Automobile mcu diagnosis early warning method, system, device and storage medium

Abstract

The embodiment of the application provides a kind of car MCU diagnosis early warning method, system, equipment and storage medium, comprising: the MCU data information of first vehicle and second vehicle is acquired, and the MCU data information is sent to data sharing center, the data sharing center is used to store and manage MCU data, and establishes MCU information base;Data obtained from the data sharing center is executed first operation, and target data is obtained;According to the target data, establish health assessment model;The MCU data information of second vehicle is uploaded to the data sharing center, and is input into the health assessment model for comparison, and prediction result is obtained;According to the state of current MCU and the prediction result, determine the MCU health safety level of second vehicle.By this method, not only the accuracy and timeliness of MCU fault detection can be improved, but also the potential failure trend can be predicted, to help the owner and repair center to deal with the problem in advance, improve the reliability and safety of automotive electronic system.

Description

Technical Field

[0001] This application relates to the field of electric vehicle technology, and in particular to a method, system, device and storage medium for automotive MCU diagnostic early warning. Background Technology

[0002] With the rapid development of automotive electronics technology, the Electronic Control Unit (ECU) has gradually become a core component in modern automobiles. As a key component of the ECU, the Microcontroller Unit (MCU) undertakes important control and computational tasks in multiple systems, including engine control, airbags, body control, and infotainment systems. Due to the harsh operating environment, electric vehicle MCUs must meet the requirements of high reliability, high safety, and long lifespan. Therefore, ensuring the health status and fault warning capabilities of electric vehicle MCUs has become one of the key issues in ensuring the reliability of automotive electronic systems.

[0003] While some fault diagnosis and monitoring systems exist, most are limited to the ECU system level, offering limited diagnostic and early warning capabilities regarding the internal operating status and health of the MCU. Furthermore, existing diagnostic methods typically operate after a fault occurs, passively repairing or replacing components, lacking early warning mechanisms. They can only address MCU issues specific to a single vehicle and cannot be used as a reference for assessing and warning of potential similar risks in other vehicles. Summary of the Invention

[0004] This application provides a diagnostic and early warning method for automotive MCUs, which can not only improve the accuracy and timeliness of MCU fault detection, but also predict potential fault trends, helping car owners and repair centers to handle problems in advance and improve the reliability and safety of automotive electronic systems.

[0005] In a first aspect, embodiments of this application provide a diagnostic and early warning method for an automotive MCU, comprising:

[0006] The system acquires MCU data information from the first vehicle and the second vehicle, and sends the MCU data information to a data sharing center. The data sharing center is used to store and manage MCU data and establish an MCU information database.

[0007] The first operation is performed on the data obtained from the data sharing center to obtain the target data;

[0008] Based on the target data, a health assessment model is established;

[0009] The MCU data information of the second vehicle is uploaded to the data sharing center and input into the health assessment model for comparison to obtain the prediction result;

[0010] Based on the current state of the second vehicle's MCU and the prediction results, the health and safety level of the second vehicle's MCU is determined.

[0011] In one possible implementation, the first operation includes at least one of the following: data denoising, normalization, feature extraction, and missing value handling.

[0012] In one possible implementation, the MCU data information of the first vehicle or the MCU data information of the second vehicle includes at least one of the following:

[0013] MCU type, serial number, batch, manufacturing process, production date, critical point failure probability of the MCU, and critical point impact threshold.

[0014] In one possible implementation, the MCU information base includes at least one of the following: basic information of the MCU, operating status, and historical fault data.

[0015] In one possible implementation, establishing a health assessment model based on the target data includes:

[0016] The MCU data information of the first vehicle and the second vehicle is used to learn and train, and the pattern differences between healthy MCUs and potentially faulty MCUs are identified.

[0017] The health assessment model is constructed based on the differences in the patterns.

[0018] In one possible implementation, the method further includes sending the MCU health and safety level and corresponding maintenance recommendations.

[0019] Secondly, embodiments of this application provide an automotive MCU diagnostic warning system, comprising:

[0020] The data acquisition module is used to acquire MCU data information from the first vehicle and the second vehicle.

[0021] A communication module is used to send the MCU data information to a data sharing center, which is used to store and manage MCU data and establish an MCU information database.

[0022] The data processing module is used to perform a first operation on the data obtained from the data sharing center to obtain the target data;

[0023] The AI ​​module is used to build a health assessment model based on the target data; the second vehicle uploads the corresponding MCU data information to the data sharing center, and the AI ​​module compares the data to obtain the prediction result.

