材料施工
沖縄県のレディーミクストコンクリート温度の通年実態調査と機械学習によるコンクリート温度推定
2023 年 29 巻 72 号 p. 633-638
詳細
2023 年 29 巻 72 号 p. 633-638
In this study, we surveyed ready-mixed concrete shipped in Okinawa Prefecture from June 2020 to December 2021 to investigate the actual condition of concrete at the time of mixing and unloading using concrete formulation, material temperature, environmental and transportation information. In addition, Random Forest and LightGBM were used to learn to predict the concrete temperature at the time of mixing and unloading from each factor in the collected data. In addition, the effect of features on the prediction accuracy of the learning model was evaluated by Partial Dependence Plot.
