機械学習を用いたデジタル打音検査によるコンクリート構造物内部欠陥状態の予測

抄録

As an evaluation method for concrete structures, it is believed that information from hammering inspections can be digitized by AE sensor and predicted by machine learning. In this study, XGBoost, which can visualize the importance of input factors, was used to predict the internal condition of concrete structures. The results of hammering inspections of concrete specimens were used for learning, and predictions were made for four types of concrete structures: reinforced concrete, spiral sheathing, expanded polystyrene and unreinforced concrete. Through the forecasting results on this data set, an evaluation was conducted sampling techniques were discussed.