PEC defect automated classification in aircraft multi-ply structures with interlayer gaps and lift-offs

Current pulsed eddy current (PEC) defect classification method requires highly trained personnel and the results are usually influenced by subjectivity of human perception. Lift-off effect and interlayer air gaps are the main obstacles in eddy current defect classification in multi-layer structures. Therefore, automated defect classification in multi-layer structures is very desirable and stringent. In this work, principal component analysis (PCA) and support vector machine (SVM) are investigated for defect automated classification under different interlayer gaps and lift-off effects. The experimental classification and predicting results show that 1st-layer surface defects, 1st-layer sub-surface defects, 2nd-layer surface defects, and 2nd-layer sub-surface defects can be classified satisfactorily when air gap and lift-off vary from 0 to 1.4 mm through the proposed methods, which has the potential for automatic defect in-situ classification for multi-layer aircraft structures.