Automobile part failure analysis and detection method and system and medium

Abstract

The embodiment of the invention provides an automobile part failure analysis and detection method and system and a medium, and the method comprises the steps: obtaining the operation state data of an automobile part, and carrying out the preprocessing of the operation state data, and obtaining the result information; building a failure analysis model based on the big data, inputting the result information into the failure analysis model, and outputting failure state information of the parts; analyzing a part failure mode based on the part failure state information, and analyzing part failure degree information according to the part failure mode; automobile part failure risk information is analyzed based on the part failure degree information; the automobile part failure risk information is transmitted to a terminal in real time according to a preset mode; the failure analysis model is constructed to analyze the running state data of the automobile parts, so that the failure state of the parts is accurately monitored, and the failure risk early warning of the automobile parts is improved.

Description

Technical Field

[0001] The present application relates to the technical field of component failure analysis, and in particular to a method, system and medium for detecting failure analysis of automobile components. Background Art

[0002] During the process of leaving the factory, the performance of automobile parts needs to be tested in order to analyze the failure life of the parts. The existing failure analysis detection methods for automobile parts cannot dynamically analyze the status data of automobile parts according to the failure analysis model, resulting in abnormal analysis results, affecting the analysis accuracy of automobile parts, and thus affecting the safety of automobile parts. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a method, system and medium for automobile component failure analysis detection, which analyzes the operating status data of automobile components by constructing a failure analysis model, thereby accurately monitoring the failure status of components and improving the failure risk warning of automobile components.

[0004] The present application also provides a method for analyzing and detecting automobile component failure, including:

[0005] Obtain the operating status data of automobile parts, pre-process the operating status data, and obtain result information;

[0006] Build a failure analysis model based on big data, input the result information into the failure analysis model, and output the failure status information of the components;

[0007] Analyze component failure modes based on component failure status information, and analyze component failure degree information based on component failure modes;

[0008] Analyze the failure risk information of automobile parts based on the failure degree information of parts;

[0009] The failure risk information of automobile parts is transmitted to the terminal in real time according to the predetermined method.

[0010] Optionally, in the automobile parts failure analysis detection method described in the embodiment of the present application, obtaining the automobile parts operation status data, preprocessing the operation status data, and obtaining result information specifically includes:

[0011] Obtain the operating status data of automobile parts and extract data features;

[0012] Determining whether the data feature is within a set feature interval;

[0013] If it is not in the set characteristic interval, the repeated data and abnormal data of the component operation status data are analyzed based on the data characteristics, and the repeated data and abnormal data of the operation status data are eliminated to obtain optimized data;

[0014] If it is within the set feature interval, the data features are averaged to obtain the result information.

[0015] Optionally, in the automobile parts failure analysis detection method described in the embodiment of the present application, a failure analysis model is constructed based on big data, specifically including:

[0016] Obtain the type of automobile parts, and based on the type of automobile parts, obtain the historical failure analysis data of the corresponding type to obtain a training set;

[0017] Build an initial model, iteratively train the initial model based on the training set, and obtain the training results;

[0018] Determining whether the training result converges;

[0019] If converged, a failure analysis model is generated;

[0020] If it does not converge, correction information is generated, and model parameters of the initial model are dynamically adjusted based on the correction information until the model converges.

[0021] Optionally, in the automobile parts failure analysis detection method described in the embodiment of the present application, a failure analysis model is constructed based on big data, result information is input into the failure analysis model, and component failure status information is output, specifically including:

[0022] Input the result information into the failure analysis model to obtain component failure data;

[0023] Obtain the type of automobile parts and the failure assessment rules based on the type matching standard of automobile parts;

[0024] Evaluate component failure data based on standard failure assessment rules to obtain failure assessment information;

[0025] Dynamically optimize and adjust the model parameters of the failure analysis model based on failure assessment information.

