Improved genetic algorithm for integrated process planning and scheduling in distributed heterogeneous manufacturing environment

The distributed manufacturing mode is an important paradigm of networked development in the context of globalization. The integration of process planning and shop scheduling in distributed discrete manufacturing system can fully use the production system's flexibility, which is helpful to further enhance the anti-risk ability of enterprises, improve production efficiency, and reduce production costs. This paper established the mathematical model of the distributed integrated process planning and scheduling (DIPPS) in heterogeneous manufacturing environment and designed a high-dimensional integrated encoding to deal with the coupling problem of multiple sub-problems of the DIPPS. Based on this encoding method, an improved genetic algorithm (IGA) is proposed to solve the DIPPS problem. According to the characteristics of the DIPPS, a hierarchical crossover operator with three sub-crossover operations is designed to expand the search dimension of the IGA. The mutation operators are planned to maintain population variety. Finally, five sets of experiments are planned to test the viability of the suggested approach for resolving the DIPPS problem. The outcomes demonstrate that the IGA algorithm outperforms competing algorithms in various scale jobs and factories.