Smart Manufacturing Systems: A Game Theory based Approach

Abstract

This paper presents a novel approach for self-optimization and learning as well as plug-and-play control of highly flexible, modular manufacturing units. The approach is inspired by recent encouraging results of game theory (GT) based learning in computer and control science. However, instead of representing the entire control behavior as a strategic game which might results in long training times and huge data set requirements, we restrict the learning process to the supervisor level by defining appropriate parameters from the basic control level (BCL) to be learned by learning agents. To this end, we define a set of interface parameters to the BCL programmed by IEC 61131 compatible code, which will be used for learning. Typical control parameters include switching thresholds, timing parameters and transition conditions. These parameters will then be considered as players in a multi-player game resulting in a distributed optimization approach. We apply the approach to a laboratory testbed consisting of different production modules which underlines the efficiency improvements for manufacturing units. In addition, plug-and-produce control is enabled by the approach as different configuration of production modules can efficiently be put in operation by re-learning the parameter sets.