[0026] Optionally, in the automobile component failure analysis and detection method described in the embodiment of the present application, analyzing the component failure mode based on the component failure state information, and analyzing the component failure degree information according to the component failure mode, specifically includes:

[0027] Obtaining component failure status information, matching component types based on the component failure status information, and obtaining a matching combination;

[0028] Filter out component failure modes based on component types within the matching combination;

[0029] The upper and lower limits of the failure degree range are established according to the failure mode of the component, the failure degree range of the failure state information of the component is analyzed, and the corresponding component failure degree information is generated.

[0030] Optionally, in the automobile component failure analysis detection method described in the embodiment of the present application, analyzing the automobile component failure risk information based on the component failure degree information specifically includes:

[0031] Obtain information on the degree of failure of components, predict the operating risk of components based on the risk prediction model, and obtain prediction information;

[0032] Analyze the accuracy of forecast information based on the principle of contradiction;

[0033] Determine whether the accuracy is greater than or equal to the set accuracy threshold;

[0034] If it is greater than or equal to, then component failure risk information is generated;

[0035] If it is less than, feedback information is generated and the parameters of the risk prediction model are adjusted based on the feedback information.

[0036] In a second aspect, an embodiment of the present application provides an automobile component failure analysis detection system, the system comprising: a memory and a processor, the memory comprising a program of an automobile component failure analysis detection method, and the program of the automobile component failure analysis detection method is executed by the processor to implement the following steps:

[0037] Obtain the operating status data of automobile parts, pre-process the operating status data, and obtain result information;

[0038] Build a failure analysis model based on big data, input the result information into the failure analysis model, and output the failure status information of the components;

[0039] Analyze component failure modes based on component failure status information, and analyze component failure degree information based on component failure modes;

[0040] Analyze the failure risk information of automobile parts based on the failure degree information of parts;

[0041] The failure risk information of automobile parts is transmitted to the terminal in real time according to the predetermined method.

[0042] Optionally, in the automobile parts failure analysis and detection system described in the embodiment of the present application, the operation status data of the automobile parts is obtained, and the operation status data is preprocessed to obtain result information, which specifically includes:

[0043] Obtain the operating status data of automobile parts and extract data features;

[0044] Determining whether the data feature is within a set feature interval;

[0045] If it is not in the set characteristic interval, the repeated data and abnormal data of the component operation status data are analyzed based on the data characteristics, and the repeated data and abnormal data of the operation status data are eliminated to obtain optimized data;

[0046] If it is within the set feature interval, the data features are averaged to obtain the result information.

[0047] Optionally, in the automobile parts failure analysis and detection system described in the embodiment of the present application, a failure analysis model is constructed based on big data, specifically including:

[0048] Obtain the type of automobile parts, and based on the type of automobile parts, obtain the historical failure analysis data of the corresponding type to obtain a training set;

[0049] Build an initial model, iteratively train the initial model based on the training set, and obtain the training results;

[0050] Determining whether the training result converges;

[0051] If converged, a failure analysis model is generated;

[0052] If it does not converge, correction information is generated, and model parameters of the initial model are dynamically adjusted based on the correction information until the model converges.

[0053] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium includes an automobile parts failure analysis detection method program, and when the automobile parts failure analysis detection method program is executed by a processor, the steps of the automobile parts failure analysis detection method as described in any one of the above items are implemented.

[0054] As can be seen from the above, an automobile component failure analysis detection method, system and medium provided in the embodiments of the present application obtain the operating status data of automobile components, pre-process the operating status data, and obtain result information; construct a failure analysis model based on big data, input the result information into the failure analysis model, and output component failure status information; analyze component failure modes based on component failure status information, and analyze component failure degree information according to component failure modes; analyze automobile component failure risk information based on component failure degree information; transmit automobile component failure risk information to a terminal in real time according to a predetermined method; analyze automobile component operating status data by constructing a failure analysis model, thereby accurately monitoring component failure states and improving failure risk warnings of automobile components. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 A flowchart of a method for analyzing and detecting automobile parts failure provided in an embodiment of the present application;

[0057] Figure 2 A flow chart of a method for preprocessing the operating status data of automobile parts in the automobile parts failure analysis detection method provided in an embodiment of the present application;

