Emergency Decision-Making System for the Large-Scale Infrastructure: A Case Study of the South-to-North Water Diversion Project
Huimin Li, Feng Li, Jian Zuo, Jiabin Sun, Chenghui Yuan, Li Ji, Ying Ma, Yao Desheng
Abstract
Large-scale infrastructure operates in a complex and uncertain environment. When an unexpected safety accident occurs, efficient emergency decision-making plays a crucial role in safe operation. Case-based reasoning (CBR) provides an effective tool in emergency response decision-making. However, case retrieval efficiency and missing values for case attributes present significant challenges to CBR. Firstly, in this study, a unified framework representation method is constructed for accident cases of large-scale infrastructure. Secondly, an inductive indexing approach is used to preclassify cases according to key attributes of the cases in order to improve retrieval efficiency. Thirdly, this study proposes a two-layer integrated structure and attributes similarity algorithm based on the K-nearest neighbors (KNN) method in a bid to overcome the missing attribute values of the cases. Fourthly, the emergency decision-making system is developed for the large-scale infrastructure. Finally, a case study of the South-to-North Water Diversion Project in China is undertaken to verify the proposed methods and computing system. This study provides a valuable decision-making approach for operational safety-related emergency management of large-scale infrastructure.