CN120686775A - Intelligent fault diagnosis system and method - Google Patents
Intelligent fault diagnosis system and methodInfo
- Publication number
- CN120686775A CN120686775A CN202510761310.3A CN202510761310A CN120686775A CN 120686775 A CN120686775 A CN 120686775A CN 202510761310 A CN202510761310 A CN 202510761310A CN 120686775 A CN120686775 A CN 120686775A
- Authority
- CN
- China
- Prior art keywords
- data
- layer
- vehicle
- diagnosis
- fault
- 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
Landscapes
- Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
Abstract
The invention discloses an intelligent fault diagnosis system and method, and belongs to the field of vehicle fault diagnosis. The system comprises a big data preprocessing layer, a data analysis processing layer and a user application layer, wherein the big data preprocessing layer is used for acquiring vehicle data, preprocessing the vehicle data and sending the vehicle data to the data analysis processing layer, the data analysis processing layer is used for carrying out fault prediction and early warning according to input data of the big data preprocessing layer, generating a solution after diagnosing and analyzing the found fault and outputting the solution to the user application layer, and the user application layer is used for carrying out task allocation and data forwarding according to a preset processing mechanism and executing corresponding task operation after receiving and analyzing the solution. The invention realizes fault prediction and early warning, intelligently generates and executes a solution, and improves diagnosis efficiency and accuracy.
Description
Technical Field
The invention belongs to the field of vehicle fault diagnosis, and particularly relates to an intelligent fault diagnosis system and method.
Background
The new energy automobile is coming to the tide of rapid development, and the electric, intelligent and networking has become the necessary trend of industry development. People put forward higher requirements on the environmental protection, the intelligent degree and the convenience of the travel solution, expect to enjoy more novel and high-quality travel experience, and the new energy automobile certainly becomes a key force for leading future travel.
However, in the key link of fault diagnosis of the new energy automobile, the conventional fault diagnosis method adopted at present has a plurality of defects. On the one hand, the traditional diagnosis mode mainly relies on an OBD diagnostic instrument to detect the vehicle and a manual remote platform to monitor the vehicle. The method is slow in response speed, misjudgment is easy to occur, diagnosis efficiency is low, and the requirement of a user on quick and accurate diagnosis of the vehicle faults cannot be met. On the other hand, no matter the diagnosis instrument is used for diagnosing the vehicle or the remote platform is used for monitoring, the prevention and intelligent early warning prediction of the faults and the real-time intelligent analysis and effective solution can not be realized when the faults occur. In addition, the existing diagnosis service mode is single, a user often needs to start the vehicle to a maintenance shop, and the cause of the fault can be determined after the vehicle is detected by the diagnostic apparatus, so that a plurality of inconveniences are brought to the user.
Therefore, the invention provides an intelligent fault diagnosis system and method.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides an intelligent fault diagnosis system and method, so as to achieve the purposes of realizing fault prediction and early warning, intelligently generating and executing a solution and improving diagnosis efficiency and accuracy.
In order to achieve the purpose, the intelligent fault diagnosis system comprises a big data preprocessing layer, a data analysis processing layer and a user application layer, wherein the intelligent fault diagnosis system comprises the following components:
The big data preprocessing layer is used for acquiring vehicle data, preprocessing the vehicle data and then sending the vehicle data to the data analysis processing layer;
The data analysis processing layer is used for carrying out fault prediction and early warning according to the input data of the big data preprocessing layer, carrying out diagnosis analysis on the found faults, generating a solution and outputting the solution to the user application layer;
And the user application layer is used for carrying out task allocation and data forwarding according to a preset processing mechanism after receiving and analyzing the solution and executing corresponding task operation.
Preferably, the big data preprocessing layer, the data analysis processing layer and the user application layer transfer and store data through a cloud server.
Preferably, the vehicle data acquired by the big data preprocessing layer includes:
direct data, namely vehicle operation data, including vehicle T-box data, diagnostic data and cloud data;
Indirect data, i.e., system operation support data, includes vehicle operation control logic policy information, vehicle configuration and diagnostic configuration information, software information, service manual information, design prevention phase failure mode information and test data, case information, technical requests, customer requests, and the like.