[0058] Figure 3 A flow chart of a method for constructing a failure analysis model for the automobile parts failure analysis detection method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0060] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0061] Please refer to Figure 1 , Figure 1 This is a flow chart of a method for analyzing the failure of an automobile component in some embodiments of the present application. The method for analyzing the failure of an automobile component is used in a terminal device, and the method for analyzing the failure of an automobile component comprises the following steps:

[0062] S101, obtaining the operating status data of automobile parts, preprocessing the operating status data, and obtaining result information;

[0063] S102, constructing a failure analysis model based on big data, inputting result information into the failure analysis model, and outputting component failure status information;

[0064] S103, analyzing component failure modes based on component failure state information, and analyzing component failure degree information according to the component failure mode;

[0065] S104, analyzing automobile parts failure risk information based on parts failure degree information;

[0066] S105, transmitting the automobile parts failure risk information to the terminal in real time according to a predetermined method.

[0067] It should be noted that by constructing a failure analysis model to analyze the operating status data of automobile parts in real time, accurately analyze the operating abnormalities and failure status information of automobile parts, and analyze the failure degree of parts according to different failure status information, the operating risks of parts can be accurately detected.

[0068] Please refer to Figure 2 , Figure 2 This is a flow chart of a method for preprocessing the operating status data of an automobile component in a method for analyzing and detecting an automobile component failure in some embodiments of the present application. According to an embodiment of the present invention, the operating status data of an automobile component is obtained, and the operating status data is preprocessed to obtain result information, specifically including:

[0069] S201, obtaining the operating status data of automobile parts and extracting data features;

[0070] S202, determining whether the data feature is within a set feature range;

[0071] S203, if it is not in the set characteristic interval, then analyzing the duplicate data and abnormal data of the component operation status data based on the data characteristics, removing the duplicate data and abnormal data of the operation status data, and obtaining optimized data;

[0072] S204: If it is within the set feature interval, the data features are averaged to obtain result information.

[0073] It should be noted that by extracting features from the operating status data of automobile parts and filtering out duplicate data and abnormal data based on the extracted features, the operating status data is optimized and the accuracy of the operating status data is improved.

[0074] Please refer to Figure 3 , Figure 3This is a flow chart of a method for constructing a failure analysis model of a method for failure analysis and detection of automobile parts in some embodiments of the present application. According to an embodiment of the present invention, constructing a failure analysis model based on big data specifically includes:

[0075] S301, obtaining the type of automobile parts, and obtaining the historical failure analysis data of the corresponding type based on the type of automobile parts to obtain a training set;

[0076] S302, constructing an initial model, and iteratively training the initial model based on the training set to obtain a training result;

[0077] S303, determining whether the training result has converged;

[0078] S304, if converged, generating a failure analysis model;

[0079] S305: If the model does not converge, generate correction information, and dynamically adjust the model parameters of the initial model based on the correction information until the model converges.

[0080] It should be noted that by continuously training the initial model and dynamically adjusting the model parameters of the initial model during the training process, the analysis accuracy of the failure analysis model is continuously improved.

[0081] According to an embodiment of the present invention, a failure analysis model is constructed based on big data, result information is input into the failure analysis model, and component failure status information is output, specifically including:

[0082] Input the result information into the failure analysis model to obtain component failure data;

[0083] Obtain the type of automobile parts and the failure assessment rules based on the type matching standard of automobile parts;

[0084] Evaluate component failure data based on standard failure assessment rules to obtain failure assessment information;

[0085] Dynamically optimize and adjust the model parameters of the failure analysis model based on failure assessment information.

[0086] It should be noted that different types of automobile parts have different failure assessment rules. The failure status of automobile parts is evaluated through the corresponding standard failure assessment rules, so as to reversely correct and adjust the model parameters of the failure analysis model and improve the output results of the failure analysis model to be closer to the actual results.

[0087] According to an embodiment of the present invention, analyzing component failure modes based on component failure state information, and analyzing component failure degree information based on component failure modes specifically include:

[0088] Obtaining component failure status information, matching component types based on the component failure status information, and obtaining a matching combination;

[0089] Filter out component failure modes based on component types within the matching combination;

[0090] The upper and lower limits of the failure degree range are established according to the failure mode of the component, the failure degree range of the failure state information of the component is analyzed, and the corresponding component failure degree information is generated.

[0091] It should be noted that when failure analysis is performed on different types of components, it is necessary to select corresponding different failure degree intervals according to the type of component, and accurately analyze the failure degree of the component based on the failure degree interval analyzed according to the failure state of the component.

[0092] According to an embodiment of the present invention, analyzing the failure risk information of automobile parts based on the failure degree information of parts specifically includes:

[0093] Obtain information on the degree of failure of components, predict the operating risk of components based on the risk prediction model, and obtain prediction information;

[0094] Analyze the accuracy of forecast information based on the principle of contradiction;

[0095] Determine whether the accuracy is greater than or equal to the set accuracy threshold;

[0096] If it is greater than or equal to, then component failure risk information is generated;

[0097] If it is less than, feedback information is generated and the parameters of the risk prediction model are adjusted based on the feedback information.

[0098] It should be noted that the operating risk of components is predicted based on the failure degree information of different components, so as to accurately analyze the accuracy of the prediction information, and the failure state of automobile components is reversely verified based on the prediction, so as to accurately obtain the failure risk information of components and improve the accuracy of component analysis.

[0099] In a second aspect, an embodiment of the present application provides an automobile component failure analysis detection system, the system comprising: a memory and a processor, the memory comprising a program of an automobile component failure analysis detection method, and when the program of the automobile component failure analysis detection method is executed by the processor, the following steps are implemented:

[0100] Obtain the operating status data of automobile parts, pre-process the operating status data, and obtain result information;

[0101] Build a failure analysis model based on big data, input the result information into the failure analysis model, and output the failure status information of the components;

[0102] Analyze component failure modes based on component failure status information, and analyze component failure degree information based on component failure modes;

[0103] Analyze the failure risk information of automobile parts based on the failure degree information of parts;

[0104] The failure risk information of automobile parts is transmitted to the terminal in real time according to the predetermined method.

[0105] It should be noted that by constructing a failure analysis model to analyze the operating status data of automobile parts in real time, accurately analyze the operating abnormalities and failure status information of automobile parts, and analyze the failure degree of parts according to different failure status information, the operating risks of parts can be accurately detected.

[0106] According to an embodiment of the present invention, the operating status data of automobile parts is obtained, and the operating status data is preprocessed to obtain result information, which specifically includes:

[0107] Obtain the operating status data of automobile parts and extract data features;

[0108] Determine whether the data feature is within the set feature range;

[0109] If it is not in the set characteristic interval, the repeated data and abnormal data of the component operation status data are analyzed based on the data characteristics, and the repeated data and abnormal data of the operation status data are eliminated to obtain optimized data;

[0110] If it is within the set feature interval, the data features are averaged to obtain the result information.

[0111] It should be noted that by extracting features from the operating status data of automobile parts and filtering out duplicate data and abnormal data based on the extracted features, the operating status data is optimized and the accuracy of the operating status data is improved.

[0112] According to an embodiment of the present invention, a failure analysis model is constructed based on big data, specifically including:

[0113] Obtain the type of automobile parts, and based on the type of automobile parts, obtain the historical failure analysis data of the corresponding type to obtain a training set;

[0114] Build an initial model, iteratively train the initial model based on the training set, and obtain the training results;

[0115] Determine whether the training results converge;

[0116] If converged, a failure analysis model is generated;

[0117] If it does not converge, correction information is generated, and model parameters of the initial model are dynamically adjusted based on the correction information until the model converges.

[0118] It should be noted that by continuously training the initial model and dynamically adjusting the model parameters of the initial model during the training process, the analysis accuracy of the failure analysis model is continuously improved.

