Hybrid constrained permutation algorithm and genetic algorithm for process planning problem

In this research, a hybrid constrained permutation algorithm and genetic algorithm approach is proposed to solve the process planning problem and to facilitate the optimisation process. In this approach, the process planning problem is represented as a graph in which operations are clustered corresponding to their machine, tool, and tool access direction similarities. A constrained permutation algorithm (CPA) developed to generate a set of optimised feasible operations sequences based on the principles of minimising the number of setup changes and the number of tool changes. Due to its strong capability in global search through multiple optima, genetic algorithm (GA) is used to search for an optimal or near optimal process plan, in which the population is initialised according to the operations sequences generated by CPA. Furthermore, to prevent premature convergence to local optima, a mixed crossover operator is designed and equipped into GA. Four comparative case studies are carried out to evidence the feasibility and robustness of the proposed CPAGA approach against GA, simulated annealing, tabu search, ant colony optimisation, and particle swarm optimisation based approaches reported in the literature, and the results are promising.