Automobile fault monitoring and diagnosing system and method based on Internet of Things

Abstract

The invention provides an automobile fault monitoring and diagnosing system and method based on the Internet of Things, and relates to the field of intelligent automobile fault monitoring. And then analyzing the acquired running data of each part of the automobile in real time by adopting a data analysis technology based on artificial intelligence so as to judge whether the automobile has a fault hidden danger or not. In this way, more accurate and efficient automobile fault monitoring can be achieved, and therefore a powerful guarantee is provided for safe operation of a new energy automobile.

Description

Technical Field

[0001] The present application relates to the field of intelligent automobile fault monitoring, and more specifically, to an automobile fault monitoring and diagnosis system and method based on the Internet of Things. Background Art

[0002] New energy vehicles refer to vehicles that use unconventional automotive fuels as their power source and integrate advanced technologies in vehicle power control and drive to form advanced technical principles, new technologies, and new structures. Existing new energy vehicles pass quality inspection when they leave the factory, and after being delivered to customers for use for a period of time, they need to be taken to the service provider for maintenance and related diagnosis as required to ensure normal and safe operation. At present, new energy vehicle maintenance institutions mostly use diagnostic instruments to diagnose vehicle faults, and it takes a lot of time to test the various components of new energy vehicles, and the diagnostic cost is high. In addition, the current fault monitoring has not been fully subdivided into parameter diagnosis of various systems such as electric drive, battery, and brakes, so there is a certain probability of misdiagnosis in the diagnosis, resulting in the replacement of wrong parts.

[0003] Therefore, an optimized automobile fault monitoring and diagnosis solution is needed. Summary of the invention

[0004] In order to solve the above technical problems, this application is proposed. The embodiment of this application provides an automobile fault monitoring and diagnosis system and method based on the Internet of Things, which first collects real-time operating data of various components of the automobile through various sensors, and then uses artificial intelligence-based data analysis technology to analyze the collected operating data of various components of the automobile in real time, and then judges whether the automobile has hidden faults. In this way, more accurate and efficient automobile fault monitoring can be achieved, thereby providing strong protection for the safe operation of new energy vehicles.

[0005] According to one aspect of the present application, there is provided an automobile fault monitoring and diagnosis system based on the Internet of Things, which includes:

[0006] The vehicle fault monitoring related data acquisition module is used to obtain the driving motor speed value, driving motor vibration frequency value, battery pack voltage value, battery pack current value, battery pack internal resistance value, battery pack temperature value, four sets of tire pressure values, brake pad temperature value, brake pad thickness value, brake pad sound frequency value at multiple predetermined time points within a predetermined time period;

[0007] An automobile electric drive monitoring module, used for performing time-series coding on the driving motor speed values ​​and the driving motor vibration frequency values ​​at the plurality of predetermined time points to obtain an automobile electric drive monitoring time-series characteristic matrix;

[0008] The vehicle battery monitoring module is used to perform time-series coding on the battery pack voltage value, battery pack current value, battery pack internal resistance value, and battery pack temperature value at the plurality of predetermined time points to obtain a vehicle battery monitoring time-series characteristic matrix;

[0009] A vehicle tire monitoring module, used for performing time-series coding on the four groups of tire pressure values ​​at the plurality of predetermined time points to obtain a time-series characteristic matrix for monitoring vehicle tire pressure;

[0010] An automobile brake pad monitoring module, used for performing time-series coding on the brake pad temperature values, brake pad thickness values, and brake pad sound frequency values ​​at the plurality of predetermined time points to obtain an automobile brake pad monitoring time-series feature matrix;

[0011] An automobile monitoring feature fusion module, used for fusing the automobile electric drive monitoring timing feature matrix, the automobile battery monitoring timing feature matrix, the automobile tire pressure monitoring timing feature matrix and the automobile brake pad monitoring timing feature matrix to obtain an automobile monitoring feature matrix;

[0012] The vehicle fault monitoring result generating module is used to obtain the vehicle fault monitoring result based on the vehicle monitoring feature matrix.

[0013] According to another aspect of the present application, a method for monitoring and diagnosing automobile faults based on the Internet of Things is provided, which includes:

[0014] Obtaining the driving motor speed value, driving motor vibration frequency value, battery pack voltage value, battery pack current value, battery pack internal resistance value, battery pack temperature value, four sets of tire pressure values, brake pad temperature value, brake pad thickness value, and brake pad sound frequency value at multiple predetermined time points within a predetermined time period;

[0015] Performing time-series coding on the driving motor speed values ​​and the driving motor vibration frequency values ​​at the plurality of predetermined time points to obtain a vehicle electric drive monitoring time-series characteristic matrix;

[0016] Performing time-series coding on the battery pack voltage values, battery pack current values, battery pack internal resistance values, and battery pack temperature values ​​at the plurality of predetermined time points to obtain a vehicle battery monitoring time-series characteristic matrix;

[0017] Performing time series coding on the four groups of tire pressure values ​​at the plurality of predetermined time points to obtain a time series characteristic matrix for automobile tire pressure monitoring;

[0018] Performing time series coding on the brake pad temperature values, brake pad thickness values, and brake pad sound frequency values ​​at the plurality of predetermined time points to obtain a vehicle brake pad monitoring time series feature matrix;

[0019] The automobile electric drive monitoring timing feature matrix, the automobile battery monitoring timing feature matrix, the automobile tire pressure monitoring timing feature matrix and the automobile brake pad monitoring timing feature matrix are integrated to obtain an automobile monitoring feature matrix;

[0020] Based on the automobile monitoring feature matrix, an automobile fault monitoring result is obtained.

