ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING APPLICATIONS IN STRUCTURAL ENGINEERING: A COMPREHENSIVE REVIEW OF RECENT ADVANCES AND FUTURE DIRECTIONS

Abstract

Artificial intelligence (AI) and machine learning (ML), including deep learning and evolutionary algorithms, are transforming traditional design, analysis, and maintenance processes in structural engineering (Kurcjusz and Das, 2025). This comprehensive literature review synthesizes recent advances across five key application domains: structural health monitoring, damage detection, design optimization, computational mechanics, and seismic assessment. Machine learning techniques have demonstrated significant potential for improving computational accuracy and precision of simulations in structural system identification, structural design, and prediction applications (Etim et al., 2024). Artificial Intelligence-Aided Design (AIAD) has greatly alleviated challenges faced by structural design, showing great promise in design concept generation, enhancing efficiency while simplifying the workflow, reducing the design cycle time and cost, and achieving global optimal design (Ao, Li and Duan, 2025). However, widespread adoption remains constrained by data quality limitations, model interpretability challenges, validation framework gaps, and integration barriers with existing systems. While AI/ML adoption in civil engineering faces challenges including data availability, computational complexity, model interpretability, and integration with traditional systems (Jain et al., 2025), emerging solutions such as explainable AI (XAI), physics-informed neural networks (PINNs), and digital twin technologies offer pathways forward. This review integrates recent advances from 2020–2026, identifies critical research gaps, and outlines future directions for implementing trustworthy, efficient, and sustainable AI/ML systems in structural engineering practice.