Abstract：The wire bond shear strength is one of important index of bond quality. The paper using the electrical signal from the ultrasonic generator supply as the information carrier, the feature extraction method of ultrasonic electrical signals in bond shear strength identification is investigated. A new feature extraction method based on the subband envelope segmentation is proposed for characterizing the transient ultrasonic electrical signal. The filtered subband envelopes of ultrasonic electrical signal is separated into three phases individually, namely envelope rising phase, stable and damping phase. The waveform features are extracted from each phase of the envelope for further bond shear strength identification. To remove the irrelevant information and reduce the dimension of original feature variables, the principal component analysis is carried out for the feature selection. Using the selected features as inputs, an artificial neural network (ANN) is constructed to identify the complex bond fault pattern. By analyzing experimental data with the proposed feature extraction method and neural network, the results demonstrate the advantages of the proposed feature extraction method and the constructed artificial neural network in identifying bond shear strength.
2011, Vol. 30 
