Failure precursor detection in complex electrical systems using symbolic dynamics

R. P. Patankar, V. Rajagopalan, A. Ray

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Failures in a plant’s electrical components are a major source of performance degradation and plant unavailability. In order to detect and monitor failure precursors and anomalies early in electrical systems, we have developed a signal processing method that can detect and map patterns to an anomaly measure. Application of this technique for failure precursor detection in electronic circuits resulted in robust detection. This technique was observed to be superior to conventional pattern recognition techniques such as neural networks and principal component analysis for anomaly detection. Moreover, this technique based on symbolic dynamics offers superior robustness due to averaging associated with experimental probability calculations. It also provided a monotonically increasing smooth anomaly plot which was experimentally repeatable to a remarkable accuracy.

Original languageEnglish (US)
Pages (from-to)68-77
Number of pages10
JournalInternational Journal of Signal and Imaging Systems Engineering
Volume1
Issue number1
DOIs
StatePublished - Jan 1 2008

Fingerprint

Principal component analysis
Pattern recognition
Signal processing
Neural networks
Degradation
Networks (circuits)

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

@article{9fa75862892946fa959374917db56d01,
title = "Failure precursor detection in complex electrical systems using symbolic dynamics",
abstract = "Failures in a plant’s electrical components are a major source of performance degradation and plant unavailability. In order to detect and monitor failure precursors and anomalies early in electrical systems, we have developed a signal processing method that can detect and map patterns to an anomaly measure. Application of this technique for failure precursor detection in electronic circuits resulted in robust detection. This technique was observed to be superior to conventional pattern recognition techniques such as neural networks and principal component analysis for anomaly detection. Moreover, this technique based on symbolic dynamics offers superior robustness due to averaging associated with experimental probability calculations. It also provided a monotonically increasing smooth anomaly plot which was experimentally repeatable to a remarkable accuracy.",
author = "Patankar, {R. P.} and V. Rajagopalan and A. Ray",
year = "2008",
month = "1",
day = "1",
doi = "10.1504/IJSISE.2008.017776",
language = "English (US)",
volume = "1",
pages = "68--77",
journal = "International Journal of Signal and Imaging Systems Engineering",
issn = "1748-0698",
publisher = "Inderscience Enterprises Ltd",
number = "1",

}

Failure precursor detection in complex electrical systems using symbolic dynamics. / Patankar, R. P.; Rajagopalan, V.; Ray, A.

In: International Journal of Signal and Imaging Systems Engineering, Vol. 1, No. 1, 01.01.2008, p. 68-77.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Failure precursor detection in complex electrical systems using symbolic dynamics

AU - Patankar, R. P.

AU - Rajagopalan, V.

AU - Ray, A.

PY - 2008/1/1

Y1 - 2008/1/1

N2 - Failures in a plant’s electrical components are a major source of performance degradation and plant unavailability. In order to detect and monitor failure precursors and anomalies early in electrical systems, we have developed a signal processing method that can detect and map patterns to an anomaly measure. Application of this technique for failure precursor detection in electronic circuits resulted in robust detection. This technique was observed to be superior to conventional pattern recognition techniques such as neural networks and principal component analysis for anomaly detection. Moreover, this technique based on symbolic dynamics offers superior robustness due to averaging associated with experimental probability calculations. It also provided a monotonically increasing smooth anomaly plot which was experimentally repeatable to a remarkable accuracy.

AB - Failures in a plant’s electrical components are a major source of performance degradation and plant unavailability. In order to detect and monitor failure precursors and anomalies early in electrical systems, we have developed a signal processing method that can detect and map patterns to an anomaly measure. Application of this technique for failure precursor detection in electronic circuits resulted in robust detection. This technique was observed to be superior to conventional pattern recognition techniques such as neural networks and principal component analysis for anomaly detection. Moreover, this technique based on symbolic dynamics offers superior robustness due to averaging associated with experimental probability calculations. It also provided a monotonically increasing smooth anomaly plot which was experimentally repeatable to a remarkable accuracy.

UR - http://www.scopus.com/inward/record.url?scp=79958723622&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958723622&partnerID=8YFLogxK

U2 - 10.1504/IJSISE.2008.017776

DO - 10.1504/IJSISE.2008.017776

M3 - Article

AN - SCOPUS:79958723622

VL - 1

SP - 68

EP - 77

JO - International Journal of Signal and Imaging Systems Engineering

JF - International Journal of Signal and Imaging Systems Engineering

SN - 1748-0698

IS - 1

ER -