Journal of Bionic Engineering ›› 2019, Vol. 16 ›› Issue (5): 904-915.doi: 10.1007/s42235-019-0105-5

• • 上一篇    下一篇

A Neural-network-based Approach to Study the Energy-optimal Hovering Wing Kinematics of a Bionic Hawkmoth Model

Anh Tuan Nguyen1*, Ngoc Doan Tran1, Thanh Trung Vu2, Thanh Dong Pham1, Quoc Tru Vu1, Jae-Hung Han3


  

  1. 1. Faculty of Aerospace Engineering, Le Quy Don Technical University, 236 Hoang Quoc Viet, Vietnam
    2. Office of International Cooperation, Le Quy Don Technical University, 236 Hoang Quoc Viet, Vietnam
    3. Department of Aerospace Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of Korea
  • 收稿日期:2019-04-24 修回日期:2019-08-27 接受日期:2019-09-11 出版日期:2019-10-10 发布日期:2019-10-15
  • 通讯作者: Anh Tuan Nguyen E-mail:anhtuannguyen2410@gmail.com
  • 作者简介:Anh Tuan Nguyen, Ngoc Doan Tran, Thanh Trung Vu, Thanh Dong Pham, Quoc Tru Vu, Jae-Hung Han

A Neural-network-based Approach to Study the Energy-optimal Hovering Wing Kinematics of a Bionic Hawkmoth Model

Anh Tuan Nguyen1*, Ngoc Doan Tran1, Thanh Trung Vu2, Thanh Dong Pham1, Quoc Tru Vu1, Jae-Hung Han3#br#

#br#
  

  1. 1. Faculty of Aerospace Engineering, Le Quy Don Technical University, 236 Hoang Quoc Viet, Vietnam
    2. Office of International Cooperation, Le Quy Don Technical University, 236 Hoang Quoc Viet, Vietnam
    3. Department of Aerospace Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of Korea
  • Received:2019-04-24 Revised:2019-08-27 Accepted:2019-09-11 Online:2019-10-10 Published:2019-10-15
  • Contact: Anh Tuan Nguyen E-mail:anhtuannguyen2410@gmail.com
  • About author:Anh Tuan Nguyen, Ngoc Doan Tran, Thanh Trung Vu, Thanh Dong Pham, Quoc Tru Vu, Jae-Hung Han

摘要: This paper presents the application of an artificial neural network to develop an approach to determine and study the energy-optimal wing kinematics of a hovering bionic hawkmoth model. A three-layered artificial neural network is used for the rapid prediction of the unsteady aerodynamic force acting on the wings and the required power. When this artificial network is integrated into genetic and simplex algorithms, the running time of the optimization process is reduced considerably. The validity of this new approach is confirmed in a comparison with a conventional method using an aerodynamic model based on an extended unsteady vortex-lattice method for a sinusoidal wing kinematics problem. When studying the obtained results, it is found that actual hawkmoths do not hover under an energy-
optimal condition. Instead, by tilting the stroke plane and lowering the wing positions, they can compromise and expend some energy to enhance their maneuverability and the stability of their flight.


关键词: optimal hovering wing kinematics, artificial neural network, insect flight, genetic algorithm, unsteady vortex-lattice method, bionics

Abstract: This paper presents the application of an artificial neural network to develop an approach to determine and study the energy-optimal wing kinematics of a hovering bionic hawkmoth model. A three-layered artificial neural network is used for the rapid prediction of the unsteady aerodynamic force acting on the wings and the required power. When this artificial network is integrated into genetic and simplex algorithms, the running time of the optimization process is reduced considerably. The validity of this new approach is confirmed in a comparison with a conventional method using an aerodynamic model based on an extended unsteady vortex-lattice method for a sinusoidal wing kinematics problem. When studying the obtained results, it is found that actual hawkmoths do not hover under an energy-
optimal condition. Instead, by tilting the stroke plane and lowering the wing positions, they can compromise and expend some energy to enhance their maneuverability and the stability of their flight.


Key words: optimal hovering wing kinematics, artificial neural network, insect flight, genetic algorithm, unsteady vortex-lattice method, bionics