Skip to main content
SpringerLink
Log in

Optimizing the double inverted pendulum’s performance via the uniform neuro multiobjective genetic algorithm

  • Research Article
  • Published:
International Journal of Automation and Computing Aims and scope Submit manuscript

Abstract

An inverted pendulum is a sensitive system of highly coupled parameters, in laboratories, it is popular for modelling nonlinear systems such as mechanisms and control systems, and also for optimizing programmes before those programmes are applied in real situations. This study aims to find the optimum input setting for a double inverted pendulum (DIP), which requires an appropriate input to be able to stand and to achieve robust stability even when the system model is unknown. Such a DIP input could be widely applied in engineering fields for optimizing unknown systems with a limited budget. Previous studies have used various mathematical approaches to optimize settings for DIP, then have designed control algorithms or physical mathematical models. This study did not adopt a mathematical approach for the DIP controller because our DIP has five input parameters within its nondeterministic system model. This paper proposes a novel algorithm, named UniNeuro, that integrates neural networks (NNs) and a uniform design (UD) in a model formed by input and response to the experimental data (metamodel). We employed a hybrid UD multiobjective genetic algorithm (HUDMOGA) for obtaining the optimized setting input parameters. The UD was also embedded in the HUDMOGA for enriching the solution set, whereas each chromosome used for crossover, mutation, and generation of the UD was determined through a selection procedure and derived individually. Subsequently, we combined the Euclidean distance and Pareto front to improve the performance of the algorithm. Finally, DIP equipment was used to confirm the settings. The proposed algorithm can produce 9 alternative configured input parameter values to swing-up then standing in robust stability of the DIP from only 25 training data items and 20 optimized simulation results. In comparison to the full factorial design, this design can save considerable experiment time because the metamodel can be formed by only 25 experiments using the UD. Furthermore, the proposed algorithm can be applied to nonlinear systems with multiple constraints.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. A. Shukla, H. Karki. Application of robotics in onshore oil and gas industry-a review Part I. Robotics and Autonomous Systems, vol. 75, pp. 490–507, 2016.

    Article  Google Scholar 

  2. J. A. Anderson. An Introduction to Neural Networks, Cambridge, Mass, UK: MIT Press, 1995.

    MATH  Google Scholar 

  3. P. P. Palmes, S. Usui. Robustness, evolvability, and optimality of evolutionary neural networks. Biosystems, vol. 82, no. 2, pp. 168–188, 2005.

    Article  Google Scholar 

  4. A. Medio, M. Lines. Nonlinear Dynamics: A Primer, Cambridge, UK: Cambridge University Press, 2001.

    Book  MATH  Google Scholar 

  5. T. K. Liu, C. H. Chen, Z. S. Li, J. H. Chou. Method of inequalities-based multiobjective genetic algorithm for optimizing a cart-double-pendulum system. International Journal of Automation and Computing, vol. 6, no. 1, pp. 29–37, 2009.

    Article  Google Scholar 

  6. T. K. Liu, Y. C. Shen, Z. S. Li. An application of multiobjective optimization genetic algorithm for cart-doublependulum- system control. In Proceedings of IEEE International Conference on Systems, Man and Cybernetics, IEEE, Taipei, China, pp. 3292–3297, 2006.

    Google Scholar 

  7. L. B. Prasad, B. Tyagi, H. O. Gupta. Optimal control of nonlinear inverted pendulum system using PID controller and LQR: Performance analysis without and with disturbance input. International Journal of Automation and Computing, vol. 11, no. 6, pp. 661–670, 2014.

    Article  Google Scholar 

  8. F. Gazdos. Introducing a new tool for studying unstable systems. International Journal of Automation and Computing, vol. 11, no. 6, pp. 580–587, 2014.

    Article  Google Scholar 

  9. C. J. Ding, P. Duan, M. L. Zhang, Y. F. Zhang. Double inverted pendulum system control strategy based on fuzzy genetic algorithm. In Proceedings of IEEE International Conference on Automation and Logistics, IEEE, Shenyang, China, pp. 1318–1323, 2009.

    Google Scholar 

  10. M. Nalavade, M. J. Bhagat, V. V. Patil. Balancing double inverted pendulum on cart by linearization technique. In Proceedings of International Journal of Recent Technology and Engineering, ISSN, pp. 2277–3878, 2014.

    Google Scholar 

  11. M. J. Mahmoodabadi, S. A. Mostaghim, A. Bagheri, N. Nariman-Zadeh. Pareto optimal design of the decoupled sliding mode controller for an inverted pendulum system and its stability simulation via Java programming. Mathematical and Computer Modelling, vol. 57, no. 5–6, pp. 1070–1082, 2013.

    Article  MathSciNet  Google Scholar 

  12. Z. W. Ping, J. Huang. Approximate output regulation of spherical inverted pendulum by neural network control. Neurocomputing, vol. 85, pp. 38–44, 2012.

    Article  Google Scholar 

  13. Z. W. Ping. Tracking problems of a spherical inverted pendulum via neural network enhanced design. Neurocomputing, vol. 106, pp. 137–147, 2013.

    Article  Google Scholar 

  14. K. U. P. Lakshmi. Design of robust energy control for cartinverted pendulum. International Journal of Engineering and Technology, vol. 4, no. 1, pp. 66–76, 2007.

    Google Scholar 

  15. D. C. Montgomery. Design and Analysis of Experiments, 7th ed., Hoboken, USA: John Wiley and Sons, 2009.

    Google Scholar 

  16. K. Yang, B. S. El-Haik. Design for Six Sigma, New York, USA: McGraw Hill, 2003.

    Google Scholar 

  17. K. T. Fang, R. Z. Li, A. Sudjianto. Design and Modeling for Computer Experiments, Boca Raton, USA: CRC Press, 2005.

    Book  MATH  Google Scholar 

  18. K. T. Fang, D. K. J. Lin. Uniform experimental designs and their applications in industry. Handbook of Statistics, vol. 22, pp. 131–170, 2003.

    Article  MathSciNet  Google Scholar 

  19. G. Dreyfus. Neural Networks: Methodology and Applications, Heidelberg, Germany: Springer, 2005.

    MATH  Google Scholar 

  20. D. H. Al-Janan, T. K. Liu. Path optimization of CNC PCB drilling using hybrid Taguchi genetic algorithm. Kybernetes, vol. 45, no. 1, pp. 107–125, 2016.

    Article  Google Scholar 

  21. T. K. Liu, T. Ishihara. Multi-objective genetic algorithms for the method of inequalities. Control Systems Design, V. Zakian, Ed., London, UK: Springer, pp. 231–248, 2005.

    Chapter  Google Scholar 

  22. A. Konak, D. W. Coit, A. E. Smith. Multi-objective optimization using genetic algorithms: A tutorial. Reliability Engineering & System Safety, vol. 91, no. 9, pp. 992–1007, 2006.

    Article  Google Scholar 

  23. X. Q. Li, D. Wang, Z. M. Fu. Adaptive NN dynamic surface control for a class of uncertain non-affine pure-feedback systems with unknown time-delay. International Journal of Automation and Computing, vol. 13, no. 3, pp. 268–276, 2016.

    Article  Google Scholar 

  24. X. J. Wu, X. L. Wu, X. Y. Luo. Adaptive neural network dynamic surface control for a class of nonlinear systems with uncertain time delays. International Journal of Automation and Computing, vol. 13, no. 4, pp. 409–416, 2016.

    Article  Google Scholar 

  25. K. Owa, S. Sharma, R. Sutton. A wavelet neural network based non-linear model predictive controller for a multivariable coupled tank system. International Journal of Automation and Computing, vol. 12, no. 2, pp. 156–170, 2015.

    Article  Google Scholar 

  26. W. Y. Fowlkes, C. M. Creveling. Engineering Methods for Robust Product Design, Reading, Mass, USA: Addison-Wesley, 1995.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Engineering Science and Technology, National Kaohsiung First University of Science and Technology, Taiwan, China

    Dony Hidayat Al-Janan, Hao-Chin Chang, Yeh-Peng Chen & Tung-Kuan Liu

  2. Mechanical Engineering Departement, Engineeering Faculty, Semarang State University, Semarang, Center of Java, Indonesia

    Dony Hidayat Al-Janan

Authors
  1. Dony Hidayat Al-Janan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hao-Chin Chang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yeh-Peng Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tung-Kuan Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tung-Kuan Liu.

Additional information

This work was supported by Indonesian Government (No. BPPLN DIKTI 3+1).

Recommended by Associate Editor Veljko Potkonjak

Dony Hidayat Al-Janan received the B. Sc. degree in mechanical engineering from the Muhammadiyah University of Surakarta, Indonesia in 2001, received the M. Sc. degree in mechanical engineering from Gadjahmada University, Indonesia in 2004. From 2006 to 2013, he has been also a lecturer of Computer Programming of Engineering Faculty, Semarang State University. Since 2013, he is the Ph.D. degree candidate at Institute of Engineering Science and Technology, National Kaohsiung First University of Science and Technology, Taiwan, China, supported by Indonesian Directorate General of Higher Education (DIKTI) scholarship in scheme BPPLN DIKTI 3+1.

His research interests include developing a metamodel and system optimization design.

Hao-Chin Chang received the B. Sc. and M. Sc. degrees in marine engineering from National Kaohsiung Marine University, Taiwan, China in 2009 and 2011, respectively. He received Ph.D. degree from the Institute of Engineering Science and Technology, National Kaohsiung First University of Science and Technology, Taiwan, China in 2015.

His research interests include artificial intelligence and applications of multiobjective optimization genetic algorithms.

Yeh-Peng Chen received the B. Sc. degree in information engineering from I-Shou University, Taiwan, China in 1996, and the M. Sc. and Ph.D. degrees in information management science and engineering science and technology from the National Kaohsiung First University of Science and Technology, Taiwan, China in 2003 and 2015, respectively.

His research interests include artificial intelligence, applications of multiobjective optimization genetic algorithms, power systems, and data mining.

Tung-Kuan Liu received the B. Sc. degree in mechanical engineering from the National Akita University, Japan in 1992, and the M. Sc. and Ph.D. degrees in mechanical engineering and information science from the National Tohoku University, Japan in 1994 and 1997, respectively. He is a professor in Department of Mechanical and Automation Engineering and Graduate Program of Industrial Design, National Kaohsiung First University of Science and Technology, Taiwan, China since February 2011. During October 1997 to July 1999, he was a senior manager with the Institute of Information Industry, Taiwan, China. From August 1999 to July 2002, he was also an assistant professor with the Department of Marketing and Distribution Management, National Kaohsiung First University of Science and Technology, Taiwan, China.

His research and teaching interests include artificial intelligence, applications of multi objective optimization genetic algorithms, and integrated manufacturing and business systems.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Al-Janan, D.H., Chang, HC., Chen, YP. et al. Optimizing the double inverted pendulum’s performance via the uniform neuro multiobjective genetic algorithm. Int. J. Autom. Comput. 14, 686–695 (2017). https://doi.org/10.1007/s11633-017-1069-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11633-017-1069-8

Keywords

Search

Navigation