[0021] Compared with the prior art, the automobile fault monitoring and diagnosis system and method based on the Internet of Things provided by the present application first collects the real-time operation data of various automobile components through various sensors, and then uses artificial intelligence-based data analysis technology to analyze the collected operation data of various automobile components in real time, and then judges whether the automobile has hidden faults. In this way, more accurate and efficient automobile fault monitoring can be achieved, thereby providing strong protection for the safe operation of new energy vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0023] Figure 1 The system block diagram of the automobile fault monitoring and diagnosis system based on the Internet of Things according to an embodiment of the present application.

[0024] Figure 2 The block diagram is a vehicle electric drive monitoring module in the vehicle fault monitoring and diagnosis system based on the Internet of Things according to an embodiment of the present application.

[0025] Figure 3 The block diagram is a vehicle battery monitoring module in the vehicle fault monitoring and diagnosis system based on the Internet of Things according to an embodiment of the present application.

[0026] Figure 4 The block diagram is a vehicle tire monitoring module in the vehicle fault monitoring and diagnosis system based on the Internet of Things according to an embodiment of the present application.

[0027] Figure 5 The present invention is a block diagram of an automobile brake pad monitoring module in an automobile fault monitoring and diagnosis system based on the Internet of Things according to an embodiment of the present application.

[0028] Figure 6 The present invention is a block diagram of a vehicle fault monitoring result generating module in an automobile fault monitoring and diagnosis system based on the Internet of Things according to an embodiment of the present application.

[0029] Figure 7The flowchart is a method for monitoring and diagnosing automobile faults based on the Internet of Things according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0031] New energy vehicles use unconventional automotive fuels as their power source, integrate advanced technologies in vehicle power control and driving, and have the characteristics of advanced technical principles and novel structures. At present, new energy vehicles will undergo strict quality inspections when they leave the factory, and when they are delivered to customers for use for a period of time, they need to go to the service provider for maintenance and related diagnosis as required to ensure that the vehicle can operate normally and safely. At present, in new energy vehicle maintenance institutions, diagnostic instruments are often used to diagnose vehicle faults. However, when testing the various components of new energy vehicles, it often takes a lot of time and the diagnostic cost is high. In addition, the current fault monitoring has not been fully refined to the parameter diagnosis level of various systems such as electric drive, battery, and brake. For this reason, there is a certain probability of misdiagnosis during the diagnosis process, which leads to the phenomenon of replacing the wrong parts. Therefore, an optimized automobile fault monitoring and diagnosis solution is expected.

[0032] In recent years, deep learning and neural networks have been widely used in computer vision, natural language processing, text signal processing and other fields. In addition, deep learning and neural networks have also demonstrated a level close to or even beyond that of humans in image classification, object detection, semantic segmentation, text translation and other fields. The development of deep learning and neural networks has provided new solutions and solutions for automobile fault monitoring and diagnosis.

[0033] Figure 1 FIG. 1 is a system block diagram of an automobile fault monitoring and diagnosis system based on the Internet of Things according to an embodiment of the present application. Figure 1As shown, in the automobile fault monitoring and diagnosis system 100 based on the Internet of Things, it includes: an automobile fault monitoring related data acquisition module 110, which is used to obtain the driving motor speed value, driving motor vibration frequency value, battery pack voltage value, battery pack current value, battery pack internal resistance value, battery pack temperature value, four sets of tire pressure values, brake pad temperature value, brake pad thickness value, and brake pad sound frequency value at multiple predetermined time points within a predetermined time period; an automobile electric drive monitoring module 120, which is used to perform time-series encoding on the driving motor speed value and driving motor vibration frequency value at the multiple predetermined time points to obtain the automobile electric drive monitoring time-series feature matrix; an automobile battery monitoring module 130, which is used to perform time-series encoding on the battery pack voltage value, battery pack current value, battery pack internal resistance value, and battery pack temperature value at the multiple predetermined time points to obtain the automobile A vehicle battery monitoring timing feature matrix; a vehicle tire monitoring module 140, used for time-series encoding the four groups of tire pressure values ​​at the multiple predetermined time points to obtain a vehicle tire pressure monitoring timing feature matrix; a vehicle brake pad monitoring module 150, used for time-series encoding the brake pad temperature values, brake pad thickness values, and brake pad sound frequency values ​​at the multiple predetermined time points to obtain a vehicle brake pad monitoring timing feature matrix; a vehicle monitoring feature fusion module 160, used for fusing the vehicle electric drive monitoring timing feature matrix, the vehicle battery monitoring timing feature matrix, the vehicle tire pressure monitoring timing feature matrix, and the vehicle brake pad monitoring timing feature matrix to obtain a vehicle monitoring feature matrix; a vehicle fault monitoring result generation module 170, used for obtaining a vehicle fault monitoring result based on the vehicle monitoring feature matrix.

[0034] Specifically, in the technical solution of the present application, the drive motor speed value, drive motor vibration frequency value, battery pack voltage value, battery pack current value, battery pack internal resistance value, battery pack temperature value, four sets of tire pressure values, brake pad temperature value, brake pad thickness value, and brake pad sound frequency value at multiple predetermined time points within a predetermined time period are first obtained. It should be understood that the drive motor speed value reflects the running state of the motor. Abnormal speed may indicate that the motor has mechanical failure or controller failure. The drive motor vibration frequency value is related to problems such as motor bearing wear, imbalance or loose mechanical parts, and is an important indicator of the motor health status. Battery pack voltage fluctuation or abnormality indicates inconsistent performance between battery cells, battery aging or charging / discharging system problems. Abnormal battery pack current means internal short circuit and open circuit problems. Increased internal resistance of the battery pack is usually related to battery aging, reduction of active substances or electrolyte failure. Abnormal battery pack temperature indicates battery overheating and thermal runaway, which is an important monitoring parameter for battery safety. Insufficient or excessive tire pressure will affect the grip, wear and safety of the tire, which is an important part of automobile fault monitoring. Excessive brake pad temperature indicates frequent use of the braking system, severe wear of the brake pad or failure of the brake caliper. The brake pad thickness is reduced to a certain extent and needs to be replaced, otherwise it will affect the braking effect and safety. Abnormal brake pad sound indicates uneven wear of the brake pad, loose caliper or deformation of the brake disc. In general, there is a close connection between these indicators and vehicle failures. By real-time monitoring and analyzing the changes in these indicators, potential hidden dangers of failures can be discovered in a timely manner, and the occurrence or expansion of failures can be avoided, thereby ensuring the normal and safe operation of new energy vehicles.

