Vehicle fault diagnosis method and device based on multi-source data fusion and storage medium

Abstract

The invention provides a vehicle fault diagnosis method and device based on multi-source data fusion and a storage medium. The method comprises the following steps: collecting real-time state data and real-time alarm data of a target part, and obtaining external environment data and map navigation data; preprocessing the data, fusing the preprocessed data to obtain a multi-source data set target feature, inputting the target feature extracted from the multi-source data set into an adaptive neural fuzzy inference system, mapping the target feature to a plurality of fuzzy sets, and fuzzifying by using a member function; calculating the rule weight of each target feature to reflect the fuzzy intensity; and training an inference system by adopting a neural network learning algorithm, adjusting a member function and a rule weight, and converting fuzzy output into a specific numerical value or a fault level by utilizing an output member function in a defuzzification process so as to judge the health state of the part. According to the invention, high-interpretability fault diagnosis output is provided, the accuracy is improved, and fault diagnosis can be carried out in a wide vehicle operation environment.

Description

Technical Field

[0001] The present application relates to the field of new energy vehicle technology, and in particular to a vehicle fault diagnosis method, device and storage medium based on multi-source data fusion. Background Art

[0002] With the development of modern transportation technology, vehicle systems are becoming more and more complex. To ensure the safety and reliability of vehicles, fault diagnosis has become an indispensable part. Traditional fault diagnosis methods are usually based on a fixed model or expert experience, but with the increase in data volume and the complexity of vehicle systems, these methods may not be able to accurately detect and diagnose faults.

[0003] As a model integrating neural network and fuzzy reasoning technology, adaptive neuro-fuzzy inference system (ANFIS) has proved its effectiveness in many fields. However, its application in vehicle fault diagnosis is still an area to be explored, especially the method of combining multi-source data fusion for fault diagnosis.

[0004] The existing technology does not effectively collect and integrate multi-source data of the vehicle for vehicle fault diagnosis, and the traditional method based on fixed thresholds or model judgment leads to poor interpretability of the output of vehicle fault diagnosis results, low accuracy of fault diagnosis results, and inability to adapt to different types of fault diagnosis under actual vehicle operation conditions. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a vehicle fault diagnosis method, device and storage medium based on multi-source data fusion to solve the problems of poor interpretability of the output of vehicle fault diagnosis results, low accuracy of fault diagnosis results, and inability to adapt to different types of fault diagnosis under actual vehicle operation conditions in the prior art.

[0006] In a first aspect of an embodiment of the present application, a vehicle fault diagnosis method based on multi-source data fusion is provided, comprising: collecting real-time status data and real-time warning data of target components, collecting external environment data using sensors installed on the vehicle, and obtaining map navigation data of the vehicle; performing preprocessing operations on the real-time status data, real-time warning data, external environment data, and map navigation data of target components, fusing the preprocessed data to obtain a fused multi-source data set; performing feature extraction on the multi-source data set to obtain target features for vehicle fault detection, and inputting the target features into a predetermined adaptive neural fuzzy inference system, wherein the adaptive neural fuzzy inference system includes a method based on expert knowledge. The adaptive neural fuzzy inference system is used to map the target features into different fuzzy sets, and the input membership function is used to fuzzify the target features. For each fuzzy rule in the fuzzy set, the rule weight corresponding to each target feature is calculated, and the rule weight is used to characterize the fuzzy strength corresponding to the target feature. The adaptive neural fuzzy inference system is trained using a neural network learning algorithm and a training data set so as to adjust the member function and rule weight in the adaptive neural fuzzy inference system. In the defuzzification process, the output membership function is used to convert the fuzzy output into a specific value or fault level, and the health status of the target component is judged according to the output result of the adaptive neural fuzzy inference system.

