Method for monitoring abnormal state of automobile electric control equipment based on running state

Abstract

The invention relates to an automobile electric control equipment abnormal state monitoring method based on an operation state, and the method comprises the steps: constructing abnormal event big data of an automobile electric control equipment assembly, carrying out the time domain analysis of the abnormal event big data, obtaining an abnormal event vector of the automobile electric control equipment assembly, and obtaining the abnormal event vector of the automobile electric control equipment assembly; training an abnormal event identification model of the automobile electric control equipment assembly; acquiring real-time operation data of the automobile electric control equipment component, substituting the real-time operation data into the abnormal event identification model of the automobile electric control equipment component, and generating abnormal event confidence of the automobile electric control equipment component in the operation state; establishing an abnormal event confidence coefficient curve of the automobile electric control equipment component; analyzing the development trend of the abnormal event confidence coefficient curve, and evaluating the running trend vector of the automobile electric control equipment component; and judging whether the running trend vector of the automobile electric control equipment component exceeds the normal running range interval of the automobile equipment component or not. The method has the advantages that potential faults are warned in time, and the running safety of the automobile is improved.

Description

Technical Field

[0001] The present invention relates to the field of electronic control, and in particular to a method for monitoring abnormal state of automobile electronic control equipment under running state. Background Art

[0002] Automotive electronic control equipment refers to a collection of equipment systems that are integrated inside the car and use electronic and computer technologies to precisely control and manage systems such as the engine, transmission, braking, steering, and body stability.

[0003] Because the existing abnormal monitoring technology for automotive electronic control equipment has a lag problem, that is, it is often detected only when a fault has already occurred or is about to cause an unsafe condition, the safety performance of the vehicle is reduced. Secondly, it can easily pose a potential threat to the driver's life safety. Summary of the invention

[0004] The present invention aims at the technical problems existing in the prior art and provides a method for monitoring the abnormal state of an automobile electronic control device under a running state.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: A method for monitoring abnormal state of automotive electronic control equipment under running state, comprising: Based on the automobile OBD interface, the historical abnormal operation data of automobile electronic control equipment components is obtained to build abnormal event big data of automobile electronic control equipment components; Based on constructing abnormal event big data of automotive electronic control equipment components, time domain analysis is performed on the abnormal event big data to obtain abnormal event vectors of automotive electronic control equipment components; Based on the abnormal event vectors of the automotive electronic control equipment components, train the abnormal event recognition model of the automotive electronic control equipment components; Based on the automobile ECU interface, obtain the real-time operation data of automobile electronic control equipment components; Substituting the real-time operation data of the automotive electronic control device component into the abnormal event recognition model of the automotive electronic control device component to generate the abnormal event confidence of the automotive electronic control device component in the operating state; Establishing an abnormal event confidence curve of the automotive electronic control equipment component according to the abnormal event confidence of the automotive electronic control equipment component in the operating state corresponding to the real-time operating data of the automotive electronic control equipment component; Based on the abnormal event confidence curve of the automotive electronic control equipment component, analyze the development trend of the abnormal event confidence curve and evaluate the operation trend vector of the automotive electronic control equipment component; Determine whether the operating trend vector of the automotive electronic control equipment component exceeds the normal operating range of the automotive equipment component. If not, continue monitoring. If so, issue an alarm.

[0006] Preferably, based on constructing abnormal event big data of automotive electronic control equipment components, performing time domain analysis on the abnormal event big data, obtaining the abnormal event vector of the automotive electronic control equipment components specifically includes: Pre-processing of abnormal event big data of automotive electronic control equipment components; Based on the construction of abnormal event big data of automotive electronic control equipment components, the accumulated running time of automotive electronic control equipment components is used as the observation window to construct the time series big data of observed abnormal events of automotive electronic control equipment components; Extracting the operating signal parameters of the electronic control equipment components corresponding to the abnormal event time series big data within the observation window, calculating the time domain characteristics of the operating signal parameters of the electronic control equipment components, and obtaining the observed abnormal event time domain characteristic data of the automotive electronic control equipment components; Using Fourier algorithm, the time domain feature data of observed abnormal events are converted into frequency domain feature data of observed abnormal events, and the frequency domain feature matrix of observed abnormal events is established; Using principal component analysis, we screen the frequency domain features of each abnormal event for the observed frequency domain feature matrix, and obtain the abnormal event vector of the automotive electronic control equipment component. The Fourier algorithm is specifically:

[0007] In the formula, It is the time domain characteristic data of observed abnormal events of automotive electronic control equipment components. Big data on the time series of abnormal events observed in automotive electronic control equipment components. is a complex exponential function, is the time integral; The principal component analysis method is specifically as follows:

[0008] In the formula, is the abnormal event vector of the automotive electronic control equipment component, is the diagonal matrix of the frequency domain feature matrix of the observed abnormal event, is the transposed matrix of the frequency domain feature matrix of the observed abnormal event, is the frequency domain feature matrix of observed abnormal events, is the first The principal component weights.

