Model Reference Self-Adaptive Control Systems based on Single Neurons

DOI

10.2991/mseee-17.2017.5How to use a DOI?

Keywords

Model reference, Vector control, Single neuron.

Abstract

This paper presents a model based on single neuron for adaptive control. For the weakness of traditional PID controllers and complex neural networks, based on the model reference adaptive control, this text using a single neuron instead of a complex neural network, choose the linear function as the reference model, and take the velocity change into the error function, and built the control system with the structure of magnetic chain open-loop and rotate speed close-loop. And then, the control system simulation model based on this control method was established by asynchronous motor, and applied the TMS320 series DSP to set up experimental control system. The simulation and experimental results show that the controller robust is strong, with adaptive characteristics of time-varying parameters and load.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xiaobin Liu
AU  - Mengda Li
PY  - 2017/08
DA  - 2017/08
TI  - Model Reference Self-Adaptive Control Systems based on Single Neurons
BT  - Proceedings of the 2017 International Conference on Material Science, Energy and Environmental Engineering (MSEEE 2017)
PB  - Atlantis Press
SP  - 23
EP  - 27
SN  - 2352-5401
UR  - https://doi.org/10.2991/mseee-17.2017.5
DO  - 10.2991/mseee-17.2017.5
ID  - Liu2017/08
ER  -