CN116880454A - Intelligent diagnosis system and method for vehicle faults - Google Patents
Intelligent diagnosis system and method for vehicle faults Download PDFInfo
- Publication number
- CN116880454A CN116880454A CN202310946025.XA CN202310946025A CN116880454A CN 116880454 A CN116880454 A CN 116880454A CN 202310946025 A CN202310946025 A CN 202310946025A CN 116880454 A CN116880454 A CN 116880454A
- Authority
- CN
- China
- Prior art keywords
- fault
- vehicle
- data
- unit
- neural network
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003062 neural network model Methods 0.000 claims abstract description 64
- 238000012423 maintenance Methods 0.000 claims abstract description 41
- 238000004364 calculation method Methods 0.000 claims abstract description 28
- 230000005540 biological transmission Effects 0.000 claims abstract description 19
- 230000008569 process Effects 0.000 claims description 27
- 238000011156 evaluation Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 13
- 230000008447 perception Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000013461 design Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 abstract description 24
- 230000002159 abnormal effect Effects 0.000 abstract description 7
- 238000013528 artificial neural network Methods 0.000 description 7
- 230000004927 fusion Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 230000000737 periodic effect Effects 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004171 remote diagnosis Methods 0.000 description 1
- 238000004092 self-diagnosis Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
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
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to the technical field of vehicle detection, and provides a vehicle fault intelligent diagnosis system which comprises a data acquisition unit, a transmission unit and a cloud server, wherein a neural network model in the cloud server is adopted to conduct fault prediction calculation on vehicle real-time state data acquired by the data acquisition unit in different vehicles, fault nodes in a fault tree model are fused to conduct matching calculation, finally, fault codes of the fault nodes are sent to an intelligent diagnosis unit in the vehicle through the transmission unit, and the intelligent diagnosis unit is used for reading the fault codes in the intelligent diagnosis unit and then conducting vehicle fault diagnosis and maintenance. The application also discloses a method, which can analyze based on real-time and real vehicle running state data, timely reflect all abnormal states and potential faults of the vehicle, comprehensively reflect the comprehensive performance of the vehicle, and avoid the problems of missing diagnosis, misdiagnosis, repeated maintenance and the like.
Description
Technical Field
The application relates to the technical field of vehicle detection, in particular to an intelligent diagnosis system and method for vehicle faults.
Background
The intelligent diagnosis system for vehicle fault is one system utilizing artificial intelligent technology to detect, analyze and diagnose vehicle fault. The method is used for analyzing and pattern recognition by collecting vehicle sensor data, fault codes and other related information and utilizing algorithms such as machine learning, data mining and the like, so that the cause and the position of the vehicle fault can be rapidly and accurately determined. The intelligent diagnosis system can help an automobile maintenance technician to locate and solve the vehicle problem more quickly, and improve maintenance efficiency and quality. Meanwhile, the vehicle fault detection device can help a vehicle owner to better understand the vehicle fault and timely take correct countermeasures, so that further damage or potential safety hazards are avoided. The intelligent diagnosis system for the vehicle faults can also realize remote diagnosis and on-line monitoring, and timely send an alarm and provide a corresponding solution when the vehicle breaks down. The development of the system greatly simplifies the maintenance flow of the vehicle, reduces the maintenance cost and improves the reliability and safety of the vehicle.
CN202453715U discloses a vehicle fault intelligent diagnosis system, which further comprises a diagnosis center host computer arranged in a diagnosis center and an accessory maintenance service computer arranged at an after-sales support position of an accessory equipment provider, wherein the maintenance service extension is connected with the diagnosis center host computer through a communication network, and the diagnosis center host computer is also connected with the accessory maintenance service computer through the communication network.
CN116304629a discloses a mechanical equipment fault intelligent diagnosis method, system, electronic equipment and storage medium. The method comprises the following steps: acquiring data of different mechanical equipment, and dividing fault data into an offline training set D-P and an online testing set D-P according to environmental conditions; collecting vibration signals, performing equal-length segmentation, performing time-frequency domain feature extraction to obtain an initial state environment E, selecting M optimization features by adopting an AMRMR method, and constructing an optimized state environment E; the NM adopts SVDD to perform cluster analysis on the multi-condition training data, calculates the center-to-center distance matrix of each class of hypersphere, obtains a corresponding fault identification rewarding matrix, combines domain identification rewards, and sets a divide-and-conquer rewarding strategy; constructing a domain generalization Q depth network, adopting a priority experience playback mechanism, extracting a training sample to train the domain generalization Q network, observing whether a domain label and a fault label output by the network are consistent with the training sample, carrying out rewarding assignment according to a divide-by-two rewarding principle, combining a loss function, and updating parameters of the domain generalization Q depth network by using a gradient descent algorithm; d is tested by adopting the trained DGD3QN, a control strategy meeting the return is searched online, and a fault label corresponding to the return is output.
