AUTHOR=Dang Pengliang , Li Zeliang , Zou Dehai , Li Hangjun , Cheng Zilong , Chang Le , Lu Yadong 

TITLE=Monitoring data-driven dynamic safety assessment framework for deep foundation pit construction based on grey clustering and moment method

JOURNAL=Frontiers in Earth Science

VOLUME=Volume 13 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/earth-science/articles/10.3389/feart.2025.1583402

DOI=10.3389/feart.2025.1583402

ISSN=2296-6463

ABSTRACT=To address the safety challenges of deep foundation pit construction under complex conditions, this study proposes a dynamic assessment framework based on grey clustering theory and a moment estimation composite weighting method. A three-level indicator system was constructed, integrating subjective and objective weights through order relationship and entropy weight methods. Grey clustering was employed to classify real-time monitoring data and assess safety levels dynamically. Application to a large-scale water diversion shaft project in Shenzhen verified the model’s effectiveness, with assessment results closely matching observed risks during excavation. The framework improves accuracy and responsiveness in uncertain monitoring environments and supports intelligent risk management.