[0035] In an embodiment of the present application, a possible implementation method for obtaining the driving motor speed value, driving motor vibration frequency value, battery pack voltage value, battery pack current value, battery pack internal resistance value, battery pack temperature value, four sets of tire pressure values, brake pad temperature value, brake pad thickness value, and brake pad sound frequency value at multiple predetermined time points within a predetermined time period can be: the driving motor speed value and the driving motor vibration frequency value can be acquired by collecting data through a speed sensor and a vibration sensor respectively; the battery pack voltage value, the battery pack current value, the battery pack internal resistance value, and the battery pack temperature value can be acquired by collecting data through a voltage sensor, a current sensor, an internal resistance sensor, and a temperature sensor respectively; the tire pressure data can be acquired by collecting data through a wireless tire pressure sensor; the brake pad temperature value, the brake pad thickness value, and the brake pad sound frequency value can be acquired by collecting data through a temperature sensor, a thickness sensor, and a sound sensor respectively; the vehicle control unit, as the data acquisition center, is responsible for collecting data from each sensor and performing preliminary processing, and transmits the data to a cloud server through an Internet of Things communication module, and the cloud server receives the data from the vehicle and stores it in a database, and at the same time, analyzes and processes the collected operation data to monitor vehicle faults.

[0036] Figure 2 FIG. 1 is a block diagram of an automobile electric drive monitoring module in an automobile fault monitoring and diagnosis system based on the Internet of Things according to an embodiment of the present application. Figure 2 As shown, the automobile electric drive monitoring module 120 includes: an automobile electric drive monitoring related data structuring unit 121, which is used to obtain the automobile electric drive monitoring timing input matrix according to the time dimension by the driving motor speed values ​​and the driving motor vibration frequency values ​​at the multiple predetermined time points; and an automobile electric drive monitoring timing feature extraction unit 122, which is used to obtain the automobile electric drive monitoring timing feature matrix by passing the automobile electric drive monitoring timing input matrix through an automobile fault monitoring parameter timing feature encoder based on a void convolution kernel.

[0037] Failures in the electric drive system of an automobile usually manifest as abnormal changes in the motor speed and vibration frequency. In order to facilitate the analysis of the collected data related to the automobile electric drive monitoring in order to discover potential failures in the automobile electric drive system, it is necessary to obtain the automobile electric drive monitoring timing input matrix according to the time dimension by calculating the drive motor speed values ​​and the drive motor vibration frequency values ​​at the multiple predetermined time points. By integrating the drive motor related data into a matrix, batch processing can be performed using the high efficiency of matrix operations, thereby improving the efficiency of data analysis.

[0038] In order to extract features useful for fault identification from the original arranged automobile electric drive monitoring timing input matrix, such as the periodic pattern of the drive motor speed and the drive motor vibration frequency, abnormal fluctuations, trend changes, etc., which are important bases for judging whether the automobile has a fault, it is necessary to pass the automobile electric drive monitoring timing input matrix through the automobile fault monitoring parameter timing feature encoder based on the hole convolution kernel to obtain the automobile electric drive monitoring timing feature matrix. In this application, the automobile fault monitoring parameter timing feature encoder based on the hole convolution kernel is a convolutional neural network model using a hole convolution kernel. The hole convolution can increase the receptive field without increasing the number of parameters and the amount of calculation by introducing holes (i.e., zero values ​​in the convolution kernel), which means that the hole convolution neural network can capture data dependencies within a longer time range, thereby more accurately extracting features from the automobile electric drive monitoring timing input matrix. And because the hole convolution neural network can capture the input data dependencies within a longer time range, it has better robustness to noise and outliers in the data. This means that in actual automobile fault monitoring and diagnosis applications, even if there is a certain amount of noise or abnormal fluctuations in the input data, the hole convolutional neural network can still accurately extract useful features.

[0039] In an embodiment of the present application, a possible implementation method of passing the automobile electric drive monitoring timing input matrix through an automobile fault monitoring parameter timing feature encoder based on a hole convolution kernel to obtain an automobile electric drive monitoring timing feature matrix may be: using each layer of the automobile fault monitoring parameter timing feature encoder based on a hole convolution kernel to perform the following operations on the input data in the forward transfer of the layer: using the convolution unit of the automobile fault monitoring parameter timing feature encoder based on a hole convolution kernel to perform convolution processing on the input data based on a hole convolution kernel to obtain a convolution feature map; using the pooling units of each layer of the automobile fault monitoring parameter timing feature encoder based on a hole convolution kernel to perform pooling processing on the convolution feature map along the channel dimension to obtain a pooling feature map; using the activation units of each layer of the automobile fault monitoring parameter timing feature encoder based on a hole convolution kernel to perform nonlinear activation on the feature values ​​of each position in the pooling feature map to obtain an activation feature map; wherein the output of the last layer of the automobile fault monitoring parameter timing feature encoder based on a hole convolution kernel is the automobile electric drive monitoring timing feature matrix.

[0040] Figure 3 FIG. 1 is a block diagram of an automobile battery monitoring module in an automobile fault monitoring and diagnosis system based on the Internet of Things according to an embodiment of the present application. Figure 3 As shown, the automobile battery monitoring module 130 includes: an automobile battery monitoring related data structuring unit 131, which is used to arrange the battery pack voltage values, battery pack current values, battery pack internal resistance values, and battery pack temperature values ​​at the multiple predetermined time points according to the time dimension to obtain an automobile battery monitoring timing input matrix; an automobile battery monitoring timing feature extraction unit 132, which is used to pass the automobile battery monitoring timing input matrix through the automobile fault monitoring parameter timing feature encoder based on the void convolution kernel to obtain the automobile battery monitoring timing feature matrix.

