CN114839960A - Method and system for detecting vehicle fault based on artificial intelligence algorithm - Google Patents
Method and system for detecting vehicle fault based on artificial intelligence algorithm Download PDFInfo
- Publication number
- CN114839960A CN114839960A CN202210677797.3A CN202210677797A CN114839960A CN 114839960 A CN114839960 A CN 114839960A CN 202210677797 A CN202210677797 A CN 202210677797A CN 114839960 A CN114839960 A CN 114839960A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- neural network
- accessory
- fault
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0262—Confirmation of fault detection, e.g. extra checks to confirm that a failure has indeed occurred
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
- G01M17/02—Tyres
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/34—Testing dynamo-electric machines
- G01R31/343—Testing dynamo-electric machines in operation
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention belongs to the technical field of vehicle fault detection, and particularly provides a vehicle fault detection method and system based on an artificial intelligence algorithm, wherein fault information of each accessory of a vehicle is analyzed by acquiring VCU data of a vehicle controller of the vehicle; collecting vehicle running sound data in the running process of a vehicle, inputting the vehicle running sound data into a trained neural network model for training and analysis, and outputting a classification report by the model to obtain fault prediction information of each accessory of the vehicle; comparing the fault information of each accessory of the vehicle with the corresponding fault prediction information of the accessory, and extracting the fault prediction information of each accessory; and analyzing the vehicle operation sound data by using the optimized qualified neural network model, outputting a result by using the model to obtain the vehicle health degree, and determining whether maintenance is needed. Through the sound monitoring of vehicle operation, the probability of vehicle emergence is accurately forecasted, the forecast accuracy of vehicle emergence is greatly improved, the vehicle safety is improved, and the commercial operation income is improved.
Description
Technical Field
The invention relates to the technical field of vehicle fault detection, in particular to a method and a system for detecting vehicle faults based on an artificial intelligence algorithm.
Background
With the development of automobile technology, systems on automobiles become more and more complex and bulky, so that the possibility of generating faults is higher and higher, and the difficulty of troubleshooting and detecting the faults is higher and higher. Especially in the data explosion era, a vehicle can generate mass data at every moment, proper data is screened out from the data by manpower, whether faults occur or not and possible reasons are almost impossible to judge, not only can a large amount of time be wasted, but also the accuracy is not high, and some tiny faults are likely to be missed. Moreover, when a vehicle fault is manually detected, the fault of the vehicle is often checked only when the fault occurs, the frequency of the fault occurrence is very low, a lot of time is needed for the fault to reappear by manpower, and detailed data and conditions of the fault occurrence are difficult to record.
At present, the computer technology is also developed very mature, a large amount of manpower and material resources can be saved by means of the operation speed of a computer and proper programming, the speed and the accuracy of program identification faults can be greatly improved through a large amount of verification and accumulation, and the faults caused by human can be avoided. More importantly, the computer can collect and detect faults in real time and can detect faults of a plurality of vehicles at the same time, which is far beyond the reach of manpower.
Therefore, how to intelligently identify the sound of the vehicle in the driving process by means of a computer, find the vehicle fault, analyze the vehicle health degree and predict the vehicle fault in advance is an urgent problem to be solved.
Disclosure of Invention
The invention aims at the technical problem of vehicle fault prediction in the prior art.
The invention provides a vehicle fault detection method based on an artificial intelligence algorithm, which comprises the following steps:
s1, acquiring VCU data of the vehicle controller of the vehicle to analyze fault information of each accessory of the vehicle;
s2, collecting vehicle running sound data in the running process of the vehicle, inputting the vehicle running sound data into a trained neural network model for training and analysis, and outputting a classification report by the model to obtain fault prediction information of each accessory of the vehicle;
s3, comparing the fault information of each accessory of the vehicle with the corresponding fault prediction information of the accessory, extracting the fault prediction information of each accessory, and feeding the result back to the neural network model for optimization;
and S4, analyzing the vehicle running sound data by using the optimized qualified neural network model, outputting the result by using the model to obtain the vehicle health degree, and determining whether maintenance is needed.
