Application of Response Surface Methodology and Artificial Neural Network Analytical approach in modelling Shock Resistance of Pipeline Weldments

Abstract

Heat transfer, given its various applications, has long been the focus of researchers and engineers. However, Shock Resistance also takes on a pivotal role in transporting an array of fluids and gases across various industrial domains. This study bridges this discrepancy by scrutinizing the after-effects of a specific non-elastic factor, namely shock resistance, on pipeline weldments and its interaction with elastic properties. This investigation unveils the intricate interrelation, underscoring the necessity of encompassing non-elastic facets to ensure the dependability of pipeline weldments across various operational contexts. Cutting-edge techniques, such as machine learning algorithms and finite element simulations, are harnessed to accurately predict and optimize these non-elastic factors (Shock Resistance), thereby enhancing the overall strength and structural integrity of pipeline weldments. The experimental setup adheres to the central composite design, meticulously constructed using design expert software (version 13.0). The response surface methodology analysis yields optimal outcomes, suggesting a current of 160.000 amps, voltage of 21.280 volts, and gas flow rate of 14.667 liters per minute. These parameters collectively yield a welded joint with a shock resistance value of 0.729, achieving a desirability value of 0.918. Additionally, the artificial neural network model is employed to predict output parameters and compared against the RSM methodology. The findings underscore the pivotal role of optimizing non-elastic performance factors in pipeline weldments. By accurately anticipating and controlling temperature, engineers and professionals within the pipeline sector can design weldments capable of enduring harsh conditions, curbing the risk of failures, and significantly prolonging pipeline operational lifespans.