Fault classification of reciprocating compressor based on Neural Networks and Support Vector Machines

M. Ahmed, S. Abdusslam, M. Baqqar, F. Gu, A. D. Ball

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

6 Citations (Scopus)

Abstract

Reciprocating compressors play a major part in many industrial systems and faults occurring in them can degrade performance, consume additional energy, cause severe damage to the machine and possibly even system shut-down. Traditional vibration monitoring techniques have found it difficult to determine a set of effective diagnostic features due to the high complexity of the vibration signals because of the many different impact sources and wide range of practical operating conditions. This paper focuses on the development of an advanced signal classifier for a reciprocating compressor using vibration signals. Artificial Neural Networks (ANN) and Support Vector Machines (SVM) have been applied, trained and tested for feature extraction and fault classification. The accuracy of both techniques is compared to determine the optimum fault classifier. The results show that the model behaves well, and classification rate accuracy is up to 100% for both binary classes (a single fault present in the compressor) and multi-classes (three faults present).

LanguageEnglish
Title of host publication17th International Conference on Automation and Computing, ICAC 2011
PublisherIEEE
Pages213-218
Number of pages6
ISBN (Electronic)9781862180987
ISBN (Print)9781467300001
Publication statusPublished - 21 Nov 2011
Event17th International Conference on Automation and Computing - Huddersfield, United Kingdom
Duration: 10 Sep 201110 Sep 2011
Conference number: 17
http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=14139&copyownerid=20561 (Link to Event Details)

Conference

Conference17th International Conference on Automation and Computing
Abbreviated titleICAC 2011
CountryUnited Kingdom
CityHuddersfield
Period10/09/1110/09/11
Internet address

Fingerprint

Reciprocating compressors
Support vector machines
Classifiers
Neural networks
Compressors
Feature extraction
Monitoring

Cite this

Ahmed, M., Abdusslam, S., Baqqar, M., Gu, F., & Ball, A. D. (2011). Fault classification of reciprocating compressor based on Neural Networks and Support Vector Machines. In 17th International Conference on Automation and Computing, ICAC 2011 (pp. 213-218). [6084929] IEEE.
Ahmed, M. ; Abdusslam, S. ; Baqqar, M. ; Gu, F. ; Ball, A. D. / Fault classification of reciprocating compressor based on Neural Networks and Support Vector Machines. 17th International Conference on Automation and Computing, ICAC 2011. IEEE, 2011. pp. 213-218
@inproceedings{e7e4dbe6d9b44a01a69647269aad2fb3,
title = "Fault classification of reciprocating compressor based on Neural Networks and Support Vector Machines",
abstract = "Reciprocating compressors play a major part in many industrial systems and faults occurring in them can degrade performance, consume additional energy, cause severe damage to the machine and possibly even system shut-down. Traditional vibration monitoring techniques have found it difficult to determine a set of effective diagnostic features due to the high complexity of the vibration signals because of the many different impact sources and wide range of practical operating conditions. This paper focuses on the development of an advanced signal classifier for a reciprocating compressor using vibration signals. Artificial Neural Networks (ANN) and Support Vector Machines (SVM) have been applied, trained and tested for feature extraction and fault classification. The accuracy of both techniques is compared to determine the optimum fault classifier. The results show that the model behaves well, and classification rate accuracy is up to 100{\%} for both binary classes (a single fault present in the compressor) and multi-classes (three faults present).",
keywords = "Artificial Neural Networks, Fault Diagnosis, Reciprocating Compressor, Support Vector Machine",
author = "M. Ahmed and S. Abdusslam and M. Baqqar and F. Gu and Ball, {A. D.}",
year = "2011",
month = "11",
day = "21",
language = "English",
isbn = "9781467300001",
pages = "213--218",
booktitle = "17th International Conference on Automation and Computing, ICAC 2011",
publisher = "IEEE",

}

Ahmed, M, Abdusslam, S, Baqqar, M, Gu, F & Ball, AD 2011, Fault classification of reciprocating compressor based on Neural Networks and Support Vector Machines. in 17th International Conference on Automation and Computing, ICAC 2011., 6084929, IEEE, pp. 213-218, 17th International Conference on Automation and Computing, Huddersfield, United Kingdom, 10/09/11.

Fault classification of reciprocating compressor based on Neural Networks and Support Vector Machines. / Ahmed, M.; Abdusslam, S.; Baqqar, M.; Gu, F.; Ball, A. D.

17th International Conference on Automation and Computing, ICAC 2011. IEEE, 2011. p. 213-218 6084929.

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

TY - GEN

T1 - Fault classification of reciprocating compressor based on Neural Networks and Support Vector Machines

AU - Ahmed, M.

AU - Abdusslam, S.

AU - Baqqar, M.

AU - Gu, F.

AU - Ball, A. D.

PY - 2011/11/21

Y1 - 2011/11/21

N2 - Reciprocating compressors play a major part in many industrial systems and faults occurring in them can degrade performance, consume additional energy, cause severe damage to the machine and possibly even system shut-down. Traditional vibration monitoring techniques have found it difficult to determine a set of effective diagnostic features due to the high complexity of the vibration signals because of the many different impact sources and wide range of practical operating conditions. This paper focuses on the development of an advanced signal classifier for a reciprocating compressor using vibration signals. Artificial Neural Networks (ANN) and Support Vector Machines (SVM) have been applied, trained and tested for feature extraction and fault classification. The accuracy of both techniques is compared to determine the optimum fault classifier. The results show that the model behaves well, and classification rate accuracy is up to 100% for both binary classes (a single fault present in the compressor) and multi-classes (three faults present).

AB - Reciprocating compressors play a major part in many industrial systems and faults occurring in them can degrade performance, consume additional energy, cause severe damage to the machine and possibly even system shut-down. Traditional vibration monitoring techniques have found it difficult to determine a set of effective diagnostic features due to the high complexity of the vibration signals because of the many different impact sources and wide range of practical operating conditions. This paper focuses on the development of an advanced signal classifier for a reciprocating compressor using vibration signals. Artificial Neural Networks (ANN) and Support Vector Machines (SVM) have been applied, trained and tested for feature extraction and fault classification. The accuracy of both techniques is compared to determine the optimum fault classifier. The results show that the model behaves well, and classification rate accuracy is up to 100% for both binary classes (a single fault present in the compressor) and multi-classes (three faults present).

KW - Artificial Neural Networks

KW - Fault Diagnosis

KW - Reciprocating Compressor

KW - Support Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=83455163290&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781467300001

SP - 213

EP - 218

BT - 17th International Conference on Automation and Computing, ICAC 2011

PB - IEEE

ER -

Ahmed M, Abdusslam S, Baqqar M, Gu F, Ball AD. Fault classification of reciprocating compressor based on Neural Networks and Support Vector Machines. In 17th International Conference on Automation and Computing, ICAC 2011. IEEE. 2011. p. 213-218. 6084929