Neuro hybrid model to predict weld bead width in submerged arc welding process

摘要

This paper presents development of neuro hybrid model (NHM) to predict weld bead width in submerged arc welding. Experiments were designed using Taguchi's principles and results were used to develop a multiple regression model. Data set generated from Multiple Regression Analysis (MRA) was utilized in ANN model, which was trained with backpropagation algorithm in MATLAB platform and used to develop NHM to predict quality of weld. NHM is flexible and accurate than existing models for a better online monitoring system.