Structural Damage Alarm Utilizing Modified Back-Propagation Neural Networks.

Autor:	Dong, Xiaoma
Zdroj:	Intelligent Computing & Information Science (9783642181337); 2011, p273-278, 6p
Abstrakt:	Damage alarm is an important step among structure damage identification. Its objective is to evaluate the structure health. The existing damage alarm methods are mostly based on Back-Propagation Neural Networks without thinking over testing noise. Therefore, in order to avoid the disadvantages of conventional Back-Propagation Neural Networks, a modified Back-Propagation Neural Networks was proposed for structure damage alarm system in this paper. The experiment results of steel truss girder bridge show that the improved method is better than BPNN for structural damage alarm. [ABSTRACT FROM AUTHOR]
Databáze:	Complementary Index
Externí odkaz:	Zobrazit plný text záznamu