Enhancing mechanical properties and slope stability of fibre-reinforced concrete (FRC) and strength prediction using machine learning

Fibre-reinforced concrete (FRC) has emerged as a promising material for enhancing slope stability and mechanical properties in civil engineering applications. This paper presents an analysis of the use of Jute fibre-reinforced concrete in slope stabilization and mechanical performance improvement and predicts the strength by a machine learning model. The paper discusses the rationale behind using FRC, highlighting its ability to mitigate slope instability by providing additional tensile strength and crack resistance compared to traditional concrete. The incorporation of jute fibres in concrete matrices significantly enhances the material’s performance under various loading conditions. The study delves into the mechanical properties of FRC, focusing on its flexural strength, compressive strength, and toughness. Testing methods, including Tensile tests and compression tests, are employed to evaluate and compare the mechanical behaviour of FRC with conventional concrete. Furthermore, the paper examines the influence of fibre type, content, aspect ratio, and distribution on the mechanical properties of FRC. It discusses the optimal combinations of fibres and concrete mix designs to achieve superior performance in terms of strength, durability, and crack resistance. In addition to mechanical properties, the study explores the effectiveness of FRC in slope stabilization. The Machine Learning Model for Fibre-Reinforced Concrete (FRC) Strength Prediction employs the K-Nearest Neighbors (KNN) algorithm. KNN utilizes data points’ proximity to predict the strength of FRC, making it a valuable tool for predictive modelling in concrete engineering and construction applications. The findings highlight the potential of FRC as a sustainable and cost-effective solution for addressing challenges related to slope stability and infrastructure durability in geotechnical engineering.