Phase Compensation Based Dynamic Time Warping for Fault Diagnosis Using Motor Current Signal

Dynamic Time Warping (DTW) is a time domain based method and widely used in various similar recognition and data mining applications. This paper presents a phase compensation based DTW to process the motor current signals for detecting and quantifying various faults in a two-stage reciprocating compressor under different operating conditions. DTW is an effective method to align up two signals for dissimilarity analysis. However, it has drawbacks such as singularities and high computational demands that limit its application in processing motor current signals for obtaining modulation characteristics accurately in diagnosing compressor faults. Therefore, a phase compensation approach is developed to reduce the singularity effect and a sliding window is designed to improve computing efficiency. Based on the proposed method, the motor current signals measured from the compressor induced with different common faults are analysed for fault diagnosis. Results show that residual signal analysis using the phase compensation based DTW allows the fault related sideband features to be resolved more accurately for obtaining reliable fault detection and diagnosis. It provides an effective and easy approach to the analysis of motor current signals for better diagnosis in the time domain in comparison with conventional Fourier Transform based methods.