Journal
MEASUREMENT
Volume 152, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.measurement.2019.107315
Keywords
Acoustic emission; Fault diagnosis; Reciprocating compressor; Valve leakage loss; K-nearest neighbours (KNN); Support vector machine (SVM)
Funding
- Ministry of Science, Technology, and Innovation of Malaysia [03-01-03-SF1033/SF005-2015]
- Institute of Research Management and Monitoring (IPPP) from University of Malaya, Malaysia [PG233-2014B]
Ask authors/readers for more resources
Valve problems in reciprocating compressor are often resolved through parameter analysis of acoustic emission (AE) signals or intelligent system without examining the nature of signals related to its source. This study intended to explore the potential of AE signal for the measurement of valve flow rate in order to quantify the severity of valve problems. The study started with time-frequency analysis of AE signal through discrete wavelet transform, followed by valve condition classification and valve flow rate estimation for faulty valves operated from 450 to 750 rpm. The k-nearest neighbours (KNN) and support vector machine (SVM) classification algorithms are employed to classify the valve conditions before estimation of valve flow rate through regression model. The prediction accuracy of valve flow models is found between 74.5 and 98.8%. Finally, the valve leakage loss can be estimated by computing the difference of flow rate between the measured valve and its baseline (normal valve) using AE parameter. (C) 2019 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available