A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Estimation and prediction of screening efficiency of Sand Crumb Rubber (SCR) mix infill trench
The present study investigates the efficiency of using sand crumb rubber mixture for vibration isolation and its prediction using machine learning. Safe disposal of waste rubber from tire industries is a matter of concern due to its detrimental effects. A two-dimensional finite element (FE) analysis was performed in ABAQUS, considering a strip foundation as the source of vibration. The effectiveness of the screening was evaluated by calculating the Amplitude Reduction Factor (Arf) for open and infilled trench (OT and IFT) for different trench geometry (distance from the source, depth and width). In previous studies, modelling such screening problems has mostly been accomplished through regression models. The present study explored the Support Vector Regression (SVR) model since machine learning excels in modelling complex behaviours. The SVR model's optimum parameters were successfully determined by performing a grid search and selecting the best model using the Preferential Ranking Organization Method for Enrichment Evaluation (PROMETHEE) technique.
Estimation and prediction of screening efficiency of Sand Crumb Rubber (SCR) mix infill trench
The present study investigates the efficiency of using sand crumb rubber mixture for vibration isolation and its prediction using machine learning. Safe disposal of waste rubber from tire industries is a matter of concern due to its detrimental effects. A two-dimensional finite element (FE) analysis was performed in ABAQUS, considering a strip foundation as the source of vibration. The effectiveness of the screening was evaluated by calculating the Amplitude Reduction Factor (Arf) for open and infilled trench (OT and IFT) for different trench geometry (distance from the source, depth and width). In previous studies, modelling such screening problems has mostly been accomplished through regression models. The present study explored the Support Vector Regression (SVR) model since machine learning excels in modelling complex behaviours. The SVR model's optimum parameters were successfully determined by performing a grid search and selecting the best model using the Preferential Ranking Organization Method for Enrichment Evaluation (PROMETHEE) technique.
Estimation and prediction of screening efficiency of Sand Crumb Rubber (SCR) mix infill trench
Sarkar, Abir (author) / Barman, Rahul (author) / Bhowmik, Debjit (author)
International Journal of Geotechnical Engineering ; 16 ; 1013-1031
2022-09-14
19 pages
Article (Journal)
Electronic Resource
Unknown
Vibration screening , crumb rubber , ABAQUS , machine learning , SVM , SVR , PROMETHEE , MCDM techniques , FEM
Performance of Sand–Rubber Mixture Infill Trench for Ground Vibration Screening
| Springer Verlag | 2021
Numerical Study on Vibration Screening Using Trench Filled with Sand–Crumb Rubber Mixture
| Springer Verlag | 2021