Three-coupled Flexible Beam (TCFB) system is a kind of vibration structure characterized by low damping, close space modes, and coupled vibrations. To address these challenges, the control scheme of reinforcement learning (RL) algorithm based on Importance-weights Actor-Learner Architecture (IMPALA) is applied. Using wavelet transform and Peafowl Optimization Algorithm (POA) to identify the system model matrices, an accurate system model is obtained, used to train RL algorithm. After training, the effectiveness of the IMPALA controller is verified by experiments. Compared with the traditional large gain proportional-derivative (PD) controllers, the experimental results show that the IMPALA controller can enhance vibration suppression, especially in rapidly attenuating small amplitude vibration. The IMPALA controller shows excellent performance and proves robustness.
CaoYCaoDHuangW (2019) Dynamic modeling and vibration control for a T-shaped bending and torsion structure. International Journal of Mechanical Sciences157–158: 773–786.
2.
EspeholtLSoyerHMunosR, et al. (2018) IMPALA: scalable distributed deep-RL with importance weighted Actor-Learner architectures. arXiv. doi: 10.48550/arXiv.1802.01561.
3.
FaridMCleghornWL (2014) Dynamic modeling of multi-flexible-link planar manipulators using curvature-based finite element method. Journal of Vibration and Control20(11): 1682–1696.
4.
FeiWHuT (2021) Adaptive h-infinity vibration control of flexible structure using fuzzy approximator. International Journal of Innovative Computing, Information and Control17(5): 1731–1734.
5.
HanLYuYQinR, et al. (2019) Static modeling of bending characteristics on V-shaped beam actuator based on flexible substrate. IEEE Transactions on Electron Devices66(12): 5295–5300.
6.
HassainMAMadkourAAMDahalKP, et al. (2018) Comparative performance of intelligent algorithms for system identification and control. Journal of Intelligent Systems17(4): 313–329.
7.
HeWGaoHZhouC, et al. (2021) Reinforcement learning control of a flexible two-link manipulator: an experimental investigation. IEEE Transactions on Systems, Man, and Cybernetics: Systems51(12): 7326–7336.
8.
JaderbergMMnihVCzarneckiWM, et al. (2016) Reinforcement learning with unsupervised auxiliary tasks. arXiv. doi: 10.48550/arXiv.1611.05397.
9.
KhaterAAEl-NagerAMEl-BardiniM, et al. (2018) Adaptive T-S fuzzy controller using reinforcement learning based on Lyapunov stability. Journal of the Franklin Institute-Engineering and Applied Mathematics355(14): 6390–6415.
10.
LiuYFuYHeW, et al. (2019) Modeling and observer-based vibration control of a flexible spacecraft with external disturbances. IEEE Transactions on Industrial Electronics66(11): 8648–8658.
11.
LiuSYYangHLLiuZJ, et al. (2024) Adaptive neural network independent joint-based control for an ODE PDE rigid-flexible manipulator with multiple constrains. Journal of Vibration and Control30(7-8): 1647–1658.
12.
MnihVBadiaAPMirzaM, et al. (2016) Asynchronous methods for deep reinforcement learning. arXiv. doi: 10.48550/arXiv.1602.01783.
13.
NairASrinivasanPBlackwellS, et al. (2015) Massively parallel methods for deep reinforcement learning. arXiv. doi: 10.48550/arXiv.1507.04296.
14.
QiuZHeCZhangX (2022a) Multi-agent cooperative structural vibration control of three coupled flexible beams based on value decomposition network. Engineering Applications of Artificial Intelligence114: 105002.
15.
QiuZYangYZhangX (2022b) Reinforcement learning vibration control of a multi-flexible beam coupling system. Aerospace Science and Technology129: 107801.
16.
RuzzeneMFasanaAGaribaldiL, et al. (1997) Natural frequencies and dampings identification using wavelet transformation: application to real data. Mechanical Systems and Signal Processing11(2): 207–218.
17.
SchiavoFViganoLFerrettiG (2006) Object-oriented modelling of flexible beams. Multibody System Dynamics15(3): 263–286.
18.
SchulmanJLevineSMoritzP, et al. (2015) Trust region policy optimization. International Conference on Machine Learning37: 1889–1897.
19.
StaszewskiWJ (1997) Identification of damping in MDOF systems using time-scale decomposition. Journal of Sound and Vibration203(2): 283–305.
20.
VaradanVVLimYHVaradanVK (1996) Closed loop finite-element modeling of active/passive damping in structural vibration control. Smart Materials and Structures5(5): 685–694.
21.
WagnerGLimaRSampaioR (2022) Modal identification of a light and flexible wind turbine blade under wind excitation. Journal of Engineering Mathematics133(1): 3.
22.
WangJYangBChenY, et al. (2022) Novel phasianidae inspired peafowl (Pavo muticus/cristatus) optimization algorithm: design, evaluation, and SOFC models parameter estimation. Sustainable Energy Technologies and Assessments50: 101825.
23.
XieZYouWWongPK, et al. (2023) Robust fuzzy fault tolerant control for nonlinear active suspension systems via adaptive hybrid triggered scheme. International Journal of Adaptive Control and Signal Processing37(7): 1608–1627.
24.
XuJFangHZhouT, et al. (2019) Optimal robust position control with input shaping for flexible solar array drive system: a fuzzy-set theoretic approach. IEEE Transactions on Fuzzy Systems27(9): 1807–1817.
25.
ZhangLFanWChenZ, et al. (2024) Dynamics modeling and attitude-vibration hybrid control of a large flexible space structure. Journal of Vibration and Control31(3-4): 555–568.
