Classification of diesel engine health using Sparse Linear Discriminant Analysis (SLDA)

Neha Chandrachud, Ravindra Kakade, Peter H. Meckl, Galen B. King, Kristofer Jennings

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

Abstract

With requirements for on-board diagnostics on diesel engines becoming more stringent for the coming model years, diesel engine manufacturers must improve their ability to identify fault conditions that lead to increased exhaust emissions. This paper proposes a statistical classifier model to identify the state of the engine, i.e. healthy or faulty, using an optimal number of sensors based on the data acquired from the engine. The classification model proposed in this paper is based on Sparse Linear Discriminant Analysis. This technique performs Linear Discriminant Analysis with a sparseness criterion imposed such that classification, dimension reduction and feature selection are merged into one step. It was concluded that the analysis technique could produce 0% misclassification rate for the steady-state data acquired from the diesel engine using five input variables. The classifier model was also extended to transient operation of the engine. The misclassification rate in the case of transient data was reduced from 31% to 26% by using the steady-state data trained classifier using thirteen variables.

Original languageEnglish (US)
Title of host publicationProceedings of the ASME Dynamic Systems and Control Conference 2009, DSCC2009
Pages677-684
Number of pages8
EditionPART A
DOIs
StatePublished - 2010
Externally publishedYes
Event2009 ASME Dynamic Systems and Control Conference, DSCC2009 - Hollywood, CA, United States
Duration: Oct 12 2009Oct 14 2009

Other

Other2009 ASME Dynamic Systems and Control Conference, DSCC2009
CountryUnited States
CityHollywood, CA
Period10/12/0910/14/09

Fingerprint

Discriminant analysis
Diesel engines
Health
Classifiers
Engines
Feature extraction
Sensors

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Chandrachud, N., Kakade, R., Meckl, P. H., King, G. B., & Jennings, K. (2010). Classification of diesel engine health using Sparse Linear Discriminant Analysis (SLDA). In Proceedings of the ASME Dynamic Systems and Control Conference 2009, DSCC2009 (PART A ed., pp. 677-684) https://doi.org/10.1115/DSCC2009-2790

Classification of diesel engine health using Sparse Linear Discriminant Analysis (SLDA). / Chandrachud, Neha; Kakade, Ravindra; Meckl, Peter H.; King, Galen B.; Jennings, Kristofer.

Proceedings of the ASME Dynamic Systems and Control Conference 2009, DSCC2009. PART A. ed. 2010. p. 677-684.

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

Chandrachud, N, Kakade, R, Meckl, PH, King, GB & Jennings, K 2010, Classification of diesel engine health using Sparse Linear Discriminant Analysis (SLDA). in Proceedings of the ASME Dynamic Systems and Control Conference 2009, DSCC2009. PART A edn, pp. 677-684, 2009 ASME Dynamic Systems and Control Conference, DSCC2009, Hollywood, CA, United States, 10/12/09. https://doi.org/10.1115/DSCC2009-2790
Chandrachud N, Kakade R, Meckl PH, King GB, Jennings K. Classification of diesel engine health using Sparse Linear Discriminant Analysis (SLDA). In Proceedings of the ASME Dynamic Systems and Control Conference 2009, DSCC2009. PART A ed. 2010. p. 677-684 https://doi.org/10.1115/DSCC2009-2790
Chandrachud, Neha ; Kakade, Ravindra ; Meckl, Peter H. ; King, Galen B. ; Jennings, Kristofer. / Classification of diesel engine health using Sparse Linear Discriminant Analysis (SLDA). Proceedings of the ASME Dynamic Systems and Control Conference 2009, DSCC2009. PART A. ed. 2010. pp. 677-684
@inproceedings{1ea21234e4794fccb57de8695cb27505,
title = "Classification of diesel engine health using Sparse Linear Discriminant Analysis (SLDA)",
abstract = "With requirements for on-board diagnostics on diesel engines becoming more stringent for the coming model years, diesel engine manufacturers must improve their ability to identify fault conditions that lead to increased exhaust emissions. This paper proposes a statistical classifier model to identify the state of the engine, i.e. healthy or faulty, using an optimal number of sensors based on the data acquired from the engine. The classification model proposed in this paper is based on Sparse Linear Discriminant Analysis. This technique performs Linear Discriminant Analysis with a sparseness criterion imposed such that classification, dimension reduction and feature selection are merged into one step. It was concluded that the analysis technique could produce 0{\%} misclassification rate for the steady-state data acquired from the diesel engine using five input variables. The classifier model was also extended to transient operation of the engine. The misclassification rate in the case of transient data was reduced from 31{\%} to 26{\%} by using the steady-state data trained classifier using thirteen variables.",
author = "Neha Chandrachud and Ravindra Kakade and Meckl, {Peter H.} and King, {Galen B.} and Kristofer Jennings",
year = "2010",
doi = "10.1115/DSCC2009-2790",
language = "English (US)",
isbn = "9780791848920",
pages = "677--684",
booktitle = "Proceedings of the ASME Dynamic Systems and Control Conference 2009, DSCC2009",
edition = "PART A",

}

TY - GEN

T1 - Classification of diesel engine health using Sparse Linear Discriminant Analysis (SLDA)

AU - Chandrachud, Neha

AU - Kakade, Ravindra

AU - Meckl, Peter H.

AU - King, Galen B.

AU - Jennings, Kristofer

PY - 2010

Y1 - 2010

N2 - With requirements for on-board diagnostics on diesel engines becoming more stringent for the coming model years, diesel engine manufacturers must improve their ability to identify fault conditions that lead to increased exhaust emissions. This paper proposes a statistical classifier model to identify the state of the engine, i.e. healthy or faulty, using an optimal number of sensors based on the data acquired from the engine. The classification model proposed in this paper is based on Sparse Linear Discriminant Analysis. This technique performs Linear Discriminant Analysis with a sparseness criterion imposed such that classification, dimension reduction and feature selection are merged into one step. It was concluded that the analysis technique could produce 0% misclassification rate for the steady-state data acquired from the diesel engine using five input variables. The classifier model was also extended to transient operation of the engine. The misclassification rate in the case of transient data was reduced from 31% to 26% by using the steady-state data trained classifier using thirteen variables.

AB - With requirements for on-board diagnostics on diesel engines becoming more stringent for the coming model years, diesel engine manufacturers must improve their ability to identify fault conditions that lead to increased exhaust emissions. This paper proposes a statistical classifier model to identify the state of the engine, i.e. healthy or faulty, using an optimal number of sensors based on the data acquired from the engine. The classification model proposed in this paper is based on Sparse Linear Discriminant Analysis. This technique performs Linear Discriminant Analysis with a sparseness criterion imposed such that classification, dimension reduction and feature selection are merged into one step. It was concluded that the analysis technique could produce 0% misclassification rate for the steady-state data acquired from the diesel engine using five input variables. The classifier model was also extended to transient operation of the engine. The misclassification rate in the case of transient data was reduced from 31% to 26% by using the steady-state data trained classifier using thirteen variables.

UR - http://www.scopus.com/inward/record.url?scp=77953763735&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953763735&partnerID=8YFLogxK

U2 - 10.1115/DSCC2009-2790

DO - 10.1115/DSCC2009-2790

M3 - Conference contribution

AN - SCOPUS:77953763735

SN - 9780791848920

SP - 677

EP - 684

BT - Proceedings of the ASME Dynamic Systems and Control Conference 2009, DSCC2009

ER -