CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 先进机器人
Neural-Network-Based Nonlinear Model Predictive Control for Piezoelectric Actuators
Cheng, Long; Liu, Weichuan; Hou, ZengGuang; Yu, Junzhi; Tan, Min
Source PublicationIEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
2015-12-01
Volume62Issue:12Pages:7717-7727
SubtypeArticle
AbstractPiezoelectric actuators (PEAs) have been widely used in nanotechnology due to their characteristics of fast response, large mass ratio, and high stiffness. However, hysteresis, which is an inherent nonlinear property of PEAs, greatly deteriorates the control performance of PEAs. In this paper, a nonlinear model predictive control (NMPC) approach is proposed for the displacement tracking problem of PEAs. First, a "nonlinear autoregressive-moving-average with exogenous inputs" (NARMAX) model of PEAs is implemented by multilayer neural networks; second, the tracking controlproblem is converted into an optimization problem by the principle of NMPC, and then, it is solved by the Levenberg-Marquardt algorithm. The most distinguished feature of the proposed approach is that the inversion model of hysteresis is no longer a necessity, which avoids the inversion imprecision problem encountered in the widely used inversion-based control algorithms. To verify the effectiveness of the proposed modeling and control methods, experiments are made on a commercial PEA product (P-753.1CD, Physik Instrumente), and comparisons with some existing controllers and a commercial proportional-integral-derivative controller are conducted. Experimental results show that the proposed scheme has satisfactory modeling and control performance. 
KeywordNeuralnetworks Nonlinearautoregressive-moving-average With Exogenous Inputs (Narmax) Piezoelectric Actuator (Pea) Predictive Control
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TIE.2015.2455026
WOS KeywordPIEZOCERAMIC ACTUATOR ; INVERSE-FEEDFORWARD ; TRACKING CONTROL ; PREISACH MODEL ; HYSTERESIS ; COMPENSATION ; IDENTIFICATION
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China(61422310 ; Beijing Nova Program(Z121101002512066) ; 61370032 ; 61375102 ; 61225017 ; 61421004)
WOS Research AreaAutomation & Control Systems ; Engineering ; Instruments & Instrumentation
WOS SubjectAutomation & Control Systems ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
WOS IDWOS:000365019500040
Citation statistics
Cited Times:64[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/10517
Collection复杂系统管理与控制国家重点实验室_先进机器人
Corresponding AuthorCheng, Long
AffiliationState Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
Recommended Citation
GB/T 7714
Cheng, Long,Liu, Weichuan,Hou, ZengGuang,et al. Neural-Network-Based Nonlinear Model Predictive Control for Piezoelectric Actuators[J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS,2015,62(12):7717-7727.
APA Cheng, Long,Liu, Weichuan,Hou, ZengGuang,Yu, Junzhi,&Tan, Min.(2015).Neural-Network-Based Nonlinear Model Predictive Control for Piezoelectric Actuators.IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS,62(12),7717-7727.
MLA Cheng, Long,et al."Neural-Network-Based Nonlinear Model Predictive Control for Piezoelectric Actuators".IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 62.12(2015):7717-7727.
Files in This Item: Download All
File Name/Size DocType Version Access License
TIE.pdf(1541KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Cheng, Long]'s Articles
[Liu, Weichuan]'s Articles
[Hou, ZengGuang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Cheng, Long]'s Articles
[Liu, Weichuan]'s Articles
[Hou, ZengGuang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Cheng, Long]'s Articles
[Liu, Weichuan]'s Articles
[Hou, ZengGuang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: TIE.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.