Detection method for electric impact drill parts defect based on auditory peripheral model

Abstract

The accurate non-contact detection for electric impact drill parts defect can significantly improve the production efficiency. In this paper, an acoustic-based method is proposed to detect parts defect by mimicking the physiological auditory perceptual principles. The method firstly combined Gammatone filter banks and Meddis model to simulate cochlear processing mechanism to calculate the time–frequency information of the electric impact drill working acoustic signal. Then the subband energy-entropy differential ratio was described to extract the time–frequency features. Based on the optimized features by the principal component analysis, the parts defect detection was achieved by the support vector machine. The results with collected electric impact drill acoustic data show that the detection accuracy by this method can reach 97.8 %, which is 5.12 % higher than the Mel frequency cepstral coefficient method and 7.56 % higher than the time–frequency domain feature method. The proposed method can provide a new idea for non-contact part defect detection of electric impact drill in factories.