In this study, we propose the immune algorithm (IA) based on GA using a new chromosome representation to solve the job-shop scheduling problem (JSP). 1A realizes to collect various kinds of schedule solution (pareto solutions). Because a weighted scalar function is used to represent the multi-purpose function on JSP, it is important to explore a proper combination of weights for the weighted scalar function responding to manufacturing situation. However, it is hard to find out the proper combination of weights. We propose a knowledge acquiring method based self-organizing maps (SOM) to obtain a relation between the weights and pareto schedule solutions, which are obtained by the proposed 1A. This relation is so named the pareto optimum map. Numerical experiments verify that IA can obtain various types of schedules and that the pareto optimum map generated by IA and SOM can indicate the relation between the weights and schedule solutions.
展开▼