CN103323228A - Mining drill fault intelligent identification method - Google Patents
Mining drill fault intelligent identification method Download PDFInfo
- Publication number
- CN103323228A CN103323228A CN201310272937XA CN201310272937A CN103323228A CN 103323228 A CN103323228 A CN 103323228A CN 201310272937X A CN201310272937X A CN 201310272937XA CN 201310272937 A CN201310272937 A CN 201310272937A CN 103323228 A CN103323228 A CN 103323228A
- Authority
- CN
- China
- Prior art keywords
- fault
- rig
- signal
- analysis
- diagnosis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a mining drill fault intelligent identification method which mainly comprises a primary diagnosis based on signal processing and a secondary diagnosis based on hybrid intelligence. According to the primary diagnosis based on signal processing, signal processing methods such as time domain and frequency domain analysis, wavelet packet analysis and empirical mode decomposition are utilized to extract a drill fault feature, a characteristic value is obtained through calculating and doing statistics, and a drill fault is judged preliminarily. According to the secondary diagnosis based on hybrid intelligence, the feature of the primary judgment is taken as an input, a support vector machine, an expert system, a fault tree analysis are used to diagnose the drill fault, and a diagnosis result is obtained by using voting technology. According to the mining drill fault intelligent identification method, a plurality of signal processing technology and intelligent diagnosis methods are integrated, the accuracy of drill fault diagnosis can be effectively raised, the examination and repair times are reduced, and the drilling cost is reduced.
Description
Technical field
The invention belongs to the intelligent diagnostics field, be specifically related to the recognition methods of a kind of mining-drilling machine intelligent fault.
Background technology
Mining-drilling machine complex structure, work under bad environment, and need frequent carrying, various faults easily appear.The mining-drilling machine failure effect is generally more serious, directly affects the production efficiency of coal, even the production safety of down-hole.Existing conventional rig method for diagnosing faults is static investigation rig fault just, and then takes corresponding maintenance measure, and does not monitor the duty of rig.These methods can not satisfy the needs of mining-drilling machine modern production.For this reason, the present invention intends adopting the various states parameter of rig operational process to be input, uses the multi-signal disposal routes such as time domain and frequency domain statistical study, wavelet packet analysis, empirical mode decomposition to carry out feature extraction, carries out primary diagnosis with various features; Various features is inputted in the multiple intelligent diagnosing methods such as support vector machine, expert system, fault tree analysis, comprehensive various factors carries out the secondary diagnosis, and identification rig fault provides counter-measure.
Summary of the invention
The object of the invention is to, the recognition methods of a kind of mining-drilling machine intelligent fault is provided, use the multi-signal disposal route to carry out the primary fault diagnosis, use Multi Intelligent Techniques that the rig fault is carried out hybrid intelligent diagnostic.
To achieve these goals, the technical scheme taked of the present invention is:
The recognition methods of a kind of mining-drilling machine intelligent fault, it mainly comprises based on the primary diagnosis of signal processing with based on the secondary of hybrid intelligent diagnoses two parts.
Wherein, the primary diagnosis of processing based on signal uses the signal prescribing methods such as time domain and frequency domain statistical study, wavelet packet analysis, empirical mode decomposition to extract the rig fault signature, and the counting statistics eigenwert is tentatively judged the rig fault.
Analysis method of wavelet packet is to use orthonormal basis that monitor signal is divided into a plurality of frequency ranges from the low frequency to the high frequency, monitor signal is carried out irredundant, leak free decomposition, thereby the signal that comprises a large amount of medium, high frequency compositions is carried out best Time-Frequency Localization analysis.
The empirical mode decomposition method is set up the fundamental quantity with instantaneous frequency characterization signal alternation, take the local feature of monitor signal as foundation, be the form of a plurality of basic model components adaptively with signal decomposition, get rid of noise frequency in the monitor signal, extract the Weak fault feature.
Wherein, judge it is the input that is characterized as with elementary judgement based on the secondary of hybrid intelligent, simultaneously to the rig diagnosing malfunction, utilize at last the ballot decision-making to determine the last diagnostic result with support vector machine, expert system, fault tree analysis.
Support vector machine is launched as the basis take structural risk minimization, train the Monitoring Data of a small amount of known rig state, the Monitoring Data of the unknown rig state of structure optimal classification surface analysis Real-time Collection is judged the rig running status, diagnosis rig fault.
Expert system is to set up by neural network, and the learning experience sample obtains expertise, and the form of knowledge with weights and threshold value is stored in the knowledge base, and input rig monitoring information uses inference mechanism identification rig fault, provides counter-measure.
