Knowledge of process requirements, system capacities, and system reliability are the premises on which control policies are formulated. In dynamic manufacturing environments, engineering change to the product, the process, and the production equipment can cause these premises to be violated and thereby control policy to become less effective. An accurate, up-to-date model of the production system is essential to production control, but a challenge to maintain. Production system identification is a methodology that develops and updates a model of the production system. Machine-learning methods of process mining develop a model of the system by means of an analysis of frequently occurring events described in system logs. Such methods fall short of addressing the challenge of dynamic production system identification in three important respects: (1) Rather than frequently occurring events, they are the infrequent exceptional events that provide insight into system capacities and system reliability. (2) Production system behaviour, especially machine blocking and starvation, are well-understood phenomena; an analysis of cause and effects based on this understanding could be used to guide search to an accurate system model. (3) Process mining lacks inherent means to update the model as the modeled system changes. This paper describes a genetic programming methodology that uses Petri nets, probabilistic neural nets, and a causal model of production system dynamics to address these shortcomings.
Journal of Manufacturing Systems
system identification , production systems , genetic programming