Preferably, the preprocessing operation of the big data preprocessing layer comprises the steps of eliminating noise, invalid values and abnormal values in the acquired vehicle data and converting unstructured data into a structured data format.
Preferably, the data analysis processing layer includes an early warning prediction and fault model and a diagnosis analysis model, wherein:
the early warning prediction and fault model is used for predicting vehicle faults according to the input data of the big data preprocessing layer and correspondingly generating early warning signals, and the predicted vehicle faults are sent to the diagnosis analysis model;
And the diagnosis analysis model is used for carrying out attribution diagnosis according to the predicted vehicle faults, generating a targeted solution and sending the solution to the user application layer.
Preferably, the data analysis processing layer further includes an AI deep learning model, where the AI deep learning model is used to obtain the early warning prediction and fault model and the historical working data of the diagnostic analysis model, and input the historical working data into a deep learning algorithm for training and optimizing, so as to obtain optimized model parameters, and adjust the early warning prediction and fault model and the diagnostic analysis model.
Preferably, the attribution diagnosis method of the diagnosis analysis model includes a bayesian network, a decision tree, and the like.
Preferably, the user application layer includes an intelligent integrated processing module and a functional service module, wherein:
the intelligent comprehensive processing module is used for forwarding the task and the corresponding data to the corresponding functional service module according to a preset processing mechanism after receiving and analyzing the solution;
the functional service module is used for receiving the task and the corresponding data and executing the corresponding task operation according to the service logic of the functional service module.
Preferably, the functional service module comprises an early warning platform, an intelligent maintenance platform, a prevention tracking platform, a remote monitoring platform, a remote diagnosis platform, a remote maintenance scheduling platform and the like.
The application also provides an intelligent fault diagnosis method, which uses the intelligent fault diagnosis system, and comprises the following steps:
The data preprocessing layer acquires vehicle data, performs preprocessing and then sends the vehicle data to the data analysis processing layer;
the data analysis processing layer carries out fault prediction and early warning according to the input data of the big data preprocessing layer, and generates a solution after diagnosis and analysis of the found fault and outputs the solution to the user application layer;
after receiving and analyzing the solution, the user application layer performs task allocation and data forwarding according to a preset processing mechanism, and executes corresponding task operation.
The invention has the technical effects that:
(1) The invention predicts and early warns the faults of the vehicle in real time, intelligently generates a scheme and realizes the '0' perception of the faults by a user through quick response and early repair.
(2) The invention can monitor the vehicle data in real time and forecast possible faults, reduces the influence of the faults on users, and improves the real-time performance of the system.
(3) The invention reduces manual intervention, improves the efficiency and accuracy of fault processing, and simultaneously improves the diagnosis efficiency and timeliness based on efficient data processing, thereby ensuring the running of the user vehicle.
Drawings
Fig. 1 is a schematic structural diagram of an intelligent fault diagnosis system according to an embodiment of the present invention.
Detailed Description
The following detailed description of the application, given by way of illustration of the present application, is presented to aid those skilled in the art in a more complete, accurate and thorough understanding of the present application's inventive concepts, technical solutions, and to facilitate its practice. It should be noted that the terms "first," "second," and the like in the present disclosure are merely for convenience in describing the technical solution for distinguishing components, and the corresponding configurations of the components may be the same or different, and are not limited thereto. In order to make the technical scheme of the application clearer, the application is explained by the following application.
The invention provides an intelligent fault diagnosis system, as shown in fig. 1, which comprises a big data preprocessing layer, a data analysis processing layer and a user application layer, wherein:
The big data preprocessing layer is used for acquiring vehicle data, preprocessing the vehicle data and then sending the vehicle data to the data analysis processing layer;
The data analysis processing layer is used for carrying out fault prediction and early warning according to the input data of the big data preprocessing layer, carrying out diagnosis analysis on the found faults, generating a solution and outputting the solution to the user application layer;
And the user application layer is used for carrying out task allocation and data forwarding according to a preset processing mechanism after receiving and analyzing the solution and executing corresponding task operation.
