State-of-the-art AI-based computational analysis in civil engineering

With the informatization of the building and infrastructure industry, conventional analysis methods are gradually proving inadequate in meeting the demands of the new era, such as intelligent synchronization and real-time simulation. Artificial intelligence (AI) technology has emerged as a promising alternative due to its high expressiveness, efficiency, and scalability. This has given rise to a new research field of AI-based computation in civil engineering. In this study, a state-of-the-art review of the research on material and structural analyses using AI technology in civil engineering was performed to provide a general introduction to the current progress. The research was classified into static feature studies, dynamic feature studies, and composite feature studies according to the problem inputs. The general methodology, commonly used AI models, and representative applications of each research category were elaborated. On these bases, the strengths and weaknesses of current studies were discussed. To demonstrate the accuracy and efficiency of AI models in comparison with conventional numerical methods, a concrete example of an end-to-end deep learning framework for structural analysis was highlighted. Finally, we suggested four open problems from the perspective of engineering applications, indicating the major challenges and future research directions regarding AI-based computational analysis in civil engineering.