Process planning with genetic algorithms on results of knowledge-based reasoning

The paper presents a new approach to solving even unusually complex problems of computer-aided process planning (CAPP). Main principles are based on the analysis of the roles and relations of CAPP in advanced manufacturing systems. Planning is carried out in several stages, by using both domain-specific knowledge and domain-independent, general methods. First, by knowledge-based reasoning, repertoires of plan elements and technological constraints are created that the final solutions must meet. Then, a global plan merging process generates plan variants so as to meet the given optimization objective. Among the various plan merging methods, one using genetic algorithms stands preeminent by its performance and robustness. Domain-specific knowledge, methods of reasoning and plan merging are described in detail.