Early Detection and Identification of Undesirable States in Chemical Plants Using Neural Networks
Early Detection and Identification of Undesirable States in Chemical Plants Using Neural Networks
Neumann, J.; Deerberg, G.; Schlüter, S.; Schmitt, W.; Hessel, G.
The suitability of pattern recognition for safety diagnosis of chemical plants is discussed. Experiments in a miniplant and with a process simulator are carried out. The process characteristics are treated with different recognition methods and classified with the aid of expert know how. Afterwards, the trained system can be used for process diagnosis. The capability of neural networks for this problem can be shown.
-
Contribution to external collection
Keil, F., Mackens, W., Voß, H., Werther, J. (eds): Scientific Computing in Chemical Engineering II - Simulation, Image Processing, Optimization and Control, Springer-Verlag Berlin, Heidelberg, New York, 1999, S. 380-387, LSBN: 3-540-65851-3
Permalink: https://www.hzdr.de/publications/Publ-2860
