AI-Driven Optimization of Drilling Parameters for Minimizing Delamination and Improving Surface Quality in Hybrid Polymer Composites
Year: 2024
Type: article
Abstract: Hybrid polymer composites are growingly adopted in industrial applications due to their exceptional strength-to-weight ratio, and excellent durability to corrosion and wear. Drilling, a crucial machining operation in these composites is influenced by various parameters, leading to challenges like delamination, micro-cracks, thermal damage, and excessive thrust force can lead to inefficiencies and material damage. This research aims to develop an Artificial intelligence (AI) model using Support Vector Machine (SVM) to optimize machining parameters (spindle speed, feed rate, point angle) during the drilling of hybrid polymer composites. The focus is on predicting delamination, thrust force, and Surface roughness to enhance drilling efficiency. The SVM model achieves impressive performance metrics: for thrust force, an MSE of 0.63569, RMSE of 0.821569, NRMSE of 0.015246, and MAPE of 1.32548; for delamination, an MSE of 0.008952, RMSE of 0.09652, NRMSE of 1.45263, and MAPE of 6.49852; for Surface roughness, an MSE of 0.67852, RMSE of 0.82356, NRMSE of 0.15365, and MAPE of 13.025. The findings will advance the machining of hybrid polymer composites, providing industries with improved drilling processes, minimizing delamination, thrust force, and Surface roughness, and enhancing manufacturing processes, product quality, and industrial competitiveness.
Author: Yogesh Dinkar Jadhav
Language: English
Subfield: Mechanical Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7216744252