Machine learning methods for predicting the durability of concrete materials: A review

Evaluating the durability of concrete materials through experimental research is a lengthy, costly, and inefficient process. Traditional empirical formulas offer limited accuracy in predicting durability and fail to guide concrete proportioning based on performance. Consequently, it is crucial to develop new, efficient tools for material quality control and performance prediction. This can be achieved by elucidating the process involved in constructing machine learning (ML) models, delineating the fundamental operating principles and benefits of prevalent algorithms, and critically reviewing the ML-based durability index prediction algorithms and their practical applications and future directions. Furthermore, this study utilizes CiteSpace software to assess the current state of ML research in concrete durability prediction. A comprehensive analysis of the publication volume, research focal points, and emerging trends is conducted. This not only furnishes references for future research but also aims to facilitate more effective utilization of this technology, thereby fostering the development of innovative construction materials and advancing the goal of environmental sustainability.