Advertisement

Artificial Neural Networks in Fault Diagnosis: A Gas Turbine Scenario

  • Stephen Ogaji
  • Riti Singh
Part of the Advanced Information and Knowledge Processing book series (AI&KP)

6.9. Conclusion

A hierarchical approach to gas path diagnostic for a two-shaft simple gas turbine involving multiple neural networks has been presented. The described methodology has been tested with data not used for training, and generalisation is found to be appropriate for actual application of this technique. In addition, the level of accuracy achieved by this decentralised application of ANNs shows derivable benefits over techniques that require just a single network to perform fault detection, isolation and assessment. The technique presented, combined with inference tools such as expert system or fuzzy logic, could be expanded to produce an engine health monitoring scheme since ANNs also have the ability to fuse data from other associated performance monitoring techniques such as vibration and oil analysis.

Generally, as the number of simultaneously faulty components is increased, the reliability of the network to accurately assess the fault decreases. One way of improving this reliability would be the increase of sensory information by considering data at different operating points, otherwise known as multiple operating point analysis (MOPA).

The ANN structure described above forms a part of the diagnostic tool that includes other aspects involved in parameter corrections, as well as aspects that provide linguistic information on the nature and type of fault, since ANNs only give qualitative and quantitative results without any explanation for their significance.

