scholarly journals Simultaneous partial topology and size optimization of a wing structure using ant colony and gradient based methods

2011 ◽  
Vol 43 (4) ◽  
pp. 433-446 ◽  
Author(s):  
Wei Wang ◽  
Shijun Guo ◽  
Wei Yang
Keyword(s):  
Ant Colony ◽  
Size Optimization ◽  
Gradient Based ◽  
Wing Structure

Ant Colony Optimization Applied to the Training of a High Order Neural Network with Adaptable Exponential Weights

2020 ◽  
pp. 82-95
Author(s):  
Ashraf M. Abdelbar ◽  
Islam Elnabarawy ◽  
Donald C. Wunsch II ◽  
Khalid M. Salama
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Ant Colony Optimization ◽  
High Order ◽  
Ant Colony ◽  
Ant Colony Optimization Algorithm ◽  
Test Set ◽  
Benchmark Datasets ◽  
Gradient Based ◽  
High Order Neural Network

High order neural networks (HONN) are neural networks which employ neurons that combine their inputs non-linearly. The HONEST (High Order Network with Exponential SynapTic links) network is a HONN that uses neurons with product units and adaptable exponents. The output of a trained HONEST network can be expressed in terms of the network inputs by a polynomial-like equation. This makes the structure of the network more transparent and easier to interpret. This study adapts ACOℝ, an Ant Colony Optimization algorithm, to the training of an HONEST network. Using a collection of 10 widely-used benchmark datasets, we compare ACOℝ to the well-known gradient-based Resilient Propagation (R-Prop) algorithm, in the training of HONEST networks. We find that our adaptation of ACOℝ has better test set generalization than R-Prop, though not to a statistically significant extent.

Ant Colony Optimization Applied to the Training of a High Order Neural Network with Adaptable Exponential Weights

2016 ◽  
pp. 362-374 ◽  
Author(s):  
Ashraf M. Abdelbar ◽  
Islam Elnabarawy ◽  
Donald C. Wunsch II ◽  
Khalid M. Salama
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Ant Colony Optimization ◽  
High Order ◽  
Ant Colony ◽  
Ant Colony Optimization Algorithm ◽  
Test Set ◽  
Benchmark Datasets ◽  
Gradient Based ◽  
High Order Neural Network

High order neural networks (HONN) are neural networks which employ neurons that combine their inputs non-linearly. The HONEST (High Order Network with Exponential SynapTic links) network is a HONN that uses neurons with product units and adaptable exponents. The output of a trained HONEST network can be expressed in terms of the network inputs by a polynomial-like equation. This makes the structure of the network more transparent and easier to interpret. This study adapts ACOR, an Ant Colony Optimization algorithm, to the training of an HONEST network. Using a collection of 10 widely-used benchmark datasets, we compare ACOR to the well-known gradient-based Resilient Propagation (R-Prop) algorithm, in the training of HONEST networks. We find that our adaptation of ACOR has better test set generalization than R-Prop, though not to a statistically significant extent.

Concept Design of Composite Aircraft Wing

2010 ◽  
Author(s):  
J. S. Rao ◽  
S. Kiran
Keyword(s):  
Topology Optimization ◽  
Shape Optimization ◽  
Weight Reduction ◽  
Size Optimization ◽  
Material Distribution ◽  
Concept Design ◽  
Aircraft Wing ◽  
Size And Shape ◽  
Structure Topology ◽  
Wing Structure

This paper is concerned with an optimal concept design of aircraft wing from an airfoil. The airfoil itself is generated from CFD studies but there is no baseline of the wing structure. Topology optimization is recently applied for weight reduction given an operating baseline structure; here it is demonstrated that this optimization can be used to derive the concept of the wing structure directly. The optimized concept design is realized in to CAD and then a composite free-size optimization is performed to determine material distribution and ply drop regions etc. Finally a composite size and shape optimization is done and the ribs thus realized are presented.

Application of a Morphing Wing Technology on Hydra Technologies Unmanned Aerial System UAS-S4

2014 ◽  
Author(s):  
Oliviu Şugar Gabor ◽  
Antoine Simon ◽  
Andreea Koreanschi ◽  
Ruxandra Botez
Keyword(s):  
Unmanned Aerial System ◽  
Bfgs Method ◽  
Morphing Wing ◽  
Aerodynamic Coefficients ◽  
Flexible Skin ◽  
Bee Colony ◽  
Actuation System ◽  
Gradient Based ◽  
Wing Structure ◽  
Rigid Wing

The paper describes the application of a morphing wing technology on the wing of an Unmanned Aerial System (UAS). The morphing wing concept works by replacing a part of the rigid wing upper and lower surfaces with a flexible skin whose shape can be dynamically changed using an actuation system placed inside the wing structure. The aerodynamic coefficients are determined using the fast and robust XFOIL panel/boundary-layer codes, as the optimal displacements are calculated using an original, in-house optimisation tool, based on a coupling between the relatively new Artificial Bee Colony Algorithm, and the classical, gradient-based Broyden-Fletcher-Goldfarb-Shanno (BFGS) method. All the results obtained by the in-house optimisation tool have been validated using robust, commercially available optimization codes. Three different optimization scenarios were performed and promising results have been obtained for each. The numerical results have shown substantial aerodynamic performance increases obtained for different flight conditions, using the proposed morphing wing concept.

Sign in / Sign up

Export Citation Format

Share Document