This paper proposes the use of artificial neural networks methods for the stabilization control of the nonlinear rotary inverted pendulum system. The challenge lies in maintaining balance while keeping the pendulum upright. Three types of controls are proposed for stabilizing the system: multi-layer perceptron control, adaptive network fuzzy inference system control, and deep deterministic policy gradient control. Unlike the first two controllers, the third method achieves stabilization without requiring prior data or hybrid control strategies. An experimental comparison demonstrates the effectiveness and robustness of the proposed model-free controllers.
AengchuanPPhruksaphanratB (2018) Comparison of fuzzy inference system (FIS), FIS with artificial neural networks (FIS + ANN) and FIS with adaptive neuro-fuzzy inference system (FIS + ANFIS) for inventory control. Journal of Intelligent Manufacturing29: 905–923.
2.
BaekJJunHParkJ, et al. (2020) Sparse variational deterministic policy gradient for continuous real-time control. IEEE Transactions on Industrial Electronics68(10): 9800–9810.
3.
Ben HazemZBingülZ (2023) A comparative study of anti-swing radial basis neural-fuzzy LQR controller for multi-degree-of-freedom rotary pendulum systems. Neural Computing and Applications35: 17397–17413.
4.
DolatabaMRPasharaveshAKhayyatAAA (2022) Analytical and experimental analyses of nonlinear vibrations in a rotary inverted pendulum. Nonlinear Dynamics107: 1887–1902.
5.
DwivediPPandeySAnjaliSJ (2017) Stabilization of unstable equilibrium point of a rotary inverted pendulum using fractional controller. Journal of the Franklin Institute354(17): 7732–7766.
6.
GovindASelva KumarS (2020) A comparative study of controllers for QUANSER QUBE Servo 2 rotary inverted pendulum system. In: Advances in Electrical and Computer Technologies. Singapore: Springer Singapore.
7.
KimC (2021) Temporal consistency-based loss function for both deep Q-networks and deep deterministic policy gradients for continuous actions. Symmetry13(12): 2411.
8.
MahmoodabadiMJKhoobroo HaghbayanH (2020) An optimal adaptive hybrid controller for a fourth-order under-actuated nonlinear inverted pendulum system. Transactions of the Institute of Measurement and Control42: 285–294.
9.
MarakhimovARKhudaybergenovKK (2022) A fuzzy MLP approach for nonlinear system identification. Journal of Mathematical Sciences265(1): 43–51.
10.
MehediIMAnsariUBajodahAH, et al. (2020) Underactuated rotary inverted pendulum control using robust generalized dynamic inversion. Journal of Vibration and Control26(23-24): 2210–2220.
11.
MoatimidGMEl-SayedASalmanHF (2023) Dynamical analysis of an inverted pendulum with positive position feedback controller approximate uniform solution. Scientific Reports13: 8849.
12.
MofidOAlattasKAMobayenS, et al. (2023) Adaptive finite-time command-filtered backstepping sliding mode control for stabilization of a disturbed rotary-inverted-pendulum with experimental validation. Journal of Vibration and Control29: 1431–1446.
13.
Moreno-ValenzuelaJAguilar-AvelarAPuga-GuzmánCS, et al. (2016) Adaptive neural network control for the trajectory tracking of the Furuta pendulum. IEEE Transactions on Cybernetics46(12): 3439–3452.
14.
NguyenNPOhHKimY, et al. (2020) Fuzzy-based super-twisting sliding mode stabilization control for under-actuated rotary inverted pendulum systems. IEEE Access8: 185079–185092.
15.
NguyenVAPhamDBPhamDT, et al. (2022) A hybrid energy sliding mode controller for the rotary inverted pendulum. In: International Conference on Engineering Research and Applications. Cham: Springer, 34–41.
16.
NguyenTVADongBTBuiN (2023) Enhancing stability control of inverted pendulum using Takagi–Sugeno fuzzy model with disturbance rejection and input–output constraints. Scientific Reports13: 14412.
17.
PramanikSAnwarS (2022) Robust controller design for rotary inverted pendulum using H − ∞ and ν − synthesis techniques. Journal of Engineering2022: 249–260.
18.
Riahi-MadvarHDehghaniMSeifiA, et al. (2019) Comparative analysis of soft computing techniques RBF, MLP, and ANFIS with MLR and MNLR for predicting grade-control scour hole geometry. Engineering Applications of Computational Fluid Mechanics13(1): 529–550.
19.
RigatosGAbbaszadehBHamidaMA (2020) Nonlinear optimal control for the inertia wheel inverted pendulum. Cyber-Physical Systems6(2): 55–75.
20.
SaleemO (2023) An enhanced adaptive-LQR procedure for under-actuated systems using relative-rate feedback to dynamically reconfigure the state-weighting-factors. Journal of Vibration and Control29(9-10): 2316–2331.
21.
SaleemOMahmood-ul-HasanK (2019) Robust stabilisation of rotary inverted pendulum using intelligently optimised nonlinear self-adaptive dual fractional-order PD controllers. International Journal of Systems Science50(7): 1399–1414.
22.
SunZLiHZhangD, et al. (2023) Asymptotic state agreement of T–S fuzzy multi-agent systems: a dynamic event-triggered approach. International Journal of Fuzzy Systems25: 2476–2487.
23.
UnluturkAAydogduO (2022) Machine learning based self-balancing and motion control of the underactuated mobile inverted pendulum with variable load. IEEE Access10: 104706–104718.
24.
WangCLiuXShiH, et al. (2018) Design and implementation of fractional pid controller for rotary inverted pendulum. In: Chinese control and decision conference, Shenyang, China, 9 to 11 June 2018, 6730–6735.
25.
ZabihifarSHYushchenkoASNavvabiH (2020) Robust control based on adaptive neural network for rotary inverted pendulum with oscillation compensation. Neural Computing and Applications32: 14667–14679.
