Bagherzadeh, F.; Shafighfard, T. Ensemble Machine Learning Approach for Evaluating the Material Characterization of Carbon Nanotube-Reinforced Cementitious Composites. Case Studies in Construction Materials 2022, 17, e01537, doi:10.1016/j.cscm.2022.e01537.
Bagherzadeh, F.; Shafighfard, T. Ensemble Machine Learning Approach for Evaluating the Material Characterization of Carbon Nanotube-Reinforced Cementitious Composites. Case Studies in Construction Materials 2022, 17, e01537, doi:10.1016/j.cscm.2022.e01537.
Bagherzadeh, F.; Shafighfard, T. Ensemble Machine Learning Approach for Evaluating the Material Characterization of Carbon Nanotube-Reinforced Cementitious Composites. Case Studies in Construction Materials 2022, 17, e01537, doi:10.1016/j.cscm.2022.e01537.
Bagherzadeh, F.; Shafighfard, T. Ensemble Machine Learning Approach for Evaluating the Material Characterization of Carbon Nanotube-Reinforced Cementitious Composites. Case Studies in Construction Materials 2022, 17, e01537, doi:10.1016/j.cscm.2022.e01537.
Abstract
Time and cost-efficient techniques are essential to avoid extra conventional experimental studies with large date-set to characterize the mechanical properties of composite materials. Correlation between the structural performance and mechanical properties could be captured through the efficient predictive models. Several ensembled Machine Learning (ML) methods were implemented in this study, to materially characterize carbon nanotube (CNT)-reinforced cement-based composites. Proposed models were compared with each other to represent the accuracy of each method. The Flexural and Compressive Strength (target values) of CNT reinforced composites were predicted based on the data-rich framework provided in previous experimental investigations. These data were utilized for training of the proposed models by employing SciKit-Learn library in Python, followed by hyper-parameter tuning and k-fold cross-validation method for obtaining an efficient model to predict the target values. Random Forest (RF) and Gradient Boosting Machine (GBM) were developed for this purpose. The findings of this study would be useful for prospective composite designers in case of sufficient experimental data availability for ML model training.
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
