Intelligent networked automobile fault detection method and system

Abstract

The invention belongs to the technical field of automobile fault detection, and provides an intelligent networked automobile fault detection method and system, and the method comprises the steps: S1, collecting real-time data, including vehicle sensor data, network communication data, user behavior data and environment perception data, of an intelligent networked automobile in a driving process; s2, performing real-time analysis on the data by adopting a deep learning model, identifying a fault omen mode, and predicting a potential fault type; s3, based on an analysis result, an AI decision system built in the vehicle is used; according to the invention, accurate prediction and rapid positioning of faults can be realized by collecting and analyzing diversified real-time data and using a deep learning model, and compared with a current fault detection method which mainly depends on a mechanical sensor and artificial experience, the response speed and the diagnosis accuracy are significantly improved, and the fault detection method is suitable for large-scale popularization and application. Therefore, the safe operation of the intelligent networked automobile is more effectively guaranteed, and the user experience is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of automobile fault detection, and specifically relates to a method and system for detecting faults of intelligent networked automobiles. Background Art

[0002] With the rapid development of intelligent connected vehicle technology, vehicle fault detection and diagnosis have become key technologies to ensure safe vehicle operation and improve user experience. At the same time, as the degree of vehicle intelligence and networking deepens, the amount of data generated by vehicles has increased dramatically, but how to effectively use this data for efficient and accurate fault detection has become a new challenge.

[0003] Currently, most of the intelligent connected vehicle fault detection methods on the market rely on single sensor data or the vehicle's built-in diagnostic system (OBD). The above fault detection methods mainly rely on mechanical sensors and manual experience, and have problems such as long response time and low diagnostic accuracy.

[0004] To this end, those skilled in the art have proposed a method and system for detecting faults in an intelligent connected vehicle to solve the problems raised by the background technology. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a method and system for fault detection of intelligent connected vehicles, so as to solve the problems that the fault detection method in the prior art mainly relies on mechanical sensors and manual experience, has a long response time and low diagnostic accuracy.

[0006] A method for detecting faults in an intelligent connected vehicle, comprising:

[0007] S1. First, collect real-time data of intelligent connected vehicles during driving, including vehicle sensor data, network communication data, user behavior data and environmental perception data;

[0008] S2. Then, a deep learning model is used to analyze the above data in real time to identify fault precursor patterns and predict potential fault types;

[0009] S3. Then, based on the analysis results, the vehicle's built-in AI decision-making system will promptly issue a fault warning signal and accurately locate the source of the fault to a specific component or system to obtain a fault diagnosis result;

[0010] S4. Feedback fault diagnosis results to the vehicle display or driver, and provide corresponding fault handling suggestions, support users to customize fault warning levels and receiving methods, and enhance user experience.

[0011] Preferably, the method also includes: establishing a real-time communication mechanism between the cloud data center and the vehicle-mounted terminal to achieve continuous updating of the fault prediction model, fault case sharing and remote technical support, while supporting data exchange with other intelligent connected vehicles to enhance prediction accuracy.

[0012] Preferably, in step S1, based on the original data collection, a data preprocessing and screening module is introduced, which is responsible for preliminarily processing the collected vehicle sensor data, network communication data, user behavior data and environmental perception data, removing noise and redundant information, and screening the data according to its importance and relevance. The data preprocessing and screening module optimizes the data quality by adopting the principal component analysis (PCA) algorithm to ensure the accuracy and efficiency of subsequent analysis;

[0013] At the same time, after data preprocessing, real-time data fusion technology is further introduced: a multi-source data fusion algorithm is used to fuse data from different sensors and systems to generate a more comprehensive and accurate description of the vehicle status. This fusion not only improves the richness and reliability of the data, but also provides a richer information basis for subsequent fault detection.

[0014] Preferably, in step S1, encryption technology is used during data collection to ensure the security of the collected data during transmission and storage, while protecting the privacy rights and interests of users. This step not only meets the current society's strict requirements for data security and privacy protection, but also improves the overall reliability and user trust of the intelligent connected vehicle fault detection system;

[0015] At the same time, the frequency, accuracy and scope of data collection are dynamically adjusted according to the actual operating conditions of the vehicle and the requirements of the fault prediction model; it includes:

[0016] When the vehicle is in complex road conditions or under high load, the density and accuracy of data collection are increased to more accurately capture potential fault information; when the vehicle is running smoothly, the frequency of data collection is appropriately reduced to save resources and energy. This dynamic adjustment strategy makes data collection more intelligent and efficient.

