Dual redundant fault recognition method and device for seat control system

Abstract

This application relates to the field of vehicle intelligent control technology, and in particular to a dual-redundancy fault identification method and device for a seat control system. The method includes: acquiring first operating data of the seat control system and extracting principal component feature vectors; determining key feature vectors; determining the fault type when the key feature vectors meet preset fault conditions; generating a switching request signal from the main controller to the corresponding backup controller based on the fault type, second operating data, and third operating data; switching the main controller to the corresponding backup controller according to the switching request signal, and generating fault description information. This solves the problems in related technologies, such as insufficient consideration of signal synchronization, quality assessment, and switching decision optimization between the main and backup controllers, resulting in poor fault tolerance; low signal processing fault tolerance and high fault misjudgment rate when facing environmental interference; difficulty in balancing real-time performance and accuracy; and inability to quickly locate faults and generate effective decisions in dynamic scenarios.

Description

Technical Field

[0001] This application relates to the field of vehicle intelligent control technology, and in particular to a dual-redundancy fault identification method and device for a seat control system. Background Technology

[0002] In related technologies, by initializing a PC (Personal Computer), powering the underlying controller and sensors and downloading the control program, two experimental scenarios are set for the electric power-assisted braking system: normal and failure. In the event of failure, the electronic stability control system uses PWM (Pulse Width Modulation) control and PI (Proportional Integral) feedback control algorithms to achieve brake pressure compensation and complete the brake failure redundancy function.

[0003] However, the relevant technologies do not fully consider the synchronization of signals between the main and backup controllers, quality assessment, and optimization of switching decisions, making it difficult to achieve efficient fault tolerance; the signal processing fault tolerance rate is low and the fault misjudgment rate is high when facing environmental interference; and it is difficult to balance real-time performance and accuracy, making it impossible to quickly locate faults and generate effective decisions in dynamic scenarios, which urgently needs improvement. Summary of the Invention

[0004] This application provides a dual-redundancy fault identification method and device for a seat control system to solve the problems in related technologies, such as insufficient consideration of signal synchronization, quality assessment and switching decision optimization of the main and backup controllers, difficulty in efficient fault tolerance; low signal processing fault tolerance and high fault misjudgment rate when facing environmental interference; difficulty in balancing real-time performance and accuracy, and inability to quickly locate faults and generate effective decisions in dynamic scenarios.

[0005] A first aspect of this application provides a dual-redundancy fault identification method for a seat control system. The seat control system includes a main controller and at least one backup controller. The method includes the following steps: collecting first operating data of the seat control system and extracting corresponding principal component feature vectors from the first operating data; determining corresponding key feature vectors based on the principal component feature vectors and the first operating data; determining the fault type of the main controller when the key feature vectors satisfy preset fault conditions; generating a switching request signal for switching from the main controller to the corresponding backup controller based on the fault type, second operating data of the main controller, and third operating data corresponding to the at least one backup controller; switching the main controller to the corresponding backup controller according to the switching request signal, and generating fault description information of the main controller based on the fault type, the second operating data, and the third operating data.

[0006] Optionally, in one embodiment of this application, the step of extracting the corresponding principal component feature vector from the first running data includes: constructing a covariance matrix based on the first running data; determining the eigenvalues ​​and eigenvectors corresponding to the first running data based on the covariance matrix; and determining the principal component feature vectors in the feature vectors based on the eigenvalues.

[0007] Optionally, in one embodiment of this application, determining the corresponding key feature vector based on the principal component feature vector and the first operating data includes: determining an initial key feature vector based on the principal component feature vector and the first operating data; performing fault detection on the seat control system based on the initial key feature vector; if the fault identification accuracy of the seat control system is greater than a preset threshold, then using the initial key feature vector as the key feature vector; if the fault identification accuracy is less than or equal to the preset threshold, then re-determining the initial key feature vector until the fault identification accuracy is greater than the preset threshold, to obtain the key feature vector.

[0008] Optionally, in one embodiment of this application, generating fault description information of the main controller based on the fault type, the second operating data, and the third operating data includes: determining evaluation indicators for the second operating data and the third operating data based on the fault type; extracting a first fault signal that meets preset evaluation conditions from the second operating data and a second fault signal that meets the preset evaluation conditions from the third operating data based on the evaluation indicators; and obtaining the fault description information based on the first fault signal and the second fault signal.

[0009] Optionally, in one embodiment of this application, obtaining the fault description information based on the first fault signal and the second fault signal includes: obtaining weight information corresponding to the first fault signal and the second fault signal respectively; calculating a comprehensive feature vector based on the weight information, the first fault signal and the second fault signal; and obtaining the fault description information based on the fault points of the comprehensive feature vector.

[0010] Optionally, in one embodiment of this application, generating a switching request signal from the main controller to the corresponding backup controller based on the fault type, the second operating data of the main controller, and the third operating data corresponding to the at least one backup controller includes: calculating the data deviation between the second operating data and the third operating data based on the fault type; determining the switching priority of the corresponding backup controller based on the data deviation; and determining the switching request signal based on the switching priority.

[0011] A second aspect of this application provides a dual-redundancy fault identification device for a seat control system. The seat control system includes a main controller and at least one backup controller. The device includes: an extraction module for collecting first operating data of the seat control system and extracting corresponding principal component feature vectors from the first operating data; a first determination module for determining corresponding key feature vectors based on the principal component feature vectors and the first operating data; a second determination module for determining the fault type of the main controller when the key feature vectors satisfy preset fault conditions; a first generation module for generating a switching request signal for switching from the main controller to the corresponding backup controller based on the fault type, second operating data of the main controller, and third operating data corresponding to the at least one backup controller; and a second generation module for switching the main controller to the corresponding backup controller according to the switching request signal, and generating fault description information of the main controller based on the fault type, the second operating data, and the third operating data.

