By Topic

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

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

5 Author(s)
Ahmed, M. ; Univ. of Huddersfield, Huddersfield, UK ; Abdusslam, S. ; Baqqar, M. ; Gu, F.
more authors

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).

Published in:

Automation and Computing (ICAC), 2011 17th International Conference on

Date of Conference:

10-10 Sept. 2011