Skip to main content
SpringerLink
Log in

Fault Diagnosis Using Artificial Neural Networks (ANNs)

  • Chapter
Real Time Fault Monitoring of Industrial Processes

  • 343 Accesses

Abstract

The theory and practical applications of Artificial Neural Networks (ANNs) are expanding with very high rates, and the fields of application are increasing. It is not surprising, therefore, that fault diagnosis is one of the main areas that ANNs have been used with promising results, along with similar progress in control and identification of non-linear dynamical systems.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 219.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  • Ant saklis P.J. (1992). Neural networks for the intelligent control of high autonomy systems. Intelligent Systems Technical Report 92–9–1, Department of Electrical Engineering, University of Notre Dame.

    Google Scholar 

  • Barschdorff D., Monostori L. and T. Kottenstede (1993). Wear estimation and state classification of cutting tools in turning via artificial neural networks. Proceedings, International Conference on Fault Diagnosis TOOLDIAG 93, Toulouse, France, April 5–7, 669–677.

    Google Scholar 

  • Baba N. (1989). A new approach for finding the global minimum of error function of neural networks. Neural networks, 2.

    Google Scholar 

  • Barschdorff D., Monostori L., A.F. Ndenge and G.W. Wöstenkühler (1991). Multiprocessor systems for connectionist diagnosis of technical processes. Computers in Industry, 17, 131–145.

    Article  Google Scholar 

  • Bartlett E. and R.E. Uhrig (1992). Nuclear Power Plant Status Diagnostics Using An Artificial Neural Network. Nuclear Technology, 97.

    Google Scholar 

  • Boshers J. A., Saylor C., Kamadolli S., Wood R. and C. Isik. (1992). Control Rod Wear Recognition Using Neural Nets. In D.J. Sobajic, (Editor), Proceedings of the 1992 Summer Workshop on “Neural Networks Computing for the Electric Power Industry, Stanford, CA., August 17–19.

    Google Scholar 

  • Carpenter G.A. and S. Grossberg (1987). A massively parallel architecture for a self-organizing neural pattern recognition machine. Computer Vision, Graphics and Image Processing, 37, 54–115.

    Article  MATH  Google Scholar 

  • Carpenter G.A. and S. Grossberg (1987). ART2: Self-organization of stable category recognition codes for analog input patterns. Applied Optics, 26, 3, 4919–4930.

    Article  Google Scholar 

  • Chang K. and W.G. Wee (1988). A Knowledge-based planning system for mechanical assembly using robots. IEEE Expert, 18–30.

    Google Scholar 

  • Cheon S.W., Kang G.S. and S.H. Chang (1992). Application of Neural Networks to Connectionist Expert System for Identification of Transients in Nuclear Power Plants. Proceedings, 2nd International Forum. Expert Systems and Computer Simulation in Energy Engineering, Erlangen, Germany, March 17–20, pp 22–1–1 to 22–1–5.

    Google Scholar 

  • Chen S., Cowan C.F.N. and P.M. Grant (1991). Orthogonal least squares learning algorithm for radial basis function networks. IEEE Transactions on Neural Networks, 2, 2, 302–309.

    Article  Google Scholar 

  • Cho S.B. and J.H. Kim (1993). Rapid back-propagation learning algorithms. Circuits, Systems and Signal Processes, 12, 2.

    Google Scholar 

  • Chow M.-y., Mangum P.M. and S.O. Yee (1991). A neural network approach to real-time condition monitoring of induction motors. IEEE Transactions on Industrial Electronics, 38, 6, 448–453.

    Article  Google Scholar 

  • Cybenko G. (1989). Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems, 2, 303–314.

    Article  MathSciNet  MATH  Google Scholar 

  • Davis R. (1984). Diagnostic reasoning based on structure and behavior. Artifical Intelligence, 24, 347–410.

    Article  Google Scholar 

  • Doremus R. (1992). SAMSOM: Severe Accident Management System On-Line Network. In D.J. Sobajic, (Editor), Proceedings of the 1992 Summer Workshop on “Neural Network Computing for the Electric Power Industry, Stanford, CA, August 1719.

    Google Scholar 

  • Feldman J.A. and D.H. Ballard (1982). Connectionist models and their properties. Cognitive Science, 6, 205–254.

    Article  Google Scholar 

  • Feng X., Zhang Y. and Q. Chen (1993). Fault simulation of a variable thrust liquid rocket engine based on neural networks. Proceedings, International Conference on Fault Diagnosis TOOLDIAG ‘83, Toulouse, France, April 5–7, 787–791.

    Google Scholar 

  • Gien D. et al. (1993). A neuro-fuzzy approach for real-time diagnosis on flexible manufacturing cells. Proceedings, Sixth International Conference on Neural networks and other industrial and cognitive applications, Nimes, France, October 25–29.