[0009] Preferably, based on the abnormal event vector of the automotive electronic control device component, training the abnormal event recognition model of the automotive electronic control device component specifically includes: According to the abnormal event vector of the automotive electronic control device component, positive and negative sample annotation is performed on the abnormal event big data of the automotive electronic control device component to obtain positive and negative label data samples of the abnormal event of the automotive electronic control device component; Taking the positive and negative label data samples of abnormal events of automotive electronic control equipment components as input, training the SVM support vector machine, taking the accuracy of abnormal event label recognition as the training goal, and minimizing the loss function of the model as the training end goal, to generate an abnormal event recognition model for automotive electronic control equipment components; The abnormal event recognition model of the automotive electronic control equipment component is specifically:

[0010] In the formula, is the classification function of SVM support vector machine, is the symbolic function, is the positive and negative label of the abnormal event corresponding to the i-th data sample, is the kernel function, The positive and negative label data samples of abnormal events of automotive electronic control equipment components, is the i-th data sample of the positive and negative labels of abnormal events of automotive electronic control equipment components, is the bias term of the classification hyperplane, is the Lagrange multiplier of the ith data sample, and n is the total number of data samples.

[0011] Preferably, the real-time operation data of the automobile electronic control device component is substituted into the abnormal event recognition model of the automobile electronic control device component to generate the abnormal event confidence of the automobile electronic control device component in the operating state; Standardize the big data of abnormal events and real-time operation data of automotive electronic control equipment components; Substituting the abnormal event big data of the automotive electronic control equipment component and the real-time operation data of the automotive electronic control equipment component into the abnormal event recognition model of the automotive electronic control equipment component to obtain the decision boundary of the abnormal event big data and the decision boundary of the real-time operation data; The spatial distance between the decision boundary based on abnormal event big data and the decision boundary of real-time operation data is calculated and normalized to obtain the abnormal event confidence of the automotive electronic control equipment components in the operating state; The confidence level of abnormal events of the automotive electronic control equipment components in the operating state specifically includes:

[0012] In the formula, In the running state The first automotive electronic control equipment component The confidence level of an abnormal event, is the decision boundary of abnormal event big data, Decision boundary for real-time operational data. is the median function.

[0013] Preferably, based on the abnormal event confidence curve of the automotive electronic control device component, analyzing the abnormal event confidence curve development trend, and evaluating the operation trend vector of the automotive electronic control device component specifically include: Based on AR autoregression, an abnormal state monitoring model for automotive electronic control equipment components is established; Substituting the real-time operation data of the automotive electronic control equipment component into the abnormal state monitoring model of the automotive electronic control equipment component, using the abnormal event confidence of the automotive electronic control equipment component in the operating state as the autoregressive coefficient, and predicting and analyzing the operation trend vector of the automotive electronic control equipment component; The abnormal state monitoring model of the automotive electronic control equipment component is specifically:

[0014] In the formula, is the operating trend vector of the automotive electronic control equipment components, For the Real-time operating data of automotive electronic control equipment components at each moment, is the autoregressive coefficient of the pth autoregressive order.

