化工矿物与加工2023，Vol.52Issue(12)：52-58,7.DOI:10.16283/j.cnki.hgkwyjg.2023.12.008
基于KPCA-KNN算法的边坡稳定性预测
Slope stability prediction based on KPCA-KNN algorithm
摘要
Abstract
In order to determine the stability of slope more accurately and efficiently,55 groups of slope case samples were selected.Six indexes,including bulk density,cohesion,internal friction angle,slope angle,slope height and pore pressure ratio,were used as slope stability prediction indexes.Kernel principal component analysis(KPCA)was used to map the index data into high-dimensional space for linear calculation.In order to improve the operation efficiency and prediction accuracy of K-nearest neighbor(KNN)model,KPCA-KNN slope stability prediction model was con-structed after training,and it was compared with other three prediction models.The results show that the prediction accuracy of the test set of the proposed model is 100%,which is superior to the traditional KNN,BP neural network and support vector machine(SVM)models,and the training time is shorter.The application results of six engineering examples show that the prediction results of KPCA-KNN model are completely consistent with the actual state of slope,and the accuracy is better than the other three prediction models.关键词
核主成分分析/K近邻算法/机器学习/边坡稳定性/预测模型/高维空间Key words
kernel principal component analysis/k-nearest neighbor algorithm/machine learning/slope stability/prediction model/high-dimensional space分类
建筑与水利引用本文复制引用
王团辉,王超,李岳峰,徐健珲,王琦玮..基于KPCA-KNN算法的边坡稳定性预测[J].化工矿物与加工,2023,52(12):52-58,7.基金项目
云南省教育厅科学研究基金项目(2021J0060) （2021J0060）
云南省创新团队项目(202105AE160023). （202105AE160023）