    Google Scholar 

  • Guo Y. and K.J. Doodley (1992). Identification of change structure in statistical process control. International Journal of Production Research, 30, 7, 1655–1669.

    Article  Google Scholar 

  • Guo Z. and R.E. Uhrig R.E. (1992). Using Modular Neural Networks to Monitor Accident Conditions in Nuclear Power Plants. Proceedings of the SPIE Technical Symposium on Intelligent Information Systems, Application of Artificial Neural Networks III, Orlando, FL, April 20–24.

    Google Scholar 

  • Guo Z. and R.E. Uhrig (1992). Use of Artificial Neural Networks to Analyze Nuclear Power Plant Performance. Nuclear Technology, 99.

    Google Scholar 

  • Himmelblau D.M. (1978). Fault detection in chemical and petrochemical processes. Elsevier Publishers, Amsterdam.

    Google Scholar 

  • Hopfield J.J. (1982). Neural networks and physical systems with emergent computational abilities. Proceedings of the National Academy of Sciences (Biophysics), 79, 2554–2558.

    Article  MathSciNet  Google Scholar 

  • Hoskins J.C. and D.M. Himmelblau (1988). Artificial neural network models of knowledge representation in chemical engineering. Comput. Chem. Eng., 12, 881–890.

    Article  Google Scholar 

  • Ikonomopoulos A., Tsoukalas L.H., Mullens J.A. and R.E. Uhrig (1992). Monitoring nuclear reactor systems using neural network and fuzzy logic. Proceedings, 1992 Topical Meeting in Advances in Reactor Physics, March 8–11, Charleston, U.S.A.

    Google Scholar 

  • Ikonomopoulos A., Tsoukalas L. H. and R.E. Uhrig (1992). Use of Neural Networks to Monitor Power Plant Components. Proceedings of the American Power Conference, Chicago, IL., April 13–15, 1992

    Google Scholar 

  • Kim K., Aljundi T.L. and E. Bartlett (1992). Confirmation of Artificial Neural Networks: Nuclear Power Plant Fault Diagnostics. Transactions of the American Nuclear Society, 66, Chicago, IL, November 15–20.

    Google Scholar 

  • Kim H.K., Lee S.H. and S.H. Chang (1992). Neural Network Model for On–Line Thermal Margin Estimation of a Nuclear Power Plant. Proceedings of the Second International Forum, Expert Systems and Computer Simulation in Energy Engineering, Erlangen, Germany, March 17–20, pp 7–2–1 to 7–2–6.

    Google Scholar 

  • Kohonen T. (1984). Self-organisation and associative memory. Springer-Verlag, Berlin.

    Google Scholar 

  • Konstantopoulos I.K. and P.J. Antsaklis (1993). The four parameter controller: A neural network implementation. Proceedings, IEEE Meditteranean Symposium on New Directions in Control Theory and Applications, Chania, Greece, June 21–23.

    Google Scholar 

  • Kosko B. (1990). Unsupervised learning in noise. IEEE Transactions on Neural Networks, 1, 1, 44–57.

    Article  Google Scholar 

  • Kosmatopoulos E. B., Ioannou P. A. and M.A. Christodoulou (1992). Identification of Nonlinear Systems Using New Dynamic Neural Network Structures. Proceedings, 31st IEEE Conference on Decision and Control, Tucson, Arizona, USA, December 16–18.

    Google Scholar 

  • Kosmatopoulos E. B., Christodoulou M. A. and P.A. Ioannou (1993). Learning laws that ensure exponential error convergence. Proceedings, 32nd IEEE Conference on Decision and Control, San Antonio, Texas, USA, December 15–17.

    Google Scholar 

  • Kusiak A. and G. Finke (1988). Selection of process plans in automated manufacturing systems. IEEE Transactions of Robotics and Automation, 4, 4.

    Google Scholar 

  • Lippmann R.P. (1987). An introduction to computing with neural nets. IEEE ASP Magazine, 4, 4–22.

    Article  Google Scholar 

  • Lo A. and B. Bavarian (1991). Scheduling with neural networks for flexible manufacturing systems. Proceedings, IEEE International Conference on Robotics and Automation, 818–823.

    Google Scholar 

  • Mirchandani G. and W. Cao (1989). On hidden nodes for neural nets. IEEE Transactions on Circuits and Systems, 36, 661–664.

    Article  MathSciNet  Google Scholar 

  • Moon Y.B. (1990). Forming part-machine families for cellular manufacturing: A neural-network approach. Internatioanl Journal of Advanced Manufacturing Technology, 5, 278–291.

    Article  Google Scholar 

  • Matsumoto K. and T. Sakaguchi (1983). Methods to determine the restoration plan of power system by a knowledge based system. Transactions, IEE of Japan, 103 B, 3.

