Application of artificial neural networks to the prediction of minor axis steel connections
UNSPECIFIED (1997) Application of artificial neural networks to the prediction of minor axis steel connections. In: 3rd International Conference in the Application of Artificial Intelligence to Civil and Structural Engineering, AUG 17-19, 1993, EDINBURGH, SCOTLAND.Full text not available from this repository.
In steel frames, it is usually the minor-axis beam-to-column connections that govern restraint to the columns against buckling. There is, however, no generally accepted method to predict the behaviour of such connections. To clarify the response, a series of tests has been performed, in which significant parameters have been systematically varied. The results have been used to train an artificial neural network (ANN) to predict bi-linear moment-rotation characteristics for minor-axis connections. The paper describes the test programme, the choice of ANN and the result for each connection, based on learning from 20 other connections. The results are found to provide approximations to the experimental response that are satisfactory for use in structural engineering design. (C) 1997 Civil-Comp Ltd and Elsevier Science Ltd.
|Item Type:||Conference Item (UNSPECIFIED)|
|Subjects:||Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
T Technology > TA Engineering (General). Civil engineering (General)
|Journal or Publication Title:||COMPUTERS & STRUCTURES|
|Publisher:||PERGAMON-ELSEVIER SCIENCE LTD|
|Number of Pages:||8|
|Page Range:||pp. 685-692|
|Title of Event:||3rd International Conference in the Application of Artificial Intelligence to Civil and Structural Engineering|
|Location of Event:||EDINBURGH, SCOTLAND|
|Date(s) of Event:||AUG 17-19, 1993|
Actions (login required)