CN113569481B - Mining comprehensive protector fault diagnosis method based on SVM - Google Patents
Mining comprehensive protector fault diagnosis method based on SVM Download PDFInfo
- Publication number
- CN113569481B CN113569481B CN202110857421.6A CN202110857421A CN113569481B CN 113569481 B CN113569481 B CN 113569481B CN 202110857421 A CN202110857421 A CN 202110857421A CN 113569481 B CN113569481 B CN 113569481B
- Authority
- CN
- China
- Prior art keywords
- fault diagnosis
- mining
- circuit
- protector
- comprehensive
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Abstract
According to the SVM-based fault diagnosis method for the mining comprehensive protector, the mining motor comprehensive protector is selected as a fault diagnosis object, the fault diagnosis is carried out by adopting a support vector machine method in the machine learning field, and the support vector machine model optimization is carried out by utilizing a Monte Carlo method; the method establishes an electromagnetic interference model of the mining comprehensive protection test system, so that interference can be estimated on one hand, and a reference is provided for electromagnetic shielding technology application on the other hand; researching and using two data, namely simulation data and measured data, diagnosing circuit faults by using a support vector machine method, and optimizing a support vector machine model by using a Monte Carlo method; analyzing the influence of factors such as electromagnetic interference and the like on the accuracy of a test result of a test system; in conclusion, the fault is effectively positioned in the minimum replaceable unit, so that the maintenance efficiency of the mining comprehensive protector is effectively improved, the production efficiency is greatly improved, the coal supply is effectively ensured, and the energy safety is ensured.
Description
Technical Field
The invention relates to the technical field of automatic control, in particular to a fault diagnosis method of a mining comprehensive protector based on SVM.
Background
Coal is the main energy resource of China, and is the starting point of the energy strategy of China. The comprehensive protector for mine is easy to lose efficacy in use, loses the protection function of electrical equipment and systems, endangers the safety of personal equipment, and can cause accidents such as gas and coal dust explosion and the like seriously endangering the safety of mines under specific conditions. Therefore, the mining comprehensive protector is used for periodically performing functional tests, timely screening out failure comprehensive protection and avoiding the occurrence of the situations.
At present, failure comprehensive protection of the mining comprehensive protector is subjected to fault diagnosis, and faults cannot be located in a minimum replaceable unit, so that maintenance efficiency of the mining comprehensive protector is extremely low, production efficiency is seriously affected, coal supply cannot be effectively guaranteed, and energy safety is guaranteed.
Disclosure of Invention
In order to solve the defects and shortcomings of the prior art, the fault diagnosis method of the mining comprehensive protector based on the SVM is provided, so that the problem of extremely low maintenance efficiency of the mining comprehensive protector can be solved.
The invention provides a fault diagnosis method for a mining comprehensive protector based on SVM, which is characterized in that a mining motor comprehensive protector is selected as a fault diagnosis object, a support vector machine method in the machine learning field is adopted for fault diagnosis, a Monte Carlo method is utilized for support vector machine model optimization, a simulation circuit is adopted for obtaining the training sample number of a data expansion fault diagnosis algorithm, error distribution analysis is carried out on a test system, and main factors generated by electromagnetic interference and other errors are controlled according to analysis results, so that the aim of improving test precision is fulfilled:
(1) Failure comprehensive protection fault diagnosis
Aiming at circuit simulation under the conditions of normal comprehensive protection and various failures of the mine, carrying out circuit modeling according to the working principle of a circuit of a comprehensive protector of the mine motor, and obtaining input and output signals of the comprehensive protection of the mine under normal and different failure conditions by utilizing a circuit model as training samples required by a machine learning method for training failure comprehensive protection failure diagnosis; taking a small amount of collected actual failure comprehensive protection input/output data as a fault diagnosis algorithm verification sample; optimizing a support vector machine model by adopting a Monte Carlo method, and positioning a comprehensive protection fault of a failed mine in a maintenance replaceable unit;
(2) Electromagnetic interference and test error control of comprehensive protection test system for mine
Performing mechanism analysis on main components of the test system, and establishing a component model suitable for electromagnetic interference analysis; aiming at two modes of differential mode interference and common mode interference, carrying out accurate time domain circuit modeling of the differential mode interference and the common mode interference on the basis of component modeling; aiming at the main interference sources of two interference modes, simplifying a time domain circuit model to obtain a simplified time domain circuit model and a corresponding frequency domain model, performing qualitative and quantitative analysis of electromagnetic interference according to the simplified time domain model and the frequency domain model, further adopting measures to control test errors caused by the electromagnetic interference, analyzing and testing error distribution of a system, evaluating the influence of other factors such as power supply voltage, environmental temperature and the like on test precision, and adopting corresponding measures to reduce the main errors and improve the test precision according to the analysis result of the error distribution.
