Prediction of rock drillability using gray wolf optimization and teaching-learning-based optimization techniques

被引：13

作者：

Fattahi, Hadi ^{[1
]}

Ghaedi, Hossein ^{[1
]}

Malekmahmoodi, Farshad ^{[1
]}

机构：

[1] Arak Univ Technol, Fac Earth Sci Engn, Arak, Iran

来源：

SOFT COMPUTING | 2024年 / 28卷 / 01期

关键词：

Drilling rate index; Prediction; Teaching-learning-based optimization; Gray wolf optimization; DRILLING RATE INDEX; VECTOR REGRESSION-MODEL; PENETRATION RATE; MECHANICAL-PROPERTIES; COMPRESSIVE STRENGTH; DEFORMATION MODULUS; MACHINE; DESIGN; MASS; PERFORMANCE;

D O I：

10.1007/s00500-023-08233-6

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

An important index to evaluate the rock drilling ability in mines, tunnel drilling and underground drilling is the drilling rate index (DRI). Due to the complexity and nonlinearity of mechanical and physical properties of rocks, there are many uncertainties in DRI evaluation. For this reason, teaching-learning-based optimization (TLBO) and gray wolf optimization (GWO) have been used to consider uncertainties and establish a precise nonlinear relationship in the estimation of the DRI. In this study, 32 different rock types included metamorphic, igneous and sedimentary rocks were investigated in the laboratory to investigate the relationships between the DRI and input parameters. The modeling results show that the relationships determined for estimating the DRI by TLBO and GWO algorithms are accurate and close to the real value. It can also be concluded that the use of optimization algorithms to predict the DRI is very efficient.

引用

页码：461 / 476

页数：16