    Google Scholar 

  • de Mello L. S. H. and A.C. Sanderson (1990). AND/OR Graph representation of assembly plans. IEEE Transactions on Robotics and Automation, 6, 2, 188–199.

    Article  Google Scholar 

  • Miguel L.J., Baeyens E. and J.L. Coronado (1993). Application of an ART-3 based neural network to fault diagnosis in dynamic systems. Proceedings, International Conference on Fault Diagnosis TOOLDIAG ‘83, Toulouse, France, April 5–7, 713–717.

    Google Scholar 

  • Minsky M. and Papert S. (1969). Perceptrons - An introduction to computational geometry. MIT Press, Cambridge, Mass.

    MATH  Google Scholar 

  • Naidu R.S., Zafiriou E. and T.J. McAvoy (1990). Use of neural networks for sensor failure detection in a control system. IEEE Control Systems Magazine, 10, 49–55.

    Article  Google Scholar 

  • Nett C.N., Jacobson C.A. and A.T. Miller (1988). An integrated approach to controls and diagnostics: the 4-parameter controller. Proceedings, 1988 American Control Conference, 824–835.

    Google Scholar 

  • Ogi H., Tanaka H. and Y. Akimoto (1991). Module neural network application for power system/equipment diagnosis. Proceedings of ESAP ‘81, April, 1991.

    Google Scholar 

  • Ohga Y. and H. Seki (1991). Using a Neural Network for Abnormal Event Identification in BWRs. Transactions of the American Nuclear Society, 63, 110–111.

    Google Scholar 

  • Pao Y. (1989). Adaptive pattern recognition and neural networks. Addison Wesley, N.Y.

    Google Scholar 

  • Passino K.M., Sartori M.A. and P.J. Antsaklis (1989). Neural computing for numericto-symbolic conversion in control systems. IEEE Control Systems Magazine, 9, 44–52.

    Article  Google Scholar 

  • Peng Y. and J.A. Reggia (1989). A connectionist model for diagnostic problem solving. IEEE Transactions on Systems, Man and Cybernetics, 19, 2, 285–298.

    Article  MathSciNet  Google Scholar 

  • Polycarpou M. M. and P.A. Ioannou (1992). Neural Networks as On-Line Approximators of Nonlinear Systems. Proceedings, 31st IEEE Conference on Decision and Control, Tucson, Arizona, USA, December 16–18.

    Google Scholar 

  • Rauch H.E., Kline-Schoder R.J., Adams J.C. and H.M. Youssef (1993). Fault detection, isolation and reconfiguration for aircraft using neural networks. Proceedings, AIAA Conference on Guidance, Navigation and Control, August ‘83.

    Google Scholar 

  • Rauch H.E. and D.B. Schaechter (1992). Neural networks for control, identification and diagnosis. Proceedings, World Space Congress, Washington, D.C., August 28-September 5.

    Google Scholar 

  • Ray A.K. (1991). Equipment fault diagnosis–A neural network approach. Computers in Industry, 16, 169–177.

    Article  Google Scholar 

  • Reed N.E. et al. (1988). Specialized Strategies: An alternative to first principles in diagnostic problem solving. AAAI, 364–368.

    Google Scholar 

  • Roh M. S., Cheon S.W., Kim H.G. and S.H. Chang (1992). Prediction of Nuclear Reactor Parameters using Artificial Neural Network Models. Proceedings of the 2nd International Forum on “Expert Systems and Computer Simulation in Energy Engineering”, Erlangen, Germany, March 17–20.

    Google Scholar 

  • Rummelhart D.E. and J.L. McClelland (1986). Parallel Distributed Processing - Explorations in the microstructure of cognition, Volume 1: Foundations. MIT Press, Cambridge, Mass.

    Google Scholar 

  • Rummelhart D.E. and J.L. McClelland (1986). Parallel Distributed Processing - Explorations in the microstructure of cognition, Volume 2: Psychological and biological models. MIT Press, Cambridge, Mass.

    Google Scholar 

  • Schutte P. et al. (1987). An evaluation of a real-time fault diagnosis expert system for aircraft applications. Proceedings, 26th IEEE Conference on Decision and Control.

    Google Scholar 

  • Sorsa T. and H.N. Koivo (1991). Applications of artificial neural networks in process fault diagnosis. Proceedings, IFAC Fault Detection, Supervision and Safety for Technical Processes, Baden-Baden, Germany, September 10–13.

    Google Scholar 

  • Sorsa T., Koivo H.N. and H. Koivisto (1991). Neural networks in process fault diagnosis. IEEE Transactions on Systems, Man and Cybernetics, 21, 4, 815–825

    Article  Google Scholar 

  • Sorsa T., Suontausta J. and H.N. Koivo (1993). Dynamic fault diagnosis using radial basis function networks. Proceedings, International Conference on Fault Diagnosis TOOLDIAG ‘83, Toulouse, France, April 5–7, 160–169.

