Laser Welding Multimodel Quality Forecast Method Based on Dynamic Geometric Features of the Molten Pool.

Abstract

Laser welding quality forecast is highly significant during the laser manufacturing process. However, extracting the dynamic characteristics of the molten pool in the short laser welding process makes predicting of the welding quality in real time difficult. Accordingly, this study proposes a multimodel quality forecast (MMQF) method based on dynamic geometric features of molten pool to forecast the welding quality in real time. For extraction of geometric features of molten pool, an improved fully convolutional neural network is proposed to segment the collected dynamic molten pool images during the entire welding process. In addition, several dynamic geometric features of the molten pool are extracted by using the minimum enclosed rectangle algorithm with an evaluation of the performance by several statistical indexes. With regard to forecasting the welding quality, a nonlinear quadratic kernel logistic regression model is proposed by mapping the linear inseparable features to the high dimensional space. Experimental results show that the MMQF method can make an effective and stable forecast of welding quality. It performs well under small data and can satisfy the requirement of real-time forecast.