PID Neural Network Decoupling Control of Multi-variable System and its Application

DOI

10.2991/icimm-16.2016.54How to use a DOI?

Keywords

MPIDNN; Decoupling Control; Multi-variable; Simulation

Abstract

In this thesis, multi-output PID neural network (MPIDNN) is proposed based on the research on single-output PID and it is simulated. MPIDNN is also proposed for the characteristics of coupling system which is difficult to control in industrial process. The results of the simulation show that the control algorithm has the function of online learning to adjust parameters. For multi-input and multi-output system, by using the MPIDNN decoupling control method, there is no need to get the exact model of object. It can offset the effects of the internal model or other disturbance and achieve better control effect.

Copyright

© 2016, 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  - DongJiang Yu
AU  - WeiZhi Long
AU  - JiaBing He
PY  - 2016/11
DA  - 2016/11
TI  - PID Neural Network Decoupling Control of Multi-variable System and its Application
BT  - Proceedings of the 6th International Conference on Information Engineering for Mechanics and Materials
PB  - Atlantis Press
SP  - 288
EP  - 293
SN  - 2352-5401
UR  - https://doi.org/10.2991/icimm-16.2016.54
DO  - 10.2991/icimm-16.2016.54
ID  - Yu2016/11
ER  -