Intelligent nonsingular terminal sliding-mode control using MIMO elman neural network for piezo-flexural nanopositioning stage

Faa Jeng Lin, Shih Yang Lee, Po Huan Chou

Research output: Contribution to journalArticlepeer-review

21 Scopus citations

Abstract

The objective of this study is to develop an intelligent nonsingular terminal sliding-mode control (INTSMC) system using an Elman neural network (ENN) for the threedimensional motion control of a piezo-flexural nanopositioning stage (PFNS). First, the dynamic model of the PFNS is derived in detail. Then, to achieve robust, accurate trajectory-tracking performance, a nonsingular terminal sliding-mode control (NTSMC) system is proposed for the tracking of the reference contours. The steady-state response of the control system can be improved effectively because of the addition of the nonsingularity in the NTSMC. Moreover, to relax the requirements of the bounds and discard the switching function in NTSMC, an INTSMC system using a multi-input-multioutput (MIMO) ENN estimator is proposed to improve the control performance and robustness of the PFNS. The ENN estimator is proposed to estimate the hysteresis phenomenon and lumped uncertainty, including the system parameters and external disturbance of the PFNS online. Furthermore, the adaptive learning algorithms for the training of the parameters of the ENN online are derived using the Lyapunov stability theorem. In addition, two robust compensators are proposed to confront the minimum reconstructed errors in INTSMC. Finally, some experimental results for the tracking of various contours are given to demonstrate the validity of the proposed INTSMC system for PFNS.

Original languageEnglish
Article number6373795
Pages (from-to)2716-2730
Number of pages15
JournalIEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
Volume59
Issue number12
DOIs
StatePublished - 2012

Fingerprint

Dive into the research topics of 'Intelligent nonsingular terminal sliding-mode control using MIMO elman neural network for piezo-flexural nanopositioning stage'. Together they form a unique fingerprint.

Cite this