Computational Intelligence Methodologies in Fault Diagnosis: Review and State of the Art

  • Cosmin Danut Bocaniala
  • Vasile Palade
Part of the Advanced Information and Knowledge Processing book series (AI&KP)


This first chapter of the book introduces the reader to the area of computational intelligence techniques and to their significant and abundant applications to fault diagnosis. Fault diagnosis represents an important contemporary research field, due to the ever-increasing need for safety, maintainability and reliability of industrial plants. The research in this field influences important areas of our day-to-day life by increasing security when using safety-critical devices, extending the lifetime of many expensive devices, and improving efficiency of manufacturing lines, which leads to smaller production expenses and lower prices for the end user.

The main problems raised by the processes taking place within modern industrial plants are their high nonlinearity, noisy signals, and uncertainty. Computational intelligence techniques — neural networks, fuzzy techniques, genetic algorithms, etc. — are the very answer of the fault diagnosis research community to these problems. This book represents a collection of recent results on applying various computational intelligence techniques to fault diagnosis. In this introductory chapter, the reader is presented with a short description of the main computational intelligence techniques together with a literature review on their applications to fault diagnosis.

Another major problem raised by the modern industrial plants is their high level of complexity. The complexity of a plant is understood here as the impossibility to model its global emergent behavior using state-of-the-art modeling techniques. Unfortunately, even if they offer better performance than mathematical models when modeling processes with reasonable complexity, the computational intelligence techniques cannot successfully model very complex processes.

The answer given by the research community to this problem is to develop distributed fault diagnosis methodologies. The main idea is to partition the monitored system in subsystems having a reasonable complexity level and, then, to successfully apply state-of-the-art methodologies on each one of them. The global diagnosis of the system is going to be based on all these local diagnosis processes. Implementing the local diagnosis processes using computational intelligence methodologies retains their ability to treat the local nonlinearities, noise and uncertainty. The book contains a special chapter dealing with distributed fault diagnosis methodologies.


