Skip to main content
SpringerLink
Log in

Adaptive feedforward RBF neural network control with the deterministic persistence of excitation

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Based on the partial persistence of excitation (PE), the recent deterministic learning theory of adaptive RBF neural network (RBFNN) control can just guarantee that the partial weights of RBFNNs converge to their optimal values. This paper proposes two kinds of adaptive feedforward RBFNN control frameworks with a more deterministic learning mechanism: the reduced lattice scheme and the optimized scheme. Specifically, the RBFNNs satisfy a standard PE condition and the PE levels are deterministic. The reduced lattice scheme removes the insignificant hidden nodes from the lattice scheme, whereas the optimized scheme calculates the distribution of hidden nodes to optimally distribute along the desired trajectory by the K-means algorithm. Under the proposed method, the weights of all the hidden nodes converge to their optimal values, while a deeper insight on the convergence rate of the weights of the RBFNN is drawn. Comparative simulation experiments demonstrate that the optimized scheme outperforms both the reduced lattice scheme and the traditional lattice scheme from the perspectives of both the approximate performance and the PE level. Furthermore, when the sampling frequency is low, both the optimized and reduced lattice schemes achieve better tracking performance than the model-based scheme.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Liu A, Zhao H, Song T, Liu Z, Wang H, Sun D (2021) Adaptive control of manipulator based on neural network. Neural Comput Appl 33(9):4077–4085. https://doi.org/10.1007/s00521-020-05515-0

    Article  Google Scholar 

  2. Montoya-Cháirez J, Rossomando FG, Carelli R, Santibáñez V, Moreno-Valenzuela J (2021) Adaptive RBF neural network-based control of an underactuated control moment gyroscope. Neural Comput Appl 33(12):6805–6818. https://doi.org/10.1007/s00521-020-05456-8

    Article  Google Scholar 

  3. Tang Z, Ge SS, Tee KP, He W (2016) Robust adaptive neural tracking control for a class of perturbed uncertain nonlinear systems with state constraints. IEEE Trans Syst Man Cybern Syst 46(12):1618–1629. https://doi.org/10.1109/TSMC.2015.2508962

    Article  Google Scholar 

  4. He S, Fang H, Zhang M, Liu F, Luan X, Ding Z (2019) Online policy iterative-based H\(\infty\) optimization algorithm for a class of nonlinear systems. Inf Sci 495:1–13. https://doi.org/10.1016/j.ins.2019.04.027

    Article  MathSciNet  MATH  Google Scholar 

  5. Ren C, He S (2020) Finite-time stabilization for positive markovian jumping neural networks. Appl Math Comput 365:124631. https://doi.org/10.1016/j.amc.2019.124631

    Article  MathSciNet  MATH  Google Scholar 

  6. Ge SS, Hang CC, Lee TH, Zhang T (2001) Stable adaptive neural network control. Kluwer, Norwell, MA

    MATH  Google Scholar 

  7. Wang C, Hill DJ (2006) Learning from neural control. IEEE Trans Neural Netw 17(1):130–146. https://doi.org/10.1109/TNN.2005.860843

    Article  Google Scholar 

  8. Zhang JJ (2019) State observer-based adaptive neural dynamic surface control for a class of uncertain nonlinear systems with input saturation using disturbance observer. Neural Comput Appl 31(9):4993–5004. https://doi.org/10.1007/s00521-018-03993-x

    Article  Google Scholar 

  9. Peng J, Ding S, Dubay R (2021) Adaptive composite neural network disturbance observer-based dynamic surface control for electrically driven robotic manipulators. Neural Comput Appl 33(11):6197–6211. https://doi.org/10.1007/s00521-020-05391-8

    Article  Google Scholar 

  10. He W, Sun Y, Yan Z, Yang C, Li Z, Kaynak O (2020) Disturbance observer-based neural network control of cooperative multiple manipulators with input saturation. IEEE Trans Neural Netw Learn Syst 31(5):1735–1746. https://doi.org/10.1109/TNNLS.2019.2923241

