Modelling and prediction of strength of ultrasonically welded electrical contact joints using Artificial Neural Network

Abstract

Abstract Ultrasonic welding is an advanced green solid state welding process used to weld similar or dissimilar materials of same or dissimilar shapes. Ultrasonic welding is used to join both conductive and non-conductive materials. Copper is an excellent conductive non-ferrous metal widely used in wide variety of electrical and electronic components manufacturing applications. Many electrical components have a need to join copper wire to copper sheet and these applications demands inevitably for superior weld strength. In this paper, ultrasonic welding is carried out on copper wire-sheet to produce quality electrical contact joints. The present study deals with the formulation of mathematical model between the predominant input parameters such as clamping force, amplitude of vibration of sonotrode and weld time and the output parameter such as weld strength using Artificial neural network and regression technique. Based on the results from experiments and prediction models, the ANN model is found to be effective when compared with the developed third order polynomial regression model