Preferably, the vehicle operation sound data includes a plurality of category data of battery voltage, battery uniformity, tire pressure, motor rotation speed, running speed, and location information.
Preferably, the S2 specifically includes:
the neural network model comprises a plurality of sub neural network models, each category of data in the vehicle running sound data is respectively used as input data of the sub neural network models, each sub neural network model outputs a corresponding fault score based on the corresponding input data, and a final overall automobile health score is obtained based on the output result of each sub neural network model.
Preferably, the obtaining of the final overall automobile health score based on the output result of each sub-neural network model specifically includes:
and for each sub-neural network model, acquiring a corresponding score weight based on the input behavior data type, and performing algorithm weighting on the output result of each sub-neural network model based on the score weight of each sub-neural network model so as to obtain the final output result of the automobile health degree score.
Preferably, the neural network model is a convolutional neural network CNN, a recurrent neural network RNN, or a long-term memory network LSTM.
Preferably, the S2 specifically includes:
s21, preprocessing, namely cutting off the mute of the head end and the tail end of the vehicle running sound data to reduce the interference on the subsequent steps, then framing the sound, and cutting the sound into data of one frame;
s22, extracting features, and converting each frame of waveform into a multi-dimensional vector containing sound information by applying a cepstrum coefficient algorithm;
s23, training by using an RNN model;
and S24, extracting fault prediction information of each accessory, and classifying corresponding sound data.
Preferably, the S2 specifically includes:
firstly, loading an audio file, namely the collected vehicle running sound, by using a librosa tool load () method, and drawing a waveform diagram by using a waveplot () method;
secondly, firstly splitting a data set of all vehicle running sounds into a 90% training set and a 10% testing set; then, splitting 90% of the training set into 80% of the training set and 20% of the verification set;
thirdly, classifying the target by using an ANN algorithm to construct a neural network classification model;
fourthly, evaluating the model;
and fifthly, outputting an ANN classification model classification report to predict the vehicle health degree.
The invention provides a vehicle fault detection system based on an artificial intelligence algorithm, which is used for realizing a vehicle fault detection method based on the artificial intelligence algorithm, and specifically comprises the following steps:
the acquisition module is used for acquiring vehicle control unit VCU data of a vehicle and vehicle running sound data in the vehicle running process and analyzing fault information of each accessory of the vehicle;
the neural network module is used for inputting the vehicle operation sound data into a trained neural network model for training and analysis, and the model outputs a classification report to obtain fault prediction information of each accessory of the vehicle;
the structure output module is used for comparing the fault information of each accessory of the vehicle with the corresponding fault prediction information of the accessories, extracting the fault prediction information of each accessory and feeding the result back to the neural network model for optimization; and finally, analyzing the vehicle operation sound data by using the optimized qualified neural network model, outputting a result by using the model to obtain the vehicle health degree, and determining whether maintenance is needed.
The invention provides electronic equipment which comprises a memory and a processor, wherein the processor is used for realizing the steps of a vehicle fault detection method based on an artificial intelligence algorithm when executing a computer management program stored in the memory.
The present invention provides a computer readable storage medium having stored thereon a computer management-like program, which when executed by a processor, performs the steps of a method for vehicle fault detection based on an artificial intelligence algorithm.
Has the advantages that: the invention provides a vehicle fault detection method and system based on an artificial intelligence algorithm, wherein the method comprises the following steps: acquiring VCU data of a vehicle controller of a vehicle to analyze fault information of each accessory of the vehicle; collecting vehicle running sound data in the running process of a vehicle, inputting the vehicle running sound data into a trained neural network model for training and analysis, and outputting a classification report by the model to obtain fault prediction information of each accessory of the vehicle; comparing the fault information of each accessory of the vehicle with corresponding fault prediction information of the accessories, extracting the fault prediction information of each accessory, and feeding the result back to a neural network model for optimization; and analyzing the vehicle operation sound data by using the optimized qualified neural network model, outputting a result by using the model to obtain the vehicle health degree, and determining whether maintenance is needed. The collected vehicle running sound data are processed through the neural network model to obtain the health grade of the vehicle, so that safety management and danger prediction are performed, on the other hand, the probability of vehicle danger can be accurately predicted through monitoring of the real-time state of the vehicle, the prediction accuracy of the vehicle danger is greatly improved, the safety of the vehicle is improved, and the commercial operation income is improved.
