ARTIFICIAL INTELLIGENCE APPLICATIONS IN PRODUCTION SCHEDULING PROBLEMS: A REVIEW STUDY

Abstract

ABSTRACT

Researchers have developed many methods for solving production scheduling problems, which have an important place in short-term production planning. In addition to mathematical methods in the literature, it is possible to encounter heuristic, meta heuristic and  hyper heuristic methods and even hybrid methods. The aim of this study is to help researchers who want to work on production scheduling to determine the methods they can use. In this study, a brief summary of the literature on artificial intelligence applications encountered in the production scheduling literature is presented. First of all, the importance and types of production scheduling problems are explained and the methods used in their solution are shown. In the next part, a literature summary including some studies using artificial intelligence methods in production scheduling problems is presented. In the literature research, it has been seen that genetic algorithms, particle swarm optimization and hybrid approaches are mostly used in the solution of job shop type scheduling problems; genetic algorithms, evolutionary programming and hybrid algorithms are mostly used in the solution of flow shop scheduling problems; mostly used  genetic algorithms, ant colony optimization and hybrid approaches in solution of batch scheduling problems; in the solution of manufacturing cell scheduling problems,  genetic algorithms, artificial neural networks, deep learning approaches and hybrid approaches are mostly used.