[0012] Optionally, in one embodiment of this application, the extraction module includes: a construction unit, configured to construct a covariance matrix based on the first running data; a first determination unit, configured to determine the eigenvalues ​​and eigenvectors corresponding to the first running data based on the covariance matrix; and a second determination unit, configured to determine the principal component eigenvectors in the eigenvectors based on the eigenvalues.

[0013] Optionally, in one embodiment of this application, the first determining module includes: a third determining unit, configured to determine an initial key feature vector based on the principal component feature vector and the first running data; a first generating unit, configured to perform fault detection on the seat control system based on the initial key feature vector, and if the fault identification accuracy of the seat control system is greater than a preset threshold, then the initial key feature vector is used as a key feature vector; and a second generating unit, configured to re-determine the initial key feature vector when the fault identification accuracy is less than or equal to the preset threshold, until the fault identification accuracy is greater than the preset threshold, so as to obtain the key feature vector.

[0014] Optionally, in one embodiment of this application, the second generation module includes: a fourth determining unit, configured to determine evaluation indicators for the second operating data and the third operating data based on the fault type; an extraction unit, configured to extract a first fault signal that meets preset evaluation conditions from the second operating data and a second fault signal that meets the preset evaluation conditions from the third operating data based on the evaluation indicators; and a third generation unit, configured to obtain the fault description information based on the first fault signal and the second fault signal.

[0015] Optionally, in one embodiment of this application, the third generation unit includes: an acquisition subunit, configured to acquire weight information corresponding to the first fault signal and the second fault signal respectively; a calculation subunit, configured to calculate a comprehensive feature vector based on the weight information, the first fault signal, and the second fault signal; and a generation subunit, configured to obtain the fault description information based on the fault points of the comprehensive feature vector.

[0016] Optionally, in one embodiment of this application, the first generation module includes: a calculation unit, configured to calculate the data deviation between the second operating data and the third operating data based on the fault type; a fifth determination unit, configured to determine the switching priority of the corresponding backup controller based on the data deviation; and a sixth determination unit, configured to determine the switching request signal based on the switching priority.

[0017] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a dual-redundancy fault identification method for a seat control system as described in the above embodiments.

[0018] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the dual-redundancy fault identification method for the seat control system described above.

[0019] A fifth aspect of this application provides a computer program product, including a computer program that, when executed, implements the dual-redundancy fault identification method for the seat control system described above.

[0020] This application embodiment can extract the corresponding principal component feature vector from the first operating data of the seat control system, and then determine the corresponding key feature vector. When the key feature vector meets the preset fault conditions, the fault type of the main controller is determined. Based on the fault type, the second operating data of the main controller, and the third operating data of at least one backup controller, a switching request signal is generated to switch the main controller to the corresponding backup controller. The main controller is switched to the corresponding backup controller according to the switching request signal, thereby obtaining the corresponding fault description information. By extracting principal component features to compress data dimensions and eliminate redundant interference, and relying on feature thresholds to achieve accurate fault determination, combined with multi-controller operating data linkage comparison, rapid redundant switching and fault information synchronization and archiving are completed, effectively improving the fault identification accuracy and the continuity and reliability of control operation of the seat control system. Thus, it solves the problems in related technologies, such as insufficient consideration of the synchronization, quality assessment and switching decision optimization of the main and backup controller signals, difficulty in efficient fault tolerance; low signal processing fault tolerance and high fault misjudgment rate when facing environmental interference; difficulty in balancing real-time performance and accuracy, and inability to quickly locate faults and generate effective decisions in dynamic scenarios.

[0021] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0022] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a dual-redundancy fault identification method for a seat control system provided according to an embodiment of this application; Figure 2 This is a flowchart illustrating the working principle of a dual-redundancy fault identification method for a seat control system according to an embodiment of this application; Figure 3 This is a block diagram of a dual-redundant fault identification device for a seat control system provided according to an embodiment of this application; Figure 4 This is a structural schematic diagram of a vehicle provided according to an embodiment of this application. Detailed Implementation

[0023] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0024] The following description, with reference to the accompanying drawings, describes a dual-redundancy fault identification method and apparatus for a seat control system according to an embodiment of this application. To address the issues mentioned in the background technology, such as insufficient consideration of signal synchronization, quality assessment, and switching decision optimization between primary and backup controllers, resulting in inefficient fault tolerance; low signal processing fault tolerance and high fault misjudgment rate when facing environmental interference; and difficulty in balancing real-time performance and accuracy, making it impossible to quickly locate faults and generate effective decisions in dynamic scenarios, this application provides a dual-redundancy fault identification method for a seat control system. In this method, principal component feature vectors are extracted from the first operating data of the seat control system to determine the corresponding key feature vectors. When the key feature vectors meet preset fault conditions, the fault type of the primary controller is determined. Based on the fault type, the second operating data of the primary controller, and the third operating data corresponding to at least one backup controller, a switching request signal is generated to switch the primary controller to the corresponding backup controller. The primary controller is then switched to the corresponding backup controller according to the switching request signal, thereby obtaining the corresponding fault description information. By extracting principal component features to compress data dimensions and eliminate redundant interference, accurate fault determination is achieved based on feature thresholds. Combined with multi-controller operating data linkage comparison, rapid redundancy switching and fault information synchronization and archiving are completed, effectively improving the fault identification accuracy and the continuity and reliability of control operation in the seat control system. This solves the problems in related technologies, such as insufficient consideration of signal synchronization, quality assessment and switching decision optimization between primary and backup controllers, difficulty in efficient fault tolerance; low signal processing fault tolerance and high fault misjudgment rate when facing environmental interference; difficulty in balancing real-time performance and accuracy, and inability to quickly locate faults and generate effective decisions in dynamic scenarios.

