An information-theoretic measure for anomaly detection in complex dynamical systems

Abhishek Srivastav, Asok Ray, Shalabh Gupta

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

This paper presents information-theoretic analysis of time-series data to detect slowly evolving anomalies (i.e., deviations from a nominal operating condition) in dynamical systems. A measure for anomaly detection is formulated based on the concepts derived from information theory and statistical thermodynamics. The underlying algorithm is first tested on a low-dimensional complex dynamical system with a known structure-the Duffing oscillator with slowly changing dissipation. Then, the anomaly detection tool is experimentally validated on test specimens of 7075-T6 aluminum alloy under cyclic loading. The results are presented for both cases and the efficacy of the proposed method is thus demonstrated for systems of known and unknown structures.

Original languageEnglish (US)
Pages (from-to)358-371
Number of pages14
JournalMechanical Systems and Signal Processing
Volume23
Issue number2
DOIs
StatePublished - Feb 1 2009

Fingerprint

Dynamical systems
Information analysis
Statistical mechanics
Information theory
Time series
Aluminum alloys

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Signal Processing
  • Civil and Structural Engineering
  • Aerospace Engineering
  • Mechanical Engineering
  • Computer Science Applications

Cite this

@article{ff1ff99c66d040e994ca079d58899ce8,
title = "An information-theoretic measure for anomaly detection in complex dynamical systems",
abstract = "This paper presents information-theoretic analysis of time-series data to detect slowly evolving anomalies (i.e., deviations from a nominal operating condition) in dynamical systems. A measure for anomaly detection is formulated based on the concepts derived from information theory and statistical thermodynamics. The underlying algorithm is first tested on a low-dimensional complex dynamical system with a known structure-the Duffing oscillator with slowly changing dissipation. Then, the anomaly detection tool is experimentally validated on test specimens of 7075-T6 aluminum alloy under cyclic loading. The results are presented for both cases and the efficacy of the proposed method is thus demonstrated for systems of known and unknown structures.",
author = "Abhishek Srivastav and Asok Ray and Shalabh Gupta",
year = "2009",
month = "2",
day = "1",
doi = "10.1016/j.ymssp.2008.04.007",
language = "English (US)",
volume = "23",
pages = "358--371",
journal = "Mechanical Systems and Signal Processing",
issn = "0888-3270",
publisher = "Academic Press Inc.",
number = "2",

}

An information-theoretic measure for anomaly detection in complex dynamical systems. / Srivastav, Abhishek; Ray, Asok; Gupta, Shalabh.

In: Mechanical Systems and Signal Processing, Vol. 23, No. 2, 01.02.2009, p. 358-371.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An information-theoretic measure for anomaly detection in complex dynamical systems

AU - Srivastav, Abhishek

AU - Ray, Asok

AU - Gupta, Shalabh

PY - 2009/2/1

Y1 - 2009/2/1

N2 - This paper presents information-theoretic analysis of time-series data to detect slowly evolving anomalies (i.e., deviations from a nominal operating condition) in dynamical systems. A measure for anomaly detection is formulated based on the concepts derived from information theory and statistical thermodynamics. The underlying algorithm is first tested on a low-dimensional complex dynamical system with a known structure-the Duffing oscillator with slowly changing dissipation. Then, the anomaly detection tool is experimentally validated on test specimens of 7075-T6 aluminum alloy under cyclic loading. The results are presented for both cases and the efficacy of the proposed method is thus demonstrated for systems of known and unknown structures.

AB - This paper presents information-theoretic analysis of time-series data to detect slowly evolving anomalies (i.e., deviations from a nominal operating condition) in dynamical systems. A measure for anomaly detection is formulated based on the concepts derived from information theory and statistical thermodynamics. The underlying algorithm is first tested on a low-dimensional complex dynamical system with a known structure-the Duffing oscillator with slowly changing dissipation. Then, the anomaly detection tool is experimentally validated on test specimens of 7075-T6 aluminum alloy under cyclic loading. The results are presented for both cases and the efficacy of the proposed method is thus demonstrated for systems of known and unknown structures.

UR - http://www.scopus.com/inward/record.url?scp=56249103088&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56249103088&partnerID=8YFLogxK

U2 - 10.1016/j.ymssp.2008.04.007

DO - 10.1016/j.ymssp.2008.04.007

M3 - Article

AN - SCOPUS:56249103088

VL - 23

SP - 358

EP - 371

JO - Mechanical Systems and Signal Processing

JF - Mechanical Systems and Signal Processing

SN - 0888-3270

IS - 2

ER -