Multiple information fusion of aluminum alloy resistance spot welding based on principal component analysis

Abstract

The monitoring of aluminum alloy resistance spot welding (RSW) is realized by distributed multiple sensor synchronous collection system and the data processing software is also developed by using LABVIEW graphical language. Statistical analysis has been applied to investigate the relationship between the extracted features and the RSW quality. The results show that the expulsion in spot welding is related to the notching curve of voltage and electrode displacement signal. Moreover, there is a correlation between the high frequency impulse amplitude and duration of the electrode force signal and the expulsion strength, and three features simultaneously or separately occur according to the expulsion strength in spot welding. Resistance spot welding quality can be assessed by nine features of high Signal-to-Noise ratio, and these may be the base of on-line quality classification of aluminum alloy spot welding in future. Furthermore, using principal component analysis (PCA) may implement the information fusion and data compression. The percentage of spot welding quality classification accuracy can reach 98%.