Skip to main content
SpringerLink
Log in

Nonlinear model predictive control based on hyper chaotic diagonal recurrent neural network

基于超混沌对角递归神经网络的非线性模型预测控制

  • Published:
Journal of Central South University Aims and scope Submit manuscript

Abstract

Nonlinear model predictive controllers (NMPC) can predict the future behavior of the under-controlled system using a nonlinear predictive model. Here, an array of hyper chaotic diagonal recurrent neural network (HCDRNN) was proposed for modeling and predicting the behavior of the under-controller nonlinear system in a moving forward window. In order to improve the convergence of the parameters of the HCDRNN to improve system’s modeling, the extent of chaos is adjusted using a logistic map in the hidden layer. A novel NMPC based on the HCDRNN array (HCDRNN-NMPC) was proposed that the control signal with the help of an improved gradient descent method was obtained. The controller was used to control a continuous stirred tank reactor (CSTR) with hard-nonlinearities and input constraints, in the presence of uncertainties including external disturbance. The results of the simulations show the superior performance of the proposed method in trajectory tracking and disturbance rejection. Parameter convergence and neglectable prediction error of the neural network (NN), guaranteed stability and high tracking performance are the most significant advantages of the proposed scheme.

摘要

非线性模型预测控制器使用非线性预测模型来预测受控制系统的行为。在此, 提出了一个超混 沌对角递归神经网络数组, 用于在前进窗口中建模和预测控制器下非线性系统的行为。为了改善超混 沌对角线递归神经网络参数的收敛性, 以更好地进行系统建模, 可使用隐藏层中的逻辑映像来调整混 沌程度。提出了一种基于超混沌对角递归神经网络的非线性模型预测控制方法。该方法借助改进的梯 度下降法获得控制信号。将该控制器用于控制具有硬非线性。输入约束以及存在包括外部干扰在内的 不确定性的连续搅拌反应器, 仿真结果表明该方法在轨迹跟踪和干扰抑制方面的优越性能。神经网络 的参数收敛和可忽略的预测误差、以及保证的稳定性和较高的跟踪性能是该方案的最大优势。

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. LI Z J, XIAO H, YANG C, et al. Model predictive control of nonholonomic chained systems using general projection neural networks optimization [J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2015, 45(10): 1313–1321.

    Article  Google Scholar 

  2. HOANG T, SAVKIN A V, NGUYEN T N, et al. Decentralised model predictive control with stability constraints and its application in process control [J]. Journal of Process Control, 2015, 26: 73–89. DOI: https://doi.org/10.1016/j.jprocont.2015.01.002.

    Article  Google Scholar 

  3. GRÜNE L, PANNEK J. Nonlinear model predictive control [M]// Nonlinear Model Predictive Control. Cham: Springer International Publishing, 2016: 45–69. DOI: https://doi.org/10.1007/978-3-319-46024-6_3.

    MATH  Google Scholar 

  4. HOSEN M A, HUSSAIN M A, MJALLI F S. Control of polystyrene batch reactors using neural network based model predictive control (NNMPC): An experimental investigation [J]. Control Engineering Practice, 2011, 19(5): 454–467. DOI: https://doi.org/10.1016/j.conengprac.2011.01.007.

    Article  Google Scholar 

  5. ŁAWRYŃCZUK M. On improving accuracy of computationally efficient nonlinear predictive control based on neural models [J]. Chemical Engineering Science, 2011, 66(21): 5253–5267. DOI: https://doi.org/10.1016/j.ces.2011.07.015.

    Article  Google Scholar 

  6. ŁAWRYŃCZUK M. Practical nonlinear predictive control algorithms for neural Wiener models [J]. Journal of Process Control, 2013, 23(5): 696–714. DOI: https://doi.org/10.1016/j.jprocont.2013.02.004.

    Article  Google Scholar 

  7. ZHOU Feng, PENG Hui, QIN Ye-mei, et al. RBF-ARX model-based MPC strategies with application to a water tank system [J]. Journal of Process Control, 2015, 34: 97–116. DOI: https://doi.org/10.1016/j.jprocont.2015.07.010.

