CN103743585A - Mechanical failure diagnosing method - Google Patents
Mechanical failure diagnosing method Download PDFInfo
- Publication number
- CN103743585A CN103743585A CN201310734953.6A CN201310734953A CN103743585A CN 103743585 A CN103743585 A CN 103743585A CN 201310734953 A CN201310734953 A CN 201310734953A CN 103743585 A CN103743585 A CN 103743585A
- Authority
- CN
- China
- Prior art keywords
- vibration signal
- vibration
- running
- mechanical
- 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
Images
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a mechanical failure diagnosing method. In an adjusted operation state of a mechanical device, by acquiring a vibrating signal of mechanical device in adjusted operation with a vibrating sensor deployed in advance and analyzing the vibrating signal, diagnosis and identification of mechanical device in adjusted operation are achieved. The mechanical failure diagnosing method analyzes the vibrating signal appearing in a high-speed operating process of the mechanical device and achieves fault detection so as to achieve fault detection while not stopping a tested mechanical device, thereby increasing efficiency of fault detection.
Description
Technical field
The present invention relates to a kind of high mechanical equipment fault detection method to running up, especially by carry out the fault detection method of Measurement and analysis to adjusting running device vibration signal.
Background technology
At present; the plant equipment running up is in operational process; may there are some potential failure risks; and this class high speed running apparatus is shut down; carry out again the fault detect of equipment; although existing quite a few fault in can discovering device, this detection method can reduce the service efficiency of plant equipment on the one hand.High speed running apparatus is at the detected fault type of stationary state on the other hand, there is certain difference with the failure mode showing and type under high-speed cruising state, especially some potential failure risks, under static state be difficult to be detected, only, when equipment is running up, just likely show out of order feature.A kind of effective approach of the method therefore detecting towards high speed machine equipment failure is by allowing plant equipment carry out the detection of fault under the environment that runs up.
The current approach that plant equipment is run up and carries out fault detect under condition, mainly that the external features such as the vibration that shows under the condition of running up by plant equipment, noise are analyzed, this class physical signalling is extracted and signature analysis, and then whether exist failure risk to differentiate to the plant equipment running up.The precision and the accuracy that in order to improve mechanical equipment fault, detect, need to carry out deep research to the method for high speed machine device signal analysis and treatment technology, designs and have high-resolution, to be easy to realization mechanical equipment fault detection method.
Summary of the invention
The defect that the present invention seeks to exist for prior art provides a kind of accurately effective fault detection method, by the analysis to mechanical oscillation signal, can solve most application demands that can produce the mechanical equipment fault detection of vibration signal in the process of running up.
The present invention for achieving the above object, adopt following technical scheme: a kind of mechanical failure diagnostic method, under the state in machinery adjustment running, utilize the vibration transducer of disposing in advance to obtain the mechanical vibration signal of adjusting running, then by the analysis of vibration signal and extraction are realized adjusting diagnosis and the identification of conveyer tool fault.
Further, it comprises following concrete diagnosis algorithm:
1), start plant equipment and make its state that runs up in normally;
2), by being deployed in the vibration transducer in plant equipment, the original vibration signal of collection machinery equipment in the process of running up;
3) the described vibration signal, vibration transducer being collected carries out data fusion, be about to the vibration signal that in plant equipment, two adjacent vibration transducers of any place collect and sue for peace and average, obtain this and locate metastable Mean Oscillation signal value;
4), resulting everywhere vibration signal value is carried out to wavelet transformation, obtain after conversion the running up eigenwert of vibration signal;
5), extract at least one thousand groups of steps 2) in original vibration signal, and the run up vibration signal of machinery when variety classes fault, the numerical value of all vibration signals is carried out respectively to wavelet transformation, and resulting result is carried out to the structure of C4.5 categorised decision tree;
6), after completing the structure of C4.5 categorised decision tree, by the vibration signal that the actual mechanical high-speed collecting turns round each time, through wavelet transformation, obtain actual vibration signal characteristic value, then utilize C4.5 categorised decision tree to classify to resulting actual vibration signal characteristic value;
7), by C4.5 categorised decision, set given actual vibration signal characteristic value is carried out to Classification and Identification, provide the result of identification;
8), according to initial C4.5 categorised decision tree training result table, table look-up and obtain the state that C4.5 categorised decision is set the corresponding high speed machine running of each classification situation, and the concrete fault type that contains of this state.
Beneficial effect of the present invention: 1, the mechanical fault detection method of the present invention's design; by the vibration signal showing in mechanical high-speed operation process is analyzed; and realize the detection of fault; can realize detected plant equipment without shutting down the detection that realizes fault, improve the efficiency of fault detect.
2, the fault detection method of the present invention's design, by the vibration signal to mechanical, gather and wavelet transformation, can effectively extract the fault-signal feature comprising in vibration signal, and can amplify with separated fault-signal feature, contribute to the identification of mechanical fault and classification.
3, the mechanical fault detection method of the present invention's design is trained by predefined a large amount of fault-signals and data when carrying out failure modes, has obtained the fault grader based on C4.5 categorised decision tree.This categorised decision device is with respect to simple manual sort, or carry out by rule of thumb failure modes, there is higher failure modes accuracy and objectivity, can either guarantee that fault detection method has higher precision, also can guarantee that this detection method has stronger versatility simultaneously.
Accompanying drawing explanation
Fig. 1 is fault detection method process flow diagram of the present invention.
Fig. 2 is that fault-signal measurement data of the present invention merges schematic diagram.
Fig. 3 is the data de-noising process flow diagram after wavelet transformation of the present invention.
Fig. 4 is the process flow diagram that decision tree of the present invention generates.
Embodiment
Design concept of the present invention is to gather by the vibration signal in high speed running apparatus operational process, obtains the vibration signal characteristics of adjusting running device, and vibration signal is carried out to wavelet transformation, extracts the feature in vibration signal.And set by designing special mechanical oscillation signal categorised decision, realize the classification output to mechanical oscillation signal, thereby solve the application demand that the mechanical equipment fault to running up detects.And because exported vibration signal is classified, once therefore find fault, not only can judge the plant equipment running up and whether have fault, also can provide the fault type that this equipment exists simultaneously.
Known according to Fig. 1-Fig. 4, the present invention is specifically related to a kind of mechanical failure diagnostic method, under the state in machinery adjustment running, utilize the vibration transducer of disposing in advance to obtain the mechanical vibration signal of adjusting running, then by the analysis of vibration signal and extraction are realized adjusting diagnosis and the identification of conveyer tool fault.
It comprises following concrete diagnosis algorithm:
1), start plant equipment and make its state that runs up in normally;
2), by being deployed in the vibration transducer in plant equipment, the original vibration signal of collection machinery equipment in the process of running up;
3) the described vibration signal, vibration transducer being collected carries out data fusion, be about to the vibration signal that in plant equipment, two adjacent vibration transducers of any place collect and sue for peace and average, obtain this and locate metastable Mean Oscillation signal value;
4), resulting everywhere vibration signal value is carried out to wavelet transformation, obtain after conversion the running up eigenwert of vibration signal;
5), extract at least one thousand groups of steps 2) in original vibration signal, and the run up vibration signal of machinery when variety classes fault, the numerical value of all vibration signals is carried out respectively to wavelet transformation, and resulting result is carried out to the structure of C4.5 categorised decision tree;
6), after completing the structure of C4.5 categorised decision tree, by the vibration signal that the actual mechanical high-speed collecting turns round each time, through wavelet transformation, obtain actual vibration signal characteristic value, then utilize C4.5 categorised decision tree to classify to resulting actual vibration signal characteristic value;
7), by C4.5 categorised decision, set given actual vibration signal characteristic value is carried out to Classification and Identification, provide the result of identification;
8), according to initial C4.5 categorised decision tree training result table, table look-up and obtain the state that C4.5 categorised decision is set the corresponding high speed machine running of each classification situation, and the concrete fault type that contains of this state.
The foregoing is only preferred embodiment of the present invention, in order to limit the present invention, within the spirit and principles in the present invention not all, any modification of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (2)
1. a mechanical failure diagnostic method, it is characterized in that, under the state in machinery adjustment running, utilize the vibration transducer of disposing in advance to obtain the mechanical vibration signal of adjusting running, then by the analysis of vibration signal and extraction are realized adjusting diagnosis and the identification of conveyer tool fault.
2. a kind of mechanical failure diagnostic method as claimed in claim 1, it comprises following concrete diagnosis algorithm:
1), start plant equipment and make its state that runs up in normally;
2), by being deployed in the vibration transducer in plant equipment, the original vibration signal of collection machinery equipment in the process of running up;
3) the described vibration signal, vibration transducer being collected carries out data fusion, be about to the vibration signal that in plant equipment, two adjacent vibration transducers of any place collect and sue for peace and average, obtain this and locate metastable Mean Oscillation signal value;
4), resulting everywhere vibration signal value is carried out to wavelet transformation, obtain after conversion the running up eigenwert of vibration signal;
5), extract at least one thousand groups of steps 2) in original vibration signal, and the run up vibration signal of machinery when variety classes fault, the numerical value of all vibration signals is carried out respectively to wavelet transformation, and resulting result is carried out to the structure of C4.5 categorised decision tree;
6), after completing the structure of C4.5 categorised decision tree, by the vibration signal that the actual mechanical high-speed collecting turns round each time, through wavelet transformation, obtain actual vibration signal characteristic value, then utilize C4.5 categorised decision tree to classify to resulting actual vibration signal characteristic value;
7), by C4.5 categorised decision, set given actual vibration signal characteristic value is carried out to Classification and Identification, provide the result of identification;
8), according to initial C4.5 categorised decision tree training result table, table look-up and obtain the state that C4.5 categorised decision is set the corresponding high speed machine running of each classification situation, and the concrete fault type that contains of this state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310734953.6A CN103743585A (en) | 2013-12-27 | 2013-12-27 | Mechanical failure diagnosing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310734953.6A CN103743585A (en) | 2013-12-27 | 2013-12-27 | Mechanical failure diagnosing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103743585A true CN103743585A (en) | 2014-04-23 |
Family
ID=50500623
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310734953.6A Pending CN103743585A (en) | 2013-12-27 | 2013-12-27 | Mechanical failure diagnosing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103743585A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105628403A (en) * | 2016-03-14 | 2016-06-01 | 重庆工商大学 | Damper fault detection method and system |
| CN106840379A (en) * | 2017-03-08 | 2017-06-13 | 潘小胜 | A kind of failure analysis methods of mechanical oscillation signal |
| CN107132063A (en) * | 2017-04-12 | 2017-09-05 | 柳州易农科技有限公司 | A kind of agricultural machinery fault finding system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010066188A (en) * | 2008-09-12 | 2010-03-25 | Mitsubishi Heavy Ind Ltd | Method and device for diagnosing failure of rotating body of industrial vehicle |
| CN101788378A (en) * | 2009-01-23 | 2010-07-28 | 西门子公司 | Mechanical failure diagnostic method and device |
| KR20110122483A (en) * | 2010-05-04 | 2011-11-10 | 시그널링크 주식회사 | Built-in vibration monitor having order spectrum analysis function and fault diagnosis method of variable rotating speed machine using the monitor |
| CN102539159A (en) * | 2010-12-24 | 2012-07-04 | 中国船舶研究设计中心 | Fault diagnosis method for valve mechanism of diesel engine |
-
2013
- 2013-12-27 CN CN201310734953.6A patent/CN103743585A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010066188A (en) * | 2008-09-12 | 2010-03-25 | Mitsubishi Heavy Ind Ltd | Method and device for diagnosing failure of rotating body of industrial vehicle |
| CN101788378A (en) * | 2009-01-23 | 2010-07-28 | 西门子公司 | Mechanical failure diagnostic method and device |
| KR20110122483A (en) * | 2010-05-04 | 2011-11-10 | 시그널링크 주식회사 | Built-in vibration monitor having order spectrum analysis function and fault diagnosis method of variable rotating speed machine using the monitor |
| CN102539159A (en) * | 2010-12-24 | 2012-07-04 | 中国船舶研究设计中心 | Fault diagnosis method for valve mechanism of diesel engine |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105628403A (en) * | 2016-03-14 | 2016-06-01 | 重庆工商大学 | Damper fault detection method and system |
| CN106840379A (en) * | 2017-03-08 | 2017-06-13 | 潘小胜 | A kind of failure analysis methods of mechanical oscillation signal |
| CN107132063A (en) * | 2017-04-12 | 2017-09-05 | 柳州易农科技有限公司 | A kind of agricultural machinery fault finding system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cui et al. | Quantitative trend fault diagnosis of a rolling bearing based on Sparsogram and Lempel-Ziv | |
| CN106526400B (en) | The earth fault diagnostic method and device of DC600V power supply system of train | |
| CN106447040B (en) | Mechanical equipment health state evaluation method based on Heterogeneous Multi-Sensor Data fusion | |
| CN202083555U (en) | System for extracting and diagnosing fault feature of gasoline engine | |
| CN104132250B (en) | A kind of pipe leakage characteristic vector pickup method based on improvement wavelet packet | |
| CN102226740A (en) | Bearing fault detection method based on manner of controlling stochastic resonance by external periodic signal | |
| CN103149029B (en) | Cepstrum identification aeromotor is utilized to turn quiet method of touching position of rubbing | |
| CN107064298B (en) | The laser detecting method of blower blade cracks in a kind of operation | |
| CN104408477A (en) | Key part fault detection method and device | |
| CN101793892A (en) | On-line detection method of oil contamination in hydraulic system | |
| CN103674234A (en) | State early warning method and system for abnormal vibration of wind generating set | |
| CN103743585A (en) | Mechanical failure diagnosing method | |
| CN203009263U (en) | Air compressor performance test board for vehicle | |
| CN107576380A (en) | A kind of three-dimensional vibrating Modulation recognition method towards Φ OTDR techniques | |
| Verma et al. | Finding sensitive sensor positions under faulty condition of reciprocating air compressors | |
| CN104359689A (en) | Method and device for testing brake performance of motor train units | |
| CN103758742A (en) | Plunger pump failure analysis system based on double-class feature fusion diagnosis | |
| CN103821749B (en) | On-line diagnosis method of stall and surge of axial fan | |
| CN103743477B (en) | A kind of mechanical fault detection diagnostic method and equipment thereof | |
| CN104457973A (en) | Vibration signal detection and fault diagnosis system in shield tunneling process | |
| CN105987809A (en) | Centrifugal-compressor semi-open-type impeller crack detection method based on random resonance | |
| CN107037133A (en) | A kind of combination sound emission and the machining state monitoring method of current detecting | |
| CN112781721B (en) | Intelligent noise acquisition method and intelligent noise acquisition device of mobile inspection platform | |
| CN103821750A (en) | Current-based method for monitoring and diagnosing stall speed and surge of ventilator | |
| CN108303465A (en) | A kind of fault detection method and system based on machine vibration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140423 |