The concrete operations of Fault Tree Analysis are distinguished system failure reason for the event of failure that occurs in the system is analyzed on refinement ground by dendroid to part step by step by overall, determine the probability that fault occurs, and giving is out of order, and possible priority occurs.
Ballot decision-making is that the diagnostic result to various intelligent methods considers, and different diagnostic results are voted, and determines the possibility of its generation, and most possible result is decided to be the last diagnostic conclusion.
Beneficial effect
1) Real-Time Monitoring rig running status of the present invention is extracted feature to operational monitoring data application multi-signal disposal route, carries out primary diagnosis, but real-time judge rig running status
2) the present invention uses the input that is characterized as of primary diagnosis, uses multiple Intelligent Diagnosis Technology that the rig fault is carried out the secondary diagnosis, and most possible fault type is judged in utilization ballot decision-making, and diagnosis is comprehensive, and diagnostic accuracy is high.
3) universality of the present invention, real-time are all better, are convenient to use in the engineering reality.
Description of drawings
Figure 1 shows that mining-drilling machine intelligent fault recognition methods frame diagram
Figure 2 shows that analysis method of wavelet packet
Figure 3 shows that the empirical mode decomposition method
Figure 4 shows that the support vector machine frame diagram
Figure 5 shows that expert system shells figure
Figure 6 shows that the fault tree process flow diagram
Embodiment
The present invention is further described below in conjunction with accompanying drawing.
As shown in Figure 1, the recognition methods of a kind of mining-drilling machine intelligent fault mainly comprises based on the primary diagnosis of signal processing with based on the secondary of hybrid intelligent and diagnoses two parts.In the primary diagnosis of processing based on signal, at first gather the rig status data as input, then utilize the noise signal in wavelet packet analysis and the empirical mode decomposition elimination status data, extract failure message, calculate original signal and decompose after Time-domain Statistics feature and the frequency domain statistical nature of signal, tentatively judge whether fault of rig according to eigenwert.In the secondary diagnosis based on hybrid intelligent, utilize all latent structure feature databases of primary diagnosis, difference failure judgement type in input expert system, support vector machine, the fault tree analysis, for different diagnostic results, use the ballot decision rule to provide the probability that various results occur, determine most possible diagnostic result according to the probability size.
The wavelet packet analysis process as shown in Figure 2, monitor signal x obtains low frequency signal A1 and high-frequency signal D1 after being decomposed for the first time by wavelet packet, decomposes for the second time A1, D1 are decomposed into A21, D21, A22, D22 etc., until the n time decomposition is 2 with signal decomposition
nIndividual frequency range.Wavelet packet analysis can be realized the multi-level division to signal, and selects adaptively frequency band according to the feature of analyzed signal, makes it to be complementary with signal spectrum, thereby improves time frequency resolution.
The empirical mode decomposition method is shown in Figure 3, at first ground floor basic model component c1 is decomposed out from primary monitoring signal x, then second layer basic model component c2 is decomposed from remainder r1 and comes, until till remainder can not decompose.The characteristic of empirical mode decomposition is that its basis function does not have unified expression formula, but the characteristics of basis signal self are constructed the best base function adaptively by matching pursuit algorithm, thereby realizes the adaptive decomposition to signal.
Support vector machine as shown in Figure 4, monitor signal statistical nature X
iIn the input support vector machine, through kernel function K (X
i, X) map in the higher dimensional space, in higher dimensional space, find the solution Lagrange multiplier a
i, judge the rig state by discriminant function at last, identification rig fault.
The expert system aufbauprinciple as shown in Figure 5, the automatic acquisition expertise is set up knowledge base, the knowledge engineer uses interpre(ta)tive system to provide diagnostic result, at last by I/O system user oriented by inference mechanism identification rig state.
Fault Tree Analysis is shown in Figure 6, phylogenetic event of failure is decided to be top event, determine the fault type of system according to the performance characteristic of fault, then utilize logical calculated to seek the multiple direct factor that causes fault to occur, analyze the directly intermediate event M relevant with these factors, from top to bottom decompose step by step, until can not decompose, find the stratum event.
It should be noted that at last: obviously, above-described embodiment only is for the application's example clearly is described, and is not the restriction to embodiment.For those of ordinary skill in the field, can also make other changes in different forms on the basis of the above description.Here need not also can't give all embodiments exhaustive.And the apparent variation of being amplified out thus or change still are among the protection domain of the application's type.
Claims (9)
1. mining-drilling machine intelligent fault recognition methods is characterized in that: mainly comprise based on the primary diagnosis of signal processing with based on the secondary of hybrid intelligent and diagnose two parts.
