ANFIS Based Weld Metal Deposition Prediction System in MAG Welding using Hybrid Learning Algorithm

Abstract

This work proposes a soft computing based artificial intelligent technique Adaptive Neuro Fuzzy Interference System (ANFIS), to predict the weld metal deposition in the Metal Active Gas (MAG) welding process for a given set of welding parameters using hybrid learning algorithm to have a correct amount of weld metal deposition to meet the correct welding requirement. Total 81 nos. of experiments are designed according to full factorial design of experiments with varied input parameters and its results are used to develop an ANFIS model. Multiple sets of data from experiments are utilized to train, check and validate the intelligent network, which is used to predict the amount of weld metal deposition. The proposed ANFIS, developed using MATLAB functions, is flexible, and it scopes for a better online monitoring system to achieve better welding requirement.