Intelligent Mechanical Fault Diagnosis Based on Multiwavelet Adaptive Threshold Denoising and MPSO

The condition diagnosis of rotating machinery depends largely on the feature analysis of vibration signals measured for the condition diagnosis. However, the signals measured from rotating machinery usually are nonstationary and nonlinear and contain noise. The useful fault features are hidden in the heavy background noise. In this paper, a novel fault diagnosis method for rotating machinery based on multiwavelet adaptive threshold denoising and mutation particle swarm optimization (MPSO) is proposed. Geronimo, Hardin, and Massopust (GHM) multiwavelet is employed for extracting weak fault features under background noise, and the method of adaptively selecting appropriate threshold for multiwavelet with energy ratio of multiwavelet coefficient is presented. The six nondimensional symptom parameters (SPs) in the frequency domain are defined to reflect the features of the vibration signals measured in each state. Detection index (DI) using statistical theory has been also defined to evaluate the sensitiveness of SP for condition diagnosis. MPSO algorithm with adaptive inertia weight adjustment and particle mutation is proposed for condition identification. MPSO algorithm effectively solves local optimum and premature convergence problems of conventional particle swarm optimization (PSO) algorithm. It can provide a more accurate estimate on fault diagnosis. Practical examples of fault diagnosis for rolling element bearings are given to verify the effectiveness of the proposed method.