Title :
Network of dynamic neurons in fault detection systems
Author :
Korbiez, J. ; Obuchowicz, A. ; Patan, K.
Author_Institution :
Dept. of Robotics & Software Eng., Tech. Univ. of Zielona Gora, Poland
Abstract :
The neural-residual generator (NRG) construction for a dynamic system is the goal of this paper. The neural networks modeling the dynamic system are constructed with dynamics models of artificial neurons, which contain inner feedbacks. Such a model consists of an adder module, a linear dynamic system and a nonlinear activation function. Two optimization problems are solved with NRG construction: searching for an optimal network architecture and dynamic neuron model (DNM) network training. The boiler unit of a power plant is chosen as a modeled dynamic system
Keywords :
adders; boilers; fault diagnosis; feedback; neural nets; optimisation; power engineering computing; power plants; transfer functions; DNM network training; NRG; adder module; boiler unit; dynamic neuron model network training; dynamic neuron network; dynamic system; dynamics models; fault detection systems; inner feedbacks; linear dynamic system; neural-residual generator; nonlinear activation function; optimal network architecture; optimization problems; power plant; Artificial neural networks; Bibliographies; Fault detection; IIR filters; Intelligent networks; Neurons; Nonlinear dynamical systems; Power generation; Power system modeling; System identification;
Conference_Titel :
Systems, Man, and Cybernetics, 1998. 1998 IEEE International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-4778-1
DOI :
10.1109/ICSMC.1998.728167
