Developmentofprediction models for strength behavior of MSWIA mixedwithfiberandcement
No Thumbnail Available
Date
2025
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Engineersareincreasinglyinterestedinusingmunicipalsolidwasteincineratorash(MSWIA)toconstructdifferentgeotechni
cal structures. This practice not only helps manage waste but also positively impacts the environment. Stabilizing such wastes
by adding admixture and reinforcing material significantly improves their load bearing capacity. This study investigates the
strength behavior of the MSWIA mixed with cement and fiber, providing valuable insights for the practical application of
these materials. Unconfined compressive strength (UCS) and split tensile strength (STS) tests were conducted to understand
the behavior. The aspect ratio of the fiber, cement content, fiber content, and curing period varied during testing. The impact
of individual variables was evaluated based on the results of the tests through sensitivity analysis. Further, a mathematical
model based on the Artificial Neural network (ANN) and Multivariable linear regression model (MLRM) was developed, and
results were compared. The coefficient of determination ‘R2’ for UCS in ANN was 0.996 and in STS was 0.995 while for
MLRM,‘R2’was0.94 for UCSand 0.93 for STS. From the results, it was found that the ANN can predict the strength better
than MLRM. Also, a correlation between the UCS and STS for the MSWIA mixed with fiber and cement was established.