Digital twins-boosted intelligent maintenance of ageing bridge hangers exposed to coupled corrosion–fatigue deterioration

• Published in: Automation in construction Vol. 167; p. 105697
• Main Authors: Heng, Junlin, Dong, You, Lai, Li, Zhou, Zhixiang, Frangopol, Dan M.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.11.2024
• Subjects: Ageing infrastructure; Corrosion–fatigue (C[sbnd]F); Digital twins; Intelligent maintenance; Partially Observable Markov Decision Processes (POMDPs); Steel bridge hanger; Corrosion–fatigue (CF); Ageing infrastructure; Digital twins; Partially Observable Markov Decision Processes (POMDPs); Intelligent maintenance; Steel bridge hanger
• ISSN: 0926-5805
• DOI: 10.1016/j.autcon.2024.105697

The corrosion–fatigue coupled deterioration of ageing steel bridge hangers presents significant structural challenges, demanding rigorous condition assessments and timely maintenance interventions. This paper introduces a framework of digital twins-boosted intelligent maintenance (DTIM) tailored for ageing hangers, integrating the prediction model, monitoring data and inspection results. The DTIM features a suite of algorithms adaptation and innovations, including dynamic Partially Observable Markov Decision Processes (POMDP), Asynchronous Advantage Actor Critic (A3C), and Bayesian Dynamic Linear Models (BDLM). The DTIM emphasises regular early-life repairs, strategic inspections, and timely replacements towards life-end, tailored to the condition of specific bridge hangers in the case study presented. By coordinating actions across hangers, the DTIM enables opportunistic maintenance to further optimise resource allocation. The output highlights digital twins in exploring the add-on value of monitoring and inspection for the proactive and sustainable maintenance of ageing infrastructure, promising enhanced structural integrity and serviceability in a cost-effective and well-informed manner. •A digital twins-boosted intelligent maintenance framework is tailored for bridge hangers.•Probabilistic prognosis is made by integrating prediction, monitoring and inspection.•Dynamic POMDP is proposed to incorporate monitoring data and time-variant effects.•A3C reinforcement learning is adapted to guide optimal maintenance after prognosis.•The case study promises prominent cost saving, lifespan extension and risk mitigation.