    Google Scholar 

  • Stavrakakis G.S. and E.N. Dialynas (1991). Efficient computer-based scheme for improving the reliability performance of power substations. International Journal of Systems Science, 22, 9, 1527–1539.

    Article  Google Scholar 

  • Suna R. and K. Berns (1993). Pipeline diagnosis using backpropagation networks. Proceedings, of Sixth International Confernece on Neural networks and other industrial and cognitive applications, Nimes, France, October 25–29.

    Google Scholar 

  • Syed A., El-Maraghy H.A. and N. Chagneux. Application of Kohonen maps in real-time monitoring and diagnosing of robotic assembly. Proceedings, International Conference on Fault Diagnosis TOOLDIAG ‘83, Toulouse, France, April 5–7, 780–786.

    Google Scholar 

  • Tinghu Y., Binglin Z. and H. Ren (1993). A neural network methodology for rotating machinery fault diagnosis. Proceedings, International Conference on Fault Diagnosis TOOLDIAG ‘83, Toulouse, France, April 5–7, 170–178.

    Google Scholar 

  • Tsoukalas L. H., Ikonomopoulos A. and R.E. Uhrig (1991). Hybrid Expert System-Neural Network Methodology for Transient Identification. Proceedings of the American Power Conference, Chicago, IL, April 29-May 1.

    Google Scholar 

  • Wake T. and T. Sakaguchi (1984). Method to determine the fault components of power system based on description of structure and function of relay system. Transactions, IEE of Japan, 101 B, 10.

    Google Scholar 

  • Wasserman P.D. (1989). Neural Computing: Theory and Practice. Van Nostrand Reinhold, N.Y.

    Google Scholar 

  • Widrow B. and M.A. Lehr (1990). 30 years of adaptive neural networks: Perceptron, Madaline and Back-propagation. Proceedings of the IEEE, 78, 9.

    Google Scholar 

  • Upadhyaya B. R. and E. Eryurek (1992). Application of Neural Networks for Sensor Validation and Plant Monitoring. Nuclear Technology, 97, p 170.

    Google Scholar 

  • Vaidyanathan R. and V. Venkatasubramanian (1990). Process fault detection and diagnosis using neural networks: Dynamic processes. Proceedings, AIChE Annual National Meeting, Chicago, U.S.A.

    Google Scholar 

  • Venkatasubramanian V. and K. Chan (1989). A neural network methodology for process fault diagnosis. AIChE Journal, 35, 1993–2002.

    Article  Google Scholar 

  • Watanabe K., Matsuura I., Abe M., Kubota M. and D.M. Himmelblau (1989). Incipient fault diagnosis of chemical processes via artificial neural networks. AIChE Journal, 35, 1803–1812.

    Article  Google Scholar 

  • Widrow B. and M.E. Hoff (1960). Adaptive switching circuits. 1960 IRE WESCON Cony. Record, Part 4, August 1960, 96–104.

    Google Scholar 

  • Widrow B. and R. Winter (1988). Neural nets for adaptive filtering and adaptive pattern recognition. IEEE Computer Magazine, March, 25–39.

    Google Scholar 

  • Yamashina H., Kumamoto H., Okumura S. and T. Ikesaki (1990). Failure diagnosis of a servovalve by neural networks with new learning algorithm and structure analysis. International Journal of Production Research, 28, 6, 1009–1021.

    Article  Google Scholar 

  • Zeilingold D. and J. Hoey (1990). Model for a space shuttle safing and failure detection expert system. Proceedings, 5th Conference on Artificial Intelligence for Space Applications.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Production Engineering and Management, Technical University of Crete, Chania, Greece

    A. D. Pouliezos

  2. Electronic Engineering and Computer Science Department, Technical University of Crete, Chania, Greece

    G. S. Stavrakakis

Authors
  1. A. D. Pouliezos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. G. S. Stavrakakis
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

Copyright information

© 1994 Springer Science+Business Media Dordrecht

About this chapter

Cite this chapter

Pouliezos, A.D., Stavrakakis, G.S. (1994). Fault Diagnosis Using Artificial Neural Networks (ANNs). In: Real Time Fault Monitoring of Industrial Processes. International Series on Microprocessor-Based and Intelligent Systems Engineering, vol 12. Springer, Dordrecht. https://doi.org/10.1007/978-94-015-8300-8_5

Download citation

  • DOI: https://doi.org/10.1007/978-94-015-8300-8_5

  • Publisher Name: Springer, Dordrecht

  • Print ISBN: 978-90-481-4374-0

  • Online ISBN: 978-94-015-8300-8

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation