Application of a Fuzzy Inference System for the optimization of material removal rate and multiple surface roughness characteristics in the machining of GFRP polyester composites

Abstract

This paper presents a multi-objective extended optimization methodology applied in the machining of a randomly oriented GFRP rod. Design of Experiment (DOE) has been selected based on a L9 orthogonal array design with varying process control parameters like: spindle speed, feed rate and depth of cut. Multiple surface roughness parameters of the machined FRP product along with the Material Removal Rate (MRR) of the machining process have been optimized simultaneously. The Fuzzy Inference System (FIS) has been proposed for providing feasible means for the meaningful aggregation of multiple objective functions into an equivalent single performance index (MPCI). This Multi-Performance Characteristic Index (MPCI) has been optimized using the Taguchi method. The approach adapted here is capable of overcoming limitations/assumptions of existing optimization methodologies available in the literature.