Application of genetic algorithm to external noise cancellation and compensation in automatic arc welding system

This paper develops an automatic welding control system which uses a genetic algorithm to carry out external noise cancellation and compensation. In the proposed approach, the genetic algorithm is used to identify the polynomial form or parameters of the external force or disturbance, including the amplitude, frequency and phase to compensate for nonlinear phenomenon such as disturbance in the mechanical system. In compensating for the nonlinear phenomenon, a piecewise linearization of the approximation polynomial is performed and the genetic algorithm optimization process is then used to identify the parameters of the polynomial function. The simulation and experimental results confirm that the proposed automatic welding control system provides an effective means of compensating for the effects of the external force or disturbance and therefore results in an enhanced welding performance.