[0007] According to a second aspect of an embodiment of the present application, a vehicle fault diagnosis device based on multi-source data fusion is provided, including: an acquisition module, configured to acquire real-time status data and real-time alarm data of target components, acquire external environment data using sensors installed on the vehicle, and obtain map navigation data of the vehicle; a preprocessing module, configured to perform preprocessing operations on the real-time status data, real-time alarm data, external environment data and map navigation data of target components, fuse the preprocessed data to obtain a fused multi-source data set; a feature extraction module, configured to extract features from the multi-source data set to obtain target features for vehicle fault detection, and input the target features into a predetermined adaptive neural-fuzzy inference system, wherein the adaptive neural-fuzzy inference system includes a method defined based on expert knowledge. A plurality of fuzzy rules; a fuzzy processing module configured to map target features into different fuzzy sets by using an adaptive neural-fuzzy inference system, and to perform fuzzification on the target features by using an input membership function; a calculation module configured to calculate the rule weight corresponding to each target feature for each fuzzy rule in the fuzzy set, and the rule weight is used to characterize the fuzzy strength corresponding to the target feature; a training module configured to train the adaptive neural-fuzzy inference system by using a neural network learning algorithm and a training data set, so as to adjust the member function and rule weight in the adaptive neural-fuzzy inference system; an output module configured to convert the fuzzy output into a specific numerical value or fault level by using the output membership function during the defuzzification process, and to judge the health status of the target component according to the output result of the adaptive neural-fuzzy inference system.

[0008] According to a third aspect of an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the steps of the above method are implemented when the processor executes the program.

[0009] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0010] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0011] The real-time status data and real-time alarm data of the target components are collected, and the external environment data are collected by using sensors installed on the vehicle, and the map navigation data of the vehicle is obtained; the real-time status data, real-time alarm data, external environment data and map navigation data of the target components are preprocessed, and the preprocessed data are fused to obtain a fused multi-source data set; feature extraction is performed on the multi-source data set to obtain target features for vehicle fault detection, and the target features are input into a predetermined adaptive neural fuzzy inference system, wherein the adaptive neural fuzzy inference system includes a plurality of fuzzy rules defined based on expert knowledge; the target features are mapped to different fuzzy sets by using the adaptive neural fuzzy inference system, and the target features are fuzzified by using the input membership function; for each fuzzy rule in the fuzzy set, the rule weight corresponding to each target feature is calculated, and the rule weight is used to characterize the fuzzy strength corresponding to the target feature; the adaptive neural fuzzy inference system is trained by using a neural network learning algorithm and a training data set, so as to adjust the member functions and rule weights in the adaptive neural fuzzy inference system; in the defuzzification process, the fuzzy output is converted into a specific value or fault level by using the output membership function, and the health status of the target component is judged according to the output result of the adaptive neural fuzzy inference system. The vehicle fault diagnosis result output of the present application is highly interpretable, which improves the accuracy of the fault diagnosis results and can cover more fault diagnosis under vehicle operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0013] Figure 1 It is a flow chart of a vehicle fault diagnosis method based on multi-source data fusion provided in an embodiment of the present application;

[0014] Figure 2 is a structural schematic diagram of a vehicle fault diagnosis device based on multi-source data fusion provided in an embodiment of the present application;

[0015] Figure 3 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0017] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or apparatus.

[0018] The vehicle fault diagnosis method and device based on multi-source data fusion provided by the technical solution of the present application are described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0019] Figure 1 It is a flow chart of a vehicle fault diagnosis method based on multi-source data fusion provided in an embodiment of the present application. Figure 1 The vehicle fault diagnosis method based on multi-source data fusion can be executed by a server.

[0020] like Figure 1 As shown, the vehicle fault diagnosis method based on multi-source data fusion may specifically include:

[0021] S101, collecting real-time status data and real-time alarm data of target components, collecting external environment data using sensors installed on the vehicle, and obtaining map navigation data of the vehicle;

[0022] S102, performing preprocessing operations on the real-time status data, real-time alarm data, external environment data, and map navigation data of the target component, and fusing the preprocessed data to obtain a fused multi-source data set;

[0023] S103, extracting features from the multi-source data sets to obtain target features for vehicle fault detection, and inputting the target features into a predetermined adaptive neural-fuzzy inference system, wherein the adaptive neural-fuzzy inference system includes a plurality of fuzzy rules defined based on expert knowledge;

[0024] S104, using an adaptive neuro-fuzzy inference system, mapping the target features into different fuzzy sets, and using an input membership function to perform fuzzification processing on the target features;

[0025] S105, for each fuzzy rule in the fuzzy set, calculating the rule weight corresponding to each target feature, the rule weight is used to characterize the fuzzy strength corresponding to the target feature;

[0026] S106, training the adaptive neural network fuzzy inference system using a neural network learning algorithm and a training data set, so as to adjust the member functions and rule weights in the adaptive neural network fuzzy inference system;

[0027] S107, in the defuzzification process, the fuzzy output is converted into a specific value or fault level using the output membership function, and the health status of the target component is determined according to the output result of the adaptive neural fuzzy inference system.

