In this study, an adaptive control based on fuzzy adapting rate for neural emulator of nonlinear systems having unknown dynamics is proposed. The indirect adaptive control scheme is composed by the neural emulator and the neural controller which are connected by an autonomous algorithm inspired from the real-time recurrent learning. In order to ensure stability and faster convergence, a neural controller adapting rate is established in the sense of the continuous Lyapunov stability method. Numerical simulations are included to illustrate the effectiveness of the proposed method. The performance of the proposed control strategy is also demonstrated through an experimental simulation.
PometJBPralyL.Adaptive nonlinear regulation: estimation from the Lyapunov equation. IEEE Trans Automat Contr1992; 37(6): 729–740.
2.
HaddadWMHayakawaTChellaboinaV.Adaptive control for uncertain systems. Automatica2003; 39(3): 551–556.
3.
HanwateSHoteYVBudhrajaA.Design and implementation of adaptive control logic for cart-inverted pendulum system. Proc IMechE Part I: J Systems Control Engineering2019; 233(2): 164–178.
4.
RezaSSaeedRNMoharamHK, et al. Finite-time nonsingular terminal sliding mode control: A time setting approach. Proc IMechE Part I: J Systems Control Engineering; 2019; 233: 1–21.
5.
SadatiNGhadamiR.Adaptive multi-model sliding mode control of robotic manipulators using soft computing. Neurocomputing2008; 71(13-15): 2702–2710.
6.
ChijunZJihongZHuminL, et al. Robust constraint backstepping control for high-performance aircraft with account of unsteady aerodynamic effects. Proc IMechE Part I: J Systems Control Engineering2016; 230(13): 2484–2503.
7.
KokotovicPV.The joy of feedback: nonlinear and adaptive. IEEE Contr Syst1992; 12(3): 7–17.
8.
PanpanGSenpingTQianL.Decentralized iterative learning control for switched large-scale systems. T I Meas Contr2018; 41(4): 1045–1056.
9.
GuoYHillDJWangY.Nonlinear decentralized control of large-scale power systems. Automatica2000; 36(9): 1275–1289.
10.
ChenLNarendraKS.Identification and control of a nonlinear discrete-time system based on its linearization: a unified framework. IEEE Trans Neural Netw2004; 15(3): 663–673.
11.
TheofilatosKBeligiannisGLikothanassisS.Combining evolutionary and stochastic gradient techniques for system identification. J Computat Appl Mathe2009; 227(1): 147–160.
12.
ZhangYChaiTWangH.A nonlinear control method based on ANFIS and multiple models for a class of SISO nonlinear systems and its application. IEEE Trans Neural Netw2011; 22(11): 1783–1795.
13.
MoonJWJungSKKimY, et al. Comparative study of artificial intelligence-based building thermal control methods—application of fuzzy, adaptive neuro-fuzzy inference system, and artificial neural network. Appl Therm Eng2011; 31(14-15): 2422–2429.
14.
NarendraKSParthasarathyK.Identification and control of dynamical systems using neural networks. IEEE Trans Neural Netw1990; 1(1): 4–27.
15.
YabutaTYamadaT.Neural network controller characteristics with regard to adaptive control. IEEE Trans Syst Man Cybernet1992; 22(1): 170–177.
16.
TangJZhaoXWangY, et al. Adaptive neural network control for rotor’s stable suspension of Vernier-gimballing magnetically suspended flywheel. Proc IMechE Part I: J Systems Control Engineering2019; 233(8): 1017–1029.
17.
ShinJKimSTsourdosA.Neural-networks-based adaptive control for an uncertain nonlinear system with asymptotic stability. Int J Contr Autom Syst2018; 16(4): 1989–2001.
18.
LinTC.Observer-based robust adaptive interval type-2 fuzzy tracking control of multivariable nonlinear systems. Eng Appl Artif Intel2010; 23(3): 386–399.
19.
SadatiSParvarMSMenhajM, et al. Backstepping controller design using neural networks for a fighter aircraft. Eur J Contr2007; 13(5): 516–526.
20.
BudikDElhananyI. TRTRL: a localized resource-efficient learning algorithm for recurrent neural networks. In: Proceedings of the IEEE international conference midwest symposium on circuits and systems, volume 1. San Juan, PR, 6-9 August 2006, pp. 371–374. New York: IEEE.
21.
NellesO.Nonlinear system identification: from classical approaches to neural networks and fuzzy models. Berlin Heidelberg: Springer Science & Business Media, 2013.