    Article  Google Scholar 

  8. ZHOU Feng, PENG Hui, QIN Ye-mei, et al. A RBF-ARX model-based robust MPC for tracking control without steady state knowledge [J]. Journal of Process Control, 2017, 51: 42–54. DOI: https://doi.org/10.1016/j.jprocont.2016.12.008.

    Article  Google Scholar 

  9. ZHOU Feng, PENG Hui, ZENG Xiao-yong, et al. RBF-ARX model-based two-stage scheduling RPC for dynamic systems with bounded disturbance [J]. Neural Computing and Applications, 2019, 31(8): 4185–4200. DOI: https://doi.org/10.1007/s00521-018-3347-y.

    Article  Google Scholar 

  10. PAN Yun-peng, WANG Jun. Model predictive control of unknown nonlinear dynamical systems based on recurrent neural networks [J]. IEEE Transactions on Industrial Electronics, 2012, 59(8): 3089–3101. DOI: https://doi.org/10.1109/TIE.2011.2169636.

    Article  MathSciNet  Google Scholar 

  11. HUANG Xin-jian, CUI Bao-tong. A neural dynamic system for solving convex nonlinear optimization problems with hybrid constraints [J]. Neural Computing and Applications, 2019, 31(10): 6027–6038. DOI: https://doi.org/10.1007/s00521-018-3422-4.

    Article  Google Scholar 

  12. KUMAR R, SRIVASTAVA S, GUPTA J R P. Diagonal recurrent neural network based adaptive control of nonlinear dynamical systems using Lyapunov stability criterion [J]. ISA Transactions, 2017, 67: 407–427. DOI: https://doi.org/10.1016/j.isatra.2017.01.022.

    Article  Google Scholar 

  13. QIAO Jun-fei, MENG Xi, LI Wen-jing. An incremental neuronal-activity-based RBF neural network for nonlinear system modeling [J]. Neurocomputing, 2018, 302: 1–11. DOI: https://doi.org/10.1016/j.neucom.2018.01.001.

    Article  Google Scholar 

  14. CHEN C S. Robust self-organizing neural-fuzzy control with uncertainty observer for MIMO nonlinear systems [J]. IEEE Transactions on Fuzzy Systems, 2011, 19(4): 694–706. DOI: https://doi.org/10.1109/TFUZZ.2011.2136349.

    Article  Google Scholar 

  15. HAN Hong-gui, QIAO Jun-fei. Nonlinear model-predictive control for industrial processes: An application to wastewater treatment process [J]. IEEE Transactions on Industrial Electronics, 2014, 61(4): 1970–1982. DOI: https://doi.org/10.1109/TIE.2013.2266086.

    Article  Google Scholar 

  16. HAN Hong-gui, ZHANG Lu, HOU Ying, et al. Nonlinear model predictive control based on a self-organizing recurrent neural network [J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(2): 402–415. DOI: https://doi.org/10.1109/TNNLS.2015.2465174.

    Article  MathSciNet  Google Scholar 

  17. AIHARA K, TAKABE T, TOYODA M. Chaotic neural networks [J]. Physics Letters A, 1990, 144(6, 7): 333–340. DOI:https://doi.org/10.1016/0375-9601(90)90136-C.

    Article  MathSciNet  Google Scholar 

  18. LI Juan, LIU Feng, GUAN Zhi-hong, et al. A new chaotic Hopfield neural network and its synthesis via parameter switchings [J]. Neurocomputing, 2013, 117: 33–39. DOI: https://doi.org/10.1016/j.neucom.2012.11.022.

    Article  Google Scholar 

  19. MAZROOEI-SEBDANI R, FARJAMI S. RETRACTED: Bifurcations and chaos in a discrete-time-delayed Hopfield neural network with ring structures and different internal decays [J]. Neurocomputing, 2013, 99: 154–162. DOI: https://doi.org/10.1016/j.neucom.2012.06.007.

    Article  Google Scholar 

  20. WANG Li-biao, MENG Zhuo, SUN Yi-ze, et al. Design and analysis of a novel chaotic diagonal recurrent neural network [J]. Communications in Nonlinear Science and Numerical Simulation, 2015, 26(1–3): 11–23. DOI: https://doi.org/10.1016/j.cnsns.2015.01.021.