[0025] Specifically, Figure 1 This is a flowchart of a dual-redundancy fault identification method for a seat control system provided according to an embodiment of this application.

[0026] like Figure 1 As shown, the dual-redundancy fault identification method for the seat control system includes a main controller and at least one backup controller. The method includes the following steps: In step S101, the first operating data of the seat control system is collected, and the corresponding principal component feature vector is extracted from the first operating data.

[0027] It is understood that, in the embodiments of this application, the seat control system can be understood as an electronic or mechanical system in a vehicle used to adjust parameters such as seat position, angle, height, and tilt, in order to improve passenger comfort and riding experience.

[0028] The first operating data can be understood as various data generated by the seat control system during normal operation. It can be obtained from the controller operating data, sensor signals and actuator feedback, such as operating status, signal strength and feedback delay, according to the control authority of the seat control system. This application does not impose specific limitations.

[0029] Principal component eigenvectors can be understood as a set of vectors extracted from the first set of operating data through PCA (Principal Component Analysis) that represent the main features of the data. They can reflect the main change patterns and trends of the seat control system's operating status, which is helpful for subsequent data analysis, fault diagnosis, and performance optimization.

[0030] PCA is a statistical method that transforms original data into a new set of uncorrelated variables through orthogonal transformation. These uncorrelated variables are called principal components, used to reduce data redundancy, improve data processing efficiency, and reveal potential structures and patterns in the data. Furthermore, in this embodiment of the application, the eigenvectors in PCA correspond to the eigenvectors of the data covariance matrix; these are vectors that maintain their direction during linear transformation and can only be scaled proportionally.

[0031] As one possible approach, embodiments of this application may first collect the first operating data of the seat control system and extract the corresponding principal component feature vector from the first operating data.

[0032] For example, in this application embodiment, control authority of the seat control system can be obtained first, and the operating status, signal strength, and feedback delay can be obtained from the controller operating data, sensor signals, and actuator feedback according to the control authority. Time series sampling is used to determine the sampling frequency and sampling time. For example, in the seat adjustment start-up stage, the sampling time can be 0-0.5 seconds and the sampling frequency can be 500Hz; in the steady-state operation stage, the sampling time can be 0.5 seconds and the sampling frequency can be 100Hz; when a fault is triggered, the sampling frequency can be 2000Hz. The specific sampling time and sampling frequency can be set by those skilled in the art according to the actual situation, and this application does not impose specific limitations.

[0033] Furthermore, in this embodiment of the application, the initial first running data is determined based on the acquisition frequency and sampling time, and preprocessed, such as data cleaning and format conversion, to obtain the first running data. By acquiring and preprocessing multi-source data, the integrity and consistency of the first running data are ensured, the accuracy of subsequent analysis is improved, and the risk of misjudgment caused by missing data or noise is effectively reduced.

[0034] Data cleaning can be understood as the process of improving data quality by identifying, correcting, or removing erroneous, duplicate, inconsistent, or missing values ​​in a dataset, eliminating noise and anomalies, and ensuring the accuracy of subsequent analysis. It may include, but is not limited to, outlier detection, missing value handling, duplicate value handling, and logical error correction.

[0035] Outlier detection can be understood as identifying data points that deviate from the normal range based on statistical methods (such as the 3σ principle, box plots, etc., which are not specifically limited in this application) or machine learning models (such as isolated forests, which are not specifically limited in this application).

[0036] Missing value handling can be understood as directly deleting samples containing missing values ​​(applicable when the missing rate is low) or filling in the missing values ​​through imputation strategies (such as mean, median, interpolation, etc., which are not specifically limited in this application).

[0037] Duplicate value handling can be understood as identifying and merging duplicate records through hash algorithms or similarity comparisons.

[0038] Logical error correction can be understood as correcting contradictory data according to business rules (such as seat position cannot be negative, etc., this application does not impose specific restrictions).

[0039] Format conversion can be understood as the process of converting data from one storage or transmission format to another to adapt to the needs of different systems or algorithms and solve data compatibility issues. It can include, but is not limited to, structure conversion, encoding conversion, unit standardization, and protocol conversion.

[0040] In this context, structured transformation can be understood as converting unstructured data (such as text logs) into structured tables (such as CSV (Comma Separated Values), etc., which are not specifically limited in this application).

[0041] Encoding conversion can be understood as converting a unified character encoding (such as UTF-8 (8-bit Unicode Transformation Format) to ASCII (American Standard Code for Information Interchange), etc., which is not specifically limited in this application) or a numeric type (such as converting a floating-point number to an integer, etc., which is not specifically limited in this application).

[0042] Unit standardization can be understood as standardizing data or timestamps from different units.

[0043] Protocol conversion can be understood as converting the sensor's original protocol (such as CAN (Controller Area Network) bus, etc., which is not specifically limited in this application) into a common format (such as JSON (JavaScript Object Notation), XML (Extensible Markup Language, etc., which is not specifically limited in this application).

[0044] Furthermore, in this embodiment of the application, for the first running data, a principal component analysis algorithm is used to perform feature selection and transformation, determine the principal component weights and data dimensions, and generate principal component feature vectors.

[0045] Optionally, in one embodiment of this application, extracting the corresponding principal component eigenvectors from the first running data includes: constructing a covariance matrix based on the first running data; determining the eigenvalues ​​and eigenvectors corresponding to the first running data based on the covariance matrix; and determining the principal component eigenvectors in the eigenvectors based on the eigenvalues.

[0046] It is understood that, in the embodiments of this application, the principal component eigenvectors are the vectors corresponding to the larger eigenvalues ​​in the covariance matrix eigenvectors, used to define the main direction of change of the data. They can be sorted according to the size of the eigenvalues, and the first k eigenvectors are taken to form the principal component space. Among them, k can be set by those skilled in the art according to the actual situation, and this application does not impose specific limitations.

[0047] As one possible implementation method, embodiments of this application can first construct a covariance matrix based on the first running data, and determine the corresponding eigenvalues ​​and eigenvectors based on the covariance matrix, and then determine the principal component eigenvectors in the eigenvectors based on the eigenvalues.

[0048] For example, this application embodiment can use PCA for feature selection and transformation to determine the principal component weights and data dimensions, thereby obtaining the corresponding principal component eigenvectors. The main content is as follows: First, calculate the covariance matrix of the first running data, and determine the corresponding eigenvalues ​​and eigenvectors based on the covariance matrix. Then, arrange the eigenvalues ​​in descending order to determine the principal component contribution rate, and select the top k eigenvectors whose cumulative contribution rate reaches a preset contribution rate threshold as principal component eigenvectors. This projects the first running data onto the low-dimensional space spanned by the principal component eigenvectors, achieving data dimension reduction and feature transformation, thereby obtaining a new feature set after dimensionality reduction. The preset contribution rate threshold can be set by those skilled in the art according to actual conditions, and this application does not impose specific limitations.

[0049] Furthermore, in some embodiments, the main content of determining the principal component eigenvectors based on PCA in this application embodiment is as follows: by calculating the covariance matrix and eigenvalue decomposition of the first running data, the corresponding eigenvalues ​​and eigenvectors are obtained. The eigenvalues ​​represent the variance explained by each principal component, and the eigenvalues ​​are sorted from largest to smallest. The variance contribution rate and cumulative contribution rate of each principal component are calculated. A preset contribution rate threshold corresponding to the cumulative contribution rate is set. The top few principal components with cumulative contribution rates greater than the preset contribution rate threshold are selected as key dimensions. The principal component eigenvectors are constructed based on the selected principal components and their corresponding eigenvectors, ensuring that the main information of the seat control system's operating status is retained while reducing data redundancy and computational complexity.

[0050] In step S102, the corresponding key feature vectors are determined based on the principal component feature vectors and the first running data.

[0051] As one possible implementation method, embodiments of this application can determine the corresponding key feature vector based on the principal component feature vector and the first running data.

[0052] Optionally, in one embodiment of this application, determining the corresponding key feature vector based on the principal component feature vector and the first operating data includes: determining an initial key feature vector based on the principal component feature vector and the first operating data; performing fault detection on the seat control system based on the initial key feature vector; if the fault identification accuracy of the seat control system is greater than a preset threshold, then using the initial key feature vector as the key feature vector; if the fault identification accuracy is less than or equal to the preset threshold, then re-determining the initial key feature vector until the fault identification accuracy is greater than the preset threshold, so as to obtain the key feature vector.

[0053] In some embodiments, this application can combine principal component feature vectors with first operating data to obtain an initial key feature vector, and use the initial key feature vector to perform fault detection on the seat control system. The initial key feature vector is then iteratively updated based on the comparison between the fault identification accuracy and a preset threshold until the fault identification accuracy exceeds the preset threshold, thereby determining the final key feature vector. Specifically, this application can directly use the initial key feature vector as the key feature vector if the fault identification accuracy exceeds the preset threshold; otherwise, the initial key feature vector is re-determined until the fault identification accuracy exceeds the preset threshold to obtain the final key feature vector.

[0054] In addition, the preset threshold can be set by those skilled in the art according to the actual situation, and this application does not impose any specific restrictions.

[0055] For example, in this embodiment of the application, the principal component feature vector and the first running data can be input into a pre-constructed convolutional neural network. Then, the convolutional neural network is used to extract the dynamic characteristics of sensor signals and actuator feedback in the seat control system, generate an initial key feature vector, and perform anomaly detection in combination with a preset threshold. If the fault identification accuracy is less than or equal to the preset threshold, the convolutional kernel size, stride and number of network layers are dynamically adjusted through backpropagation, and feature extraction is performed again until the fault identification accuracy is greater than the preset threshold. Otherwise, the initial key feature vector is directly used as the key feature vector, and the convolutional neural network is used to extract dynamic characteristics and optimize features to ensure accurate identification of complex time-series data, improve the fault tolerance rate of anomaly detection, and reduce false alarms and false negatives.

[0056] In addition, in the anomaly detection process, the embodiments of this application can use a convolutional neural network to perform denoising and normalization preprocessing on the first running data to reduce noise interference in the original data and ensure the accuracy of subsequent feature extraction and fault detection results. This preprocessing method can be flexibly selected according to the actual working conditions, and this application does not impose specific restrictions.

[0057] Furthermore, the convolutional neural network used in this application can be configured by those skilled in the art according to the actual situation, and this application does not impose any specific restrictions.

[0058] In step S103, when the key feature vector meets the preset fault conditions, the fault type of the main controller is determined.

[0059] It is understood that, in the embodiments of this application, the fault types may include, but are not limited to, sensor faults, actuator faults, communication faults, power supply faults, and software logic faults.

[0060] Among them, sensor failure can be understood as damage to sensor hardware or abnormal signal in the seat control system; actuator failure can be understood as the actuator in the seat control system failing to respond to control commands normally; communication failure can be understood as interruption or delay in data communication between the main and backup controllers or with external modules in the seat control system; power failure can be understood as unstable voltage or power failure of the power supply module in the seat control system; software logic failure can be understood as program infinite loop, parameter configuration error or status judgment error, causing the system to deviate from the expected operation. The specific settings can be made by those skilled in the art according to the actual situation, and this application does not impose specific limitations.

[0061] In actual implementation, the embodiments of this application can determine the fault type of the main controller when the key feature vector meets the preset fault conditions. The preset fault conditions can be set by those skilled in the art according to actual circumstances, and this application does not impose specific limitations.