[0024] The fault warning module is used to determine the health and safety level of the second vehicle's MCU based on the current status of the second vehicle's MCU and the prediction result.

[0025] In one possible implementation, the system performs the method corresponding to any embodiment of the first aspect of the present application.

[0026] Thirdly, embodiments of this application also provide an electronic device, which includes:

[0027] At least one processor;

[0028] and memory that is communicatively connected to at least one processor;

[0029] The memory stores instructions that can be executed by at least one processor to cause the electronic device to perform a method corresponding to any embodiment of the first aspect of the present application.

[0030] Fourthly, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement any of the methods described in the first aspect of embodiments of this application.

[0031] Fifthly, this disclosure also provides a computer program product comprising computer-executable instructions, which, when executed by a processor, are used to implement the methods of any embodiment corresponding to the first aspect of this disclosure.

[0032] In summary, the automotive MCU diagnostic and early warning method provided in this application can not only improve the accuracy and timeliness of MCU fault detection, but also predict potential fault trends, helping car owners and repair centers to handle problems in advance and improve the reliability and safety of automotive electronic systems. Attached Figure Description

[0033] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0034] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is a schematic diagram of the system framework of an automotive MCU diagnostic and early warning method provided in one embodiment of this application;

[0036] Figure 2 This is a schematic flowchart of an automotive MCU diagnostic and early warning method provided in one embodiment of this application;

[0037] Figure 3 An electronic device corresponding to the automotive MCU diagnostic warning method provided in one embodiment of this application. Detailed Implementation

[0038] In the following description, when referring to the accompanying drawings, the same numbers in different drawings denote the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0039] The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0040] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0041] In related technologies, the number of differences between parameters read by a single MCU and pre-set parameters is used as the standard for judging the status of the MCU, which solves the problem of a single MCU failing. However, there are some drawbacks or limitations, as follows:

[0042] 1. Relying on the MCU's own diagnostic capabilities carries significant risks, typically only enabling basic fault detection and failing to provide preventative maintenance recommendations or predict future problems. Furthermore, existing systems generally lack self-learning and self-optimization capabilities, hindering performance improvement over time.

[0043] 2. Untimely anomaly detection: Existing technologies rely on periodic maintenance checks or detection only when obvious faults are encountered, which cannot provide real-time monitoring. Existing systems lack predictive capabilities and can only be dealt with after a fault occurs.

[0044] 3. Inaccurate diagnostic information: Due to the use of traditional fault diagnosis methods, it is often impossible to accurately determine the cause and location of the fault.

[0045] 4. Judging the MCU status solely by comparing the MCU feedback value with the preset value is limited because the parameters are dynamic, and parameter comparison and analysis lack sufficient references and are therefore difficult to deduce the optimal parameter range.

[0046] 5. Because it reads the operating results of a single MCU as parameters, it cannot provide advance warnings for similar or even batch-type MCU products. It can only solve problems of a single MCU and cannot provide comprehensive and advance warnings of potential risks.

[0047] Therefore, in order to address the shortcomings of health monitoring in automotive MCUs (Microcontroller Units), this invention proposes an automotive MCU diagnostic and early warning method and system, aiming to improve the MCU's ability to diagnose faults, monitor in real time, perform preventive maintenance, and predict potential risks.

[0048] In the embodiments of this application, the automotive MCU diagnostic warning method can be applied to health diagnosis, or fault diagnosis, and can also be used in the airbags, infotainment systems, etc. of gasoline vehicles.

[0049] Figure 1 This is a schematic diagram of the system framework for an automotive MCU diagnostic and early warning method provided in one embodiment of this application. Figure 1 The system includes a data acquisition module, a communication module, a data sharing center, a data processing module, an AI module, an optimization module, and a fault early warning module. The modules are connected by wired or wireless means, or by a combination of wired and wireless means. This application does not limit the connection method.

[0050] exist Figure 1 In this embodiment, the automotive MCU unit refers to the MCU unit of the first vehicle, and the other automotive MCU units refer to the MCU units of the second vehicle. In this embodiment, all online vehicles include both the first and second vehicles. That is, the data used for AI module training includes all online vehicles, which can be understood as vehicles of the same batch and model, or vehicles from different batches. Regardless of whether they are from the same batch, different batches, or different models, the data required for model building is all acquired automotive-grade MCU data information, and model training is performed using this automotive-grade MCU data information. This embodiment does not limit the scope of this application.

