Trajectory tracking with dynamic neural networks


Konar A., Becerikli Y. , Samad T.

1997 IEEE International Symposium on Intelligent Control, İstanbul, Türkiye, 16 - 18 Temmuz 1997, ss.173-180 identifier identifier

  • Doi Numarası: 10.1109/isic.1997.626448
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.173-180

Özet

The application of artificial neural networks to dynamical systems has been constrained by the non-dynamical nature popular network architectures. Many of-the difficulties that ensue-large network sizes, long training times, the need to predetermine buffer lengths- can be overcomed with dynamic neural networks. The minimization of a quadratic performance index is considered for trajectory tracking or process simulation applications. Two approaches for gradient computation are discussed: forward and adjoint sensitivity analysis. The computational complexity of the latter is significantly less, but it requires a backward integration capability. We also discuss two parameter updating methods: gradient descent and a Levenberg-Marquardt approach.