[0028] Adaptive Neuro-Fuzzy Inference System (ANFIS) is an intelligent system that combines fuzzy logic system and neural network. ANFIS can use the interpretation ability of fuzzy logic system and the learning ability of neural network to achieve adaptive learning and adjustment of fuzzy system.

[0029] The working process of the adaptive neuro-fuzzy inference system includes: First, ANFIS receives raw input data and converts these raw data into fuzzy values ​​or memberships through input membership functions. This process is called fuzzification. The fuzzified data is passed into a predefined set of fuzzy rules. These rules are evaluated based on the membership of the input data and generate an output value for each rule. The output of each fuzzy rule has a weight associated with it. These weights are usually determined based on the membership of the input data and the structure of the rules. The weighted rule outputs are summarized or accumulated to produce a total fuzzy output. Finally, ANFIS uses the output membership function to convert the fuzzy output into a specific value, a process called defuzzification. One of the characteristics of ANFIS is that it can learn and adjust. Based on the training data, the algorithms of the neural network part (such as back propagation) will adjust the system to optimize the parameters of the membership function and the rule weights to reduce the prediction error.

[0030] In some embodiments, real-time status data and real-time warning data of target components are collected, external environment data are collected using sensors installed on the vehicle, and map navigation data of the vehicle is obtained, including:

[0031] The status monitoring system installed on the vehicle is used to monitor the real-time status data generated by the target components in real time. When an abnormal state is detected or the parameters exceed the predetermined range, real-time alarm data is generated. The environmental sensors on the vehicle are used to collect the external environment data of the vehicle in real time, obtain the vehicle's map navigation data from the vehicle's navigation system, and obtain the weather data on the expected driving route from the predetermined application.

[0032] Specifically, the new energy vehicle (referred to as the vehicle) of the present application is equipped with an advanced status monitoring system, which is integrated into various key components of the vehicle, such as the engine, brake system, tires and batteries. These monitoring points can monitor the working status of these components in real time, such as the engine speed, brake system pressure, tire pressure and battery power, etc. When these data show abnormalities or any parameters exceed the preset safety range, the monitoring system will immediately generate and send real-time alarm data.

[0033] At the same time, the vehicle is also equipped with multiple environmental sensors, which are distributed in the front, rear, left, right and top of the vehicle. These sensors can monitor the external environmental conditions of the vehicle in real time, such as temperature, humidity, raindrop detection, road conditions, etc. These data are particularly critical for judging the working status of the vehicle in a specific environment.

[0034] In addition, the vehicle is equipped with a high-precision navigation system. This navigation system can not only provide current location information, but also provide real-time map navigation data such as upcoming road conditions, traffic flow, traffic accidents, etc. This data can help the vehicle prepare in advance and avoid potential risks.

[0035] In order to better assess the vehicle's operating conditions on the upcoming route, this application also integrates a weather forecast application, through which you can obtain real-time and predicted weather data such as temperature, precipitation, wind speed and direction on the vehicle's expected route.

[0036] In some embodiments, preprocessing operations are performed on the real-time status data, real-time alarm data, external environment data, and map navigation data of the target component, including:

[0037] The real-time status data, real-time alarm data, external environment data, map navigation data and weather data of the target components are used as raw data;

[0038] Perform data cleaning on the raw data to detect and delete missing values, duplicate values ​​or erroneous values ​​in the raw data; perform scaling processing on different types of raw data to unify raw data of different dimensions; use the autoencoder model to perform anomaly detection on the raw data to identify abnormal data.

[0039] Specifically, in the vehicle fault diagnosis system, in order to ensure the quality and validity of the data, all collected data, including the real-time status data of the target components, real-time alarm data, external environment data, map navigation data and weather data, will first be identified as raw data. These raw data are directly obtained from various sensors and systems and have not been processed in any way.

[0040] Furthermore, for the raw data, data cleaning must be performed first. Data cleaning is mainly to ensure the integrity, consistency and accuracy of the data. During the data cleaning process, the system automatically detects and deletes missing values, duplicate values ​​or error values ​​in the raw data. For example, if a sensor sends two identical data, then this duplicate data will be deleted; similarly, if a sensor sends data that is obviously beyond the normal range, such as a temperature sensor suddenly reporting a temperature of -200°C, this data will also be marked as an error value and deleted.

[0041] Furthermore, in order to ensure the consistency of data in subsequent processing, the system will scale different types of raw data. This is because data from different sensors or systems may have different scales or units. For example, engine speed may be in "rpm" and temperature may be in "℃". In order to unify these data, the system will use methods such as maximum-minimum scaling and Z-score normalization to convert these data to the same scale, such as [0,1].

[0042] In one example, to further ensure the reliability of the data, an autoencoder model is used to detect anomalies in the raw data. An autoencoder is a neural network model that can learn the characteristics of data and reconstruct the data. In this application, the autoencoder is trained to recognize normal data patterns. When the input data deviates from this pattern, the reconstruction error of the autoencoder increases, and the system will regard this data as abnormal data and mark it.

[0043] In some embodiments, the preprocessed data is fused to obtain a fused multi-source data set, including:

[0044] According to the fusion weights corresponding to the original data of different dimensions, the original data are weighted to obtain a weighted multi-source data set;

[0045] Alternatively, feature fusion is performed on raw data of different dimensions, and multiple raw data are mutually fused to obtain a fused multi-source data set;

[0046] Alternatively, the original data is classified, and according to the classification result, the classified original data is fused to obtain a fused multi-source data set.

[0047] Specifically, considering that the importance of raw data of different dimensions for fault diagnosis may be different, different weights can be assigned to each data dimension. For example, for engine fault diagnosis, engine temperature and oil pressure data may be more important than external temperature or map navigation data. Therefore, higher weights can be assigned to engine temperature and oil pressure data. By combining these weights through weighted averaging, each data dimension will be weighted and fused to obtain a weighted multi-source data set.

[0048] In another example, in addition to direct weighted fusion, the raw data of each dimension can also be fused. Feature fusion involves combining or converting different data features into new features, which can reflect the characteristics of the data from different angles. For example, the two features of engine temperature and speed can be fused into a feature of "engine efficiency". Through feature fusion, a new multi-source data set that integrates multiple raw data can be obtained.

[0049] In another example, considering that there may be multiple categories in the original data, such as sensor sources, data types (such as temperature, pressure, speed, etc.) or other factors. First, the data can be classified according to these categories, and then, according to the characteristics and importance of each category, a suitable fusion method (such as weighted fusion, feature fusion, etc.) is selected for each category of data. Finally, these fused category data are further integrated to obtain the final fused multi-source data set.

[0050] In some embodiments, an adaptive neural fuzzy inference system is used to map target features into different fuzzy sets, and the target features are fuzzified using input membership functions, including:

[0051] Based on the target features, corresponding fuzzy variables are defined, and a fuzzy set is defined for each fuzzy variable. A membership function is selected to describe each fuzzy set so that each target feature obtains a membership value on the corresponding fuzzy set.

[0052] For each target feature, the membership value on each fuzzy set is calculated using the selected input membership function so that each target feature is converted into a fuzzy value, and the calculated fuzzy value is stored in the fuzzy matrix for fuzzy reasoning and defuzzification operations.

[0053] Specifically, for each target feature in vehicle fault diagnosis, such as engine temperature, speed, or oil pressure, the corresponding fuzzy variables are first defined. For example, engine temperature can be defined as three fuzzy variables: "low", "medium", and "high". Subsequently, a fuzzy set is defined for each fuzzy variable, such as "low" temperature can correspond to a temperature range (e.g., 0-50°C), "medium" temperature corresponds to another range (e.g., 50-80°C), and so on.

[0054] Furthermore, according to the characteristics of each fuzzy set, a suitable membership function is selected to describe it. Commonly used membership functions include triangular, trapezoidal or Gaussian functions. For example, for the "low" temperature fuzzy set, a triangular membership function that increases in the range of 0-50°C may be selected; while for the "medium" temperature, a Gaussian function centered at 65°C may be selected.

[0055] Furthermore, when real-time target feature data is generated during vehicle operation, such as the engine temperature of 55°C, the membership value of each fuzzy set can be calculated using the previously selected input membership function. For example, under the triangular membership function of the "low" temperature fuzzy set, the membership value of 55°C may be 0.5; while under the Gaussian function of the "medium" temperature, its membership value may be 0.7.

[0056] Furthermore, the calculated fuzzy values ​​of each target feature are stored in a fuzzy matrix. For example, the rows of the fuzzy matrix represent different target features, such as engine temperature, speed, etc., while the columns represent fuzzy variables such as "low", "medium" and "high". The corresponding matrix elements are the membership values ​​of the target feature under the corresponding fuzzy variables.

[0057] Through the method of the above embodiment, each target feature is converted into a fuzzy value and integrated into a fuzzy matrix. This fuzzy matrix provides a basis for subsequent fuzzy reasoning and defuzzification operations, thereby helping to determine the health status and possible faults of various components of the vehicle.

[0058] In some embodiments, for each fuzzy rule in the fuzzy set, calculating the rule weight corresponding to each target feature includes:

[0059] For each fuzzy rule, the fuzzy value of the target feature is used to perform fuzzy logic operations, and the rule weight is determined according to the activation degree of each fuzzy rule and the pre-defined evaluation rules. The rule weight of each fuzzy rule is normalized to obtain the rule weight of the fuzzy rule corresponding to each target feature.

[0060] Specifically, first, for each target feature's fuzzy value, a fuzzy logic operation is performed with the corresponding fuzzy rule. For example, assuming there is a fuzzy rule that "if the engine temperature is medium and the speed is high, a fault may occur", then the embodiment of the present application needs to obtain the membership value of the engine temperature feature on the "medium" fuzzy set and the membership value of the speed on the "high" fuzzy set, and perform a logical "and" operation.

[0061] Furthermore, the result of the above fuzzy logic operation is the activation degree of the fuzzy rule, which represents the applicability of this rule in the current situation. For example, if the obtained engine temperature membership value is 0.7 and the speed membership value is 0.8, then the activation degree of the above fuzzy rule is the minimum value of 0.7 and 0.8, that is, 0.7.

[0062] Furthermore, a weight is determined for each fuzzy rule based on predefined evaluation rules. The evaluation rules may be based on historical data of the vehicle, expert knowledge, or other relevant information. For example, based on past experience, the probability of failure is greater when the engine temperature and speed are high, so the corresponding fuzzy rule may be assigned a higher weight.

[0063] Furthermore, to ensure that the sum of the weights of all fuzzy rules is 1, the weight of each fuzzy rule is normalized. For example, if there are three fuzzy rules, their original weights are 0.5, 0.3, and 0.4, respectively, and the normalized weights are 0.5 / 1.2 = 0.4167, 0.3 / 1.2 = 0.25, and 0.4 / 1.2 = 0.3333. Finally, the normalized weights of all fuzzy rules of each target feature are comprehensively considered to determine the final weight of the feature, thereby reflecting the importance of the feature in fault diagnosis.

[0064] In some embodiments, during the defuzzification process, the fuzzy output is converted into a specific value or fault level using the output membership function, and the health status of the target component is determined according to the output result of the adaptive neural fuzzy inference system, including:

[0065] For each activated fuzzy rule, the fuzzy output value of the fuzzy rule is calculated based on the conclusion part of the fuzzy rule and the corresponding rule weight;

[0066] Based on the fuzzy output value of each fuzzy rule and the corresponding rule weight, a weighted average is performed to obtain the fuzzy output;

[0067] Based on the output membership function, the fuzzy output is mapped to a specific value or fault level using a defuzzification method;

[0068] Based on the specific value or fault level, the health status of the target component is judged using the preset fault judgment threshold.

[0069] Specifically, for each activated fuzzy rule, the fuzzy output value is calculated based on the conclusion part of the fuzzy rule and its corresponding rule weight. For example, a fuzzy rule may be "If the engine temperature is high and the speed is high, then the risk of failure is large", and the corresponding conclusion part "large" may correspond to a fuzzy output value of 0.8. If the weight of the rule is 0.6, the weighted fuzzy output value is 0.8x0.6=0.48.

[0070] Furthermore, the fuzzy output values ​​of all activated fuzzy rules and their corresponding rule weights are weighted averaged to obtain the total fuzzy output. For example, if there are three activated fuzzy rules, and their weighted fuzzy output values ​​are 0.48, 0.3, and 0.6, respectively, then the total fuzzy output is (0.48+0.3+0.6) / 3=0.46.

[0071] Furthermore, according to the predefined output membership function, a defuzzification method (such as the center of gravity method) is applied to map the fuzzy output value 0.46 to a specific numerical value or fault level. For example, the numerical value can be a value between 0 and 1, where 1 represents the highest risk of failure. Finally, according to the specific numerical value or fault level obtained by mapping, the health status of the target component is evaluated in combination with the preset fault judgment threshold. For example, the following judgment criteria can be set:

[0072] If the value is between 0 and 0.3, it is judged as “healthy”;

[0073] If the value is between 0.3 and 0.7, it is judged as "caution";

[0074] If the value is between 0.7 and 1, it is considered "high risk".