[0051] exist Figure 1The cloud center unit comprises a fault early warning module, a data sharing center, a communication module, a data processing module, an AI module, and an optimization module. The data sharing center includes a cloud-based data center.

[0052] Figure 2 This is a schematic flowchart of an automotive MCU diagnostic and early warning method provided in one embodiment of this application. Figure 2 The process includes steps S201 to S205. Wherein:

[0053] Step S201: The data acquisition module acquires MCU data information of the first vehicle and the second vehicle, and sends the MCU data information to the data sharing center. The data sharing center is used to store and manage MCU data and establish an MCU information database.

[0054] In this embodiment of the application, the data module may collect only the MCU data information of the first vehicle, or it may collect the MCU data information of the first vehicle and the MCU data information of the second vehicle simultaneously.

[0055] In one possible implementation, the MCU data information of the first vehicle or the MCU data information of the second vehicle includes at least one of the following:

[0056] MCU type, serial number, batch, manufacturing process, production date, critical point failure probability of the MCU, and critical point impact threshold.

[0057] In one possible implementation, the MCU information base includes at least one of the following: basic information of the MCU, operating status, and historical fault data.

[0058] In one embodiment of this application, the data acquisition module is responsible for collecting operational data from the vehicle's MCU. The collected data includes, but is not limited to, basic information such as the MCU's type, serial number, batch, manufacturing process, and production date. It also includes the MCU's critical point failure probability and critical point impact threshold. The module also checks the operating status of various MCU systems, such as the clock system, memory, I / O interfaces, AD / DA converters, communication interfaces, and other peripherals. This information can be obtained by reading the values ​​of the corresponding registers. In some cases, the data acquisition module is also used to evaluate the MCU's performance. For example, when the MCU needs to execute complex algorithms, the data acquisition module can evaluate its performance by measuring the algorithm's execution time. This data will serve as the basis for subsequent system diagnosis and fault prediction. The data acquisition module is connected to the MCU via an interface, acquiring the operating status in real time and feeding it back to the system. It is understood that "vehicle" here includes both the first vehicle and the second vehicle.

[0059] In one embodiment of this application, a data sharing center is used to store and manage all data collected from the vehicle's MCU and to establish a relevant information database. The database includes basic information about the MCU, its operating status, and historical fault data. The data center has large-scale data storage capabilities and supports horizontal scaling to handle real-time data aggregation and analysis from multiple vehicles. As the data core of the system, the data sharing center's main function is to provide a data foundation for subsequent data processing and AI modules.

[0060] Step S202: The data processing module performs a first operation on the data obtained from the data sharing center to obtain the target data.

[0061] In one possible implementation, the first operation includes at least one of the following: data denoising, normalization, feature extraction, and missing value handling.

[0062] The data processing module utilizes big data processing technologies, such as the NumPy mathematical operation library, which supports efficient multidimensional array operations and basic data preprocessing, or the scikit-learn library, which contains various data preprocessing tools, such as data normalization, standardization, and feature extraction, to clean, integrate, mine, and analyze data aggregated from the data sharing center. This module includes the following processing steps:

[0063] Data denoising: removing noise and outliers from data. For example, filtering algorithms can be used to remove noise from sensor readings, and statistical methods can be used to identify and eliminate outliers to ensure data accuracy.

[0064] Normalization: This involves standardizing the data to ensure that data of different scales can be used uniformly, preventing certain features from having an excessive impact on model training. Common methods include Min-Max normalization and Z-score normalization.

[0065] Feature Extraction: TSfresh is used for feature extraction of time series data. Features related to the health status of the MCU are extracted from the raw data, such as basic information like manufacturing process and delivery time. In addition, features include the MCU's critical point failure probability, critical point impact threshold, clock system, memory, I / O interface, AD / DA conversion, communication interface, and the operating status of other peripherals. Examples include statistical features (mean, variance, peak value, etc.), time domain features (zero crossing rate, energy, etc.), and frequency domain features (spectrum, power spectral density, etc.).

[0066] Missing value handling: For missing parts in the data, interpolation or prediction is used to fill in the missing parts.

[0067] Understandably, the processed data serves as input for training and optimizing AI models, ensuring that the models can learn and predict based on high-quality data.

[0068] Step S203: Establish a health assessment model based on the target data.