Specifically, the big data preprocessing layer, the data analysis processing layer and the user application layer of the application transmit and store data through the cloud server. The cloud server is generally deployed in a high-speed network environment, can realize rapid data transmission, ensures the high-efficiency work of the system, has massive storage resources, can meet the storage requirement of a large amount of data when the system works, and is more convenient to operate, easier to expand and lower in cost compared with physical storage equipment.
The big data preprocessing layer communicates with the vehicle through an API interface so as to acquire vehicle data. The acquired vehicle data includes direct data and indirect data, wherein:
The direct data, namely vehicle operation data, comprises vehicle T-box data, diagnosis data and cloud data. And more particularly to vehicle real-time data, DTC (trouble code) and health report data (i.e., on-board diagnostic data), vehicle maintenance monitoring data, and aggregate data defined by a CAN communication matrix.
The indirect data, namely the system operation support data, refers to various information which does not come from the vehicle operation state directly, but plays a supporting role in links such as vehicle function realization, system analysis, fault diagnosis and the like. The indirect data includes vehicle operation control logic policy information, vehicle configuration and diagnosis configuration information, software information, maintenance manual information (including diagnosis fault scripts, circuit diagrams, etc.), design prevention stage failure mode information and test data, case information (such as technical support and claim information), technical requests, customer requests, and other comprehensive information.
And correspondingly carrying out preprocessing operation on the obtained vehicle data by the big data preprocessing layer, wherein the preprocessing operation comprises removing noise, invalid values and abnormal values in the obtained vehicle data, and carrying out clear identification on the data, so that the data classification management is facilitated. Meanwhile, a large amount of unstructured data exists in the acquired vehicle data, and for the data, a machine cannot directly extract the logical relationship between the data, so that the processing efficiency is low, therefore, the invention also converts the unstructured data into a structured data format stored in a form of a table and a key value pair, and the structured data input with high quality and high availability is ensured to be provided for the subsequent analysis and processing links, and meanwhile, the data is properly stored in the cloud server so as to be conveniently called at any time. After unstructured data are converted into structured data, the machine can directly perform logic analysis and extraction, and the working efficiency is improved.
The data analysis processing layer is the core of the intelligent fault diagnosis system, receives structured data input from the big data preprocessing layer, processes data by utilizing a plurality of pre-established algorithm models, improves the intelligent level of the system and reduces manual intervention. The data analysis processing layer comprises an early warning prediction and fault model and a diagnosis analysis model.
And the early warning prediction and fault model is used for predicting the vehicle fault according to the input data of the big data preprocessing layer and correspondingly generating an early warning signal, and the predicted vehicle fault is sent to the diagnosis analysis model to provide a clear direction for subsequent diagnosis analysis. In the design and manufacturing stage of the vehicle, various failure conditions of the vehicle are deduced, correspondingly, a deduction result is constructed into an early warning prediction and failure model, for example, for the failure conditions of unstable engine power output, the characteristics of engine speed fluctuation range, torque change condition, abnormal sensor signals and the like are taken as input parameters of the model, and corresponding threshold values and judgment rules are set, so that the constructed early warning prediction and failure model can be used for engine power system failure prediction.
And the diagnosis analysis model is used for carrying out attribution diagnosis according to the predicted vehicle faults, generating a targeted solution and sending the solution to the user application layer. Specifically, the diagnosis and analysis model is combined with the predicted vehicle faults, the fault sources are traced back through an attribution diagnosis method, and the reason of the faults is analyzed, wherein the attribution diagnosis method comprises a Bayesian network, a decision tree and the like, all adopt the prior art, and the working principle of the vehicle fault diagnosis method is not repeated here. For example, according to vehicle history data, an unstable engine output fault may be caused by a sensor fault, a temperature abnormality and other reasons, and the relationship between the fault and various fault reasons can be modeled by processing the data through a Bayesian network, a decision tree and other attributive diagnosis methods, so that the fault source is obtained by analysis.
