Intelligent lithology prediction method based on vibration signal while drilling and deep learning

Authors

WANG Sheng, State Key Laboralory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, ChinaFollow
LAI Kun, State Key Laboralory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, ChinaFollow
ZHANG Zheng, State Key Laboralory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, China
BAI Jun, State Key Laboralory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, China
LUO Zhongbin, State Key Laboralory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, China
LI Bingle, State Key Laboralory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, China
ZHANG Jie, State Key Laboralory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, China

Abstract

Intelligent lithology prediction is of great importance in geological drilling, capable of improving exploration and mining efficiency, as well as the quality of results. In this study, a method of intelligent lithology prediction while drilling was proposed based on the vibration signals produced by the drill bit breaking rocks during drilling. Specifically, seven types of rocks with the same size and different lithologies were selected, and a micro-drilling experiment was designed to apply different drilling rates and rotary speeds to the rocks, in order to collect the triaxial vibration signals while drilling under multiple drilling conditions. The signals were preprocessed to filter out the interference information and generate the time-frequency images that characterize the signal’s time-frequency domain features through short-time Fourier transform. Then, multiple data augmentation techniques were used to increase the number of images and establish a database to enhance the robustness and generalization ability of the model. The VGG11 (Visual Geometry Group) convolutional neural network algorithm in deep learning was modified, and the database was divided into the training set and test set at a proportion of 8∶2. The effective image information of the training set was extracted, learned and iteratively trained, to obtain an intelligent lithology prediction model. Meanwhile, the three hyperparameters of the model (learning rate, batch size, and iteration times) were continuously adjusted to fit the loss function curve of the training set and the test set and thereby improve the model's prediction accuracy. Finally, the model was evaluated with multiple indicators on the test set. The experimental results showed that: the intelligent lithology prediction model trained based on the vibration data while drilling has strong generalization ability and high prediction accuracy, with an ultimate overall lithology prediction accuracy of 96.85%. Besides, the impact of the dataset size on lithology prediction accuracy was also discussed herein. Moreover, different drilling conditions could cause certain regular changes in the vibration signals while drilling, the rock properties could also cause changes in the vibration signals in the tri-axis direction, and the X, Y and Z axis signals could characterize different processes of the drill bit breaking rocks during drilling. Generally, the intelligent real-time lithology prediction method proposed in this study provides a basis and reference for lithology prediction in practical drilling engineering.

Keywords

intelligent lithology prediction, triaxial vibration signals while drilling, short-time Fourier transform, data augmentation, deep learning, improved VGG11 algorithm

DOI

10.12363/issn.1001-1986.23.03.0149

Recommended Citation

WANG Sheng, LAI Kun, ZHANG Zheng, et al. (2023) "Intelligent lithology prediction method based on vibration signal while drilling and deep learning," Coal Geology & Exploration: Vol. 51: Iss. 9, Article 18.
DOI: 10.12363/issn.1001-1986.23.03.0149
Available at: https://cge.researchcommons.org/journal/vol51/iss9/18

Reference

[1] 付光明,严加永,张昆,等. 岩性识别技术现状与进展[J]. 地球物理学进展,2017,32(1):26−40.

FU Guangming,YAN Jiayong,ZHANG Kun,et al. Current status and progress of lithology identification technology[J]. Progress in Geophysics,2017,32(1):26−40.

[2] 许振浩,马文,林鹏,等. 基于岩石图像迁移学习的岩性智能识别[J]. 应用基础与工程科学学报,2021,29(5):1075−1092.

XU Zhenhao,MA Wen,LIN Peng,et al. Intelligent lithology identification based on transfer learning of rock images[J]. Journal of Basic Science and Engineering,2021,29(5):1075−1092.

[3] 高岩,陈亚西,郭学增. 钻柱振动信号采集系统及谱分析[J]. 录井技术,1998,9(3):44−51.

GAO Yan,CHEN Yaxi,GUO Xuezeng. The acquisition system for drill string vibration signals and the spectrum analysis[J]. Mud Logging Technology,1998,9(3):44−51.

[4] MANSURE A，FINGER J T，KNUDSEN S D，et al. Interpretation of diagnostics–while–drilling data[C]//SPE Annual Technical Conference and Exhibition. USA：Society of Petroleum Engineers，2003：SPE–84244–MS.

[5] AL–SHUKER N，KIRBY C，BRINSDON M. The application of real time downhole drilling dynamic signatures as a possible early indicator of lithology changes[C]//SPE/DGS Saudi Arabia Section Technical Symposium and Exhibition. USA：Society of Petroleum Engineers，2011：SPE–149056–MS.

[6] 李想. 煤矿巷道顶板岩层强度智能随钻识别技术[D]. 徐州：中国矿业大学，2022.

LI Xiang. Intelligent identification technology while drilling for roof rock strength of coal mine roadway[D]. Xuzhou：China University of Mining and Technology，2022.

