Model Reference Adaptive Control based-on Neural Networks for Nonlinear time-varying System

Authors: ,

Abstract: This paper presents a Direct Model Reference Adaptive Control (MRAC) for nonlinear time-varying system. A mechanism adaptation algorithm is proposed. This corresponding algorithm depends on the error between the actual plant output and the output of the reference model, and also is depending on variable learning rate. The control strategy is based on two-steps; the first is initialization parameters of the controller using reduced number of observation. In the second phase, the parameters of the controller are directly tuned from the training data via the tracking error. The simulation results show that the proposed algorithm is simple to implement and may be extended to multivariable system.

International Journal of Applied Mathematics, Computational Science and Systems Engineering, E-ISSN: 2766-9823, Volume 1, 2019, Art. #2

PDF
XML
Cite
×
Citation Tools
WSEAS AMA
Ayachi Errachdi, Mohamed Benrejeb, "Model Reference Adaptive Control based-on Neural Networks for Nonlinear time-varying System," International Journal of Applied Mathematics, Computational Science and Systems Engineering, vol. 1, pp. 6-10, 2019, DOI:
Ayachi Errachdi, Mohamed Benrejeb. Model Reference Adaptive Control based-on Neural Networks for Nonlinear time-varying System. International Journal of Applied Mathematics, Computational Science and Systems Engineering. 2019;1:6-10.
Copy to Clipboard
Citation copied to Clipboard

Certification

---