[0015] The beneficial effects of the present invention are: obtaining historical abnormal data of electronic control equipment components through the automobile OBD interface, constructing abnormal event big data, and training abnormal event recognition models based on these data, using the automobile ECU interface to obtain real-time operation data, substituting into the model to generate abnormal event confidence, and establishing a confidence curve to evaluate the abnormal trend of electronic control equipment components. If the abnormal trend exceeds the normal operating range, an alarm is issued. The beneficial effect is that the abnormal state of automobile electronic control equipment can be monitored in real time, potential faults can be warned in time, and the safety and reliability of automobile operation can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of a method for monitoring abnormal state of automotive electronic control equipment under operating state; Figure 2 A flow chart of a method for obtaining abnormal event vectors of automotive electronic control equipment components; Figure 3 A flow chart of a method for training an abnormal event recognition model for automotive electronic control equipment components; Figure 4 A flow chart of a method for generating confidence levels of abnormal events of automotive electronic control equipment components in a running state; Figure 5A flow chart of a method for evaluating the operating trend vector of an automotive electronic control device component according to the present invention; Figure 6 A schematic diagram of an electronic device according to an embodiment of the present invention; Figure 7 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0018] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0019] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. In order to enable any technician in the field to implement and use the present invention, the following description is given. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details that make the description of the present invention obscure. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0020] Example 1, reference Figure 1 As shown, a method for monitoring abnormal state of automotive electronic control equipment under running state specifically includes: Based on the automobile OBD interface, the historical abnormal operation data of automobile electronic control equipment components is obtained to build abnormal event big data of automobile electronic control equipment components; Based on constructing abnormal event big data of automotive electronic control equipment components, time domain analysis is performed on the abnormal event big data to obtain abnormal event vectors of automotive electronic control equipment components; Based on the abnormal event vectors of the automotive electronic control equipment components, train the abnormal event recognition model of the automotive electronic control equipment components; Based on the automobile ECU interface, obtain the real-time operation data of automobile electronic control equipment components; Substituting the real-time operation data of the automotive electronic control device component into the abnormal event recognition model of the automotive electronic control device component to generate the abnormal event confidence of the automotive electronic control device component in the operating state; Establishing an abnormal event confidence curve of the automotive electronic control equipment component according to the abnormal event confidence of the automotive electronic control equipment component in the operating state corresponding to the real-time operating data of the automotive electronic control equipment component; Based on the abnormal event confidence curve of the automotive electronic control equipment component, analyze the development trend of the abnormal event confidence curve and evaluate the operation trend vector of the automotive electronic control equipment component; Determine whether the operating trend vector of the automotive electronic control equipment component exceeds the normal operating range of the automotive equipment component. If not, continue monitoring. If so, issue an alarm.

[0021] This solution obtains historical abnormal data of electronic control equipment components through the car OBD interface, builds abnormal event big data, and trains abnormal event recognition models based on these data. It uses the car ECU interface to obtain real-time operation data, substitutes it into the model to generate abnormal event confidence, and establishes a confidence curve to evaluate the abnormal trend of electronic control equipment components. If the abnormal trend exceeds the normal operating range, an alarm is issued. The beneficial effect is that it can monitor the abnormal state of automotive electronic control equipment in real time, warn potential faults in time, and improve the safety and reliability of vehicle operation.

[0022] Reference Figure 2 As shown, based on constructing the abnormal event big data of the automotive electronic control equipment components, the time domain analysis is performed on the abnormal event big data to obtain the abnormal event vector of the automotive electronic control equipment components, which specifically includes: Pre-processing of abnormal event big data of automotive electronic control equipment components; Based on the construction of abnormal event big data of automotive electronic control equipment components, the accumulated running time of automotive electronic control equipment components is used as the observation window to construct the time series big data of observed abnormal events of automotive electronic control equipment components; Extracting the operating signal parameters of the electronic control equipment components corresponding to the abnormal event time series big data within the observation window, calculating the time domain characteristics of the operating signal parameters of the electronic control equipment components, and obtaining the observed abnormal event time domain characteristic data of the automotive electronic control equipment components; Using Fourier algorithm, the time domain feature data of observed abnormal events are converted into frequency domain feature data of observed abnormal events, and the frequency domain feature matrix of observed abnormal events is established; Using principal component analysis, we screen the frequency domain features of each abnormal event for the observed frequency domain feature matrix, and obtain the abnormal event vector of the automotive electronic control equipment component. The Fourier algorithm is specifically:

[0023] In the formula, It is the time domain characteristic data of observed abnormal events of automotive electronic control equipment components. Big data on the time series of abnormal events observed in automotive electronic control equipment components. is a complex exponential function, is the time integral; The principal component analysis method is specifically as follows:

[0024] In the formula, is the abnormal event vector of the automotive electronic control equipment component, is the diagonal matrix of the frequency domain feature matrix of the observed abnormal event, is the transposed matrix of the frequency domain feature matrix of the observed abnormal event, is the frequency domain feature matrix of observed abnormal events, is the first The principal component weights.

[0025] It should be noted that the abnormal event big data in this solution refers to obtaining the abnormal operation data of the automotive electronic control equipment components corresponding to all automobile OBD interfaces of several maintenance sites of this type of vehicle, and classifying them according to the abnormal events corresponding to the abnormal operation data to construct the abnormal event big data of the automotive electronic control equipment components as the feature data judgment experience set for subsequent abnormal events.

