Wavelet-based PCA defect classification for pulsed eddy current NDT

A new approach for defect classification and quantification by using pulsed eddy current sensors and integration of principal component analysis and wavelet transform for feature based signal interpretation is presented. After reviewing the limitation of current parameters of peak value and its arrival time from pulsed eddy current signals, a two-step framework for defect classification and quantification is proposed by using adopted features from principal component analysis and wavelet analysis. For defect classification and quantification, different features have been extracted from the pulsed eddy current signals. Experimental tests have been undertaken for ferrous and non-ferrous metal samples with manufactured defects. The results have illustrated the new approach has better performance than the current approaches for surface and sub-surface defect classification. The defect quantification performance, which is difficult by using current approaches, is impressive.