[0017] Preferably, in step S2, an attention mechanism is introduced into the deep learning model so that the model can automatically focus on the most important features or time series points for fault prediction, which helps the model to filter out key information in complex data and improve the accuracy of prediction.

[0018] Preferably, in step S3, a hierarchical warning module is introduced, which issues warning signals of different levels according to the severity and urgency of the fault; including: for minor faults, early warnings can be issued and regular inspections are recommended; for serious faults, emergency warnings are immediately issued and immediate parking inspections are recommended.

[0019] Preferably, in step S4, a personalized fault warning interface is introduced; the interface may include user-defined colors, icons, layouts, etc., so that the fault information is more intuitive and easy to understand, thereby improving user acceptance and reaction speed;

[0020] At the same time, emotional design elements are introduced, such as using friendly voice prompts, animation effects or emoticons to convey the urgency and importance of fault information; this can reduce the driver's nervousness when receiving fault warnings and improve the user experience;

[0021] A fault warning community is also established to allow drivers to share their own fault situations, handling experiences and suggestions; the system can automatically collect and analyze this data to optimize the accuracy of fault warnings and handling suggestions.

[0022] A smart connected vehicle fault detection system, using the above-mentioned smart connected vehicle fault detection method, comprises:

[0023] The data collection module is used to collect real-time data of intelligent connected vehicles during driving, including vehicle sensor data, network communication data, user behavior data and environmental perception data;

[0024] The data preprocessing and screening module performs preliminary processing on the collected data, removes noise and redundant information, and screens the data according to its importance and relevance, using the principal component analysis (PCA) algorithm to optimize data quality;

[0025] Real-time data fusion module, which uses multi-source data fusion algorithm to fuse data from different sensors and systems to generate a comprehensive and accurate description of vehicle status;

[0026] The deep learning analysis module uses a deep learning model to analyze the fused data in real time, identify fault precursor patterns, predict potential fault types, and introduce an attention mechanism into the model to improve prediction accuracy;

[0027] The fault warning and location module, based on the analysis results, promptly issues fault warning signals through the vehicle's built-in AI decision-making system, and accurately locates the source of the fault to a specific component or system. The introduction of a hierarchical warning module issues warning signals of different levels according to the severity and urgency of the fault;

[0028] The user interaction module feeds back the fault diagnosis results to the vehicle display or the driver, and provides corresponding fault handling suggestions. It supports users to customize the fault warning level and receiving method, introduces a personalized fault warning interface and emotional design elements, and establishes a fault warning community for drivers to share fault conditions and handling experiences;

[0029] The cloud communication and update module establishes a real-time communication mechanism between the cloud data center and the on-board terminal to achieve continuous updating of the fault prediction model, fault case sharing and remote technical support. It also supports data exchange with other intelligent connected vehicles to enhance prediction accuracy.

[0030] A processor is configured to execute the above-mentioned intelligent connected vehicle fault detection method.

[0031] A computer-readable storage medium stores a computer program, which implements the above-mentioned intelligent connected vehicle fault detection method when executed by a processor.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] The present invention can collect and analyze diversified real-time data and use deep learning models to accurately predict and quickly locate faults. Compared with the current fault detection methods that mainly rely on mechanical sensors and manual experience, it significantly improves the response speed and diagnostic accuracy, thereby more effectively ensuring the safe operation of intelligent connected vehicles and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a flow chart of the intelligent connected vehicle fault detection method of the present invention;

[0035] Figure 2 This is a framework diagram of the intelligent connected vehicle fault detection system of the present invention. DETAILED DESCRIPTION

[0036] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0037] Embodiment: The present invention provides a method for detecting faults in an intelligent networked vehicle, such as Figure 1 As shown, including:

[0038] S1. First, collect real-time data of intelligent connected vehicles during driving, including vehicle sensor data, network communication data, user behavior data and environmental perception data;

[0039] S2. Then, a deep learning model is used to analyze the above data in real time to identify fault precursor patterns and predict potential fault types;

[0040] S3. Then, based on the analysis results, the vehicle's built-in AI decision-making system will promptly issue a fault warning signal and accurately locate the source of the fault to a specific component or system to obtain a fault diagnosis result;

[0041] S4. Feedback fault diagnosis results to the vehicle display or driver, and provide corresponding fault handling suggestions, support users to customize fault warning levels and receiving methods, and enhance user experience.

