A time-series deep learning model for predicting concrete shrinkage and creep verified with in-situ and laboratory test data

• Published in: Construction & building materials Vol. 447; p. 138140
• Main Authors: Fan, Zihao, Zhan, Yulin, Xiang, Tianyu, Huang, Yuanyuan, Li, Binghui, Xiang, Hui, Li, Yingxiong
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 11.10.2024
• Subjects: Deep learning; Field test; Long-term prediction; Prediction model; Short-term prediction; Shrinkage and creep of concrete; Deep learning; Short-term prediction; Field test; Shrinkage and creep of concrete; Prediction model; Long-term prediction
• ISSN: 0950-0618
• DOI: 10.1016/j.conbuildmat.2024.138140

This paper proposed a time series prediction method for concrete shrinkage and creep based on deep learning and the accuracy of the method was verified by field tests. Based on the experiment data in the Northwestern University (NU database), a deep learning model considering the material, environment, and history was constructed by integrating Gated Recurrent Units and Self-Attention mechanism (GSA model). To validated the model, short-term indoor and outdoor field tests of concrete shrinkage and creep were conducted. The proposed GSA model outperformed the LSTM model for both creep and shrinkage predictions. Moreover, the comparison between the GSA model prediction and the outdoor test data indicated that the model can accurately capture the real-time outdoor temperature and humidity variation through historical data. To predict the ten-year shrinkage and creep of concrete, a recursive multi-step method was proposed to extrapolate the short-term predictions of the GSA model. The effectiveness of the recursive multi-step method was validated against the long-term test data in the NU database. Overall, the proposed GSA model demonstrated high accuracy in both short-term and long-term predictions. •The proposed GSA model outperforms the LSTM model in predicting concrete shrinkage and creep.•The GSA model demonstrates superior accuracy over the code specifications in both indoorand outdoor environments.•A recursive multi-step approach for long-term prediction is proposed and validated with the tests from the NU database.