Title:
Prediction of Transfer Length of Prestressing Strands
Using Neural Networks
Author(s):
Mehmet M. Kose
Publication:
Structural Journal
Volume:
104
Issue:
2
Appears on pages(s):
162-169
Keywords:
prestressed concrete; test; transfer length.
DOI:
10.14359/18528
Date:
3/1/2007
Abstract:
In this study, the efficiency of an artificial neural network (ANN) in predicting the transfer length of prestressing strands in prestressed concrete beams was investigated. An ANN is an information processing system that imitates the way biological nervous systems, such as the brain, process information. The main element of neural network is the structure of the information processing system. It is composed of highly interconnected processing neurons and has the ability of self-learning from the examples. The transfer results from various research projects have been collected to train and test the ANN model. Each parameter (that is, ratio of the area of prestressing strand to the area of concrete Aps/Ac , surface condition of prestressing strand [rusty or bright], diameter of prestressing strand, percentage of debonded prestressing strands, effective prestress, plateau in strain profile, and concrete strength at the time of measurement) affecting the transfer length of prestressing strands was arranged in an input vector and a corresponding output vector that includes the measured transfer length of prestressing strands. Results showed that the ANN model developed is capable of accurately predicting the transfer lengths used in the training and testing phase of the study.