[0041] The performance parameters of the battery pack (such as voltage, current, internal resistance, and temperature) change over time. These changes contain important information about the working status of the battery pack. In order to reveal the changing trends and potential faults of the performance of the automotive battery pack, the battery pack voltage values, battery pack current values, battery pack internal resistance values, and battery pack temperature values ​​at the multiple predetermined time points can be arranged according to the time dimension to obtain the automotive battery monitoring timing input matrix. By arranging according to the time dimension, the battery pack monitoring time series data formed is convenient for time series analysis. Each row in the arranged automotive battery monitoring timing input matrix is ​​the battery pack monitoring data at a time point, and each column is a specific battery pack monitoring indicator.

[0042] By analyzing the abnormal fluctuations or trend changes of relevant data in the automotive battery monitoring timing input matrix, the abnormalities of the battery pack performance parameters can be discovered in time, and potential faults can be warned. For example, a sudden increase in the internal resistance of the battery pack means that faults such as plate sulfation and active material shedding have occurred inside the battery pack. Therefore, in the technical solution of the present application, it is necessary to pass the automotive battery monitoring timing input matrix through the automotive fault monitoring parameter timing feature encoder based on the void convolution kernel to obtain the automotive battery monitoring timing feature matrix. It should be understood that the void convolution kernel can capture the time-dependent features in the battery monitoring data by applying convolution operations at different time steps. These features can reflect the trend and periodicity of battery performance parameters over time, which is conducive to identifying battery performance degradation and fault signs.

[0043] Figure 4 FIG. 1 is a block diagram of a vehicle tire monitoring module in an automobile fault monitoring and diagnosis system based on the Internet of Things according to an embodiment of the present application. Figure 4 As shown, the automobile tire monitoring module 140 includes: an automobile tire monitoring related data structuring unit 141, which is used to arrange the four groups of tire pressure values ​​at the multiple predetermined time points according to the time dimension and the tire dimension to obtain the automobile tire pressure monitoring timing input matrix; an automobile tire monitoring timing feature extraction unit 142, which is used to pass the automobile tire pressure monitoring timing input matrix through the automobile fault monitoring parameter timing feature encoder based on the void convolution kernel to obtain the automobile tire pressure monitoring timing feature matrix.

[0044] In order to organize the original tire pressure data collected by the wireless tire pressure sensor into a form that is convenient for subsequent analysis and processing, the four groups of tire pressure values ​​at the multiple predetermined time points can be arranged according to the time dimension and the tire dimension to obtain a time series input matrix for automobile tire pressure monitoring. After the tire pressure data is organized into a time series input matrix, the time series analysis method can be conveniently applied to analyze abnormal changes in tire pressure, thereby realizing tire fault diagnosis. And because the time dimension and the tire dimension are considered at the same time, the changes in automobile tire pressure can be more comprehensively understood, thereby improving the accuracy and reliability of automobile fault detection.

[0045] The original automobile tire pressure monitoring time series input matrix contains a large number of data points. Although these data points are detailed, they often contain redundant information and noise. In order to effectively extract the key features in the tire pressure data and reduce the data dimension, it is necessary to pass the automobile tire pressure monitoring time series input matrix through the automobile fault monitoring parameter time series feature encoder based on the hole convolution kernel to obtain the automobile tire pressure monitoring time series feature matrix. It should be understood that tire pressure data is time series data, and its change trend and periodicity are crucial for judging the tire state. Through its unique structure, the hole convolution kernel can expand the receptive field of the convolution kernel without increasing the computational complexity, thereby better capturing the time series features in the tire pressure data. Compared with traditional tire pressure monitoring methods, they often only focus on whether the absolute value of the tire pressure exceeds the preset range, while ignoring the time series characteristics of the tire pressure data. Through the time series feature encoder based on the hole convolution kernel, the tire pressure data can be analyzed more comprehensively, thereby improving the accuracy of automobile fault diagnosis.

[0046] Figure 5 FIG. 1 is a block diagram of an automobile brake pad monitoring module in an automobile fault monitoring and diagnosis system based on the Internet of Things according to an embodiment of the present application. Figure 5 As shown, the automobile brake pad monitoring module 150 includes: an automobile brake pad monitoring related data structuring unit 151, which is used to arrange the brake pad temperature values, brake pad thickness values, and brake pad sound frequency values ​​at the multiple predetermined time points according to the time dimension to obtain the automobile brake pad monitoring timing input matrix; an automobile brake pad monitoring timing feature extraction unit 152, which is used to pass the automobile brake pad monitoring timing input matrix through the automobile fault monitoring parameter timing feature encoder based on the void convolution kernel to obtain the automobile brake pad monitoring timing feature matrix.

[0047] Brake pads are important components in the automotive brake system, and their performance status will change with the use of the vehicle. Parameters such as temperature, thickness, and sound frequency can reflect the working status of the brake pads and their changing trends. In order to intuitively display the performance status of the brake pads at different time points, thereby capturing their dynamic change process, it is necessary to arrange the brake pad temperature values, brake pad thickness values, and brake pad sound frequency values ​​at the multiple predetermined time points according to the time dimension to obtain the automotive brake pad monitoring time series input matrix. It should be understood that the brake pads may have abnormal conditions such as wear and overheating during use, and these abnormal conditions often show specific patterns in the time dimension. For example, excessive wear of the brake pads will cause the thickness value to gradually decrease, while overheating will cause the temperature value to increase abnormally. By arranging the monitoring data according to the time dimension, these abnormal patterns can be more easily identified, providing a basis for subsequent fault warning and diagnosis. In the arranged automotive brake pad monitoring time series input matrix, each row is the automotive brake pad monitoring data at a time point, and each column is a specific automotive brake pad monitoring indicator.