Keywords

Artificial Neural Network Fault Diagnosis Life Cycle Cost Probabilistic Neural Network Sensor Fault 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Abernethy RB and Thomson JW Jr (1973) Uncertainty in Gas Turbine Measurements. In: Proceedings of the AIAA/SAE 9th Propulsion Conference, 5–7 November, Las Vegas, NV, USA, AIAA 73-1230Google Scholar
  2. 2.
    Agrawal RK, MacIsaac BD and Saravanamuttoo HIH (1978) An Analysis Procedure for Validation of On-Site Performance Measurements of Gas Turbines. ASME Journal of Engineering for Power, paper no. 78-GT-152Google Scholar
  3. 3.
    Aker GF and Saravanamuttoo HIH (1989) Prediction Gas Turbine Performance Behaviour Due to Compressor Fouling Using Computer Simulation Techniques. ASME Journal of Engineering for Gas Turbines and Power 111:343–350CrossRefGoogle Scholar
  4. 4.
    Angelakis C, Loukis EN, Pouliezos AD and Stavrakakis GS (2001) A Neural Network Based Method for Gas Turbine Blading Fault Diagnosis. International Journal of Modelling and Simulation 21(1)Google Scholar
  5. 5.
    Bakal B, Adali T, Fakory R, Sonmez MK and Tsaoi O (1995) Neural Network Simulation of Real Time Core Neutronic Model. In: Proceedings of the SCS Simulation Multiconference, Phoenix, AZ, USAGoogle Scholar
  6. 6.
    Barlett EB and Uhrig RE (1992) Power Plant Status Diagnostics Using Artificial Neural Network. Nuclear Technology 97:272–281Google Scholar
  7. 7.
    Cifaldi ML and Chokani N (1998) Engine Monitoring Using Neural Networks. American Institute of Aeronautics and Astronautics, AIAA-98-3548Google Scholar
  8. 8.
    Demuth H and Beale M (1992) Matlab Neural Networks Users Guide Ver. 4. MathWorksGoogle Scholar
  9. 9.
    Denney G (1993) F16 Jet Engine Trending and Diagnostics with Neural Networks. SPIE Applications of Artificial Neural Networks IV 1965:419–422Google Scholar
  10. 10.
    Diakunchak IS (1992) Performance Deterioration in Industrial Gas Turbines. ASME Journal of Engineering for Gas Turbines and Power 114:161–168Google Scholar
  11. 11.
    Dietz WE, Kiech EL and Ali M (1989) Jet and Rocket Engine Fault Diagnosis in Real Time. Journal of Neural Network Computing 1(1):5–18Google Scholar
  12. 12.
    Dong DW, Hopfield JJ and Unnikrishnan KP (1997) Neural Networks for Engine Fault Diagnostics. In: Proceedings of the 1997 IEEE Workshop, pp. 636–644Google Scholar
  13. 13.
    Escher PC and Singh R (1995) An Object-Oriented Diagnostics Computer Program Suitable for Industrial Gas Turbines. In: Proceedings of the United 21st International Congress on Combustion Engines (CIMAC), Interlaken, Switzerland, 15–18 MayGoogle Scholar
  14. 14.
    Eustace R and Merrington G (1995) Fault Diagnosis of Fleet Engines Using Neural Networks. In: Proceedings of the Twelfth International Symposium on Air Breathing Engines, Melbourne, Australia, September 10–15, paper no. ISABE 95-7085Google Scholar
  15. 15.
    Fantoni PF and Mazzola A (1996) Multiple Failure Signal Validation in Nuclear Power Plants Using Artificial Neural Networks. Nuclear Technology 113(3)Google Scholar
  16. 16.
    Fukuzaki T, Ohga Y and Kobayashi Y (1992) Feasibility Studies on Applying Neural Network Techniques in Nuclear Power Plants. In: Proceedings of the OECD-NEA/IAEA International Symposium on NPP Instrumentation and Control, Tokyo, JapanGoogle Scholar
  17. 17.
    Green A and Allen D (1997) Artificial Intelligence for Real Time Diagnostics and Prognostics of Gas Turbine Engines. In: Proceedings of the 33rd AIAA/ASME/SAE/ASEE Joint Propulsion Conference and Exhibition, Seattle, WA, 6–9 July, paper no. AIAA 97-2899Google Scholar
  18. 18.
    Guo Z and Uhrig RE (1992) Use of Artificial Neural Networks to Analyze Nuclear Power Plant Performance. Nuclear Technology 99:36–42Google Scholar
  19. 19.
    Guo T-H and Nurre J (1991) Sensor Failure Detection and Recovery by Neural Networks. International Joint Conference on Neural Networks, Seattle, Washington, 8–12 July, paper no. NASA-TM-104484Google Scholar
  20. 20.
    Guo T-H, Saus J, Lin C-F and Ge J-H (1996) Sensor Validation for Turbofan Engines Using an Autoassociative Neural Network. AIAA Guidance Navigation and Control Conference, San Diego, CA, 29–31 July, paper no. AIAA-96-3926Google Scholar
  21. 21.
    Haykin S. (1999) Neural networks. A comprehensive foundation. Prentice-HallGoogle Scholar
  22. 22.
    Huang H, Vian J, Choi J, Carlson D and Wunsch D (2001) Neural Network Inverse Models for Propulsion Vibration Diagnostics. In: Proceedings of SPIE 4390:12–21Google Scholar
  23. 23.
    Illi OJ, Greitzer FL, Kangas LJ and Reeve TJ (1994) An Artificial Neural Network System for Diagnosing Gas Turbine Engine Fuel Faults. In: Proceedings of the 48th Meeting of the Mechanical Failure Group, April 19–21. Wakefield, MA, paper no. MFPG 48Google Scholar
  24. 24.
    Jouse WC and Williams JG (1990) Neural Control of Temperature and Pressure during PWR Start-up. American Nuclear Society Transactions 61:219–220Google Scholar
  25. 25.
    Kanelopoulos K, Stamatis A and Mathioudakis K (1997) Incorporating Neural Networks into Gas Turbine Performance Diagnostics. In: Proceedings of the International Gas Turbine and Aeroengine Congress and Exhibition, Orlando, Florida, June 2–5, paper no. 97-GT-35Google Scholar
  26. 26.
    Kobayashi T and Simon DL (2001) A Hybrid Neural Network-Genetic Algorithm Technique for Aircraft Engine Performance Diagnostics. In: Proceedings of the 37th AIAA/ASME/SAE/ASEE Joint Propulsion Conference and Exhibit, Salt Lake City, Utah, paper no. AIAA-2001-3763Google Scholar
  27. 27.
    Lakshminarasimha AN, Boyce MP and Meher-Homji CB (1994) Modelling and Analysis of Gas Turbine Performance Deterioration. ASME Journal of Engineering for Gas Turbines and Power 116:46–52Google Scholar
  28. 28.
    Lu P, Hsu T, Zhang M and Zang J (2000) An Evaluation of Engine Faults Diagnostics Using Artificial Neural Networks. In: Proceedings of ASME Turbo Expo 2000: Land, Sea and Air, Munich, Germany, 8–11 May, paper no. 2000-GT-0029Google Scholar
  29. 29.
    Napolitano M, Windon D, Casanova J and Innocenti M (1996) A Comparison between Kalman Filter and Neural Network Approaches for Sensor Validation. In: Proceedings of the AIAA Guidance Navigation and Control Conference, San Diego, CA, July 29–31, paper no. AIAA-96-3894Google Scholar
  30. 30.
    Ogaji SOT and Singh R (2002a) Advanced Engine Diagnostics Using Artificial Neural Networks. In: Proceedings of the IEEE International Conference on Artificial Intelligence Systems, 5–10 September, Gelendzhik, Black Sea Coast, Russia, pp. 236–241Google Scholar
  31. 31.
    Ogaji SOT and Singh R (2002b) Study of the Optimisation of Measurement Sets for Gas Path Fault Diagnosis in Gas Turbines. In: Proceedings of ASME Turbo Expo 2002, Amsterdam, The Netherlands, 3–6 June, paper no. GT-2002-30050Google Scholar
  32. 32.
    Ogaji SOT, Singh R and Probert SD (2002a) Multiple-sensor fault-diagnoses for a 2-shaft stationary gas-turbine. Applied Energy 71:321–339CrossRefGoogle Scholar
  33. 33.
    Ogaji S, Sampath S and Singh R (2002b) Gas Turbine Faults: Detection, Isolation and Assessment Using Neural Networks. In: Proceedings of the Sixth International Conference on Knowledge-Based Intelligent Information & Engineering Systems, 16–18 September, Crema, Italy, pp. 141–145Google Scholar
  34. 34.
    Parlos AG, Muthusami J and Atiya AF (1994) Incipient Fault Detection and Identification in Progress Systems Using Accelerated Neural Network Learning. Nuclear Technology 105(2): 145–161Google Scholar
  35. 35.
    Paya BA, Esat II and Badi MNN (1997) Artificial Neural Network Based Fault Diagnostics of Rotating Machinery Using Wavelet Transforms as a Pre-processor. Mechanical Systems and Signal Processing 11(5): 751–765CrossRefGoogle Scholar
  36. 36.
    Simani S and Fantuzzi C (2000) Fault Diagnosis in Power Plant Using Neural Networks. Information Sciences 127:125–136CrossRefGoogle Scholar
  37. 37.
    Singh R (1999) Managing Gas Turbine Availability, Performance and Life Usage via Advanced Diagnostics. In: Proceedings of the 44th Gas Turbine Users Association Annual Conference, Dubai, UAE, 9–14 MayGoogle Scholar
  38. 38.
    Singh R (2001) Managing Gas Turbine Availability, Performance and Life Usage Via Advanced Diagnostics. In: Proceedings of the Symposium for Diesel and Gas Turbine Engineers (IDGTE), Milton Keynes, United Kingdom, September 27–28Google Scholar
  39. 39.
    Sofa T, Eryurek E, Uhrig RE, Dodds HL and Cook DH (1990) Estimation of HFIR Core Flow Rate Using a Backpropagation Network. American Nuclear Society Transactions 61Google Scholar
  40. 40.
    Tsai TM and Chou HP (1996) Recurrent Neural Networks for Fault Detection and Isolation. In: Proceedings of the 1996 American Nuclear Society International Topical Meeting on Nuclear Plant Instrumentation, Control and Human-Machine Interface Technologies, Pennsylvania, USA, pp. 921–926Google Scholar
  41. 41.
    Tsoukalas LH (1994) Virtual Measurement and Prediction in Human-Centered Automation. In: Proceedings of the Topical Meeting on Computer-Based Human Support Systems: Technology, Methods, and Future, The American Nuclear Society’s Human Factors Division, Pennsylvania, USA, pp. 235–241Google Scholar
  42. 42.
    Upadhyaya BR and Eryurek E (1992) Application of Neural Networks for Sensor Validation and Plant Monitoring. Nuclear Technology 97(2):170–176Google Scholar
  43. 43.
    Urban LA (1972) Gas Path Analysis Applied to Turbine Engine Condition Monitoring. In: Proceedings of the AIAA/SAE 8th Joint Propulsion Specialist Conference, New Orleans, Louisiana, paper no. AIAA-72-1082Google Scholar
  44. 44.
    Weidong H, Kechang W and Qizhi C (1996) Sensor Failure Detection and Data Recovery Based on Neural Network. In: Proceedings of the 32nd AIAA/ASME/SAE/ASEE Joint Propulsion Conference, Lake Buena Vista, FL, July 1–3, paper no. AIAA-96-2932Google Scholar
  45. 45.
    Zaita AV, Buley G and Karlsons G (1998) Performance Deterioration Modelling in Aircraft Gas Turbine Engines. ASME Journal of Engineering for Gas Turbines and Power 120:344–349Google Scholar
  46. 46.
    Zedda M and Singh R (1998) Fault Diagnosis of a Turbofan Engine Using Neural Networks: A Quantitative Approach. In: Proceedings of the 34th AIAA/ASME/SAE/ASEE Joint Propulsion Conference & Exhibit, Cleveland, OH, 13–15 July, paper no. AIAA 98-3602Google Scholar

Copyright information

© Springer-Verlag London Limited 2006

Authors and Affiliations

  • Stephen Ogaji
    • 1
  • Riti Singh
    • 1
  1. 1.Department of Power, Propulsion and Aerospace Engineering School of EngineeringCranfield UniversityBeds.UK

Personalised recommendations