Advertisement

Level Identification in Coupled Tanks Using Extreme Learning Machine

  • Alanio Ferreira de Lima
  • Gabriel F. Machado
  • Darielson A. SouzaEmail author
  • Francisco H. V. da Silva
  • Josias G. Batista
  • José N. N. Júnior
  • Deivid M. de Freitas
Conference paper
  • 304 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1160)

Abstract

This paper presents a study on the use of intelligent algorithms in the identification of nonlinear plant systems. The method of applied is an Artificial Neural Network (ANN) called Extreme Learning Machine (ELM), its choice for this work was because of its simplicity and high computational power. The nonlinear plant used is a bench of two coupled tanks. Several types of ELM ANN architectures have been tested. The architectures are all compared to each other using the adjusted R2 metric, it will faithfully evaluate the model approach including the number of neurons used in each ELM ANN architecture.

Keywords

Systems identification Coupled tanks Artificial Neural Network Extreme Learning Machine 

Notes

Acknowledgment

The authors thank the IFCE (Federal Institute of Ceará-Fortaleza) and SENAI, for providing the experimental bench for the article.

References

  1. 1.
    da Silva, P.R.A., de Souza, A.V., Henriques, L.F., Coelho, P.H.G.: Controle De Nível Em Tanques Acoplados Usando Sistemas Inteligentes. I Simpósio Brasileiro de Inteligência Computacional (2007)Google Scholar
  2. 2.
    Haykin, S.: Neural Networks: Principios and Pratice (2001)Google Scholar
  3. 3.
    Souza, D.A., Reis, L.L.N., Batista, J.G., Costa, J.R., Antonio Jr., B.S., Araújo, J.P.B., Braga, A.P.S.: Nonlinear identification of a robotic arm using machine learning techniques. In: Rocha, Á., Adeli, H., Reis, L., Costanzo, S. (eds.) New Knowledge in Information Systems and Technologies. WorldCIST 2019. Advances in Intelligent Systems and Computing, vol. 931. Springer, Cham (2019)CrossRefGoogle Scholar
  4. 4.
    Yu, Z.: Research on intelligent fuzzy control algorithm for moving path of handling robot. In: International Conference on Robots & Intelligent System (ICRIS) (2019)Google Scholar
  5. 5.
    Mekhilef, S., Saymbetov, A., Nurgaliyev, M., Meiirkhanov, A., Dosymbetova, G., Kopzhan, Z.: An automated intelligent solar tracking control system with adaptive algorithm for different weather conditions. In: IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS) (2019)Google Scholar
  6. 6.
    Mastacan, L., Dosoftei, C.-C.: Temperature intelligent control based on soft computing technology. In: International Conference and Exposition on Electrical and Power Engineering (EPE) (2016)Google Scholar
  7. 7.
    Shamily, S., Praveena, Bhuvaneswari, N.S.: Intelligent control and adaptive control for interacting system. In: IEEE Technological Innovation in ICT for Agriculture and Rural Development (TIAR) (2015)Google Scholar
  8. 8.
    Huang, G.-B., Zhu, Q.-Y., Siew, C.-K.: Extreme learning machine: theory and applications. Neurocomputing 70, 489–501 (2006)CrossRefGoogle Scholar

Copyright information

© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Alanio Ferreira de Lima
    • 1
  • Gabriel F. Machado
    • 2
  • Darielson A. Souza
    • 2
    Email author
  • Francisco H. V. da Silva
    • 3
  • Josias G. Batista
    • 2
    • 4
  • José N. N. Júnior
    • 2
  • Deivid M. de Freitas
    • 2
  1. 1.Federal University of Ceará-UFC, Campus SobralSobralBrazil
  2. 2.Federal University of Ceará-UFC, Campus PiciFortalezaBrazil
  3. 3.National Industrial Learning Service - SENAIFortalezaBrazil
  4. 4.Federal Institute of Education, Science and Technology of Ceará-IFCEFortalezaBrazil

Personalised recommendations