PERFORMANCE-BASED PREDICTIVE ANALYTICS OF SHIELD TUNNELS

摘要

An ageing infrastructure system like shield tunnel often contains a wide variety of potential deficiencies such as seepage, spalling and crack.Scientific maintenance methodologies are therefore specially needed to enhance system reliability and safety, maintain service conditions, reduce maintenance manpower, spares, and repair costs, eliminate scheduled inspections, and maximize lead time for maintenance and parts procurement.This paper presents a comprehensive methodology for aggressive inspection and performance based predictive maintenance of a shield tunnel.A system engineering framework is proposed for predictive maintenance of a tunnel structure.Based on advanced probabilistic modeling, a systemlevel lifing analysis method is proposed for proactive maintenance of the tunnel system.The method includes data preprocessing, risk model establishment, quantitative model validation, empirical lifing analysis, and system-level maintenance schedule.The empirical lifing analysis involves both statistical risk prediction and damage accumulation models for service limit determination, system-level risk analysis, and system-level conditional risk for maintenance schedule.The proposed methodology is demonstrated with the inspection data for six typical deficiencies observed in real-world shield tunnels consisting of prefabricated lining rings.