Fuzzy Neural Networks Applied to Fault Diagnosis

  • João Calado
  • José Sá da Costa
Part of the Advanced Information and Knowledge Processing book series (AI&KP)

10.5. Summary

This chapter is concerned with the application of fuzzy neural networks to fault detection and isolation systems. Thus, for readers not familiar with the subject, the background knowledge associated with artificial neural networks and the potential fields of application of this technology is presented in the introduction section. Furthermore, aiming to demonstrate that such a technology is mature enough to be applied in the solution of several kinds of industrial problems, a wide range of industrial applications of classical feedforward artificial neural networks are also reported in section 10.2, as well as applications of different types of fuzzy neural networks.

Section 10.3 is concerned with the development of FDI approaches based on fuzzy neural networks and a specific fault isolation system based on a hierarchical structure of several fuzzy neural networks is described in detail. The robustness and performance of such a fault isolation system has been assessed in section 10.4 by using a test bed consisting of a pneumatic servomotor actuated industrial control valve. Different kinds of faults have been considered, which has been assumed to occur in an abrupt or incipient manner, or by affecting the measurement variables in the process under supervision in an abrupt way or, instead, by affecting the process behaviour slowly (incipient faults).

The results presented in section 10.4 have shown that, under abrupt faults, the HSFNN provides very accurate results and is characterized by a good generalization capability as a fault isolation system. Under incipient or multiple simultaneous faulty scenarios, the performance of the proposed methodology depends on the fault development speed and/or on the system nonlinearities.


Neural Network Artificial Neural Network Fault Diagnosis Induction Motor Fuzzy Neural Network 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    AlguÍndigue IE and Uhrig RE (1994) Automatic fault recognition in mechanical components using coupled artificial neural networks. In: Proceedings of IEEE World Congress on Computational Intelligence, June–July, pp. 3312–3317Google Scholar
  2. 2.
    Andersen K, Cook GE, Karsai G and Ramaswamy K (1990) Artificial neural networks applied to arc welding process modeling and control. IEEE Transactions on Industry Applications 26:824–830CrossRefGoogle Scholar
  3. 3.
    Anderson JA (1995) An Introduction to Neural Networks. MIT PressGoogle Scholar
  4. 4.
    Alport M, Mhlongo A, Naicker J and Plumb S (2002) Application of Neural Networks to Solve Industrial Problems: Bridging in Practice. Physica Scripta T97:118–121CrossRefGoogle Scholar
  5. 5.
    Bezdek JC (1981) Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum Press, New YorkzbMATHGoogle Scholar
  6. 6.
    Bhat NV, Minderman PA, McAvoy T and Wang NS (1990) Modeling chemical process systems via neural computation. IEEE Control Systems Magazine 10:24–30CrossRefGoogle Scholar
  7. 7.
    Bishop CM (1995) Neural Networks for Pattern Recognition. Oxford University Press.Google Scholar
  8. 8.
    Buckley JJ and Hayashi Y (1994a) Fuzzy Neural Networks. In: Yager RR and Zadeh LA (eds) Fuzzy Sets, Neural Networks, and Soft Computing. Van Nostrand Reinhold, New York, pp. 233–249Google Scholar
  9. 9.
    Buckley JJ and Hayashi Y (1994b) Can fuzzy neural nets approximate continuous functions, Fuzzy Sets and Systems 61(1):43–51CrossRefMathSciNetzbMATHGoogle Scholar
  10. 10.
    Buhl M and Lorenz RD (1991) Design and implementation of neural networks for digital current regulation of inverter drives. In: Proceedings of Conf. Rec. IEEE-IAS Annual Meeting, pp. 415–423Google Scholar
  11. 11.
    Burton B and Harley RG (1998) Reducing the computational demands of continually online-trained artificial neural networks for system identification and control of fast processes. IEEE Trans. on Industry Applications 34:589–596CrossRefGoogle Scholar
  12. 12.