As a further improvement of the scheme, the failure comprehensive protection fault diagnosis is carried out by taking a mining motor comprehensive protector as an object, researching a circuit principle and constructing a primary simulation circuit; parameter adjustment is carried out on the simulation circuit, so that the input and output of the simulation circuit are consistent with those of an actual circuit, and a fault diagnosis algorithm training sample is obtained through circuit simulation; and collecting actual faults of the mining motor comprehensive protector.
As a further improvement of the scheme, the failure comprehensive protection fault diagnosis is to perform fault diagnosis training by using a simulation circuit data sample to obtain a fault diagnosis algorithm preliminary model, and continuously collect the actual fault mining motor comprehensive protector.
As a further improvement of the scheme, the electromagnetic interference and test error control of the mining comprehensive protection test system is used for collecting the mining motor comprehensive protector with actual faults and carrying out manual fault analysis on the collected mining motor protector with actual faults; and taking the actual fault mining motor protector as a verification sample to verify the fault diagnosis algorithm.
The beneficial effects of the invention are as follows:
compared with the prior art, the fault diagnosis method for the mining comprehensive protector based on the SVM solves the following problems:
(1) Modeling of electromagnetic interference of test system
An electromagnetic interference model of the mining comprehensive protection test system is established, so that on one hand, interference can be estimated, the blindness of EMC design is reduced, and on the other hand, reference is provided for electromagnetic shielding technology application;
(2) Electronic failure mining comprehensive protection fault diagnosis algorithm
Researching and using two data, namely simulation data and measured data, diagnosing circuit faults by using a support vector machine method, and optimizing a support vector machine model by using a Monte Carlo method;
(3) Analyzing influence of electromagnetic interference and other factors on accuracy of test result of test system
Improving the testing system according to the error distribution obtained by analysis to improve the testing accuracy, meeting the requirement of DL/T624-2010 relay protection microcomputer type test device technical condition, and metering and verifying the improved testing system;
in conclusion, the fault is effectively positioned in the minimum replaceable unit, so that the maintenance efficiency of the mining comprehensive protector is effectively improved, the production efficiency is greatly improved, the coal supply is effectively ensured, and the energy safety is ensured.
Detailed Description
The fault diagnosis method of the mining comprehensive protector based on the SVM selects the mining motor comprehensive protector as a fault diagnosis object, performs fault diagnosis by adopting a support vector machine method in the machine learning field, performs support vector machine model optimization by adopting a Monte Carlo method, acquires the number of training samples of a data expansion fault diagnosis algorithm by adopting a simulation circuit, performs error distribution analysis on a test system, controls main factors generated by electromagnetic interference and other errors according to analysis results, and achieves the aim of improving test precision:
(1) Failure comprehensive protection fault diagnosis
Aiming at circuit simulation under the conditions of normal comprehensive protection and various failures of the mine, carrying out circuit modeling according to the working principle of a circuit of a comprehensive protector of the mine motor, and obtaining input and output signals of the comprehensive protection of the mine under normal and different failure conditions by utilizing a circuit model as training samples required by a machine learning method for training failure comprehensive protection failure diagnosis; taking a small amount of collected actual failure comprehensive protection input/output data as a fault diagnosis algorithm verification sample; optimizing a support vector machine model by adopting a Monte Carlo method, and positioning a comprehensive protection fault of a failed mine in a maintenance replaceable unit;
(2) Electromagnetic interference and test error control of comprehensive protection test system for mine
Performing mechanism analysis on main components of the test system, and establishing a component model suitable for electromagnetic interference analysis; aiming at two modes of differential mode interference and common mode interference, carrying out accurate time domain circuit modeling of the differential mode interference and the common mode interference on the basis of component modeling; aiming at the main interference sources of two interference modes, simplifying a time domain circuit model to obtain a simplified time domain circuit model and a corresponding frequency domain model, performing qualitative and quantitative analysis of electromagnetic interference according to the simplified time domain model and the frequency domain model, further adopting measures to control test errors caused by the electromagnetic interference, analyzing and testing error distribution of a system, evaluating the influence of other factors such as power supply voltage, environmental temperature and the like on test precision, and adopting corresponding measures to reduce the main errors and improve the test precision according to the analysis result of the error distribution.
