Recent advances in controlling, monitoring and optimization of the friction stir welding process

Friction Stir Welding (FSW) is a solid-state welding process and currently turns out to be the most widely used friction joining technique for light alloys, dissimilar materials, and metals that are not easily weldable. This process offers many advantages with respect to the traditional welding methods and it is considered an energy-saving, environment friendly, and relatively versatile technology. In the last years, several works in literature focused on the study and optimization of the process parameters directly related to the quality of the produced joints. This work presents a collection of new advanced studies for investigating the correlation between the process parameters and the quality of joints in terms of their mechanical properties such as the Ultimate Tensile Strength and hardness. Moreover, it is presented the capability of thermography to study the FSW process. A new approach based on the investigation of the thermal behaviour of plates during both the heating and cooling phase is proposed. This approach revealed more effective in the description of the process parameters than the classical one based on the monitoring of the absolute temperature. In addition, Artificial Neural Networks (ANNs) were used for optimizing and predicting the mechanical properties (output values) of the welded joints based on the FSW process parameters (input variables).