After determining the root cause of the fault, the diagnostic analysis model may intelligently generate a targeted solution, and illustratively, the diagnostic analysis model may match corresponding solutions from a historical solution library based on the root cause of the fault.
In addition, the data analysis processing layer of the invention also comprises an AI deep learning model, wherein the AI deep learning model is used for acquiring the early warning prediction and fault model and the historical working data of the diagnosis analysis model, inputting the data into a deep learning algorithm for training and optimizing, and obtaining optimized model parameters for adjusting the early warning prediction and fault model and the diagnosis analysis model. Illustratively, the AI deep learning model trains a neural network model (such as a convolutional neural network) based on the early warning prediction and fault model and massive historical working data of the diagnostic analysis model, so as to obtain optimized model parameters and feed the optimized model parameters back to the early warning prediction and fault model, and the diagnostic analysis model, for example, provides more accurate fault judgment threshold values for the early warning prediction and fault model to reduce misjudgment and more efficient and reliable attribution logic for the diagnostic analysis model to improve attribution accuracy.
The data analysis processing layer intelligently identifies faults and generates corresponding solutions, and meanwhile, the AI deep learning model endows the system with self-evolution capability. Through a machine self-learning and deep learning mechanism, the system continuously perfects and optimizes the model, and continuously improves the precision and accuracy of fault prediction analysis, so that the intelligent fault diagnosis system can accurately make judgment and decision when facing complex and changeable vehicle fault scenes, and the intellectualization and standardization of fault processing are realized.
In the application, the user application layer is a key link of tightly interfacing the intelligent fault diagnosis system with the actual service scene of the user, and comprises an intelligent comprehensive processing module and a functional service module, wherein:
And the intelligent comprehensive processing module is used for forwarding the task and the corresponding data to the corresponding functional service module according to a preset processing mechanism after receiving and analyzing the solution. The functional service module is used for receiving the tasks and the corresponding data, executing corresponding task operations according to self service logic, and introducing other functional service modules according to actual requirements when the functional service module is specifically implemented, such as an early warning platform, an intelligent maintenance platform, a preventive tracking platform, a remote diagnosis platform, a remote monitoring platform, a remote maintenance scheduling platform and the like.
The preset processing mechanism in the intelligent comprehensive processing module is essentially a mapping relation between data characteristics of a solution and a service module, for example, when faults need to be monitored and analyzed in real time, the potential risks are predicted, alarms are triggered in advance, an early warning platform is called, when the faults can be updated and repaired through software, OTA upgrading is conducted through a remote diagnosis platform, when the faults need to be collected in real time and the global running state is visualized, a remote monitoring platform is called, when the faults need to be repaired on site, DMS inventory information is automatically inquired through a remote maintenance scheduling platform, spare part preparation and technical tool preparation are timely notified to network points in an area, customers are reserved through a call center, mobile service or shop-end service is flexibly arranged, maintenance requirements of users are met in all directions, when the faults need to be continuously tracked and the safety risks are prevented, the intelligent maintenance platform is called when the fault needs to be repaired. The user application layer converts the high-efficiency advantage of the intelligent fault diagnosis system into the actual convenience experience of the user.
The intelligent fault diagnosis system of the invention is also reserved with a plurality of API interfaces for communicating with external systems, for example, synchronizing fault diagnosis results to a quality feedback system to continuously optimize vehicle performance.
Meanwhile, the invention also provides an intelligent fault diagnosis method, which uses the intelligent fault diagnosis system, and comprises the following steps:
The data preprocessing layer acquires vehicle data, performs preprocessing and then sends the vehicle data to the data analysis processing layer;
the data analysis processing layer carries out fault prediction and early warning according to the input data of the big data preprocessing layer, and generates a solution after diagnosis and analysis of the found fault and outputs the solution to the user application layer;
after receiving and analyzing the solution, the user application layer performs task allocation and data forwarding according to a preset processing mechanism, and executes corresponding task operation.
One embodiment of the invention is as follows:
In the running process of the vehicle, real-time data of the vehicle are sent to an intelligent fault diagnosis system through a T-Box and a cloud, the big data preprocessing layer carries out data preprocessing on the collected vehicle data and transmits the data to the data analysis processing layer, the early warning prediction and fault model of the data analysis processing layer detects potential health hazards of a battery system of the vehicle through analysis and timely sends early warning signals, and the diagnosis analysis model generates a detailed battery maintenance scheme. After receiving the proposal, the intelligent comprehensive processing system of the user application layer forwards the proposal to a remote maintenance scheduling platform (notifying corresponding network points to prepare spare parts, tools and technologies) according to a preset processing mechanism, reserves maintenance service for the clients through a call center, and sends a reminder through a client APP after reservation confirmation. After a customer arrives at a store, maintenance personnel rapidly complete battery maintenance operation according to the scheme, normal operation of the vehicle is ensured, vehicle stopping time caused by battery faults is reduced, and operation time of the vehicle and use experience of a user are improved.
In conclusion, the invention carries out real-time fault prediction and early warning on the vehicle, intelligently generates a scheme and realizes '0' perception of the fault by a user through quick response and early repair. Breaks through the limitations of the traditional diagnosis method and provides a more efficient, accurate and convenient intelligent fault diagnosis solution.
The invention is described above by way of example with reference to the accompanying drawings. It will be clear that the invention is not limited to the embodiments described above. It is within the scope of the present invention to apply the above-described concepts and technical solutions of the present invention directly to other applications, as long as they are various insubstantial modifications made by using the method concepts and technical solutions of the present invention, or not.
Claims (10)
1. The intelligent fault diagnosis system is characterized by comprising a big data preprocessing layer, a data analysis processing layer and a user application layer, wherein:
The big data preprocessing layer is used for acquiring vehicle data, preprocessing the vehicle data and then sending the vehicle data to the data analysis processing layer;
The data analysis processing layer is used for carrying out fault prediction and early warning according to the input data of the big data preprocessing layer, carrying out diagnosis analysis on the found faults, generating a solution and outputting the solution to the user application layer;
And the user application layer is used for carrying out task allocation and data forwarding according to a preset processing mechanism after receiving and analyzing the solution and executing corresponding task operation.
2. The intelligent fault diagnosis system according to claim 1, wherein the big data preprocessing layer, the data analysis processing layer and the user application layer are used for data transfer and storage through a cloud server.
3. The intelligent fault diagnosis system according to claim 1, wherein the vehicle data acquired by the big data preprocessing layer comprises:
direct data, namely vehicle operation data, including vehicle T-box data, diagnostic data and cloud data;
Indirect data, i.e., system operation support data, includes vehicle operation control logic policy information, vehicle configuration and diagnostic configuration information, software information, service manual information, design prevention phase failure mode information and test data, case information, technical requests, and customer requests.
4. An intelligent fault diagnosis system according to claim 1 or 3, wherein the preprocessing operation of the big data preprocessing layer comprises removing noise, invalid values and abnormal values from the acquired vehicle data, and converting unstructured data into a structured data format.
5. The intelligent fault diagnosis system according to claim 1, wherein the data analysis processing layer comprises an early warning prediction and fault model and a diagnosis analysis model, wherein:
the early warning prediction and fault model is used for predicting vehicle faults according to the input data of the big data preprocessing layer and correspondingly generating early warning signals, and the predicted vehicle faults are sent to the diagnosis analysis model;
And the diagnosis analysis model is used for carrying out attribution diagnosis according to the predicted vehicle faults, generating a targeted solution and sending the solution to the user application layer.
6. The intelligent fault diagnosis system according to claim 5, wherein the data analysis processing layer further comprises an AI deep learning model, the AI deep learning model is used for obtaining historical working data of the early warning prediction and fault model and the diagnosis analysis model, and inputting the historical working data into a deep learning algorithm for training and optimizing to obtain optimized model parameters for adjusting the early warning prediction and fault model and the diagnosis analysis model.
7. The intelligent fault diagnosis system according to claim 5, wherein the attribution diagnosis method of the diagnosis analysis model comprises a Bayesian network, a decision tree, etc.
8. The intelligent fault diagnosis system according to claim 1, wherein the user application layer comprises an intelligent integrated processing module and a functional service module, wherein:
the intelligent comprehensive processing module is used for forwarding the task and the corresponding data to the corresponding functional service module according to a preset processing mechanism after receiving and analyzing the solution;
the functional service module is used for receiving the task and the corresponding data and executing the corresponding task operation according to the service logic of the functional service module.
9. The intelligent fault diagnosis system according to claim 8, wherein the functional service module comprises an early warning platform, an intelligent maintenance platform, a remote monitoring platform, a preventive tracking platform, a remote diagnosis platform and a remote maintenance scheduling platform.
10. An intelligent fault diagnosis method using an intelligent fault diagnosis system according to any one of claims 1to 9, characterized in that the method comprises:
The data preprocessing layer acquires vehicle data, performs preprocessing and then sends the vehicle data to the data analysis processing layer;
the data analysis processing layer carries out fault prediction and early warning according to the input data of the big data preprocessing layer, and generates a solution after diagnosis and analysis of the found fault and outputs the solution to the user application layer;
after receiving and analyzing the solution, the user application layer performs task allocation and data forwarding according to a preset processing mechanism, and executes corresponding task operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510761310.3A CN120686775A (en) | 2025-06-09 | 2025-06-09 | Intelligent fault diagnosis system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510761310.3A CN120686775A (en) | 2025-06-09 | 2025-06-09 | Intelligent fault diagnosis system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN120686775A true CN120686775A (en) | 2025-09-23 |
Family
ID=97074035
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510761310.3A Pending CN120686775A (en) | 2025-06-09 | 2025-06-09 | Intelligent fault diagnosis system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120686775A (en) |
-
2025
- 2025-06-09 CN CN202510761310.3A patent/CN120686775A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110221558B (en) | Electro-hydraulic servo valve online fault diagnosis gateway based on edge computing technology | |
| CN113112086A (en) | Intelligent production system based on edge calculation and identification analysis | |
| CN118915566A (en) | Heating ventilation equipment abnormity on-line monitoring system based on Internet of things | |
| CA2564724C (en) | Automatic remote monitoring and diagnostics system and communication method for communicating between a programmable logic controller and a central unit | |
| CN102055803B (en) | Integrative ship engine room monitoring system | |
| KR20190107080A (en) | Cloud-based vehicle fault diagnosis method, apparatus and system | |
| CN118313812A (en) | A method for collecting and processing power big data based on machine learning | |
| CN116107282B (en) | Industrial robot predictive maintenance system based on enterprise application integration | |
| US6834257B2 (en) | Method for providing diagnostic messages | |
| CN110658760A (en) | A power operation and maintenance terminal with remote positioning and communication | |
| CN110210632A (en) | Failure emergency processing method, device and terminal based on ubiquitous electric power Internet of Things | |
| CN106525415A (en) | A system and method for evaluating the health status of a transmission chain of a wind turbine | |
| CN112541563A (en) | Rotary equipment vibration prediction management system based on edge calculation technology | |
| CN118796603A (en) | A machine nest cloud edge intelligent inspection and equipment status monitoring system and method | |
| CN118732662A (en) | A vehicle remote fault diagnosis and recovery system and method | |
| CN120124443A (en) | A method and system for monitoring production safety in power plant areas based on digital twin technology | |
| CN118780774A (en) | Industrial robot predictive maintenance method, system and electronic equipment | |
| CN103616877A (en) | Monitoring diagnostic method and system for energy pipe network | |
| CN119887125B (en) | Industrial Internet of things main service platform data analysis collaboration system and method | |
| CN111539642B (en) | Object-oriented power plant data acquisition and processing system and method thereof | |
| CN120686775A (en) | Intelligent fault diagnosis system and method | |
| CN112116108A (en) | Expert system and method for failure analysis of power equipment | |
| CN118336903A (en) | An active monitoring system for power supply services based on big data | |
| CN117875933A (en) | Comprehensive operation and maintenance guaranteeing system and method for airborne test system | |
| CN120931109A (en) | A condition monitoring method, device, equipment, and medium |
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 |