[0026] As shown in 3, based on the abnormal event vector of the automotive electronic control device component, the abnormal event recognition model of the automotive electronic control device component is trained, which specifically includes: According to the abnormal event vector of the automotive electronic control device component, positive and negative sample annotation is performed on the abnormal event big data of the automotive electronic control device component to obtain positive and negative label data samples of the abnormal event of the automotive electronic control device component; Taking the positive and negative label data samples of abnormal events of automotive electronic control equipment components as input, training the SVM support vector machine, taking the accuracy of abnormal event label recognition as the training goal, and minimizing the loss function of the model as the training end goal, to generate an abnormal event recognition model for automotive electronic control equipment components; The abnormal event recognition model of the automotive electronic control equipment component is specifically:

[0027] In the formula, is the classification function of SVM support vector machine, is the symbolic function, is the positive and negative label of the abnormal event corresponding to the i-th data sample, is the kernel function, The positive and negative label data samples of abnormal events of automotive electronic control equipment components, is the i-th data sample of the positive and negative labels of abnormal events of automotive electronic control equipment components, is the bias term of the classification hyperplane, is the Lagrange multiplier of the ith data sample, and n is the total number of data samples.

[0028] It can be understood that by using the abnormal event vectors of automotive electronic control equipment components to annotate the big data with positive and negative samples, and based on this, training the SVM support vector machine, a model that can accurately identify abnormal events of electronic control equipment components is established, providing an efficient judgment method for the subsequent discovery of whether the real-time operation data of automotive electronic control equipment components is in an abnormal state.

[0029] Reference Figure 4 As shown, the real-time operation data of the automotive electronic control device component is substituted into the abnormal event recognition model of the automotive electronic control device component to generate the abnormal event confidence of the automotive electronic control device component in the operating state; Standardize the big data of abnormal events and real-time operation data of automotive electronic control equipment components; Substituting the abnormal event big data of the automotive electronic control equipment component and the real-time operation data of the automotive electronic control equipment component into the abnormal event recognition model of the automotive electronic control equipment component to obtain the decision boundary of the abnormal event big data and the decision boundary of the real-time operation data; The spatial distance between the decision boundary based on abnormal event big data and the decision boundary of real-time operation data is calculated and normalized to obtain the abnormal event confidence of the automotive electronic control equipment components in the operating state; The confidence level of abnormal events of the automotive electronic control equipment components in the operating state specifically includes:

[0030] In the formula, In the running state The first automotive electronic control equipment component The confidence level of an abnormal event, is the decision boundary of abnormal event big data, Decision boundary for real-time operational data. is the median function.

[0031] It is understandable that since the automobile ECU electronic control model will repeatedly request execution when facing an initially abnormal device component, the data of the electronic control device component is poorly correlated in the early stage of the abnormality and is not easy to be analyzed and mined. Therefore, the accuracy of abnormal analysis can be improved by increasing the confidence of real-time operating data for abnormal events.

[0032] Reference Figure 5 The above-mentioned, based on the abnormal event confidence curve of the automotive electronic control device component, analyzing the development trend of the abnormal event confidence curve, and evaluating the operation trend vector of the automotive electronic control device component specifically include: Based on AR autoregression, an abnormal state monitoring model for automotive electronic control equipment components is established; Substituting the real-time operation data of the automotive electronic control equipment component into the abnormal state monitoring model of the automotive electronic control equipment component, using the abnormal event confidence of the automotive electronic control equipment component in the operating state as the autoregressive coefficient, and predicting and analyzing the operation trend vector of the automotive electronic control equipment component; The abnormal state monitoring model of the automotive electronic control equipment component is specifically:

[0033] In the formula, is the operating trend vector of the automotive electronic control equipment components, For the Real-time operating data of automotive electronic control equipment components at each moment, is the autoregressive coefficient of the pth autoregressive order.

