常州大学学报（自然科学版）2024，Vol.36Issue(3)：34-44,11.DOI:10.3969/j.issn.2095-0411.2024.03.005
基于深度AUC最大化算法的井漏风险预测
Lost circulation prediction based on deep AUC maximization
摘要
Abstract
Lost circulation is a significant challenge in oil and gas drilling,which can lead to various costly and time-consuming problems.It is of great significance to use artificial intelligence technology to accurately predict the risk of lost circulation.The lost circulation prediction problem was converted into an imbalanced classification problem,which pose challenges to traditional deep learning models due to the imbalance between categories and the lack of high correlation between drilling features.Ac-curacy is not an appropriate measurement for imbalanced classification algorithms.A deep AUC maxi-mization(DAM)algorithm,which is called FAUC-S,is introduced in this paper.It trains a combina-tion deep learning model by focusing on the AUC loss of hard samples(FAUC-S).Several traditional deep learning methods are also applied to classify lost circulation risk during oil exploration in the ex-periments.The result shows that the FAUC-S method achieved the highest accuracy,recall,and F1 score among the other three models.This confirms that the FAUC-S model has superior classification performance.Therefore,the successful implementation of this deep model can help drilling teams ef-fectively solve drilling problems.关键词
井漏/非均衡分类/深度学习/AUC最大化Key words
lost circulation/imbalanced classification/deep learning/AUC maximization分类
信息技术与安全科学引用本文复制引用
罗俊如,丁言瑞,徐明华,胡超,刘炳官,孔维军,马强维,石林..基于深度AUC最大化算法的井漏风险预测[J].常州大学学报（自然科学版）,2024,36(3):34-44,11.基金项目
中国石油-常州大学创新联合体资助项目(2021DQ06) （2021DQ06）
江苏省双创博士研究资助项目(JSSCBS20210885) （JSSCBS20210885）
常州大学阿里云大数据学院研究资助项目(ZMF21020012). （ZMF21020012）
