A Design Optimization Methodology Combining Artificial Neural Networks and Nonlinear programming Methods
碩士 === 元智工學院 === 機械工程學系 === 84 === This research developed a hybrid optimal design -- methodology by combining artificial neural network and nonlinear programming methods. In the process of optimization, the gradient base methods can become...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Online Access: | http://ndltd.ncl.edu.tw/handle/15586386343399541589 |
id |
ndltd-TW-084YZU00489030 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-084YZU004890302016-02-03T04:32:13Z http://ndltd.ncl.edu.tw/handle/15586386343399541589 A Design Optimization Methodology Combining Artificial Neural Networks and Nonlinear programming Methods 結合類神經網路與非線性規劃之工程最佳化設計 Huang, Chun-Ju 黃俊儒 碩士 元智工學院 機械工程學系 84 This research developed a hybrid optimal design -- methodology by combining artificial neural network and nonlinear programming methods. In the process of optimization, the gradient base methods can become very expensive or infeasible because of the difficulty to obtain the numerical data (e.g. FEM, CFD) or experimental results. Therefore, this research developed a method to solve the problem that the implicit functions have brought to the engineering design optimization process. The essence of this method is to use the learning ability of the ANN and the searching ability of the nonlinear programming algorithm with as far training sets as possible. With this approach, we do not need to calculate the gradients of the design variables of the first or second order methods which would conserve a lot of computational effect. The global learning and searching spirit of the proposed methodology are very suitable for the engineering optimal design and other optimization problems. Shuo-Jen Lee 李碩仁 學位論文 ; thesis 73 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 元智工學院 === 機械工程學系 === 84 === This research developed a hybrid optimal design -- methodology
by combining artificial neural network and nonlinear programming
methods. In the process of optimization, the gradient base
methods can become very expensive or infeasible because of the
difficulty to obtain the numerical data (e.g. FEM, CFD) or
experimental results. Therefore, this research developed a
method to solve the problem that the implicit functions have
brought to the engineering design optimization process. The
essence of this method is to use the learning ability of the ANN
and the searching ability of the nonlinear programming algorithm
with as far training sets as possible. With this approach, we do
not need to calculate the gradients of the design variables of
the first or second order methods which would conserve a lot of
computational effect. The global learning and searching spirit
of the proposed methodology are very suitable for the
engineering optimal design and other optimization problems.
|
author2 |
Shuo-Jen Lee |
author_facet |
Shuo-Jen Lee Huang, Chun-Ju 黃俊儒 |
author |
Huang, Chun-Ju 黃俊儒 |
spellingShingle |
Huang, Chun-Ju 黃俊儒 A Design Optimization Methodology Combining Artificial Neural Networks and Nonlinear programming Methods |
author_sort |
Huang, Chun-Ju |
title |
A Design Optimization Methodology Combining Artificial Neural Networks and Nonlinear programming Methods |
title_short |
A Design Optimization Methodology Combining Artificial Neural Networks and Nonlinear programming Methods |
title_full |
A Design Optimization Methodology Combining Artificial Neural Networks and Nonlinear programming Methods |
title_fullStr |
A Design Optimization Methodology Combining Artificial Neural Networks and Nonlinear programming Methods |
title_full_unstemmed |
A Design Optimization Methodology Combining Artificial Neural Networks and Nonlinear programming Methods |
title_sort |
design optimization methodology combining artificial neural networks and nonlinear programming methods |
url |
http://ndltd.ncl.edu.tw/handle/15586386343399541589 |
work_keys_str_mv |
AT huangchunju adesignoptimizationmethodologycombiningartificialneuralnetworksandnonlinearprogrammingmethods AT huángjùnrú adesignoptimizationmethodologycombiningartificialneuralnetworksandnonlinearprogrammingmethods AT huangchunju jiéhélèishénjīngwǎnglùyǔfēixiànxìngguīhuàzhīgōngchéngzuìjiāhuàshèjì AT huángjùnrú jiéhélèishénjīngwǎnglùyǔfēixiànxìngguīhuàzhīgōngchéngzuìjiāhuàshèjì AT huangchunju designoptimizationmethodologycombiningartificialneuralnetworksandnonlinearprogrammingmethods AT huángjùnrú designoptimizationmethodologycombiningartificialneuralnetworksandnonlinearprogrammingmethods |
_version_ |
1718177124561453056 |