An Effective Chromosome Representation for Optimising Product Quality

Optimising variables in the quality control of production can be a complex issue, as it may involve many different constraints and expectations on the quality of products which are normally provided from different organisations to form a multiple supply chain. The challenge of measuring product interdependence across various supply chains and identifying a trade-off between quality and cost is not trivial. In this research, which applies dynamic genetic algorithms, we propose a new approach to representing the problem domain within the chromosome which takes advantage of schema evolution and domain knowledge to refine the chromosome structure. As a result, different weightings can be derived and applied to the genes in order to improve searching efficiency of the genetic algorithms (GA). An example of multiple supply chains has been used to evaluate the proposed approach. The results show that the proposed approach outperforms traditional GA approaches.