    Article  MathSciNet  Google Scholar 

  11. Yang C, Chen C, He W, Cui R, Li Z (2019) Robot learning system based on adaptive neural control and dynamic movement primitives. IEEE Trans Neural Netw Learn Syst 30(3):777–787. https://doi.org/10.1109/TNNLS.2018.2852711

    Article  MathSciNet  Google Scholar 

  12. Zhou Q, Shi P, Tian Y, Wang M (2015) Approximation-based adaptive tracking control for MIMO nonlinear systems with input saturation. IEEE Trans Cybern 45(10):2119–2128. https://doi.org/10.1109/TCYB.2014.2365778

    Article  Google Scholar 

  13. Wang M, Wang C (2015) Learning from adaptive neural dynamic surface control of strict-feedback systems. IEEE Trans Neural Netw Learn Syst 26(6):1247–1259. https://doi.org/10.1109/TNNLS.2014.2335749

    Article  MathSciNet  Google Scholar 

  14. Zheng T, Wang C (2017) Relationship between persistent excitation levels and RBF network structures, with application to performance analysis of deterministic learning. IEEE Trans Cybern 47(10):3380–3392. https://doi.org/10.1109/TCYB.2017.2710284

    Article  Google Scholar 

  15. Chen T, Hill DJ, Wang C (2020) Distributed fast fault diagnosis for multimachine power systems via deterministic learning. IEEE Trans Ind Electron 67(5):4152–4162. https://doi.org/10.1109/TIE.2019.2917367

    Article  Google Scholar 

  16. Pan Y, Yu H (2016) Biomimetic hybrid feedback feedforward neural-network learning control. IEEE Trans Neural Netw Learn Syst 28(6):1481–1487. https://doi.org/10.1109/TNNLS.2016.2527501

    Article  MathSciNet  Google Scholar 

  17. Ren X, Lewis FL, Zhang J (2009) Neural network compensation control for mechanical systems with disturbances. Automatica 45(5):1221–1226. https://doi.org/10.1016/j.automatica.2008.12.009

    Article  MathSciNet  MATH  Google Scholar 

  18. He S, Fang H, Zhang M, Liu F, Ding Z (2019) Adaptive optimal control for a class of nonlinear systems: the online policy iteration approach. IEEE Trans Neural Netw Learn Syst 31(2):549–558. https://doi.org/10.1109/TNNLS.2019.2905715

    Article  MathSciNet  Google Scholar 

  19. Sun Y, Xu J, Lin G, Sun N (2021) Adaptive neural network control for maglev vehicle systems with time-varying mass and external disturbance. Neural Comput Appl. https://doi.org/10.1007/s00521-021-05874-2

    Article  Google Scholar 

  20. Xi X, Liu T, Zhao J, Yan L (2020) Output feedback fault-tolerant control for a class of nonlinear systems via dynamic gain and neural network. Neural Comput Appl 32(10):5517–5530. https://doi.org/10.1007/s00521-019-04583-1

    Article  Google Scholar 

  21. Zhang F, Wang C (2020) Deterministic learning from neural control for uncertain nonlinear pure-feedback systems by output feedback. Int J Robust Nonlinear Control 30(7):2701–2718. https://doi.org/10.1002/rnc.4902

    Article  MathSciNet  MATH  Google Scholar 

  22. Wang S, Na J (2020) Parameter estimation and adaptive control for servo mechanisms with friction compensation. IEEE Trans Industr Inform 16(11):6816–6825. https://doi.org/10.1109/TII.2020.2971056

    Article  Google Scholar 

  23. Peng G, Chen CLP, He W, Yang C (2021) Neural-learning-based force sensorless admittance control for robots with input deadzone. IEEE Trans Ind Electron 68(6):5184–5196. https://doi.org/10.1109/TIE.2020.2991929

    Article  Google Scholar 

  24. Liu Q, Li D, Ge SS, Ji R, Ouyang Z, Tee KP (2021) Adaptive bias RBF neural network control for a robotic manipulator. Neurocomputing 447:213–223. https://doi.org/10.1016/j.neucom.2021.03.033

    Article  Google Scholar 

  25. Chen W, Jiao L, Wu J (2012) Globally stable adaptive robust tracking control using rbf neural networks as feedforward compensators. Neural Comput Appl 21(2):351–363. https://doi.org/10.1007/s00521-010-0455-8

    Article  Google Scholar 

  26. Slotine JE, Li W (1989) Composite adaptive control of robot manipulators. Automatica 25(4):509–519. https://doi.org/10.1016/0005-1098(89)90094-0

    Article  MathSciNet  MATH  Google Scholar 

  27. Tee KP, Ge SS, Tay EH (2009) Barrier Lyapunov functions for the control of output-constrained nonlinear systems. Automatica 45(4):918–927. https://doi.org/10.1016/j.automatica.2008.11.017

    Article  MathSciNet  MATH  Google Scholar 

  28. Pan Y, Liu Y, Xu B, Yu H (2016) Hybrid feedback feedforward: An efficient design of adaptive neural network control. Neural Netw 76:122–134. https://doi.org/10.1016/j.neunet.2015.12.009

    Article  MATH  Google Scholar 

  29. Slotine JE, Li W (1987) On the adaptive control of robot manipulators. Int J Rob Res 6(3):49–59. https://doi.org/10.1177/027836498700600303

    Article  Google Scholar 

  30. Wang C, Hill DJ (2010) Deterministic learning theory for identification, recognition, and control. CRC Press, US

    MATH  Google Scholar 

  31. Sastry S, Bodson M (1989) Adaptive control: stability, convergence, and robustness. Prentice Hall, Englewood Cliffs, NJ

    MATH  Google Scholar 

  32. Boyd S, Sastry S (1986) Necessary and sufficient conditions for parameter convergence in adaptive control. Automatica 22(6):629–639. https://doi.org/10.1016/0005-1098(86)90002-6

    Article  Google Scholar 

  33. Kurdila A, Narcowich FJ, Ward JD (1995) Persistency of excitation in identification using radial basis function approximants. SIAM J Control Optim 33(2):625–642. https://doi.org/10.1016/0005-1098(86)90002-6

    Article  MathSciNet  MATH  Google Scholar 

  34. Arthur D, Vassilvitskii S (2007) k-means++: The advantages of careful seeding. In: Proceedings of the eighteenth annual ACM-SIAM symposium on discrete algorithms, pp 1027–1035

  35. Xian B, Dawson DM, de Queiroz MS, Chen JJ (2004) A continuous asymptotic tracking control strategy for uncertain nonlinear systems. IEEE Trans Automat Contr 49:1206–1211. https://doi.org/10.1109/TAC.2004.831148

    Article  MathSciNet  MATH  Google Scholar 

  36. Khalil H (2002) Nonlinear Systems. Prentice Hall, Upper Saddle River, NJ, USA

    MATH  Google Scholar 

  37. Liu Q, Li D, Ge SS, Ouyang Z (2021) Adaptive feedforward neural network control with an optimized hidden node distribution. IEEE Trans Artif Intell 2(1):71–82. https://doi.org/10.1109/TAI.2021.3074106

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Cyber Science and Technology, Beihang University, Beijing, 100191, China

    Qiong Liu & Dongyu Li

  2. Tsinghua-Berkeley Shenzhen Institute, Tsinghua University, Shenzhen, 518071, China

    Qiong Liu & Ye Guo

  3. Department of Electrical and Computer Engineering, National University of Singapore, Singapore, 117576, Singapore

    Shuzhi Sam Ge

Authors
  1. Qiong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dongyu Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shuzhi Sam Ge
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ye Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dongyu Li.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interest regarding the publication of this paper.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, Q., Li, D., Ge, S.S. et al. Adaptive feedforward RBF neural network control with the deterministic persistence of excitation. Neural Comput & Applic 33, 17013–17028 (2021). https://doi.org/10.1007/s00521-021-06293-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-021-06293-z

Keywords

Search

Navigation