CN115511136B discloses a device fault auxiliary diagnosis method and system based on hierarchical analysis and fault tree, comprising: determining a target fault event, matching corresponding fault factors from a historical fault information base, and establishing a corresponding fault tree model based on the association relation of each fault factor, wherein the target fault event is an object needing diagnosis analysis in the fault event of equipment; obtaining the periodic factor probability corresponding to each fault factor in the fault tree from the historical fault information base, and calculating the expected loss value E1 of each fault factor; acquiring the corresponding guarantee cost P of each fault factor, and generating the guarantee resource allocation information after performing hierarchical analysis processing on each fault factor; the step of obtaining the period factor probability corresponding to each fault factor in the fault tree from the historical fault information base and calculating the expected loss value E1 of each fault factor comprises the following steps: inputting a fault tree model into a fault segmentation model, determining all minimum cut sets of the fault tree model, defining events which occur simultaneously with all fault factors in the minimum cut sets as basic events, and when any basic event occurs, generating a target fault event; calculating the periodic event probability of each basic event based on the periodic factor probability of each fault factor; average loss data of each basic event is obtained from a historical fault information base, and expected loss value E1 of each fault factor is calculated; the step of obtaining the guarantee cost P corresponding to each fault factor, performing hierarchical analysis processing on each fault factor, and generating the guarantee resource allocation information comprises the following steps: acquiring the guarantee cost P corresponding to each fault factor, and calculating a guarantee expected loss value E2 corresponding to each fault factor; based on the expected loss value E1, the difference value E2 of the expected loss value and the guarantee cost P, calculating the guarantee cost performance A= (E1-E2)/P of each fault factor, and generating guarantee sequencing information based on the guarantee cost performance A of each fault factor; performing hierarchical analysis processing on the target fault event based on the guaranteed cost performance A, the periodic event probability and the influence parameters of each fault factor by taking the reduced target fault event occurrence probability as a decision target, generating a hierarchical analysis result, and determining the guaranteed priority of each fault factor; determining allocation information of the guaranteed resources based on the analytic hierarchy process result and the guaranteed resources, and generating a guaranteed flow plan; the guarantee flow plan is a plan for recording operation flow information generated based on the analytic hierarchy process result and available distributed guarantee resources for a maintainer to refer to when performing equipment maintenance work.
Along with the increasing degree of vehicle intellectualization, in the existing detection and diagnosis technology, a vehicle-mounted self-diagnosis system (OBD, on-Board Diagnostics) is still adopted for passive detection and maintenance, namely, the detection and maintenance are carried out after the vehicle fails, so that the diagnosis efficiency is low, the effect is poor, and the problems of missing diagnosis, misdiagnosis, repeated maintenance and the like are easily caused.
Disclosure of Invention
According to long-term practice, in the prior art, after a vehicle fails, the vehicle is often required to be transported to a designated maintenance point, the fault phenomenon of the vehicle is simulated and tested by adopting diagnosis and detection methods such as OBD/OBDII and the like, data are collected in the test process, and the actual running state data of the vehicle cannot be acquired in real time and truly, so that all abnormal states of the vehicle cannot be completely reflected, and missing diagnosis, misdiagnosis, multiple maintenance and the like are caused; the vehicle detection quality is different from person to person, so that different people often detect completely different results, and the requirements on the detection method and the detection personnel are high and the dependence is high; and failure early prediction diagnosis and the like cannot be performed based on the real-time state data of the vehicle.
