Open AccessARNISMC for MLS with global positioning tracking control
Author(s) -
Chen SengChi,
Kuo ChunYi
Publication year - 2018
Publication title -
iet electric power applications
Language(s) - English
Resource type - Journals
ISSN - 1751-8679
DOI - 10.1049/iet-epa.2017.0690
Subject(s) - control theory (sociology) , tracking (education) , controller (irrigation) , estimator , computer science , artificial neural network , control engineering , control (management) , engineering , artificial intelligence , mathematics , psychology , pedagogy , statistics , agronomy , biology
This study develops an adaptive recurrent neural network (NN) intelligentsliding‐mode controller (ARNISMC) for magnetic levitationsystem (MLS). First, a non‐linear dynamic model of the MLS is derived.Thereafter, a SM controller (SMC) method is presented to compensate for theuncertainties in the MLS. In addition, to enhance the control effort of aconventional SMC and further increase the tracking performance of the MLS, theuncertainty terms of the system dynamics can be estimated online by using an ARradial basis function NN estimator. Accordingly, the proposed controller notonly offers the accurate positioning tracking control, minimises steady‐stateerror, and improves conventional controller performance but also provides globalpositioning tracking control, which has not been previously reported in theliteratures. It can effectively solve problems associated with typical MLScontroller design. Moreover, the satisfactory tracking performance can beobserved from the experimental results by adopting the proposed ARNISMCscheme.