Abstract
Production scheduling of semiconductor wafer manufacturing is a challenging research topic in the field of industrial engineering. Based on this, the green manufacturing collaborative optimization problem of the semiconductor wafer distributed heterogeneous factory is first proposed, which is also a typical NP-hard problem with practical application value and significance. To solve this problem, it is very important to find an effective algorithm for rational allocation of jobs among various factories and the production scheduling of allocated jobs within each factory, so as to realize the collaborative optimization of the manufacturing process. In this paper, a scheduling model for green manufacturing collaborative optimization of the semiconductor wafer distributed heterogeneous factory is constructed. By designing a new learning strategy of initial population and leadership level, designing a new search strategy of the predatory behavior for the grey wolf algorithm, which is a new swarm intelligence optimization algorithm proposed in recent years, the diversity of the population is expanded and the local optimum of the algorithm is avoided. In the experimental stage, two factories’ and three factories’ test cases are generated, respectively. The effectiveness and feasibility of the algorithm proposed in this paper are verified through the comparative study with the improved Grey Wolf Algorithms—MODGWO, MOGWO, the fast and elitist multi-objective genetic algorithm—NSGA-II.
Highlights
With the advent of the fourth industrial revolution in the context of industrial 4.0, intelligent manufacturing has become a symbol of the new information age
Because this paper studies the collaborative optimal scheduling problem of green manufacturing in semiconductor wafer distributed heterogeneous factory, which is assumed that all jobs can be processed in any factory, the number of production stages is the same among factories, the number of machines is different, the processing time of jobs are different in each factory, and the delivery time of jobs are different in each factory
End to verify the effectiveness of the improved multi-objective Grey Wolf Optimizer (IMOGWO) algorithm proposed in this paper for solving green manufacturing collaborative optimization problems of the semiconductor wafer newX (length(a) + 1: dim ) = b distributed heterogeneous factory, the NSGA-II algorithm proposed in literature [36], the MODGWO
Summary
With the advent of the fourth industrial revolution in the context of industrial 4.0, intelligent manufacturing has become a symbol of the new information age. Xu et al [15] proposed an effective hybrid immune algorithm to solve the distributed permutation flow shop scheduling problem by designing a new cross mutation inoculation and local search operator. Zhang et al [17] proposed a two-stage heuristic search algorithm to solve the distributed flow shop scheduling problem with flexible assembly and installation time, with the objective of minimizing make span. This paper constructs a green manufacturing collaborative optimal scheduling model for a semiconductor wafer distributed heterogeneous factory for the first time, and designs an improved multi-objective Grey Wolf Optimizer (IMOGWO) to solve this problem.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have