A dynamic evolutionary mechanism for mixed-production

Abstract

This paper describes a new dynamic evolutionary mechanism which assists process engineers in devising efficient processes for manufacturing high quality items where the mixed production approach is adopted. An adaptive system, including the use of genetic algorithms (GA) as a dynamic searching mechanism, is designed in order to maximize the stability of the quality control in the mixed production processes. GA is an effective approach in optimization as it is able to alter manufacturing variables so as to reach a global optimum in complex production processes such as multiple quality chains. The choice of the GA operators and its parameters, however, is a significant problem and inappropriate selection of chromosome structure can lead to poor performance. In order to deal with these issues, a dynamic parameter and operator setting approach with a mechanism based on quality control chart theory, is proposed. The approach allows a trade-off between exploration and exploitation processes in the search. The mechanism applies evolution evidence to supervise and adjust the GA parameter settings at run time. A prototype system has been implemented and applied to optimization problems in multiple quality chains. The experimental results have revealed that the dynamic setting approach can improve the performance of a GA process in multiple quality chains. The results also established that the dynamic setting approach is superior to a static one.

Keywords:

• Genetic algorithms
• Mixed production
• Multiple quality chains
• Optimization
• Dynamic parameter setting

Acknowledgement

We would like to express our gratitude to Dr Nick Godwin's invaluable comments on the early version of this paper.