Enhancing compressive strength prediction in self-compacting concrete using machine learning and deep learning techniques with incorporation of rice husk ash and marble powder

Development of eco-friendly self-compacting concrete using marble powder, blast furnace slag and glass fibre-reinforced plastic waste: Application of mixture design approach

“…It is clear that the interaction terms MP*GGBS*GFRPW and MP*GFRPW promote the development of the 90-day compressive strength. Several researchers have reported that the use of pozzolanic additions in combination with MP improves the mechanical performance of concrete [9]. Choudhary et al found that despite the negative effect of MP on mechanical strength, the addition of FA improved the mechanical strength of SCC after 90 days of curing (2).…”

“…Mechanical strength showed an increase with higher incorporation rates of MP. Mahmood et al (9) concluded that substituting 5% of fine aggregate with marble powder and 15% with rice husk ash resulted in optimum mechanical performance for both short and long-term applications in SCC.…”

Forecasting residual mechanical properties of hybrid fibre-reinforced self-compacting concrete (HFR-SCC) exposed to elevated temperatures

“…The analysis demonstrated that RF algorithm performed well than all the other regression algorithms and predicted strength values with maximum accuracy and minimal error of 0.712. Also, in a recently conducted study by Mahmood et al [ 27 ], the authors developed SCC by incorporating rice husk ash and marble powder as a replacement of cement. The addition of these waste materials resulted in cost reduction and improvement in different SCC properties.…”

“…Artificial intelligence in the realm of civil and structural engineering essentially refers to the amalgamation of advanced ML techniques to optimize construction practices, foster sustainable and intelligent design of infrastructure, and improve the overall efficiency and accuracy of construction industry. ML is a subset of artificial intelligence which enables computers to recognize and learn patterns from the data without explicit guidance from a human and use them to make accurate predictions for future use in return [ 27 ]. Deep learning (DL) is in turn a type of ML which involves the use of neural networks to learn patterns from the data.…”