The failure comprehensive protection fault diagnosis is to take a mining motor comprehensive protector as an object, conduct circuit principle research and build a primary simulation circuit; parameter adjustment is carried out on the simulation circuit, so that the input and output of the simulation circuit are consistent with those of an actual circuit, and a fault diagnosis algorithm training sample is obtained through circuit simulation; and collecting actual faults of the mining motor comprehensive protector.
The failure comprehensive protection fault diagnosis is to perform fault diagnosis training by using a simulation circuit data sample to obtain a fault diagnosis algorithm preliminary model, and continuously collect the actual fault of the mining motor comprehensive protector.
The electromagnetic interference and test error control of the mining comprehensive protection test system is used for collecting the mining motor comprehensive protector with actual faults and carrying out manual fault analysis on the collected mining motor protector with actual faults; and taking the actual fault mining motor protector as a verification sample to verify the fault diagnosis algorithm.
The above embodiments are not limited to the technical solution of the embodiments, and the embodiments may be combined with each other to form a new embodiment. The above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and any modifications or equivalent substitutions without departing from the spirit and scope of the present invention should be covered in the scope of the technical solution of the present invention.
Claims (4)
1. The fault diagnosis method of the mining comprehensive protector based on the SVM is characterized by comprising the following steps of: selecting a mining motor comprehensive protector as a fault diagnosis object, performing fault diagnosis by adopting a support vector machine method in the machine learning field, performing support vector machine model optimization by adopting a Monte Carlo method, acquiring data by adopting a simulation circuit to expand the number of training samples of a fault diagnosis algorithm, performing error distribution analysis on a test system, controlling main factors generated by electromagnetic interference and other errors according to analysis results, and achieving the purpose of improving test precision:
(1) Failure comprehensive protection fault diagnosis
Aiming at circuit simulation under the conditions of normal comprehensive protection and various failures of the mine, carrying out circuit modeling according to the working principle of a circuit of a comprehensive protector of the mine motor, and obtaining input and output signals of the comprehensive protection of the mine under normal and different failure conditions by utilizing a circuit model as training samples required by a machine learning method for training failure comprehensive protection failure diagnosis; taking a small amount of collected actual failure comprehensive protection input/output data as a fault diagnosis algorithm verification sample; optimizing a support vector machine model by adopting a Monte Carlo method, and positioning a comprehensive protection fault of a failed mine in a maintenance replaceable unit;
(2) Electromagnetic interference and test error control of comprehensive protection test system for mine
Performing mechanism analysis on main components of the test system, and establishing a component model suitable for electromagnetic interference analysis; aiming at two modes of differential mode interference and common mode interference, carrying out accurate time domain circuit modeling of the differential mode interference and the common mode interference on the basis of component modeling; aiming at the main interference sources of two interference modes, simplifying a time domain circuit model to obtain a simplified time domain circuit model and a corresponding frequency domain model, performing qualitative and quantitative analysis of electromagnetic interference according to the simplified time domain model and the frequency domain model, further adopting measures to control test errors caused by the electromagnetic interference, analyzing and testing error distribution of a system, evaluating the influence of power supply voltage, environmental temperature and other factors on test precision, and adopting corresponding measures to reduce main errors and improve the test precision according to an error distribution analysis result.
2. The SVM-based mining integrated protector fault diagnosis method of claim 1, wherein: the failure comprehensive protection fault diagnosis is to take a mining motor comprehensive protector as an object, conduct circuit principle research and build a primary simulation circuit; parameter adjustment is carried out on the simulation circuit, so that the input and output of the simulation circuit are consistent with those of an actual circuit, and a fault diagnosis algorithm training sample is obtained through circuit simulation; and collecting actual faults of the mining motor comprehensive protector.
3. The SVM-based mining integrated protector fault diagnosis method of claim 1, wherein: the failure comprehensive protection fault diagnosis is to perform fault diagnosis training by using a simulation circuit data sample to obtain a fault diagnosis algorithm preliminary model, and continuously collect the actual fault of the mining motor comprehensive protector.