22.
NasrMBChtourouM.Neural network control of nonlinear dynamic systems using hybrid algorithm. Appl Soft Comput2014; 24: 423–431.
23.
Tzirkel-HancockEFallsideF.Stable control of nonlinear systems using neural networks. Int J Robust Nonlinear Control1992; 2(1): 63–86.
24.
ChenFCKhalilHK.Adaptive control of a class of nonlinear discrete-time systems using neural networks. IEEE Trans Autom Contr1995; 40(5): 791–801.
25.
LewisFLYesildirekALiuK.Multilayer neural-net robot controller with guaranteed tracking performance. IEEE Trans Neural Netw1996; 7(2): 388–399.
26.
BibiYBouhaliOBouktirT.Robust direct adaptive controller for a class of uncertain nonlinear systems using petri type 2 fuzzy neural networks (PT2FNN) as a new approximator. J Electr Syst2019; 15(2): 181–196.
27.
LeclercqEDruauxFLefebvreD, et al. Autonomous learning algorithm for fully connected recurrent networks. Neurocomputing2005; 63: 25–44.
28.
ZerkaouiSDruauxFLeclercqE, et al. Stable adaptive control with recurrent neural networks for square MIMO non-linear systems. Eng Applicat Artif Intel2009; 22(4-5): 702–717.
29.
AtigADruauxFLefebvreD, et al. A new neural adaptive control based on neural emulation of complex square MIMO systems. Int Rev Autom Contr2010; 3(6): 612–623.
30.
AtigADruauxFLefebvreD, et al. Neural emulator and controller with decoupled adaptive rates for nonlinear systems: application to chemical reactors. Int J Sci Tech Autom Contr Comput Eng (IJ-STA)2010; 4(2): 1298–1319.
31.
RhiliFEAtigABen AbdennourR.Fuzzy adapting rate for a neural emulator of nonlinear systems: real application on a chemical process. Trans Inst Meas Contr2019; 41(8): 2214–2222.
32.
RovithakisGA.Robust neural adaptive stabilization of unknown systems with measurement noise. IEEE Trans Syst Man Cybernet, Part B (Cybernetics)1999; 29(3): 453–459.
33.
KulawskiGJBrdyśMA.Stable adaptive control with recurrent networks. Automatica2000; 36(1): 5–22.
34.
XuXLiangYLeeH, et al. A stable adaptive neural-network-based scheme for dynamical system control. J Sound Vibr2005; 285(3): 653–667.
35.
FouratiFChtourouMKamounM.Stabilization of unknown nonlinear systems using neural networks. Appl Soft Comput2008; 8(2): 1121–1130.
36.
RajeshRPreethiRMehataP, et al. Artificial neural network based inverse model control of a nonlinear process. In: Proceedings of the international conference on computer, communication and control (IC4), Indore, India, 10–12 September 2015, pp. 1–6. New York: IEEE.
37.
YuLFeiSLongF, et al. Multilayer neural networks-based direct adaptive control for switched nonlinear systems. Neurocomputing2010; 74(1–3): 481–486.
38.
WilliamsRJ.Adaptive state representation and estimation using recurrent connectionist networks. Neural Netw Contr1990; 30: 97–114.
39.
DruauxFLeclercqELefebvreD. Adaptive neural network control for uncertain or unknown nonlinear systems. In: Proceedings of IEEE MMAR, Poland, 2004, pp. 1309–1314. New York: IEEE.
40.
Ben AbdennourRFavierGKsouriM. Fuzzy trace identification algorithms for non-stationary systems. J Intel Fuzzy Syst1998; 6(4): 403–417.
AtigADruauxFLefebvreD, et al. Adaptive control design using stability analysis and tracking errors dynamics for nonlinear square MIMO systems. Eng Appl Artif Intel2012; 25(7): 1450–1459.
43.
Ben AbdennourRBouaniFKsouriM, et al. Etude comparative des commandes floue et prédictive généralisée: application à un procédé pilote. J Eur Des Syst Autom1998; 32(2): 187–205.
44.
NorouziAKazemiRAzadiS.Vehicle lateral control in the presence of uncertainty for lane change maneuver using adaptive sliding mode control with fuzzy boundary layer. Proc IMechE, Part I: J Systems Control Engineering2018; 232(1): 12–28.
45.
MamdaniEHAssilianS.An experiment in linguistic synthesis with a fuzzy logic controller. Int J Man-mach Stud1975; 7(1): 1–13.