[0042] From the above, it can be seen that the present invention can collect and analyze diversified real-time data and use deep learning models to achieve accurate prediction and rapid positioning of faults. Compared with the current fault detection methods that mainly rely on mechanical sensors and manual experience, it significantly improves the response speed and diagnostic accuracy, thereby more effectively ensuring the safe operation of intelligent connected vehicles and improving user experience.

[0043] Furthermore, the method also includes: establishing a real-time communication mechanism between the cloud data center and the on-board terminal to achieve continuous updating of the fault prediction model, fault case sharing and remote technical support, while supporting data exchange with other intelligent connected vehicles to enhance prediction accuracy.

[0044] Furthermore, in step S1, based on the original data collection, a data preprocessing and screening module is introduced. This module is responsible for preliminarily processing the collected vehicle sensor data, network communication data, user behavior data and environmental perception data, removing noise and redundant information, and screening the data according to its importance and relevance. The data preprocessing and screening module optimizes the data quality by using the principal component analysis (PCA) algorithm to ensure the accuracy and efficiency of subsequent analysis. The specific formula of the principal component analysis (PCA) algorithm is as follows:

[0045] Original data matrix: X = [x1, x2, ..., x n ], where x i is an m-dimensional vector;

[0046] Covariance matrix: C = XT*X / (n-1);

[0047] Eigenvalues ​​and Eigenvectors: Solve for the eigenvalues ​​λ of the covariance matrix C i and the corresponding eigenvector e i ;

[0048] Principal component: Select the eigenvectors corresponding to the first k largest eigenvalues ​​to form the transformation matrix P = [e i ,e2,...,e k ];

[0049] Converted data: Y = P * XT;

[0050] Through the PCA algorithm, the dimension of the data can be reduced, noise and redundant information can be removed, and the most important data features can be retained;

[0051] At the same time, after data preprocessing, real-time data fusion technology is further introduced; the multi-source data fusion algorithm is used to fuse data from different sensors and systems to generate a more comprehensive and accurate description of the vehicle status. This fusion not only improves the richness and reliability of the data, but also provides a richer information basis for subsequent fault detection; the formula of the multi-source data fusion algorithm is as follows:

[0052] State prediction equation: x'=Fx+u; where F is the state transfer matrix and u is the control input;

[0053] Observation equation: z = Hx + v; where H is the observation matrix and v is the observation noise;

[0054] Covariance matrix update: P' = FPFT(HPH-1); where R is the observation noise covariance matrix, x new =x'+K(z-Hx'),P new =(1-KH)P'.

[0055] From the above, it can be seen that by introducing the above algorithm formula, the creativity of data preprocessing and screening as well as real-time data fusion technology can be enhanced, the accuracy and reliability of data can be improved, and a richer information basis can be provided for subsequent fault detection.

[0056] Furthermore, in step S1, encryption technology is used in the data collection process to ensure the security of the collected data during transmission and storage, while protecting the privacy rights of users. This step not only meets the current society's strict requirements for data security and privacy protection, but also improves the overall reliability and user trust of the intelligent connected vehicle fault detection system; H mapping model using encryption technology:

[0057]

[0058] Among them, x i ,y i Respectively represent the model input and output; the state of the mapping system under the condition of parameters a=1.4, b=0.3, x0=y0=0.4 is chaotic; the encryption technology processing includes the following steps:

[0059] S101, determine the initial values ​​x0, x′0, y0 of the two mapping models, and the control parameters 0, a, b, use them as the encryption key for multi-source big data, and carry out initialization processing;

[0060] S102, in order to conceal the original value of multi-source big data, set the number of iterations to 15, iterate the key processing, and improve the security of the data;

[0061] S103, select L mapping processing key, take x0 as initial parameter, input into L mapping model, obtain parameter x′0 through iteration, multiply x′0 by parameter y0, select the above product result as initial parameter of H mapping model, expand mapping operation to obtain parameter x n ,y n ,x n ,y n That is the final iterative result P of the H mapping model; the L mapping model is as follows:

[0062] x n+1 =x n ×0×σ(1-x n );

[0063] Where x∈[0,1]; o represents the control parameter; x n Represents any value;

[0064] S104, perform a modulo operation P to obtain a chaotic key P′:

[0065] P′=Pmod 256×(x i+1 +y i+1 );

[0066] S105. Finally, process the key byte P′ and the plaintext byte M to obtain the encrypted multi-source big data S:

[0067]

[0068] At the same time, the frequency, accuracy and scope of data collection are dynamically adjusted according to the actual operating conditions of the vehicle and the requirements of the fault prediction model; it includes:

[0069] When the vehicle is in complex road conditions or under high load, the density and accuracy of data collection are increased to more accurately capture potential fault information; when the vehicle is running smoothly, the frequency of data collection is appropriately reduced to save resources and energy; this dynamic adjustment strategy makes data collection more intelligent and efficient.

[0070] From the above, we can see that the system can dynamically adjust the frequency, accuracy and scope of data collection according to the actual operating conditions of the vehicle and the needs of the fault prediction model; this not only helps to improve the accuracy of fault detection, but also achieves optimal data utilization when resources are limited.

[0071] Furthermore, in step S2, an attention mechanism is introduced into the deep learning model, so that the model can automatically focus on the most important features or time series points for fault prediction, which helps the model to filter out key information from complex data and improve the accuracy of prediction;

[0072] The core of the attention mechanism is to calculate the importance or weight of each input element (or time series point) for the output (or current prediction); this is usually achieved through the following steps:

[0073] Calculate the score: For each input element x i , calculate a score s i , the score reflects the importance of the element to the current output or prediction; the score is usually calculated by a compatibility function, which can be a dot product, a bilinear function, or a trainable feedforward neural network;

[0074] s i =score(x i ,q)

[0075] Where q represents the query vector, which is used to guide the attention mechanism to focus on specific input elements;

[0076] Calculate weights: Use the softmax function to convert the scores into probability distributions (i.e. weights) to ensure that the sum of all weights is 1;

[0077]

[0078] Weighted sum: The input elements are weighted and summed according to the calculated weights to obtain the final output or prediction;

[0079] y=∑ i α i ·x i .

[0080] Furthermore, in step S3, a hierarchical warning module is introduced, which issues warning signals of different levels according to the severity and urgency of the fault; including: for minor faults, early warnings can be issued and regular inspections are recommended; for serious faults, emergency warnings are immediately issued and immediate parking inspections are recommended; its warning thresholds include:

[0081] If the probability of a “serious” failure level y severe >0.8, an emergency warning is issued and it is recommended to stop the car for inspection immediately;

[0082] If the probability of a "normal" failure level y medium >0.6 and ysevere≤0.8, an intermediate warning is issued and an inspection is recommended as soon as possible;

[0083] If the probability of a “minor” failure level y mild >0.4 and ymed i um ≤0.6, an early warning is issued and regular inspection is recommended.

[0084] From the above, it can be seen that by combining the design of emotional warning signals with hierarchical warning threshold settings, the creativity and effectiveness of the hierarchical warning module can be significantly enhanced, providing more accurate and personalized warning services for intelligent connected vehicle fault detection.

[0085] Furthermore, in step S4, a personalized fault warning interface is introduced; the interface may include user-defined colors, icons, layouts, etc., so that the fault information is more intuitive and easy to understand, thereby improving user acceptance and reaction speed;

[0086] At the same time, emotional design elements are introduced, such as using friendly voice prompts, animation effects or emoticons to convey the urgency and importance of fault information; this can reduce the driver's nervousness when receiving fault warnings and improve the user experience;

[0087] A fault warning community is also established to allow drivers to share their own fault situations, handling experiences and suggestions; the system can automatically collect and analyze this data to optimize the accuracy of fault warnings and handling suggestions.

[0088] Comparative example: A fault detection method based on single sensor data, including:

[0089] 1) Check the appearance and installation status of the sensor: This is the first step in troubleshooting. It mainly involves visual inspection to check whether the sensor is damaged, whether there are signs of water ingress, and whether the installation position is correct and firm.

[0090] 2) Hardware circuit detection: Use professional tools to troubleshoot sensor hardware, including checking whether there is a short circuit between the positive and negative poles of the component power supply, whether the sensor is working at the working voltage, and whether the grounding circuit is in good condition;

[0091] 3) Signal circuit check: Different sensors have different communication protocols. Therefore, it is necessary to use an oscilloscope or multimeter to detect whether there is signal transmission or level jump in the sensor signal circuit according to the actual situation of the sensor to determine whether the communication is normal.

[0092] The effects of a fault detection method for an intelligent connected vehicle in the embodiment and a conventional fault detection method based on single sensor data (control example) are compared to obtain the following table:

[0093]

[0094] It can be seen from the above that the intelligent connected vehicle fault detection method of the embodiment is superior to the current conventional fault detection method based on single sensor data in many aspects such as data analysis method, early warning system, response speed, and diagnostic accuracy; this method integrates multi-source data and uses deep learning models for real-time analysis. It can more accurately predict and locate faults, provide personalized early warnings and processing suggestions, thereby improving the safety and user experience of intelligent connected vehicles.

