论文信息 - Automatic tuning of controllers using a neural-genetic system

Automatic tuning of controllers using a neural-genetic system

ABSTRACT Neural networks and genetic algorithms have been in the past successfully applied, separately, to controller tuning problems. In this paper we purpose to combine its joint use, by exploiting the nonlinear mapping capabilities of neural networks to model objective functions, and to use them to supply their values to a genetic algorithm which performs on-line minimization. Simulation results show that this is a valid approach, offering desired properties for on-line use such as a dramatic reduction in computation time and avoiding the need of perturbing the closed-loop operation

Peter J. Fleming | António E. Ruano | João M. G. Lima | Ana Beatriz da Piedade de Azevedo | Nuno M. Duarte

[1] António E. Ruano,et al. Neural networks assisted PID autotuning , 1997 .

[2] Peter J. Fleming,et al. A neural network controller , 1991 .

[3] Rosbi Mamat,et al. Comparison of alternative approaches to neural network PID autotuning , 1996 .

[4] Peter J. Fleming,et al. A connectionist approach to PID autotuning , 1991 .

[5] Peter J. Fleming,et al. A new formulation of the learning problem of a neural network controller , 1991, [1991] Proceedings of the 30th IEEE Conference on Decision and Control.