[7] 朱敢为,赵宁宁,周晓忠,等. 地质超前钻探声波与岩石强度关系初步研究[J]. 地基处理,2020,2(5):383−391.

ZHU Ganwei,ZHAO Ningning,ZHOU Xiaozhong,et al. A preliminary study on relationship between sound wave and rock strength in geological advanced forecast[J]. Chinese Journal of Ground Improvement,2020,2(5):383−391.

[8] QIN Min,WANG Kai,PAN Kai,et al. Analysis of signal characteristics from rock drilling based on vibration and acoustic sensor approaches[J]. Applied Acoustics,2018,140:275−282.

[9] 马良慧,赵华山,尹杨林,等. 基于仰斜钻孔轴向加速度测井的岩性识别与岩体结构分析[J]. 中国金属通报,2019(10):201−203.

MA Lianghui,ZHAO Huashan,YIN Yanglin,et al. Lithology identification and rock mass structure analysis based on axial acceleration logging of inclined borehole[J]. China Metal Bulletin,2019(10):201−203.

[10] 李占涛,林小国,宋春霞. 岩石钻孔振动与声波频谱特性实验研究[J]. 地下空间与工程学报,2019,15(4):1008−1016.

LI Zhantao,LIN Xiaoguo,SONG Chunxia. Experimental study on spectral characteristics of sound and vibrations in rock drilling[J]. Chinese Journal of Underground Space and Engineering,2019,15(4):1008−1016.

[11] KHOSHOUEI M,BAGHERPOUR R,JALALIAN M H. Rock type identification using analysis of the acoustic signal frequency contents propagated while drilling operation[J]. Geotechnical and Geological Engineering,2022,40(3):1237−1250.

[12] 金玮,孟晓曼,武益超. 深度学习在图像分类中的应用综述[J]. 现代信息科技,2022,6(16):29−31.

JIN Wei,MENG Xiaoman,WU Yichao. A review of the application of deep learning in image classification[J]. Modern Information Technology,2022,6(16):29−31.

[13] SIMONYAN K，ZISSERMAN A. Very deep convolutional networks for large−scale image recognition[J]. CoRR，2014，abs/1409. 1556.

[14] KRIZHEVSKY A,SUTSKEVER I,HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM,2017,60(6):84−90.

[15] BAI Jun,WANG Sheng,XU Qiang,et al. Intelligent real–time predicting method for rock characterization based on multi–source information integration while drilling[J]. Bulletin of Engineering Geology and the Environment,2023,82(4):150.

[16] 苏程,朱孔阳. 岩石薄片图像智能分析研究进展[J]. 矿物岩石地球化学通报,2023,42(1):13−25.

SU Cheng,ZHU Kongyang. Research progress of intelligent image analysis for petrographic thin section images[J]. Bulletin of Mineralogy,Petrology and Geochemistry,2023,42(1):13−25.

[17] 张超群,易云恒,周文娟,等. 基于深度学习与数据增强技术的小样本岩石分类[J]. 科学技术与工程,2022,22(33):14786−14794.

ZHANG Chaoqun,YI Yunheng,ZHOU Wenjuan,et al. Small rock samples classification based on deep learning and data enhancement technologies[J]. Science Technology and Engineering,2022,22(33):14786−14794.

[18] 马文. 基于多尺度岩石图像深度学习的岩性智能识别方法[D]. 济南：山东大学，2022.

MA Wen. Deep learning of muti–scale rock images for intelligent lithology identification[D]. Jinan：Shandong University，2022.

[19] ZHANG Zhiyu,LI Heng,LEI Zhen,et al. Research on lightweight lithology intelligent recognition system incorporating attention mechanism[J]. Applied Sciences,2022,12(21):10918.

[20] 程国建,郭文惠,范鹏召. 基于卷积神经网络的岩石图像分类[J]. 西安石油大学学报(自然科学版),2017,32(4):116−122.

CHENG Guojian,GUO Wenhui,FAN Pengzhao. Study on rock image classification based on convolution neural network[J]. Journal of Xi’an Shiyou University (Natural Science Edition),2017,32(4):116−122.

[21] 刘刚,张家林,刘闯,等. 钻头钻进不同介质时的振动信号特征识别研究[J]. 振动与冲击,2017,36(8):71−78.

LIU Gang,ZHANG Jialin,LIU Chuang,et al. An identification method of vibration signal features when bit drills different mediums[J]. Journal of Vibration and Shock,2017,36(8):71−78.

[22] CHEN Gang,CHEN Mian,HONG Guobin,et al. A new method of lithology classification based on convolutional neural network algorithm by utilizing drilling string vibration data[J]. Energies,2020,13(4):888.

[23] 洪国斌. 基于振动时频图像的实时岩性识别[D]. 北京：中国石油大学(北京)，2019.

HONG Guobin. Lithology identification based on time−frequency image of vibration in nearly real time[D]. Beijing：China University of Petroleum (Beijing)，2019.