[0048] The relevant data of the current time point of the automobile brake pads often have a dependency relationship with the data of multiple time points in the past. In order to capture the long-distance dependency in the automobile brake pad data, so that the model can understand the evolution of the brake pad performance status over time, and then more accurately predict and diagnose faults, in the technical solution of the present application, the automobile brake pad monitoring time series input matrix is ​​passed through the automobile fault monitoring parameter time series feature encoder based on the void convolution kernel to obtain the automobile brake pad monitoring time series feature matrix. The automobile brake pad monitoring time series feature matrix obtained by processing the automobile fault monitoring parameter time series feature encoder based on the void convolution kernel, the feature information in the matrix can characterize the performance status of the brake pads and its change trend. When these feature information are abnormal, such as accelerated wear speed, continuous temperature increase, noise feature changes, etc., it can be judged that the automobile brake system has hidden fault hazards.

[0049] The electric drive system, battery system, tire system and brake system are crucial components of the car, and their status directly affects the overall performance and safety of the car. Considering that the operating status of the car involves the coordinated work of multiple systems and components, in order to achieve comprehensive monitoring and evaluation of multiple key systems of the car, so as to more accurately grasp the overall status of the car, the technical solution of the present application integrates the car electric drive monitoring timing feature matrix, the car battery monitoring timing feature matrix, the car tire pressure monitoring timing feature matrix and the car brake pad monitoring timing feature matrix to obtain the car monitoring feature matrix. The fused car monitoring feature matrix contains information from multiple aspects such as electric drive, battery, tire and brake system. These information complement and verify each other, and provide a comprehensive basis for judging whether the car has obvious hidden faults. Through fusion, it is helpful to improve the sensitivity of the fault diagnosis system to identify hidden faults of the car. Even if the data changes of a single system are not obvious, it may reveal potential fault risks after combining with the data of other systems.

[0050] Figure 6 FIG. 1 is a block diagram of a vehicle fault monitoring result generation module in a vehicle fault monitoring and diagnosis system based on the Internet of Things according to an embodiment of the present application. Figure 6As shown, the automobile fault monitoring result generating module 170 includes: an automobile monitoring feature enhancement unit 171, which is used to pass the automobile monitoring feature matrix through an automobile monitoring feature enhancer based on a spatial attention mechanism to obtain an automobile monitoring feature enhancement matrix; an automobile monitoring feature matrix expansion unit 172, which is used to expand the automobile monitoring feature enhancement matrix into an automobile monitoring feature enhancement vector; an automobile monitoring feature optimization unit 173, which is used to perform a back-propagation driven feature offset adjustment on the automobile monitoring feature enhancement vector to obtain an optimized automobile monitoring feature enhancement vector; and an automobile monitoring feature classification unit 174, which is used to pass the optimized automobile monitoring feature enhancement vector through a classifier-based automobile fault monitoring result generator to obtain a classification result, and the classification result is used to indicate whether the automobile at the current time point has a potential fault.

[0051] Although the automobile monitoring feature matrix obtained after fusion is comprehensive, its expressive power may be reduced due to information redundancy or interaction between features. In order to remove the redundant information in the fused feature matrix, strengthen the key features, and thus enhance the expressive power of the feature matrix so that it better reflects the actual state of the car, it is necessary to pass the automobile monitoring feature matrix through the automobile monitoring feature enhancer based on the spatial attention mechanism to obtain the automobile monitoring feature enhancement matrix. The automobile monitoring feature enhancer based on the spatial attention mechanism in this application is a convolutional neural network model using the spatial attention mechanism. It should be understood that the spatial attention mechanism can automatically learn and pay attention to the regional features in the feature matrix that are more critical for fault monitoring. In the fused feature matrix, although the monitoring data of multiple systems are included, not all features are equally important for the analysis of the current fault. Through the spatial attention mechanism, the weights of different features can be dynamically adjusted so that those features that are more relevant to the hidden dangers of the fault occupy a larger proportion in the subsequent analysis. In this way, the possible fault features can be made more prominent in the feature enhancement matrix, thereby accelerating the fault identification process.

[0052] In an embodiment of the present application, a feasible implementation method of passing the automobile monitoring feature matrix through an automobile monitoring feature enhancer based on a spatial attention mechanism to obtain an automobile monitoring feature enhancement matrix is ​​as follows: using each layer of the automobile monitoring feature enhancer based on a spatial attention mechanism to perform the following on the input data in the forward transfer of the layer: performing convolution processing based on a convolution kernel on the input data to obtain a convolution feature map; passing the convolution feature map through a spatial attention unit to obtain a spatial attention map; calculating the point-by-point multiplication of the convolution feature map and the spatial attention map to obtain a spatial attention feature map; inputting the spatial attention feature map into a nonlinear activation unit to obtain an activation feature map; wherein the input of the first layer of the automobile monitoring feature enhancer is the automobile monitoring feature matrix, and the output of the last layer of the automobile monitoring feature enhancer is the automobile monitoring feature enhancement matrix.

[0053] Considering that the automobile monitoring feature enhancement matrix has a high dimension, which is not conducive to subsequent data processing, the automobile monitoring feature enhancement matrix needs to be expanded into an automobile monitoring feature enhancement vector in the technical solution of this application. By expanding, the dimension of the feature data can be reduced, and the data after dimension reduction can reduce the computational complexity and storage requirements, thereby speeding up the operation of the automobile fault diagnosis algorithm.