[0069] In this embodiment of the application, the data sources for establishing the health assessment model include MCU data information of other online vehicles, i.e., the first vehicle, and may also include MCU data information of the current vehicle, i.e., the second vehicle.

[0070] Step S204: Upload the MCU data information of the second vehicle to the data sharing center, and input it into the health assessment model for comparison to obtain the prediction result.

[0071] In one possible implementation, establishing a health assessment model based on the target data includes: learning and training the MCU data information of the first vehicle to identify the pattern differences between healthy MCUs and potentially faulty MCUs; and constructing the health assessment model based on the pattern differences.

[0072] Understandably, the AI ​​module utilizes artificial intelligence technology to collect and analyze a large amount of operational data from MCU devices. By learning from a vast amount of data samples, it identifies the pattern differences between healthy MCUs and those with potential faults, particularly using deep learning technology to identify potential patterns and trends in MCU operational data. The system builds and trains dedicated AI models, such as the deep learning framework TensorFlow, supporting the training and deployment of various neural network architectures, especially suitable for architectures like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This enables the prediction and diagnosis of MCU faults. The AI ​​module can also learn from historical data to build health assessment models and predict potential future fault risks.

[0073] The AI ​​module includes an input layer, multiple hidden layers (such as convolutional layers and pooling layers), and an output layer. It can perform in-depth analysis of multi-dimensional data from the MCU to identify potential fault modes. On the hardware side, the AI ​​module can use processors with hardware acceleration capabilities, such as GPUs, DSPs, or NPUs, to accelerate the training and inference process of deep learning models, improving the system's response speed and processing efficiency.

[0074] In the embodiments of this application, the applicable models include, but are not limited to, any of the following: Convolutional Neural Networks (CNNs), suitable for processing data with spatial structure, such as image data. In MCU fault diagnosis, time-series data can be converted into two-dimensional data similar to images, and then features can be extracted using CNNs. For example, the failure rate of key points over a period of time, the state data of related clocks, memory, IO interfaces AD and DA, etc., at the time of key point failure can be arranged into a matrix and used as input to the CNN.

[0075] Recurrent Neural Networks (RNNs) (such as LSTM or GRU) are well-suited for processing time-series data, capturing temporal dependencies within the data. For example, an LSTM network can be used to learn historical patterns in MCU operating data and predict potential future failures. RNNs are particularly well-suited for processing time-series data like MCU operating data because they can capture patterns that change over time.

[0076] Combining models can combine models such as CNN and RNN. For example, CNN can be used to extract local features first, and then RNN can be used to capture temporal dependencies.

[0077] In the embodiments of this application, it is understood that the selected deep learning model is trained using preprocessed data. Model training includes supervised learning and unsupervised learning: In supervised learning, the model is trained using labeled data (e.g., basic information such as the manufacturing process and delivery time of a faulty MCU; in addition, it includes relevant parameters such as the MCU's key point failure probability, key point impact threshold, clock system, memory, I / O interface, AD / DA conversion, communication interface, and the operating status of other peripherals) to learn the mapping relationship between input and output. In unsupervised learning, the model searches for the inherent structure and patterns of the data in the unlabeled data. During training, it is necessary to select an appropriate loss function and optimization algorithm, and adjust the model's hyperparameters (e.g., learning rate, batch size, number of network layers, etc.) to obtain the best model performance. Techniques such as cross-validation can be used to evaluate the model's generalization ability and prevent overfitting.

[0078] Simultaneously, an optimization module continuously learns and optimizes the AI ​​module's model. This module employs deep learning frameworks such as TensorFlow, based on architectures like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), and utilizes incremental learning. This means the model automatically updates its parameters when new data arrives, without requiring complete retraining. Continuous learning and adjustment of cloud-based data are performed, and model performance is typically evaluated using various metrics (such as accuracy, recall, and F1-score). Through the optimization module, the system marks the operational data of faulty MCUs as anomalous data in the knowledge base, further optimizing model training and enhancing its fault prediction accuracy and diagnostic capabilities.

[0079] Step S205: The fault warning module determines the health and safety level of the second vehicle's MCU based on the current status of the second vehicle's MCU and the prediction result.

[0080] In one possible implementation, the method further includes sending the MCU health and safety level and corresponding maintenance recommendations.

