Abstract
This paper reviews the Higher Order Nonlinear Units (HONUs) and their fundamental supervised sample-by-sample and batch learning algorithms for data-driven controller learning when only measured data are known about the plant. We recall recently introduced conjugate gradient batch learning for weakly nonlinear plant identification with HONUs and we compare its performance to classical Levenberg-Marquard (LM). Further, we recall recursive least square (RLS) adaptation and compare its performance to L-M learning both for plant approximation and controller tuning. Further, a model reference adaptive control (MRAC) strategy with efficient controller learning for linear and weakly nonlinear plants is proposed with static HONUs that avoids recurrent computations, and its potentials and limitations with respect to plant nonlinearity are discussed. Recently developed stability approach for recurrent HONUs and for closed control loops with linear plant and nonlinear (HONU) controller is recalled and discussed in connotation stability of the adaptive closed control loop.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Abbreviations
- CG:
-
Conjugate Gradient algorithm
- CNU:
-
Cubic Neural Unit (HONU r = 3)
- \( {\mathbf{colx}} \) :
-
Long column vector of polynomial terms
- d :
-
Desired value (setpoint)
- LNU:
-
Linear Neural Unit (HONU r = 1)
- QNU:
-
Quadratic Neural Unit (HONU r = 2)
- k :
-
Discrete index of time
- L-M:
-
Levenberg-Marquardt batch learning algorithm
- n,m :
-
Length of vector \( {\mathbf{x}},\xi \)
- \( n_{y} ,n_{u} \) :
-
Length of recent history of y or u [samples]
- \( r,\gamma \) :
-
Order of polynomial nonlinearity (plant, controller)
- \( r_{o} \) :
-
Control input gain at plant input
- T :
-
Vector transposition
- u :
-
Control input
- \( {\mathbf{w}},{\mathbf{v}} \) :
-
Long row vectors of all neural weights (plant, controller)
- \( {\mathbf{x}},\xi \) :
-
Augmented input vector to HONU (plant, controller)
- \( \tilde{y} \) :
-
Neural output from HONU
- y :
-
Controlled output variable (measured)
- \( y_{ref} \) :
-
Reference model output
- e :
-
Error between real output and HONU
- \( e_{ref} \) :
-
Error between reference model and control loop
- \( \mu \) :
-
Learning rate
References
Suganthan, P.N.: Letter: on non-iterative learning algorithms with closed-form solution. Appl. Soft Comput. 70, 1078–1082 (2018)
Wang, F., Zhang, H., Liu, D.: Adaptive dynamic programming: an introduction. IEEE Comput. Intell. Mag. 4(2), 39–47 (2009)
Wang, X., Cheng, Y., Sun, W.: A proposal of adaptive PID controller based on reinforcement learning. J. China Univ. Min. Technol. 17(1), 40–44 (2007)
Liu, D., Wei, Q.: Policy iteration adaptive dynamic programming algorithm for discrete-time non-linear systems. IEEE Trans. Neural Netw. Learn. Syst. 25(3), 621–634 (2014)
Garcia, C.E., Prett, D.M., Morani, M.: Model predictive control: theory and practice—a survey. Automatica 25(3), 335–348 (1989)
Ławryńczuk, M.: Neural networks in model predictive control. Intell. Syst. Knowl. Manag. 31–63 (2009)
Morani, M., Lee, J.H.: Model predictive control: past, present and future. Comput. Chem. Eng. 23(4–5), 667–682 (1999)
Osburn, P.V.: New Developments in the Design of Model Reference Adaptive Control Systems. Institute of the Aerospace Sciences (1961)
Narendra, K.S., Valavani, L.S.: Direct and indirect model reference adaptive control. Automatica 15(6), 653–664 (1979)
Parks, P.C.: Liapunov redesign of model reference adaptive control systems. IEEE Trans. Autom. Control 11(3), 362–367 (1966)
Elbuluk, M.E., Tong, L., Husain, I.: Neural-network-based model reference adaptive systems for high-performance motor drives and motion controls. IEEE Trans. Ind. Appl. 38(3), 879–886 (2002)
Bukovsky, I., Homma, N.: An approach to stable gradient-descent adaptation of higher order neural units. IEEE Trans. Neural Netw. Learn. Syst. 28(9), 2022–2034 (2017)
Gupta, M.M., Bukovsky, I., Homma, N., Solo, A.M.G., Hou, Z.-G.: Fundamentals of higher order neural networks for modeling and simulation. In: Zhang, M. (eds.) Artificial Higher Order Neural Networks for Modeling and Simulation, pp. 103–133. IGI Global, Hershey, PA, USA (2013)
Nikolaev, N.Y., Iba, H.: Adaptive Learning of Polynomial Networks Genetic Programming, Backpropagation and Bayesian Methods. Springer, New York (2006)
Ivakhnenko, A.G.: Polynomial theory of complex systems. IEEE Trans. Syst. Man Cybern. SMC-1(4), 364–378 (1971)