Drawings
FIG. 1 is a flow chart of a method for vehicle fault detection based on an artificial intelligence algorithm according to the present invention;
fig. 2 is a schematic diagram of a hardware structure of a possible electronic device provided in the present invention;
FIG. 3 is a schematic diagram of a hardware structure of a possible computer-readable storage medium provided by the present invention;
fig. 4 is a waveform diagram of the collected vehicle running sound according to the present invention, which is drawn by the waveplot () method.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Fig. 1 is a method for detecting vehicle faults based on an artificial intelligence algorithm, which is provided by the invention, and comprises the following steps: acquiring VCU data of a vehicle controller of a vehicle to analyze fault information of each accessory of the vehicle; collecting vehicle running sound data in the running process of a vehicle, inputting the vehicle running sound data into a trained neural network model for training and analysis, and outputting a classification report by the model to obtain fault prediction information of each accessory of the vehicle; comparing the fault information of each accessory of the vehicle with corresponding fault prediction information of the accessories, extracting the fault prediction information of each accessory, and feeding the result back to a neural network model for optimization; and analyzing the vehicle operation sound data by using the optimized qualified neural network model, outputting a result by using the model to obtain the vehicle health degree, and determining whether maintenance is needed. The collected vehicle running sound data are processed through the neural network model to obtain the health grade of the vehicle, so that safety management and danger prediction are performed, on the other hand, the probability of vehicle danger can be accurately predicted through monitoring of the real-time state of the vehicle, the prediction accuracy of the vehicle danger is greatly improved, the safety of the vehicle is improved, and the commercial operation income is improved.
When some parts have some problems in the operation process of each part of the vehicle, the operation mode of the parts can be affected, and the generated sound has some abnormal characteristics. The scheme of the embodiment can grasp and identify the abnormal conditions through learning data. The whole process is realized by data acquisition in the early stage, data analysis model construction in the middle stage, machine learning, data sampling, data matching and result feedback in the later stage.
The vehicle operation sound data includes a plurality of category data of battery voltage, battery consistency, tire pressure, motor rotation speed, running speed and position information. And the fault information corresponding to the various types of data can be analyzed from the VCU data of the whole vehicle controller.
In the preferable scheme, a voice analysis method is realized by using a CNN convolutional neural network, and the vehicle running sound generated in the running process of the vehicle is used. The method comprises the following specific steps:
(1) pretreatment: the silence of the head and the tail ends is cut off, the interference to the subsequent steps is reduced, then the sound is divided into frames, and the sound is cut into data of one frame;
(2) feature extraction: the applied algorithm is a cepstrum coefficient, namely, the cepstrum coefficient algorithm is used for changing each frame waveform into a multi-dimensional vector containing sound information;
(3) RNN model training: with the features, i.e., the multi-dimensional vectors, modeling and training can be completed using mainstream tools such as TensorFlow.
(4) And (3) verifying the model: the corresponding sound data is classified.
In the preferred scheme, voice in the running process of the vehicle is collected through a recording device such as a microphone and converted into a time spectrum, and the time spectrum is guided into a neural network for fault recognition.
Preferably, the neural network model comprises a plurality of sub-neural network models, wherein battery voltage, battery consistency, tire pressure, motor rotating speed, driving speed and position information, a motor, an electric controller, an engine, a gearbox and the like are respectively used as input data of the sub-neural network models, each sub-neural network model outputs a corresponding fault score based on the corresponding input data, and a final automobile health score is obtained based on an output result of each sub-neural network model. Specifically, for each sub-neural network model, a corresponding score weight is obtained based on the input behavior data type, and the output result of each sub-neural network model is subjected to algorithm weighting based on the score weight of each sub-neural network model, so that the final output result is obtained.