[0081] Understandably, the current MCU is the same as the MCU of the second vehicle. This means that the MCU's safety level is determined based on the second vehicle's current status and the predictions obtained through the AI ​​module. Based on this safety level, repair recommendations are made, and timely feedback is provided to the vehicle owner or after-sales service center via the in-vehicle information system, improving problem-solving capabilities.

[0082] Understandably, the fault warning module, based on the AI ​​module's predictions and the current MCU's operating status, provides a safety level assessment. Safety levels are categorized into multiple levels (e.g., minor, moderate, severe, and faulty), and corresponding repair suggestions are provided. This module feeds back the diagnostic results and repair suggestions to the vehicle owner or after-sales service center through the vehicle information system, ensuring timely resolution of problems and preventing major malfunctions. Furthermore, the fault warning module has remote upgrade capabilities, allowing the system to push updates periodically or as needed, improving the overall reliability and intelligence of the system.

[0083] The beneficial effects of the method of the present invention are as follows:

[0084] 1. Enhance diagnostic depth and accuracy: Breaking through the limitations of traditional reliance on MCU self-detection, through multi-dimensional data analysis and deep learning models, it can not only detect basic faults, but also identify potential fault modes and trends, providing more accurate diagnostic and preventive maintenance suggestions, and has self-learning and optimization capabilities.

[0085] 2. Real-time anomaly detection and prediction capability: The system can monitor the MCU status in real time, and combined with the prediction model, it can give early warning of potential fault risks and avoid major losses and escalation failures.

[0086] 3. Dynamic parameter adaptation and optimization: Based on changes in environment and performance, the parameter range is dynamically adjusted to derive the optimal operating parameter range. The system learns adaptively and continuously optimizes monitoring and diagnostic capabilities.

[0087] 4. Cross-MCU cluster health monitoring and batch early warning: Through big data technology, cluster monitoring of MCUs of the same type or batch is carried out. The health diagnosis result of one MCU helps the monitoring and diagnosis of other MCUs, identify batch problems and provide early warnings, reduce safety risks, effectively reduce the overall failure rate, and help vehicle manufacturers optimize supply chain management and maintenance strategies.

[0088] In summary, the embodiments of this application provide a diagnostic and early warning method for automotive MCUs, which can not only improve the accuracy and timeliness of MCU fault detection, but also predict potential fault trends, helping car owners and repair centers to handle problems in advance and improve the reliability and safety of automotive electronic systems.

[0089] This application also provides an automotive MCU diagnostic warning system, including:

[0090] The data acquisition module is used to acquire MCU data information from the first vehicle;

[0091] A communication module is used to send the MCU data information to a data sharing center, which is used to store and manage MCU data and establish an MCU information database.

[0092] The data processing module is used to perform a first operation on the data obtained from the data sharing center to obtain the target data;

[0093] The AI ​​module is used to build a health assessment model based on the target data; the second vehicle uploads the corresponding MCU data information to the data sharing center, and the AI ​​module compares the data to obtain the prediction result.

[0094] The fault warning module is used to determine the health and safety level of the second vehicle's MCU based on the current status of the second vehicle's MCU and the prediction result.

[0095] In one possible implementation, the automotive MCU diagnostic warning system also includes an optimization module.

[0096] In one possible implementation, the first operation includes at least one of the following: data denoising, normalization, feature extraction, and missing value handling.

[0097] In one possible implementation, the MCU data information of the first vehicle or the MCU data information of the second vehicle includes at least one of the following:

[0098] MCU type, serial number, batch, manufacturing process, production date, critical point failure probability of the MCU, and critical point impact threshold.

[0099] In one possible implementation, the MCU information base includes at least one of the following: basic information of the MCU, operating status, and historical fault data.

[0100] In one possible implementation, the AI ​​module is used to: learn and train on the MCU data information of the first vehicle and the second vehicle to identify the pattern differences between healthy MCUs and potentially faulty MCUs; and construct the health assessment model based on the pattern differences.

[0101] In one possible implementation, the system further includes a sending module for sending the MCU's health and safety level and corresponding maintenance recommendations.

[0102] In one possible implementation, the data sharing center includes a cloud data center.

[0103] In one possible implementation, an embodiment of this application provides an automotive MCU diagnostic warning system for implementing the above. Figure 2 The method provided in any of the corresponding embodiments.

[0104] Figure 3 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this application, as shown below. Figure 3 As shown, the electronic device 300 includes a memory 310 and a processor 320.