In view of the above, the present application provides a vehicle fault intelligent diagnosis system, comprising,
the system comprises a data acquisition unit, a control unit and a control unit, wherein the data acquisition unit at least comprises an intelligent perception module, and the intelligent perception module is used for acquiring real-time state data of a vehicle;
the transmission unit is used for transmitting the real-time state data of the vehicle acquired by the intelligent perception module to the cloud server;
the cloud server is used for receiving the real-time state data of the vehicle, storing the real-time state data into a corresponding database and carrying out processing calculation; the cloud server comprises a neural network model, a fault tree model and an evaluation feedback unit, wherein the neural network model is trained by taking vehicle historical data as input data; the fault tree model is built based on vehicle design, production and maintenance process data;
the neural network model is used for inputting real-time state data of the vehicle, outputting fault prediction data after calculation, and sending the fault prediction data to the evaluation feedback unit;
the evaluation feedback unit is used for carrying out matching calculation on the fault prediction data and the fault nodes in the fault tree model, and sending the fault codes of the fault nodes to the intelligent diagnosis unit in the vehicle through the transmission unit;
the fault tree model is used for structuring and storing the existing fault nodes;
the intelligent diagnosis unit is used for receiving the fault code from the transmission unit; and communicates with an execution diagnostic unit of the off-line client;
and the execution diagnosis unit is used for reading the fault codes in the intelligent diagnosis unit and carrying out vehicle fault diagnosis and maintenance according to the diagnosis flow corresponding to the fault codes.
In one embodiment, the neural network model includes at least 1 middle layer neural network model.
In one embodiment, the vehicle history operational data is divided into a training set and a testing set, and training is performed on the neural network model; and outputting the neural network model after the accuracy rate of the neural network model is greater than a threshold value.
In one embodiment, the fault node data in the fault tree model is used for a test set of the neural network model.
In one embodiment, after the evaluation feedback unit performs matching calculation on the fault prediction data and the fault nodes in the fault tree model, if the fault tree model does not have the fault nodes, the fault nodes are newly built in the fault tree model.
In one embodiment, the intelligent diagnostic unit and the performing diagnostic unit comprise a wireless connection.
The application also discloses a method for the intelligent diagnosis system for vehicle faults, which comprises the following steps of,
step S1, a vehicle acquires real-time state data through an intelligent sensing module in a data acquisition unit, wherein the real-time state data at least comprises vibration, temperature, rotating speed, voltage, current and power;
step S2, transmitting the real-time state data to a cloud server, wherein the cloud server receives the real-time state data of the vehicle and stores the real-time state data into a corresponding database, and processes and calculates the real-time state data; the cloud server comprises a cloud server, a neural network model, an evaluation feedback unit, a fault prediction unit and a fault prediction unit, wherein the neural network model of the cloud server preprocesses real-time state data, inputs the neural network model to calculate to obtain fault prediction data, and sends the fault prediction data to the evaluation feedback unit;
step S3, the evaluation feedback unit performs matching calculation on the fault prediction data and fault nodes in the fault tree model to obtain fault codes, and the fault codes of the fault nodes are sent to an intelligent diagnosis unit in the vehicle through the transmission unit;
and S4, an execution diagnosis unit of the off-line client reads the fault codes in the intelligent diagnosis unit, and performs vehicle fault diagnosis and maintenance according to the diagnosis flow corresponding to the fault codes.
In one embodiment, in step S2, a neural network model is trained from vehicle history data as input data; establishing a fault tree model based on vehicle design, production and maintenance process data; the vehicle history data is divided into a training set and a testing set, and after the accuracy reaches a threshold value after the neural network model is trained, the neural network model is output for fault prediction of the vehicle real-time state data.
The application also discloses an electronic device, at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method described above.
The present application also discloses a machine-readable storage medium having stored thereon instructions for causing a machine to perform the method of the present application as described above.
