Journal ArticleDOI
Active learning of tandem flapping wings at optimizing propulsion performance
Reads0
Chats0
TLDR
An optimization framework based on the active learning method is proposed, which aims to quickly determine the conditions of tandem flapping wings for optimal performance in terms of thrust or efficiency, and it is found that the time-average thrust of the hind flapping wing increases with the frequency.Abstract:
In the present work, we propose an optimization framework based on the active learning method, which aims to quickly determine the conditions of tandem flapping wings for optimal performance in terms of thrust or efficiency. Especially, multi-fidelity Gaussian process regression is used to establish the surrogate model correlating the kinematic parameters of tandem flapping wings and their aerodynamic performances. Moreover, the Bayesian optimization algorithm is employed to select new candidate points and update the surrogate model. With this framework, the parameter space can be explored and exploited adaptively. Two optimization tasks of tandem wings are carried out using this surrogate-based framework by optimizing thrust and propulsion efficiency. The response surfaces predicted from the updated surrogate model present the influence of the flapping frequency, phase, and separation distance on thrust and efficiency. It is found that the time-average thrust of the hind flapping wing increases with the frequency. However, the increase in frequency may lead to a decrease in propulsive efficiency in some circumstances.read more
Citations
More filters
Journal ArticleDOI
DRLinFluids---An open-source python platform of coupling Deep Reinforcement Learning and OpenFOAM
TL;DR: In this article , an open-source python platform for applications of Deep Reinforcement Learning (DRL) in fluid mechanics is proposed, where an agent maximizes a cumulative reward by learning a feedback policy by acting in an environment and the cumulative reward would correspond to the cost function, the agent to the actuator, the environment to the measured signals, and the learned policy to the feedback law.
Journal ArticleDOI
Data-efficient deep reinforcement learning with expert demonstration for active flow control
TL;DR: A new data-efficient RL approach is developed for discovering active flow control strategies for vortex-induced vibration, providing a more practical methodology for industrial applications.
Journal ArticleDOI
Multi-fidelity model and reduced-order method for comprehensive hydrodynamic performance optimization and prediction of JBC ship
Xinwang Liu,Decheng Wan,Lei Lei +2 more
TL;DR: In this article , the hull form optimization process for resistance and wake performance of a Japan bulk carrier (JBC) hull at design speed is given in detail, where the evaluation results from medium and coarse grids are regarded as the high- and low-fidelity data, respectively.
Journal ArticleDOI
Aerodynamic shape optimization of co-flow jet airfoil using a multi-island genetic algorithm
Hao Jiang,Min Xu,Weigang Yao +2 more
TL;DR: In this article , a co-flow jet is integrated into aerodynamic shape optimization to further realize the potential of coflow-jet technology and improve coflow jet airfoil performance, which shows that the maximum energy efficiency ratio of lift-augmentation and drag reduction increased by 203.53% and 10.25% at the Power-1 condition (power coefficient of 0.3), respectively.
Journal ArticleDOI
Flow Control with Synthetic Jets on two Tandem Airfoils Using Machine Learning
TL;DR: In this article , an active flow control (AFC) was applied to a tandem configuration of two SD7003 airfoils in order to improve total aerodynamic performance defined as the combined total time-averaged value of lift-to-drag ratio (L/D)tot.
References
More filters
Journal ArticleDOI
Oscillating foils of high propulsive efficiency
TL;DR: In this article, the phase angle between transverse oscillation and angular motion is the critical parameter affecting the interaction of leading-edge and trailing-edge vorticity, as well as the efficiency of propulsion.
Journal ArticleDOI
Dragonfly flight: free-flight and tethered flow visualizations reveal a diverse array of unsteady lift-generating mechanisms, controlled primarily via angle of attack.
TL;DR: It appears that stability of the LEV is achieved by a general mechanism whereby flapping kinematics are configured so that a LEV would be expected to form naturally over the wing and remain attached for the duration of the stroke, however, the actual formation and shed is controlled by wing angle of attack.
Journal ArticleDOI
Flight Performance of a Dragonfly
Akira Azuma,Tadaaki Watanabe +1 more
TL;DR: The results show that without using any novel unsteady aerodynamic force generated by a separated flow over the wings, the dragonfly can make steady trimmed flight at various flight speeds, from hovering to top speed.
Journal ArticleDOI
Effect of forewing and hindwing interactions on aerodynamic forces and power in hovering dragonfly flight.
Z. Jane Wang,David Russell +1 more
TL;DR: This work film the wing motion of a tethered dragonfly and compute the aerodynamic force and power as a function of the phase, finding that the out-of-phase motion as seen in steady hovering uses nearly minimal power to generate the required force to balance the weight.