Biologically Inspired Optimization Algorithms for Flexible Process Planning
- 825 Downloads
Flexible process planning belongs to one of the most essential functions of the modern manufacturing system. The aim of this function is to define detailed methods for manufacturing of a part in an economic and competitive manner starting from the initial phase (drawing of the target part) up to the final one (the desired shape of the target part). A variety of alternative manufacturing resources (machine tools, cutting tools, tool access directions, etc.) causes flexible process planning problem to be strongly NP-hard (non deterministic polynomial) in terms of combinatorial optimization. This paper presents a comparative analysis of biologically inspired optimization algorithms which are used to solve this problem. Four different optimization algorithms, namely genetic algorithms (GA), simulated annealing (SA), chaotic particle swarm optimization algorithm (cPSO), and ant lion optimization algorithm (ALO) are proposed and implemented in Matlab environment. Optimal process plans are obtained by multi-objective optimization of production time and production cost. The experimental verification is carried out by using real-world examples. The experimental results indicate that all aforementioned algorithms can be successfully used for optimization of flexible process plans, while the best performance shows ALO algorithm.
KeywordsFlexible process planning Genetic algorithms Simulated annealing Chaotic particle swarm optimization algorithm Ant lion optimization algorithm
This paper is part of the project “An innovative, ecologically based approach to the implementation of intelligent manufacturing systems for the production of sheet metal parts”. The research in this paper was supported by the Ministry of Education, Science and Technological Development of the Serbian Government, Grant TR-35004 (2011–2017).
- 3.Kennedy J, Eberhart RC (1995) Particle swarm optimization. In: Proceedings of the IEEE international conference on neural network, vol 4. Perth, pp 1942–1948Google Scholar
- 9.Petrović M (2016) Design of intelligent manufacturing systems by using artificial intelligence. University of Belgrade—Faculty of Mechanical Engineering (Doctoral Dissertation), Serbian, pp 1–319Google Scholar