Fault Detection Fuzzy Rule Fault Diagnosis Monitor System Fault Isolation 
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.
    Ariton V and Palade V (2005) Human-like fault diagnosis using a neural network implementation of plausibility and relevance. Neural Computing & Applications 14(2):149–165CrossRefGoogle Scholar
  2. 2.
    Ayoubi M (1994) Fault diagnosis with dynamic neural structure and application to a turbocharger. In: Proceedings of 1st IFAC Symposium SAFEPROCESS’94, Espoo, Finland, vol. 2, pp. 618–623Google Scholar
  3. 3.
    Babuska R (2002) Neuro-fuzzy methods for modeling and identification. In: Abraham A, Jain LC and Kacprzyk J (eds) Recent Advances in Intelligent Paradigms and Applications, pp. 161–186, Springer-Verlag, HeidelbergGoogle Scholar
  4. 4.
    Bartys M, Patton RJ, Syfert M, De las Heras S and Quevedo J (2004) Introduction to the DAMADICS Actuator FDI Benchmark Study. Control Engineering Practice, in print (see Articles in Press section of this title on ScienceDirect)Google Scholar
  5. 5.
    Basseville M and Nikiforov IV (1993) Detection of abrupt changes: theory and application. Information and System Science. Prentice Hall, New YorkGoogle Scholar
  6. 6.
    Beard R V (1971) Failure accommodation in linear system through selfreorganization (PhD thesis). MIT, Massachusetts, USAGoogle Scholar
  7. 7.
    Bendtsen JD and Izadi-Zamanabadi R (2002) FDI using neural networks — application to ship benchmark engine gain. In: Preprints of the 15th IFAC World Congress, Barcelona, SpainGoogle Scholar
  8. 8.
    Bocaniala CD, Sa da Costa J and Palade V (2004) A Novel Fuzzy Classification Solution for Fault Diagnosis. International Journal of Fuzzy and Intelligent Systems 15(3–4):195–206zbMATHGoogle Scholar
  9. 9.
    Bocaniala CD, Sa da Costa J and Palade V (2005) Fuzzy-based refinement of the fault diagnosis task in industrial devices. International Journal of Intelligent Manufacturing, 16(6): 599–614CrossRefGoogle Scholar
  10. 10.
    Bonnisone PP and Decker KS (1986) Selecting uncertainty calculi and granularity: an experiment in trading off precision and complexity. North-Holland, AmsterdamGoogle Scholar
  11. 11.
    Breiman L (1996) Bagging predictors. Machine Learning 24(2): 123–140MathSciNetzbMATHGoogle Scholar
  12. 12.
    Brown M and Harris C (1995) Neurofuzzy Adaptive Modeling and Control. Prentice Hall InternationalGoogle Scholar
  13. 13.
    Calado JMG, 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: 248–286Google Scholar
  14. 14.
    Chen J and Patton RJ (1999) Robust Model-Based Fault Diagnosis for Dynamic Systems. Asian Studies in Computer Science and Information Science. Kluwer Academic Publishers, BostonGoogle Scholar
  15. 15.
    Chow EY and Willsky AS (1980) Issues in the development of a general algorithm for reliable failure detection. In: Proceedings of the 19th Conference of Decision and Control, Albuquerque, NM, USAGoogle Scholar
  16. 16.
    Clark RN (1978) Instrument fault detection. IEEE Transactions on Aerospace and Electronic Systems AES-14: 456–465Google Scholar
  17. 17.
    Clark RN, Fosth DC and Walton WM (1975) Detecting instrument malfunctions in control systems. IEEE Transactions on Aerospace and Electronic Systems AES-11: 465–473Google Scholar
  18. 18.
    Cordier MO, Dague P, Dumas M, Levy F, Montmain J, Staroswiecki M and Traves-Massuyes L (2000) AI and automatic control approaches of model-based diagnosis: Links and underlying hypothesis. In: Proceedings of the 4th IFAC Symposium SAFEPROCESS’00, Budapest, Hungary, vol. 1, pp. 274–279Google Scholar
  19. 19.
    Dalmi I, Kovács L, Loránt I and Terstyánszky G (2000) Diagnosing priori unknown faults by radial basis function neural network. In: Proceedings of the 4th IFAC Symposium SAFEPROCESS’00, Budapest, Hungary, vol. 1, pp. 405–409Google Scholar
  20. 20.
    Ding X and Frank PM (1990) Fault detection via factorization approach. Systems Control Letters 14(5): 431–436CrossRefMathSciNetzbMATHGoogle Scholar
  21. 21.
    Forbus KD (1984) Qualitative process theory. Artificial Intelligence 24: 85–168CrossRefGoogle Scholar
  22. 22.
