Multi-Objective Optimization of Face Milling Parameters for DIN 2714 Hardened Steel: Hybrid Taguchi–Analysis of Variance and Artificial Intelligence-Based System Modeling
TL;DR
The experimental results demonstrated that fuzzy modeling techniques can be effectively used to optimize machining operations with high precision, proving that fuzzy modeling techniques can be effectively used to optimize machining operations with high precision.
Abstract
The face milling process for hardened steels used in die and mold manufacturing involves precise parameter settings to achieve high-quality surfaces with high productivity. However, due to the nonlinear relationship between the machining parameters, it becomes challenging to optimize the machining process. This paper focuses on optimizing the face milling parameters for the DIN 2714 hardened steel by employing experimental approaches and AI-based modeling techniques. Taguchi’s L9 orthogonal array-based design of experiments with machining parameters of depth of cut, cutting speed, feed rate, and step-over is employed for the optimization. The material removal rate (MRR) and surface roughness (Ra) were considered as output responses.The results showed that surface roughness is significantly affected by cutting speed, while depth of cut primarily controls MRR. To improve the precision in predicting the output responses, two artificial intelligence (AI) based intelligent models were developed using hybrid modeling techniques—namely, PSO-FIS and GA-FIS. The experimental results demonstrated that the GA-FIS model was accurate in predicting the output response for surface roughness (Ra), with a lower error value (0.0162 μm), while the PSO-FIS model was accurate in predicting MRR with a high R2 value (0.9997), proving that fuzzy modeling techniques can be effectively used to optimize machining operations with high precision.