An SRWNN-based approach on developing a self-learning and self-evolving adaptive control system for motion platforms


Ari E. O. , Kocaoglan E.

INTERNATIONAL JOURNAL OF CONTROL, cilt.89, ss.380-396, 2016 (SCI İndekslerine Giren Dergi) identifier identifier

  • Cilt numarası: 89 Konu: 2
  • Basım Tarihi: 2016
  • Doi Numarası: 10.1080/00207179.2015.1078499
  • Dergi Adı: INTERNATIONAL JOURNAL OF CONTROL
  • Sayfa Sayıları: ss.380-396

Özet

In this paper, a self-recurrent wavelet neural network (SRWNN)-based indirect adaptive control architecture is modified for performing speed control of a motion platform. The transient behaviour of the original learning algorithm has been improved by modifying the learning rate updates. The contribution of the proposed modification has been verified via both simulations and experiments. Moreover, the performance of the proposed architecture is compared with robust RST designs performed on a similar benchmark system, to show that via adaptive nonlinear control, it is possible to obtain a fast step response without degrading the robustness of a multi-body mechanical system. Finally, the architecture is further improved so as to possess structural learning for populating the SRWNNs automatically, rather than employing static network structures, and simulation results are provided to show the performance of the proposed structural learning algorithm.