Effects of modeling means on properties of monitoring models of spot welding quality

Analyzing and modeling the relation between monitoring information during welding and quality information of the joints is the foundation of monitoring resistance spot welding quality. According to the means of modeling, the, known models can be divided into three, categories including single linear regression models, multiple linear regression models and multiple nonlinear models. By modeling the relation between dynamic resistance information and welding quality parameters with different means, the effects of modeling means on the performance of monitoring models of resistance spot welding quality were analyzed. By comparison with multiple linear regression models, artificial neural network model can describe non-linear and high coupling relation between monitoring information and quality information more reasonably, improve the performance of monitoring model remarkably, and make the estimated values of welding quality parameters more accurate and reliable.