CN103063251B - Failure recognition method based on engineering machinery - Google Patents
Failure recognition method based on engineering machinery Download PDFInfo
- Publication number
- CN103063251B CN103063251B CN201210577855.1A CN201210577855A CN103063251B CN 103063251 B CN103063251 B CN 103063251B CN 201210577855 A CN201210577855 A CN 201210577855A CN 103063251 B CN103063251 B CN 103063251B
- Authority
- CN
- China
- Prior art keywords
- characteristic
- fault
- engineering machinery
- primitive character
- failure
- 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.)
- Expired - Fee Related
Links
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a failure recognition method based on engineering machinery. The failure recognition method includes following steps that (1) common failures in the engineering machinery are listed to form a failure set A; (2) the failure collection A is defined as a characteristic set B, and each characteristic element bi of the characteristic set B is provided with threshold value; (3) characteristic elements bi of the characteristic set B and failure elements ai of the failure set A are analyzed in a correlation mode; (4) a frequency converter or a sensor which is internally arranged in the engineering machinery is utilized to monitor an intrinsic parameter and an external parameter of the engineering machinery in a real-time mode, namely, the characteristic elements bi; (5) failure recognition is conducted. The characteristic elements which are collected by the frequency converter or the sensor in the process of operation of the engineering machinery are adopted to be used as a breakthrough point, correlation of the fault elements are built, correlation coefficient is confirmed, and the correlation coefficient is used as an index of optimization of failure recognition. Efficiency and accuracy of the fault recognition are greatly improved, recognition rate of the fault is up to 80%, and the accuracy rate is up to 85%.
Description
Technical field
The present invention relates to a kind of fault recognition method, especially relate to a kind of fault recognition method based on engineering machinery.
Background technology
Engineering machinery is comparatively complicated mechanical-electrical-hydraulic integration system, and along with the develop rapidly of science and technology, engineering machinery tends to high speed, high power, high reliability, high-intelligentization gradually.In the process, because the working condition of engineering machinery is relatively complicated, working environment is also relatively severe, therefore inevitably produces various fault every now and then.Now, usually need equipment conveying to specify maintenance store to producer, carried out diagnosis and the process of fault by special technical staff by detecting instrument, like this, not only waste the valuable time, also add the cost of maintenance of equipment.Now, can effectively be addressed this problem by a kind of automatic fault recognition system integrated in the inside of engineering machinery.
Chinese patent 201110208816.X discloses a kind of long-distance intelligent Analysis Service system based on technology of Internet of things for engineering machinery, first it will gather fault message, by data collecting system, characteristic information relevant for engineering equipment and above-mentioned fault message are contrasted again, for the fault message had in database, system can identify automatically, and will be sent to analysis expert knowledge base for the raw information of failing automatically to identify and analyze.This method to a certain extent can the Remote Fault Diagnosis of quick solution engineering machinery, but the automatic discrimination of fault is too low, and Stability and dependability can not be guaranteed.
Summary of the invention
The technical problem to be solved in the present invention is, overcomes the above-mentioned defect that prior art exists, provides a kind of fault recognition method based on engineering machinery.
The technical solution adopted for the present invention to solve the technical problems is given and is:
Based on a fault recognition method for engineering machinery, its Fault Identification step is as follows:
1) list of engineering machinery most common failure is formed failure collection A;
2) inner parameter that can be recorded by frequency converter or sensor in engineering machinery and external parameter are defined as characteristic set B, to each characteristic element b in characteristic set B
ithreshold value is set;
3) to the characteristic element b in characteristic set B
iwith the fault element a in failure collection A
ido correlation analysis, calculate relative coefficient between the two, each fault element a
ione or two above characteristic element b corresponding
i, and using described relative coefficient as characteristic element b
iproperty value, be stored in primitive character set B
0in, become primitive character element b
0i, primitive character set B
0the attached set of characteristic set B, primitive character set B
0and there is one-to-one relationship between characteristic set B element, to primitive character set B
0in each primitive character element b
0isecure threshold is set, once primitive character element value b
0iexceed described secure threshold, namely engineering machinery may produce fault;
4) inner parameter and external parameter, i.e. the characteristic element b of the frequency converter be built in engineering machinery or the real-time supervision control engineering machinery of sensor difference is utilized
i;
5) as the characteristic element b of Real-Time Monitoring
iexceed characteristic element b
ithreshold value time, by characteristic element b
iproperty value find primitive character set B
0in corresponding primitive character element b
0i, be namely the fault element a in the corresponding failure collection A of index fast searching with relative coefficient
i, then by oppositely searching namely by fault element a
ifind characteristic of correspondence element b in characteristic set B
i, with fault element a
icharacteristic of correspondence element b
iquantity be one or more, realize the characteristic element b collected according to frequency converter and sensor
i(i.e. the inner parameter of engineering machinery or external parameter), to by oppositely searching one or more characteristic element b obtained
iwith fault element a
icorresponding relation whether set up and verify one by one, namely to by oppositely searching each characteristic element b obtained
iwith corresponding fault element a
ibetween relative coefficient whether exceeded secure threshold and verified one by one: when to by oppositely searching a certain characteristic element b obtained
iwith corresponding fault element a
ibetween relative coefficient exceeded or close to secure threshold time, the characteristic element b be now verified is described
iwith fault element a
icorresponding relation set up, Fault Identification completes, export fault diagnosis result; Otherwise, namely think the characteristic element b be now verified
iwith fault element a
icorresponding relation be false, and start by oppositely searching another feature element b obtained
icontrast, and so forth, until identify the fault of engineering machinery.
Described step 2) in, to each characteristic element b in characteristic set B
ithe threshold value arranged is determined by the experiment of equipment vendors and engineering experience.
In described step 3), described correlation analysis be in statistics a very common and basic data statistical analysis method with theoretical.
In described step 3), to primitive character set B
0in each primitive character element b
0iarrange secure threshold to refer to: primitive character element b
0ione group of numerical value, i.e. representation feature element b
iwith fault element a
ibetween relative coefficient, the size of relative coefficient is directly connected to interactional size degree between characteristic element bi and fault element ai, primitive character element b when described secure threshold is machinery normal work
0ithe value that can not exceed, once exceed, equipment will have fault to exist, and the setting of described secure threshold is the result drawn by many experiments by mechanical producer.
Described step 2) and step 4) in, described inner parameter is recorded by frequency converter, comprises electric current, voltage, frequency, electromagnetism intensity etc.; External parameter is recorded by sensor, comprises displacement, speed, moment of torsion, pressure, flow rate etc.
The present invention adopts characteristic element that in engineering machinery running, frequency converter and sensor gather as break-through point, set up the correlation of itself and fault element and determine its coefficient correlation, using this coefficient correlation as the index optimizing Fault Identification, substantially increase efficiency and the accuracy rate of Fault Identification, the discrimination of fault is up to 80%, and accuracy rate is up to 85%.
Accompanying drawing explanation
Fig. 1 is the Fault Identification procedural block diagram based on engineering machinery.
Detailed description of the invention
Below in conjunction with drawings and Examples, the present invention is described in further detail.
Described a kind of fault recognition method based on engineering machinery, its Fault Identification step is as follows:
1) list of engineering machinery most common failure is formed failure collection A;
2) inner parameter that can be recorded by frequency converter or sensor in engineering machinery and external parameter are defined as characteristic set B, to each characteristic element b in characteristic set B
ithreshold value is set;
3) to the characteristic element b in characteristic set B
iwith the fault element a in failure collection A
ido correlation analysis, calculate relative coefficient between the two, each fault element a
icorresponding one or more characteristic element b
i, and using described relative coefficient as characteristic element b
iproperty value, be stored in primitive character set B
0in, become primitive character element b
0i, primitive character set B
0the attached set of characteristic set B, primitive character set B
0and there is one-to-one relationship between characteristic set B element, to primitive character set B
0in each primitive character element b
0isecure threshold is set, once primitive character element value b
0iexceed described secure threshold, namely engineering machinery may produce fault;
4) inner parameter and external parameter, i.e. the characteristic element b of the frequency converter be built in engineering machinery or the real-time supervision control engineering machinery of sensor difference is utilized
i;
5) as the characteristic element b of Real-Time Monitoring
iexceed characteristic element b
ithreshold value time, by characteristic element b
iproperty value find primitive character set B
0in corresponding primitive character element b
0i, be namely the fault element a in the corresponding failure collection A of index fast searching with relative coefficient
i, then by oppositely searching namely by fault element a
ifind characteristic of correspondence element b in characteristic set B
i, with fault element a
icharacteristic of correspondence element b
iquantity be one or more, realize the characteristic element b collected according to frequency converter and sensor
i(i.e. the inner parameter of engineering machinery or external parameter), to by oppositely searching one or more characteristic element b obtained
iwith fault element a
icorresponding relation whether set up and verify one by one, namely to by oppositely searching each characteristic element b obtained
iwith corresponding fault element a
ibetween relative coefficient whether exceeded secure threshold and verified one by one: when to by oppositely searching a certain characteristic element b obtained
iwith corresponding fault element a
ibetween relative coefficient when having exceeded secure threshold, the characteristic element b be now verified is described
iwith fault element a
icorresponding relation set up, Fault Identification completes, export fault diagnosis result; Otherwise, namely think the characteristic element b be now verified
iwith fault element a
icorresponding relation be false, and start by oppositely searching another feature element b obtained
icontrast, and so forth, until identify the fault of engineering machinery.
Described step 2) in, to each characteristic element b in characteristic set B
ithe threshold value arranged is determined by the experiment of equipment vendors and engineering experience.
In described step 3), described correlation analysis be in statistics a very common and basic data statistical analysis method with theoretical.
In described step 3), to primitive character set B
0in each primitive character element b
0iarrange secure threshold to refer to: primitive character element b
0ione group of numerical value, i.e. representation feature element b
iwith fault element a
ibetween relative coefficient, the size of relative coefficient is directly connected to interactional size degree between characteristic element bi and fault element ai, primitive character element b when described secure threshold is machinery normal work
0ithe value that can not exceed, once exceed, equipment will have fault to exist, and the setting of described secure threshold is the result drawn by many experiments by mechanical producer.
Described step 2) and step 4) in, described inner parameter is recorded by frequency converter, comprises electric current, voltage, frequency, electromagnetism intensity etc.; External parameter is recorded by sensor, comprises displacement, speed, moment of torsion, pressure, flow rate etc.
Fault recognition method based on engineering machinery of the present invention substantially increases efficiency and the accuracy rate of Fault Identification, and the discrimination of fault is up to 80%, and accuracy rate is up to 85%.
Claims (2)
1. based on a fault recognition method for engineering machinery, it is characterized in that, fault recognition method comprises the steps:
1) list of engineering machinery most common failure is formed failure collection A;
2) inner parameter that can be recorded by frequency converter or sensor in engineering machinery and external parameter are defined as characteristic set B, to each characteristic element b in characteristic set B
ithreshold value is set;
3) to the characteristic element b in characteristic set B
iwith the fault element a in failure collection A
ido correlation analysis, calculate relative coefficient between the two, each fault element a
icorresponding one or more characteristic element b
i, and using described relative coefficient as characteristic element b
iproperty value, be stored in primitive character set B
0in, become primitive character element b
0i, primitive character set B
0the attached set of characteristic set B, primitive character set B
0and there is one-to-one relationship between characteristic set B element, to primitive character set B
0in each primitive character element b
0isecure threshold is set, once primitive character element value b
0iexceed described secure threshold, namely engineering machinery may produce fault;
4) inner parameter and external parameter, i.e. the characteristic element b of the frequency converter be built in engineering machinery or the real-time supervision control engineering machinery of sensor difference is utilized
i;
5) as the characteristic element b of Real-Time Monitoring
iexceed characteristic element b
ithreshold value time, by characteristic element b
iproperty value find primitive character set B
0in corresponding primitive character element b
0i, be namely the fault element a in the corresponding failure collection A of index fast searching with relative coefficient
i, then by oppositely searching namely by fault element a
ifind characteristic of correspondence element b in characteristic set B
i, with fault element a
icharacteristic of correspondence element b
iquantity be one or more, realize the characteristic element b collected according to frequency converter and sensor
i, i.e. the inner parameter of engineering machinery or external parameter, to by oppositely searching one or more characteristic element b obtained
iwith fault element a
icorresponding relation whether set up and verify one by one, namely to by oppositely searching each characteristic element b obtained
iwith corresponding fault element a
ibetween relative coefficient whether exceeded secure threshold and verified one by one: when to by oppositely searching a certain characteristic element b obtained
iwith corresponding fault element a
ibetween relative coefficient exceeded or close to secure threshold time, the characteristic element b be now verified is described
iwith fault element a
icorresponding relation set up, Fault Identification completes, export fault diagnosis result; Otherwise, namely think the characteristic element b be now verified
iwith fault element a
icorresponding relation be false, and start by oppositely searching another feature element b obtained
icontrast, and so forth, until identify the fault of engineering machinery.
2. the fault recognition method based on engineering machinery according to claim 1, is characterized in that, described step 2) and step 4) in, described inner parameter is recorded by frequency converter, comprises electric current, voltage, frequency, electromagnetism intensity; External parameter is recorded by sensor, comprises displacement, speed, moment of torsion, pressure, flow rate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210577855.1A CN103063251B (en) | 2012-12-27 | 2012-12-27 | Failure recognition method based on engineering machinery |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210577855.1A CN103063251B (en) | 2012-12-27 | 2012-12-27 | Failure recognition method based on engineering machinery |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103063251A CN103063251A (en) | 2013-04-24 |
CN103063251B true CN103063251B (en) | 2015-03-25 |
Family
ID=48105975
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210577855.1A Expired - Fee Related CN103063251B (en) | 2012-12-27 | 2012-12-27 | Failure recognition method based on engineering machinery |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103063251B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104200288B (en) * | 2014-09-18 | 2017-03-15 | 山东大学 | A kind of equipment fault Forecasting Methodology based on dependency relation identification between factor and event |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102043900A (en) * | 2010-11-24 | 2011-05-04 | 河海大学 | Failure prediction method of rod pumping system based on indicator diagram |
CN102243497A (en) * | 2011-07-25 | 2011-11-16 | 江苏吉美思物联网产业股份有限公司 | Networking technology-based remote intelligent analysis service system used for engineering machinery |
CN102436524A (en) * | 2011-10-19 | 2012-05-02 | 清华大学 | Fuzzy reasoning method for soft fault diagnosis for analog circuit |
CN102662390A (en) * | 2012-04-26 | 2012-09-12 | 杭州电子科技大学 | Fault diagnosis method of random fuzzy fault characteristic fusion rotating mechanical device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6112150A (en) * | 1999-04-09 | 2000-08-29 | Cummins Engine Co Inc | Fault recognition system and method for an internal combustion engine |
-
2012
- 2012-12-27 CN CN201210577855.1A patent/CN103063251B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102043900A (en) * | 2010-11-24 | 2011-05-04 | 河海大学 | Failure prediction method of rod pumping system based on indicator diagram |
CN102243497A (en) * | 2011-07-25 | 2011-11-16 | 江苏吉美思物联网产业股份有限公司 | Networking technology-based remote intelligent analysis service system used for engineering machinery |
CN102436524A (en) * | 2011-10-19 | 2012-05-02 | 清华大学 | Fuzzy reasoning method for soft fault diagnosis for analog circuit |
CN102662390A (en) * | 2012-04-26 | 2012-09-12 | 杭州电子科技大学 | Fault diagnosis method of random fuzzy fault characteristic fusion rotating mechanical device |
Also Published As
Publication number | Publication date |
---|---|
CN103063251A (en) | 2013-04-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104932485A (en) | Railway track switch point machine fault prediction system and method | |
CN102226898B (en) | Method and device for controlling monitoring data to be put in storage in online monitoring system | |
CN103670373B (en) | Method and system for diagnosing faults of oil pumping unit | |
CN103439091A (en) | Method and system for early warning and diagnosing water turbine runner blade crack breakdown | |
CN103675355A (en) | Anemometer monitoring method and system | |
KR20210044655A (en) | Method of preserving the prediction of a device through distribution chart | |
CN110580492A (en) | Track circuit fault precursor discovery method based on small fluctuation detection | |
CN103439944A (en) | Intelligent fault diagnosis system and method for engineering machinery and engineering machinery | |
CN104533730A (en) | State monitoring system of wind generating set | |
CN105634796A (en) | Network device failure prediction and diagnosis method | |
CN106443433A (en) | Monitoring system and monitoring method for circuit breaker state based on divide-shut brake coil current | |
CN105321039A (en) | Disconnector online monitoring data management system and method | |
CN104506137A (en) | Equipment fault diagnosis method and apparatus | |
CN114215705A (en) | Wind turbine generator fault early warning method and system | |
CN116304928A (en) | Power supply equipment fault prediction method, device, equipment and storage medium | |
CN103675357A (en) | Anemometer fault warning method and system | |
CN103063251B (en) | Failure recognition method based on engineering machinery | |
CN116990619B (en) | Intelligent monitoring method of mine frequency conversion integrated machine | |
CN116859838B (en) | Early warning system for monitoring equipment operation condition | |
CN203321490U (en) | Wireless oil well intelligent monitoring terminal RTU | |
CN202091172U (en) | Device for monitoring state and analyzing reliability of gas compressor | |
CN116089843B (en) | New energy settlement data anomaly detection and early warning method based on data clustering | |
CN106483457A (en) | A kind of catalyst fault early warning method and prior-warning device | |
CN202937433U (en) | Diaphragm pump failure warning system based on vibration detection | |
CN104765311A (en) | Pumping well monitoring and early warning device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150325 Termination date: 20151227 |
|
EXPY | Termination of patent right or utility model |