[1]曹茂俊,赵宇杰.一种基于预训练语言模型XLNet的测井曲线重构方法[J].计算机技术与发展,2025,(02):183-190.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0321]
　CAO Mao-jun,ZHAO Yu-jie.A Well Logging Curve Reconstruction Method Based on Pre-trained Language Model XLNet[J].,2025,(02):183-190.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0321]
点击复制

一种基于预训练语言模型XLNet的测井曲线重构方法()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2025年02期
页码:
183-190
栏目:
新型计算应用系统
出版日期:
2025-02-10

文章信息/Info

Title:
A Well Logging Curve Reconstruction Method Based on Pre-trained Language Model XLNet
文章编号:
1673-629X(2025)02-0183-08
作者:
曹茂俊; 赵宇杰
东北石油大学 计算机与信息技术学院,黑龙江 大庆 163318
Author(s):
CAO Mao-jun; ZHAO Yu-jie
School of Computer and Information Technology,Northeast Petroleum University,Daqing 163318,China
关键词:
测井曲线重构; 深度学习; 预训练语言模型; XLNet网络; LoRA机制
Keywords:
well logging curve reconstruction; deep learning; pre-trained language models; XLNet network; LoRA mechanism
分类号:
TP181
DOI:
10.20165/j.cnki.ISSN1673-629X.2024.0321
摘要:
在油田勘探开发过程中,测井曲线作为地球物理测井的第一手资料,能够真实反映地下空间的分布与特性。 然而,在实际工作中,由于井壁垮塌和仪器故障等原因,部分测井数据常常出现失真或缺失。 为解决这一问题,该文提出了一种基于预训练语言模型 XLNet 的测井曲线重构方法。 该方法通过筛选地层地质岩性特征指数,获取高质量的训练样本,并将其作为预训练模型重构测井曲线的依据。 构建并训练带有预训练权重信息的 XLNet 模型,使模型具备对复杂地层特性的理解和数据重构能力。 在模型的构建与训练过程中,引入了预训练权重,并进一步结合了 LoRA( Low-Rank Adaptation)模块,以充分利用测井曲线之间的高度依赖关系,进而辅助 XLNet 生成和补全失真或缺失的测井数据。 与已知曲线重构模型:基于注意力表征的长短期记忆神经网络(LSTM-Attent)、双向门控神经网络(BiGRU)、TimesNet 及 XLNet 相比,基于预训练语言模型 XLNet-LoRA 的测井曲线重构模型具有更高的预测准确性。
Abstract:
In the process of oilfield exploration and development,the logging curve,as the first-hand data of geophysical logging,can truly reflect the distribution and characteristics of underground space. However, in practice, due to borehole collapse and instrument failure,some logging data are often distorted or missing. In order to solve this problem,we propose a logging curve reconstruction method based on the pre-trained language model XLNet. In this method,high-quality training samples are obtained by screening the for-mation geological lithology characteristic index,which is used as the basis for the pre-training model to reconstruct the logging curve. An XLNet model with pre - trained weight information is constructed and trained, so that the model has the ability to understand the characteristics of complex strata and reconstruct data. In the process of model construction and training,we introduce pre-training weights and further combine LoRA (Low-Rank Adaptation) module to make full use of the high dependence between logging curves,and then assist XLNet to generate and complete distorted or missing logging data. The curve reconstruction model based on the pre - trained language model XLNet-LoRA has higher prediction accuracy than the known logging curve reconstruction models:long short - term memory neural network based on attention representation (LSTM-Attent),bidirectional gating neural network (BiGRU),TimesNet and XLNet.

相似文献/References:

[1]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(02):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[2]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(02):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[3]黄法秀,张世杰,吴志红,等.数据增广下的人脸识别研究[J].计算机技术与发展,2020,30(03):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
　HUANG Fa-xiu,ZHANG Shi-jie,WU Zhi-hong,et al.Research on Face Recognition Based on Data Augmentation[J].,2020,30(02):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
[4]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(02):19.
[5]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(02):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
[6]贺飞翔,赵启军. 基于深度学习的头部姿态估计[J].计算机技术与发展,2016,26(11):1.
　HE Fei-xiang,ZHAO Qi-jun. Head Pose Estimation Based on Deep Learning[J].,2016,26(02):1.
[7]徐 融,邱晓晖.一种改进的 YOLO V3 目标检测方法[J].计算机技术与发展,2020,30(07):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
　XU Rong,QIU Xiao-hui.An Improved YOLO V3 Object Detection[J].,2020,30(02):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
[8]曾志平[] [],萧海东[],张新鹏[]. 基于DBN的金融时序数据建模与决策[J].计算机技术与发展,2017,27(04):1.
　ZENG Zhi-ping[] [],XIAO Hai-dong[],ZHANG Xin-peng[]. Modeling and Decision-making of Financial Time Series Data with DBN[J].,2017,27(02):1.
[9]李全兵,文 钊*,田艳梅*,等.基于 WGAN 的音频关键词识别研究[J].计算机技术与发展,2021,31(08):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
　LI Quan-bing,WEN Zhao *,TIAN Yan-mei *,et al.Research on Audio Keywords Recognition Based on WassersteinGenerative Adversarial Network[J].,2021,31(02):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
[10]李宏林. 分析式纹理合成技术及其在深度学习的应用[J].计算机技术与发展,2017,27(11):7.
　LI Hong-lin. Analyzed Texture-synthesis Techniques and Their Applications in Deep Learning[J].,2017,27(02):7.
[11]尚福华,卢玉莹,曹茂俊.基于改进 LSTM 神经网络的测井曲线重构方法[J].计算机技术与发展,2022,32(06):198.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 033]
　SHANG Fu-hua,LU Yu-ying,CAO Mao-jun.Well Logging Curve Reconstruction Method Based on Improved LSTM Neural Network[J].,2022,32(02):198.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 033]

更新日期/Last Update: 2025-02-10