Control Criteria Determination and Quality Inference for Resistance Spot Welding through Monitoring the Electrode Displacement Using Bayesian Belief Networks

Currently real-time control and online quality estimation of the resistance spot welding (RSW) has benefited a lot from monitoring the electrode displacement. Based on these emerging monitoring techniques a new approach is proposed to determine the optimal welding parameters and help to assess the weld quality. Two causal models are built with the offline trained Bayesian Belief Networks (BBN). The first model which is a pattern determination net deals with the optimal control criteria, i.e. an ideal combination of the maximum electrode displacement and electrode travel velocity, to provide more reliable welding process and qualified welds. The second model which is a weld quality assessment net reveals the dependency of the weld quality on the features displayed by the displacement curve, which can be used for overdesigning the safety welds or for online assessing weld quality as the probabilistic forecasting model. The experimental results show that the proposed approach is valid and feasible to determine the controlled parameters and to predict the weld quality in practices.