Exploring steel fiber integration in dry lean concrete: predictive analysis of compressive strength and performance via machine learning

Abstract

This research investigates the effects of varying percentages of steel fibers (1%, 1.5%, 2.5%, 3.5%, 4.5%) on the compressive strength of Dry Lean Concrete (DLC). The study aims to identify the optimal steel fibre content for enhancing compressive strength and explore the use of machine learning techniques for performance prediction. The experimental program involved casting and testing DLC specimens with different steel fibre contents. The compressive strength was evaluated at 7, 14, and 28 days. Machine learning methods like as linear regression, decision trees, and random forest were used to predict compressive strength while accounting for fiber content and curing period. The results indicate a significant improvement in compressive strength with increasing fibre content up to 3.5%, beyond which the strength gain diminishes. The machine learning models demonstrated high accuracy in predicting compressive strength, with random forest providing the best performance. This research offers useful insights into the design of fiber-reinforced DLC and demonstrates the potential of machine learning in performance prediction.