This thesis documents the research and development of an architecture for cyber-physical production systems with a primary focus on the optimization of the control parameters of variable and adaptive production processes.
The algorithmic solution developed utilizes process data to generate adequate test functions and test and tune feasible algorithms during runtime for real-world problems.
In combination with the application of state-of-the-art methods from benchmarking, this enables an automatic selection of the most promising algorithm from a given portfolio according to established performance criteria.
The thesis was supervised by Prof. Dr. Günter Rudolph, Technische Universität Dortmund and Prof. Dr. Thomas Bartz-Beielstein, Technische Hochschule Köln.