Journal
CONSTRUCTION AND BUILDING MATERIALS
Volume 175, Issue -, Pages 562-569Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.conbuildmat.2018.04.169
Keywords
Recycled concrete; Compressive strength; Prediction model; Deep learning; Convolution neural network
Categories
Funding
- Natural Science Foundation of China [51577046, 51767006, 51662008]
- State Key Program of National Natural Science Foundation of China [51637004]
- National Key Research and Development Plan Important Scientific Instruments and Equipment Development [2016YFF0102200]
- Equipment Research Key Project in Advance [41402040301]
- Natural Science Foundation of Jiangxi Province [20171BAB206045]
- Science and Technology Project of Education Department of Jiangxi Province [GB160491, G11170378]
Ask authors/readers for more resources
Considering on the current difficulties of predicting the compressive strength of recycled aggregate concrete, this paper proposes a prediction model based on deep learning theory. First, the deep features of water-cement ratio, recycled coarse aggregate replacement ratio, recycled fine aggregate replacement ratio, fly ash replacement ratio as well as their combinations are learned through a convolutional neural networks. Then, the prediction model is developed using the softmax regression. 74 sets of concrete block masonry with different mix ratios are used in the experiments and the results show that the prediction model based on deep learning exhibits the advantages including higher precision, higher efficiency and higher generalization ability compared with the traditional neural network model, and could be considered as a new method for calculating the strength of recycled concrete. (C) 2018 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available