[0075] According to the value 0.46 obtained by the above defuzzification, the health status of the target component is judged to be "caution".

[0076] Through the method of the above embodiment, the vehicle can evaluate the health status of its components in real time, and promptly issue warnings or maintenance for possible problems, thereby ensuring driving safety and increasing the service life of the vehicle.

[0077] According to the technical solution provided by the embodiment of the present application, the present application can obtain more comprehensive vehicle operation information by collecting and fusing multi-source data of the vehicle, such as the real-time status of the target parts, real-time alarms, external environment, map navigation and weather data. Using these fused data sets, fault diagnosis can be performed more accurately. The adaptive neural fuzzy reasoning system is adopted, which combines the adaptability of the neural network and the processing fuzziness of fuzzy reasoning, so that the system can also perform effective fault judgment for uncertain or fuzzy data. With the accumulation of training data sets, the judgment ability of the system will gradually increase and adapt to different working environments and conditions. For each target feature in the multi-source data set, the system can automatically calculate the corresponding rule weight according to the matching degree of each feature with the fuzzy rule. In this way, even in the face of a large amount of input data, the system can quickly determine the health status of the target parts and realize efficient fault diagnosis. In the defuzzification process, the system uses the output membership function to convert the fuzzy output into a specific value or fault level. In this way, maintenance personnel or other users can intuitively understand the output results of the system and make judgments or take corresponding measures accordingly. This solution takes into full account all possible data anomalies, and ensures that the data input into the adaptive neuro-fuzzy inference system is accurate and reliable through preprocessing operations, data fusion and feature extraction. At the same time, the system is trained with training data sets and can continuously provide robust and reliable fault diagnosis services under various complex working conditions.

[0078] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0079] Figure 2 Schematic diagram of the structure of a vehicle fault diagnosis device based on multi-source data fusion provided in an embodiment of the present application. Figure 2 As shown, the vehicle fault diagnosis device based on multi-source data fusion includes:

[0080] The acquisition module 201 is configured to acquire real-time status data and real-time warning data of target components, acquire external environment data using sensors installed on the vehicle, and obtain map navigation data of the vehicle;

[0081] The preprocessing module 202 is configured to perform preprocessing operations on the real-time status data, real-time alarm data, external environment data and map navigation data of the target component, and fuse the preprocessed data to obtain a fused multi-source data set;

[0082] The feature extraction module 203 is configured to extract features from the multi-source data sets to obtain target features for vehicle fault detection, and input the target features into a predetermined adaptive neural-fuzzy inference system, wherein the adaptive neural-fuzzy inference system includes a plurality of fuzzy rules defined based on expert knowledge;

[0083] A fuzzy processing module 204 is configured to map target features into different fuzzy sets using an adaptive neuro-fuzzy inference system and to perform fuzzification on the target features using an input membership function;

[0084] The calculation module 205 is configured to calculate the rule weight corresponding to each target feature for each fuzzy rule in the fuzzy set, where the rule weight is used to characterize the fuzzy strength corresponding to the target feature;

[0085] A training module 206 is configured to train the adaptive neuro-fuzzy inference system using a neural network learning algorithm and a training data set so as to adjust the member functions and rule weights in the adaptive neuro-fuzzy inference system;

[0086] The output module 207 is configured to convert the fuzzy output into a specific value or fault level using the output membership function during the defuzzification process, and determine the health status of the target component according to the output result of the adaptive neural-fuzzy inference system.

[0087] In some embodiments, Figure 2 The acquisition module 201 utilizes the status monitoring system installed on the vehicle to monitor the real-time status data generated by the target components in real time. When an abnormal state is detected or a parameter exceeds a predetermined range, real-time alarm data is generated. The environmental sensors on the vehicle are used to collect the external environment data of the vehicle in real time, obtain the vehicle's map navigation data from the vehicle's navigation system, and obtain the weather data on the expected driving route from a predetermined application.

[0088] In some embodiments, Figure 2 The preprocessing module 202 takes the real-time status data, real-time alarm data, external environment data, map navigation data and weather data of the target components as raw data; performs data cleaning on the raw data to detect and delete missing values, duplicate values ​​or error values ​​in the raw data; performs scaling processing on different types of raw data to unify raw data of different dimensions; and uses an autoencoder model to perform anomaly detection on the raw data to identify abnormal data.

