Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Assessment and Identification of Undesired States in Chemical Semibatch Reactors Using Neural Networks

: Hessel, Günther; Kryk, H.; Schmitt, Wilfried; Seiler, T.; Weiß, Frank-Peter; Deerberg, Görge; Neumann, Joachim


Edelmayer, A. ; International Federation of Automatic Control -IFAC-:
4th IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 2000 : Budapest, Hungary, 14-16 June 2000
Amsterdam: Elsevier, 2000 (IFAC proceedings series 33, Nr.11)
Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS) <4, 2000, Budapest>
Fraunhofer UMSICHT Oberhausen ()
fault diagnosis; Process identification; Supervision; Artificial intelligence; Classifiers; Neural network; chemical industry

This paper presents a neural-network approach to operator-independent as-sessing the operational states of chemical semibatch reactors. The suitability of neu-ral networks for process monitoring was investigated in a miniplant in which strongly exothermic chemical reference processes were carried out. Before being applied to state classification, the neural-network classifiers first have be trained using process data of normal and abnormal sequences of reaction to establish a non-linear decision model between process parameters and state classification. After-wards, the trained classifiers can be used for process monitoring. Best results were reached with three-layer perceptron networks. For assessing the danger potential of fault states, separate perceptron networks for danger classification and for fault identification were used.