[0034] See also Figure 6 , Figure 6 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 6As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, the following steps are implemented: based on the automobile OBD interface, historical abnormal operation data of the automobile electronic control device component is obtained, and abnormal event big data of the automobile electronic control device component is constructed; based on the abnormal event big data of the automobile electronic control device component, time domain analysis is performed on the abnormal event big data to obtain the abnormal event vector of the automobile electronic control device component; based on the abnormal event vector of the automobile electronic control device component, an abnormal event recognition model of the automobile electronic control device component is trained; based on the automobile ECU interface, the abnormal event vector of the automobile electronic control device component is obtained. Real-time operation data of automotive electronic control equipment components; substituting the real-time operation data of automotive electronic control equipment components into the abnormal event recognition model of automotive electronic control equipment components to generate the abnormal event confidence of the automotive electronic control equipment components in the operating state; establishing the abnormal event confidence curve of the automotive electronic control equipment components according to the abnormal event confidence of the automotive electronic control equipment components in the operating state corresponding to the real-time operation data of the automotive electronic control equipment components; based on the abnormal event confidence curve of the automotive electronic control equipment components, analyzing the development trend of the abnormal event confidence curve and evaluating the operation trend vector of the automotive electronic control equipment components; judging whether the operation trend vector of the automotive electronic control equipment components exceeds the normal operating range of the automotive equipment components, if not, continue monitoring, and if yes, issue an alarm.

[0035] See also Figure 7 , Figure 7 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 7As shown, this embodiment provides a computer-readable storage medium 600, on which a computer program 611 is stored. When the computer program 611 is executed by a processor, the following steps are implemented: based on the automobile OBD interface, historical abnormal operation data of the automobile electronic control device component is obtained to construct abnormal event big data of the automobile electronic control device component; based on the construction of the abnormal event big data of the automobile electronic control device component, time domain analysis is performed on the abnormal event big data to obtain the abnormal event vector of the automobile electronic control device component; based on the abnormal event vector of the automobile electronic control device component, an abnormal event recognition model of the automobile electronic control device component is trained; based on the automobile ECU interface, real-time operation data of the automobile electronic control device component is obtained; Substitute the real-time operation data of the automotive electronic control equipment component into the abnormal event recognition model of the automotive electronic control equipment component to generate the abnormal event confidence of the automotive electronic control equipment component in the operating state; establish the abnormal event confidence curve of the automotive electronic control equipment component according to the abnormal event confidence of the automotive electronic control equipment component in the operating state corresponding to the real-time operation data of the automotive electronic control equipment component; analyze the development trend of the abnormal event confidence curve based on the abnormal event confidence curve of the automotive electronic control equipment component, and evaluate the operation trend vector of the automotive electronic control equipment component; determine whether the operation trend vector of the automotive electronic control equipment component exceeds the normal operating range of the automotive equipment component, if not, continue monitoring, and if yes, issue an alarm.

[0036] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0037] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0038] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0039] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0040] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0041] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0042] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for monitoring abnormal state of automotive electronic control equipment under running state, characterized in that: include: Based on the automobile OBD interface, the historical abnormal operation data of automobile electronic control equipment components is obtained to build abnormal event big data of automobile electronic control equipment components; Based on constructing abnormal event big data of automotive electronic control equipment components, time domain analysis is performed on the abnormal event big data to obtain abnormal event vectors of automotive electronic control equipment components; Based on the abnormal event vectors of the automotive electronic control equipment components, train the abnormal event recognition model of the automotive electronic control equipment components; Based on the automobile ECU interface, obtain the real-time operation data of automobile electronic control equipment components; Substituting the real-time operation data of the automotive electronic control device component into the abnormal event recognition model of the automotive electronic control device component to generate the abnormal event confidence of the automotive electronic control device component in the operating state; Establishing an abnormal event confidence curve of the automotive electronic control equipment component according to the abnormal event confidence of the automotive electronic control equipment component in the operating state corresponding to the real-time operating data of the automotive electronic control equipment component; Based on the abnormal event confidence curve of the automotive electronic control equipment component, analyze the development trend of the abnormal event confidence curve and evaluate the operation trend vector of the automotive electronic control equipment component; Determine whether the operating trend vector of the automotive electronic control equipment component exceeds the normal operating range of the automotive equipment component. If not, continue monitoring. If so, issue an alarm.