[0089] In some embodiments, Figure 2The preprocessing module 202 weights the original data according to the fusion weights corresponding to the original data of different dimensions to obtain a weighted multi-source data set; or, performs feature fusion on the original data of different dimensions and fuses multiple original data with each other to obtain a fused multi-source data set; or, classifies the original data and, based on the classification results, performs category fusion on the classified original data to obtain a fused multi-source data set.

[0090] In some embodiments, Figure 2 The fuzzy processing module 204 defines corresponding fuzzy variables based on the target features, defines a fuzzy set for each fuzzy variable, selects a membership function to describe each fuzzy set, so that each target feature obtains a membership value on the corresponding fuzzy set; for each target feature, uses the selected input membership function to calculate its membership value on each fuzzy set, so as to convert each target feature into a fuzzy value, and stores the calculated fuzzy value in a fuzzy matrix for fuzzy reasoning and defuzzification operations.

[0091] In some embodiments, Figure 2 The calculation module 205 performs fuzzy logic operations on each fuzzy rule using the fuzzy value of the target feature, determines the rule weight according to the activation degree of each fuzzy rule and the predefined evaluation rules, normalizes the rule weight of each fuzzy rule, and obtains the rule weight of the fuzzy rule corresponding to each target feature.

[0092] In some embodiments, Figure 2 The output module 207 calculates the fuzzy output value of each activated fuzzy rule according to the conclusion part of the fuzzy rule and the corresponding rule weight; performs weighted average based on the fuzzy output value of each fuzzy rule and the corresponding rule weight to obtain the fuzzy output; based on the output membership function, uses the defuzzification method to map the fuzzy output to a specific value or fault level; and uses a preset fault judgment threshold to judge the health status of the target component according to the specific value or fault level.

[0093] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0094] Figure 3 Schematic diagram of the structure of the electronic device 3 provided in the embodiment of the present application. Figure 3As shown, the electronic device 3 of this embodiment includes: a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and executable on the processor 301. When the processor 301 executes the computer program 303, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 301 executes the computer program 303, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0095] Exemplarily, the computer program 303 may be divided into one or more modules / units, which are stored in the memory 302 and executed by the processor 301 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 303 in the electronic device 3.

[0096] The electronic device 3 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that Figure 3 It is only an example of the electronic device 3 and does not constitute a limitation of the electronic device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0097] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0098] The memory 302 may be an internal storage unit of the electronic device 3, for example, a hard disk or memory of the electronic device 3. The memory 302 may also be an external storage device of the electronic device 3, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 3. Further, the memory 302 may also include both an internal storage unit and an external storage device of the electronic device 3. The memory 302 is used to store computer programs and other programs and data required by the electronic device. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0099] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0100] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0101] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0102] In the embodiments provided in the present application, it should be understood that the disclosed devices / computer equipment and methods can be implemented in other ways. For example, the device / computer equipment embodiments described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. Multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0103] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0105] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, which may be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0106] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A vehicle fault diagnosis method based on multi-source data fusion, characterized in that: include: Collecting real-time status data and real-time alarm data of target components, collecting external environment data using sensors installed on the vehicle, and obtaining map navigation data of the vehicle; Performing preprocessing operations on the real-time status data of the target component, the real-time alarm data, the external environment data, and the map navigation data, and fusing the preprocessed data to obtain a fused multi-source data set; Performing feature extraction on the multi-source data set to obtain target features for vehicle fault detection, and inputting the target features into a predetermined adaptive neural-fuzzy inference system, wherein the adaptive neural-fuzzy inference system includes a plurality of fuzzy rules defined based on expert knowledge; Mapping the target features into different fuzzy sets using the adaptive neuro-fuzzy inference system, and fuzzifying the target features using input membership functions; For each fuzzy rule in the fuzzy set, calculating a rule weight corresponding to each target feature, wherein the rule weight is used to characterize the fuzzy strength corresponding to the target feature; Training the adaptive neuro-fuzzy inference system using a neural network learning algorithm and a training data set so as to adjust the member functions and rule weights in the adaptive neuro-fuzzy inference system; In the defuzzification process, the fuzzy output is converted into a specific value or fault level using the output membership function, and the health status of the target component is determined based on the output result of the adaptive neuro-fuzzy inference system.

2. The method according to claim 1, characterized in that The real-time status data and real-time alarm data of the target components are collected, external environment data are collected using sensors installed on the vehicle, and map navigation data of the vehicle is obtained, including: The status monitoring system installed on the vehicle is used to monitor the real-time status data generated by the target components in real time. When an abnormal state is detected or a parameter exceeds a predetermined range, real-time alarm data is generated. The environmental sensors on the vehicle are used to collect the external environment data of the vehicle in real time, the vehicle's map navigation data is obtained from the vehicle's navigation system, and the weather data on the expected driving route is obtained from a predetermined application.

3. The method according to claim 2, characterized in that The preprocessing operation on the real-time status data of the target component, the real-time alarm data, the external environment data and the map navigation data includes: The real-time status data of the target component, the real-time alarm data, the external environment data, the map navigation data and the weather data are used as raw data; The raw data is cleaned to detect and delete missing values, duplicate values ​​or erroneous values ​​in the raw data; different types of raw data are scaled to unify raw data of different dimensions; anomaly detection is performed on the raw data using an autoencoder model to identify abnormal data.

4. The method according to claim 3, characterized in that The preprocessed data is fused to obtain a fused multi-source data set, including: The original data are weighted according to the fusion weights corresponding to the original data of different dimensions to obtain a weighted multi-source data set; Alternatively, the original data of different dimensions are subjected to feature fusion, and a plurality of the original data are mutually fused to obtain a fused multi-source data set; Alternatively, the original data is classified, and according to the classification result, the classified original data is fused into categories to obtain a fused multi-source data set.

5. The method according to claim 1, characterized in that The method of using the adaptive neural fuzzy inference system to map the target features into different fuzzy sets and using an input membership function to perform fuzzification processing on the target features includes: Based on the target feature, corresponding fuzzy variables are defined, and a fuzzy set is defined for each of the fuzzy variables, and a membership function is selected to describe each of the fuzzy sets, so that each of the target features obtains a membership value on the corresponding fuzzy set; For each of the target features, the membership value on each fuzzy set is calculated using the selected input membership function so as to convert each target feature into a fuzzy value, and the calculated fuzzy value is stored in a fuzzy matrix for fuzzy reasoning and defuzzification operations.

6. The method according to claim 1, characterized in that For each fuzzy rule in the fuzzy set, calculating the rule weight corresponding to each target feature includes: For each of the fuzzy rules, fuzzy logic operations are performed using the fuzzy value of the target feature, and the rule weight is determined according to the activation degree of each fuzzy rule and a predefined evaluation rule. The rule weight of each fuzzy rule is normalized to obtain the rule weight of the fuzzy rule corresponding to each of the target features.

7. The method according to claim 1, characterized in that In the defuzzification process, the fuzzy output is converted into a specific value or fault level by using the output membership function, and the health status of the target component is judged according to the output result of the adaptive neural fuzzy inference system, including: For each activated fuzzy rule, a fuzzy output value of the fuzzy rule is calculated according to the conclusion part of the fuzzy rule and the corresponding rule weight; A fuzzy output is obtained by performing weighted averaging based on the fuzzy output value of each fuzzy rule and the corresponding rule weight; Based on the output membership function, mapping the fuzzy output to a specific value or fault level using a defuzzification method; According to the specific value or fault level, a preset fault judgment threshold is used to judge the health status of the target component.

8. A vehicle fault diagnosis device based on multi-source data fusion, characterized in that: include: A collection module is configured to collect real-time status data and real-time warning data of target components, collect external environment data using sensors installed on the vehicle, and obtain map navigation data of the vehicle; A preprocessing module is configured to perform preprocessing operations on the real-time status data of the target component, the real-time alarm data, the external environment data, and the map navigation data, and fuse the preprocessed data to obtain a fused multi-source data set; A feature extraction module is configured to extract features from the multi-source data set to obtain target features for vehicle fault detection, and input the target features into a predetermined adaptive neural-fuzzy inference system, wherein the adaptive neural-fuzzy inference system includes a plurality of fuzzy rules defined based on expert knowledge; a fuzzy processing module configured to map the target features into different fuzzy sets using the adaptive neuro-fuzzy inference system and to perform fuzzification processing on the target features using an input membership function; A calculation module is configured to calculate a rule weight corresponding to each of the target features for each fuzzy rule in the fuzzy set, wherein the rule weight is used to characterize the fuzzy strength corresponding to the target feature; A training module, configured to train the adaptive neural-fuzzy inference system using a neural network learning algorithm and a training data set, so as to adjust the member functions and rule weights in the adaptive neural-fuzzy inference system; The output module is configured to convert the fuzzy output into a specific value or fault level using the output membership function during the defuzzification process, and determine the health status of the target component according to the output result of the adaptive neural-fuzzy inference system.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images