Fault diagnosis of an automobile cylinder head using low frequency vibrational data

Maryam Taajobian, Morteza Zaheri, Mojtaba Doustmohammadi, Amirhosein Amouzadeh, Mohammadreza Emadi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper proposes a vibration-based fault-diagnosis method for mechanical parts. This method, after algorithm development, only requires a single inexpensive test to inspect the part which could take as short as half a second. The algorithm is developed in three major stages, (i) exciting specimens without or with known faults using a controlled force and recording acceleration of a single point for a short time (ii) finding a signature for each faulty specimen, using Fourier transform and statistical analysis. (iii) Developing a multi-layer perceptron, as a mathematical model, using the results of stage (ii). The elements of a part signature are the inputs to the model. The location (and possibly size and shape factor) of the fault is model output. Stage (i) can be performed experimentally or alternatively with a validated FEM, one experiment or simulation per specimen. The proposed technique was examined to locate (isolate) a fault on an automobile cylinder head. The presented accuracy is considerable, and the data collected at fairly low frequency range (below 1200 Hz) were found to be sufficient for this technique. In the case study of this paper, possible fault locations are on a line; as a result, fault location has one dimension. It is shown that the technique can be extended to higher dimensions.

Original languageEnglish
Pages (from-to)3037-3045
Number of pages9
JournalJournal of Mechanical Science and Technology
Volume32
Issue number7
DOIs
Publication statusPublished - Jul 1 2018

Fingerprint

Cylinder heads
Electric fault location
Vibrational spectra
Automobiles
Failure analysis
Multilayer neural networks
Statistical methods
Fourier transforms
Mathematical models
Finite element method
Experiments

Keywords

  • Artificial neural network
  • Automobile
  • Fault diagnosis
  • Fault signature
  • Vibrations

ASJC Scopus subject areas

  • Mechanics of Materials
  • Mechanical Engineering

Cite this

Fault diagnosis of an automobile cylinder head using low frequency vibrational data. / Taajobian, Maryam; Zaheri, Morteza; Doustmohammadi, Mojtaba; Amouzadeh, Amirhosein; Emadi, Mohammadreza.

In: Journal of Mechanical Science and Technology, Vol. 32, No. 7, 01.07.2018, p. 3037-3045.

Research output: Contribution to journalArticle

Taajobian, Maryam ; Zaheri, Morteza ; Doustmohammadi, Mojtaba ; Amouzadeh, Amirhosein ; Emadi, Mohammadreza. / Fault diagnosis of an automobile cylinder head using low frequency vibrational data. In: Journal of Mechanical Science and Technology. 2018 ; Vol. 32, No. 7. pp. 3037-3045.
@article{e7ef35bcb7ea4f309aeb11ed7d2bd2ee,
title = "Fault diagnosis of an automobile cylinder head using low frequency vibrational data",
abstract = "This paper proposes a vibration-based fault-diagnosis method for mechanical parts. This method, after algorithm development, only requires a single inexpensive test to inspect the part which could take as short as half a second. The algorithm is developed in three major stages, (i) exciting specimens without or with known faults using a controlled force and recording acceleration of a single point for a short time (ii) finding a signature for each faulty specimen, using Fourier transform and statistical analysis. (iii) Developing a multi-layer perceptron, as a mathematical model, using the results of stage (ii). The elements of a part signature are the inputs to the model. The location (and possibly size and shape factor) of the fault is model output. Stage (i) can be performed experimentally or alternatively with a validated FEM, one experiment or simulation per specimen. The proposed technique was examined to locate (isolate) a fault on an automobile cylinder head. The presented accuracy is considerable, and the data collected at fairly low frequency range (below 1200 Hz) were found to be sufficient for this technique. In the case study of this paper, possible fault locations are on a line; as a result, fault location has one dimension. It is shown that the technique can be extended to higher dimensions.",
keywords = "Artificial neural network, Automobile, Fault diagnosis, Fault signature, Vibrations",
author = "Maryam Taajobian and Morteza Zaheri and Mojtaba Doustmohammadi and Amirhosein Amouzadeh and Mohammadreza Emadi",
year = "2018",
month = "7",
day = "1",
doi = "10.1007/s12206-018-0606-x",
language = "English",
volume = "32",
pages = "3037--3045",
journal = "Journal of Mechanical Science and Technology",
issn = "1738-494X",
publisher = "Korean Society of Mechanical Engineers",
number = "7",

}

TY - JOUR

T1 - Fault diagnosis of an automobile cylinder head using low frequency vibrational data

AU - Taajobian, Maryam

AU - Zaheri, Morteza

AU - Doustmohammadi, Mojtaba

AU - Amouzadeh, Amirhosein

AU - Emadi, Mohammadreza

PY - 2018/7/1

Y1 - 2018/7/1

N2 - This paper proposes a vibration-based fault-diagnosis method for mechanical parts. This method, after algorithm development, only requires a single inexpensive test to inspect the part which could take as short as half a second. The algorithm is developed in three major stages, (i) exciting specimens without or with known faults using a controlled force and recording acceleration of a single point for a short time (ii) finding a signature for each faulty specimen, using Fourier transform and statistical analysis. (iii) Developing a multi-layer perceptron, as a mathematical model, using the results of stage (ii). The elements of a part signature are the inputs to the model. The location (and possibly size and shape factor) of the fault is model output. Stage (i) can be performed experimentally or alternatively with a validated FEM, one experiment or simulation per specimen. The proposed technique was examined to locate (isolate) a fault on an automobile cylinder head. The presented accuracy is considerable, and the data collected at fairly low frequency range (below 1200 Hz) were found to be sufficient for this technique. In the case study of this paper, possible fault locations are on a line; as a result, fault location has one dimension. It is shown that the technique can be extended to higher dimensions.

AB - This paper proposes a vibration-based fault-diagnosis method for mechanical parts. This method, after algorithm development, only requires a single inexpensive test to inspect the part which could take as short as half a second. The algorithm is developed in three major stages, (i) exciting specimens without or with known faults using a controlled force and recording acceleration of a single point for a short time (ii) finding a signature for each faulty specimen, using Fourier transform and statistical analysis. (iii) Developing a multi-layer perceptron, as a mathematical model, using the results of stage (ii). The elements of a part signature are the inputs to the model. The location (and possibly size and shape factor) of the fault is model output. Stage (i) can be performed experimentally or alternatively with a validated FEM, one experiment or simulation per specimen. The proposed technique was examined to locate (isolate) a fault on an automobile cylinder head. The presented accuracy is considerable, and the data collected at fairly low frequency range (below 1200 Hz) were found to be sufficient for this technique. In the case study of this paper, possible fault locations are on a line; as a result, fault location has one dimension. It is shown that the technique can be extended to higher dimensions.

KW - Artificial neural network

KW - Automobile

KW - Fault diagnosis

KW - Fault signature

KW - Vibrations

UR - http://www.scopus.com/inward/record.url?scp=85050158356&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050158356&partnerID=8YFLogxK

U2 - 10.1007/s12206-018-0606-x

DO - 10.1007/s12206-018-0606-x

M3 - Article

VL - 32

SP - 3037

EP - 3045

JO - Journal of Mechanical Science and Technology

JF - Journal of Mechanical Science and Technology

SN - 1738-494X

IS - 7

ER -