Wherein, the neural network model is a convolutional neural network CNN, a recurrent neural network RNN or a long-term memory network LSTM.
In a specific implementation scenario, step S2 specifically includes:
1. waveform visualization
The audio file, i.e., the collected vehicle running sound, is loaded by the librosa tool load () method, and the waveform diagram is drawn by the waveplot () method, as shown in fig. 4. And the mapping can be further drawn by specshow () and colorbar () methods.
2. Extracting audio features and preparing modeling data
And splitting the data set into a training set, a verification set and a test set. Firstly, splitting all data sets into a 90% training set and a 10% testing set; then, the 90% training set is further split into 80% training set and 20% validation set.
3. Constructing a neural network classification model: the ANN algorithm is mainly used for object classification.
4. And (3) carrying out model evaluation: the evaluation indexes and results are similar, and the evaluation indexes mainly comprise accuracy, F1 score and the like.
5. And (4) classification report: an ANN classification model classification report may be output, and outputting F1 scores for various classification types and the accuracy of the entire model may be done.
6. And (5) outputting the model and predicting.
Deep learning, the hottest research of artificial intelligence, is being widely used for recognizing voice, images and texts and achieves remarkable effect; speech recognition, as the main interface of future man-machine interfaces, directly affects the user experience of intelligent systems. According to the technical scheme, the two technologies are organically combined, on one hand, a large amount of training data collected by the voice recognition system are beneficial to training a deep network with stronger robustness and generalization capability, on the other hand, the deep network with stronger robustness such as a neural network algorithm is better, the recognition accuracy of the voice recognition system can be effectively improved, and the influence of noise on the voice recognition system is reduced.
Fig. 2 is a schematic diagram of an embodiment of an electronic device according to an embodiment of the invention. As shown in fig. 2, an embodiment of the present invention provides an electronic device, which includes a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor 1320, where the processor 1320 executes the computer program 1311 to implement the following steps: s1, acquiring VCU data of the vehicle controller of the vehicle to analyze fault information of each accessory of the vehicle;
s2, collecting vehicle running sound data in the running process of the vehicle, inputting the vehicle running sound data into a trained neural network model for training and analysis, and outputting a classification report by the model to obtain fault prediction information of each accessory of the vehicle;
s3, comparing the fault information of each accessory of the vehicle with the corresponding fault prediction information of the accessory, extracting the fault prediction information of each accessory, and feeding the result back to the neural network model for optimization;
and S4, analyzing the vehicle running sound data by using the optimized qualified neural network model, outputting the result by using the model to obtain the vehicle health degree, and determining whether maintenance is needed.
Fig. 3 is a schematic diagram of an embodiment of a computer-readable storage medium according to the present invention. As shown in fig. 3, the present embodiment provides a computer-readable storage medium 1400, on which a computer program 1411 is stored, which computer program 1411, when executed by a processor, implements the steps of: s1, acquiring VCU data of the vehicle controller of the vehicle to analyze fault information of each accessory of the vehicle;
s2, collecting vehicle running sound data in the running process of the vehicle, inputting the vehicle running sound data into a trained neural network model for training and analysis, and outputting a classification report by the model to obtain fault prediction information of each accessory of the vehicle;
s3, comparing the fault information of each accessory of the vehicle with the corresponding fault prediction information of the accessory, extracting the fault prediction information of each accessory, and feeding the result back to the neural network model for optimization;
and S4, analyzing the vehicle running sound data by using the optimized qualified neural network model, outputting the result by using the model to obtain the vehicle health degree, and determining whether maintenance is needed.
It should be noted that, in the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to relevant descriptions of other embodiments for parts that are not described in detail in a certain embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A vehicle fault detection method based on an artificial intelligence algorithm is characterized by comprising the following steps:
s1, acquiring VCU data of the vehicle controller of the vehicle to analyze fault information of each accessory of the vehicle;
s2, collecting vehicle running sound data in the running process of the vehicle, inputting the vehicle running sound data into a trained neural network model for training and analysis, and outputting a classification report by the model to obtain fault prediction information of each accessory of the vehicle;
s3, comparing the fault information of each accessory of the vehicle with the corresponding fault prediction information of the accessory, extracting the fault prediction information of each accessory, and feeding the result back to the neural network model for optimization;
and S4, analyzing the vehicle running sound data by using the optimized qualified neural network model, outputting the result by using the model to obtain the vehicle health degree, and determining whether maintenance is needed.
2. The artificial intelligence algorithm-based vehicle fault detection method of claim 1, wherein the vehicle operation sound data includes a plurality of category data of battery voltage, battery consistency, tire pressure, motor speed, driving speed and position information.
3. The method for vehicle fault detection based on artificial intelligence algorithm according to claim 2, wherein the S2 specifically comprises:
the neural network model comprises a plurality of sub neural network models, each category of data in the vehicle running sound data is respectively used as input data of the sub neural network models, each sub neural network model outputs a corresponding fault score based on the corresponding input data, and a final overall automobile health score is obtained based on the output result of each sub neural network model.
4. The method for vehicle fault detection based on artificial intelligence algorithm as claimed in claim 3, wherein said obtaining the final overall vehicle health score based on the output result of each sub-neural network model specifically comprises:
and for each sub-neural network model, acquiring a corresponding score weight based on the input behavior data type, and performing algorithm weighting on the output result of each sub-neural network model based on the score weight of each sub-neural network model so as to obtain the final output result of the automobile health degree score.
5. The artificial intelligence algorithm-based vehicle fault detection method of claim 1, wherein the neural network model is a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), or a long-term memory network (LSTM).
6. The method for vehicle fault detection based on artificial intelligence algorithm according to claim 1, wherein the S2 specifically comprises:
s21, preprocessing, namely cutting off the mute of the head end and the tail end of the vehicle running sound data to reduce the interference on the subsequent steps, then framing the sound, and cutting the sound into data of one frame;
s22, extracting features, and converting each frame of waveform into a multi-dimensional vector containing sound information by applying a cepstrum coefficient algorithm;
s23, training by using an RNN model;
and S24, extracting fault prediction information of each accessory, and classifying corresponding sound data.
7. The method for vehicle fault detection based on artificial intelligence algorithm according to claim 1, wherein the S2 specifically comprises:
firstly, loading an audio file, namely the collected vehicle running sound, by using a librosa tool load () method, and drawing a waveform diagram by using a waveplot () method;
secondly, firstly splitting a data set of all vehicle running sounds into a 90% training set and a 10% testing set; then, splitting 90% of the training set into 80% of the training set and 20% of the verification set;
thirdly, classifying the target by using an ANN algorithm to construct a neural network classification model;
fourthly, evaluating the model;
and fifthly, outputting an ANN classification model classification report to predict the vehicle health degree.
8. An artificial intelligence algorithm-based vehicle fault detection system, which is used for implementing the artificial intelligence algorithm-based vehicle fault detection method according to any one of claims 1-7, and specifically comprises:
the acquisition module is used for acquiring vehicle control unit VCU data of a vehicle and vehicle running sound data in the vehicle running process and analyzing fault information of each accessory of the vehicle;
the neural network module is used for inputting the vehicle operation sound data into a trained neural network model for training and analysis, and the model outputs a classification report to obtain fault prediction information of each accessory of the vehicle;
the structure output module is used for comparing the fault information of each accessory of the vehicle with the corresponding fault prediction information of the accessories, extracting the fault prediction information of each accessory and feeding the result back to the neural network model for optimization; and finally, analyzing the vehicle operation sound data by using the optimized qualified neural network model, outputting a result by using the model to obtain the vehicle health degree, and determining whether maintenance is needed.
