Physics-Informed Machine Learning for Structural Safety, Reliability, and Lifecycle Management

Submission Deadline: 30 June 2027 View: 77 Submit to Special Issue

Guest Editor(s)

Prof. Dr. Qiang Zhang

Email: 2t@gxu.edu.cn

Affiliation: School of Civil Engineering and Architecture, Guangxi University, Nanning, China

Homepage:

Research Interests: structural reliability, uncertainty quantification, structural dynamics

Assist. Prof. Luchuan DING

Email: luchuanding@tongji.edu.cn

Affiliation: Department of Structural Engineering, Tongji University, Shanghai, China

Homepage: https://orcid.org/0000-0001-5870-3276

Research Interests: structural robustness or progressive collapse, structural reliability and intelligent optimal design, disaster resilience of infrastructure systems under multiple hazards, machine learning, structural seismic isolation and control

Prof. Dr. Lei Xu

Email: leix_2013@163.com

Affiliation: School of Civil Engineering, Central South University, Changsha, China

Homepage:

Research Interests: system dynamics, stochastic analysis, smart management and maintenance

Dr. Wenliu Xu

Email: xuwenliu92@qq.com

Affiliation: School of Urban Construction, Jiangxi Normal University, Nanchang, China

Homepage:

Research Interests: progressive collapse, seismic resilience, prefabricated structure

Dr. Xiangwei Li

Email: lxwlxw123666@163.com

Affiliation: Guangxi Transportation Science and Technology Group Co., Ltd., Nanning, China

Homepage:

Research Interests: risk assessment of civil infrastructure, health monitoring of bridge structures, reliability analysis of engineering systems

Summary

Modern engineering structures face escalating demands across structural safety, reliability, lifecycle management and economic viability, rendering traditional methodologies increasingly insufficient. In this evolving landscape, advanced machine learning techniques offer opportunities to reshape structural engineering—enabling smarter, highly adaptive, and sustainable design, safety assessment, reliability-based optimization, lifecycle management, and decision-making.

Contributions may cover theoretical developments, AI-driven computational models, material modelling and multi-scale simulations, disaster prevention for new energy infrastructure, structural strengthening and reinforcement technologies, and lifecycle smart maintenance strategies.

By conducting high-quality research, the safety and resilience of infrastructure and urban communities will be enhanced, and lifecycle costs will also be reduced. Researchers are invited to submit work that addresses challenges and opportunities in this rapidly evolving field.

The themes of this special issue include but not limited to:
-Physics-informed machine learning methods for structural safety analysis
-AI-driven computation models for structural reliability
-Material modelling and multi-scale simulations
-Disaster prevention for new energy infrastructure
-Advanced numerical simulation of dynamic behavior of railway infrastructure
-Building resilience and sustainability
-Structural strengthening and reinforcement technologies
-Lifecycle smart maintenance strategies

Keywords