TY - JOUR
T1 - Intelligent prediction of engineered cementitious composites with limestone calcined clay cement (LC3-ECC) compressive strength based on novel machine learning techniques
AU - Li, Enming
AU - Zhang, Ning
AU - Xi, Bin
AU - Tam, Vivian W.Y.
AU - Wang, Jiajia
AU - Zhou, Jian
PY - 2023
Y1 - 2023
N2 - Engineered cementitious composites with calcined clay limestone cement (LC3-ECC) as a kind of green, low-carbon and high toughness concrete, has recently received significant investigation. However, the complicated relationship between potential influential factors and LC3-ECC compressive strength makes the prediction of LC3-ECC compressive strength difficult. Regarding this, the machine learning-based prediction models for the compressive strength of LC3-ECC concrete is firstly proposed and developed. Models combine three novel meta-heuristic algorithms (golden jackal optimization algorithm, butterfly optimization algorithm and whale optimization algorithm) with support vector regression (SVR) to improve the accuracy of prediction. A new dataset about LC3-ECC compressive strength was integrated based on 156 data from previous studies and used to develop the SVR-based models. Thirteen potential factors affecting the compressive strength of LC3-ECC were comprehensively considered in the model. The results show all hybrid SVR prediction models can reach the Coefficient of determination (R2) above 0.95 for the testing set and 0.97 for the training set. Radar and Taylor plots also show better overall prediction performance of the hybrid SVR models than several traditional machine learning techniques, which confirms the superiority of the three proposed methods. The successful development of this predictive model can provide scientific guidance for LC3-ECC materials and further apply to such low-carbon, sustainable cement-based materials.
AB - Engineered cementitious composites with calcined clay limestone cement (LC3-ECC) as a kind of green, low-carbon and high toughness concrete, has recently received significant investigation. However, the complicated relationship between potential influential factors and LC3-ECC compressive strength makes the prediction of LC3-ECC compressive strength difficult. Regarding this, the machine learning-based prediction models for the compressive strength of LC3-ECC concrete is firstly proposed and developed. Models combine three novel meta-heuristic algorithms (golden jackal optimization algorithm, butterfly optimization algorithm and whale optimization algorithm) with support vector regression (SVR) to improve the accuracy of prediction. A new dataset about LC3-ECC compressive strength was integrated based on 156 data from previous studies and used to develop the SVR-based models. Thirteen potential factors affecting the compressive strength of LC3-ECC were comprehensively considered in the model. The results show all hybrid SVR prediction models can reach the Coefficient of determination (R2) above 0.95 for the testing set and 0.97 for the training set. Radar and Taylor plots also show better overall prediction performance of the hybrid SVR models than several traditional machine learning techniques, which confirms the superiority of the three proposed methods. The successful development of this predictive model can provide scientific guidance for LC3-ECC materials and further apply to such low-carbon, sustainable cement-based materials.
KW - engineered cementitious composites (ECC)
KW - green concrete
KW - limestone calcined clay cement (LC)
KW - metaheuristic optimization
KW - support vector regression
UR - http://www.scopus.com/inward/record.url?scp=85178061821&partnerID=8YFLogxK
UR - https://ezproxy.uws.edu.au/login?url=https://doi.org/10.12989/cac.2023.32.6.577
U2 - 10.12989/cac.2023.32.6.577
DO - 10.12989/cac.2023.32.6.577
M3 - Article
AN - SCOPUS:85178061821
SN - 1598-8198
VL - 32
SP - 577
EP - 594
JO - Computers and Concrete
JF - Computers and Concrete
IS - 6
ER -