Ant colony optimization to select the best process plan in an automated manufacturing environment

Abstract

In the present dynamic manufacturing systems, optimal process plan selection is quite an intricate task. Systematic determination of processing steps for the transformation of raw material to finished products is known as process planning. The complexity of process plan selection increases with the availability of alternative machines, alternative set-ups, and alternative processes for manufacturing the same part types. The ant colony optimization (ACO) algorithms are multiagent systems in which the behaviour of each ant is inspired by the foraging behaviour of real ants to solve the optimization problem. This paper presents yet another successful application of ACO to solve real-world problems by resolving the complex process plan selection (PPS) problem. The primary advantage of using ACO is that it stabilizes the solution with considerably less computational effort and time without any deterioration in the quality. The proposed strategy has been applied over a few benchmark problems from the literature, and the results establish the competitive advantage of ACO over the established strategies. Comparative analysis of the proposed strategy with other well-established methodologies confirms its effectiveness and superiority.