Prediction of flutter derivatives by artificial neural networks
β Scribed by Chern-Hwa Chen; Jong-Cheng Wu; Jow-Hua Chen
- Publisher
- Elsevier Science
- Year
- 2008
- Tongue
- English
- Weight
- 451 KB
- Volume
- 96
- Category
- Article
- ISSN
- 0167-6105
No coin nor oath required. For personal study only.
β¦ Synopsis
This study presents an approach using artificial neural networks (ANN) algorithm for predicting the flutter derivatives of rectangular section models without wind tunnel tests. Firstly, a database of flutter derivatives is identified from a back-propagation (BP) ANN model that is built using experimental dynamic responses of rectangular section models in smooth flow as the input/output data. Then, these limited sets of database are employed as input/output data to establish a prediction ANN frame model to further predict the flutter derivatives for other rectangular section models without conducting wind tunnel tests. The results presented indicate that this ANN prediction scheme works reasonably well. Therefore, instead of going through wind tunnel tests, this ANN approach provides a convenient and feasible option for expanding the flutter derivative database that can help to determine an appropriate basic shape of the bridge section in the preliminary design.
π SIMILAR VOLUMES
## Methanol-steam reformation in internal reforming fuel cell The kinetics of methanol-steam reformation were studied in an idealized tube reactor and a non-ideal internal reforming fuel cell. Methanol conversion in the IRFC was significantly less than in an ideal plug flow reactor, but for higher
## Abstract The neural network method was applied to the prediction of the content of protein secondary structure elements, including Ξ±βhelix, Ξ²βstrand, Ξ²βbridge, 3~10~βhelix, Οβhelix, Hβbonded turn, bend, and random coil. The βpairβcoupled amino acid compositionβ originally proposed by K. C. Chou