Intelligent CNC Tool Path Optimization for Sculptured Surface Machining Through a Virus-Evolutionary Genetic Algorithm

Abstract

Priorities for manufacturers worldwide include their attempt towards optimizing modern manufacturing systems to satisfy the needs of their customers. Major goal of the proposed study is to present a novel optimization methodology based on Artificial Intelligence using the Virus Theory of Evolution. The methodology implements a Virus-Evolutionary Genetic Algorithm to undertake sculptured surface tool path optimization in terms of geometrical machining error to reflect part quality and machining time to reflect productivity for both 3- and 5-axis sculptured surface machining. The algorithm implements its virus operators to create efficient solution representations, to rabidly reproduce enhanced schemata during the evaluations’ loops, and finally come up with the optimum machining parameters based on the available resources and constraints ought to be imposed. Through a fully automated environment, time-consuming activities and repetitive tasks are no more of the CNC programmers’ concern since the algorithm handles the CAM system’s routines to handle them for its own benefit. The proposed methodology is deemed capable of providing uniform tool paths with low geometric machining error distribution as well as high productivity rates to the best possible extent.