Data-Driven Decision Algorithm for Open Caisson Foundation Construction

Abstract

The accuracy of instructions for the extraction of large open caissons directly affects the construction quality and safety. This study is focused on developing a smart construction methodology for predicting open caisson excavation instructions. The proposed approach aims to reduce the errors in excavation instructions attributable to the subjective and varying experiences of decision-makers. The multilabel classification task of predicting the instructions of large open caisson excavation is accomplished through the problem analysis. The study conducted a comparative analysis of a multilayer perceptron model, a classifier chain model, and a multilabel K-nearest neighbor model (MLKNN) based on Hamming loss and accuracy. The results revealed that MLKNN exhibits significant differences from the other models and is most suitable for predicting open caisson excavation instructions. Furthermore, the traditional MLKNN model was improved by refining the normalization and distance measurement methods for the open caisson scenario. The prediction accuracy of the improved MLKNN model is 89.04% for the excavation instructions and 98.63% for the nonexcavation decisions. The successful prediction of excavation instructions for a large open caisson can compensate for the lack of data mining capability of the existing monitoring system. This can reduce construction risks. Finally, this study discussed the robustness of the improved MLKNN in a real project, highlighting the model’s high accuracy during the midstage of open caisson construction.