2. method according to claim 1, it is characterized in that: the described primary diagnosis of processing based on signal comprises that utilization time domain and frequency domain statistical study, wavelet packet analysis, empirical mode decomposition signal prescribing method extract the rig fault signature, the counting statistics eigenwert is tentatively judged the rig fault.
3. method according to claim 2, it is characterized in that: described analysis method of wavelet packet is to use orthonormal basis that monitor signal is divided into a plurality of frequency ranges from the low frequency to the high frequency, monitor signal is carried out irredundant, leak free decomposition, thereby the signal that comprises a large amount of medium, high frequency compositions is carried out the Time-Frequency Localization analysis.
4. method according to claim 2, it is characterized in that: described empirical mode decomposition method is set up the fundamental quantity with instantaneous frequency characterization signal alternation, take the local feature of monitor signal as foundation, be the form of a plurality of basic model components adaptively with signal decomposition, get rid of noise frequency in the monitor signal, extract the Weak fault feature.
5. method according to claim 1, it is characterized in that: described secondary judgement based on hybrid intelligent is the input that is characterized as with elementary judgement, simultaneously to the rig diagnosing malfunction, utilize at last the ballot decision-making to determine the last diagnostic result with support vector machine, expert system, fault tree analysis.
6. method according to claim 5, it is characterized in that: described support vector machine is launched as the basis take structural risk minimization, train the Monitoring Data of a small amount of known rig state, the Monitoring Data of the unknown rig state of structure optimal classification surface analysis Real-time Collection, judge the rig running status, diagnosis rig fault.
7. method according to claim 5, it is characterized in that: described expert system is to set up by neural network, the learning experience sample, obtain expertise, and the form of knowledge with weights and threshold value be stored in the knowledge base, input rig monitoring information uses inference mechanism identification rig fault, provides counter-measure.
8. method according to claim 5, it is characterized in that: the concrete operations of described Fault Tree Analysis are for being analyzed on refinement ground step by step by dendroid by overall extremely part the event of failure that occurs in the system, distinguish system failure reason, determine the probability that fault occurs, giving is out of order, and possible priority occurs.
9. method according to claim 5, it is characterized in that: described ballot decision-making is that the diagnostic result to various intelligent methods considers, different diagnostic results are voted, determine the possibility of its generation, most possible result is decided to be the last diagnostic conclusion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310272937XA CN103323228A (en) | 2013-07-02 | 2013-07-02 | Mining drill fault intelligent identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310272937XA CN103323228A (en) | 2013-07-02 | 2013-07-02 | Mining drill fault intelligent identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103323228A true CN103323228A (en) | 2013-09-25 |
Family
ID=49192118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310272937XA Pending CN103323228A (en) | 2013-07-02 | 2013-07-02 | Mining drill fault intelligent identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103323228A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103575525A (en) * | 2013-11-18 | 2014-02-12 | 东南大学 | Intelligent diagnosis method for mechanical fault of circuit breaker |
| CN106198000A (en) * | 2016-07-11 | 2016-12-07 | 太原理工大学 | A kind of rocker arm of coal mining machine gear failure diagnosing method |
| CN106530082A (en) * | 2016-10-25 | 2017-03-22 | 清华大学 | Stock predication method and stock predication system based on multi-machine learning |
| CN106897740A (en) * | 2017-02-17 | 2017-06-27 | 重庆邮电大学 | EEMD DFA feature extracting methods under Human bodys' response system based on inertial sensor |
| CN107709700A (en) * | 2015-05-13 | 2018-02-16 | 科诺科菲利浦公司 | Drill big data analytic approach engine |
| CN108361020A (en) * | 2018-04-03 | 2018-08-03 | 中煤科工集团西安研究院有限公司 | Underground drill rig diagnosis protective device and method based on virtual instrument |
| CN109035836A (en) * | 2018-08-14 | 2018-12-18 | 青岛海信网络科技股份有限公司 | A kind of transit equipment operational system |
| CN109117959A (en) * | 2018-06-20 | 2019-01-01 | 中译语通科技（青岛）有限公司 | A kind of artificial intelligence automatic recognition system and method based on intelligent operation platform |
| CN110276372A (en) * | 2019-05-08 | 2019-09-24 | 复变时空(武汉)数据科技有限公司 | Fuel battery engines method for diagnosing faults based on cloud platform |
| CN111596230A (en) * | 2020-06-11 | 2020-08-28 | 贵州中烟工业有限责任公司 | Method for establishing electrical troubleshooting model |
| CN112014094A (en) * | 2020-09-03 | 2020-12-01 | 盾构及掘进技术国家重点实验室 | Shield tunneling machine main driving performance monitoring and repairing method |
| CN112082639A (en) * | 2019-06-14 | 2020-12-15 | 现代自动车株式会社 | Engine state diagnosis method and diagnosis modeling method thereof |
| CN112434930A (en) * | 2020-11-20 | 2021-03-02 | 中国地质大学（武汉） | Fault diagnosis method, system and equipment in drilling process |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030154051A1 (en) * | 2002-02-13 | 2003-08-14 | Kabushiki Kaisha Toshiba | Method and system for diagnosis of plant |
| CN1514209A (en) * | 2003-08-01 | 2004-07-21 | 重庆大学 | Rotary machine failure intelligent diagnosis method and device |
| CN1811367A (en) * | 2006-03-03 | 2006-08-02 | 西安交通大学 | Integrated supporting vector machine mixed intelligent diagnosing method for mechanical fault |
| CN102830250A (en) * | 2011-06-14 | 2012-12-19 | 湘潭大学 | Method for diagnosing faults of wind speed sensor at wind power plant based on spatial relevancy |
| CN103018660A (en) * | 2012-12-25 | 2013-04-03 | 重庆邮电大学 | Multi-fault intelligent diagnosing method for artificial circuit utilizing quantum Hopfield neural network |
-
2013
- 2013-07-02 CN CN201310272937XA patent/CN103323228A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030154051A1 (en) * | 2002-02-13 | 2003-08-14 | Kabushiki Kaisha Toshiba | Method and system for diagnosis of plant |
| CN1514209A (en) * | 2003-08-01 | 2004-07-21 | 重庆大学 | Rotary machine failure intelligent diagnosis method and device |
| CN1811367A (en) * | 2006-03-03 | 2006-08-02 | 西安交通大学 | Integrated supporting vector machine mixed intelligent diagnosing method for mechanical fault |
| CN102830250A (en) * | 2011-06-14 | 2012-12-19 | 湘潭大学 | Method for diagnosing faults of wind speed sensor at wind power plant based on spatial relevancy |
| CN103018660A (en) * | 2012-12-25 | 2013-04-03 | 重庆邮电大学 | Multi-fault intelligent diagnosing method for artificial circuit utilizing quantum Hopfield neural network |
Non-Patent Citations (5)
| Title |
|---|
| 何正嘉 等: "《机械故障诊断理论及应用》", 30 June 2010, 高等教育出版社, article "经验模式分解", pages: 74-83 * |
| 宋光明: "《爆破振动小波包分析理论与应用研究》", 31 July 2008, 国防科技大学出版社, article "小波包分析技术", pages: 20-30 * |
| 杨志伊 等: "《设备状态监测与故障诊断》", 30 June 2006, 中国计划出版社, article "专家系统与故障树分析", pages: 7-8 * |
| 赵洪波: "《岩土力学与工程中的支持向量机分析》", 30 June 2008, 煤炭工业出版社, article "支持向量机", pages: 15-31 * |
| 雷亚国 等: "混合智能故障诊断与预示技术的应用进展", 《振动与冲击》, vol. 30, no. 9, 31 December 2011 (2011-12-31), pages 129 - 135 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103575525A (en) * | 2013-11-18 | 2014-02-12 | 东南大学 | Intelligent diagnosis method for mechanical fault of circuit breaker |
| CN107709700A (en) * | 2015-05-13 | 2018-02-16 | 科诺科菲利浦公司 | Drill big data analytic approach engine |
| CN106198000A (en) * | 2016-07-11 | 2016-12-07 | 太原理工大学 | A kind of rocker arm of coal mining machine gear failure diagnosing method |
| CN106530082A (en) * | 2016-10-25 | 2017-03-22 | 清华大学 | Stock predication method and stock predication system based on multi-machine learning |
| CN106897740A (en) * | 2017-02-17 | 2017-06-27 | 重庆邮电大学 | EEMD DFA feature extracting methods under Human bodys' response system based on inertial sensor |
| CN108361020B (en) * | 2018-04-03 | 2021-04-23 | 中煤科工集团西安研究院有限公司 | Virtual instrument-based diagnosis and protection device and method for tunnel drilling machine |
| CN108361020A (en) * | 2018-04-03 | 2018-08-03 | 中煤科工集团西安研究院有限公司 | Underground drill rig diagnosis protective device and method based on virtual instrument |
| CN109117959A (en) * | 2018-06-20 | 2019-01-01 | 中译语通科技（青岛）有限公司 | A kind of artificial intelligence automatic recognition system and method based on intelligent operation platform |
| CN109035836A (en) * | 2018-08-14 | 2018-12-18 | 青岛海信网络科技股份有限公司 | A kind of transit equipment operational system |
| CN110276372A (en) * | 2019-05-08 | 2019-09-24 | 复变时空(武汉)数据科技有限公司 | Fuel battery engines method for diagnosing faults based on cloud platform |
| CN110276372B (en) * | 2019-05-08 | 2022-02-11 | 复变时空(武汉)数据科技有限公司 | Fuel cell engine fault diagnosis method based on cloud platform |
| CN112082639A (en) * | 2019-06-14 | 2020-12-15 | 现代自动车株式会社 | Engine state diagnosis method and diagnosis modeling method thereof |
| CN111596230A (en) * | 2020-06-11 | 2020-08-28 | 贵州中烟工业有限责任公司 | Method for establishing electrical troubleshooting model |
| CN111596230B (en) * | 2020-06-11 | 2022-07-15 | 贵州中烟工业有限责任公司 | Method for establishing electrical troubleshooting model |
| CN112014094A (en) * | 2020-09-03 | 2020-12-01 | 盾构及掘进技术国家重点实验室 | Shield tunneling machine main driving performance monitoring and repairing method |
| CN112434930A (en) * | 2020-11-20 | 2021-03-02 | 中国地质大学（武汉） | Fault diagnosis method, system and equipment in drilling process |
| CN112434930B (en) * | 2020-11-20 | 2023-08-08 | 中国地质大学（武汉） | Drilling process fault diagnosis method, system and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103323228A (en) | Mining drill fault intelligent identification method | |
| CN111999657B (en) | Method for evaluating driving mileage of lithium ion battery of electric vehicle in residual life | |
| CN110334764B (en) | Rotary machine intelligent fault diagnosis method based on integrated depth self-encoder | |
| CN102435910B (en) | Power electronic circuit health monitoring method based on support vector classification | |
| CN103995237A (en) | Satellite power supply system online fault diagnosis method | |
| CN101634605B (en) | Intelligent gearbox fault diagnosis method based on mixed inference and neural network | |
| CN110779746A (en) | Diagnosis method for improving composite fault of deep sparse self-encoder network rotating machinery | |
| CN108256556A (en) | Wind-driven generator group wheel box method for diagnosing faults based on depth belief network | |
| CN105466693B (en) | The pre- diagnostic method of Fault of Diesel Fuel System based on gray model | |
| CN103018660B (en) | Multi-fault intelligent diagnosing method for artificial circuit utilizing quantum Hopfield neural network | |
| CN111504635B (en) | Planetary gear fault diagnosis method based on differential evolution probability neural network | |
| CN109389325B (en) | Method for evaluating state of electronic transformer of transformer substation based on wavelet neural network | |
| CN109827777A (en) | Rolling bearing fault prediction technique based on Partial Least Squares extreme learning machine | |
| CN112270312B (en) | Fan bearing fault diagnosis method, system, computer equipment and storage medium | |
| CN104569694B (en) | Electric signal feature extraction and recognition system oriented to aircraft flying process | |
| CN102054179A (en) | Online state monitoring and fault diagnosis device and method for rotary machine | |
| CN102722471B (en) | Fuzzy relation matrix generating method based on comprehensive correlation matrix | |
| CN106198000A (en) | A kind of rocker arm of coal mining machine gear failure diagnosing method | |
| CN105677791A (en) | Method and system used for analyzing operating data of wind generating set | |
| CN116226646B (en) | Method, system, equipment and medium for predicting health state and residual life of bearing | |
| CN104793124A (en) | Switched circuit fault diagnosis method based on wavelet transformation and ICA (independent component analysis) feature extraction | |
| CN105137354A (en) | Motor fault detection method based on nerve network | |
| Lu et al. | Early fault warning and identification in condition monitoring of bearing via wavelet packet decomposition coupled with graph | |
| Du et al. | A hybrid transfer learning method for fault diagnosis of machinery under variable operating conditions | |
| CN104280253A (en) | Immune detector based fault diagnosis method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 710077 Xi'an high tech Zone, Shaanxi Jin Industry Road, No. 82 Applicant after: Xi'an Research Institute, CCTEG Address before: 710077 Xi'an high tech Zone, Shaanxi Jin Industry Road, No. 82 Applicant before: China Coal Technology & Engineering Group Xi'an Research Institute |
|
| COR | Change of bibliographic data |
Free format text: CORRECT: APPLICANT; FROM: CHINA COAL TECHNOLOGY + ENGINEERING GROUP XI'AN RESEARCH INSTITUTE TO: XI'AN RESEARCH INSTITUTE OF CHINA COAL TECHNOLOGY + ENGINEERING GROUP CO., LTD. |
|
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130925 |