[0062] For example, in this embodiment of the application, when the fluctuation amplitude of the key feature vector exceeds a preset fluctuation threshold, it can be determined that the key feature vector meets a preset fault condition. A support vector machine classifier is then used to classify the key feature vector to obtain a fault type label for the seat control system, thereby determining the corresponding fault type. The preset fluctuation threshold can be set by those skilled in the art according to actual conditions, and this application does not impose specific limitations.

[0063] Among them, the support vector machine classifier classifies fault types by constructing an optimal hyperplane. The process is as follows: the key feature vectors are mapped to a high-dimensional space using radial basis function kernel function, and the classification boundary is adjusted by combining soft margin parameter and penalty coefficient to ensure the accuracy of classification of complex fault modes. In the classification process, a multi-class label system is pre-established for different fault types of the seat control system, and clear fault type labels are output to determine the corresponding fault type, thus providing a precise basis for dual redundancy switching.

[0064] The expression for the radial basis function kernel can be, but is not limited to, as follows: , in, and The key feature vector is the input. The kernel function parameter controls the distribution complexity of the feature vector after it is mapped to a high-dimensional space, in order to adapt to different classification requirements.

[0065] In step S104, a switching request signal is generated to switch from the main controller to the corresponding backup controller based on the fault type, the second operating data of the main controller, and the third operating data corresponding to at least one backup controller.

[0066] It is understood that, in the embodiments of this application, the second operating data can be understood as real-time data collected by the main controller within a preset time before and after the fault occurs, used to assess the current state of the main controller and the scope of the fault's impact; the third operating data can be understood as real-time data collected by the backup controller within a preset time before and after the fault occurs, used to assess the availability of the backup controller and its state matching degree with the main controller. The preset time can be set by those skilled in the art according to actual conditions, and this application does not impose specific limitations.

[0067] In actual execution, the embodiments of this application can generate a switching request signal from the main controller to the corresponding backup controller based on the fault type, the second operating data, and the third operating data.

[0068] For example, in this application embodiment, the fault type and the second operating data can be compared to determine that the primary and backup controllers are abnormal. An initial switching request signal is generated in combination with the switching conditions. Based on the initial switching request signal, the consistency between the primary and backup states is verified. After verifying the consistency between the primary and backup states, the final switching request signal is generated to ensure the dual redundancy reliability of the seat control system.

[0069] In this embodiment, during state consistency verification, the signal strength, feedback delay, and operating status codes of the primary and backup controllers are compared to calculate the data deviation. If the data deviation exceeds a preset safety threshold, a secondary verification process is triggered to obtain the final switchover request signal. Data snapshots before and after the switchover are recorded to ensure that the primary and backup controllers are in the same state after the switchover and that the system operates stably. The preset safety threshold can be set by those skilled in the art according to actual conditions, and this application does not impose specific limitations.

[0070] The switching conditions may include, but are not limited to, the severity of the primary unit failure, the availability of the backup unit, and the system load status, etc., and this application does not impose specific restrictions.

[0071] Optionally, in one embodiment of this application, a switching request signal for switching from the main controller to the corresponding backup controller is generated based on the fault type, the second operating data of the main controller, and the third operating data corresponding to at least one backup controller. This includes: calculating the data deviation between the second operating data and the third operating data based on the fault type; determining the switching priority of the corresponding backup controller based on the data deviation; and determining the switching request signal based on the switching priority.

[0072] It is understood that, in the embodiments of this application, data deviation can be understood as a quantitative representation of the difference between the second operating data and the third operating data. This deviation may include, but is not limited to, deviations in signal strength, feedback delay, and operating status codes, and is used to measure the degree of state matching between the standby controller and the main controller. A larger data deviation indicates a greater state difference between the standby controller and the main controller, and a higher risk to system stability after the switchover.

[0073] Switching priority can be understood as the takeover order level assigned to the standby controller after a comprehensive evaluation of data deviation and fault type. The higher the priority, the earlier the standby controller will be switched to the master controller.

[0074] In some embodiments, the present application embodiments may calculate the data deviation between the second operating data and the third operating data based on the fault type, thereby determining the switching priority of the corresponding backup controller, and thus determining the switching request signal based on the switching priority.

[0075] For example, in the embodiments of this application, the switching request signal generated after selecting the backup controller by switching priority and verifying the consistency of the primary and backup states can ensure the dual redundancy reliability of the seat control system.

[0076] In step S105, the main controller is switched to the corresponding backup controller according to the switching request signal, and fault description information of the main controller is generated based on the fault type, the second operating data and the third operating data.

[0077] It is understood that, in the embodiments of this application, the fault description information is a comprehensive and detailed description of the fault, which may include, but is not limited to, fault type, fault partition code, severity level, occurrence time, occurrence location, fault area, etc., and this application does not impose specific limitations.

[0078] In some embodiments, the present application can switch the main controller to the corresponding backup controller according to the switching request signal, and then generate fault description information of the main controller based on the fault type, the second operating data and the third operating data.

[0079] In this embodiment, after the switching request signal is generated, a switching log including switching time, fault type and switching result information can be recorded, supporting subsequent fault tracing and optimization of the seat control system.

[0080] Optionally, in one embodiment of this application, generating fault description information of the main controller based on fault type, second operating data, and third operating data includes: determining evaluation indicators for the second operating data and third operating data based on fault type; extracting a first fault signal that meets preset evaluation conditions from the second operating data and a second fault signal that meets preset evaluation conditions from the third operating data based on the evaluation indicators; and obtaining fault description information based on the first fault signal and the second fault signal.

[0081] It is understood that, in the embodiments of this application, the evaluation indicators may include, but are not limited to, time-dimensional evaluation indicators, such as timestamp alignment accuracy and time synchronization stability, etc., and this application does not impose specific limitations; quality-dimensional evaluation indicators, such as signal-to-noise ratio and latency indicators, etc., are also not subject to specific limitations in this application.

[0082] In actual implementation, the embodiments of this application can determine the evaluation indicators corresponding to the second and third operating data based on the fault type, and select the corresponding first and second fault signals from the second and third operating data according to preset evaluation conditions, and generate corresponding fault description information based on the first and second fault signals. The preset evaluation conditions can be set by those skilled in the art according to actual conditions, and this application does not impose specific limitations.

[0083] For example, in this application embodiment, the second and third operating data can be timestamped and quality evaluated in combination with the fault type. High-quality first and second fault signals that meet the preset evaluation conditions can be extracted to improve the accuracy of dual-redundancy fault identification. The first and second fault signals are then fused together, and the fault area of ​​the seat control system is located through anomaly detection and coordinate calculation to obtain the corresponding fault description information.

[0084] Optionally, in one embodiment of this application, obtaining fault description information based on a first fault signal and a second fault signal includes: acquiring weight information corresponding to the first fault signal and the second fault signal respectively; calculating a comprehensive feature vector based on the weight information, the first fault signal, and the second fault signal; and obtaining fault description information based on the fault points of the comprehensive feature vector.

[0085] It is understood that in this embodiment, the weight is a numerical value used to measure the importance of different fault signals in fault diagnosis. The larger the weight, the greater the role of the signal in fault diagnosis and the greater its influence on the comprehensive feature vector. It can be determined in various ways, such as expert experience, analytic hierarchy process (AHP), and entropy weight method, etc., and this application does not impose specific limitations. Expert experience relies on the knowledge and experience of domain experts to subjectively determine the weight; AHP decomposes complex problems into multiple levels, determines the relative importance of each factor through comparison, and then calculates the weight; entropy weight method determines the weight based on the information entropy of the fault signal. The smaller the information entropy, the more useful information the signal contains, and the greater the weight. It should be noted that the entropy weight method can automatically increase the weight of high-discrimination features and suppress the influence of noise features. The weight of the same feature in the primary and backup controllers is calculated independently to ensure that the fault signal is captured by a high weight. Therefore, this embodiment uses the entropy weight method to calculate the weight information corresponding to the first fault signal and the second fault signal, and its expression can be, but is not limited to: , in, The weight representing the j-th feature. This represents the number of samples, specifically the number of sampling points within a 100ms sliding window. This represents the number of feature dimensions, i.e., the number of features extracted from each redundant unit. Represents the normalized eigenvalues. The information entropy represents the k-th feature. The natural logarithm represents the sample size.

[0086] In actual implementation, the embodiments of this application first obtain the weight information corresponding to the first fault signal and the second fault signal, and then combine the first fault signal and the second fault signal to calculate the comprehensive feature vector, thereby accurately generating the corresponding fault description information based on the fault point represented by the comprehensive feature vector.

[0087] For example, in this application embodiment, the entropy weight method can be used to calculate the weight information corresponding to the first fault signal and the second fault signal to generate a comprehensive feature vector. Then, anomaly points are detected and analyzed using a coordinate calculation method, namely Mahalanobis distance. Combining the physical layout and signal distribution characteristics of the seat control system, the anomaly points are mapped to a preset region description template, forming fault description information including fault partition codes and severity levels. Mahalanobis distance is a distance metric that considers the correlation between different dimensions of data and eliminates the influence of dimensions. Relying on the mean and covariance matrix of the dataset, it measures the degree of deviation of a single sample from the center of the overall data distribution, and can accurately identify anomalies that deviate from the normal data distribution.

[0088] The working principle of the dual-redundancy fault identification method for the seat control system proposed in this application will be introduced below with reference to a specific embodiment.

[0089] in, Figure 2 This is a flowchart illustrating the working principle of a dual-redundancy fault identification method for a seat control system provided according to an embodiment of this application.

[0090] Step S201: Obtain control authority from the seat control system, and obtain operating status, signal strength and feedback delay from controller operating data, sensor signals and actuator feedback. Use time series sampling to determine the acquisition frequency and sampling time, generate initial first operating data, and perform preprocessing to obtain the first operating data.

[0091] Step S202: For the first running data, use PCA to perform feature selection and transformation, determine the principal component weights and data dimensions, and generate principal component feature vectors.

[0092] Step S203: Based on the principal component feature vector and the first running data, a pre-built convolutional neural network is used to extract the dynamic characteristics of sensor signals and actuator feedback in the seat control system, and generate key feature vectors.

[0093] It should be noted that, in the embodiments of this application, when generating key feature vectors, if the fault identification accuracy is less than or equal to a preset threshold, the convolution kernel size, stride and number of network layers are dynamically adjusted through backpropagation, and feature extraction is performed again until the fault identification accuracy is greater than the preset threshold, thereby determining the corresponding key feature vector.

[0094] Step S204: When the key feature vector meets the preset fault conditions, a support vector machine classifier is used to classify the key feature vector and generate fault type labels for the seat control system to determine the corresponding fault type.

[0095] In this embodiment, when the fluctuation amplitude of the key feature vector is greater than a preset fluctuation threshold, it can be determined that the key feature vector meets the preset fault condition.

[0096] Step S205: Compare the fault type with the second and third operating data respectively, determine the main controller is abnormal, generate an initial switching request signal in combination with the switching conditions, select the standby controller through the switching priority, and generate the final switching request signal after verifying the consistency of the main and standby states.

[0097] Step S206: Perform timestamp alignment and quality assessment on the operating data of the main and backup controllers, extract and fuse high-quality fault signals, locate the fault area of ​​the seat control system through anomaly detection and coordinate calculation, and generate corresponding fault description information.

