重庆科技大学学报（自然科学版）2025，Vol.27Issue(5)：50-58,9.DOI:10.19406/j.issn.2097-4531.2025.05.007
基于RF-PSO-SVM的测井岩性识别方法研究
Research on Logging Lithology Identification Method Based on RF-PSO-SVM
摘要
Abstract
In response to the unsatisfactory application effects of conventional lithology identification methods,a li-thology identification model based on RF-PSO-SVM is proposed.Firstly,logging parameters of high importance are selected through the out-of-bag(OOB)principle in the RF algorithm.Secondly,the optimal parameter combination for the Support Vector Machine(SVM)model is obtained by optimizing different particle numbers based on the par-ticle swarm optimization(PSO)algorithm.Finally,the RF-PSO-SVM lithology identification model is established to conduct lithology prediction on 908 experimental data.Compared with the PSO-SVM model,SVM model,and RF model,it has a higher identification accuracy.The RF-PSO-SVM lithology identification model can effectively improve lithology identification results,providing an optimized approach for the application of machine learning al-gorithms in lithology identification.关键词
测井/岩性识别/RF算法/SVM算法/PSO算法/RF-PSO-SVM模型Key words
logging/lithology identification/random forest algorithm/support vector machine algorithm/particle swarm optimization algorithm/RF-PSO-SVM model分类
地质学引用本文复制引用
朱斌,赵军龙..基于RF-PSO-SVM的测井岩性识别方法研究[J].重庆科技大学学报（自然科学版）,2025,27(5):50-58,9.基金项目
国家自然科学基金面上项目"压力-应力耦合对前陆冲断带深层—超深层碎屑岩储层异常高原生孔隙的保存机制研究"(42172164) （42172164）
