Fault Feature Extraction of Escalator Foundation Loosening Based on Empirical Wavelet Decomposition and Bispectral Analysis
Escalator is an essential large-scale public transportation equipment.Once the failure occurs,it will inevitably affect the operation and even cause safety accidents.As an important part of the structure of escalator,the loosening of the anchor bolt will lead to abnormal operation of escalator.Aiming at the problem that it is difficult to extract the fault features of anchor bolt loosening,this paper constructed a fault feature extraction method of escalator anchor loosening based on empirical wavelet decomposition(EWT)and bispectral analysis.First,a series of empirical mode component functions(EMF)were obtained by EWT decomposition of the original vibration acceleration signals of the footing.Then,for each empirical mode component function,the bispectrum was calculated by using bispectrum analysis method,and six texture features of the bispectrum were extracted as fault feature vectors by means of gray-gradient co-occurrence matrix.Finally,the extracted multi-scale fault feature vectors and bi-directional long-short time network(BI-LSTM)were used to classify and identify the four types of fault signals with different degrees of foot loosening,and the fault types of foot loosening were determined.The results show that the feature extraction method based on empirical wavelet decomposition and bispectrum analysis can more effectively identify the loosening level of anchor bolts.
NETL
NSTL
万方数据
