Reciprocating compressor valve condition monitoring using image-based pattern recognition

John N. Trout and Jason R. Kolodziej
Submission Type: 
Full Paper
AttachmentSizeTimestamp
phmc_16_005.pdf5.18 MBAugust 15, 2016 - 12:09pm

This work presents the development of a vibration-based condition monitoring method for early detection and classification of valve wear within industrial reciprocating compressors through the combined use of time-frequency analysis with image-based pattern recognition techniques. A common valve related fault condition is valve seat wear that is caused by repeated impact and accentuated by chatter. Seeded faults consistent with valve seat wear are introduced on the crank-side discharge valves of a Dresser-Rand ESH-1 industrial compressor. A variety of operational data including vibration, cylinder pressure, and crank shaft position are collected and processed using a time-frequency domain approach. The resulting diagrams are processed as images with features extracted using 1st and 2nd order image statistics. A Bayesian classification strategy is employed with accuracy rates greater than 90\% achieved using two and three-dimensional features spaces.

Publication Year: 
2016
Publication Volume: 
7
Publication Control Number: 
005
Page Count: 
10
Submission Keywords: 
data-driven
PHM industrial applications
condition based maintenance (CBM)
Submission Topic Areas: 
CBM and informed logistics
Data-driven methods for fault detection, diagnosis, and prognosis
Industrial applications
Submitted by: 
  
 
 
 

follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed