Spring International Engineering Research Journal

ISSN 2384-5058

Prediction and Optimization of Pipeline Welded Tool Life using Response Surface Methodology (RSM) and Artificial Neural Network (ANN)

Abstract:  Pipeline networks play a pivotal role in transporting an array of fluids and gases across various industrial domains. The study aims to fill this void by investigating the impact of a specific non-flexible component, namely the surface area of contact, on pipeline weldments and its interaction with elastic properties. To fulfil this objective, a comprehensive experimental inquiry is conducted, encompassing diverse welding methods, materials, and environmental conditions to authentically replicate real-world situations. The response surface methodology analysis yields optimal outcomes, suggesting a depth of cut of 0.400, cutting speed of 250.000, and feed rate of 0.500. These input parameters collectively yielded a machined structure with tool life of 149.958 and this was attained at a desirability value of 0.973. Additionally, the Artificial Neural Network model is utilized to forecast output parameters and compared against the Response Surface Methodology. The findings underscore the pivotal role of optimizing non-elastic performance factors in pipeline weldments. By accurately controlling the surface area of contact, weldments can be designed with capabilities of enduring harsh conditions, curbing the risk of failures, and significantly prolonging pipeline operational lifespans.


Keywords: Pipeline networks, tool life, response Surface methodology, artificial neural network