Compared with the prior art, the intelligent diagnosis system for the vehicle fault comprises a data acquisition unit, a transmission unit and a cloud server, wherein a neural network model in the cloud server is used for carrying out fault prediction calculation on real-time state data of the vehicle, which are acquired by the data acquisition unit in different vehicles, fault nodes in a fault tree model are fused for carrying out matching calculation, finally, fault codes of the fault nodes are sent to an intelligent diagnosis unit in the vehicle through the transmission unit, the diagnosis unit is used for reading the fault codes in the intelligent diagnosis unit, and vehicle fault diagnosis and maintenance are carried out according to diagnosis flows corresponding to the fault codes. The application also discloses a method for the intelligent diagnosis system of the vehicle faults, which can analyze based on real-time and real running state data of the vehicle, adopts the fusion of a neural network model and a fault tree model, rapidly and timely reflects all abnormal states and potential faults of the vehicle, can completely and comprehensively reflect the comprehensive performance of the vehicle, and does not cause the problems of missing diagnosis, misdiagnosis, repeated maintenance and the like. The diagnosis and detection processes of the vehicle are made by the cloud server according to the neural network model fusion fault tree model, not only can the vehicle fault information be quickly and predictively obtained in advance before the vehicle enters the maintenance process, but also the detection maintenance personnel can directly read the fault codes in the intelligent diagnosis unit in the vehicle through the execution diagnosis unit, so that the dependence degree and the working strength of the detection personnel can be reduced, and the intellectualization, the accuracy and the efficiency of the vehicle diagnosis are improved.
Additional features and advantages of the application will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:
FIG. 1 is a schematic diagram of the modules of a vehicle fault intelligent diagnostic system according to one embodiment of the present application;
fig. 2 is a schematic flow chart of a vehicle fault intelligent diagnosis method according to an embodiment of the application.
Detailed Description
The following describes specific embodiments of the present application in detail with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the application, are not intended to limit the application.
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," "third," "fourth," and the like in the description and claims of the present application and in the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the prior art, after a vehicle breaks down, the vehicle is often required to be transported to a designated maintenance point, and the fault phenomenon of the vehicle is simulated and tested by adopting diagnosis and detection methods such as OBD/OBDII and the like, and data are acquired in the test process, so that the actual running state data of the vehicle cannot be acquired in real time and truly, and all abnormal states of the vehicle cannot be completely reflected, and diagnosis omission, misdiagnosis, multiple maintenance and the like are caused; the vehicle detection quality is different from person to person, so that different people often detect completely different results, and the requirements on the detection method and the detection personnel are high and the dependence is high; and the technical problems of failure early prediction diagnosis and the like cannot be performed based on the real-time state data of the vehicle. 1-2, the application provides a vehicle fault intelligent diagnosis system, which comprises a data acquisition unit, a control unit and a control unit, wherein the data acquisition unit at least comprises an intelligent perception module, and the intelligent perception module is used for acquiring real-time state data of a vehicle;
the transmission unit is used for transmitting the real-time state data of the vehicle acquired by the intelligent perception module to the cloud server;
the cloud server is used for receiving the real-time state data of the vehicle, storing the real-time state data into a corresponding database and carrying out processing calculation; the cloud server comprises a neural network model, a fault tree model and an evaluation feedback unit, wherein the neural network model is trained by taking vehicle historical data as input data; the fault tree model is built based on vehicle design, production and maintenance process data;
the neural network model is used for inputting real-time state data of the vehicle, outputting fault prediction data after calculation, and sending the fault prediction data to the evaluation feedback unit;
the evaluation feedback unit is used for carrying out matching calculation on the fault prediction data and the fault nodes in the fault tree model, and sending the fault codes of the fault nodes to the intelligent diagnosis unit in the vehicle through the transmission unit;
the fault tree model is used for structuring and storing the existing fault nodes;
the intelligent diagnosis unit is used for receiving the fault code from the transmission unit; and communicates with an execution diagnostic unit of the off-line client;
and the execution diagnosis unit is used for reading the fault codes in the intelligent diagnosis unit and carrying out vehicle fault diagnosis and maintenance according to the diagnosis flow corresponding to the fault codes.