    Burton B, Kamran F, Harley RG, Habetler TG, Brooke M and Poddar R (1995) Identification and control of induction motor stator currents using fast on-line random training of a neural network. In: Proceedings of Conf. Rec. IEEE-IAS Annual Meeting, pp. 1781–1787Google Scholar
  13. 13.
    Boger Z (1995) Experience in developing models of industrial plants by large scale artificial neural networks. In: Proceedings of the Second New Zealand International Two-Stream Conf. Artificial Neural Networks and Expert Systems, pp. 326–329Google Scholar
  14. 14.
    Calado JMF and Sa da Costa JMG (1999) An Expert System Coupled with a Hierarchical Fuzzy Neural Network Approach for Multiple Fault Diagnosis. International Journal of Applied Mathematics and Computer Sciences 9(3): 667–687Google Scholar
  15. 15.
    Calado JMF, Korbicz J, Patan K, Patton RJ and Sa da Costa JMG (2001) Soft computing approaches to fault diagnosis for dynamic systems. European Journal of Control 7(2–3):169–208Google Scholar
  16. 16.
    Calado JMF, Carreira FPNF, Mendes MJGC, Sa da Costa JMG and Bartys M (2003b) Fault Detection Approach Based on Fuzzy Qualitative Reasoning Applied to the DAMADICS Benchmark Problem. In: Proceedings of the 5th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes, SAFEPROCESS’2003, Washington, D. C., USA, June 9–11, pp. 1179–1184Google Scholar
  17. 17.
    Carelli R, Camacho EF and Patiño D (1995) A neural network based feed forward adaptive controller for robots. IEEE Trans. on Systems, Man and Cybernetics 25: 1281–1288CrossRefGoogle Scholar
  18. 18.
    Cichowlas M, Sobczuk D, Kazmierkowski MP and Malinowski M (2000) Novel artificial neural network based current controller for PWM rectifiers. In: Proceedings of the 9th Int. Conf. on Power Electronics and Motion Control, pp. 41–46Google Scholar
  19. 19.
    Chakraborty S, Pal K and Pal NR (2002) A neuro-fuzzy framework for inference. Neural Networks 15:247–261CrossRefGoogle Scholar
  20. 20.
    Chen J (1995) Robust Residual Generation for Model-Based Fault Diagnosis of Dynamic Systems. PhD Thesis, Department of Electronics, University of York, UKGoogle Scholar
  21. 21.
    Chen J and Patton RJ (1999) Robust Model Based Fault Diagnosis for Dynamic Systems. Kluwer Academic Publishers, New YorkzbMATHGoogle Scholar
  22. 22.
    Chen YC and Teng CC (1995) A model reference control structure using a fuzzy neural network. Fuzzy Sets and Systems 73:291–312CrossRefMathSciNetzbMATHGoogle Scholar
  23. 23.
    Cherian RP, Smith LN and Midha PS (2000) A neural network approach for selection of powder metallurgy materials and process parameters. Artificial Intelligence Engineering 14:39–44CrossRefGoogle Scholar
  24. 24.
    Chow MY, Mangum PM and Yee SO (1991) A neural network approach to real-time condition monitoring of induction motors. IEEE Trans. ion Industrial Electronics 38:448–453CrossRefGoogle Scholar
  25. 25.
    Chow MY, Sharpe RN and Hung JC (1993) On the application and design of artificial neural networks for motor fault detection—Part II. IEEE Trans. on Industrial Electronics 40: 189–196CrossRefGoogle Scholar
  26. 26.
    Cook GE, Barnett RJ, Andersen K and Strauss AM (1995) Weld modelling and control using artificial neural network. IEEE Trans. on Industry Applications 31:1484–1491CrossRefGoogle Scholar
  27. 27.
    Edwards PJ, Murray AF, Papadopoulos G, Wallace AR, Barnard J and Smith G (1999) The application of neural networks to the papermaking industry. IEEE Trans. on Neural Networks 10: 1456–1464CrossRefGoogle Scholar
  28. 28.
