Multi-agent reinforcement learning vibration control and trajectory planning of a double flexible beam coupling system

[Display omitted] •A coupling system of moving double flexible beams is designed, FEM is obtained.•Wavelet function and FOA are used to identify the model parameters.•Trajectory planning using tabu search optimization algorithm is conducted.•Vibration controller is trained by the COMARL algorithm.•T...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Mechanical systems and signal processing Ročník 200; s. 110502
Hlavní autoři:	Qiu, Zhi-cheng, Hu, Jun-fei, Zhang, Xian-min
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 01.10.2023
Témata:	Counterfactual Multi-Agent reinforcement learning algorithm Double piezoelectric flexible beam coupling system Model identification Trajectory Planning Vibration control Vibration control Counterfactual Multi-Agent reinforcement learning algorithm COMARL Double piezoelectric flexible beam coupling system Trajectory Planning Model identification
ISSN:	0888-3270, 1096-1216
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	[Display omitted] •A coupling system of moving double flexible beams is designed, FEM is obtained.•Wavelet function and FOA are used to identify the model parameters.•Trajectory planning using tabu search optimization algorithm is conducted.•Vibration controller is trained by the COMARL algorithm.•The experiments verify that the COMARL algorithm and the optimized trajectory are effective for vibration suppression. A multi-agent reinforcement learning vibration controller is designed for active vibration suppression of a movable double piezoelectric flexible beam coupling system, and the motion trajectory is optimized to minimize vibration excitation during motion and residual vibration after motion. The finite element method is used to model the system dynamics, then, the actual model parameters are identified by combining wavelet and intelligent optimization algorithm. The corrected piezoelectric driving model is used to train the counterfactual multi-agent reinforcement learning (COMARL) algorithm, and an excellent nonlinear controller for vibration control of piezoelectric actuators is obtained. The motion trajectory of the double flexible beam coupling system is designed by using the corrected motor-driven model. The optimal vibration suppression trajectory is obtained by using tabu search algorithm. The simulation and experimental results show that the optimized trajectory greatly reduces the vibration excitation. The controller trained by the COMARL algorithm fully considers the influence of either beam in the system, and infers the contribution of piezoelectric actuators to the completion of the overall task through counterfactual thinking. The control effect is better than that of PD control, especially the small-amplitude vibration suppression. The effectiveness of the COMARL controller is further verified by simultaneous piezoelectric control during trajectory motion. Vibrations during translational motion and at the end of motion are suppressed quickly.
ISSN:	0888-3270 1096-1216
DOI:	10.1016/j.ymssp.2023.110502