Quantum Inspired Evolutionary Technique for Optimization of End Milling Process

In this paper an attempt is made to develop a new Quantum Inspired Evolutionary Technique (QIET) that is general, flexible and efficient in solving single objective constrained optimization problems. It generates initial parents using quantum seeds. It is here that QIET incorporates ideas from the principles of quantum computation and integrates them in the current frame work of Real Coded Evolutionary Algorithm (RCEA). It also incorporates Simulated Annealing (SA) in the selection process of Evolutionary Algorithm (EA) for child generation. In order to test this algorithm on domain specific manufacturing problems, Neuro-Fuzzy (NF) modeling of end milling process is attempted and the NF model is incorporated as a fitness evaluator inside the QIET to form a new variant of this technique, i.e. Quantum Inspired Neuro Fuzzy Evolutionary Technique (QINFET) and is effectively applied for process optimization of end milling process. The optimal process parameters obtained by QINFET correlates better than those reported in literature. The proposed methodology using QINFET is a step towards meeting the challenges posed in intelligent manufacturing systems and opens new avenues for parameter estimation and optimization.