Title :
Prediction of Concrete Carbonization Depth Based on DE-BP Neural Network
Author :
Bu, Narui ; Yang, Guoli ; Zhao, Hui
Abstract :
Based on the DE-BP (Back Propagation-Differential Evolution) neural network, the predicting model of concrete carbonization depth is presented. The precision of the model is checked using the monitoring data. The comparisons between the predicted results of the three models (BP model, GA-BP model and DE-BP model) and the monitoring data show that the precision of the present algorithm is higher with the maximum relative error being 2.8%.
Keywords :
backpropagation; civil engineering computing; concrete; genetic algorithms; neural nets; BP model; DE-BP model; GA-BP model; back propagation differential evolution neural network; concrete carbonization depth prediction; monitoring data; Biological cells; Civil engineering; Concrete; Information technology; Intelligent networks; Mathematical model; Monitoring; Neural networks; Predictive models; Production; DE-BP neural network; concrete carbonization depth; prediction;
Conference_Titel :
Intelligent Information Technology Application, 2009. IITA 2009. Third International Symposium on
Conference_Location :
Nanchang
Print_ISBN :
978-0-7695-3859-4
DOI :
10.1109/IITA.2009.252
