Substructure Online Test Using Parallel Hysteresis Modeling by Neural Network
Abstract eng: In general, hysteresis models that are applied to a numerical analysis part of substructure online tests do not refer directly to the experimental behavior of the members or subassemblage under loading tests. The objective of this study is to develop a new experimental technique for substructure online tests based on nonlinear hysteretic characteristics estimated with a neural network. A new learning algorithm for the network applicable to substructure online tests is proposed, focusing on input layer variables and their scaling method, and its validity is examined through several numerical and experimental investigations. The results show that the proposed testing scheme successfully reproduces the dynamic behavior of the model structure.
Contributors:
Conference Title:
Conference Title:
14th World Conference on Earthquake Engineering
Conference Venue:
Bejing (CN)
Conference Dates:
2008-10-12 / 2008-10-17
Rights:
Text je chráněný podle autorského zákona č. 121/2000 Sb.
Record appears in:
Record created 2014-12-05, last modified 2014-12-05
guest ::
