A hyper-heuristic approach to aircraft structural design optimization

被引:0
|
作者
Jonathan G. Allen
Graham Coates
Jon Trevelyan
机构
[1] Durham University,School of Engineering and Computing Sciences
关键词
Aircraft conceptual design; Structural optimization; Hyper-heuristic optimization;
D O I
暂无
中图分类号
学科分类号
摘要
The conceptual design of an aircraft is a challenging problem in which optimization can be of great importance to the quality of design generated. Mass optimization of the structural design of an aircraft aims to produce an airframe of minimal mass whilst maintaining satisfactory strength under various loading conditions due to flight and ground manoeuvres. Hyper-heuristic optimization is an evolving field of research wherein the optimization process is continuously adapted in order to provide greater improvements in the quality of the solution generated. The relative infancy of hyper-heuristic optimization has resulted in limited application within the field of aerospace design. This paper describes a framework for the mass optimization of the structural layout of an aircraft at the conceptual level of design employing a novel hyper-heuristic approach. This hyper-heuristic approach encourages solution space exploration, thus reducing the likelihood of premature convergence, and improves the feasibility of and convergence upon the best solution found. A case study is presented to illustrate the effects of hyper-heuristics on the problem for a large commercial aircraft. Resulting solutions were generated of considerably lighter mass than the baseline aircraft. A further improvement in solution quality was found with the use of the hyper-heuristics compared to that obtained without, albeit with a penalty on computation time.
引用
收藏
页码:807 / 819
页数:12
相关论文
共 50 条
  • [41] A reinforcement learning hyper-heuristic in multi-objective optimization with application to structural damage identification
    Cao, Pei
    Zhang, Yang
    Zhou, Kai
    Tang, J.
    STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2023, 66 (01)
  • [42] A reinforcement learning hyper-heuristic in multi-objective optimization with application to structural damage identification
    Pei Cao
    Yang Zhang
    Kai Zhou
    J. Tang
    Structural and Multidisciplinary Optimization, 2023, 66
  • [43] A Dynamic Hyper-Heuristic Based on Scatter Search for the Aircraft Landing Scheduling Problem
    Shi, Wen
    Song, Xueyan
    Sun, Jizhou
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2014, E97A (10): : 2090 - 2094
  • [44] An evolutionary-based hyper-heuristic approach for the Jawbreaker puzzle
    S. Salcedo-Sanz
    J. M. Matías-Román
    S. Jiménez-Fernández
    A. Portilla-Figueras
    L. Cuadra
    Applied Intelligence, 2014, 40 : 404 - 414
  • [45] A Hyper-Heuristic Approach to Solving the Ski-Lodge Problem
    Hassan, Ahmed
    Pillay, Nelishia
    ADVANCES IN NATURE AND BIOLOGICALLY INSPIRED COMPUTING, 2016, 419 : 201 - 210
  • [46] Multi-period portfolio optimization using a deep reinforcement learning hyper-heuristic approach
    Cui, Tianxiang
    Du, Nanjiang
    Yang, Xiaoying
    Ding, Shusheng
    TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE, 2024, 198
  • [47] Hyper-Heuristic Approach for Tuning Parameter Adaptation in Differential Evolution
    Stanovov, Vladimir
    Kazakovtsev, Lev
    Semenkin, Eugene
    AXIOMS, 2024, 13 (01)
  • [48] A Late Acceptance Hyper-Heuristic Approach for the Optimization Problem of Distributing Pilgrims over Mina Tents
    Shambour, Mohd Khaled Y.
    Khan, Esam A.
    JOURNAL OF UNIVERSAL COMPUTER SCIENCE, 2022, 28 (04) : 396 - 413
  • [49] Emergency Railway Transportation Planning Using a Hyper-Heuristic Approach
    Zheng, Yu-Jun
    Zhang, Min-Xia
    Ling, Hai-Feng
    Chen, Sheng-Yong
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2015, 16 (01) : 321 - 329
  • [50] An evolutionary-based hyper-heuristic approach for the Jawbreaker puzzle
    Salcedo-Sanz, S.
    Matias-Roman, J. M.
    Jimenez-Fernandez, S.
    Portilla-Figueras, A.
    Cuadra, L.
    APPLIED INTELLIGENCE, 2014, 40 (03) : 404 - 414