Selection of Optimum Friction Welding Condition using Neural Networks

Abstract

A selection method of optimum friction welding condition using neural networks is proposed. The data used for analyses are the friction welding condition, burn-off length and joint strength on 5056 aluminum alloy friction welding. The learning of the synapse weights of the neural network is performed using the extended Kalman filtering algorithm. The results of analysis suggest that the proposed method is an effective method to select an optimum welding condition.