Prediction of extreme temperatures in weld zone of friction stir welding

The extreme temperatures in weld zone during friction stir welding (FSW) directly affect the welding quality of the joints. Therefore, characterization of the maximum and minimum temperatures in weld zone is essential to ensure welding quality. However, direct measurement or prediction based on simulation is difficult due to the occlusion of the tool shoulder and the severe plastic deformation of the weldment under thermo-mechanical effects during the welding process. To solve the problem, this paper presents a method for prediction of extreme temperatures in weld zone based on infrared thermography. Firstly, a 3D temperature field simulation model of FSW is established based on DEFORM, and the experiments are conducted to verify the validity of the simulation model. The data sets of temperature of surface feature points and the maximum and minimum temperatures in weld zone are obtained. Then, support vector regression (SVR) is used to establish a temperature prediction model, which represents the correlation between the temperature of surface feature point and the extreme temperatures in weld zone. In practical FSW process, an infrared thermal imager is used to measure the temperature of the surface feature point. Combined with the built temperature prediction model, the prediction of the extreme temperatures in the weld zone is achieved. The research provides references for temperature-based process control of FSW.