Knowledge-based event control for flow-shops using simulation and rules

The requirements on production systems and their planning and control systems are constantly growing. Systems have to be flexible and provide viable solutions at the same time. Different planning and control approaches, such as optimization, simulation and combination of techniques etc., that attempt to solve the scheduling problems are available. Mathematical solutions which can be found in literature didn't solve the real-world problems in an appropriate way. Current knowledge based solutions did not give any value about decision reliability as well as their decision attributes are not differentiate enough. We are developing a new rule based approach by using a combination of simulation and a knowledge generation within a dynamic production planning and -control for flow-shops. Ideas of how knowledge can be trained by simulation are presented. Furthermore which kind of rules and attributes can be used and how decisions about the rule selection can be made are shown.