Diagnostic fault detection for internal combustion engines via pressure curve reconstruction

Brian J. Murphy, Mitchell S. Lebold, Karl Martin Reichard, T. Galie, C. Byington

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

10 Citations (Scopus)

Abstract

One proven technique for monitoring the health of a sealed internal combustion engine is to analyze the combustion pressure cycle curves of the individual cylinders. Current techniques for doing this require a pressure sensor mounted directly in the combustion chamber. This necessitates maintenance and design considerations that may be unacceptable especially on legacy systems. This paper describes a non-invasive technique developed for monitoring combustion pressure cycle related faults. This method has been developed and tested on a diesel engine test bed at Penn State University's Applied Research Laboratoq (ARL), Condition Based Maintenance Department. The diesel engine test bed was used to gather all forms of data under different engine operating conditions. Using crdshaft angular velocity data fiom a high-resolution encoder, a trained neural network is used to reconstruct the combustion pressure cycle curves. These reconstructed combustion pressure curves are then passed into another trained neural network for fault detection analysis.

Original languageEnglish (US)
Title of host publication2003 IEEE Aerospace Conference, Proceedings
Pages3239-3246
Number of pages8
Volume7
DOIs
StatePublished - Dec 1 2003
Event2003 IEEE Aerospace Conference - Big Sky, MT, United States
Duration: Mar 8 2003Mar 15 2003

Other

Other2003 IEEE Aerospace Conference
CountryUnited States
CityBig Sky, MT
Period3/8/033/15/03

Fingerprint

internal combustion engines
fault detection
Internal combustion engines
Fault detection
combustion
engine tests
diesel engines
test stands
curves
cycles
maintenance
Diesel engines
diesel engine
Neural networks
Legacy systems
Monitoring
Pressure sensors
Angular velocity
pressure sensors
Engine cylinders

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Space and Planetary Science

Cite this

Murphy, B. J., Lebold, M. S., Reichard, K. M., Galie, T., & Byington, C. (2003). Diagnostic fault detection for internal combustion engines via pressure curve reconstruction. In 2003 IEEE Aerospace Conference, Proceedings (Vol. 7, pp. 3239-3246). [1234167] https://doi.org/10.1109/AERO.2003.1234167
Murphy, Brian J. ; Lebold, Mitchell S. ; Reichard, Karl Martin ; Galie, T. ; Byington, C. / Diagnostic fault detection for internal combustion engines via pressure curve reconstruction. 2003 IEEE Aerospace Conference, Proceedings. Vol. 7 2003. pp. 3239-3246
@inproceedings{1fa2d6ce5772435c8d1e66231bc7eee6,
title = "Diagnostic fault detection for internal combustion engines via pressure curve reconstruction",
abstract = "One proven technique for monitoring the health of a sealed internal combustion engine is to analyze the combustion pressure cycle curves of the individual cylinders. Current techniques for doing this require a pressure sensor mounted directly in the combustion chamber. This necessitates maintenance and design considerations that may be unacceptable especially on legacy systems. This paper describes a non-invasive technique developed for monitoring combustion pressure cycle related faults. This method has been developed and tested on a diesel engine test bed at Penn State University's Applied Research Laboratoq (ARL), Condition Based Maintenance Department. The diesel engine test bed was used to gather all forms of data under different engine operating conditions. Using crdshaft angular velocity data fiom a high-resolution encoder, a trained neural network is used to reconstruct the combustion pressure cycle curves. These reconstructed combustion pressure curves are then passed into another trained neural network for fault detection analysis.",
author = "Murphy, {Brian J.} and Lebold, {Mitchell S.} and Reichard, {Karl Martin} and T. Galie and C. Byington",
year = "2003",
month = "12",
day = "1",
doi = "10.1109/AERO.2003.1234167",
language = "English (US)",
isbn = "078037651X",
volume = "7",
pages = "3239--3246",
booktitle = "2003 IEEE Aerospace Conference, Proceedings",

}

Murphy, BJ, Lebold, MS, Reichard, KM, Galie, T & Byington, C 2003, Diagnostic fault detection for internal combustion engines via pressure curve reconstruction. in 2003 IEEE Aerospace Conference, Proceedings. vol. 7, 1234167, pp. 3239-3246, 2003 IEEE Aerospace Conference, Big Sky, MT, United States, 3/8/03. https://doi.org/10.1109/AERO.2003.1234167

Diagnostic fault detection for internal combustion engines via pressure curve reconstruction. / Murphy, Brian J.; Lebold, Mitchell S.; Reichard, Karl Martin; Galie, T.; Byington, C.

2003 IEEE Aerospace Conference, Proceedings. Vol. 7 2003. p. 3239-3246 1234167.

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

TY - GEN

T1 - Diagnostic fault detection for internal combustion engines via pressure curve reconstruction

AU - Murphy, Brian J.

AU - Lebold, Mitchell S.

AU - Reichard, Karl Martin

AU - Galie, T.

AU - Byington, C.

PY - 2003/12/1

Y1 - 2003/12/1

N2 - One proven technique for monitoring the health of a sealed internal combustion engine is to analyze the combustion pressure cycle curves of the individual cylinders. Current techniques for doing this require a pressure sensor mounted directly in the combustion chamber. This necessitates maintenance and design considerations that may be unacceptable especially on legacy systems. This paper describes a non-invasive technique developed for monitoring combustion pressure cycle related faults. This method has been developed and tested on a diesel engine test bed at Penn State University's Applied Research Laboratoq (ARL), Condition Based Maintenance Department. The diesel engine test bed was used to gather all forms of data under different engine operating conditions. Using crdshaft angular velocity data fiom a high-resolution encoder, a trained neural network is used to reconstruct the combustion pressure cycle curves. These reconstructed combustion pressure curves are then passed into another trained neural network for fault detection analysis.

AB - One proven technique for monitoring the health of a sealed internal combustion engine is to analyze the combustion pressure cycle curves of the individual cylinders. Current techniques for doing this require a pressure sensor mounted directly in the combustion chamber. This necessitates maintenance and design considerations that may be unacceptable especially on legacy systems. This paper describes a non-invasive technique developed for monitoring combustion pressure cycle related faults. This method has been developed and tested on a diesel engine test bed at Penn State University's Applied Research Laboratoq (ARL), Condition Based Maintenance Department. The diesel engine test bed was used to gather all forms of data under different engine operating conditions. Using crdshaft angular velocity data fiom a high-resolution encoder, a trained neural network is used to reconstruct the combustion pressure cycle curves. These reconstructed combustion pressure curves are then passed into another trained neural network for fault detection analysis.

UR - http://www.scopus.com/inward/record.url?scp=84877490148&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877490148&partnerID=8YFLogxK

U2 - 10.1109/AERO.2003.1234167

DO - 10.1109/AERO.2003.1234167

M3 - Conference contribution

AN - SCOPUS:84877490148

SN - 078037651X

SN - 9780780376519

VL - 7

SP - 3239

EP - 3246

BT - 2003 IEEE Aerospace Conference, Proceedings

ER -

Murphy BJ, Lebold MS, Reichard KM, Galie T, Byington C. Diagnostic fault detection for internal combustion engines via pressure curve reconstruction. In 2003 IEEE Aerospace Conference, Proceedings. Vol. 7. 2003. p. 3239-3246. 1234167 https://doi.org/10.1109/AERO.2003.1234167