[0119] According to an embodiment of the present invention, a failure analysis model is constructed based on big data, result information is input into the failure analysis model, and component failure status information is output, specifically including:

[0120] Input the result information into the failure analysis model to obtain component failure data;

[0121] Obtain the type of automobile parts and the failure assessment rules based on the type matching standard of automobile parts;

[0122] Evaluate component failure data based on standard failure assessment rules to obtain failure assessment information;

[0123] Dynamically optimize and adjust the model parameters of the failure analysis model based on failure assessment information.

[0124] It should be noted that different types of automobile parts have different failure assessment rules. The failure status of automobile parts is evaluated through the corresponding standard failure assessment rules, so as to reversely correct and adjust the model parameters of the failure analysis model and improve the output results of the failure analysis model to be closer to the actual results.

[0125] According to an embodiment of the present invention, analyzing component failure modes based on component failure state information, and analyzing component failure degree information based on component failure modes specifically include:

[0126] Obtaining component failure status information, matching component types based on the component failure status information, and obtaining a matching combination;

[0127] Filter out component failure modes based on component types within the matching combination;

[0128] The upper and lower limits of the failure degree range are established according to the failure mode of the component, the failure degree range of the failure state information of the component is analyzed, and the corresponding component failure degree information is generated.

[0129] It should be noted that when failure analysis is performed on different types of components, it is necessary to select corresponding different failure degree intervals according to the type of component, and accurately analyze the failure degree of the component based on the failure degree interval analyzed according to the failure state of the component.

[0130] According to an embodiment of the present invention, analyzing the failure risk information of automobile parts based on the failure degree information of parts specifically includes:

[0131] Obtain information on the degree of failure of components, predict the operating risk of components based on the risk prediction model, and obtain prediction information;

[0132] Analyze the accuracy of forecast information based on the principle of contradiction;

[0133] Determine whether the accuracy is greater than or equal to the set accuracy threshold;

[0134] If it is greater than or equal to, then component failure risk information is generated;

[0135] If it is less than, feedback information is generated and the parameters of the risk prediction model are adjusted based on the feedback information.

[0136] It should be noted that the operating risk of components is predicted based on the failure degree information of different components, so as to accurately analyze the accuracy of the prediction information, and the failure state of automobile components is reversely verified based on the prediction, so as to accurately obtain the failure risk information of components and improve the accuracy of component analysis.

[0137] A third aspect of the present invention provides a computer-readable storage medium, which includes an automobile component failure analysis detection method program. When the automobile component failure analysis detection method program is executed by a processor, the steps of any of the above-mentioned automobile component failure analysis detection methods are implemented.

[0138] The present invention discloses a method, system and medium for failure analysis and detection of automobile parts. The method obtains operation status data of automobile parts, pre-processes the operation status data and obtains result information; constructs a failure analysis model based on big data, inputs the result information into the failure analysis model and outputs component failure status information; analyzes component failure modes based on component failure status information, and analyzes component failure degree information according to component failure modes; analyzes automobile component failure risk information based on component failure degree information; transmits automobile component failure risk information to a terminal in real time according to a predetermined method; and analyzes automobile component operation status data by constructing a failure analysis model, thereby accurately monitoring component failure states and improving failure risk warning of automobile parts.

[0139] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0140] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0141] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0142] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, the aforementioned program can be stored in a readable storage medium, and when the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0143] Or, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A method for failure analysis of automobile parts, characterized in that: include: Obtain the operating status data of automobile parts, pre-process the operating status data, and obtain result information; Build a failure analysis model based on big data, input the result information into the failure analysis model, and output the failure status information of the components; Analyze component failure modes based on component failure status information, and analyze component failure degree information based on component failure modes; Analyze the failure risk information of automobile parts based on the failure degree information of parts; The failure risk information of automobile parts is transmitted to the terminal in real time according to the predetermined method.

2. The automobile parts failure analysis detection method according to claim 1, characterized in that: Obtain the operating status data of automobile parts, pre-process the operating status data, and obtain result information, including: Obtain the operating status data of automobile parts and extract data features; Determining whether the data feature is within a set feature interval; If it is not in the set characteristic interval, the repeated data and abnormal data of the component operation status data are analyzed based on the data characteristics, and the repeated data and abnormal data of the operation status data are eliminated to obtain optimized data; If it is within the set feature interval, the data features are averaged to obtain the result information.