    Article  MathSciNet  Google Scholar 

  21. TAHERKHANI A, SEYYEDSALEHI S A, MOHAMMADI A. Design of chaotic neural network for robust phoneme recognition [C]// 2008 IEEE International Symposium on Signal Processing and Information Technology. IEEE, 2008: 106–110. DOI: https://doi.org/10.1109/ISSPIT.2008.4775643.

  22. TAHERKHANI A, SEYYEDSALEHI S A, JAFARI A H. Design of a chaotic neural network for training and retrieval of grayscale and binary patterns [J]. Neurocomputing, 2011, 74(17): 2824–2833. DOI: https://doi.org/10.1016/j.neucom.2011.03.037.

    Article  Google Scholar 

  23. SINHA A, MISHRA R K. Temperature regulation in a continuous stirred tank reactor using event triggered sliding mode control [J]. IFAC-Papers OnLine, 2018, 51(1): 401–406. DOI: https://doi.org/10.1016/j.ifacol.2018.05.060.

    Article  Google Scholar 

  24. SALAHSHOUR E, MALEKZADEH M, GORDILLO F, et al. Quantum neural network-based intelligent controller design for CSTR using modified particle swarm optimization algorithm [J]. Transactions of the Institute of Measurement and Control, 2019, 41(2): 392–404. DOI: https://doi.org/10.1177/0142331218764566.

    Article  Google Scholar 

  25. LI Dong-juan, LI Da-peng. Adaptive controller design-based neural networks for output constraint continuous stirred tank reactor [J]. Neurocomputing, 2015, 153: 159–163. DOI: https://doi.org/10.1016/j.neucom.2014.11.041.

    Article  Google Scholar 

  26. PRABHAKER R G, RADHIKA G, ANIL K. Control of continuous stirred tank reactor using artificial neural networks based predictive control [J]. Advanced Materials Research, 2012, 550–553: 2908–2912. DOI: https://doi.org/10.4028/www.scientific.net/amr.550-553.2908.

    Article  Google Scholar 

  27. DEEPA S N, BARANILINGESAN I. Optimized deep learning neural network predictive controller for continuous stirred tank reactor [J]. Computers & Electrical Engineering, 2018, 71: 782–797. DOI: https://doi.org/10.1016/j.compeleceng.2017.07.004.

    Article  Google Scholar 

  28. KU C C, LEE K Y. Diagonal recurrent neural networks for dynamic systems control [J]. IEEE Transactions on Neural Networks, 1995, 6(1): 144–156. DOI: https://doi.org/10.1109/72.363441.

    Article  Google Scholar 

  29. HAN Hong-gui, WU Xiao-long, QIAO Jun-fei. Real-time model predictive control using a self-organizing neural network [J]. IEEE Transactions on Neural Networks and Learning Systems, 2013, 24(9): 1425–1436. DOI: https://doi.org/10.1109/TNNLS.2013.2261574.

    Article  Google Scholar 

  30. SHRIVASTAVA P. Modeling and control of CSTR using model based neural network predictive control [J]. International Journal of Computer Science & Information, 2012. arXiv:1208.3600.

Download references

Author information

Authors and Affiliations

  1. Department of Control, Mashhad Branch, Islamic Azad University, Mashhad, 9187147578, Iran

    Samira Johari & Mahdi Yaghoobi

  2. Department of Biomedical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, 9187147578, Iran

    Hamid R. Kobravi

Authors
  1. Samira Johari
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mahdi Yaghoobi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hamid R. Kobravi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mahdi Yaghoobi.

Additional information

Contributors

All authors including Samira Johari, Mahdi Yaghoobi, and Hamid Reza Kobravi contributed equally in developing the main idea of the research, writing the initial draft of manuscript, replying to the reviewe’s comments and revising the final version.

Conflict of interest

Samira Johari, Mahdi Yaghoobi, and Hamid Reza Kobravi declare that they have no conflict of interest.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Johari, S., Yaghoobi, M. & Kobravi, H.R. Nonlinear model predictive control based on hyper chaotic diagonal recurrent neural network. J. Cent. South Univ. 29, 197–208 (2022). https://doi.org/10.1007/s11771-022-4915-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11771-022-4915-y

Key words

关键词

Search

Navigation