Vibration Fault Diagnosis Method of Centrifugal Pump Based on EMD Complexity Feature and Least Square Support Vector Machine

• DOI: 10.1016/j.egypro.2012.02.191
• Publication Date: 2012-04-25T00:28:11Z
• Authors: Zhou Yunlong; Zhao Peng
• Keywords: 0209 industrial biotechnology; Energy(all); 0202 electrical engineering, electronic engineering, information engineering; Empirical Mode Decomposition; Least Square Support Vector Machine; 02 engineering and technology; centrifugal pump; fault diagnosis; complexity

AbstractAiming at the non-stationary and non-linearity characteristics of the vibration signals of centrifugal pump, a new method based on complexity feature of Empirical Mode Decomposition (EMD) and Least Square Support Vector Machine (LS-SVM) is put forward. First of all, the Empirical Mode Decomposition (EMD) method was used to decompose the vibration signals into a finite number of stationary Intrinsic Mode Functions (IMF), and then complexity features of each IMF is extracted as the fault characteristics vectors and served as input parameters of LS-SVM classifier to diagnosis fault. Application results showed that the proposed method is very effective, which can better extract the nonlinear features of the fault and more exactly diagnosis fault.