Developing an artificial neural network model to predict the durability of the RC beam by machine learning approaches

Eco-Transformation of Construction: Harnessing Machine Learning and Shap for Crumb Rubber Concrete Sustainability

“…ML has emerged as an effective tool for analyzing complex data and identifying patterns that are difficult to detect using conventional statistical techniques. ML has been used in civil engineering to optimize the design of mixes of concrete [43], predict the strength and durability of concrete structures [44,45], and assess the effectiveness of different construction materials [46,47]. In this research paper, we present a new approach based on the SHAP framework, which allows us to evaluate the interactions between raw materials in CRC using ML.…”

Deep learning-based prediction for time-dependent chloride penetration in concrete exposed to coastal environment

“…With the increasing accumulation of experimental data, machine learning methods have become widely utilized for data analysis and prediction. Some commonly employed methods include Support Vector Machine (SVM) and Artificial Neural Network (ANN) [ [3] , [4] , [5] , [6] , [7] , [8] , [9] , [10] , [11] ]. Zhu et al [ 7 ] conducted an in-depth analysis of critical chloride concentration using the ANN method by summarizing and organizing published literature data.…”

“…Zhu et al [ 7 ] conducted an in-depth analysis of critical chloride concentration using the ANN method by summarizing and organizing published literature data. Yu [ 9 ] analyzed the impact of water-cement ratio, concrete cover depth, coarse aggregate volume, and ambient temperature and humidity on chloride diffusion using machine learning methods such as decision tree (DT), linear regression (LR), Back Propagation (BP) neural network, random forest (RF), and ridge regression (RR). Song and Kwon [ 10 ] developed a neural network model considering eight input parameters, including water-cement ratio and mineral admixture, and successfully predicted chloride diffusion coefficients with an average difference of approximately 7.5% compared to measured values.…”