Taylor, J.G., Coombes, S.: Learning higher order correlations. Neural Netw. 6(3), 423–427 (1993)
Kosmatopoulos, E.B., Polycarpou, M.M., Christodoulou, M.A., Ioannou, P.A.: High-order neural network structures for identification of dynamical systems. IEEE Trans. Neural Netw. 6(2), 422–431 (1995)
Tripathi, B.K.: Higher-order computational model for novel neurons. In: High Dimensional Neurocomputing, vol. 571, pp. 79–103. Springer India, New Delhi (2015)
Dai, Y., Yuan, Y.: A nonlinear conjugate gradient method with a strong global convergence property. SIAM J. Optim. 10(1), 177–182 (1999)
El-Nabarawy, I., Abdelbar, A.M., Wunsch, D.C.: Levenberg-Marquardt and Conjugate Gradient methods applied to a high-order neural network. In: Presented at the 2013 International Joint Conference on Neural Networks (IJCNN), Dallas, TX, USA, pp. 1–7 (2013)
Zhu, T., Yan, Z., Peng, X.: A modified nonlinear conjugate gradient method for engineering computation. Math. Probl. Eng. 1–11 (2017)
Benes, P.M., Bukovsky, I., Cejnek, M., Kalivoda, J.: Neural network approach to railway stand lateral skew control. In: Computer Science & Information Technology (CS& IT), Sydney, Australia, vol. 4, pp. 327–339 (2014)
Benes, P., Bukovsky, I.: Neural network approach to hoist deceleration control. In: 2014 International Joint Conference on Neural Networks (IJCNN), pp. 1864–1869 (2014)
Bukovsky, I., Benes, P., Slama, M.: Laboratory systems control with adaptively tuned higher order neural units. In: Silhavy, R., Senkerik, R., Oplatkova, Z.K., Prokopova, Z., Silhavy, P. (eds.) Intelligent Systems in Cybernetics and Automation Theory, pp. 275–284. Springer International Publishing (2015)
Benes, P., Bukovsky, I.: On the intrinsic relation between linear dynamical systems and higher order neural units. In: Silhavy, R., Senkerik, R., Oplatkova, Z.K., Prokopova, Z., Silhavy, P. (eds.) Intelligent Systems in Cybernetics and Automation Theory. Springer International Publishing (2016)
Benes, P., Bukovsky, I.: An input to state stability approach for evaluation of nonlinear control loops with linear plant model. In: Silhavy, R., Senkerik, R., Oplatkova, Z.K., Prokopova, Z., Silhavy, P. (eds.) Cybernetics and Algorithms in Intelligent Systems, vol. 765, pp. 144–154. Springer International Publishing (2018)
Ahn, C.K.: Robust stability of recurrent neural networks with ISS learning algorithm. Nonlinear Dyn. 65, 413–419 (2011)
Yang, Z., Zhou, W., Huang, T.: Exponential input-to-state stability of recurrent neural networks with multiple time-varying delays. Cogn. Neurodyn. 8(1), 47–54 (2014)
Wang, Z., Liu, D.: Stability analysis for a class of systems: from model-based methods to data-driven methods. IEEE Trans. Ind. Electron. 61(11), 6463–6471 (2014)
Zhang, H., Wang, Z., Liu, D.: A comprehensive review of stability analysis of continuous-time recurrent neural networks. IEEE Trans. Neural Netw. Learn. Syst. 25(7), 1229–1262 (2014)
Bukovsky, I., Voracek, J., Ichiji, K., Noriyasu, H.: Higher order neural units for efficient adaptive control of weakly nonlinear systems. In: Proceedings of the 9th International Joint Conference on Computational Intelligence, Funchal, Madeira, Portugal, vol. 1, pp. 149–157 (2017)
Benes, P.M., Erben, M., Vesely, M., Liska, O., Bukovsky, I.: HONU and supervised learning algorithms in adaptive feedback control. In: Applied Artificial Higher Order Neural Networks for Control and Recognition, pp. 35–60. IGI Global (2016)
Acknowledgements
Authors acknowledge support from the EU Operational Programme Research, Development and Education, and from the Center of Advanced Aerospace Technology (CZ.02.1.01/0.0/0.0/16_019/0000826), and the Japanese JSPS KAKENHI Grant Number 15J05402.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Benes, P.M., Bukovsky, I., Vesely, M., Voracek, J., Ichiji, K., Homma, N. (2019). Framework for Discrete-Time Model Reference Adaptive Control of Weakly Nonlinear Systems with HONUs. In: Sabourin, C., Merelo, J.J., Madani, K., Warwick, K. (eds) Computational Intelligence. IJCCI 2017. Studies in Computational Intelligence, vol 829. Springer, Cham. https://doi.org/10.1007/978-3-030-16469-0_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-16469-0_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-16468-3
Online ISBN: 978-3-030-16469-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)