    Er MJ and Liew KC (1997) Control of adept one SCARA robot using neural networks. IEEE Trans. on Industrial Electronics 44: 762–768CrossRefGoogle Scholar
  29. 29.
    Farag WA, Quintana VH and Torres GL (1998) A genetic-based neuro-fuzzy approach for modelling and control of dynamical systems. IEEE Trans. on Neural Networks 9: 756–767CrossRefGoogle Scholar
  30. 30.
    Feuring T, Buckley JJ and Hayashi Y (1999) Fuzzy neural nets can solve the overfitting problem. In: Proceedings of the Int. Joint Conference on Neural Networks 4: 4197–4201Google Scholar
  31. 31.
    Filippetti F, Franceschini G and Tassoni C (1995) Neural networks aided online diagnostics of induction motor rotor faults. IEEE Trans. on Industry Applications 31:892–899CrossRefGoogle Scholar
  32. 32.
    Filippetti F, Franceschini G, Tassoni C and Vas P (2000) Recent developments of induction motor drives fault diagnosis using AI techniques. IEEE Trans. on Industrial Electronics 47: 994–1004CrossRefGoogle Scholar
  33. 33.
    Fisher Controls, Control Valve Engineering. USAGoogle Scholar
  34. 34.
    Fogel DB (1990) Selecting an optimal neural network industrial electronics society. In: Proceedings of IEEE IECON’90,vol. 2, pp. 1211–1214Google Scholar
  35. 35.
    Fukuda T and Shibata T (1992) Theory and applications of neural networks for industrial control systems. IEEE Trans. on Industrial Applications 39: 472–489CrossRefGoogle Scholar
  36. 36.
    Garcia FJ, Izquierdo V, Miguel L and Peran J (1997) Fuzzy Identification of Systems and its Applications to Fault Diagnosis Systems. In: Proceedings of the 3rd IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes — SAFEPROCESS’97, Hull, UK, vol. 2, August 26–28, pp. 705–712Google Scholar
  37. 37.
    Gorni AA (1997) The application of neural networks in the modeling of plate rolling processes. JOM-e 49(4) (electronic document)Google Scholar
  38. 38.
    Hashimoto H, Kubota T, Sato M and Harashima F (1992) Visual control of robotic manipulator based on neural networks. IEEE Trans. on Industrial Electronics 39: 490–496CrossRefGoogle Scholar
  39. 39.
    Hayashi Y, Buckley JJ and Czogala E (1993) Fuzzy Neural Networks with Fuzzy Signals and Weights. International Journal of Intelligent Systems 8: 527–537zbMATHGoogle Scholar
  40. 40.
    Haykin S (1999) Neural Networks — A Comprehensive Foundation (2nd Edition). Prentice-Hall, New JerseyzbMATHGoogle Scholar
  41. 41.
    Horikawa S, Furuhashi T and Uchikawa Y (1992) On fuzzy modelling using fuzzy neural networks with the back-propagation algorithm. IEEE Trans. on Neural Networks 3:801–806CrossRefGoogle Scholar
  42. 42.
    Huang CY, Chen TC and Huang CL (1999) Robust control of induction motor with a neural-network load torque estimator and a neural-network identification. IEEE Trans. on Industrial Electronics 46:990–998CrossRefGoogle Scholar
  43. 43.
    Ikonomopoulos A, Uhrig RE and Tsoukalas LH (1992) Use of neural networks to monitor power plant components. In: Proceedings of American Power Conference, vol. 54?II, April, pp. 1132–1137Google Scholar
  44. 44.
    Ishibuchi H, Morioka K and Turksen IB (1995) Learning by fuzzified neural networks. International Journal of Approximate Reasoning 13(3):327–358CrossRefzbMATHGoogle Scholar
  45. 45.
    Ishibuchi H and Nii M (2001) Numerical analysis of the learning of fuzzified neural networks from if-then rules. Fuzzy Sets and Systems 120(2):281–307CrossRefMathSciNetzbMATHGoogle Scholar
  46. 46.
