Early detection of fatigue damage using escort distributions of ultrasonic data sequences

Dheeraj Sharan Singh; Shalabh Gupta; Subhadeep Chakraborthy; Asok Ray

doi:10.1109/ACC.2008.4587167

Early detection of fatigue damage using escort distributions of ultrasonic data sequences

Dheeraj Sharan Singh, Shalabh Gupta, Subhadeep Chakraborthy, Asok Ray

Mechanical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper presents real-time detection of fatigue damage in mechanical structures using ultrasonic sensing methodology. The data-driven pattern identification method for anomaly detection is based on the tools derived from Statistical Mechanics and Symbolic Dynamics. The concept of Escort Distributions has been used to identify the behavioral patterns changes in complex systems due to gradual evolution of anomalies. The real-time information of evolving fatigue damage provides early warnings of forthcoming catastrophic failures. The anomaly detection method has been experimentally validated on poly-crystalline alloys using ultrasonic data generated from a fatigue damage testing apparatus.

Original language	English (US)
Title of host publication	2008 American Control Conference, ACC
Pages	4286-4291
Number of pages	6
DOIs	https://doi.org/10.1109/ACC.2008.4587167
State	Published - 2008
Event	2008 American Control Conference, ACC - Seattle, WA, United States Duration: Jun 11 2008 → Jun 13 2008

Publication series

Name	Proceedings of the American Control Conference
ISSN (Print)	0743-1619

Other

Other	2008 American Control Conference, ACC
Country/Territory	United States
City	Seattle, WA
Period	6/11/08 → 6/13/08

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering

Access to Document

10.1109/ACC.2008.4587167

Cite this

@inproceedings{333158ab2b5a4832ba7b81a63027fb3a,

title = "Early detection of fatigue damage using escort distributions of ultrasonic data sequences",

abstract = "This paper presents real-time detection of fatigue damage in mechanical structures using ultrasonic sensing methodology. The data-driven pattern identification method for anomaly detection is based on the tools derived from Statistical Mechanics and Symbolic Dynamics. The concept of Escort Distributions has been used to identify the behavioral patterns changes in complex systems due to gradual evolution of anomalies. The real-time information of evolving fatigue damage provides early warnings of forthcoming catastrophic failures. The anomaly detection method has been experimentally validated on poly-crystalline alloys using ultrasonic data generated from a fatigue damage testing apparatus.",

author = "Singh, {Dheeraj Sharan} and Shalabh Gupta and Subhadeep Chakraborthy and Asok Ray",

year = "2008",

doi = "10.1109/ACC.2008.4587167",

language = "English (US)",

isbn = "9781424420797",

series = "Proceedings of the American Control Conference",

pages = "4286--4291",

booktitle = "2008 American Control Conference, ACC",

note = "2008 American Control Conference, ACC ; Conference date: 11-06-2008 Through 13-06-2008",

}

Singh, DS, Gupta, S, Chakraborthy, S & Ray, A 2008, Early detection of fatigue damage using escort distributions of ultrasonic data sequences. in 2008 American Control Conference, ACC., 4587167, Proceedings of the American Control Conference, pp. 4286-4291, 2008 American Control Conference, ACC, Seattle, WA, United States, 6/11/08. https://doi.org/10.1109/ACC.2008.4587167

TY - GEN

T1 - Early detection of fatigue damage using escort distributions of ultrasonic data sequences

AU - Singh, Dheeraj Sharan

AU - Gupta, Shalabh

AU - Chakraborthy, Subhadeep

AU - Ray, Asok

PY - 2008

Y1 - 2008

N2 - This paper presents real-time detection of fatigue damage in mechanical structures using ultrasonic sensing methodology. The data-driven pattern identification method for anomaly detection is based on the tools derived from Statistical Mechanics and Symbolic Dynamics. The concept of Escort Distributions has been used to identify the behavioral patterns changes in complex systems due to gradual evolution of anomalies. The real-time information of evolving fatigue damage provides early warnings of forthcoming catastrophic failures. The anomaly detection method has been experimentally validated on poly-crystalline alloys using ultrasonic data generated from a fatigue damage testing apparatus.

AB - This paper presents real-time detection of fatigue damage in mechanical structures using ultrasonic sensing methodology. The data-driven pattern identification method for anomaly detection is based on the tools derived from Statistical Mechanics and Symbolic Dynamics. The concept of Escort Distributions has been used to identify the behavioral patterns changes in complex systems due to gradual evolution of anomalies. The real-time information of evolving fatigue damage provides early warnings of forthcoming catastrophic failures. The anomaly detection method has been experimentally validated on poly-crystalline alloys using ultrasonic data generated from a fatigue damage testing apparatus.

UR - http://www.scopus.com/inward/record.url?scp=52449103250&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=52449103250&partnerID=8YFLogxK

U2 - 10.1109/ACC.2008.4587167

DO - 10.1109/ACC.2008.4587167

M3 - Conference contribution

AN - SCOPUS:52449103250

SN - 9781424420797

T3 - Proceedings of the American Control Conference

SP - 4286

EP - 4291

BT - 2008 American Control Conference, ACC

T2 - 2008 American Control Conference, ACC

Y2 - 11 June 2008 through 13 June 2008

ER -

Early detection of fatigue damage using escort distributions of ultrasonic data sequences

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this