Machine intelligence for adaptable closed loop and open loop production engineering systems

Johannes Günther

Abstract: This thesis investigates the application of machine learning algorithms for industrial production processes. First, the PID controller as an already existing closed loop control approach is improved. For this purpose, a neural network tunes the PID parameters, while the process is running. Second, a new architecture, consisting of several machine learning algorithms, is introduced for industrial laser welding. Following this approach, the control can be changed from open to closed loop.