[0054] In particular, considering that the present application relies on various sensors to collect automobile monitoring data, these sensors may produce errors due to manufacturing defects, aging or environmental factors (such as temperature, humidity), and in the process of data collection, they may also be affected by factors such as electromagnetic interference and signal attenuation. These factors will introduce noise into the collected data, thereby causing local feature disturbances in the final encoded automobile monitoring feature enhancement vector. Since in actual applications, the automobile fault monitoring system needs to operate stably for a long time, in order to ensure reliable automobile fault monitoring under various conditions, in the technical solution of the present application, it is necessary to perform a back-propagation driven feature offset adjustment on the automobile monitoring feature enhancement vector to obtain an optimized automobile monitoring feature enhancement vector.

[0055] Specifically, in an embodiment of the present application, the vehicle monitoring feature enhancement vector is subjected to a back-propagation driven feature offset adjustment to obtain an optimized vehicle monitoring feature enhancement vector, including: determining a first weight matrix and a second weight matrix of the classifier before and after each iterative update; performing matrix multiplication of the first weight matrix and the second weight matrix with the vehicle monitoring feature enhancement vector respectively to obtain a first vehicle monitoring modulation feature vector and a second vehicle monitoring modulation feature vector; calculating the position difference between the first vehicle monitoring modulation feature vector and the second vehicle monitoring modulation feature vector to obtain a vehicle monitoring shift information representation vector; calculating the F norm of the position mean vector between the first vehicle monitoring modulation feature vector and the second vehicle monitoring modulation feature vector as a shift compensation scaling factor; linearly scaling the vehicle monitoring shift information representation vector with the shift compensation scaling factor to obtain a scaled vehicle monitoring shift information representation vector, and inputting the scaled vehicle monitoring shift information representation vector into Sigmoi d activation function to obtain a vehicle monitoring back-propagation shift compensation representation vector; calculate the point-by-point multiplication of the vehicle monitoring back-propagation shift compensation representation vector and the vehicle monitoring feature enhancement vector to obtain the optimized vehicle monitoring feature enhancement vector.

[0056] In an embodiment of the present application, another expression of performing a back-propagation driven feature offset adjustment on the vehicle monitoring feature enhancement vector to obtain an optimized vehicle monitoring feature enhancement vector may be: processing the vehicle monitoring feature enhancement vector using the following formula to obtain the optimized vehicle monitoring feature enhancement vector; wherein the formula is:

[0057]

[0058] Wherein, M1 is the first weight matrix, M2 is the second weight matrix, V is the vehicle monitoring feature enhancement vector, represents matrix multiplication, Indicates adding by position point, ||·|| F represents the F norm of the feature vector, S represents the shift compensation scaling factor, ⊙ represents the point multiplication by position, represents point-by-point subtraction, sigmoid represents an activation function, and V' represents the optimized vehicle monitoring feature enhancement vector.

[0059] In order to enhance the robustness of the classifier to local disturbances in the input feature vector, the vehicle monitoring feature enhancement vector is subjected to displacement compensation based on back propagation representation. The key to the displacement compensation based on back propagation representation of the vehicle monitoring feature enhancement vector is to capture the information of the weight matrix changing with the training process, and to use this information to generate the vehicle monitoring displacement information representation vector, and then generate the vehicle monitoring back propagation displacement compensation representation vector through scaling and nonlinear transformation (Sigmoid function). In this way, the vehicle monitoring feature enhancement vector is described by the local displacement of the feature by supporting the distribution difference of different classification scenarios of the classifier during the training process, so that not only the displacement of the feature vector caused by the change of the weight matrix can be quantified, but also a compensation vector can be generated according to the displacement information. The role of the compensation vector is to weight and adjust each element in the feature vector according to the degree of influence of the disturbance, thereby reducing the influence of the disturbance on the classification result. In this way, the robustness of the classifier to local disturbances in the input data can be significantly improved, the stability and generalization ability of the classifier can be enhanced, and by reducing the influence of local disturbances on the classification results, the classifier can still maintain a high classification accuracy when facing noise or variant data.

[0060] Finally, the optimized automobile monitoring feature enhancement vector is passed through the automobile fault monitoring result generator based on the classifier to obtain a classification result, and the classification result is used to indicate whether the automobile at the current time point has a hidden fault. It should be understood that the optimized automobile monitoring feature enhancement vector is a high-dimensional feature data that is not easy to be directly understood. In order to automatically convert complex monitoring feature data into easy-to-understand fault classification results, the optimized automobile monitoring feature enhancement vector can be passed through the automobile fault monitoring result generator based on the classifier. As a machine learning model, the classifier can analyze and judge according to the input data and map it to different categories, that is, to judge whether the automobile at the previous time point has a hidden fault according to the information of the optimized automobile monitoring feature enhancement vector. When the classifier outputs a classification result indicating the existence of a hidden fault, the system can alert the driver by issuing an alarm, so as to take timely measures to avoid the expansion of the fault or the occurrence of an accident. In this way, by analyzing the real-time data of key automobile components, potential faults can be discovered earlier and the accuracy of fault diagnosis can be improved.

[0061] In summary, the automobile fault monitoring and diagnosis system 100 based on the Internet of Things according to the embodiment of the present application is explained, which first collects the real-time operation data of various components of the automobile through various sensors, and then uses the data analysis technology based on artificial intelligence to analyze the collected operation data of various components of the automobile in real time, and then judges whether the automobile has hidden faults. In this way, more accurate and efficient automobile fault monitoring can be achieved, thereby providing a strong guarantee for the safe operation of new energy vehicles.

[0062] As described above, the automobile fault monitoring and diagnosis system 100 based on the Internet of Things according to the embodiment of the present application can be implemented in various terminal devices, such as a server for automobile fault monitoring and diagnosis based on the Internet of Things. In one example, the automobile fault monitoring and diagnosis system 100 based on the Internet of Things according to the embodiment of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the automobile fault monitoring and diagnosis system 100 based on the Internet of Things can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the automobile fault monitoring and diagnosis system 100 based on the Internet of Things can also be one of the many hardware modules of the terminal device.

