Fault detection in reciprocating compressor valves under varying load conditions

Abstract This paper presents a novel approach for detecting cracked or broken reciprocating compressor valves under varying load conditions. The main idea is that the time frequency representation of vibration measurement data will show typical patterns depending on the fault state. The problem is to detect these patterns reliably. For the detection task, we make a detour via the two dimensional autocorrelation. The autocorrelation emphasizes the patterns and reduces noise effects. This makes it easier to define appropriate features. After feature extraction, classification is done using logistic regression and support vector machines. The method׳s performance is validated by analyzing real world measurement data. The results will show a very high detection accuracy while keeping the false alarm rates at a very low level for different compressor loads, thus achieving a load-independent method. The proposed approach is, to our best knowledge, the first automated method for reciprocating compressor valve fault detection that can handle varying load conditions.

[1]  F. Hlawatsch,et al.  Linear and quadratic time-frequency signal representations , 1992, IEEE Signal Processing Magazine.

[2]  Khaled H. Hamed,et al.  Time-frequency analysis , 2003 .

[3]  M. Elhaj,et al.  A Combined Practical Approach to Condition Monitoring of Reciprocating Compressors using IAS and Dynamic Pressure , 2010 .

[4]  J. A. Anderson,et al.  7 Logistic discrimination , 1982, Classification, Pattern Recognition and Reduction of Dimensionality.

[5]  Xiaojiang Ma,et al.  Application of Support Vector Machines in Reciprocating Compressor Valve Fault Diagnosis , 2005, ICNC.

[6]  E. Drewes.  Condition monitoring for reciprocating compressors , 2002 .

[7]  Youmin Zhang,et al.  Condition monitoring and fault detection of a compressor using signal processing techniques , 2001, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[8]  J. Antoni,et al.  Cyclostationary Modelling of Reciprocating Compressors and Application to Valve Fault Detection , 2007 .

[9]  Yih-Hwang Lin,et al.  Automated condition classification of a reciprocating compressor using time–frequency analysis and an artificial neural network , 2006 .

[10]  Yih-Hwang Lin,et al.  Automated valve condition classification of a reciprocating compressor with seeded faults: experimentation and validation of classification strategy , 2009 .

[11]  Matthias Huschenbett,et al.  A Switching Model for Fault Detection in Reciprocating Compressor Valves under Varying Load Conditions , 2011 .

[12]  Bo-Suk Yang,et al.  Condition classification of small reciprocating compressor for refrigeration using artificial neural networks and support vector machines , 2005 .

[13]  Kent A. Spackman,et al.  Signal Detection Theory: Valuable Tools for Evaluating Inductive Learning , 1989, ML.

[14]  O. Bardou,et al.  Early detection of leakages in the exhaust and discharge systems of reciprocating machines by vibration analysis , 1994 .

[15]  Andrew R. Webb,et al.  Statistical Pattern Recognition , 1999 .

[16]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[17]  Yuefei Wang,et al.  Fault diagnosis of reciprocating compressor valve with the method integrating acoustic emission signal and simulated valve motion , 2015 .

[18]  Haifeng Li,et al.  Fault Diagnosis for Reciprocating Air Compressor Valve Using P-V Indicator Diagram and SVM , 2010, 2010 Third International Symposium on Information Science and Engineering.

[19]  N. Draper,et al.  Applied Regression Analysis , 1967 .

[20]  J. Antoni.  Cyclostationarity by examples , 2009 .

[21]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[22]  Matthias Huschenbett,et al.  Fault detection in reciprocating compressor valves for steady-state load conditions , 2011, 2011 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).