Title :
Identification of non-linear dynamic systems in power plants
Author :
Alippi, C. ; Piuri, V.
Author_Institution :
Dipartimento di Elettronica ed Inf., Politecnico di Milano, Italy
Abstract :
Problems related to the identification of non-linear systems are analysed by considering as a case study the neural modelling of the furnace and the superheater systems. As far as the furnace is concerned, identification addresses neural modelling of the total heat reaching the evaporator; the process is not dynamic because the heat generation is particularly rapid. Conversely, this is not the case in a superheater where dynamics play a relevant role: identification of the steam and the flue gas temperatures requires specific recurrent type neural models. Identification of such systems, belonging to a one-through 320 MW group, are the first step in developing computationally simple distributed nonlinear neural models for the whole plant. Issues related to training data extraction, training algorithms and stability are taken into account
Keywords :
feedforward neural nets; furnaces; identification; learning (artificial intelligence); nonlinear dynamical systems; power system analysis computing; power system stability; recurrent neural nets; steam plants; 320 MW; distributed nonlinear neural models; flue gas temperature; furnace; neural modelling; nonlinear dynamic system identification; one-through 320 MW group; power plants; recurrent type neural models; stability; steam temperature; superheater systems; training algorithms; training data extraction; Data mining; Differential algebraic equations; Distributed computing; Flue gases; Furnaces; Network topology; Neural networks; Power generation; Power system modeling; Predictive models; Stability; Temperature; Training data; Turbines;
Conference_Titel :
Circuits and Systems, 1995., Proceedings., Proceedings of the 38th Midwest Symposium on
Conference_Location :
Rio de Janeiro
Print_ISBN :
0-7803-2972-4
DOI :
10.1109/MWSCAS.1995.504484