    Frank PM (1987) Fault diagnosis in dynamic system via state estimation — a survey. In: Systems fault diagnostics, reliability and related knowledge-based approaches. D. Reidel Press, Dordrecht, GermanyGoogle Scholar
  23. 23.
    Frank PM (1991) Enhancement of robustness in observer-based fault detection. Preprints of IFAC/IMACS Symposium SAFEPROCESS’91, Baden-Baden, Germany, vol.1, pp. 275–287Google Scholar
  24. 24.
    Frank PM (1996) Analytical and qualitative model-based fault diagnosis — a survey and some new results. European Journal of Control 2: 6–28zbMATHGoogle Scholar
  25. 25.
    Frank PM, Ding X and Köppen B (1993) A frequency domain approach for fault detection at the inverted pendulum. In: Proceedings of International Conference on Fault Diagnosis TOOLDIAG’93, Toulouse, France, pp. 987–994Google Scholar
  26. 26.
    Fuente MJ and Saludes S (2000) Fault detection and isolation in a non-linear plant via neural networks. In: Proceedings of the 4th IFAC Symposium SAFEPROCESS’00, Budapest, Hungary, vol. 1, pp. 472–477Google Scholar
  27. 27.
    Gertler J (1991) Analytical redundancy methods in failure detection and isolation. In: Preprints of IFAC/IMACS Symposium SAFEPROCESS’91, Baden-Baden, Germany, vol. 1, pp. 9–21Google Scholar
  28. 28.
    Goldberg DE (1989) Genetic algorithms in search, optimization, and machine learning. Addison-Wesley, Boston, USAzbMATHGoogle Scholar
  29. 29.
    Hamscher WC, de Kleer J and Console L (1992) Readings in model-based diagnosis. Morgan Kaufmann, San Mateo, CA, USAGoogle Scholar
  30. 30.
    Haykin S (1999) Neural networks. A comprehensive foundation. Prentice-HallGoogle Scholar
  31. 31.
    Isermann R (1984) Process fault detection based on modeling and estimation methods: A survey. Automatica 20(4): 387–404CrossRefzbMATHGoogle Scholar
  32. 32.
    Isermann R (1991) Fault diagnosis of machine via parameter estimation and knowledge processing — tutorial paper. In: Preprints of IFAC/IMACS Symposium SAFEPROCESS’91, Baden-Baden, Germany, vol. 1, pp. 121–133Google Scholar
  33. 33.
    Isermann R (1997) Supervision, fault-detection and fault-diagnosis methods — an introduction. Control Engineering Practice 5(5): 639–652CrossRefGoogle Scholar
  34. 34.
    Isermann R and Ballé P (1997) Trends in the application of model-based fault detection and diagnosis of technical processes. Control Engineering Practice 5(5): 709–719CrossRefGoogle Scholar
  35. 35.
    Jones HL (1973) Failure detection in linear systems (PhD thesis). MIT, Massachusetts, USAGoogle Scholar
  36. 36.
    Kay H (1996) Refining imprecise models and their behaviors (PhD thesis). The University of Texas at Austin, USAGoogle Scholar
  37. 37.
    de Kleer J and Brown JS (1987) A qualitative physics based on confluences. Artificial Intelligence 24: 7–83CrossRefGoogle Scholar
  38. 38.
    de Kleer J and Kurien J (2003) Fundamentals of model-based diagnosis. In: Proceedings of the 5th IFAC Symposium SAFEPROCESS’03, Washington, USA, pp. 25–36Google Scholar
  39. 39.
    de Kleer J and Williams BC (1987) Diagnosing multiple faults. Artificial Intelligence 32: 97–130CrossRefzbMATHGoogle Scholar
  40. 40.
    Koscielny JM, Sedziak D and Zackroczymsky K (1999) Fuzzy-logic fault isolation in large-scale systems. International Journal of Applied Mathematics and Computer Science 9(3): 637–652zbMATHGoogle Scholar
  41. 41.
    Krogh A and Vedelsby L (1995) Neural networks ensembles, cross validation, and active learning. In: Advances in neural information processing systems. MIT Press, Cambridge, MA, USAGoogle Scholar
  42. 42.
    Korbicz, J, Patan K and Obuchowicz A (1999) Dynamic neural networks for process modeling in fault detection and isolation systems. International Journal of Applied Mathematics and Computer Science 9(3): 519–546zbMATHGoogle Scholar
  43. 43.
    Kuipers B (1984) Common sense reasoning about causality: deriving behavior from structure. Artificial Intelligence 24: 169:204CrossRefGoogle Scholar
  44. 44.
    Kuipers B (1986) Qualitative simulation. Artificial Intelligence 29: 289–338CrossRefMathSciNetzbMATHGoogle Scholar
  45. 45.
