Vibration control in civil engineering is often challenging due to the nonlinear nature of structures. Traditional control strategies have limitations in terms of modeling accuracy and scalability, especially when analyzing complex nonlinear systems. To solve this problem, this study proposes a model-free active vibration control technique specifically for nonlinear systems, which employs deep reinforcement learning (DRL) to train a neural network controller. The effectiveness and practicality of the proposed method have been validated on a shallow, simply supported buckled beam. The results prove that DRL can significantly increase the safety margin and effectively mitigate buckling under high load levels without requiring extra energy. Compared with conventional model-based linear and polynomial controllers, the proposed control strategy demonstrates excellent adaptability and ease of implementation. This research aims to supplement and expand the existing understanding of DRL applications in structural control, pointing towards a promising direction for future technological advancements and real-world applications.
CaiQZhuS (2022) The nexus between vibration-based energy harvesting and structural vibration control: a comprehensive review. Renewable and Sustainable Energy Reviews155: 111920.
11.
CasciatiFRodellarJYildirimU (2012) Active and semi-active control of structures - theory and applications: a review of recent advances. Journal of Intelligent Material Systems and Structures23(11): 1181–1195.
12.
DattaT (2003) A state-of-the-art review on active control of structures. ISET Journal of Earthquake Technology40(1): 1–17.
13.
FujimotoSHoofHMegerD (2018) Addressing function approximation error in actor-critic methods. In: International conference on machine learning, Stockholm, Sweden, pp. 1587–1596. PMLR.
14.
HaarnojaTZhouAAbbeelPet al. (2018) Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning, Stockholm, Sweden, pp. 1861–1870. PMLR.
15.
IqbalJUllahMKhanSG, et al. (2017) Nonlinear control systems-A brief overview of historical and recent advances. Nonlinear Engineering6(4): 301–312.
16.
JansenE (2008) A perturbation method for nonlinear vibrations of imperfect structures: application to cylindrical shell vibrations. International Journal of Solids and Structures45(3–4): 1124–1145.
17.
KhalatbarisoltaniASoleymaniMKhodadadiM (2019) Online control of an active seismic system via reinforcement learning. Structural Control and Health Monitoring26(3): e2298.
18.
LewisFLVrabieDSyrmosVL (2012) Optimal Control. Hoboken, NJ: John Wiley & Sons.
19.
LiY (2017) Deep reinforcement learning: an overview. ArXiv preprint arXiv:1701.07274.
20.
LiWTodorovE (2004) Iterative linear quadratic regulator design for nonlinear biological movement systems. ICINCO1: 222–229.
21.
LiJ-YZhuS (2022) Self-powered active vibration control: concept, modeling, and testing. Engineering11: 126–137.
22.
LillicrapTPHuntJJPritzelA, et al. (2015) Continuous control with deep reinforcement learning. ArXiv preprint arXiv:1509.02971.
23.
LüQWangXLuK, et al. (2020) Nonlinear stochastic optimal control using piezoelectric stack inertial actuator. Shock and Vibration2020: 1–7.
24.
MahmoudiRGhaffarzadehHAhaniE, et al. (2019) Sliding mode control of linear structures and a Duffing system using active tendons. Proceedings of the Institution of Civil Engineers - Engineering and Computational Mechanics172(3): 106–117.
25.
MnihVKavukcuogluKSilverD, et al. (2013) Playing atari with deep reinforcement learning. ArXiv preprint arXiv:1312.5602.
26.
NachumOGuSSLeeH, et al. (2018) Data-efficient hierarchical reinforcement learning. Advances in Neural Information Processing Systems31.
27.
NagendraSPodilaNUgarakhodR, et al. (2017) Comparison of reinforcement learning algorithms applied to the cart-pole problem. 2017 international conference on advances in computing, communications and informatics (ICACCI), Manipal. India: IEEE, 26–32.
PandaJChopraMMatsagarV, et al. (2024) An iterative gradient descent-based reinforcement learning policy for active control of structural vibrations. Computers & Structures290: 107183.
30.
PantelidesCNelsonP (1995) Continuous pulse control of nonlinear structures. Computers & Structures55(6): 997–1006.
31.
PintoOGonçalvesP (2000) Non-linear control of buckled beams under step loading. Mechanical Systems and Signal Processing14(6): 967–985.
32.
PintoOGonçalvesP (2002) Active non-linear control of buckling and vibrations of a flexible buckled beam. Chaos, Solitons & Fractals14(2): 227–239.
33.
PisarskiDJankowskiŁ (2023) Reinforcement learning‐based control to suppress the transient vibration of semi‐active structures subjected to unknown harmonic excitation. Computer-Aided Civil and Infrastructure Engineering38(12): 1605–1621.
34.
RahmaniHRChaseGWieringM, et al. (2019) A framework for brain learning-based control of smart structures. Advanced Engineering Informatics42: 100986.
35.
SaaedTENikolakopoulosGJonassonJE, et al. (2015) A state-of-the-art review of structural control systems. Journal of Vibration and Control21(5): 919–937.
36.
EshkevariSSSadeghi EshkevariSSenD, et al. (2023) Active structural control framework using policy-gradient reinforcement learning. Engineering Structures274: 115122.
37.
SchulmanJLevineSAbbeelP, et al. (2015) Trust region policy optimization. International conference on machine learning. Lille, France: JMLR, 1889–1897.
SheferMBreakwellJ (1987) Estimation and control with cubic nonlinearities. Journal of Optimization Theory and Applications53(1): 1–7.
40.
SongGGuH (2007) Active vibration suppression of a smart flexible beam using a sliding mode based controller. Journal of Vibration and Control13(8): 1095–1107.
41.
SoongTTCostantinouMC (2014) Passive and Active Structural Vibration Control in Civil Engineering. Berlin: Springer.
42.
SpencerBFJrNagarajaiahS (2003) State of the art of structural control. Journal of structural engineering129(7): 845–856.
43.
SuhardjoJSpencerBJrSainM (1992) Non-linear optimal control of a Duffing system. International Journal of Non-Linear Mechanics27(2): 157–172.
44.
TomasulaDSpencerBFJrSainM (1996) Nonlinear control strategies for limiting dynamic response extremes. Journal of Engineering Mechanics122(3): 218–229.
45.
WuZLinRSoongT (1995) Non-linear feedback control for improved peak response reduction. Smart Materials and Structures4(1A): A140–A148.
46.
XieYZEbad SichaniMPadgettJE, et al. (2020) The promise of implementing machine learning in earthquake engineering: a state-of-the-art review. Earthquake Spectra36(4): 1769–1801.
47.
XingLWenCLiuZ, et al. (2017) Event-triggered adaptive control for a class of uncertain nonlinear systems. IEEE Transactions on Automatic Control62(4): 2071–2076.
48.
YangJWuJLiZ (1996) Control of seismic-excited buildings using active variable stiffness systems. Engineering Structures18(8): 589–596.
49.
ZhangY-AZhuS (2023) Novel model-free optimal active vibration control strategy based on deep reinforcement learning. Structural Control and Health Monitoring2023: 1–15.
50.
ZhaoBLuXWuM, et al. (2000) Sliding mode control of buildings with base‐isolation hybrid protective system. Earthquake engineering & structural dynamics29(3): 315–326.
