Designing an Artificial Muscle Based on PID Controller and Tuned by Neural Network with a NN Identification of the Plant


In this paper we are presenting a study on developing an Artificial Muscle based on a PID Controller tuned by a Neural Network with a NN Identification of the plant. The non linear identification of the Muscle is based on a NNARX (Neural Network Auto-Regressive exogenous) (Noorgard, 2000) structure. The NN used to control the PID parameters has a special learning algorithm in order to let the output of the closed loop formed by the motor and the controller to follow that of this non linear Muscle Model. An identification of the plant using Neural Network was developed in order to reduce the mathematics calculation when the plant transfer function is complicated or not known. Two structures are developed and compared, than a comparison with results obtained in our previous works is presented.

  • Abstract
  • Introduction
  • Muscle Model
  • Neural Identification of the Plant
  • Physical Emulation of a Muscle
  • Implementation and Results
  • Conclusions
  • References

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In