Intelligent modelling in manufacturing

Purpose: Modeling of production systems is very important and makes optimization of complicated relation in production system possible. The purpose of this paper is introducing artificial techniques, like Genetic Algorithms in modeling and optimization of job shop scheduling in production environment and in programming of CNC machine tools. Design/methodology/approach: Conventional methods are not suitable for solving such complicated problems. Therefore Artificial Intelligent method was used. We apply Genetic Algorithm method. Genetic Algorithms are computation methods owing their power in particular to autonomous mechanisms in biological evolution, such as selection, “survival of the fittest” (competition), and recombination. Findings: In example solutions are developed for an optimization problem of job shop scheduling by natural selection. Thus no explicit knowledge was required about how to create a good solution: the evolutionary algorithm itself implicitly builds up knowledge about good solutions, and autonomously absorbs knowledge. CNC machining time was significant shorter by using GA method for NC programming. Research limitations/implications: The system was developed for PC and tested in simulation process. It needs to be tested more in detail in the real manufacturing environment. Practical implications: It is suitable for small and medium-sized companies. Human errors are avoid or at lover level. It is important for engineers in job – shops. Originality/value: The present paper is a contribution to more intelligent systems in production environment. It used genetic based methods to solve engineering problem.