In an indirect adaptive neural control scheme, the performance can be significantly impacted by arbitrary selection of the neural emulator and neural controller’s adaptive learning rates. This paper presents a novel method for adjusting the adaptive learning rates of both the neural network emulator and controller using reinforcement learning, thereby improving the closed-loop system’s performance. Key advantages of this new control algorithm include: (1) real-time optimization of the adaptive learning rates, eliminating the need for manual tuning typically required by conventional methods, and (2) faster convergence, disturbance rejection, and accurate tracking. The efficiency of the reinforcement learning-based adaptive rate adjustment is validated through two numerical control of a SISO nonlinear systems. Results demonstrate the improved performance of the proposed neural controller compared to existing methods. The developed approach is also applied to a semi-batch reactor to validate the simulation results.
ChengLWangZJiangF, et al. Adaptive neural network control of nonlinear systems with unmodeled dynamics. Adv Space Res2021; 67(3): 1114–1123.
2.
FarhatYAtigAZribiA, et al. Neural emulator for nonlinear systems based on PSO algorithm: real-time validation. Cluster Comput2024; 27(4): 5107–5119.
3.
CuiGYuJShiP.Observer-based finite-time adaptive fuzzy control with prescribed performance for nonstrict-feedback nonlinear systems. IEEE Trans Fuzzy Syst2022; 30(3): 767–778.
4.
MuliadiJKusumoputroB.Neural network control system of UAV altitude dynamics and its comparison with the pid control system. J Adv Transp2021; 18(2): 1–19.
5.
SultanHSKJawadR.Comparison between PID and artificial neural networks to control of boiler for steam power plant. J Eng Sci2019; 6(1): 10–15.
6.
BasaranSBolatCSivriogluS.Vibration suppression of wind turbine nacelle with active electromagneticmass damper systems using adaptive backstepping control. J Vib Control1999; 27(13–14): 1–14.
7.
YuJShiPChenX, et al. Finite-time command filtered adaptive control for nonlinear systems via immersion and invariance. Sci China Inf Sci2021; 64(192202): 1–14.
8.
Rodríguez-MolinaAVillarreal-CervantesMGAldape-PérezM. Indirect adaptive control using the novel online hypervolume-based differential evolution for the four-bar mechanism. Mechatronics2020; 36(102384): 811–853.
9.
AelaKenneAAJean-PierreKMintsaHA.Adaptive neural network and nonlinear electrohydraulic active suspension control system. J Vib Control2020; 28(3-4): 243–259.
10.
DierksTJagannathanS.Output feedback control of a quadrator UAV using neural networks. IEEE Trans Neural Netw2010; 21(1): 50–66.
11.
ZengSHuHXuL, et al. Nonlinear adaptive PID control for greenhouse environment based on rbf network. Sensors2012; 12(5): 5328–5348.
12.
WilliamsRJZipserD.A learning algorithm for continually running fully recurrent neural networks. Comput Ind Eng1989; 1(2): 270–280.
13.
SlamaSErrachdiABenrejebM.Neural adaptive PID and neural indirect adaptive control switch controller for nonlinear MIMO systems. Math Probl Eng2019; 36(4): 1–11.
14.
FrijetZZribiAChtourouM.An adaptive neural network controller based on PSO and gradient descent method for PMSM speed drive. Int J Power Electron Drive Syst2018; 9(3): 1412–1422.
15.
AtigADruauxFLefebvreD, et al. A multi-objective criterion and stability analysis for neural adaptive control of nonlinear MIMO systems: an experimental validation. Int J Autom Control2022; 6(3–4): 433–458.
16.
BentaherAZribiAHamzaR.A multi-objective indirect neural adaptive processes control design for minimization of energy consumption: an experimental validation on a transesterification reactor. J Vib Control2024; 45(6): 1–20.
17.
FarhatYZribiAAtigA, et al. A neuralmulticontroller for strongly nonlinear systems. Int J Syst Sci2022; 53(8): 1778–1795.
18.
MeiXZhangKLiH, et al. Fast online adaptive neural MPC via meta-learning. arXiv preprint arXiv:250416369 2025. https://arxiv.org/abs/2504.16369
19.
ZhouYChenMLiW.Adaptive optimization of hyper-parameters for robotic manipulation through evolutionary reinforcement learning. J Intell Robot Syst2024; 110(3): 108.
20.
YoussefWShalabyA.Reinforcement learning-enhanced adaptive sliding mode control for nonlinear systems. Complex Intell Syst2025; 11: 351.
21.
DaoTPhamMVuH, et al. Adaptive reinforcement learning in control design for cooperating manipulator systems. Asian J Control2022; 24(6): 2381–2395.
22.
LiuQZhaoYWangW.Adaptive output feedback reinforcement learning control for continuous time switched stochastic nonlinear systems with unknown control coefficients and full-state constraints. Int J Syst Sci2023; 54(15): 3034–3052.
23.
FarhatYRhiliFAtigA, et al. Stability analysis strategy for the adaptive neural control system: A practical validation via a transesterification reactor. Iran J Sci Technol Trans Electr Eng2021; 45(6): 1395–1409.
24.
HamzaRFarhatYZribiA.A new indirect adaptive neural control for nonlinear systems: a real validation on a chemical process. Int J Artif Intell Tools2022; 31(8): 2250041.
25.
HamzaRFarhatYZribiA.A novel neural emulator identification of nonlinear dynamical systems using lyapunov stability theory. Trans Inst Meas Control2023; 45(2): 1–17.
26.
JiangYFanJChaiT, et al. Data-driven flotation industrial process operational optimal control based on reinforcement learning. IEEE Trans Ind Inform2017; 14(5): 1974–1989.
27.
DietterichTG.Hierarchical reinforcement learning with the maxq value function decomposition. J Artif Intell Res2000; 13(5): 227–303.
28.
ZhangQLinMYangLT, et al. Energy-efficient scheduling for real-time systems based on deep q-learning model. IEEE Trans Sustain Comput2019; 4(1): 132–141.
29.
YangLSunQMaD, et al. Nash q-learning based equilibrium transfer for integrated energy management game with we-energy. Neurocomputing2020; 396(1): 216–223.
30.
LeeCTengC.Identification and control of dynamic systems using recurrent fuzzy neural networks. IEEE Trans Fuzzy Syst2000; 8(4): 349–366.
31.
ElkhalilKZribiA.Systematic model bank determination approach for nonlinear systems using gap metric and stability margin. J Process Control2023; 132: 103126–103236.
32.
ElkhalilKZribiA.Linear controller design approach for nonlinear systems by integrating gap metric and stability margin. Proc IMechE Part I: J Syst Control Eng2023; 237: 1800–1811.
