA file to obtain FMEA data; using a preset natural language processing tool to extract feature values ​​of each potential failure mode from the preprocessed FMEA data; extracting each vehicle fault signal from the preprocessed FMEA data; performing word vector parsing on each potential failure mode feature value and each vehicle fault signal to obtain a potential failure mode vector corresponding to each potential failure mode feature value and a vehicle fault signal vector corresponding to each vehicle fault signal; calculating the correlation degree between each potential failure mode vector and each vehicle fault signal vector; obtaining a preset number of vehicle fault signal vectors in descending order of correlation degree, and associating the vehicle fault signal corresponding to each obtained vehicle fault signal vector with the potential failure mode feature value corresponding to the potential failure mode vector.

[0113] The step of determining the fault occurrence rate corresponding to the fault type of the real-time fault signal includes: reading the fault type and reporting timestamp in the real-time fault signal; if the difference between the reporting timestamp of the current real-time fault signal and the reporting timestamp of the previous real-time fault signal of the same fault type is greater than a preset time length, then the number of fault occurrences corresponding to the fault type is accumulated; and the fault occurrence rate corresponding to the fault type is determined based on the number of fault occurrences corresponding to the fault type.

[0114] The step of determining the supplementary potential failure cause corresponding to the real-time fault signal includes: reading the fault type in the real-time fault signal; querying the supplementary potential failure cause corresponding to the fault type in the real-time fault signal in a preset signal fault association table; wherein the signal fault association table is used to record at least the association relationship between fault type and supplementary potential failure cause.

[0115] The step of determining the supplementary potential failure cause corresponding to the potential failure mode based on the vehicle fault signal associated with the potential failure mode, the real-time fault signal matched by the associated vehicle fault signal, and the supplementary potential failure cause corresponding to the matched real-time fault signal includes: for the vehicle fault signal associated with the potential failure mode, determining the real-time fault signal matched by the vehicle fault signal from the real-time fault signals reported by the target vehicle; for the real-time fault signal matched by the vehicle fault signal, determining the supplementary potential failure cause corresponding to the real-time fault signal as the supplementary potential failure cause corresponding to the vehicle fault signal; and for the vehicle fault signal associated with the potential failure mode, determining the supplementary potential failure cause corresponding to the potential failure mode based on the supplementary potential failure cause corresponding to the vehicle fault signal.

[0116] The step of determining the supplementary potential failure cause corresponding to the potential failure mode based on the supplementary potential failure cause corresponding to the vehicle fault signal includes: if the potential failure mode is associated with at least two vehicle fault signals, then the supplementary potential failure causes corresponding to the at least two vehicle fault signals are merged into one supplementary potential failure cause, which is used as the supplementary potential failure cause corresponding to the potential failure mode.

[0117] The step of updating the FMEA file based on the supplementary potential failure causes corresponding to the potential failure mode and the failure occurrence rate corresponding to the failure type includes: determining the original potential failure causes corresponding to the potential failure mode and the original failure occurrence rate corresponding to the failure type in the FMEA file; aggregating the original potential failure causes and supplementary potential failure causes corresponding to the potential failure mode to obtain the potential failure causes corresponding to the potential failure mode; updating the original potential failure causes corresponding to the potential failure mode to the potential failure causes corresponding to the potential failure mode in the FMEA file, and updating the original failure occurrence rate corresponding to the failure type to the failure occurrence rate corresponding to the failure type.

[0118] This application also provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the steps of the vehicle FMEA data update method provided in any of the foregoing method embodiments. Since the vehicle FMEA data update method has been described in detail above, any omissions in this embodiment can be found in the relevant descriptions in the foregoing embodiments, and will not be repeated here.

[0119] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0120] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0121] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0122] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for updating vehicle FMEA data, characterized in that, include: Obtain the vehicle failure mode and impact analysis (FMEA) file corresponding to the target vehicle, and determine the vehicle failure signals associated with potential failure modes based on the vehicle FMEA file. Based on the real-time fault signals reported by the target vehicle during its operation, determine the fault occurrence rate corresponding to the fault type of the real-time fault signal and determine the supplementary potential failure causes corresponding to the real-time fault signal. Based on the vehicle fault signal associated with the potential failure mode, the real-time fault signal matched by the associated vehicle fault signal, and the supplementary potential failure cause corresponding to the matched real-time fault signal, the supplementary potential failure cause corresponding to the potential failure mode is determined. The FMEA file is updated based on the supplementary potential failure causes corresponding to the potential failure modes and the failure occurrence rates corresponding to the failure types.

