Corrosion Rate Optimization and Prediction for Enhanced Strength and Structural Integrity of Pipeline Weldments Using RSM and ANN

Abstract

This study investigates the optimization and prediction of non-elastic performance factors required to augment the pipeline weldments' structural integrity and strength. The study's main focus is on the components of the operation, like the welding current, voltage, and gas flow rate to optimize and predict the corrosion rate of the pipeline weldment. Utilizing Design Expert software for experimental design and data analysis, the study employs the Central Composite Design (CCD) methodology to generate a quadratic model that predicts the responses effectively. The research also integrates Artificial Neural Networks (ANN) to further enhance the prediction accuracy. Experimental results indicate that the optimal welding parameters 160 amps current, 21.28 volts voltage, and 14.67 liters/min gas flow rate—yield a corrosion rate of 0.018 mm/yr. The study concludes that both RSM and ANN can be effectively used for optimization and prediction in welding processes, with RSM showing slightly better predictive capabilities.