Title :
An ANN´s evolved by a new evolutionary system and its application
Author :
Zhang, Chunkai ; Shao, Huihe
Author_Institution :
Autom. Dept., Shanghai Jiaotong Univ., China
Abstract :
The paper presents a new evolutionary system for evolving artificial neural networks (ANN). In the process of evolution, the network architecture and the node weights of ANN are evolved alternately, and the evolution value of network architecture is related to the error value of ANN evolved by node weights. An evolved ANN has been used in modelling product quality estimator for a fractionator of the hydrocracking unit in the oil refining industry. The results show that it has good accuracy and generalisation ability
Keywords :
evolutionary computation; neural nets; ANN; artificial neural network evolution; fractionator; hydrocracking unit; node weights; oil refining industry; product quality estimator modelling; Aerospace industry; Artificial neural networks; Automation; Evolutionary computation; Fractionation; Oil refineries; Particle swarm optimization; Partitioning algorithms; Random number generation; Search problems;
Conference_Titel :
Decision and Control, 2000. Proceedings of the 39th IEEE Conference on
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7803-6638-7
DOI :
10.1109/CDC.2000.912257