3. The automobile parts failure analysis detection method according to claim 2, characterized in that: Build failure analysis models based on big data, including: Obtain the type of automobile parts, and based on the type of automobile parts, obtain the historical failure analysis data of the corresponding type to obtain a training set; Build an initial model, iteratively train the initial model based on the training set, and obtain the training results; Determining whether the training result converges; If converged, a failure analysis model is generated; If it does not converge, correction information is generated, and model parameters of the initial model are dynamically adjusted based on the correction information until the model converges.

4. The automobile parts failure analysis detection method according to claim 3, characterized in that: Build a failure analysis model based on big data, input the result information into the failure analysis model, and output the failure status information of the components, including: Input the result information into the failure analysis model to obtain component failure data; Obtain the type of automobile parts and the failure assessment rules based on the type matching standard of automobile parts; Evaluate component failure data based on standard failure assessment rules to obtain failure assessment information; Dynamically optimize and adjust the model parameters of the failure analysis model based on failure assessment information.

5. The automobile parts failure analysis detection method according to claim 4, characterized in that: Analyze component failure modes based on component failure status information, and analyze component failure degree information based on component failure modes, including: Obtaining component failure status information, matching component types based on the component failure status information, and obtaining a matching combination; Filter out component failure modes based on component types within the matching combination; The upper and lower limits of the failure degree range are established according to the failure mode of the component, the failure degree range of the failure state information of the component is analyzed, and the corresponding component failure degree information is generated.

6. The automobile parts failure analysis detection method according to claim 5, characterized in that: Analyze the failure risk information of automobile parts based on the failure degree information of parts, including: Obtain information on the degree of failure of components, predict the operating risk of components based on the risk prediction model, and obtain prediction information; Analyze the accuracy of forecast information based on the principle of contradiction; Determine whether the accuracy is greater than or equal to the set accuracy threshold; If it is greater than or equal to, then component failure risk information is generated; If it is less than, feedback information is generated and the parameters of the risk prediction model are adjusted based on the feedback information.

7. An automobile parts failure analysis and detection system, characterized in that: The system includes: a memory and a processor, wherein the memory includes a program of a method for analyzing and detecting failure of automobile parts, and when the program of the method for analyzing and detecting failure of automobile parts is executed by the processor, the following steps are implemented: Obtain the operating status data of automobile parts, pre-process the operating status data, and obtain result information; Build a failure analysis model based on big data, input the result information into the failure analysis model, and output the failure status information of the components; Analyze component failure modes based on component failure status information, and analyze component failure degree information based on component failure modes; Analyze the failure risk information of automobile parts based on the failure degree information of parts; The failure risk information of automobile parts is transmitted to the terminal in real time according to the predetermined method.

8. The automobile parts failure analysis and detection system according to claim 7, characterized in that: Obtain the operating status data of automobile parts, pre-process the operating status data, and obtain result information, including: Obtain the operating status data of automobile parts and extract data features; Determining whether the data feature is within a set feature interval; If it is not in the set characteristic interval, the repeated data and abnormal data of the component operation status data are analyzed based on the data characteristics, and the repeated data and abnormal data of the operation status data are eliminated to obtain optimized data; If it is within the set feature interval, the data features are averaged to obtain the result information.

9. The automobile parts failure analysis and detection system according to claim 8, characterized in that: Build failure analysis models based on big data, including: Obtain the type of automobile parts, and based on the type of automobile parts, obtain the historical failure analysis data of the corresponding type to obtain a training set; Build an initial model, iteratively train the initial model based on the training set, and obtain the training results; Determining whether the training result converges; If converged, a failure analysis model is generated; If it does not converge, correction information is generated, and model parameters of the initial model are dynamically adjusted based on the correction information until the model converges.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes an automobile component failure analysis detection method program, and when the automobile component failure analysis detection method program is executed by a processor, the steps of the automobile component failure analysis detection method according to any one of claims 1 to 6 are implemented.

Images