Gaussian Processes-based Parametric Identification for Dynamical Systems

被引：1

作者：

Benosman, Mouhacine ^{[1
]}

Farahmand, Amir-massoud ^{[1
]}

机构：

[1] MERL, Cambridge, MA 02139 USA

来源：

IFAC PAPERSONLINE | 2017年 / 50卷 / 01期

关键词：

DIFFERENTIAL-EQUATIONS; MODEL;

D O I：

10.1016/j.ifacol.2017.08.2431

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper we present some results on parametric identification for dynamical systems. More specifically, we consider the general case of dynamics described by partial differential equations (PDEs), which includes the special case of ordinary differential equations (ODES). We follow a stochastic approach and formulate the identification problem as a Gaussian process optimization with respect to the unknown parameters of the PDE. We use proper orthogonal decomposition (POD) model reduction theory together with a data-driven Gaussian Process Upper Confidence Bound (GP-UCB), to solve the identification problem. The proposed approach is validated on the coupled Burgers' equation benchmark. (C) 2017, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

引用

页码：14034 / 14039

页数：6

共 50 条

[21] Parametric Identification of a Dynamical System with Switching
Golovkina, Anna
Kozynchenko, Vladimir
COMPUTATIONAL SCIENCE AND ITS APPLICATIONS - ICCSA 2022 WORKSHOPS, PART IV, 2022, 13380 : 557 - 569
[22] Dynamical systems identification using Gaussian process models with incorporated local models
Azman, K.
Kocijan, J.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2011, 24 (02) : 398 - 408
[23] Impact of the Parametric Noise on Map-based Dynamical Systems
Bashkirtseva, I.
Tsvetkov, I.
APPLICATION OF MATHEMATICS IN TECHNICAL AND NATURAL SCIENCES (AMITANS'18), 2018, 2025
[24] Dynamical Pose Filtering for Mixtures of Gaussian Processes
Fergie, Martin
Galata, Aphrodite
PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2012, 2012,
[25] Gaussian processes and universal parametric decorrelations of wavefunctions
Center for Theoretical Physics, Sloane Physics Laboratory, Yale University, New Haven, CT 06520, United States
Phys Lett Sect A Gen At Solid State Phys, 1-2 (21-25):
[26] Gaussian processes and universal parametric decorrelations of wavefunctions
Mitchell, D
Alhassid, Y
Kusnezov, D
PHYSICS LETTERS A, 1996, 215 (1-2) : 21 - 25
[27] Equal transfer processes-based distance protection of EHV transmission lines
Wen, Minghao
Chen, Deshu
Yin, Xianggen
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2013, 52 : 81 - 86
[28] PARAMETRIC MODELS OF NONSTATIONARY GAUSSIAN-PROCESSES
GRIGORIU, M
PROBABILISTIC ENGINEERING MECHANICS, 1995, 10 (02) : 95 - 102
[29] Predicting Latent States of Dynamical Systems With State-Space Reconstruction and Gaussian Processes
Butler, Kurt
Feng, Guanchao
Mikell, Charles B.
Mofakham, Sima
Djuric, Petar M.
2022 30TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2022), 2022, : 2216 - 2220
[30] Identification of quadratic Volterra systems driven by non-Gaussian processes
Zoubir, A.M.
IEEE Transactions on Signal Processing, 1995, 43 (05): : 1302 - 1306

← 1 2 3 4 5 →