Structural Engineering

This study explores the transformative impact of Machine Learning (ML), Deep Learning (DL), and Artificial Intelligence (AI) in structural engineering, focusing on their applications in information, process, and design engineering. It highlights ML’s integration with IoT for real-time structural health monitoring, and its role in performance evaluation and multi-objective optimization. The research emphasizes the potential of these technologies to enhance structural integrity, durability, and cost-efficiency. It calls for further development of robust algorithms, improved data access, and continued exploration to fully realize ML, DL, and AI's potential in revolutionizing structural engineering practices.

This paper presents a comprehensive review of how machine learning (ML) is transforming modeling and simulation in structural engineering. As high-fidelity simulations demand greater computational resources, ML techniques—such as enhanced probabilistic neural networks and dynamic ensemble learning—offer faster, more accurate alternatives. The survey covers ML applications in computational mechanics, structural health monitoring, design, stress and failure analysis, material modeling, and optimization. By leveraging AI advancements and abundant data, ML-based methods are becoming practical solutions for complex, resource-intensive problems, positioning them as powerful alternatives to traditional simulation approaches in structural engineering.

Explores how AI—including deep learning, neural networks, swarm optimization, and fuzzy logic—can transform structural engineering. It highlights applications like structural health monitoring, modular construction decisions, and vibration control. The study discusses AI’s challenges and limitations but emphasizes its vast potential to improve efficiency, safety, and sustainability. It concludes that advancing AI in structural engineering requires ongoing research and strong collaboration between academia and industry to fully harness its benefits.

This review highlights four structural engineering strategies—crystal engineering, 2D engineering, heterostructure engineering, and MOF derivatives engineering—to enhance MOFs’ CO2 reduction performance. The insights aim to guide the rational design of efficient MOF materials and encourage further research to overcome current limitations in catalytic CO2 reduction applications.

The 19th-century Industrial Revolution transformed the US but often neglected environmental and human health impacts. The Linville Creek Bridge (1898) in Virginia is a rare example where community input shaped its design, resembling modern human-centered Design Thinking. This empathetic approach led to a unique truss bridge that met local needs and gained historic value. The case highlights how integrating social dimensions in structural engineering—then and now—can create lasting, successful infrastructure that serves communities effectively. It offers valuable lessons for 21st-century engineers on blending technical and human-centered design principles.

This study addresses concrete’s high environmental impact through structural optimization, demonstrated in the Concrete Girder Optimization Competition 2021. Two optimized concrete girder designs—one with internal and one with external reinforcement—based on strut-and-tie modeling were evaluated. Key findings include the importance of properly interpreting topology optimization for structural performance and the significant environmental impact of reinforcement mass. Numerical re-simulation of girders provides a modeling basis for future research. Compared to conventional designs, the optimized girders achieved over 30% greater resource efficiency, balancing load capacity with reduced environmental impact.