A Visual Contrast–Based Fruit Fly Algorithm for Optimizing Conventional and Nonconventional Machining Processes

Swarm intelligence has been extensively adopted to develop and deploy optimization algorithms to almost all branches of science and engineering. In this paper, a visual contrast–based fruit fly algorithm (c-mFOA) is presented to push further the improvement of intelligent optimization when it comes to general engineering problem solving with emphasis to conventional and nonconventional manufacturing processes implemented to modern industry. In this fruit fly algorithmic variant, the natural mechanisms of surging, visual contrast, and casting are incorporated to enhance the algorithm’s exploration and exploitation. The proposed algorithm has been tested to optimize a set of known, widely used benchmark functions and is further implemented to optimize the process parameters of machining processes namely turning; focused ion beam micro milling; laser cutting; wire electrodischarge machining; and microwire electrodischarge machining. The results obtained by examining the multiple solutions, their nonparametric statistical outputs, and hypervolumes of their related Pareto fronts, suggest clear superiority of the c-mFOA against its competing multiobjective optimization algorithms (MOEAs).