The intelligent diagnosis system for the vehicle fault comprises a data acquisition unit, a transmission unit and a cloud server, wherein a neural network model in the cloud server is used for carrying out fault prediction calculation on real-time state data of the vehicle, which are acquired by the data acquisition unit in different vehicles, fault nodes in a fault tree model are fused for carrying out matching calculation, finally, fault codes of the fault nodes are sent to an intelligent diagnosis unit in the vehicle through the transmission unit, the diagnosis unit is used for reading the fault codes in the intelligent diagnosis unit, and vehicle fault diagnosis and maintenance are carried out according to diagnosis flows corresponding to the fault codes. The system can analyze based on real-time and real vehicle running state data, adopts the fusion of the neural network model and the fault tree model, rapidly and timely reflects all abnormal states and potential faults of the vehicle, completely and comprehensively reflects the comprehensive performance of the vehicle, and does not cause the problems of missing diagnosis, misdiagnosis, repeated maintenance and the like. The diagnosis and detection processes of the vehicle are made by the cloud server according to the neural network model fusion fault tree model, so that the vehicle fault information can be quickly and predictively obtained in advance before the vehicle enters the maintenance process, and the detection maintenance personnel can directly read the fault codes in the intelligent diagnosis unit in the vehicle through the execution diagnosis unit, so that the dependence degree and the working strength of the detection personnel can be reduced, and the accuracy and the efficiency of vehicle diagnosis are improved. The intelligent diagnosis system and method for the online+offline fusion can be used for carrying out intelligent prediction calculation on the vehicle real-time operation data, fusing the online neural network model, fusing fault node data from the vehicle fault tree, reading the fault codes in the intelligent diagnosis unit by the offline execution diagnosis unit, and finally completing diagnosis of the vehicle according to the diagnosis flow corresponding to the fault codes.
Because the neural network with hidden layers has more hidden layers and nodes, the neural network can learn deeper features under a nonlinear activation function. In order to output the failure prediction data after calculation, preferably by inputting the real-time state data of the vehicle, the neural network model comprises at least 1 neural network model of middle layers in a more preferable case of the application. To further improve the accuracy of the prediction, a recurrent neural network (RNN, recurrent Neural Network) or convolutional neural network (CNN, convolutional Neural Network) is included. For example, the intelligent sensing module in the data acquisition unit comprises an operation parameter acquisition of the power system. The instantaneous operation parameters of the engine [ basic attribute data, rotating speed, power, temperature and output torque value ], wherein the basic attribute data comprise the number, cylinder number, displacement, model, cooling mode and the like of the engine. If the power system is an electric automobile, the operation parameters of the power system at least comprise [ basic attribute data, motor rotating speed, voltage of each phase, current of each phase and motor temperature ], wherein the basic attribute data comprise the number, the type, rated voltage, rated current, cooling mode and the like of the driving motor. In order to better process the input data, the present application preferably requires preprocessing of the input data, including normalization processing, to form dimensionless numerical vectors. For example, the normalization process includes a Z-score or Max-min normalization method. In a more preferable case of the application, the intelligent sensing module integrates the requirements of the calculation amount and the calculation precision of balance data, and the intelligent sensing module comprises the operation parameters of an electric system, such as the value of tire pressure monitoring, an instrument system and the like. The sampling period of the operating parameter of the power system is less than the sampling period of the operating parameter of the electrical system. In the case of a bandwidth limitation of the communication network, the acquisition of the operating parameters of the power system is prioritized.
Because the diagnosis efficiency is high only based on the fault tree, but the dynamic data of the running process of the vehicle is ignored, the real running condition of the vehicle is difficult to be reflected well. In order to train the neural network better and improve the accuracy of the neural network, under the more preferable condition of the application, the historical operation data of the vehicle is divided into a training set and a testing set, and the training is carried out aiming at the neural network model; and outputting the neural network model after the accuracy rate of the neural network model is greater than a threshold value. For example, a training set is adopted, wherein the training set comprises data with faults, the trained neural network is tested by adopting a testing set, and when the accuracy rate is greater than or equal to 85%, a neural network model is output, and at the moment, the threshold value is 85%. More preferably, the higher the threshold setting, the better the effect. In order to better complete the fault diagnosis of the vehicle according to the fault codes, in a more preferable case of the application, the fault codes are in one-to-one correspondence with the diagnosis flow at the workflow layer of the system.
In order to make up for the problems of insufficient data, default, and lack of systematicness of the neural network model in the diagnosis and calculation process. The data in the fault tree model is better used for supporting the establishment and training of the neural network model, and the prediction accuracy of the neural network model is improved. In a more preferred aspect of the application, the fault node data in the fault tree model is used for a test set of the neural network model. Since not all faults occur in the vehicle history operation data, the abnormal data of some operation faults are clarified by the vehicle before shipment, for example, the possible reasons for determining the single-phase no-voltage state of the driving motor in the vehicle design stage are. In a real situation, the historical running data of the vehicle cannot completely cover all fault types of the vehicle, and the vehicle fault data is more completely and systematically covered by combining the data of the fault tree.