[0095] A fault detection system for an intelligent connected vehicle, such as Figure 2 As shown, the above-mentioned intelligent connected vehicle fault detection method includes:

[0096] The data collection module is used to collect real-time data of intelligent connected vehicles during driving, including vehicle sensor data, network communication data, user behavior data and environmental perception data;

[0097] The data preprocessing and screening module performs preliminary processing on the collected data, removes noise and redundant information, and screens the data according to its importance and relevance, using the principal component analysis (PCA) algorithm to optimize data quality;

[0098] Real-time data fusion module, which uses multi-source data fusion algorithm to fuse data from different sensors and systems to generate a comprehensive and accurate description of vehicle status;

[0099] The deep learning analysis module uses a deep learning model to analyze the fused data in real time, identify fault precursor patterns, predict potential fault types, and introduce an attention mechanism into the model to improve prediction accuracy;

[0100] The fault warning and location module, based on the analysis results, promptly issues fault warning signals through the vehicle's built-in AI decision-making system, and accurately locates the source of the fault to a specific component or system. The introduction of a hierarchical warning module issues warning signals of different levels according to the severity and urgency of the fault;

[0101] The user interaction module feeds back the fault diagnosis results to the vehicle display or the driver, and provides corresponding fault handling suggestions. It supports users to customize the fault warning level and receiving method, introduces a personalized fault warning interface and emotional design elements, and establishes a fault warning community for drivers to share fault conditions and handling experiences;

[0102] The cloud communication and update module establishes a real-time communication mechanism between the cloud data center and the on-board terminal to achieve continuous updating of the fault prediction model, fault case sharing and remote technical support. It also supports data exchange with other intelligent connected vehicles to enhance prediction accuracy.

[0103] In summary: the present invention has the following beneficial effects:

[0104] 1) Improve fault detection accuracy: By collecting and analyzing diversified real-time data (including vehicle sensor data, network communication data, user behavior data, and environmental perception data), and using deep learning models for real-time analysis, it is possible to more accurately identify fault precursor patterns and predict potential fault types;

[0105] 2) Enhanced fault location capability: Based on the analysis results, the fault source can be accurately located to a specific component or system, avoiding the problem of relatively vague fault location in traditional methods and facilitating rapid troubleshooting;

[0106] 3) Improve the intelligence level of the early warning system: Introduce a hierarchical early warning module to issue early warning signals of different levels according to the severity and urgency of the fault, thereby improving the intelligence level of the early warning system and enabling drivers to understand the vehicle status more timely and accurately;

[0107] 4) Optimize user experience: Support users to customize fault warning levels and receiving methods, introduce personalized fault warning interfaces and emotional design elements, reduce drivers' nervousness when receiving fault warnings, and improve user experience;

[0108] 5) Promote data sharing and model updating: Establish a real-time communication mechanism between the cloud data center and the vehicle terminal to achieve continuous updating of the fault prediction model, fault case sharing and remote technical support, while supporting data exchange with other intelligent connected vehicles to enhance prediction accuracy;

[0109] 6) Ensure data security and privacy: Encryption technology is used in the data collection process to ensure the security of the collected data during transmission and storage, while protecting the privacy rights of users;

[0110] 7) Improve response speed: Through real-time data collection and analysis, as well as the vehicle's built-in AI decision-making system, rapid response and immediate warning of faults can be achieved, helping to reduce vehicle downtime caused by faults;

[0111] 8) Reduce maintenance costs: Through accurate fault prediction and location, as well as personalized fault handling suggestions, the maintenance cost and time cost of the vehicle can be reduced;

[0112] 9) Enhance system reliability and stability: Through the application of multi-source data fusion technology and deep learning models, the reliability and stability of the system are improved, and the risk of safety accidents caused by system failures is reduced;

[0113] 10) Promote the development of intelligent connected vehicle technology: The application of this fault detection method and system has promoted the further development of intelligent connected vehicle technology and provided strong technical support for the popularization and application of intelligent connected vehicles.

[0114] The embodiment of the present application provides an electronic device, which is applicable to the above-mentioned intelligent connected vehicle fault detection method, including:

[0115] Memory, used to protect computer programs and data;

[0116] Processor, used to run system programs.

[0117] An embodiment of the present application provides a computer storage medium, which is applicable to the above-mentioned intelligent connected vehicle fault detection method, and performs hierarchical confidentiality management on the above-mentioned system and data in accordance with confidentiality management requirements.

