arrow
返回

A Data-Driven Method for Predicting Rocks' Young’s Modulus: Case Study

delete2026-03-13
delete0
PRE
AI
W
Wei Xin
J
Jun Li
X
Xigui Zheng *
X
Xiaowei Qin
DOI:10.1007/s00603-026-05419-wdelete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
杨氏模量(E)是预测材料抗压能力的关键参数,在岩石工程项目设计中至关重要。E在采矿、岩土工程等领域具有广泛应用。虽然E可以通过实验室测试直接测量,但这需要高质量岩心样本和昂贵的现代化设备。因此,间接估计E的方法是一种有吸引力的替代方案。本研究开发了四种新型数据驱动方法——岭回归(RR)、Lasso回归(LR)、人工神经网络(ANN)和梯度提升回归器(GBR)——用于预测E。E的数据集按70%训练集和30%测试集的比例分配给每个模型。为提升各模型性能,采用了迭代五折交叉验证方法。结果表明,GBR回归模型优于其他模型,训练集上的相关系数(R²)达到0.995,测试集为0.992;平均绝对误差(MAE)分别为0.0162和0.0147;均方根误差(RMSE)分别为0.02和0.0173。该模型在a20指数上的得分也很高,训练集为0.96,测试集为0.98。通过这四种回归模型,本研究提供了准确高效预测E的替代方法。要点
Keyword:
Young’s modulus
Data-driven approach
Gradient boosting regression
Mining rock engineering

期刊

Rock Mechanics and Rock Engineering 封面图
Rock Mechanics and Rock Engineering
IF:
6.6
论文数:
6.1K
被引数:
3.0W

机构

C
Colorado School of Mines
学者数:
5.6K
论文数: 5.5K
被引数: 1.0W
引用论文

引用论文

Modeling of the uniaxial compressive strength of some clay-bearing rocks using neural network
err2011-03-01
err119
PREAI
errCevik, Abdulkadir; Sezer, Ebru Akcapinar; Cabalar, Ali Firat; Gokceoglu, Candan
err分享
err收藏
The strength of weak learnability
err1990-06-01
err0
errOAAI
errRobert E. Schapire
err分享
err收藏
A novel systematic and evolved approach based on XGBoost-firefly algorithm to predict Young's modulus and unconfined compressive strength of rock
err2021-01-16
err81
PREAI
errCao, Jing; Gao, Juncheng; Rad, Hima Nikafshan; Mohammed, Ahmed Salih; Hasanipanah, Mahdi; Zhou, Jian
err分享
err收藏
Prediction of airblast-overpressure induced by blasting using a hybrid artificial neural network and particle swarm optimization
err2014-06-01
err160
PREAI
errHajihassani, M.; Armaghani, D. Jahed; Sohaei, H.; Mohamad, E. Tonnizam; Marto, A.
err分享
err收藏
An adaptive neuro-fuzzy inference system for predicting unconfined compressive strength and Young's modulus: a study on Main Range granite
err2014-10-18
err166
PREAI
errArmaghani, Danial Jahed; Mohamad, Edy Tonnizam; Momeni, Ehsan; Narayanasamy, Mogana Sundaram; Amin, Mohd For Mohd
err分享
err收藏
学者 查看更多内容