TY - JOUR
T1 - Improving pressure drops estimation of fresh cemented paste backfill slurry using a hybrid machine learning method
AU - Qi, Chongchong
AU - Guo, Li
AU - Ly, Hai Bang
AU - Le, Hiep Van
AU - Pham, Binh Thai
PY - 2021/3/15
Y1 - 2021/3/15
N2 - Estimation of pressure drops of fresh cemented paste backfill slurry is a novel idea with great potentials. This paper presented a hybrid machine learning (ML) method for improved pressure drops estimation using a combination of artificial neural network and differential evolution. A comprehensive parametric study was conducted on training dataset size (Nsize), ML methods, and Monte Carlo random sampling. Moreover, dependent analysis of pressure drops to each influencing variable was performed. The results indicate that 300 Monte Carlo realizations were sufficient for the converged and reliable results. The optimum Nsize was determined to be 70%, and the proposed hybrid method outperformed six individual ML methods. The estimation performance has been significantly improved compared to the methods used in the literature (R2 increased from 0.83 to 0.95 on the testing dataset). Solids content, inlet velocity, SiO2, CaO, and Fe2O3 were determined to be the most significant variables for pressure drops.
AB - Estimation of pressure drops of fresh cemented paste backfill slurry is a novel idea with great potentials. This paper presented a hybrid machine learning (ML) method for improved pressure drops estimation using a combination of artificial neural network and differential evolution. A comprehensive parametric study was conducted on training dataset size (Nsize), ML methods, and Monte Carlo random sampling. Moreover, dependent analysis of pressure drops to each influencing variable was performed. The results indicate that 300 Monte Carlo realizations were sufficient for the converged and reliable results. The optimum Nsize was determined to be 70%, and the proposed hybrid method outperformed six individual ML methods. The estimation performance has been significantly improved compared to the methods used in the literature (R2 increased from 0.83 to 0.95 on the testing dataset). Solids content, inlet velocity, SiO2, CaO, and Fe2O3 were determined to be the most significant variables for pressure drops.
KW - Artificial neural network
KW - Differential evolution
KW - Fresh cemented paste backfill slurry
KW - Parametric study
KW - Pressure drops
UR - http://www.scopus.com/inward/record.url?scp=85099626426&partnerID=8YFLogxK
U2 - 10.1016/j.mineng.2021.106790
DO - 10.1016/j.mineng.2021.106790
M3 - Article
AN - SCOPUS:85099626426
SN - 0892-6875
VL - 163
JO - Minerals Engineering
JF - Minerals Engineering
M1 - 106790
ER -