WPT-SVMs based approach for fault detection of valves in reciprocating pumps

Proceedings of the American Control Conference - Tập 6 - Trang 4566-4570 vol.6 - 2002
Fujun He1, Wengang Shi2
1Department of Mechanical Engineering, Daqing Petroleum Institute, Anda, Heilongjiang, China
2Department of Astronautics and Mechanics, Harbin Institute of Technology, Harbin, China

Tóm tắt

This paper presents a novel approach for fault detection of valves in three-cylinder reciprocating pumps. Since the vibration signals collected from pumps apparently show the existence of non-stationary signals and the interference of neighboring valves, the wavelet packet transform (WPT) is introduced as a preprocessing means of extracting time-frequency information from vibration signals to obtain the fault characteristics of the valves. To classify multiple fault modes of valves, a support vector machines (SVMs) based multi-class classifier is constructed and used in the valve faults detection. The results in experiments prove that fault types and positions of faulty valves can be identified and diagnosed by the above method. Furthermore, compared with the results using an artificial neural network, more excellent diagnosis accuracy indicates the potential of the SVMs techniques in machinery fault detection.

Từ khóa

#Fault detection #Valves #Fault diagnosis #Pumps #Interference #Wavelet packets #Wavelet transforms #Data mining #Time frequency analysis #Support vector machines

Tài liệu tham khảo

10.1007/BF00994018 10.1007/978-1-4757-2440-0 10.1109/CVPR.1997.609310 10.1109/18.57199 10.1115/1.2893984 10.1109/ICIPS.1997.669280 10.1080/10402009108982040 10.1023/A:1009715923555 10.1109/ICSMC.1993.384947 10.1006/mssp.1997.0090 10.1016/S0043-1648(98)00165-3 10.1115/1.2894007 10.1115/1.2818515 li, 1998, Detection of common motor bearing faults using frequency-domain vibration signals and a neural network based approach, Proc of the 1998 American Control Conference Philadelphia Pennsylvania USA June 24-26, 2032