Neuro-genetic Pid autotuning

A new PID autotuning technique, involving neural networks and genetic algorithms is proposed. The validity of this approach is shown, through the results of several experiments. Special attention is given to the off-line training of one of the auto-tuner models, the criterion networks. Procedures us...

ver descrição completa

Detalhes bibliográficos
Autor principal: Lima, João (author)
Outros Autores: Azevedo, Ana Beatriz da Piedade de (author), Duarte, N. M. (author), Fonseca, C. M. (author), Ruano, Antonio (author), Fleming, P. J. (author)
Formato: conferenceObject
Idioma:eng
Publicado em: 2013
Assuntos:
Neural networks
Genetic algorithms
Autotuning
Texto completo:http://hdl.handle.net/10400.1/2315
País:Portugal
Oai:oai:sapientia.ualg.pt:10400.1/2315
Descrição
Resumo:A new PID autotuning technique, involving neural networks and genetic algorithms is proposed. The validity of this approach is shown, through the results of several experiments. Special attention is given to the off-line training of one of the auto-tuner models, the criterion networks. Procedures used to obtain good training data are described.

Registros relacionados