Feature Extraction and Detection Method of Series Arc Faults in a Motor With Inverter Circuits Under Vibration Conditions
Abstract
Certain faults occurring in a three-phase asynchronous motor generate a mechanical vibration of a specific frequency. Moreover, poor electrical contact points cause series arc faults (SAFs) under mechanical vibration. To detect SAFs under different vibration frequencies and amplitude conditions, we propose an SAF detection method based on an improved recurrence quantification analysis (IRQA) and a back-propagation neural network. First, we designed an arc fault generator and then completed an SAF experiment of the motor with inverter circuits under different vibration conditions. Next, we extracted the high-dimensional characteristics of the fault phase current by using an IRQA. In the IRQA, we performed phase space reconstruction processing on the fault phase current signal and then converted the processed signal into thresholded and unthresholded recurrence plots. The nine SAF features in the plots were extracted. Training and testing sets were constructed based on these SAF features. Finally, by training and testing of the BP neural network, we established an SAF detection model. The test results show that the SAF detection model distinguished between the normal and SAF current signal with 100% accuracy, and that it judged the mechanical vibration frequency caused by some motor faults with 98.17% accuracy.
