• Home
  • Search
  • Optimum Morphing Shape Design for Morphing Wing with Corrugated Structure Using RBF Network
  • Cite Icon5
  • https://doi.org/10.1007/978-3-319-67988-4_70Copy DOI Icon

Optimum Morphing Shape Design for Morphing Wing with Corrugated Structure Using RBF Network

  • Dec 6, 2017
  • Gen Nakamura +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The morphing wing changes the geometrical shape seamlessly and continuously to improve the aerodynamic performance. Several studies have been conducted with variety of approaches. This study focuses on obtaining the optimum airfoil shape to maximize the lift-to-drag ratio or the maximum lift coefficient for the morphing wing using the corrugated flexible structures arranged in the rear side of the airfoil developed by one of the authors. The corrugated structure is connected to the upper skin to bend the airfoil as a morphing flap. During the morphing, the upper skin length is unchanged, but, on the other hand, the lower skin length is shorten. This airfoil morphing shape is modeled by using non-uniform rational basis spline (NURBS) curves with considering the above curve length condition, where the NURBS passing points are adopted as design variables. For numerical efficient optimization, sequential approximate optimization method using radial basis function (RBF) network is adopted. During the optimization, a design candidate will have an irrational wavy shape that brings an ill condition to the aerodynamic analysis, where the two-dimensional panel method is adopted as the aerodynamic analysis. To avoid the aerodynamic analysis for the violated design, the concept of tabu search is introduced to the RBF network. That is, if a violated wavy design candidate is selected during the optimization, the design is added to the tabu list without performing aerodynamic analysis. That is, the RBF network learning makes the searching region enclosed into the feasible design space and then the optimum design found rationally. The idea of the tabu search is also adopted to find the feasible initial design candidates. Through numerical examples, the validity of the proposed optimization method is demonstrated. Then, the optimum morphing wing shape is discussed.

Similar Papers
  • Research Article
  • Citations537

Three learning phases for radial-basis-function networks

  • May 01, 2001
  • Neural Networks
  • Friedhelm Schwenker +2
  • PDF
  • Research Article
  • Citations10

Differential radial basis function network for sequence modelling

  • Oct 13, 2021
  • Expert Systems with Applications
  • Kojo Sarfo Gyamfi +2
  • Conference Article
  • Citations2

An Efficient Method to Set RBF Network Paramters Based on SOM Training

  • Jun 01, 2010
  • Kazuhiko Yamashita +3
  • Conference Article
  • Citations4

Research on Missile storage reliability forecasting based on neural network

  • Aug 01, 2010
  • Haijian Chen +2
  • PDF
  • Book Chapter
  • Citations58

Firefly Meta-Heuristic Algorithm for Training the Radial Basis Function Network for Data Classification and Disease Diagnosis

  • Mar 16, 2012
  • Ming-Huwi Horng +3
  • Dissertation

Meta-cognitive sequential learning in RBF network for diagnosis of neurodegenerative diseases

  • Jan 01, 2014
  • Sateesh Babu Giduthuri
  • Research Article
  • Citations14

Adaptive Dynamic RBF Fuzzy Neural Controller Design with a Constructive Learning

  • Sep 01, 2011
  • International Journal of Fuzzy Systems
  • Chun‐Fei Hsu +2
  • Research Article
  • Citations4

Generalized [formula omitted]-sparse algorithms for constructing fault tolerant RBF networks

  • Aug 14, 2024
  • Neural Networks
  • Hiu-Tung Wong +3
  • Conference Article
  • Citations2

Learning method of RBF network based on FCM and ACO

  • Jul 01, 2008
  • Zhen Ziyang +3
  • Conference Article
  • Citations2

Multiresolutional training of RBF networks for enhanced approximation

  • Jul 25, 2001
  • O Ciftcioglu +2
  • Research Article
  • Citations17

An Improved Fast Training Algorithm for RBF Networks Using Symmetry-Based Fuzzy C-Means Clustering

  • Dec 01, 2008
  • Mathematika
  • Eng Aik Lim +1
  • Conference Article
  • Citations31

Unlocking Fast Reservoir Predictions via Non-Intrusive Reduced Order Models

  • Feb 18, 2013
  • Hector Klie
  • Conference Article
  • Citations2

Enhanced Multivariable TS Fuzzy Modeling in Neural Network Perspective

  • Jun 26, 2005
  • O Ciftcioglu +1
  • Book Chapter

Face Representation Using Averaged Wavelet, Micro Patterns and Recognition Using RBF Network

  • Jan 01, 2013
  • Thangairulappan Kathirvalavakumar +1
  • Research Article
  • Citations14

Integrated neural network model with pre-RBF kernels.

  • Jul 01, 2021
  • Science Progress
  • Hui Wen +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.