4. The SVM-based mining integrated protector fault diagnosis method of claim 1, wherein: the electromagnetic interference and test error control of the mining comprehensive protection test system is used for collecting the mining motor comprehensive protector with actual faults and carrying out manual fault analysis on the collected mining motor protector with actual faults; and taking the actual fault mining motor protector as a verification sample to verify the fault diagnosis algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110857421.6A CN113569481B (en) | 2021-07-28 | 2021-07-28 | Mining comprehensive protector fault diagnosis method based on SVM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110857421.6A CN113569481B (en) | 2021-07-28 | 2021-07-28 | Mining comprehensive protector fault diagnosis method based on SVM |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113569481A CN113569481A (en) | 2021-10-29 |
| CN113569481B true CN113569481B (en) | 2023-08-08 |
Family
ID=78168473
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110857421.6A Active CN113569481B (en) | 2021-07-28 | 2021-07-28 | Mining comprehensive protector fault diagnosis method based on SVM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113569481B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1687798A (en) * | 2005-03-29 | 2005-10-26 | 煤炭科学研究总院抚顺分院 | Distributing and electrical appliance state controlling diagnosis sensor for mine |
| CN101251579A (en) * | 2008-03-05 | 2008-08-27 | 湖南大学 | Analog circuit failure diagnosis method based on supporting vector machine |
| CN104569934A (en) * | 2014-12-31 | 2015-04-29 | 中国气象局气象探测中心 | Radar fault-handling system |
| WO2017128455A1 (en) * | 2016-01-25 | 2017-08-03 | 合肥工业大学 | Analogue circuit fault diagnosis method based on generalized multiple kernel learning-support vector machine |
-
2021
- 2021-07-28 CN CN202110857421.6A patent/CN113569481B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1687798A (en) * | 2005-03-29 | 2005-10-26 | 煤炭科学研究总院抚顺分院 | Distributing and electrical appliance state controlling diagnosis sensor for mine |
| CN101251579A (en) * | 2008-03-05 | 2008-08-27 | 湖南大学 | Analog circuit failure diagnosis method based on supporting vector machine |
| CN104569934A (en) * | 2014-12-31 | 2015-04-29 | 中国气象局气象探测中心 | Radar fault-handling system |
| WO2017128455A1 (en) * | 2016-01-25 | 2017-08-03 | 合肥工业大学 | Analogue circuit fault diagnosis method based on generalized multiple kernel learning-support vector machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113569481A (en) | 2021-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2628146C2 (en) | Method of warning detection of failure in the device, computer program, system and module for warning detection of failure in the device | |
| CN102566505B (en) | Intelligent fault diagnosis method for numerical control machine | |
| CN105467971B (en) | A kind of second power equipment monitoring system and method | |
| CN103487781B (en) | A kind of reliability estimation method of the electronic mutual inductor based on accelerated deterioration | |
| CN105425768A (en) | Electric power secondary equipment monitoring device and method | |
| CN103165203A (en) | Detection method for nuclear power station circuit board component | |
| CN103760895A (en) | Hardware-in-loop test device and method for vehicle-mounted charger control device of new energy automobile | |
| CN105445585A (en) | Fault diagnosis method and system for primary loop of power grid | |
| CN108920341A (en) | A kind of moonlet and its constellation availability appraisal procedure based on Monte Carlo simulation | |
| Chowdhury et al. | A methodology for the experimental validation of an aircraft ECS digital twin targeting system level diagnostics | |
| CN110264053A (en) | A kind of distribution network reliability evaluation method for considering Strategies of Maintenance and failure rate being influenced | |
| CN103616888A (en) | Function test board for traction control unit of internal combustion locomotive | |
| CN113569481B (en) | Mining comprehensive protector fault diagnosis method based on SVM | |
| CN112836396B (en) | Building real-time energy consumption abnormity diagnosis system | |
| CN108169678B (en) | Electric control development test system for simulating fuel cell | |
| CN103823978A (en) | Method and system for authenticating safety of alternative fuel in aircraft engine | |
| CN105891637A (en) | Intelligent substation secondary device testing method and intelligent substation secondary device testing system | |
| CN103389457A (en) | Method for assessing service lives of fuses by determining activation energy of melts | |
| Dong et al. | Design of PHM test verification method and system for aviation electrical system | |
| CN204374333U (en) | A kind of numerically-controlled machine regulator cubicle reliability test with environment-loading function | |
| CN112906237A (en) | Engine component fault analysis method and system | |
| Ross | Prognostics and Health Management for Power Electronics and Electrical Power Systems | |
| CN111090037A (en) | Reliability detection method for instrument control card | |
| RU2770316C1 (en) | System for testing an aviation gas turbine engine | |
| CN105303315B (en) | A kind of power equipment reliability appraisal procedure counted and maintenance randomness influences |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |