Title :
Enhancing multi-layer perceptron [process control and modelling]
Author :
Galán, R. ; Mariño, M. ; Jiménez, A.
Author_Institution :
Dept. de Automatica, Ingenieria Electron. e Inf. Ind., Univ. Politecnica de Madrid, Spain
fDate :
27 Jun-2 Jul 1994
Abstract :
This paper present the results of a research on process modelling and control with neural networks, carried out in DISAM: Division de Ingenieria de Sistemas y Automatica, Universidad Politecnica de Madrid. The main goal of this research is the integration of neural networks in intelligent control applications of complex processes. A performance evaluation analyzing the number of delays, hidden layers and the quality of learning inputs is shown. Finally, the authors propose an enhancement of inputs with new information-products of inputs-to improve the accuracy of the neural network
Keywords :
intelligent control; learning (artificial intelligence); multilayer perceptrons; neurocontrollers; process control; accuracy; delays; hidden layers; multi-layer perceptron; neural networks; performance evaluation; process control; process modelling; Adaptive control; Backpropagation; Delay; Industrial control; Intelligent control; Multi-layer neural network; Multilayer perceptrons; Neural networks; Performance analysis; Process control;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374642
