Escalator Fault Diagnosis Method Based on SVM and Feature Frequency Extraction

For the problem of escalator step system faults, this paper proposes a method based on the combination of SVM and fault feature frequency extraction to diagnose the fault. Firstly, the vibration signal is analyzed and processed to extract the characteristics, and the SVM fault detection model is constructed to realize the detection of the fault signal. Then, the wavelet threshold method based on EMD is used to denoise the fault signal, and the method based on the combination of high-frequency matching method and envelope spectrum analysis is used to extract the fault characteristic frequency, and the fault type is determined by the fault characteristic frequency to realize the fault diagnosis. The experimental results show that the method has high accuracy for the fault diagnosis of escalator step system.