Because the generated partial fault data are case data which do not exist in the fault nodes in the fault tree in the running process of the vehicle, the fault tree can cover more comprehensive fault types by generating the fault node data from actual running data in a case mode. In a more preferable case of the present application, after the evaluation feedback unit performs matching calculation on the fault prediction data and the fault nodes in the fault tree model, if the fault tree model does not have a fault node, the fault node is newly built in the fault tree model. In a more preferred case of the present application, for each vehicle model, the same mechanical structure configuration corresponds to one fault tree and one neural network model.
In order to better realize online intelligent diagnosis, directly read diagnosis data offline, reduce communication cost and improve diagnosis efficiency, in a more preferable case of the application, the intelligent diagnosis unit and the execution diagnosis unit are connected in a wireless way. Wherein, wireless connection includes bluetooth or Wifi connection.
The present application also provides a method for the intelligent diagnosis system for vehicle faults as described above, the method comprising,
step S1, a vehicle acquires real-time state data through an intelligent sensing module in a data acquisition unit, wherein the real-time state data at least comprises vibration, temperature, rotating speed, voltage, current and power;
step S2, transmitting the real-time state data to a cloud server, wherein the cloud server receives the real-time state data of the vehicle and stores the real-time state data into a corresponding database, and processes and calculates the real-time state data; the cloud server comprises a cloud server, a neural network model, an evaluation feedback unit, a fault prediction unit and a fault prediction unit, wherein the neural network model of the cloud server preprocesses real-time state data, inputs the neural network model to calculate to obtain fault prediction data, and sends the fault prediction data to the evaluation feedback unit;
step S3, the evaluation feedback unit performs matching calculation on the fault prediction data and fault nodes in the fault tree model to obtain fault codes, and the fault codes of the fault nodes are sent to an intelligent diagnosis unit in the vehicle through the transmission unit;
and S4, an execution diagnosis unit of the off-line client reads the fault codes in the intelligent diagnosis unit, and performs vehicle fault diagnosis and maintenance according to the diagnosis flow corresponding to the fault codes.
The method for the intelligent diagnosis system of the vehicle fault comprises the steps that the vehicle obtains real-time state data comprising vibration, temperature, rotating speed, voltage, current, power and the like through an intelligent sensing module in a data acquisition unit. The real-time status data is transmitted to the cloud server, where it is received and stored in a corresponding database for processing and computation. The neural network model of the cloud server preprocesses the real-time state data, inputs the real-time state data into the neural network model for calculation, generates fault prediction data, and then sends the fault prediction data to the evaluation feedback unit. And the evaluation feedback unit performs matching calculation on the fault prediction data and fault nodes in the fault tree model to obtain fault codes, and sends the fault codes to the intelligent diagnosis unit in the vehicle through the transmission unit. And the execution diagnosis unit of the off-line client reads the fault code in the intelligent diagnosis unit and performs vehicle fault diagnosis and maintenance according to the corresponding diagnosis flow. The method can analyze based on real-time and real vehicle running state data, adopts the fusion of the neural network model and the fault tree model, rapidly and timely reflects all abnormal states and potential faults of the vehicle, completely and comprehensively reflects the comprehensive performance of the vehicle, and does not cause the problems of missing diagnosis, misdiagnosis, repeated maintenance and the like. The diagnosis and detection processes of the vehicle are made by the cloud server according to the neural network model fusion fault tree model, so that the vehicle fault information can be quickly and predictively obtained in advance before the vehicle enters the maintenance process, and the detection maintenance personnel can directly read the fault codes in the intelligent diagnosis unit in the vehicle through the execution diagnosis unit, so that the dependence degree and the working strength of the detection personnel can be reduced, and the accuracy and the efficiency of vehicle diagnosis are improved.
In order to better integrate the vehicle running process, running data can be calculated in a neural network model in real time and comprehensively diagnosed by combining fault nodes of a fault tree, so that the fault prediction and diagnosis can be performed based on the vehicle real-time running dynamic data and the static system data of the fault tree is fused, the detection efficiency and quality of the fault tree and the accurate prediction characteristic of the neural network model are integrated, and the intelligent diagnosis of the whole vehicle can be realized by considering the quality and efficiency. In a more preferred case of the present application, in step S2, a neural network model is trained from vehicle history data as input data; establishing a fault tree model based on vehicle design, production and maintenance process data; the vehicle history data is divided into a training set and a testing set, and after the accuracy reaches a threshold value after the neural network model is trained, the neural network model is output for fault prediction of the vehicle real-time state data.
Further, the application also provides electronic equipment, at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method described above.
Further, the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above-mentioned method provided by the present application.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, such as the division of the units, merely a logical function division, and there may be additional manners of dividing the actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, or may be in electrical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of 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.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution contributing to the prior art or in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a mobile terminal, a server or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A vehicle fault intelligent diagnosis system is characterized in that the vehicle fault intelligent diagnosis system comprises,
the system comprises a data acquisition unit, a control unit and a control unit, wherein the data acquisition unit at least comprises an intelligent perception module, and the intelligent perception module is used for acquiring real-time state data of a vehicle;
the transmission unit is used for transmitting the real-time state data of the vehicle acquired by the intelligent perception module to the cloud server;
the cloud server is used for receiving the real-time state data of the vehicle, storing the real-time state data into a corresponding database and carrying out processing calculation; the cloud server comprises a neural network model, a fault tree model and an evaluation feedback unit, wherein the neural network model is trained by taking vehicle historical data as input data; the fault tree model is built based on vehicle design, production and maintenance process data;
the neural network model is used for inputting real-time state data of the vehicle, outputting fault prediction data after calculation, and sending the fault prediction data to the evaluation feedback unit;
the evaluation feedback unit is used for carrying out matching calculation on the fault prediction data and the fault nodes in the fault tree model, and sending the fault codes of the fault nodes to the intelligent diagnosis unit in the vehicle through the transmission unit;
the fault tree model is used for structuring and storing the existing fault nodes;
the intelligent diagnosis unit is used for receiving the fault code from the transmission unit; and communicates with an execution diagnostic unit of the off-line client;
and the execution diagnosis unit is used for reading the fault codes in the intelligent diagnosis unit and carrying out vehicle fault diagnosis and maintenance according to the diagnosis flow corresponding to the fault codes.
2. The vehicle fault intelligent diagnostic system of claim 1, wherein the neural network model comprises at least 1 middle layer neural network model.
3. The vehicle fault intelligent diagnostic system of claim 1, wherein vehicle historical operating data is divided into a training set and a test set, and training is performed for the neural network model; and outputting the neural network model after the accuracy rate of the neural network model is greater than a threshold value.
4. The vehicle fault intelligent diagnostic system of claim 3, wherein the fault node data in the fault tree model is used for a test set of the neural network model.
5. The vehicle fault intelligent diagnostic system according to any one of claims 1 to 4, wherein after the evaluation feedback unit performs a matching calculation of the fault prediction data with the fault nodes in the fault tree model, if the fault tree model does not have a fault node, the fault node is newly built in the fault tree model.
6. The vehicle fault intelligent diagnostic system of any one of claims 1-4, wherein the intelligent diagnostic unit and the performance diagnostic unit comprise a wireless connection.
7. A method for a vehicle fault intelligent diagnostic system as claimed in any one of claims 1 to 6, wherein the method comprises,
step S1, a vehicle acquires real-time state data through an intelligent sensing module in a data acquisition unit, wherein the real-time state data at least comprises vibration, temperature, rotating speed, voltage, current and power;
step S2, transmitting the real-time state data to a cloud server, wherein the cloud server receives the real-time state data of the vehicle and stores the real-time state data into a corresponding database, and processes and calculates the real-time state data; the cloud server comprises a cloud server, a neural network model, an evaluation feedback unit, a fault prediction unit and a fault prediction unit, wherein the neural network model of the cloud server preprocesses real-time state data, inputs the neural network model to calculate to obtain fault prediction data, and sends the fault prediction data to the evaluation feedback unit;
step S3, the evaluation feedback unit performs matching calculation on the fault prediction data and fault nodes in the fault tree model to obtain fault codes, and the fault codes of the fault nodes are sent to an intelligent diagnosis unit in the vehicle through the transmission unit;
and S4, an execution diagnosis unit of the off-line client reads the fault codes in the intelligent diagnosis unit, and performs vehicle fault diagnosis and maintenance according to the diagnosis flow corresponding to the fault codes.
