ISSN 2384-5058
Abstract: Enhancing the dimensional accuracy of thick materials is crucial in manufacturing processes, directly impacting the quality and performance of the final products. This study investigates the optimization of machining parameters to maximize the rigidity index, a key factor in maintaining dimensional stability. Utilizing Response Surface Methodology (RSM) and Artificial Neural Networks (ANN), this research aims to predict and optimize the rigidity index, thereby improving precision in machining thick materials. The methodology involves designing experiments using a central composite design matrix. Statistical tools were employed to analyze the data, and the quadratic model was identified as the best fit for predicting rigidity index. Results indicate that optimizing parameters such as depth of cut, cutting speed, and feed rate significantly enhances the rigidity index, leading to improved dimensional accuracy. Experimental validation and predictive modeling demonstrate that both RSM and ANN are effective in optimizing machining parameters. The study provides a robust framework for manufacturers to achieve higher precision and efficiency in processing thick materials, contributing valuable insights into the optimization of rigidity index for enhanced manufacturing outcomes.
Keywords: Dimensional Accuracy, RSM, ANN, Rigidity Index Enhancement