    Lopez-Toribio CJ, Patton RJ and Daley S (2000) Takagi-Sugeno Fault-Tolerant Control of an Induction Motor. Neural Computation and Applications 9: 19–28, Springer-Verlag, London, UKGoogle Scholar
  46. 46.
    Ma XJ, Sun ZQ and He YY (1998) Analysis and design of fuzzy controller and fuzzy observer. IEEE Transactions on Fuzzy Systems 6(1): 41–51CrossRefGoogle Scholar
  47. 47.
    Mamdani EH (1976) Advances in the linguistic synthesis of fuzzy controllers. International Journal of Man-Machine Studies 8:669–678CrossRefzbMATHGoogle Scholar
  48. 48.
    Marcu T, Mirea L and Frank PM (1999). Development of dynamic neural networks with application to observer-based fault detection and isolation. International Journal of Applied Mathematics and Computer Science 9(3): 547–570zbMATHGoogle Scholar
  49. 49.
    Marcu, T, Köppen-Seliger B, Frank PM and Ding SX (2003) Dynamic functional-link neural networks genetically evolved applied to fault diagnosis. In: Proceedings of the 7th European Control Conference ECC’03, September 1–4, University of Cambridge, UKGoogle Scholar
  50. 50.
    Marcu T, Mirea L, Ferariu L and Frank PM (2000) Miscellaneous neural networks applied to fault detection and isolation of an evaporation station. In: Proceedings of the 4th IFAC Symposium SAFEPROCESS’00, Budapest, Hungary, vol. 1, pp. 352–357Google Scholar
  51. 51.
    Mehra RK and Peschon J (1971) An innovations approach to fault detection and diagnosis in dynamic systems. Automatica 7: 637–640CrossRefGoogle Scholar
  52. 52.
    Metenidis MF, Witczak M and Korbicz J (2004) A novel genetic programming approach to nonlinear system modelling: application to the DAMADICS benchmark problem. Engineering Applications of Artificial Intelligence 17(4): 363–370CrossRefGoogle Scholar
  53. 53.
    Michalewicz Z (1996) Genetic Algorithms + Data Structures = Evolution Programs. Springer, BerlinzbMATHGoogle Scholar
  54. 54.
    Mirea L and Marcu T (2002) System identification using functional-link neural networks with dynamic structure. In: Preprints of the 15th IFAC World Congress, Barcelona, SpainGoogle Scholar
  55. 55.
    Mironovsky LA (1980) Functional diagnosis of linear dynamic systems — a survey. Automation Remote Control 41: 1122–1143Google Scholar
  56. 56.
    Negoita M, Neagu D and Palade V (2005) Computational Intelligence: Engineering of Hybrid Systems. Springer-VerlagGoogle Scholar
  57. 57.
    Palade V, Patton RJ, Uppal FJ, Quevedo J and Daley S (2002) Fault Diagnosis of An Industrial Gas Turbine Using Neuro-Fuzzy Methods. In: Proceedings of the 15th IFAC World Congress, 21–26 July, Barcelona, pp. 2477–2482Google Scholar
  58. 58.
    Patan K and Parisini T (2002) Stochastic approaches to dynamic neural network training. Actuator fault diagnosis study. In: Preprints of the 15th IFAC World Congress, Barcelona, SpainGoogle Scholar
  59. 59.
    Patra JC, Pal RN, Chatterji BN and Panda G (1999) Identification of non-linear dynamic systems using functional-link artificial neural networks. IEEE Transactions on Systems, Man and Cybernetics — part B 29(2):254–262CrossRefGoogle Scholar
  60. 60.
    Patton RJ (1997) Fault tolerant control: the 1997 situation (survey). In: Proceedings of the IFAC Symposium SAFEPROCESS’97, Pergamon, University of Hull, UK, pp. 1029–1052Google Scholar
  61. 61.
    Patton RJ and Chen J (1991) A review of parity space approaches to fault diagnosis. In: Preprints of IFAC/IMACS Symposium SAFEPROCESS’91, Baden-Baden, Germany, vol.1, pp. 239–255Google Scholar
  62. 62.
    Patton RJ and Chen J (1996) Robust fault detection and isolation (FDI) systems. Dynamics and Control (vol. 74): Techniques in discrete and continuous robust systems. Academic PressGoogle Scholar
  63. 63.
    Patton RJ and Chen J (1997) Observer-based fault detection and isolation: robustness and applications. Control Engineering Practice 5(5): 671–682CrossRefGoogle Scholar
  64. 64.
    Patton RJ and Kangethe SM (1989) Robust fault diagnosis using eigenstructure assignment of observers. In: Fault diagnosis in dynamic systems, theory and application. Control Engineering Series. Prentice Hall, New YorkGoogle Scholar
  65. 65.
    Patton RJ, Lopez-Toribio CJ and Uppal FJ (1999) Artificial intelligence approaches to fault diagnosis for dynamic systems. International Journal of Applied Mathematics and Computer Science 9(3): 471–518Google Scholar
  66. 66.
    Patton RJ, Lopez-Toribio CJ and Uppal FJ (2000) Soft computing approaches to fault diagnosis for dynamic systems: a survey. In: Proceedings of the 4th IFAC Symposium SAFEPROCESS’00, Budapest, Hungary, vol. 1, pp. 298–311Google Scholar
  67. 67.
    Puscasu G, Palade V, Stancu A, Buduleanu S and Nastase G (2000) Sisteme de conducere clasice si inteligente a proceselor. MATRIX ROM, Bucharest, RomaniaGoogle Scholar
  68. 68.
    Raiman O (1991) Order of magnitude reasoning. Artificial Intelligence 51: 11–38CrossRefGoogle Scholar
  69. 69.
    Reiter R (1987) A theory of diagnosis from First Principles. Artificial Intelligence 32: 57–95CrossRefMathSciNetzbMATHGoogle Scholar
  70. 70.
    Roverso D (2000) Neural ensembles for system identification. In: Proceedings of the 4th IFAC Symposium SAFEPROCESS’00, Budapest, Hungary, vol. 1, pp. 478–483Google Scholar
  71. 71.
    Sá da Costa J and Louro R (2003) Modelling and simulation of an industrial actuator valve for fault diagnosis benchmark. In: Proceedings of the Fourth International Symposium on Mathematical Modelling, Vienna, pp. 1212–1221, Agersin-Verlag.Google Scholar
  72. 72.
    Spanache S, Escobet T and Travé-Massuyès L (2004) Sensor Placement Optimisation Using Genetic Algorithms. In: Proceedings of the Fifteenth International Workshop on Principles of Diagnosis DX’04, June 23–25, Carcassonne, FranceGoogle Scholar
  73. 73.
    Sun R, Tsung F and Qu L (2004) Combining bootstrap and genetic programming for feature discovery in diesel engine diagnosis. International Journal of Industrial Engineering 11(3): 273–281Google Scholar
  74. 74.
    Takagi T and Sugeno M (1985) Fuzzy identification of systems and its application to modeling and control. IEEE Transactions on Systems, Man and Cybernetics 15(1): 116–132zbMATHGoogle Scholar
  75. 75.
    Terstyánszky G and Kovács L (2002) Improving fault diagnosis using proximity and homogeneity measure. In: Preprints of the 15th IFAC World Congress, Barcelona, SpainGoogle Scholar
  76. 76.
    Tzafestas SG and Watanabe K (1990) Modern approaches to system/sensor fault detection and diagnosis. Journal A 31(4): 42–57Google Scholar
  77. 77.
    Unland R and Ulieru M (2005) Swarm Intelligence and the Holonic Paradigm: A Promising Symbiosis for Medical Diagnostic Systems Design. In: Proceedings of the 9th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES2005, September 14–16, Melbourne, AustraliaGoogle Scholar
  78. 78.
    Uppal FJ, Patton RJ and Palade V (2002) Neuro-Fuzzy Based Fault Diagnosis Applied to an Electro-Pneumatic Valve. In: Proceedings of the 15th IFAC World Congress, 21–26 July, Barcelona, Spain, pp. 2483–2488Google Scholar
  79. 79.
    Vidyasagar M (1985) Control systems synthesis: a factorization approach. System and Control Series. North-Holland, MIT Press, Cambridge, MA, USAGoogle Scholar
  80. 80.
    Viswanadham N, Taylor JH and Luce EC (1987) A frequency-domain approach to failure detection and isolation with application to GE-21 turbine engine control systems. Control-Theory and Advanced Technology 3(1): 45–72MathSciNetGoogle Scholar
  81. 81.
    Waltz D (1975) Understanding line drawings of scene with drawings. In: The psychology of computer vision. McGraw-Hill, New YorkGoogle Scholar
  82. 82.
    Willsky AS and Jones HL (1974) A generalized likelihood approach to state estimation in linear systems subjected to abrupt changes. In: Proceedings of the 1974 IEEE Conference on Control and Decision, Arizona, USAGoogle Scholar
  83. 83.
    Yangping Z, Bingquan Z and DongXin W (2000) Application of genetic algorithms to fault diagnosis in nuclear power plants. Reliability Engineering and Systems Safety 67: 153–160CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2006

Authors and Affiliations

  • Cosmin Danut Bocaniala
    • 1
  • Vasile Palade
    • 2
  1. 1.Computer Science and Engineering Department“Dunarea de Jos” University of GalatiGalatiRomania
  2. 2.Computing LaboratoryOxford UniversityOxfordUK

Personalised recommendations