9. An electronic device comprising a memory, a processor for implementing the steps of the artificial intelligence algorithm based vehicle fault detection method according to any one of claims 1-7 when executing a computer management class program stored in the memory.
10. A computer-readable storage medium, having stored thereon a computer management-like program which, when executed by a processor, carries out the steps of the artificial intelligence algorithm based vehicle fault detection method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210677797.3A CN114839960A (en) | 2022-06-15 | 2022-06-15 | Method and system for detecting vehicle fault based on artificial intelligence algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210677797.3A CN114839960A (en) | 2022-06-15 | 2022-06-15 | Method and system for detecting vehicle fault based on artificial intelligence algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114839960A true CN114839960A (en) | 2022-08-02 |
Family
ID=82575128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210677797.3A Pending CN114839960A (en) | 2022-06-15 | 2022-06-15 | Method and system for detecting vehicle fault based on artificial intelligence algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114839960A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116304863A (en) * | 2023-02-08 | 2023-06-23 | 北京北明数科信息技术有限公司 | Multi-data-fusion vehicle fault monitoring and early warning method, equipment and medium |
-
2022
- 2022-06-15 CN CN202210677797.3A patent/CN114839960A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116304863A (en) * | 2023-02-08 | 2023-06-23 | 北京北明数科信息技术有限公司 | Multi-data-fusion vehicle fault monitoring and early warning method, equipment and medium |
| CN116304863B (en) * | 2023-02-08 | 2024-06-11 | 北京北明数科信息技术有限公司 | Multi-data-fusion vehicle fault monitoring and early warning method, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111325095B (en) | Intelligent detection method and system for equipment health state based on acoustic wave signals | |
| CN109949823B (en) | DWPT-MFCC and GMM-based in-vehicle abnormal sound identification method | |
| US20220180894A1 (en) | Voice Activity Detection Method and System Based on Joint Deep Neural Network | |
| CN112660745B (en) | Intelligent diagnosis method and system for carrier roller fault and readable storage medium | |
| CN112504673B (en) | Carrier roller fault diagnosis method, system and storage medium based on machine learning | |
| CN113566948A (en) | Fault audio recognition and diagnosis method for robot coal pulverizer | |
| Kemalkar et al. | Engine fault diagnosis using sound analysis | |
| CN114297912B (en) | Cutter abrasion prediction method based on deep learning | |
| CN114926825A (en) | Vehicle driving behavior detection method based on space-time feature fusion | |
| CN116778964A (en) | Power transformation equipment fault monitoring system and method based on voiceprint recognition | |
| CN112348052A (en) | Power transmission and transformation equipment abnormal sound source positioning method based on improved EfficientNet | |
| CN117591857A (en) | Motor detection method based on deep learning | |
| CN116361191A (en) | Software compatibility processing method based on artificial intelligence | |
| CN114839960A (en) | Method and system for detecting vehicle fault based on artificial intelligence algorithm | |
| CN112306816A (en) | Method and system for evaluating entity robot response based on deep learning | |
| Nasim et al. | Intelligent Sound-Based Early Fault Detection System for Vehicles. | |
| CN114999527A (en) | Transformer anomaly detection model training and deploying method and device | |
| CN114330430A (en) | Elevator fault judgment method and system based on big data characteristic analysis | |
| CN113450827A (en) | Equipment abnormal condition voiceprint analysis algorithm based on compressed neural network | |
| CN118035411A (en) | Customer service voice quality inspection method, customer service voice quality inspection device, customer service voice quality inspection equipment and storage medium | |
| CN114550711A (en) | Cable surrounding environment sound identification method based on time-frequency attention network model | |
| CN111931511B (en) | Semantic analysis method and system based on wide area distributed architecture | |
| CN116072146A (en) | Pumped storage station detection method and system based on voiceprint recognition | |
| CN112660746B (en) | Roller fault diagnosis method and system based on big data technology and storage medium | |
| Chen et al. | Sound-Based Real-Time Scrap Falling State Monitoring in the Shearing Process of Wide Heavy Plate Mill |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |