Support vector machines based approach for fault diagnosis of valves in reciprocating pumps
| Autor: | Jianxun Tan, Junfeng Gao, Fengjin Zhong, Wengang Shi |
|---|---|
| Rok vydání: | 2003 |
| Předmět: |
Signal processing
Engineering business.industry ComputingMilieux_PERSONALCOMPUTING Condition monitoring Reciprocating pump Wavelet transform Pattern recognition Hardware_PERFORMANCEANDRELIABILITY Fault detection and isolation Wavelet packet decomposition Time–frequency analysis Support vector machine ComputingMethodologies_PATTERNRECOGNITION Computer Science::Sound Artificial intelligence business human activities |
| Zdroj: | IEEE CCECE2002. Canadian Conference on Electrical and Computer Engineering. Conference Proceedings (Cat. No.02CH37373). |
| DOI: | 10.1109/ccece.2002.1012999 |
| Popis: | Support vector machines (SVMs) represent an approach to pattern classification. The paper presents a SVMs based approach for fault diagnosis of valves in three-cylinder reciprocating pumps. The vibration signals collected from pumps are preprocessed with the wavelet packet transform and time-frequency information is extracted as the character vector for training mid testing the SVMs. To classify multiple fault modes of valves, a SVMs based multi-class classifier is constructed and used in the valve faults diagnosis. The results in experiments show that fault types and positions of faulty valves can be identified and diagnosed by the above method. Furthermore, compared with the results of a BP network, more excellent diagnosis accuracy indicates the potential of the SVMs techniques in machinery fault detection. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|