Skip to main content
SpringerLink
Log in
Book cover

International Conference on Automation

ICA 2016: Challenges in Automation, Robotics and Measurement Techniques pp 165–175Cite as

Two- and Three-Layer Recurrent Elman Neural Networks as Models of Dynamic Processes

  • Conference paper
  • First Online:

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 440))

Abstract

The goal of paper is to study and compare the effectiveness of two- and three-layer Elman recurrent neural networks used for modelling of dynamic processes. Training of such networks is discussed. For a neutralisation reactor benchmark system it is shown that the rudimentary Elman structure with two layers is much better in terms of accuracy and the number of parameters. Furthermore, its training is much easier.

This is a preview of subscription content, 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 EPUB and 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

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

References

  1. Elman, J.L.: Finding structure in time. Cogn. Sci. 14, 179–211 (1990)

    Article  Google Scholar 

  2. Gómez, J.C., Jutan, A., Baeyens, E.: Wiener model identification and predictive control of a pH neutralisation process. IEEE Proc. Part D Control Theory Appl. 151, 25–35 (2004)

    Google Scholar 

  3. Haykin, S.: Neural Networks-A Comprehensive Foundation. Prentice Hall, Upper Saddle River (2008)

    Google Scholar 

  4. Li, P.: Application of a hybrid quantized Elman neural network in short-term load forecasting. Int. J. Electr. Power Energy Syst. 55, 749–759 (2014)

    Article  Google Scholar 

  5. Li, Q.: Prediction of urban rail transit sectional passenger flow based on Elman neural network. Appl. Mech. Mater. 505–506, 1023–1027 (2014)

    Google Scholar 

  6. Liou, J.-W.: Distributed representation of word by using Elman network. Int. J. Intell. Inf. Database Syst. 7, 373–386 (2013)

    Google Scholar 

  7. Mandic, D.: Recurrent Neural Networks for Prediction. Wiley, Chichester (2001)

    Book  Google Scholar 

  8. Nocedal, J., Wright, S.J.: Numerical Optimization. Springer, New York (2006)

    MATH  Google Scholar 

  9. Osowski, S.: Neural networks for information processing (in Polish). OWPW, Warsaw (2006)

    Google Scholar 

  10. Wang, J.-C.: Elman network based on EPSO-BP and its application in flight trajectory prediction. Control Decis. 28, 1884–1888 (2013)

    Google Scholar 

  11. Wysocki, A.: Efficient training of Elman neural networks (in Polish). In: Malinowski, K., Józefczyk, J., Światek, J. (eds.) Current Problems of Automation and Robotics, pp. 754–764, Exit, Wrocĺaw (2014)

    Google Scholar 

  12. Zhou, C., Ding, L.Y., He, R.: PSO-based Elman neural network model for predictive control of air chamber pressure in slurry shield tunneling under Yangtze river. Autom. Constr. 36, 208–217 (2013)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Control and Computation Engineering, Warsaw University of Technology, ul. Nowowiejska 15/19, 00-665, Warsaw, Poland

    Antoni Wysocki & Maciej Ławryńczuk

Authors
  1. Antoni Wysocki
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Maciej Ławryńczuk
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Antoni Wysocki .

Editor information

Editors and Affiliations

  1. Automation and Measurements PIAP, Industrial Research Institute for, Warsaw, Poland

    Roman Szewczyk

  2. Automation and Measurements PIAP, Industrial Research Institute for, Warsaw, Poland

    Cezary Zieliński

  3. Automation and Measurements PIAP, Industrial Research Institute for, Warsaw, Poland

    Małgorzata Kaliczyńska

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing Switzerland

About this paper

Cite this paper

Wysocki, A., Ławryńczuk, M. (2016). Two- and Three-Layer Recurrent Elman Neural Networks as Models of Dynamic Processes. In: Szewczyk, R., Zieliński, C., Kaliczyńska, M. (eds) Challenges in Automation, Robotics and Measurement Techniques. ICA 2016. Advances in Intelligent Systems and Computing, vol 440. Springer, Cham. https://doi.org/10.1007/978-3-319-29357-8_15

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-29357-8_15

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-29356-1

  • Online ISBN: 978-3-319-29357-8

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation