Neural network applications in fault diagnosis and detection: an overview of implementations in engineering-related systems

  • Ahmad Azharuddin Azhari Mohd Amiruddin
  • Haslinda Zabiri
  • Syed Ali Ammar Taqvi
  • Lemma Dendena Tufa
Review Article


The use of artificial neural networks (ANN) in fault detection analysis is widespread. This paper aims to provide an overview on its application in the field of fault identification and diagnosis (FID), as well as the guiding elements behind their successful implementations in engineering-related applications. In most of the reviewed studies, the ANN architecture of choice for FID problem-solving is the multilayer perceptron (MLP). This is likely due to its simplicity, flexibility, and established usage. Its use managed to find footing in a variety of fields in engineering very early on, even before the technology was as polished as it is today. Recurrent neural networks, while having overall stronger potential for solving dynamic problems, are only suggested for use after a simpler implementation in MLP was attempted. Across various ANN applications in FID, it is observed that preprocessing of the inputs is extremely important in obtaining the proper features for use in training the network, particularly when signal analysis is involved. Normalization is practically a standard for ANN use, and likely many other decision-based learning methods due to its ease of use and high impact on speed of convergence. A simple demonstration of ANN’s ease of use in solving a unique FID problem was also shown.


Artificial neural network Fault detection Fault diagnosis Engineering application Data preprocessing 



The authors would like to thank MOSTI Grant Science Fund 0153AB-B67 for the funding provided for this work. The authors would also like to thank Universiti Teknologi PETRONAS (UTP) for the support provided for this research.


  1. 1.
    Pandya DH, Upadhyay SH, Harsha SP (2012) ANN based fault diagnosis of rolling element bearing using time-frequency domain feature. Int J Eng Sci Technol 4(6):2878–2886Google Scholar
  2. 2.
    Zhou J et al (2014) Fault detection and identification spanning multiple processes by integrating PCA with neural network. Appl Soft Comput 14:4–11Google Scholar
  3. 3.
    Gastaldello D et al (2012) Fault location in underground systems using artificial neural networks and PSCAD/EMTDC. In: IEEE 16th international conference on intelligent engineering systems (INES) 2012. IEEE, Lisbon, pp 423–427Google Scholar
  4. 4.
    Samanta B, Al-Balushi KR, Al-Araimi SA (2004) Bearing fault detection using artificial neural networks and genetic algorithm. EURASIP J Adv Signal Process 2004(3):785672Google Scholar
  5. 5.
    Kumar A (2003) Neural network based detection of local textile defects. Pattern Recognit 36(7):1645–1659Google Scholar
  6. 6.
    Mekki H, Mellit A, Salhi H (2016) Artificial neural network-based modelling and fault detection of partial shaded photovoltaic modules. Simul Model Pract Theory 67(Supplement C):1–13Google Scholar
  7. 7.
    Hwang BC, Saif M, Jamshidi M (1993) Neural based fault detection and identification for a nuclear reactor. IFAC Proc Vol 26(2, Part 5):547–550Google Scholar
  8. 8.
    Patton RJ, Frank PM, Clark RN (2013) Issues of fault diagnosis for dynamic systems. Springer, BerlinGoogle Scholar
  9. 9.
    Rajakarunakaran S et al (2008) Artificial neural network approach for fault detection in rotary system. Appl Soft Comput 8(1):740–748Google Scholar
  10. 10.
    Taqvi S et al (2017) Artificial neural network for anomalies detection in distillation column. In: Modeling, design and simulation of systems: 17th Asia simulation conference, AsiaSim 2017, Melaka, Malaysia. Springer, SingaporeGoogle Scholar
  11. 11.
    López-Mata E et al (2016) Development of a direct-solution algorithm for determining the optimal crop planning of farms using deficit irrigation. Agric Water Manag 171:173–187Google Scholar
  12. 12.
    Choudhury S, Jain M, Shah S (2008) Stiction-definition, modelling, detection and quantification. J Process Control 18(3–4):232–243Google Scholar
  13. 13.
    Chen J, Patton RJ (1999) Robust model-based fault diagnosis for dynamic systems. Kluwer, New York, p 354zbMATHGoogle Scholar
  14. 14.
    Schmitz GPJ, Aldrich C, Gouws FS (1999) ANN-DT: an algorithm for extraction of decision trees from artificial neural networks. IEEE Trans Neural Netw 10(6):1392–1401Google Scholar
  15. 15.
    Muhammad T, Halim Z (2016) Employing artificial neural networks for constructing metadata-based model to automatically select an appropriate data visualization technique. Appl Soft Comput 49(Supplement C):365–384Google Scholar
  16. 16.
    Zhang G, Eddy Patuwo B, Hu MY (1998) Forecasting with artificial neural networks: the state of the art. Int J Forecast 14(1):35–62Google Scholar
  17. 17.
    Dougherty M (1995) A review of neural networks applied to transport. Transp Res Part C Emerg Technol 3(4):247–260Google Scholar
  18. 18.
    Jayas DS, Paliwal J, Visen NS (2000) Review paper (AE—automation and emerging technologies): multi-layer neural networks for image analysis of agricultural products. J Agric Eng Res 77(2):119–128Google Scholar
  19. 19.
    Catelani M, Gori M (1996) On the application of neural networks to fault diagnosis of electronic analog circuit. Measurement 17(2):73–80Google Scholar
  20. 20.
    Aminian M, Aminian F (2000) Neural-network based analog-circuit fault diagnosis using wavelet transform as preprocessor. IEEE Trans Circuits Syst II Analog Digit Signal Process 47(2):151Google Scholar
  21. 21.
    Spina R, Upadhyaya S (1997) Linear circuit fault diagnosis using neuromorphic analyzers. IEEE Trans Circuits Syst II Analog Digit Signal Process 44(3):188–196Google Scholar
  22. 22.
    Dreiseitl S, Ohno-Machado L (2002) Logistic regression and artificial neural network classification models: a methodology review. J Biomed Inform 35(5):352–359Google Scholar
  23. 23.
    Patan K (2008) Artificial neural networks for the modelling and fault diagnosis of technical processes. Springer, BerlinGoogle Scholar
  24. 24.
    Hussain M (1999) Review of the applications of neural networks in chemical process control—simulation and online implementation. Artif Intell Eng 13(1):55–68MathSciNetGoogle Scholar
  25. 25.
    Bhat NV et al (1990) Modeling chemical process systems via neural computation. IEEE Control Syst Mag 10(3):24–30Google Scholar
  26. 26.
    Miller WT, Werbos PJ, Sutton RS (1995) Neural networks for control. MIT Press, CambridgezbMATHGoogle Scholar
  27. 27.
    Antsaklis PJ (1990) Neural networks for control systems. IEEE Trans Neural Netw 1(2):242–244Google Scholar
  28. 28.
    Koivo HN (1994) Artificial neural networks in fault diagnosis and control. Control Eng Pract 2(1):89–101Google Scholar
  29. 29.
    Narendra KS, Parthasarathy K (1990) Identification and control of dynamical systems using neural networks. IEEE Trans Neural Netw 1(1):4–27Google Scholar
  30. 30.
    Nelles O (2013) Nonlinear system identification: from classical approaches to neural networks and fuzzy models. Springer, BerlinzbMATHGoogle Scholar
  31. 31.
    Rutkowski L, Rutkowski L (2004) New soft computing techniques for system modeling, pattern classification and image processing. Springer, BerlinzbMATHGoogle Scholar
  32. 32.
    Zhang J, Man K (1998) Time series prediction using RNN in multi-dimension embedding phase space. In: 1998 IEEE international conference on systems, man, and cybernetics. IEEEGoogle Scholar
  33. 33.
    Haykin S (1994) Neural networks: a comprehensive foundation. Prentice Hall PTR, Upper Saddle RiverzbMATHGoogle Scholar
  34. 34.
    Janczak A (2004) Identification of nonlinear systems using neural networks and polynomial models: a block-oriented approach, vol 310. Springer, BerlinzbMATHGoogle Scholar
  35. 35.
    Patan K, Parisini T (2005) Identification of neural dynamic models for fault detection and isolation: the case of a real sugar evaporation process. J Process Control 15(1):67–79Google Scholar
  36. 36.
    Frank PM, Köppen-Seliger B (1997) New developments using AI in fault diagnosis. Eng Appl Artif Intell 10(1):3–14Google Scholar
  37. 37.
    Calado J et al (2001) Soft computing approaches to fault diagnosis for dynamic systems. Eur J Control 7(2–3):248–286zbMATHGoogle Scholar
  38. 38.
    Korbicz J et al (2012) Fault diagnosis: models, artificial intelligence, applications. Springer, BerlinGoogle Scholar
  39. 39.
    Zhang J, Roberts PD (1992) On-line process fault diagnosis using neural network techniques. Trans Inst Meas Control 14(4):179–188Google Scholar
  40. 40.
    Svozil D, Kvasnicka V, Pospichal J (1997) Introduction to multi-layer feed-forward neural networks. Chemometr Intell Lab Syst 39(1):43–62Google Scholar
  41. 41.
    Stinchcombe M, White H (1989) Universal approximation using feedforward networks with non-sigmoid hidden layer activation functions. In: International 1989 joint conference on neural networks, Washington DC, USA, vol 1, pp 613–617Google Scholar
  42. 42.
    Nawi NM, Atomi WH, Rehman MZ (2013) The effect of data pre-processing on optimized training of artificial neural networks. Procedia Technol 11(Supplement C):32–39Google Scholar
  43. 43.
    Al-Naser M, Elshafei M, Al-sarkhi A (2016) Artificial neural network application for multiphase flow patterns detection: a new approach. J Petrol Sci Eng 145:548–564Google Scholar
  44. 44.
    Gertler J (1998) Fault detection and diagnosis in engineering systems. Marcel Dekker, New YorkGoogle Scholar
  45. 45.
    Isermann R, Ballé P (1997) Trends in the application of model-based fault detection and diagnosis of technical processes. Control Eng Pract 5(5):709–719Google Scholar
  46. 46.
    Venkatasubramanian V, Rengaswamy R, Kavuri SN (2003) A review of process fault detection and diagnosis: part II: qualitative models and search strategies. Comput Chem Eng 27(3):313–326Google Scholar
  47. 47.
    Venkatasubramanian V et al (2003) A review of process fault detection and diagnosis: part III: process history based methods. Comput Chem Eng 27(3):327–346MathSciNetGoogle Scholar
  48. 48.
    Venkatasubramanian V (2003) A review of process fault detection and diagnosis: part I: quantitative model-based methods. Comput Chem Eng 27(3):293–311MathSciNetGoogle Scholar
  49. 49.
    Basheer IA, Hajmeer M (2000) Artificial neural networks: fundamentals, computing, design, and application. J Microbiol Methods 43(1):3–31Google Scholar
  50. 50.
    Śmieja FJ (1993) Neural network constructive algorithms: trading generalization for learning efficiency? Circuits Syst Signal Process 12(2):331–374zbMATHGoogle Scholar
  51. 51.
    Westreich D, Lessler J, Funk MJ (2010) Propensity score estimation: neural networks, support vector machines, decision trees (CART), and meta-classifiers as alternatives to logistic regression. J Clin Epidemiol 63(8):826–833Google Scholar
  52. 52.
    Santín D, Delgado FJ, Valiño A (2004) The measurement of technical efficiency: a neural network approach. Appl Econ 36(6):627–635Google Scholar
  53. 53.
    Gurney K (1997) An introduction to neural networks. UCL Press, LondonGoogle Scholar
  54. 54.
    Demuth HB, Beale MH (2000) Neural network toolbox; for use with MATLAB; computation, visualization, programming; user's guide, version 4. Math WorksGoogle Scholar
  55. 55.
    Reed RD, Marks RJ (1998) Neural smithing: supervised learning in feedforward artificial neural networks. MIT Press, Cambridge, p 346Google Scholar
  56. 56.
    Setiono R (1997) Extracting rules from neural networks by pruning and hidden-unit splitting. Neural Comput 9(1):205–225zbMATHGoogle Scholar
  57. 57.
    Garson G (1991) Interpreting neural-network connections. AI Expert 6:46–51Google Scholar
  58. 58.
    Haykin SS, Haykin SS (2009) Neural networks and learning machines, 3rd edn. Prentice Hall, New YorkzbMATHGoogle Scholar
  59. 59.
    Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. Trans Neural Netw 5(2):157–166Google Scholar
  60. 60.
    Hagan M, Demuth H, Beale M, Jesús O (2014) Neural network design. University of Colorado, BoulderGoogle Scholar
  61. 61.
    Chen L (2009) Curse of dimensionality. In: Liu L, ÖZsu MT (eds) Encyclopedia of database systems. Springer, Boston, pp 545–546Google Scholar
  62. 62.
    Smith LI (2002) A tutorial on Principal Components Analysis. Computer Science Technical Report No. OUCS-2002-12. Accessed 2 Feb 2018
  63. 63.
    Merry RJE (2005) Wavelet theory and applications: a literature study, p 41. Accessed 20 Dec 2017
  64. 64.
    Dolley Shukla JS (2013) Wavelets: basic concepts. Int J Electr Electron Eng Telecommun 4:33Google Scholar
  65. 65.
    Mallat SG (1989) A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell 11(7):674–693zbMATHGoogle Scholar
  66. 66.
    Sharma R et al (2004) Neural network applications for detecting process faults in packed towers. Chem Eng Process 43(7):841–847Google Scholar
  67. 67.
    Paya BA, Esat II, Badi MNM (1997) Artificial neural network based fault diagnostics of rotating machinery using wavelet transforms as a preprocessor. Mech Syst Signal Process 11(5):751–765Google Scholar
  68. 68.
    Banjanovic-Mehmedovic L et al (2017) Neural network based data-driven modelling of anomaly detection in thermal power plant. Automatika 58:69–79Google Scholar
  69. 69.
    Misra M et al (2002) Multivariate process monitoring and fault diagnosis by multi-scale PCA. Comput Chem Eng 26(9):1281–1293Google Scholar
  70. 70.
    Feng Z, Xu T (2011) Comparison of SOM and PCA-SOM in fault diagnosis of ground-testing bed. Procedia Eng 15(Supplement C):1271–1276Google Scholar
  71. 71.
    Ziani R et al (2012) Bearing fault diagnosis using neural network and genetic algorithms with the trace criterion. In: Fakhfakh T et al (eds) Condition monitoring of machinery in non-stationary operations: proceedings of the second international conference “condition monitoring of machinery in non-stationary operations” CMMNO’2012. Springer, Berlin, pp 89–96Google Scholar
  72. 72.
    Behbahani RM, Jazayeri-Rad H, Hajmirzaee S (2009) Fault detection and diagnosis in a sour gas absorption column using neural networks. Chem Eng Technol 32(5):840–845Google Scholar
  73. 73.
    Manssouri I, Chetouani Y, Kihel BE (2008) Using neural networks for fault detection in a distillation column. Int J Comput Appl Technol 32(3):181–186Google Scholar
  74. 74.
    Jamil M, Sharma SK, Singh R (2015) Fault detection and classification in electrical power transmission system using artificial neural network. SpringerPlus 4(1):334Google Scholar
  75. 75.
    Abbasi Nozari H et al (2012) Model-based robust fault detection and isolation of an industrial gas turbine prototype using soft computing techniques. Neurocomputing 91:29–47Google Scholar
  76. 76.
    Taqvi SA, Tufa LD, Zabiri H et al (2018) Fault detection in distillation column using NARX neural network. Neural Comput Applic. Google Scholar
  77. 77.
    Kiakojoori S, Khorasani K (2016) Dynamic neural networks for gas turbine engine degradation prediction, health monitoring and prognosis. Neural Comput Appl 27(8):2157–2192Google Scholar
  78. 78.
    Tidriri K et al (2016) Bridging data-driven and model-based approaches for process fault diagnosis and health monitoring: a review of researches and future challenges. Annu Rev Control 42:63–81Google Scholar
  79. 79.
    LeCun Y et al (1998) Efficient BackProp. In: Orr GB, Müller K-R (eds) Neural networks: tricks of the trade. Springer, Berlin, pp 9–50Google Scholar
  80. 80.
    Starr KD, Petersen H, Bauer M (2016) Control loop performance monitoring—ABB’s experience over two decades. IFAC-PapersOnLine 49(7):526–532Google Scholar
  81. 81.
    Kline DM, Berardi VL (2005) Revisiting squared-error and cross-entropy functions for training neural network classifiers. Neural Comput Appl 14(4):310–318Google Scholar
  82. 82.
    Shoukat Choudhury MAA, Thornhill NF, Shah SL (2005) Modelling valve stiction. Control Eng Pract 13(5):641–658Google Scholar
  83. 83.
    Choudhury MAAS, Kariwala V, Shah SL, Douke H, Takada H, Thornhill NF (2005) A simple test to confirm control valve stiction. IFAC Proc 38(1):81–86. Google Scholar
  84. 84.
    Jelali M, Huang B (2010) Detection and diagnosis of stiction in control loops: state of the art and advanced methods. Springer, LondonGoogle Scholar
  85. 85.
    Farenzena M, Trierweiler JO (2009) A novel technique to estimate valve stiction based on pattern recognition. In: de Brito Alves RM, do Nascimento CAO, Biscaia EC (eds) Computer aided chemical engineering. Elsevier, Amsterdam, pp 1191–1196Google Scholar
  86. 86.
    Venceslau AR, Guedes LA, Silva DR (2012) Artificial neural network approach for detection and diagnosis of valve stiction. In: 2012 IEEE 17th conference on emerging technologies and factory automation (ETFA). IEEEGoogle Scholar
  87. 87.
    Bacci di Capaci R, Scali C (2018) Review and comparison of techniques of analysis of valve stiction: from modeling to smart diagnosis. Chem Eng Res Des 130:230–265Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Chemical EngineeringUniversiti Teknologi PETRONASBandar Seri IskandarMalaysia
  2. 2.Department of Chemical EngineeringNED University of Engineering & TechnologyKarachiPakistan

Personalised recommendations