Artificial Intelligent-Based Parameter Tuning of an Active Disturbance Rejection Controller for Electrode Wire Feeding Mechanism

This study introduces a method to enhance the performance of electrode wire feeding mechanisms (EWFMs) in arc welding machines using an artificial intelligent (AI) method., called radial basis function neural network (RBFNN)., to implement a self-tuning active disturbance rejection controller (ADRC). The method involves developing an ADRC approach to improve tracking and robustness against disturbances., followed by employing an RBFNN-based method for precise tuning of the ADRC controller's parameters. A real-time testing system on the dSPACE platform is used to validate the effectiveness of this method. The results show that the ADRC controller with RBFNN-based parameter tuning effectively rejects disturbances., minimizes overshoot., and ensures rapid response and high precision., thereby improving the stability and quality of the arc welding process.