化工矿物与加工2023，Vol.52Issue(12)：59-65,7.DOI:10.16283/j.cnki.hgkwyjg.2023.12.009
基于PCA-RF的边坡稳定性预测
Slope stability prediction based on PCA-RF
摘要
Abstract
With the increase of mining depth in open-pit mines,there are more and more high and steep slopes,and the frequency of slope disasters is increasing year by year.In order to reduce the occurrence of slope disasters,it is necessary to carry out slope stability prediction research.A open-pit slope stability prediction model combining princi-pal component analysis(PCA)and random forest model(RF)was proposed by comparing and screening machine learning algorithms.The results of slope instance prediction showed that the accuracy of the model reached 100%;Through the 6-fold cross validation method evaluation,it was found that the prediction accuracy of the model is as high as 94.44%.The model was applied to the stability prediction of the end slope of the open-pit mining site in the eastern part of Lala Copper Mine.The results showed that the east,west,south,and north slopes of the slope were all in a stable state.The prediction results can provide reference for the actual production of the mine.关键词
露天矿山/边坡稳定性/主成分分析/随机森林/6折交叉验证/机器学习Key words
open-pit mine/slope stability/principal component analysis/random forests/6-folder cross validation/machine learning分类
建筑与水利引用本文复制引用
林逸晖,李广涛,杨天雨,乔登攀,王俊,张希,赵怀军..基于PCA-RF的边坡稳定性预测[J].化工矿物与加工,2023,52(12):59-65,7.基金项目
云南省基础研究专项-青年项目(202101AU070022) （202101AU070022）
昆明理工大学人培基金项目(KKZ3202021040,KKSY201921017). （KKZ3202021040,KKSY201921017）