    Jang J-SR (1993) ANFIS: Adaptive-network-based fuzzy inference system. IEEE Trans. on Systems, Man and Cybernetics 23:665–684CrossRefGoogle Scholar
  47. 47.
    Jung S and Hsia TC (1998) Neural network impedance force control of robot manipulator. IEEE Trans. on Industrial Electronics 45:451–461CrossRefGoogle Scholar
  48. 48.
    Kavaklioglu K and Upadhyaya BR (1994) Monitoring feedwater flow rate and component thermal performance of pressurized water reactors by means of artificial neural networks. Nuclear Technology 107:112–123Google Scholar
  49. 49.
    Keller JM and Hunt D (1985) Incorporating Fuzzy Membership Functions into the Perceptron Algorithm. IEEE Trans. on Pattern Analysis and Machine Intelligence 7: 693–699CrossRefGoogle Scholar
  50. 50.
    Khalid M and Omatu S (1992) A neural network controller for a temperature control system. IEEE Control Systems Magazine 12:58–64CrossRefGoogle Scholar
  51. 51.
    Khalid M, Omatu S and Yusof R (1995) Temperature regulation with neural networks and alternative control schemes. IEEE Trans. on Neural Networks 6:572–582CrossRefGoogle Scholar
  52. 52.
    Khotanzad A, Elragal H and Lu TL (2000) Combination of artificial neural-network forecasters for prediction of natural gas consumption. IEEE Trans. on Neural Networks 11:464–473CrossRefGoogle Scholar
  53. 53.
    Kiguchi K and Fukuda T (1997) Intelligent position/force controller for industrial robot manipulators — application of fuzzy neural networks. IEEE Trans. on Industrial Electronics 44:753–761CrossRefGoogle Scholar
  54. 54.
    Klir JG and Folger AT (1988) Fuzzy Sets, Uncertainty and Information. Prentice-Hall, New YorkzbMATHGoogle Scholar
  55. 55.
    Koj J (1998) The Fault Sources of Pneumatic Servo-Motor-Control Valve Assembly. In: Proceedings of the III Polish National conference on Diagnosis of Industrial Processes, Jurata, Poland, pp. 415–419 (in Polish)Google Scholar
  56. 56.
    Koscielny JM and Syfert M (2000) Application of Fuzzy Neural Networks for Fault Isolation-Example for Power Boiler System. In: Proceedings of 6th IEEE International Conference on Methods and Models in Automation and Robotics-MMAR’2000, Miedzyzdroje, Poland, vol. 2, pp. 801–806Google Scholar
  57. 57.
    Kowal M, Korbicz J, Mendes MJGC and Calado JMF (2002) Fault Detection Using Neuro-Fuzzy Networks. Systems Science Journal 28(1):45–57Google Scholar
  58. 58.
    Lampinen J, Smolander S and Korhonen M (1998) Wood surface inspection system based on generic visual features. In: Fogelman-Soulié F and Gallinari P (eds) Industrial Applications of Neural Networks. World Scientific, pp. 35–42Google Scholar
  59. 59.
    Lee SC and Lee ET (1975) Fuzzy neural networks. Mathematical Biosciences 23:151–177CrossRefMathSciNetzbMATHGoogle Scholar
  60. 60.
    Leonhardt S and Ayoubi M (1997) Methods of fault diagnosis. Control Engineering Practice 5(5):683–692CrossRefGoogle Scholar
  61. 61.
    Lewicki P, Hill T and Czyzewska M (1992) Nonconscious Acquisition of Information. American Psychologist 47(6):796–801CrossRefGoogle Scholar
  62. 62.
    Lin C-T and Lee CSG (1996) Neural Fuzzy Systems: A Neuro-Fuzzy Synergism to Intelligent Systems. Prentice-Hall, Upper Saddle River, NJGoogle Scholar
  63. 63.