[0063] Alternatively, in another example, the Internet of Things-based automobile fault monitoring and diagnosis system 100 and the terminal device may also be separate devices, and the Internet of Things-based automobile fault monitoring and diagnosis system 100 may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0064] Figure 7 FIG. 1 is a flow chart of a vehicle fault monitoring and diagnosis method based on the Internet of Things according to an embodiment of the present application. Figure 7 As shown, in the automobile fault monitoring and diagnosis method based on the Internet of Things, it includes: S110, obtaining the driving motor speed value, driving motor vibration frequency value, battery pack voltage value, battery pack current value, battery pack internal resistance value, battery pack temperature value, four sets of tire pressure values, brake pad temperature value, brake pad thickness value, brake pad sound frequency value at multiple predetermined time points within a predetermined time period; S120, time-series encoding the driving motor speed value and driving motor vibration frequency value at the multiple predetermined time points to obtain the automobile electric drive monitoring time-series feature matrix; S130, time-series encoding the battery pack voltage value, battery pack current value, battery pack internal resistance value, and battery pack temperature value at the multiple predetermined time points to obtain the automobile electric drive monitoring time-series feature matrix. Obtain a vehicle battery monitoring timing feature matrix; S140, time-code the four groups of tire pressure values ​​at the multiple predetermined time points to obtain a vehicle tire pressure monitoring timing feature matrix; S150, time-code the brake pad temperature values, brake pad thickness values, and brake pad sound frequency values ​​at the multiple predetermined time points to obtain a vehicle brake pad monitoring timing feature matrix; S160, fuse the vehicle electric drive monitoring timing feature matrix, the vehicle battery monitoring timing feature matrix, the vehicle tire pressure monitoring timing feature matrix, and the vehicle brake pad monitoring timing feature matrix to obtain a vehicle monitoring feature matrix; S170, based on the vehicle monitoring feature matrix, obtain a vehicle fault monitoring result.

[0065] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned automobile fault monitoring and diagnosis method based on the Internet of Things have been referred to above. Figures 1 to 6 The description of the IoT-based automobile fault monitoring and diagnosis system has been introduced in detail, and therefore, its repeated description will be omitted.

[0066] In summary, the automobile fault monitoring and diagnosis method based on the Internet of Things according to the embodiment of the present application is explained, which first collects the real-time operation data of various automobile components through various sensors, and then uses artificial intelligence-based data analysis technology to analyze the collected operation data of various automobile components in real time, and then judges whether the automobile has hidden faults. In this way, more accurate and efficient automobile fault monitoring can be achieved, thereby providing strong protection for the safe operation of new energy vehicles.

Claims

1. An automobile fault monitoring and diagnosis system based on the Internet of Things, characterized in that: include: The vehicle fault monitoring related data acquisition module is used to obtain the driving motor speed value, driving motor vibration frequency value, battery pack voltage value, battery pack current value, battery pack internal resistance value, battery pack temperature value, four sets of tire pressure values, brake pad temperature value, brake pad thickness value, brake pad sound frequency value at multiple predetermined time points within a predetermined time period; An automobile electric drive monitoring module, used for performing time-series coding on the driving motor speed values ​​and the driving motor vibration frequency values ​​at the plurality of predetermined time points to obtain an automobile electric drive monitoring time-series characteristic matrix; The vehicle battery monitoring module is used to perform time-series coding on the battery pack voltage value, battery pack current value, battery pack internal resistance value, and battery pack temperature value at the plurality of predetermined time points to obtain a vehicle battery monitoring time-series characteristic matrix; A vehicle tire monitoring module, used for performing time-series coding on the four groups of tire pressure values ​​at the plurality of predetermined time points to obtain a time-series characteristic matrix for monitoring vehicle tire pressure; An automobile brake pad monitoring module, used for performing time-series coding on the brake pad temperature values, brake pad thickness values, and brake pad sound frequency values ​​at the plurality of predetermined time points to obtain an automobile brake pad monitoring time-series feature matrix; An automobile monitoring feature fusion module, used for fusing the automobile electric drive monitoring timing feature matrix, the automobile battery monitoring timing feature matrix, the automobile tire pressure monitoring timing feature matrix and the automobile brake pad monitoring timing feature matrix to obtain an automobile monitoring feature matrix; The vehicle fault monitoring result generating module is used to obtain the vehicle fault monitoring result based on the vehicle monitoring feature matrix.

2. The automobile fault monitoring and diagnosis system based on the Internet of Things according to claim 1 is characterized in that: The automobile electric drive monitoring module comprises: The vehicle electric drive monitoring related data structuring unit is used to obtain the vehicle electric drive monitoring timing input matrix according to the time dimension by converting the driving motor speed values ​​and the driving motor vibration frequency values ​​at the plurality of predetermined time points; The automobile electric drive monitoring timing feature extraction unit is used to obtain the automobile electric drive monitoring timing feature matrix by passing the automobile electric drive monitoring timing input matrix through an automobile fault monitoring parameter timing feature encoder based on a hole convolution kernel.

3. The automobile fault monitoring and diagnosis system based on the Internet of Things according to claim 2 is characterized in that: The automobile battery monitoring module comprises: The vehicle battery monitoring related data structuring unit is used to arrange the battery pack voltage values, battery pack current values, battery pack internal resistance values, and battery pack temperature values ​​at the plurality of predetermined time points according to the time dimension to obtain a vehicle battery monitoring timing input matrix; The automobile battery monitoring timing feature extraction unit is used to pass the automobile battery monitoring timing input matrix through the automobile fault monitoring parameter timing feature encoder based on the void convolution kernel to obtain the automobile battery monitoring timing feature matrix.

4. The automobile fault monitoring and diagnosis system based on the Internet of Things according to claim 3 is characterized in that: The automobile tire monitoring module comprises: A vehicle tire monitoring related data structuring unit, used for arranging the four groups of tire pressure values ​​at the plurality of predetermined time points according to the time dimension and the tire dimension to obtain a vehicle tire pressure monitoring time series input matrix; The automobile tire monitoring time series feature extraction unit is used to pass the automobile tire pressure monitoring time series input matrix through the automobile fault monitoring parameter time series feature encoder based on the void convolution kernel to obtain the automobile tire pressure monitoring time series feature matrix.

5. The automobile fault monitoring and diagnosis system based on the Internet of Things according to claim 4 is characterized in that: The automobile brake pad monitoring module comprises: A data structuring unit related to automobile brake pad monitoring, used for arranging the brake pad temperature values, brake pad thickness values, and brake pad sound frequency values ​​at the plurality of predetermined time points according to the time dimension to obtain an automobile brake pad monitoring time series input matrix; The automobile brake pad monitoring timing feature extraction unit is used to pass the automobile brake pad monitoring timing input matrix through the automobile fault monitoring parameter timing feature encoder based on the void convolution kernel to obtain the automobile brake pad monitoring timing feature matrix.

6. The automobile fault monitoring and diagnosis system based on the Internet of Things according to claim 5 is characterized in that: The automobile fault monitoring result generating module comprises: A vehicle monitoring feature enhancement unit, used for passing the vehicle monitoring feature matrix through a vehicle monitoring feature enhancer based on a spatial attention mechanism to obtain a vehicle monitoring feature enhancement matrix; An automobile monitoring feature matrix expansion unit, used for expanding the automobile monitoring feature enhancement matrix into an automobile monitoring feature enhancement vector; A vehicle monitoring feature optimization unit, configured to perform a back-propagation driven feature offset adjustment on the vehicle monitoring feature enhancement vector to obtain an optimized vehicle monitoring feature enhancement vector; The automobile monitoring feature classification unit is used to pass the optimized automobile monitoring feature enhancement vector through a classifier-based automobile fault monitoring result generator to obtain a classification result, and the classification result is used to indicate whether the automobile has a potential fault at the current time point.

7. The automobile fault monitoring and diagnosis system based on the Internet of Things according to claim 6 is characterized in that: The vehicle monitoring feature optimization unit is used to: Determining a first weight matrix and a second weight matrix of the classifier before and after each iterative update; Performing matrix multiplication of the first weight matrix and the second weight matrix with the vehicle monitoring feature enhancement vector respectively to obtain a first vehicle monitoring modulation feature vector and a second vehicle monitoring modulation feature vector; Calculating the position difference between the first automobile monitoring modulation feature vector and the second automobile monitoring modulation feature vector to obtain an automobile monitoring shift information representation vector; Calculating an F-norm of a position mean vector between the first vehicle monitoring modulation feature vector and the second vehicle monitoring modulation feature vector as a shift compensation scaling factor; Linearly scaling the vehicle monitoring shift information representation vector by the shift compensation scaling factor to obtain a scaled vehicle monitoring shift information representation vector, and inputting the scaled vehicle monitoring shift information representation vector into a Sigmoid activation function to obtain a vehicle monitoring back-propagation shift compensation representation vector; The optimized vehicle monitoring feature enhancement vector is obtained by calculating the point-by-point multiplication of the vehicle monitoring back-propagation shift compensation representation vector and the vehicle monitoring feature enhancement vector.

8. The automobile fault monitoring and diagnosis system based on the Internet of Things according to claim 7 is characterized in that: The automobile fault monitoring parameter temporal feature encoder based on the hole convolution kernel is a convolutional neural network model using the hole convolution kernel, and the automobile monitoring feature enhancer based on the spatial attention mechanism is a convolutional neural network model using the spatial attention mechanism.

9. A vehicle fault monitoring and diagnosis method based on the Internet of Things, characterized in that: include: Obtaining the driving motor speed value, driving motor vibration frequency value, battery pack voltage value, battery pack current value, battery pack internal resistance value, battery pack temperature value, four sets of tire pressure values, brake pad temperature value, brake pad thickness value, and brake pad sound frequency value at multiple predetermined time points within a predetermined time period; Performing time-series coding on the driving motor speed values ​​and the driving motor vibration frequency values ​​at the plurality of predetermined time points to obtain a vehicle electric drive monitoring time-series characteristic matrix; Performing time-series coding on the battery pack voltage values, battery pack current values, battery pack internal resistance values, and battery pack temperature values ​​at the plurality of predetermined time points to obtain a vehicle battery monitoring time-series characteristic matrix; Performing time series coding on the four groups of tire pressure values ​​at the plurality of predetermined time points to obtain a time series characteristic matrix for automobile tire pressure monitoring; Performing time series coding on the brake pad temperature values, brake pad thickness values, and brake pad sound frequency values ​​at the plurality of predetermined time points to obtain a vehicle brake pad monitoring time series feature matrix; The automobile electric drive monitoring timing feature matrix, the automobile battery monitoring timing feature matrix, the automobile tire pressure monitoring timing feature matrix and the automobile brake pad monitoring timing feature matrix are integrated to obtain an automobile monitoring feature matrix; Based on the automobile monitoring feature matrix, an automobile fault monitoring result is obtained.

10. The automobile fault monitoring and diagnosis method based on the Internet of Things according to claim 9 is characterized in that: Based on the automobile monitoring feature matrix, the automobile fault monitoring result is obtained, including: Passing the vehicle monitoring feature matrix through a vehicle monitoring feature enhancer based on a spatial attention mechanism to obtain a vehicle monitoring feature enhancement matrix; Expanding the vehicle monitoring feature enhancement matrix into a vehicle monitoring feature enhancement vector; Performing a back-propagation driven feature offset adjustment on the vehicle monitoring feature enhancement vector to obtain an optimized vehicle monitoring feature enhancement vector; The optimized vehicle monitoring feature enhancement vector is passed through a classifier-based vehicle fault monitoring result generator to obtain a classification result, and the classification result is used to indicate whether the vehicle has a potential fault at the current time point.

Images