Time–Frequency Feature Extraction of Acoustic Emission Signals in Aluminum Alloy MIG Welding Process Based on SST and PCA

The acoustic emission (AE) signal is weak due to the coupling and intersecting coexistence of other disturbance components in aluminum alloy metal inert-gas welding (MIG) process. It is necessary to analyze and process the AE signal for the accurate identification of the welding state. A time frequency feature extraction method based on synchronous compression wavelet (SST) and principal component analysis (PCA) is proposed in this paper. The SST transform is performed to the collected AE signal of the MIG welding process to obtain the time frequency distribution. The PCA is subsequently performed to the time frequency distribution of the AE signals to determine the principal components. The approximate entropies of the principal components are calculated to quantitatively express the state characteristics of the welding process. The proposed method is applied to the AE signal of the friction, arc shock and the crack in the aluminum alloy MIG welding process. The three kinds AE signals are identified by inputting the calculated approximate entropies into the support vector machine (SVM). The results indicate that the calculated approximate entropies highlight the characteristic ability of the different modal AE signals, which can be used for monitoring the aluminum alloy MIG welding process quantitatively.