[0118] Those skilled in the art will appreciate that the embodiments of the present application may be provided as a system or a computer program product. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0119] The present application is described with reference to the flowcharts and / or block diagrams of the devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0120] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0121] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0122] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0123] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0124] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory media such as modulated data signals and carrier waves.

[0125] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, commodity or device including the elements.

[0126] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for detecting faults in an intelligent networked vehicle, characterized in that: include: S1. First, collect real-time data of intelligent connected vehicles during driving, including vehicle sensor data, network communication data, user behavior data and environmental perception data; S2. Then, a deep learning model is used to analyze the above data in real time to identify fault precursor patterns and predict potential fault types; S3. Then, based on the analysis results, the vehicle's built-in AI decision-making system will promptly issue a fault warning signal and accurately locate the source of the fault to a specific component or system to obtain a fault diagnosis result; S4. Feedback fault diagnosis results to the vehicle display or driver, and provide corresponding fault handling suggestions, support users to customize fault warning levels and receiving methods, and enhance user experience.

2. A method for detecting faults in an intelligent networked vehicle as claimed in claim 1, characterized in that: The method also includes: establishing a real-time communication mechanism between the cloud data center and the vehicle-mounted terminal, while supporting data exchange with other intelligent connected vehicles.

3. A method for detecting faults in an intelligent networked vehicle as claimed in claim 1, characterized in that: In the step S1, based on the original data collection, a data preprocessing and screening module is introduced; At the same time, after data preprocessing, real-time data fusion technology is further introduced.

4. A method for detecting faults in an intelligent networked vehicle as claimed in claim 1, characterized in that: In the step S1, encryption technology is used during data collection; At the same time, the frequency, accuracy and scope of data collection are dynamically adjusted according to the actual operating conditions of the vehicle and the requirements of the fault prediction model.

5. A method for detecting faults in an intelligent networked vehicle as claimed in claim 1, characterized in that: In step S2, an attention mechanism is introduced into the deep learning model so that the model can automatically focus on the most important features or time series points for fault prediction.

6. A method for detecting faults in an intelligent networked vehicle as claimed in claim 1, characterized in that: In step S3, a hierarchical warning module is introduced, which issues warning signals of different levels according to the severity and urgency of the fault.

7. A method for detecting faults in an intelligent networked vehicle as claimed in claim 1, characterized in that: In step S4, a personalized fault warning interface is introduced; At the same time, introduce emotional design elements, including using friendly voice prompts, animation effects or emoticons to convey the urgency and importance of fault information; A fault warning community is also established to allow drivers to share their own fault situations, handling experiences and suggestions.

8. An intelligent networked vehicle fault detection system, characterized in that: Using a method for detecting faults in an intelligent connected vehicle as described in claims 1 to 7, comprising: The data collection module is used to collect real-time data of intelligent connected vehicles during driving, including vehicle sensor data, network communication data, user behavior data and environmental perception data; The data preprocessing and screening module performs preliminary processing on the collected data, removes noise and redundant information, and screens the data according to its importance and relevance, using the principal component analysis (PCA) algorithm to optimize data quality; Real-time data fusion module, which uses multi-source data fusion algorithms, including Kalman filtering, particle filtering or fusion networks in deep learning, to fuse data from different sensors and systems to generate a comprehensive and accurate description of the vehicle status; The deep learning analysis module uses a deep learning model to analyze the fused data in real time, identify fault precursor patterns, predict potential fault types, and introduce an attention mechanism into the model to improve prediction accuracy; The fault warning and location module, based on the analysis results, promptly issues fault warning signals through the vehicle's built-in AI decision-making system, and accurately locates the source of the fault to a specific component or system. The introduction of a hierarchical warning module issues warning signals of different levels according to the severity and urgency of the fault; The user interaction module feeds back the fault diagnosis results to the vehicle display or the driver, and provides corresponding fault handling suggestions. It supports users to customize the fault warning level and receiving method, introduces a personalized fault warning interface and emotional design elements, and establishes a fault warning community for drivers to share fault conditions and handling experiences; The cloud communication and update module establishes a real-time communication mechanism between the cloud data center and the on-board terminal to achieve continuous updating of the fault prediction model, fault case sharing and remote technical support. It also supports data exchange with other intelligent connected vehicles to enhance prediction accuracy.

9. A processor, characterized in that: The method is configured to execute the intelligent connected vehicle fault detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the intelligent connected vehicle fault detection method according to any one of claims 1 to 7 is implemented.

Images