[0105] The memory 310 stores a computer program that can be executed by at least one processor 320. This computer program is executed by at least one processor 320 to cause the electronic device to perform the methods provided in any of the above embodiments.

[0106] The memory 310 and the processor 320 can be connected via a bus 330.

[0107] The relevant explanations can be understood by referring to the corresponding descriptions and effects in the method embodiments, and will not be repeated here.

[0108] One embodiment of this application provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to perform the following: Figure 2 The method provided in any of the corresponding embodiments.

[0109] The computer-readable storage medium can be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0110] One embodiment of this application provides a computer program product comprising computer-executable instructions, which, when executed by a processor, are used to implement, as described above. Figure 2 The method provided in any of the corresponding embodiments.

[0111] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0112] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope of this application is indicated by the claims.

[0113] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A diagnostic and early warning method for automotive MCUs, characterized in that, include: The system acquires MCU data information from the first vehicle and the second vehicle, and sends the MCU data information to a data sharing center. The data sharing center is used to store and manage MCU data and establish an MCU information database. The first operation is performed on the data obtained from the data sharing center to obtain the target data; Based on the target data, a health assessment model is established; The MCU data information of the second vehicle is uploaded to the data sharing center and input into the health assessment model for comparison to obtain the prediction result; Based on the current state of the second vehicle's MCU and the prediction results, the health and safety level of the second vehicle's MCU is determined.

2. The method according to claim 1, characterized in that, The first operation includes at least one of the following: data denoising, normalization, feature extraction, and missing value processing.

3. The method according to claim 1, characterized in that, The MCU data information of the first vehicle or the MCU data information of the second vehicle includes at least one of the following: MCU type, serial number, batch, manufacturing process, production date, critical point failure probability of the MCU, and critical point impact threshold.

4. The method according to any one of claims 1-3, characterized in that, The MCU information base includes at least one of the following: basic information of the MCU, operating status, and historical fault data.

5. The method according to any one of claims 1-3, characterized in that, The step of establishing a health assessment model based on the target data includes: The MCU data information of the first vehicle and the second vehicle is used for learning and training to identify the pattern differences between healthy MCUs and potentially faulty MCUs; The health assessment model is constructed based on the differences in the patterns.

6. The method according to any one of claims 1-4, characterized in that, The method also includes sending the MCU's health and safety level and corresponding maintenance recommendations.

7. The method according to any one of claims 1-4, characterized in that, The data sharing center includes a cloud data center.

8. A diagnostic and early warning system for automotive MCUs, characterized in that, include: The data acquisition module is used to acquire MCU data information from the first vehicle and the second vehicle. A communication module is used to send the MCU data information to a data sharing center, which is used to store and manage MCU data and establish an MCU information database. The data processing module is used to perform a first operation on the data obtained from the data sharing center to obtain the target data; The AI ​​module is used to build a health assessment model based on the target data; the second vehicle uploads the corresponding MCU data information to the data sharing center, and the AI ​​module compares the data to obtain the prediction result. The fault warning module is used to determine the health and safety level of the second vehicle's MCU based on the current status of the second vehicle's MCU and the prediction result.

9. The system according to claim 8, characterized in that, The first operation includes at least one of the following: data denoising, normalization, feature extraction, and missing value processing.

10. The system according to claim 8, characterized in that, The MCU data information of the first vehicle or the MCU data information of the second vehicle includes at least one of the following: MCU type, serial number, batch, manufacturing process, production date, critical point failure probability of the MCU, and critical point impact threshold.

11. The system according to any one of claims 8-10, characterized in that, The MCU information base includes at least one of the following: basic information of the MCU, operating status, and historical fault data.

12. The system according to any one of claims 8-10, characterized in that, The AI ​​module is used for: The MCU data information of the first vehicle and the second vehicle is used for learning and training to identify the pattern differences between healthy MCUs and potentially faulty MCUs; The health assessment model is constructed based on the differences in the patterns.

13. The system according to any one of claims 8-10, characterized in that, The system also includes a sending module for sending the health and safety level of the MCU and corresponding maintenance recommendations.

14. The system according to any one of claims 8-10, characterized in that, The data sharing center includes a cloud data center.

15. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, cause the electronic device to perform the method as described in any one of claims 1 to 7.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

17. A computer program product comprising computer-executable instructions, characterized in that, The computer executes the instructions when they are executed by the processor to implement the method as described in any one of claims 1-7.

Images