arrow
返回

Gaussian Process-Based Predictive Control for Periodic Error Correction

delete2016-01-01
delete82
PRE
AI
E
Edgar D. Klenske *
M
Melanie N. Zeilinger
B
Bernhard Schölkopf
P
Philipp Hennig
DOI:10.1109/TCST.2015.2420629delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Many controlled systems suffer from unmodeled nonlinear effects that recur periodically over time. Model-free controllers generally cannot compensate these effects, and good physical models for such periodic dynamics are challenging to construct. We investigate nonparametric system identification for periodically recurring nonlinear effects. Within a Gaussian process (GP) regression framework, we use a locally periodic covariance function to shape the hypothesis space, which allows for a structured extrapolation that is not possible with more widely used covariance functions. We show that hyperparameter estimation can be performed online using the maximum a posteriori point estimate, which provides an accuracy comparable with sampling methods as soon as enough data to cover the periodic structure has been collected. It is also shown how the periodic structure can be exploited in the hyperparameter optimization. The predictions obtained from the GP model are then used in a model predictive control framework to correct the external effect. The availability of good continuous predictions allows control at a higher rate than that of the measurements. We show that the proposed approach is particularly beneficial for sampling times that are smaller than, but of the same order of magnitude as, the period length of the external effect. In experiments on a physical system, an electrically actuated telescope mount, this approach achieves a reduction of about 20% in root mean square tracking error.
Keyword:
Adaptive control
nonlinear control systems
optimal control
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Control Systems Technology 封面图
IEEE Transactions on Control Systems Technology
IF:
3.9
论文数:
4.9K
被引数:
1.7W

机构

M
Max Planck Society
学者数:
8.2W
论文数: 7.7W
被引数: 3.3W
引用论文

引用论文

Assessment of fish consumption and mercury exposure among pregnant women in Jamaica and Trinidad & Tobago
err2016-12-01
err0
PREAI
errPhylicia Ricketts; Niladri Basu; Horace Fletcher; Mitko Voutchkov; Bharat Bassaw
err分享
err收藏
Chance-constrained model predictive control
err2004-04-16
err234
PREAI
errSchwarm, AT; Nikolaou, M
err分享
err收藏
err分享
err收藏
Predominio del genotipo G9 de rotavirus en Valencia y Castellón entre 2005 y 2007
err2010-01-01
err0
PREAI
errC.J. Téllez Castillo; R. Montava Vilaplana; M. Fernández Jiménez; J.M. Ribes Fernández; J. Buesa Gómez
err分享
err收藏
Chemically deposited thin films of PbSe as an absorber component in solar cell structures
err2011-08-01
err0
PREAI
errEnue Barrios-Salgado; M.T.S. Nair; P.K. Nair; Ralph A. Zingaro
err分享
err收藏
Synthesis of Nitrogen‐Containing Derivatives of (18α,19β)‐19‐Hydroxy‐2,3‐secooleanane‐2,3,28‐trioic Acid 28,19‐Lactone
err2013-09-18
err0
PREAI
errAndrey V. Shernyukov; Ilya Ya. Mainagashev; Dina V. Korchagina; Alexander M. Genaev; Nina I. Komarova; Nariman F. Salakhutdinov; Genrikh A. Tolstikov
err分享
err收藏
err分享
err收藏
学者 查看更多内容