8. The method according to claim 7, characterized in that in step S2, a neural network model is trained from vehicle history data as input data; establishing a fault tree model based on vehicle design, production and maintenance process data; the vehicle history data is divided into a training set and a testing set, and after the accuracy reaches a threshold value after the neural network model is trained, the neural network model is output for fault prediction of the vehicle real-time state data.
9. An electronic device characterized by at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 7-8.
10. A machine-readable storage medium having stored thereon instructions for causing a machine to perform the method of any of claims 7-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310946025.XA CN116880454A (en) | 2023-07-28 | 2023-07-28 | Intelligent diagnosis system and method for vehicle faults |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310946025.XA CN116880454A (en) | 2023-07-28 | 2023-07-28 | Intelligent diagnosis system and method for vehicle faults |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116880454A true CN116880454A (en) | 2023-10-13 |
Family
ID=88258637
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310946025.XA Pending CN116880454A (en) | 2023-07-28 | 2023-07-28 | Intelligent diagnosis system and method for vehicle faults |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116880454A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117290764A (en) * | 2023-11-23 | 2023-12-26 | 湖南省交通科学研究院有限公司 | Method for intelligently identifying and diagnosing faults of ultra-system based on data feature analysis |
| CN117590837A (en) * | 2024-01-18 | 2024-02-23 | 深圳市伟创高科电子有限公司 | Electric vehicle controller fault diagnosis method based on tree structure |
-
2023
- 2023-07-28 CN CN202310946025.XA patent/CN116880454A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117290764A (en) * | 2023-11-23 | 2023-12-26 | 湖南省交通科学研究院有限公司 | Method for intelligently identifying and diagnosing faults of ultra-system based on data feature analysis |
| CN117290764B (en) * | 2023-11-23 | 2024-02-09 | 湖南省交通科学研究院有限公司 | Method for intelligently identifying and diagnosing faults of ultra-system based on data feature analysis |
| CN117590837A (en) * | 2024-01-18 | 2024-02-23 | 深圳市伟创高科电子有限公司 | Electric vehicle controller fault diagnosis method based on tree structure |
| CN117590837B (en) * | 2024-01-18 | 2024-03-29 | 深圳市伟创高科电子有限公司 | Electric vehicle controller fault diagnosis method based on tree structure |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109001649B (en) | Intelligent power supply diagnosis system and protection method | |
| CN108681747B (en) | Rotary machine fault diagnosis and state monitoring system and method based on deep learning | |
| CN106406273B (en) | Determination of the cause of a fault in a vehicle | |
| CN116880454A (en) | Intelligent diagnosis system and method for vehicle faults | |
| CN102375452B (en) | Event-driven data mining method for improving fault code settings and isolating faults | |
| EP1242923B1 (en) | A process for the monitoring and diagnostics of data from a remote asset | |
| CN111947928B (en) | Multi-source information fusion bearing fault prediction system and method | |
| CN114585983B (en) | Method, device and system for detecting abnormal operation state of equipment | |
| CN112926257A (en) | Reciprocating natural gas compressor fault diagnosis system and diagnosis method | |
| CN108027611B (en) | Decision assistance system and method for machine maintenance using expert opinion supervised decision mode learning | |
| KR102427205B1 (en) | Apparatus and method for generating training data of artificial intelligence model | |
| EP3866177A1 (en) | Abnormal driving state determination device and method using neural network model | |
| CN113339204B (en) | Wind driven generator fault identification method based on hybrid neural network | |
| KR102368396B1 (en) | Method for aligning of period-varying random signal using K-means clustering algorithm and system and method for fault diagnosis of internal combustion engine using thereof | |
| JP2021108110A (en) | System and method for monitoring and predicting vehicle damage | |
| US12007745B2 (en) | Apparatus for predicting equipment damage | |
| KR102545672B1 (en) | Method and apparatus for machine fault diagnosis | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN115031994B (en) | Vehicle endurance test method and system | |
| WO2022175767A1 (en) | Equipment fault detection system using artificial intelligence(icms) | |
| CN110758478B (en) | Pre-warning system and method for railway signal equipment | |
| Byttner et al. | A field test with self-organized modeling for knowledge discovery in a fleet of city buses | |
| CN114757366A (en) | Fault prediction method and system for vehicle | |
| He et al. | Probabilistic model based algorithms for prognostics | |
| CN117589444B (en) | Wind driven generator gear box fault diagnosis method based on federal learning |
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 |