    Lin FJ, Hwang WJ and Wai RJ (1999) A supervisory fuzzy neural network control system for tracking periodic inputs. IEEE Trans. on Fuzzy Systems 7:41–52CrossRefGoogle Scholar
  64. 64.
    Lin FJ, Wai RJ and Hong CM (2001) Hybrid Supervisory Control Using Recurrent Fuzzy Neural Network for Tracking Periodic Inputs. IEEE Trans. on Neural Networks 12(1):68–90CrossRefGoogle Scholar
  65. 65.
    Liu P (2000) On the approximation realization of fuzzy closure mapping by multilayer regular fuzzy neural network. Multiple Valued Logic 5(2): 463–480MathSciNetzbMATHGoogle Scholar
  66. 66.
    Liu P and Wang H (1999) Research on approximation capability of regular fuzzy neural network to continuous fuzzy function. Science in China, Series E 41(2):143–151Google Scholar
  67. 67.
    Liu Y, Upadhyaya BR and Naghedolfeizi M (1993) Chemometric data analysis using artificial neural networks. Applied Spectroscopy. 47(1):12–23CrossRefGoogle Scholar
  68. 68.
    Lopez-Toribio C, Patton R and Uppal F (1999) Artificial Intelligence Approaches to Fault Diagnosis for Dynamic Systems. International Journal of Applied Mathematics and Computer Science 9(3):471–518zbMATHGoogle Scholar
  69. 69.
    Louro R (2003) Fault Diagnosis of an Industrial Actuator Valve. MSc Dissertation, Instituto Superior Técnico, Technical University of Lisbon, NovemberGoogle Scholar
  70. 70.
    Marquardt D (1963) An Algorithm for Least-Squares Estimation of Nonlinear Parameters. SIAM Journal ofn Applied Mathematics 11:164–168MathSciNetGoogle Scholar
  71. 71.
    Martineau S, Gaura E, Burnham KJ and Haas OCL (2002) Neural network control approach for an industrial furnace. In: Proceedings of the 14th International Conference on Systems Science, Las Vegas, USA, pp. 227–233Google Scholar
  72. 72.
    McCulloch WS and Pitts W (1943) A Logical Calculus of the Ideas Immanent in Nervous Activity. Bulletin of Mathematics and Biophysics 5:115–133CrossRefMathSciNetzbMATHGoogle Scholar
  73. 73.
    Mendes MJGC, Kowal M, Calado JMF, Korbicz J and Sa da Costa JMG (2002) Fault Isolation Approach Using a Profibus Network: a case study. In: CONTROLO’2002, 5th Portuguese Conference on Automatic Control, pp. 525–530Google Scholar
  74. 74.
    Naidu SR, Zafiriou E and McAvoy TJ (1990) Use of neural networks for sensor failure detection in a control system. IEEE Control Systems Magazine 10:49–55CrossRefGoogle Scholar
  75. 75.
    Ozaki T, Suzuki T, Furuhashi T, Okuma S and Uchikawa Y (1991) Trajectory control of robotic manipulators using neural networks. IEEE Trans. on Industrial Electronics 38Google Scholar
  76. 76.
    Patterson DW (1996) Artificial Neural Networks: Theory and Applications. Prentice-HallGoogle Scholar
  77. 77.
    Patton RJ, Lopez-Toribio CJ and Uppal FJ (1999) Artificial Intelligence Approaches to Fault Diagnosis. International Journal of Applied Mathematics and Computer Sciences 9(3):471–518Google Scholar
  78. 78.
    Patton RJ, Frank PM and Clark RN (2000) Issues of Fault Diagnosis for Dynamic Systems. Springer, LondonGoogle Scholar
  79. 79.
    Payeur P, Le-Huy H and Gosselin CM (1995) Trajectory prediction for moving objects using artificial neural networks. IEEE Trans. on Industrial Electronics 42:147–158CrossRefGoogle Scholar
  80. 80.
    Rahman MH, Fazlur R, Devanathan R and Kuanyi Z (2000) Neural network approach for linearizing control of nonlinear process plants. IEEE Trans. on Industrial Electronics 47:470–477CrossRefGoogle Scholar
  81. 81.
    Rosenblatt F (1958) The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review 65:386–408CrossRefMathSciNetGoogle Scholar
  82. 82.
    Rubaai A and Kotaru R (2000) Online identification and control of a DC motor using learning adaptation of neural networks. IEEE Trans. on Industry Applications 36:935–942CrossRefGoogle Scholar
  83. 83.
    Rumelhart DE, Widrow B and Lehr MA (1994) The basic ideas in neural networks. Communications of the ACM 37(3):87–92CrossRefGoogle Scholar
  84. 84.
    Rutkowska D and Hayashi Y (1999) Neuro-Fuzzy Systems Approaches. Journal of Advanced Computational Intelligence 3(3):177–185Google Scholar
  85. 85.
    Sardy S, Ibrahim L and Yasuda Y (1993) An application of vision system for the identification and defect detection on woven fabrics by using artificial neural networks. In: Proceedings of Int. Joint Conference on Neural Networks, pp. 2141–2144Google Scholar
  86. 86.
    Sorsa T, Koivo HN and Koivisto H (1991) Neural networks in process fault diagnosis. IEEE Trans. on Systems, Man and Cybernetics 21:815–825CrossRefGoogle Scholar
  87. 87.
    Sun F, Sun Z and Woo PY (2001) Neural network-based adaptive controller design of robotic manipulators with an observer. IEEE Trans. on Neural Networks 12:54–67CrossRefGoogle Scholar
  88. 88.
    Sundareshan MK and Askew C (1997) Neural network-assisted variable structure control scheme for control of a flexible manipulator arm. Automatica 33(9):1699–1710CrossRefMathSciNetGoogle Scholar
  89. 89.
    Takagi H (1990) Fusion technology of fuzzy theory and neural networks — Survey and future directions. In: Proceedings of International Conference on Fuzzy Logic and Neural Networks (IIZUKA’90), Iizuka, Japan, July 20–24, pp. 13–26Google Scholar
  90. 90.
    Tsoukalas L and Reyes-Jimenez J (1990) Hybrid expert system-neural network methodology for nuclear plant monitoring and diagnostics. In: Proceedings of SPIE Applications of Artificial Intelligence VIII, vol. 1293, April 1990, pp. 1024–1030Google Scholar
  91. 91.
    Uhrig RE (1994) Application of artificial neural networks in industrial technology. In: Proceedings of the IEEE Int. Conf. Industrial Technology, pp.73–77Google Scholar
  92. 92.
    Vemuri AT and Polycarpou MM (1997) Neural-network-based robust fault diagnosis in robotic systems. IEEE Trans. on Neural Networks 8:1410–1420CrossRefGoogle Scholar
  93. 93.
    Venayagamoorthy GK and Harley RG (1999) Experimental studies with a continually online-trained artificial neural network controller for a turbo generator. In: Proceedings of the International Joint Conference on Neural Networks, vol. 3, Washington, DC, July, pp. 2158–2163Google Scholar
  94. 94.
    Zurada JM (1992) Introduction to Artificial Neural Systems. West Publishing CompanyGoogle Scholar
  95. 95.
    Wang LX (1997) A Course in Fuzzy Systems and Control. Prentice-Hall, Englewood Cliffs, NJzbMATHGoogle Scholar
  96. 96.
    Wishart M and Harley RG (1995) Identification and control of induction machines using artificial neural networks. IEEE Trans. on Industry Applications 31:612–619CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2006

Authors and Affiliations

  • João Calado
    • 1
  • José Sá da Costa
    • 2
  1. 1.Mechanical Engineering Studies CentreIDMEC/ISEL, Polytechnic Institute of LisbonLisbonPortugal
  2. 2.Department of Mechanical Engineering, GCAR/IDMECTechnical University of LisbonLisbonPortugal

Personalised recommendations