Publication: Prediction of geopolymer concrete compressive strength using novel machine learning algorithms
5
0
Issued Date
2021
Resource Type
Language
eng
File Type
application/pdf
ISSN
20734360
Other identifier(s)
2-s2.0-85116312721
Rights Holder(s)
มหาวิทยาลัยศรีนครินทรวิโรฒ
Bibliographic Citation
Polymers. Vol 13, No.19 (2021)
Suggested Citation
Ahmad A., Ahmad W., Chaiyasarn K., Ostrowski K.A., Aslam F., Zajdel P., Joyklad P. Prediction of geopolymer concrete compressive strength using novel machine learning algorithms. Polymers. Vol 13, No.19 (2021). doi:10.3390/polym13193389 Retrieved from: https://hdl.handle.net/20.500.14740/8179
Abstract
The innovation of geopolymer concrete (GPC) plays a vital role not only in reducing the environmental threat but also as an exceptional material for sustainable development. The application of supervised machine learning (ML) algorithms to forecast the mechanical properties of concrete also has a significant role in developing the innovative environment in the field of civil engineering. This study was based on the use of the artificial neural network (ANN), boosting, and AdaBoost ML approaches, based on the python coding to predict the compressive strength (CS) of high calcium fly-ash-based GPC. The performance comparison of both the employed techniques in terms of prediction reveals that the ensemble ML approaches, AdaBoost, and boosting were more effective than the individual ML technique (ANN). The boosting indicates the highest value of R2 equals 0.96, and AdaBoost gives 0.93, while the ANN model was less accurate, indicating the coefficient of determination value equals 0.87. The lesser values of the errors, MAE, MSE, and RMSE of the boosting technique give 1.69 MPa, 4.16 MPa, and 2.04 MPa, respectively, indicating the high accuracy of the boosting algorithm. However, the statistical check of the errors (MAE, MSE, RMSE) and k-fold cross-validation method confirms the high precision of the boosting technique. In addition, the sensitivity analysis was also introduced to evaluate the contribution level of the input parameters towards the prediction of CS of GPC. The better accuracy can be achieved by incorporating other ensemble ML techniques such as AdaBoost, bagging, and gradient boosting. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
Subject(s)
Adaptive boosting
Compressive strength
Concretes
Fly ash
Geopolymers
Inorganic polymers
Neural networks
Sensitivity analysis
Slags
Supervised learning
Sustainable development
Coefficient of determination
Concrete compressive strength
Environment
Environmental threats
Geopolymer concrete
Machine learning algorithms
Machine learning approaches
Machine learning techniques
Properties of concretes
Supervised machine learning
Forecasting
Compressive strength
Concretes
Fly ash
Geopolymers
Inorganic polymers
Neural networks
Sensitivity analysis
Slags
Supervised learning
Sustainable development
Coefficient of determination
Concrete compressive strength
Environment
Environmental threats
Geopolymer concrete
Machine learning algorithms
Machine learning approaches
Machine learning techniques
Properties of concretes
Supervised machine learning
Forecasting