Nonlinear system identification using compressed sensing

Manjish Naik, Douglas Cochran

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper describes an approach to system identification based on compressive sensing and demonstrates its efficacy on a challenging classical benchmark single-input, multiple output (SIMO) mechanical system consisting of an inverted pendulum on a cart. The differential equations describing the system dynamics are to be determined from measurements of the system's input-output behavior. These equations are assumed to consist of the superposition, with unknown weights, of a small number of terms drawn from a large library of nonlinear terms. Under this assumption, compressed sensing allows the constituent library elements and their corresponding weights to be identified by decomposing a time-series signal of the system's outputs into a sparse superposition of corresponding time-series signals produced by the library components.

Original languageEnglish (US)
Title of host publicationConference Record - Asilomar Conference on Signals, Systems and Computers
Pages426-430
Number of pages5
DOIs
StatePublished - 2012
Event46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012 - Pacific Grove, CA, United States
Duration: Nov 4 2012Nov 7 2012

Other

Other46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012
CountryUnited States
CityPacific Grove, CA
Period11/4/1211/7/12

Fingerprint

Compressed sensing
Nonlinear systems
Identification (control systems)
Time series
Pendulums
Dynamical systems
Differential equations

Keywords

  • Basis Pursuit
  • Compressed Sensing
  • Inverted Pendulum
  • Non-Linear
  • Sparsity
  • System Identification

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Cite this

Naik, M., & Cochran, D. (2012). Nonlinear system identification using compressed sensing. In Conference Record - Asilomar Conference on Signals, Systems and Computers (pp. 426-430). [6489039] https://doi.org/10.1109/ACSSC.2012.6489039

Nonlinear system identification using compressed sensing. / Naik, Manjish; Cochran, Douglas.

Conference Record - Asilomar Conference on Signals, Systems and Computers. 2012. p. 426-430 6489039.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Naik, M & Cochran, D 2012, Nonlinear system identification using compressed sensing. in Conference Record - Asilomar Conference on Signals, Systems and Computers., 6489039, pp. 426-430, 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012, Pacific Grove, CA, United States, 11/4/12. https://doi.org/10.1109/ACSSC.2012.6489039
Naik M, Cochran D. Nonlinear system identification using compressed sensing. In Conference Record - Asilomar Conference on Signals, Systems and Computers. 2012. p. 426-430. 6489039 https://doi.org/10.1109/ACSSC.2012.6489039
Naik, Manjish ; Cochran, Douglas. / Nonlinear system identification using compressed sensing. Conference Record - Asilomar Conference on Signals, Systems and Computers. 2012. pp. 426-430
@inproceedings{cff398bcfe224eaeb1b1b3829f16472f,
title = "Nonlinear system identification using compressed sensing",
abstract = "This paper describes an approach to system identification based on compressive sensing and demonstrates its efficacy on a challenging classical benchmark single-input, multiple output (SIMO) mechanical system consisting of an inverted pendulum on a cart. The differential equations describing the system dynamics are to be determined from measurements of the system's input-output behavior. These equations are assumed to consist of the superposition, with unknown weights, of a small number of terms drawn from a large library of nonlinear terms. Under this assumption, compressed sensing allows the constituent library elements and their corresponding weights to be identified by decomposing a time-series signal of the system's outputs into a sparse superposition of corresponding time-series signals produced by the library components.",
keywords = "Basis Pursuit, Compressed Sensing, Inverted Pendulum, Non-Linear, Sparsity, System Identification",
author = "Manjish Naik and Douglas Cochran",
year = "2012",
doi = "10.1109/ACSSC.2012.6489039",
language = "English (US)",
isbn = "9781467350518",
pages = "426--430",
booktitle = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

}

TY - GEN

T1 - Nonlinear system identification using compressed sensing

AU - Naik, Manjish

AU - Cochran, Douglas

PY - 2012

Y1 - 2012

N2 - This paper describes an approach to system identification based on compressive sensing and demonstrates its efficacy on a challenging classical benchmark single-input, multiple output (SIMO) mechanical system consisting of an inverted pendulum on a cart. The differential equations describing the system dynamics are to be determined from measurements of the system's input-output behavior. These equations are assumed to consist of the superposition, with unknown weights, of a small number of terms drawn from a large library of nonlinear terms. Under this assumption, compressed sensing allows the constituent library elements and their corresponding weights to be identified by decomposing a time-series signal of the system's outputs into a sparse superposition of corresponding time-series signals produced by the library components.

AB - This paper describes an approach to system identification based on compressive sensing and demonstrates its efficacy on a challenging classical benchmark single-input, multiple output (SIMO) mechanical system consisting of an inverted pendulum on a cart. The differential equations describing the system dynamics are to be determined from measurements of the system's input-output behavior. These equations are assumed to consist of the superposition, with unknown weights, of a small number of terms drawn from a large library of nonlinear terms. Under this assumption, compressed sensing allows the constituent library elements and their corresponding weights to be identified by decomposing a time-series signal of the system's outputs into a sparse superposition of corresponding time-series signals produced by the library components.

KW - Basis Pursuit

KW - Compressed Sensing

KW - Inverted Pendulum

KW - Non-Linear

KW - Sparsity

KW - System Identification

UR - http://www.scopus.com/inward/record.url?scp=84876270828&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876270828&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2012.6489039

DO - 10.1109/ACSSC.2012.6489039

M3 - Conference contribution

AN - SCOPUS:84876270828

SN - 9781467350518

SP - 426

EP - 430

BT - Conference Record - Asilomar Conference on Signals, Systems and Computers

ER -