The vibration signals are usually characterized by nonstationary, nonlinearity, and high frequency shocks, and the redundant features degrade the performance of fault diagnosis methods. To deal with the problem, a novel fault diagnosis approach for rotating machinery is presented by combining improved local mean decomposition (LMD) with support vector machine–recursive feature elimination with minimum redundancy maximum relevance (SVM-RFE-MRMR). Firstly, an improved LMD method is developed to decompose vibration signals into a subset of amplitude modulation/frequency modulation (AM-FM) product functions (PFs). Then, time and frequency domain features are extracted from the selected PFs, and the complicated faults can be thus identified efficiently. Due to degradation of fault diagnosis methods resulting from redundant features, a novel feature selection method combining SVM-RFE with MRMR is proposed to select salient features, improving the performance of fault diagnosis approach. Experimental results on reducer platform demonstrate that the proposed method is capable of revealing the relations between the features and faults and providing insights into fault mechanism.

This paper is to propose a novel fault diagnosis method for broken rotor bars in squirrel-cage induction motor of hoister, which is based on duffing oscillator and multifractal dimension. Firstly, based on the analysis of the structure and performance of modified duffing oscillator, the end of transitional slope from chaotic area to large-scale cycle area is selected as the optimal critical threshold of duffing oscillator by bifurcation diagrams and Lyapunov exponent. Secondly, the phase transformation duffing oscillator from chaos to intermittent chaos is sensitive to the signals, whose frequency difference is quite weak from the reference signal. The spectrums of the largest Lyapunov exponents and bifurcation diagrams of the duffing oscillator are utilized to analyze the variance in different parameters of frequency. Finally, this paper is to analyze the characteristics of both single fractal (box-counting dimension) and multifractal and make a comparison between them. Multifractal detrended fluctuation analysis is applied to detect extra frequency component of current signal. Experimental results reveal that the method is effective for early detection of broken rotor bars in squirrel-cage induction motor of hoister.

No abstract

No abstract