Future Prospects and Recent Advancements in Machine Learning for Assessing the Service Life and Durability of Reinforced Concrete Buildings

Abstract

For necessary action to be taken in a timely and economical way, accurate service-life forecast of buildings is essential. But the oversimplified assumptions of the traditional prediction models result in approximations that are not correct. The capacity of “machine learning” to overcome the shortcomings of traditional future models is reviewed in this research. This can be attributed to its capacity to represent the intricate physical and chemical dynamics of the degradation mechanism. The study also summarizes other studies that suggested “machine learning” may be used to support the assessment of reinforced concrete building durability. Comprehensive discussion is also held regarding the benefits of using machine learning to evaluate the service life and durability of “reinforced concrete” buildings. It is becoming easier to apply “machine learning for durability and service-life” evaluation thanks to the growing trend of wireless sensors gathering an increasing amount of in-service data. In light of the most recent developments and the state of the art in this particular field, the presentation ends by suggesting future directions.