Fault Diagnosis Method of Escalator Step System Based on Vibration Signal Analysis

For the problem that escalator fault diagnosis is difficult to realize, this paper proposes a fault diagnosis method based on vibration signal analysis. The vibration signal is collected from three parts: step guide rail, main drive shaft and main engine. The wavelet threshold denoising algorithm based on Ensemble Empirical Mode Decomposition (EEMD) is used to denoise the vibration signal. The signal characteristics are extracted, and the fault detection is performed through the Support Vector Machine (SVM) fault detection model. For the fault signal, the improved envelope spectrum analysis method is used to extract the characteristic frequency and corresponding amplitude to form the characteristic vector, and the Support Vector Machine for Particle Swarm Optimization (PSO-SVM) algorithm is used to identify the location of the fault. The experimental results show that this method has high accuracy in the fault diagnosis of escalator step system.