A neural network controls the galvannealing process

High-quality galvanized steel strip is a need of today's manufacturers of v arious products. In particular, in the top-quality section, steel strips fo r the automotive, building, and consumer goods industries, only those steel producers who are applying state-of-the-art process technologies mill be s uccessful. For this reason, VOEST-ALPINE Industrieanlagenbau GmbH (VAI) and VOEST-ALPINE Stahl Lint have developed a new galvannealing control system to optimize this metallurgical process, As the latest improvement of the ga lvannealing control strategy, a neural network controller has been develope d by VAI in cooperation with the Christian Doppler Laboratory for Intellige nt Control Methods for Process Technologies, Vienna University of Technolog y. This paper describes the galvannealing process as far as it is necessary for the understanding of the controller functions, the controller structur e, and its essential functions. Furthermore, the used neural network struct ure and its integration in the controller system are explained. A discussio n of simulation and practical operation results shows the improvements achi eved by using a neural network controller in comparison to the conventional controller.