[0098] In this embodiment, the second and third operating data can be timestamped and evaluated for quality in combination with the fault type. High-quality first and second fault signals that meet the preset evaluation conditions can be extracted respectively. Then, through fusion, anomaly detection and coordinate positioning, the fault area of ​​the seat control system can be determined, and the corresponding fault description information can be obtained.

[0099] The dual-redundancy fault identification method for a seat control system proposed in this application can extract the corresponding principal component feature vector from the first operating data of the seat control system, thereby determining the corresponding key feature vector. When the key feature vector meets the preset fault conditions, the fault type of the main controller is determined. Based on the fault type, the second operating data of the main controller, and the third operating data corresponding to at least one backup controller, a switching request signal for switching from the main controller to the corresponding backup controller is generated. The main controller is switched to the corresponding backup controller according to the switching request signal, thereby obtaining the corresponding fault description information. By extracting principal component features to compress data dimensions and eliminate redundant interference, and relying on feature thresholds to achieve accurate fault determination, combined with multi-controller operating data linkage comparison, rapid redundancy switching and fault information synchronization and archiving are completed, effectively improving the fault identification accuracy and the continuity and reliability of control operation of the seat control system. Thus, it solves the problems in related technologies, such as insufficient consideration of the synchronization, quality assessment, and switching decision optimization of the main and backup controller signals, difficulty in efficient fault tolerance; low signal processing fault tolerance and high fault misjudgment rate when facing environmental interference; difficulty in balancing real-time performance and accuracy; and inability to quickly locate faults and generate effective decisions in dynamic scenarios.

[0100] Next, referring to the accompanying drawings, a dual-redundant fault identification device for a seat control system proposed according to an embodiment of this application is described.

[0101] Figure 3 This is a block diagram of a dual-redundant fault identification device for a seat control system provided according to an embodiment of this application.

[0102] like Figure 3 As shown, the dual-redundant fault identification device 10 of the seat control system includes a main controller and at least one backup controller. The dual-redundant fault identification device 10 of the seat control system includes: an extraction module 100, a first determination module 200, a second determination module 300, a first generation module 400, and a second generation module 500.

[0103] The extraction module 100 is used to collect the first operating data of the seat control system and extract the corresponding principal component feature vector from the first operating data.

[0104] The first determining module 200 is used to determine the corresponding key feature vector based on the principal component feature vector and the first running data.

[0105] The second determining module 300 is used to determine the fault type of the main controller when the key feature vector meets the preset fault conditions.

[0106] The first generation module 400 is used to generate a switching request signal from the main controller to the corresponding backup controller based on the fault type, the second operating data of the main controller and the third operating data corresponding to at least one backup controller.

[0107] The second generation module 500 is used to switch the main controller to the corresponding standby controller according to the switching request signal, and generate fault description information of the main controller based on the fault type, the second operating data and the third operating data.

[0108] Optionally, in one embodiment of this application, the extraction module 100 includes: a construction unit, a first determination unit, and a second determination unit.

[0109] The construction unit is used to construct the covariance matrix based on the first running data.

[0110] The first determining unit is used to determine the eigenvalues ​​and eigenvectors corresponding to the first running data based on the covariance matrix.

[0111] The second determining unit is used to determine the principal component eigenvectors in the eigenvector based on the eigenvalues.

[0112] Optionally, in one embodiment of this application, the first determining module 200 includes: a third determining unit, a first generating unit, and a second generating unit.

[0113] The third determining unit is used to determine the initial key feature vector based on the principal component feature vector and the first running data.

[0114] The first generation unit is used to perform fault detection on the seat control system based on the initial key feature vector. If the fault identification accuracy of the seat control system is greater than a preset threshold, the initial key feature vector is used as the key feature vector.

[0115] The second generation unit is used to redetermine the initial key feature vector when the fault identification accuracy is less than or equal to a preset threshold, until the fault identification accuracy is greater than the preset threshold, so as to obtain the key feature vector.

[0116] Optionally, in one embodiment of this application, the second generation module 500 includes: a fourth determining unit, an extraction unit, and a third generation unit.

[0117] The fourth determining unit is used to determine the evaluation indicators of the second and third operating data based on the fault type.

[0118] The extraction unit is used to extract, based on evaluation indicators, a first fault signal that meets preset evaluation conditions from the second operating data and a second fault signal that meets preset evaluation conditions from the third operating data.

[0119] The third generation unit is used to obtain fault description information based on the first fault signal and the second fault signal.

[0120] Optionally, in one embodiment of this application, the third generation unit includes: an acquisition subunit, a calculation subunit, and a generation subunit.

[0121] The acquisition subunit is used to acquire the weight information corresponding to the first fault signal and the second fault signal, respectively.

[0122] The computational subunit is used to calculate the comprehensive feature vector based on weight information, the first fault signal, and the second fault signal.

[0123] Sub-units are generated to obtain fault description information based on the comprehensive feature vector of the fault point.

[0124] Optionally, in one embodiment of this application, the first generation module 400 includes: a calculation unit, a fifth determination unit, and a sixth determination unit.

[0125] The calculation unit is used to calculate the data deviation between the second and third operating data based on the fault type.

[0126] The fifth determining unit determines the switching priority of the corresponding backup controller based on the data deviation.

[0127] The sixth determining unit determines the handover request signal based on the handover priority.

[0128] It should be noted that the foregoing explanation of the dual-redundancy fault identification method embodiment for the seat control system also applies to the dual-redundancy fault identification device for the seat control system in this embodiment, and will not be repeated here.

[0129] The dual-redundancy fault identification device for a seat control system proposed in this application can extract the corresponding principal component feature vector from the first operating data of the seat control system, thereby determining the corresponding key feature vector. When the key feature vector meets the preset fault conditions, the fault type of the main controller is determined. Based on the fault type, the second operating data of the main controller, and the third operating data corresponding to at least one backup controller, a switching request signal is generated to switch the main controller to the corresponding backup controller. The main controller is switched to the corresponding backup controller according to the switching request signal, thereby obtaining the corresponding fault description information. By extracting principal component features to compress data dimensions and eliminate redundant interference, and relying on feature thresholds to achieve accurate fault determination, combined with multi-controller operating data linkage comparison, rapid redundancy switching and fault information synchronous archiving are completed, effectively improving the fault identification accuracy and the continuity and reliability of control operation of the seat control system. Thus, it solves the problems in related technologies, such as insufficient consideration of the synchronization, quality assessment, and switching decision optimization of the main and backup controller signals, difficulty in efficient fault tolerance; low signal processing fault tolerance and high fault misjudgment rate when facing environmental interference; difficulty in balancing real-time performance and accuracy, and inability to quickly locate faults and generate effective decisions in dynamic scenarios.

[0130] Figure 4 This is a schematic diagram of the structure of a vehicle according to an embodiment of this application. The vehicle may include: The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0131] When the processor 402 executes the program, it implements the dual-redundancy fault identification method for the seat control system provided in the above embodiments.

[0132] Furthermore, the vehicle also includes: Communication interface 403 is used for communication between memory 401 and processor 402.

[0133] The memory 401 is used to store computer programs that can run on the processor 402.

[0134] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0135] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0136] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0137] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0138] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the dual-redundancy fault identification method for the seat control system described above.

[0139] This application also provides a computer program product, including a computer program that, when executed, implements the dual-redundancy fault identification method for the seat control system described above.

[0140] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0141] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0142] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0143] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). In addition, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically by optically scanning paper or other media, then editing, interpreting or otherwise processing them as necessary, and then storing them in computer memory.

[0144] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0145] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0146] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0147] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A dual-redundancy fault identification method for a seat control system, characterized in that, The seat control system includes a main controller and at least one backup controller, wherein the method includes the following steps: Collect the first operating data of the seat control system, and extract the corresponding principal component feature vector from the first operating data; Based on the principal component feature vectors and the first running data, the corresponding key feature vectors are determined; When the key feature vector satisfies the preset fault conditions, the fault type of the main controller is determined; Based on the fault type, the second operating data of the main controller, and the third operating data corresponding to the at least one backup controller, a switching request signal is generated to switch from the main controller to the corresponding backup controller; The main controller is switched to the corresponding backup controller according to the switching request signal, and the fault description information of the main controller is generated based on the fault type, the second operating data and the third operating data.

2. The method according to claim 1, characterized in that, The step of extracting the corresponding principal component feature vector from the first running data includes: Based on the first set of operational data, construct the covariance matrix; Based on the covariance matrix, determine the eigenvalues ​​and eigenvectors corresponding to the first running data; Based on the eigenvalues, the principal component eigenvectors in the eigenvectors are determined.

3. The method according to claim 2, characterized in that, The step of determining the corresponding key feature vector based on the principal component feature vector and the first running data includes: Based on the principal component feature vector and the first running data, an initial key feature vector is determined; Based on the initial key feature vector, fault detection is performed on the seat control system. If the fault identification accuracy of the seat control system is greater than a preset threshold, the initial key feature vector is used as the key feature vector. If the fault identification accuracy is less than or equal to the preset threshold, the initial key feature vector is redefined until the fault identification accuracy is greater than the preset threshold, so as to obtain the key feature vector.

4. The method according to claim 1, characterized in that, The step of generating fault description information for the main controller based on the fault type, the second operating data, and the third operating data includes: Based on the fault type, the evaluation indicators for the second operating data and the third operating data are determined; Based on the evaluation indicators, a first fault signal that meets the preset evaluation conditions is extracted from the second operating data and a second fault signal that meets the preset evaluation conditions is extracted from the third operating data. The fault description information is obtained based on the first fault signal and the second fault signal.

5. The method according to claim 4, characterized in that, The process of obtaining the fault description information based on the first fault signal and the second fault signal includes: Obtain the weight information corresponding to the first fault signal and the second fault signal respectively; Based on the weight information, the first fault signal, and the second fault signal, a comprehensive feature vector is calculated. The fault description information is obtained based on the fault points of the comprehensive feature vector.

6. The method according to claim 1, characterized in that, The step of generating a switchover request signal from the main controller to the corresponding backup controller based on the fault type, the second operating data of the main controller, and the third operating data corresponding to the at least one backup controller includes: Based on the fault type, calculate the data deviation between the second operating data and the third operating data; Based on the data deviation, the switching priority of the corresponding backup controller is determined; The handover request signal is determined based on the handover priority.

7. A dual-redundancy fault identification device for a seat control system, characterized in that, The seat control system includes a main controller and at least one backup controller, wherein the device includes: The extraction module is used to collect the first operating data of the seat control system and extract the corresponding principal component feature vector from the first operating data; The first determining module is used to determine the corresponding key feature vector based on the principal component feature vector and the first running data; The second determining module is used to determine the fault type of the main controller when the key feature vector satisfies the preset fault conditions; The first generation module is used to generate a switching request signal from the main controller to the corresponding backup controller based on the fault type, the second operating data of the main controller and the third operating data corresponding to the at least one backup controller; The second generation module is used to switch the main controller to the corresponding backup controller according to the switching request signal, and generate fault description information of the main controller based on the fault type, the second operating data and the third operating data.

8. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the dual-redundancy fault identification method for a seat control system as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the dual-redundancy fault identification method for the seat control system as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program, which, when executed, is used to implement the dual-redundancy fault identification method for the seat control system as described in any one of claims 1-6.

Images