2. The method for monitoring abnormal state of automobile electronic control equipment in operation according to claim 1, characterized in that: Based on the construction of abnormal event big data of automotive electronic control equipment components, time domain analysis is performed on the abnormal event big data to obtain abnormal event vectors of automotive electronic control equipment components, including: Pre-processing of abnormal event big data of automotive electronic control equipment components; Based on the construction of abnormal event big data of automotive electronic control equipment components, the accumulated running time of automotive electronic control equipment components is used as the observation window to construct the time series big data of observed abnormal events of automotive electronic control equipment components; Extracting the operating signal parameters of the electronic control equipment components corresponding to the abnormal event time series big data within the observation window, calculating the time domain characteristics of the operating signal parameters of the electronic control equipment components, and obtaining the observed abnormal event time domain characteristic data of the automotive electronic control equipment components; Using Fourier algorithm, the time domain feature data of observed abnormal events are converted into frequency domain feature data of observed abnormal events, and the frequency domain feature matrix of observed abnormal events is established; Using principal component analysis, we screen the frequency domain features of each abnormal event for the observed frequency domain feature matrix, and obtain the abnormal event vector of the automotive electronic control equipment component. The Fourier algorithm is specifically: In the formula, It is the time domain characteristic data of observed abnormal events of automotive electronic control equipment components. Big data on the time series of abnormal events observed in automotive electronic control equipment components. is a complex exponential function, is the time integral; The principal component analysis method is specifically as follows: In the formula, is the abnormal event vector of the automotive electronic control equipment component, is the diagonal matrix of the frequency domain feature matrix of the observed abnormal event, is the transposed matrix of the frequency domain feature matrix of the observed abnormal event, is the frequency domain feature matrix of observed abnormal events, is the first The principal component weights.

3. The method for monitoring abnormal state of automobile electronic control equipment in operation according to claim 2, characterized in that: Based on the abnormal event vector of the automotive electronic control device component, the abnormal event recognition model of the automotive electronic control device component is trained including: According to the abnormal event vector of the automotive electronic control device component, positive and negative sample annotation is performed on the abnormal event big data of the automotive electronic control device component to obtain positive and negative label data samples of the abnormal event of the automotive electronic control device component; Taking the positive and negative label data samples of abnormal events of automotive electronic control equipment components as input, training the SVM support vector machine, taking the accuracy of abnormal event label recognition as the training goal, and minimizing the loss function of the model as the training end goal, to generate an abnormal event recognition model for automotive electronic control equipment components; The abnormal event recognition model of the automotive electronic control equipment component is specifically: In the formula, is the classification function of SVM support vector machine, is the symbolic function, is the positive and negative label of the abnormal event corresponding to the i-th data sample, is the kernel function, The positive and negative label data samples of abnormal events of automotive electronic control equipment components, is the i-th data sample of the positive and negative labels of abnormal events of automotive electronic control equipment components, is the bias term of the classification hyperplane, is the Lagrange multiplier of the ith data sample, and n is the total number of data samples.

4. The method for monitoring abnormal state of automobile electronic control equipment in operation according to claim 3, characterized in that: Substituting the real-time operation data of the automotive electronic control device component into the abnormal event recognition model of the automotive electronic control device component to generate the abnormal event confidence of the automotive electronic control device component in the operating state; Standardize the big data of abnormal events and real-time operation data of automotive electronic control equipment components; Substituting the abnormal event big data of the automotive electronic control equipment component and the real-time operation data of the automotive electronic control equipment component into the abnormal event recognition model of the automotive electronic control equipment component to obtain the decision boundary of the abnormal event big data and the decision boundary of the real-time operation data; The spatial distance between the decision boundary based on abnormal event big data and the decision boundary of real-time operation data is calculated and normalized to obtain the abnormal event confidence of the automotive electronic control equipment components in the operating state; The confidence level of abnormal events of the automotive electronic control equipment components in the operating state specifically includes: In the formula, In the running state The first automotive electronic control equipment component The confidence level of an abnormal event, is the decision boundary of abnormal event big data, Decision boundary for real-time operational data. is the median function.

5. The method for monitoring abnormal state of automobile electronic control equipment in operation according to claim 4, characterized in that: Based on the abnormal event confidence curve of the automotive electronic control equipment component, the development trend of the abnormal event confidence curve is analyzed, and the operating trend vector of the automotive electronic control equipment component is evaluated, including: Based on AR autoregression, an abnormal state monitoring model for automotive electronic control equipment components is established; Substituting the real-time operation data of the automotive electronic control equipment component into the abnormal state monitoring model of the automotive electronic control equipment component, using the abnormal event confidence of the automotive electronic control equipment component in the operating state as the autoregressive coefficient, and predicting and analyzing the operation trend vector of the automotive electronic control equipment component; The abnormal state monitoring model of the automotive electronic control equipment component is specifically: In the formula, is the operating trend vector of the automotive electronic control equipment components, For the Real-time operating data of automotive electronic control equipment components at each moment, is the autoregressive coefficient of the pth autoregressive order.

6. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the abnormal state monitoring method of automobile electronic control equipment based on the running state as described in any one of claims 1-5.

7. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, it implements the abnormal state monitoring method of the automobile electronic control equipment based on the running state as described in any one of claims 1 to 5.

Images