Malfunction detection in multi-cylinder engines using wavelet packet dictionary

Reza Tafreshi, F. Sassani, H. Ahmadi, G. Dumont

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

3 Citations (Scopus)

Abstract

In this paper, wavelets as signal processing tools are used to analyze the acceleration data acquired at the cylinder head for the detection and characterization of combustion malfunctions in multi-cylinder industrial engines. The objectives were to collect data on 1) normal operations, and 2) operations with a deactivated cylinder to simulate a faulty condition. Wavelet packet and local discriminatory basis algorithm are used to select wavelets that can recognize different conditions. It is shown that the wavelet packet provides a useful data analysis structure for extracting features that are capable of detecting the combustion malfunction of one cylinder in a 12-cylinder engine. Feature extraction is followed by a classification that uses a neural network for the fault identification phase.

Original languageEnglish
Title of host publicationSAE 2005 Noise and Vibration Conference and Exhibition
DOIs
Publication statusPublished - 2005
Externally publishedYes
EventSAE 2005 Noise and Vibration Conference and Exhibition - Traverse City, MI, United States
Duration: 16 May 200519 May 2005

Other

OtherSAE 2005 Noise and Vibration Conference and Exhibition
CountryUnited States
CityTraverse City, MI
Period16/5/0519/5/05

Fingerprint

Engine cylinders
Glossaries
Cylinder heads
Feature extraction
Signal processing
Engines
Neural networks

ASJC Scopus subject areas

  • Automotive Engineering
  • Safety, Risk, Reliability and Quality
  • Pollution
  • Industrial and Manufacturing Engineering

Cite this

Tafreshi, R., Sassani, F., Ahmadi, H., & Dumont, G. (2005). Malfunction detection in multi-cylinder engines using wavelet packet dictionary. In SAE 2005 Noise and Vibration Conference and Exhibition https://doi.org/10.4271/2005-01-2261

Malfunction detection in multi-cylinder engines using wavelet packet dictionary. / Tafreshi, Reza; Sassani, F.; Ahmadi, H.; Dumont, G.

SAE 2005 Noise and Vibration Conference and Exhibition. 2005.

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

Tafreshi, R, Sassani, F, Ahmadi, H & Dumont, G 2005, Malfunction detection in multi-cylinder engines using wavelet packet dictionary. in SAE 2005 Noise and Vibration Conference and Exhibition. SAE 2005 Noise and Vibration Conference and Exhibition, Traverse City, MI, United States, 16/5/05. https://doi.org/10.4271/2005-01-2261
Tafreshi R, Sassani F, Ahmadi H, Dumont G. Malfunction detection in multi-cylinder engines using wavelet packet dictionary. In SAE 2005 Noise and Vibration Conference and Exhibition. 2005 https://doi.org/10.4271/2005-01-2261
Tafreshi, Reza ; Sassani, F. ; Ahmadi, H. ; Dumont, G. / Malfunction detection in multi-cylinder engines using wavelet packet dictionary. SAE 2005 Noise and Vibration Conference and Exhibition. 2005.
@inproceedings{9e38c2422ccc466bb628a128345247d6,
title = "Malfunction detection in multi-cylinder engines using wavelet packet dictionary",
abstract = "In this paper, wavelets as signal processing tools are used to analyze the acceleration data acquired at the cylinder head for the detection and characterization of combustion malfunctions in multi-cylinder industrial engines. The objectives were to collect data on 1) normal operations, and 2) operations with a deactivated cylinder to simulate a faulty condition. Wavelet packet and local discriminatory basis algorithm are used to select wavelets that can recognize different conditions. It is shown that the wavelet packet provides a useful data analysis structure for extracting features that are capable of detecting the combustion malfunction of one cylinder in a 12-cylinder engine. Feature extraction is followed by a classification that uses a neural network for the fault identification phase.",
author = "Reza Tafreshi and F. Sassani and H. Ahmadi and G. Dumont",
year = "2005",
doi = "10.4271/2005-01-2261",
language = "English",
booktitle = "SAE 2005 Noise and Vibration Conference and Exhibition",

}

TY - GEN

T1 - Malfunction detection in multi-cylinder engines using wavelet packet dictionary

AU - Tafreshi, Reza

AU - Sassani, F.

AU - Ahmadi, H.

AU - Dumont, G.

PY - 2005

Y1 - 2005

N2 - In this paper, wavelets as signal processing tools are used to analyze the acceleration data acquired at the cylinder head for the detection and characterization of combustion malfunctions in multi-cylinder industrial engines. The objectives were to collect data on 1) normal operations, and 2) operations with a deactivated cylinder to simulate a faulty condition. Wavelet packet and local discriminatory basis algorithm are used to select wavelets that can recognize different conditions. It is shown that the wavelet packet provides a useful data analysis structure for extracting features that are capable of detecting the combustion malfunction of one cylinder in a 12-cylinder engine. Feature extraction is followed by a classification that uses a neural network for the fault identification phase.

AB - In this paper, wavelets as signal processing tools are used to analyze the acceleration data acquired at the cylinder head for the detection and characterization of combustion malfunctions in multi-cylinder industrial engines. The objectives were to collect data on 1) normal operations, and 2) operations with a deactivated cylinder to simulate a faulty condition. Wavelet packet and local discriminatory basis algorithm are used to select wavelets that can recognize different conditions. It is shown that the wavelet packet provides a useful data analysis structure for extracting features that are capable of detecting the combustion malfunction of one cylinder in a 12-cylinder engine. Feature extraction is followed by a classification that uses a neural network for the fault identification phase.

UR - http://www.scopus.com/inward/record.url?scp=84877417526&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877417526&partnerID=8YFLogxK

U2 - 10.4271/2005-01-2261

DO - 10.4271/2005-01-2261

M3 - Conference contribution

BT - SAE 2005 Noise and Vibration Conference and Exhibition

ER -