2. The method according to claim 1, characterized in that, The step of determining the vehicle fault signals associated with potential failure modes based on the vehicle FMEA file includes: The vehicle FMEA file is preprocessed to obtain FMEA data; Using a pre-set natural language processing tool, feature values ​​of each potential failure mode are extracted from the pre-processed FMEA data. The fault signals of each vehicle are extracted from the preprocessed FMEA data; For each potential disappearance mode feature value and each vehicle fault signal, word vector parsing is performed to obtain the potential failure mode vector corresponding to each potential disappearance mode feature value and the vehicle fault signal vector corresponding to each vehicle fault signal; For each potential failure mode vector, the correlation degree between the potential failure mode vector and each vehicle fault signal vector is calculated; a preset number of vehicle fault signal vectors are obtained in descending order of correlation degree, and the vehicle fault signal corresponding to each obtained vehicle fault signal vector is associated with the potential failure mode feature value corresponding to the potential failure mode vector.

3. The method according to claim 1, characterized in that, Determining the fault occurrence rate corresponding to the fault type to which the real-time fault signal belongs includes: Read the fault type and reporting timestamp from the real-time fault signal; If the difference between the reporting timestamp of the current real-time fault signal and the reporting timestamp of the previous real-time fault signal of the same fault type is greater than a preset time length, then the number of fault occurrences corresponding to the fault type will be accumulated. The failure rate corresponding to the failure type is determined based on the number of failures that occur for that failure type.

4. The method according to claim 1, characterized in that, Determining the supplementary potential failure cause corresponding to the real-time fault signal includes: Read the fault type from the real-time fault signal; In a preset signal fault association table, supplementary potential failure causes corresponding to the fault type in the real-time fault signal are queried; wherein, the signal fault association table is used to record at least the association relationship between fault type and supplementary potential failure cause.

5. The method according to claim 1, characterized in that, The step of determining the supplementary potential failure cause corresponding to the potential failure mode based on the vehicle fault signal associated with the potential failure mode, the real-time fault signal matched by the associated vehicle fault signal, and the supplementary potential failure cause corresponding to the matched real-time fault signal includes: For the vehicle fault signals associated with the potential failure modes, determine the real-time fault signal that matches the vehicle fault signal from the real-time fault signals reported by the target vehicle. For the real-time fault signal matched with the vehicle fault signal, the supplementary potential failure cause corresponding to the real-time fault signal is determined as the supplementary potential failure cause corresponding to the vehicle fault signal. For the vehicle fault signal associated with the potential failure mode, the supplementary potential failure cause corresponding to the potential failure mode is determined based on the supplementary potential failure cause corresponding to the vehicle fault signal.

6. The method according to claim 1, characterized in that, The step of determining the supplementary potential failure cause corresponding to the potential failure mode based on the supplementary potential failure cause corresponding to the vehicle fault signal includes: If the potential failure mode is associated with at least two vehicle fault signals, then the supplementary potential failure causes corresponding to the at least two vehicle fault signals are merged into one supplementary potential failure cause, which is used as the supplementary potential failure cause corresponding to the potential failure mode.

7. The method according to claim 1, characterized in that, The step of updating the FMEA file based on the supplementary potential failure causes corresponding to the potential failure modes and the failure incidence rates corresponding to the failure types includes: In the FMEA file, the original potential failure causes corresponding to the potential failure modes and the original failure incidence rates corresponding to the failure types are determined. The original potential failure causes and supplementary potential failure causes corresponding to the potential failure modes are aggregated to obtain the potential failure causes corresponding to the potential failure modes. In the FMEA file, the original potential failure cause corresponding to the potential failure mode is updated to the original potential failure cause corresponding to the potential failure mode, and the original failure occurrence rate corresponding to the failure type is updated to the original failure occurrence rate corresponding to the failure type.

8. A device for updating vehicle FMEA data, characterized in that, include: The acquisition and determination module is used to acquire the vehicle FMEA file corresponding to the target vehicle, and, based on the vehicle FMEA file, determine the vehicle fault signals associated with potential failure modes. The first determining module is used to determine the fault occurrence rate corresponding to the fault type of the real-time fault signal and to determine the supplementary potential failure cause corresponding to the real-time fault signal based on the real-time fault signal reported by the target vehicle during driving. The second determining module is used to determine the supplementary potential failure cause corresponding to the potential failure mode based on the vehicle fault signal associated with the potential failure mode, the real-time fault signal matched by the associated vehicle fault signal, and the supplementary potential failure cause corresponding to the matched real-time fault signal. The file update module is used to update the FMEA file based on the supplementary potential failure causes corresponding to the potential failure modes and the failure occurrence rate corresponding to the failure types.

9. A device for updating vehicle FMEA data, characterized in that, include: At least one communication interface; At least one bus connected to the at least one communication interface; At least one processor connected to the at least one bus; At least one memory connected to the at least one bus, wherein the processor is configured to execute an update program for vehicle FMEA data stored in the memory to implement the vehicle FMEA data update method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that are executed to implement the method for updating vehicle FMEA data according to any one of claims 1-7.

Images