Experimental Studies on Sugarcane Bagasse Ash and Rice Husk Ash Based Sustainable Material with AI-Driven Techno-Economic Approach

Abstract

The increasing demand for sustainable construction materials has accelerated the search for eco-friendly alternatives capable of reducing cement consumption and mitigating environmental pollution caused by industrial and agricultural wastes. However, the extensive use of Ordinary Portland Cement (OPC) contributes significantly to global CO₂ emissions, while the disposal of Sugarcane Bagasse Ash (SCBA) and Rice Husk Ash (RHA) creates serious waste management challenges. This study proposes the combined utilization of SCBA and RHA as supplementary cementitious materials to produce sustainable concrete with enhanced mechanical and durability performance. Experimental investigations were carried out by replacing cement with 0%, 5%, 10%, 15%, 20%, and 25% combined SCBA-RHA while maintaining a constant water-to-binder ratio of 0.45. The prepared concrete specimens were evaluated through workability, compressive strength, flexural strength, split tensile strength, water absorption, durability, density, Rapid Chloride Penetration Test (RCPT), and Ultrasonic Pulse Velocity (UPV) analyses. The results revealed that the 15% replacement level (SR-15) provided optimum performance, achieving a 56-day compressive strength of 56.3 MPa, flexural strength of 6.21 MPa, and split tensile strength of 4.84 MPa, representing improvements of approximately 24%, 23%, and 23.5%, respectively, over the control mix. Water absorption decreased from 5.24% to 3.71%, chloride penetration reduced from 18.4 mm to 11.3 mm, RCPT charge passed decreased from 2685 to 1268 Coulombs, and the durability index increased from 100% to 116%. These findings confirm that a 15% combined SCBA-RHA replacement offers the optimum balance of strength, durability, cost efficiency, and environmental sustainability for advanced concrete applications. Furthermore, the experimental dataset generated in this study provides a structured foundation for future Artificial Intelligence (AI) and Machine Learning (ML)-based prediction of concrete strength and durability. Such data-driven approaches can support intelligent mix proportion optimization and sustainable material design for next-generation smart construction systems. This paper also discusses techno-economic implications associated with sustainable material utilization, highlighting improvements in, life-cycle cost reduction, and circular economy implementation.