Global Journal of Environmental Science and Technology

Prediction of Machining Parameters on Welded Materials using Response Surface Methodology (RSM) and Artificial Neural Network (ANN)

Abstract In welding processes, achieving the desired weld quality involves a multitude of factors that can interact with each other, thus, impacting key parameters like the cutting force. Some factors hold more significance, while the influence of others is minimal. Determining the optimal combination of these factors to maximize cutting force is a challenging endeavor. This study is focused on the prediction and optimization of machining parameters for welded joints, including depth of cut, cutting speed, and feed rate, in relation to cutting force. To accomplish this, the study utilizes both the Response Surface Methodology (RSM) and Artificial Neural Network (ANN). The central composite design was meticulously created using Design expert software (version 13.0). The RSM analysis produced a coefficient of determination of 0.9961. Additionally, an artificial neural network model was employed to predict output parameters and was compared with the RSM approach. The training of the neural network utilized 70% of the data for training, 15% for validation, and the remaining 15% for testing. The training process extended for a maximum of 1000 epochs, resulting in a coefficient of determination of 0.87834. The study's findings indicate that, in this specific context, the Response Surface Methodology (RSM) outperformed the Artificial Neural Network (ANN) as a predictive model.

Keywords: cutting force, central composite design, response surface methodology, artificial neural network