Integrating testing and modeling methods to examine the feasibility of blended waste materials for the compressive strength of rubberized mortar
This research integrated glass powder (GP), marble powder (MP), and silica fume (SF) into rubberized mortar to evaluate their effectiveness in enhancing compressive strength (fc′{f}_{\text{c}}^{^{\prime} }). Rubberized mortar cubes were produced by replacing fine aggregates with shredded rubber in v...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2024-12-01
|
| Series: | Reviews on Advanced Materials Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/rams-2024-0081 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This research integrated glass powder (GP), marble powder (MP), and silica fume (SF) into rubberized mortar to evaluate their effectiveness in enhancing compressive strength (fc′{f}_{\text{c}}^{^{\prime} }). Rubberized mortar cubes were produced by replacing fine aggregates with shredded rubber in varying proportions. The decrease in rubberized mortar’s fc′{f}_{\text{c}}^{^{\prime} } was controlled by substituting cement with GP, MP, and SF. Although many literature studies have evaluated the suitability of industrial waste, such as MP, SF, and GP, as construction material, no studies have yet included the combined effect of these wastes on the fc′{f}_{\text{c}}^{^{\prime} } of rubberized mortar. This study aims to provide complete insight into the combined effect of industrial waste on the fc′{f}_{\text{c}}^{^{\prime} } of rubberized mortar. By substituting cement, GP, MP, and SF were added to rubberized mortar in different proportions from 5 to 25%. Furthermore, artificial intelligence prediction models were developed using experimental data to assess the fc′{f}_{\text{c}}^{^{\prime} } of rubberized mortar. The study determined that the optimal substitution levels for GP, MP, and SF in rubberized mortar were 15, 10, and 15%, respectively. Similarly, partial dependence plot analysis suggests that SF, MP, and GP have a comparable effect on the fc′{f}_{\text{c}}^{^{\prime} } of rubberized mortar. The machine learning models demonstrated a significant resemblance to test results. Two individual techniques, support vector machine and random forest, generate R
2 values of 0.943 and 0.983, respectively. |
|---|---|
| ISSN: | 1605-8127 |