On data-driven identification: Is automatically discovering equations of motion from data a Chimera?

被引：6

作者：

Antonelli, Gianluca ^{[1
]}

Chiaverini, Stefano ^{[1
]}

Di Lillo, Paolo ^{[1
]}

机构：

[1] Univ Cassino & Southern Lazio, Dept Elect & Informat Engn, Cassino, Italy

来源：

NONLINEAR DYNAMICS | 2023年 / 111卷 / 07期

关键词：

Identification theory; Dynamic modeling; Machine learning; Data-driven identification; MODEL;

D O I：

10.1007/s11071-022-08192-x

中图分类号：

TH [机械、仪表工业];

学科分类号：

0802 ;

摘要：

In this paper, a simple inverted pendulum is considered in order to discover, or extract, its dynamic equation from experimental data acquired during proper motion. This textbook case study achieved both in numerical simulations and with an off-the-shelf hardware reveals structural deficiencies in algorithms pretending to distill physics from data. In short, the outcome is that the obtained equations are not reliable and thus the model is practically equivalent to a black-box one. The data appropriateness is checked against a model-based identification. Is automatically discovering equations of motion from data then a Chimera?

引用

页码：6487 / 6498

页数：12

共 33 条

[1] AAVV, 2021, EUR
[2] A systematic procedure for the identification of dynamic parameters of robot manipulators
Antonelli, G
Caccavale, F
Chiacchio, P
[J]. ROBOTICA, 1999, 17 : 427 - 435
[3] Dynamic Mode Decomposition for Compressive System Identification
Bai, Zhe
Kaiser, Eurika
Proctor, Joshua L.
Kutz, J. Nathan
Brunton, Steven L.
[J]. AIAA JOURNAL, 2020, 58 (02) : 561 - 574
[4] Estimation of perturbations in robotic behavior using dynamic mode decomposition
Berger, Erik
Sastuba, Mark
Vogt, David
Jung, Bernhard
Ben Amor, Heni
[J]. ADVANCED ROBOTICS, 2015, 29 (05) : 331 - 343
[5] Billard A., 2022, Learning for adaptive and reactive robot control:a dynamical systems approach
[6] Data-Driven Control of Soft Robots Using Koopman Operator Theory
Bruder, Daniel
Fu, Xun
Gillespie, R. Brent
Remy, C. David
Vasudevan, Ram
[J]. IEEE TRANSACTIONS ON ROBOTICS, 2021, 37 (03) : 948 - 961
[7] Brunton S.L., 2019, The Koopman Operator in Systems and Control, DOI [DOI 10.1017/9781108380690, DOI 10.1007/978-3-030-35713-98]
[8] Discovering governing equations from data by sparse identification of nonlinear dynamical systems
Brunton, Steven L.
Proctor, Joshua L.
Kutz, J. Nathan
[J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2016, 113 (15) : 3932 - 3937
[9] Sparse identification of nonlinear dynamical systems via reweighted l1-regularized least squares
Cortiella, Alexandre
Park, Kwang-Chun
Doostan, Alireza
[J]. COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2021, 376
[10] Cranmer M., 2020, arXiv

← 1 2 3 4 →