• G.VIMALESH
• Mr.O.N.V.P BHAGAVAN KUMAR
• N.BHARATH
• R.PURNA SA

This term paper presents a study of different Artificial Intelligence (AI) andMachineLearning (ML) techniques applied to predict the compressive and tensile strength of concrete. Thedatasets used in the studies contain information about cement, water, aggregates, fly ash, slag, superplasticizers, and curing age. Various models such as Artificial Neural Networks (ANN), Support Vector Machines (SVM), Random Forest (RF), Gradient Boosting, XGBoost, Decision Trees, andHybrid ANN models were tested. Advanced optimization algorithms such as Genetic Algorithm(GA), Particle Swarm Optimization (PSO), and Firefly Optimization were also applied to improve accuracy. The results show that AI models perform better than traditional statistical methods, givinghigheraccuracy (R² close to 0.99) and lower error values (MAE and RMSE). The studies also usedSHAPanalysis to identify the most important factors influencing concrete strength, such as cement, water, and curing age. Overall, the research proves that AI and ML can reduce manual laboratorytesting, save time and cost, and provide reliable predictions for concrete design. These methods help engineersand researchers to create sustainable, strong, and eco-friendly concrete mixtures for futureconstruction projects.

compressive strength, tensile strength, machine learning XGBoost, fine aggregates, sustainable construction

"A REVIEW ON PREDICTIVEANALYSISOFCONCRETE’S ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 9, page no.d314-d326, September-2025, Available :http://www.jetir.org/papers/JETIR2509345.pdf

"A REVIEW ON PREDICTIVEANALYSISOFCONCRETE’S ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 9, page no. ppd314-d326, September-2025, Available at : http://www.jetir.org/papers/JETIR2509345.pdf