Pattern Analysis and Applications

, Volume 18, Issue 2, pp 461–472 | Cite as

Detecting cracks in reciprocating compressor valves using pattern recognition in the pV diagram

  • Kurt Pichler
  • Edwin Lughofer
  • Markus Pichler
  • Thomas Buchegger
  • Erich Peter Klement
  • Matthias Huschenbett
Industrial and Commercial Application

Abstract

We present a novel approach to detecting leaking reciprocating compressor valves based on the idea that a leaking valve affects the shape of the pressure-volume diagram (pV diagram). This effect can be observed when the valves are closed. To avoid disturbances due to the load control, we concentrate on the expansion phase, and linearize it using the logarithmic pV diagram. The gradient of the expansion phase serves as an indicator for the fault state of the valve. Since the gradient is also affected by the pressure conditions, both are used as features in our approach. After feature extraction, classification is performed using several established approaches and a one-class classification method based on linearizing the classification boundary and thresholding. The method was validated using real-world data, and the results show high classification accuracy for varying compressor loads and pressure conditions as well as different valve types.

Keywords

Fault detection Varying load conditions Varying pressure conditions pV diagram Feature extraction Classification 

References

  1. 1.
    Bloch HP (2006) A practical guide to compressor technology. Wiley, HobokenCrossRefGoogle Scholar
  2. 2.
    Huschenbett M, Will G (2005) Thermodynamic simulation of reciprocating compressors to enable diagnostics based on measured temperatures and pressures. In: Proceedings of the 4th conference of the European forum of reciprocating compressorsGoogle Scholar
  3. 3.
    Lin YH, Wu HC, Wu CY (2006) Automated condition classification of a reciprocating compressor using time-frequency analysis and an artificial neural network. Inst Phys Publ Smart Mater Struct 15:1576–1584CrossRefGoogle Scholar
  4. 4.
    Lin YH, Liu HS, Wu CY (2009) Automated valve condition classification of a reciprocating compressor with seeded faults: experimentation and validation of classification strategy. Inst Phys Publ Smart Mater Struct 18:095020Google Scholar
  5. 5.
    Tiwari A, Yadav P (2008) Application of ANN in condition monitoring of a defective reciprocating air compressor. J Instrum Soc. India 38(1):13–20Google Scholar
  6. 6.
    Ren Q, Ma X, Miao G (2005) Application of support vector machines in reciprocating compressor valve fault diagnosis. In: Wang L, Chen K, Ong YS (Eds) Advances in natural computation. Springer, Berlin Heidelberg, pp 81–84Google Scholar
  7. 7.
    Vapnik V (1998) Statistical learning theory. Wiley, New YorkMATHGoogle Scholar
  8. 8.
    Cortes C, Vapnik V (1995) Support vector networks. Mach Learn 20:273–297MATHGoogle Scholar
  9. 9.
    Drewes E (2002) Condition monitoring for reciprocating compressors. Hydrocarb Process 81(9):77–79Google Scholar
  10. 10.
    Zhang Y, Jiang J, Flatley M, Hill B (2001) Condition monitoring and fault detection of a compressor using signal processing techniques. In: Proceedings of the American control conference, Arlington, VA. vol 6, pp 4460–4465Google Scholar
  11. 11.
    Elhaj M, Almrabet M, Rgeai M, Ehtiwesh I (2010) A combined practical approach to condition monitoring of reciprocating compressors using IAS and dynamic pressure. World Acad Sci Eng Technol 63:186–192Google Scholar
  12. 12.
    Wang F, Song L, Zhang L, Li H (2010) Fault diagnosis for reciprocating air compressor valve using p-V indicator diagram and SVM. In: Proceedings of the 3rd international symposium on information science and engineering, pp 255–258Google Scholar
  13. 13.
    Hsu CW, Chang CC, Lin CJ (2003) A practical guide to support vector classification. Department of Computer Science, National Taiwan University, Technical report Google Scholar
  14. 14.
    Schoelkopf B, Smola AJ (2002) Learning with kernels-support vector machines, regularization, optimization and beyond. MIT Press, LondonGoogle Scholar
  15. 15.
    Ma Y, Guo G (2014) Support vector machines applications. Springer, New YorkCrossRefGoogle Scholar
  16. 16.
    Wu X, Kumar V, Quinlan JR, Gosh J, Yang Q, Motoda H, MacLachlan GJ, Ng A, Liu B, Yu PS, Zhou ZH, Steinbach M, Hand DJ, Steinberg D (2006) Top 10 algorithms in data mining. Knowl Inf Syst 14(1):1–37CrossRefMATHGoogle Scholar
  17. 17.
    Bishop CM (2007) Pattern recognition and machine learning. Springer, New YorkGoogle Scholar
  18. 18.
    Lewicki MS (1998) A review of methods for spike sorting: the detection and classification of neural action potentials. Network 9:R53–78CrossRefMATHGoogle Scholar
  19. 19.
    Bloch HP, Hoefner JJ (1996) Reciprocating compressors: operation and maintenance. Gulf Publishing Company, HoustonGoogle Scholar
  20. 20.
    Machu EH (1996) Reciprocating compressor diagnostics, detecting abnormal conditions from measured indicator cards. International compressor engineering conference, School of Mechanical Engineering, Purdue UniversityGoogle Scholar
  21. 21.
    Draper NR, Smith H (1998) Applied regression analysis. Wiley, New YorkCrossRefMATHGoogle Scholar
  22. 22.
    Haykin S (1999) Neural networks: a comprehensive foundation. Prentice Hall, EnglewoodMATHGoogle Scholar
  23. 23.
    Bauer F, Lukas M (2011) Comparing parameter choice methods for regularization of ill-posed problems. Math Comput Simul 81(9):1795–1841CrossRefMATHMathSciNetGoogle Scholar
  24. 24.
    Lughofer E, Kindermann S (2009) SparseFIS: data-driven learning of fuzzy systems with sparsity constraints. IEEE Trans Fuzzy Syst 18(2):396–411Google Scholar
  25. 25.
    Dy JG, Brodley CE (2004) Feature selection for unsupervised learning. J Mach Learn Res 5:845–889Google Scholar
  26. 26.
    Lughofer E (2011) On-line incremental feature weighting in evolving fuzzy classifiers. Fuzzy Sets Syst 163(1):1–23Google Scholar
  27. 27.
    Snyman JA (2005) Practical mathematical optimization: an introduction to basic optimization theory and classical and new gradient-based algorithms. Springer Science+Business Media, New YorkGoogle Scholar
  28. 28.
    Manevitz LM, Yousef M (2001) One-class SVMs for document classification. J Mach Learn Res 2:139–154Google Scholar
  29. 29.
    Tax DMJ, Duin RPW (2004) Support vector data description. Mach Learn 54(1):45–66CrossRefMATHGoogle Scholar
  30. 30.
    Mahadevan S, Shah SL (2009) Fault detection and diagnosis in process data using one-class support vector machines. J Process Control 19(10):1627–1693CrossRefGoogle Scholar
  31. 31.
    Shalchyan V, Jensen W, Farina D (2012) Spike detection and clustering with unsupervised wavelet optimization in extracellular neural recordings. IEEE Trans Biomed Eng 59(9):2576–2585CrossRefGoogle Scholar
  32. 32.
    Tax DMJ (2001) One-class classifcation. PhD thesis, Delft University of Technology, NetherlandsGoogle Scholar

Copyright information

© Springer-Verlag London 2014

Authors and Affiliations

  • Kurt Pichler
    • 1
  • Edwin Lughofer
    • 2
  • Markus Pichler
    • 1
  • Thomas Buchegger
    • 1
  • Erich Peter Klement
    • 2
  • Matthias Huschenbett
    • 3
  1. 1.Information Analysis and Fault DiagnosticsLinz Center of Mechatronics GmbHLinzAustria
  2. 2.Department of Knowledge-based Mathematical SystemsJohannes Kepler University LinzLinzAustria
  3. 3.Compression TechnologyHoerbiger Service America, Inc.Greenwood VillageUSA

Personalised recommendations