Abstract：In the process of cutting logging, the lithology of cuttings is mainly manually analyzed, which is inefficient and unstable, and it is difficult to quickly identify the lithology change of the stratum during the drilling. Therefore, an intelligent lithology identification method based on the texture, color, and shape characteristics of rock particles in returned cuttings images is proposed. Firstly, the gradient of the pixel value of the returned cuttings image is calculated, and the particle centroid is obtained. The contour line of the rock particles is obtained and marked by using the watershed algorithm. Then the image segmentation algorithm is used to separate the single rock particle image to be detected from the returned cuttings image, and a sample library of rock particle images is established. Finally, the MobileNetV2 network is improved by using the attention mechanism and feature fusion module to extract and classify the features of rock particles, so as to identify the lithology of a single rock particle image and then obtain the composition ratio of the returned cuttings sample. The proposed method transforms the overall identification method of returned cuttings, which is often used in the intelligent identification of lithology, into the lithology identification method of a single rock particle in returned cuttings, which greatly filters out the mutual interference of rock particles. The test results of returned cuttings images collected from several oil and gas blocks show that the proposed method can reach an accuracy of more than 92% in identifying limestone, mudstone, sandstone, and shale, and the time consumption for lithology analysis of a group of returned cuttings images is less than 10s.
夏文鹤, 谢万洋, 唐印东, 李皋, 韩玉娇. 砂样岩屑图像特征的岩性智能高效识别[J]. 石油地球物理勘探, 2023, 58(3): 495-506.
XIA Wenhe, XIE Wanyang, TANG Yindong, LI Gao, HAN Yujiao. Intelligent and efficient lithology identification based on image features of returned cuttings. Oil Geophysical Prospecting, 2023, 58(3): 495-506.
王光宇, 宋建国, 徐飞, 等. 不平衡样本集随机森林岩性预测方法[J]. 石油地球物理勘探, 2021, 56(4): 679-687.WANG Guangyu, SONG Jianguo, XU Fei, et al. Random forests lithology prediction method for imbalanced data sets[J]. Oil Geophysical Prospecting, 2021, 56(4): 679-687.
[2]
雷军, 王慎实, 杨钰. 岩屑录井数字化技术在塔里木油田的应用[J]. 录井工程, 2017, 28(4): 1-6.LEI Jun, WANG Shenshi, YANG Yu. Application of digital technology of cutting logging in Tarim oilfield Mud Logging Engineering[J]. Mud Logging Engineering, 2017, 28(4): 1-6.
[3]
王有涛, 何展翔, 陈学国, 等. 基于物性分析建模的时频电磁反演及储层评价——以准北缘石北构造带为例[J]. 石油地球物理勘探, 2022, 57(6): 1489-1497.WANG Youtao, HE Zhanxiang, CHEN Xueguo, et al. Time-frequency electromagnetic data inversion and reservoir evaluation based on physical property analysis modeling: A case study of the Shibei structural belt on the northern margin of the Junggar Basin[J]. Oil Geophysical Prospecting, 2022, 57(6): 1489-1497.
[4]
周游, 张广智, 高刚, 等. 核主成分分析法在测井浊积岩岩性识别中的应用[J]. 石油地球物理勘探, 2019, 54(3): 667-675.ZHOU You, ZHANG Guangzhi, GAO Gang, et al. Application of kernel principal component analysis in well logging turbidite lithology identification[J]. Oil Geophysical Prospecting, 2019, 54(3): 667-675.
[5]
张野, 李明超, 韩帅. 基于岩石图像深度学习的岩性自动识别与分类方法[J]. 岩石学报, 2018, 34(2): 333-342.ZHANG Ye, LI Mingchao, HAN Shuai. Automatic identification and classification in lithology based on deep learning in rock images[J]. Acta Petrologica Sinica, 2018, 34(2): 333-342.
[6]
郑尊凯. 深度学习模型下岩屑图像识别研究[D]. 湖北荆州: 长江大学, 2019.ZHENG Zunkai. Debris Image Recognition Based on Deep Learning Model[D]. Yangtze University, Jingzhou, Hubei, 2019.
[7]
BAKLANOVA O E, BAKLANOV A, SHVETS O Y. Methods and algorithms of computer vision for automated processing of mineral rocks images[C]. 2015 IEEE 10th Jubilee International Symposium on Applied Computational Intelligence and Informatics, 2015，449-454.
[8]
GAO T, WANG W, LIU W, et al. Rock particle image segmentation based on improved normalized cut[J]. International Journal of Control and Automation, 2017, 10(4): 271-286.
[9]
KARIMPOULI S,TAHMASEBI P.Segmentation of digital rock images using deep convolutional autoencoder networks[J].Computers & Geosciences, 2019, 126: 142-150.
[10]
张贤, 李帝铨, 李晋, 等. 基于特征提取与聚类识别的人工源电磁伪随机信号处理方法[J]. 石油地球物理勘探, 2022, 57(4): 973-981, 1008.ZHANG Xian, LI Diquan, LI Jin, et al. CSEM pseudo-random signal processing method based on feature extraction and clustering identification[J]. Oil Geophysical Prospecting, 2022, 57(4): 973-981, 1008.
[11]
于达. 基于局部不变特征和点云配准的目标识别与定位技术研究[D]. 黑龙江哈尔滨: 哈尔滨工业大学, 2018.YU Da. Research on Target Recognition and Location Based on Local Invariant Features and Point Cloud Registration[D]. Harbin Institute of Technology, Harbin, Heilongjiang, 2018.
[12]
戴宗, 罗东红, 谢明英, 等. 基于改进分水岭算法的岩屑扫描图像粒径分析新方法[J]. 中国海上油气, 2019, 31(2): 103-107.DAI Zong, LUO Donghong, XIE Mingying, et al. A new method for particle size analysis of cuttings image based on improved watershed algorithm[J]. China Offshore Oil and Gas, 2019, 31(2): 103-107.
[13]
刘之瑜, 张淑芬, 刘洋, 等. 基于图像梯度的数据增广方法[J]. 应用科学学报, 2021, 39(2): 302-311.LIU Zhiyu, ZHANG Shufen, LIU Yang, et al. Data augmentation method based on image gradient[J]. Journal of Applied Sciences, 2021, 39(2): 302-311.
[14]
崔智勇. 基于深度卷积神经网络的作物病害图像分类研究[D]. 河南新乡: 河南师范大学, 2020.CUI Zhiyong. Classification and Identification of Crop Disease Images Based on Deep Convolutional Neural Network[D]. Henan Normal University, Xinxiang, Henan, 2020.
[15]
程先琼, 蒋科植. 基于深度降噪自编码神经网络的中国大陆地壳厚度反演[J]. 地震学报, 2021, 43(1): 34-47.CHENG Xianqiong, JIANG Kezhi. Inversion of crustal thickness in Chinese mainland based on deep denoising autoencoder neural network[J]. Acta Seismologica Sinica, 2021, 43(1): 34-47.
[16]
张金斗, 李京. 一种结合层次化类别信息的知识图谱表示学习方法[J]. 软件学报, 2022, 33(9): 3331-3346.ZHANG Jindou, LI Jing. Knowledge graph embedding combining with hierarchical type information[J]. Journal of Software, 2022, 33(9): 3331-3346.
[17]
刘江鹏, 牛群峰, 靳毅, 等. 基于高效通道注意力机制与多尺度特征融合的烟丝图像识别方法研究[J]. 河南农业科学, 2022, 51(11): 145-154.LIU Jiangpeng, NIU Qunfeng, JIN Yi, et al. Research on tobacco shred image recognition method based on efficient channel attention mechanism and multi-scale feature fusion[J]. Journal of Henan Agricultural Sciences, 2022, 51(11): 145-154.
HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design[C]. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021,13708-13717.
[20]
丁浩. 基于特殊卷积和注意力机制的生成对抗网络跨视角图像生成算法研究[D]. 江苏南京: 南京邮电大学, 2021.DING Hao. Research on Cross-View Image Synthesis Based on Special Convolution and Attention Mechanism[D]. Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu，2021.
[21]
BADRINARAYANAN V, KENDALL A, CIPOLLA R. SegNet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481-2495.
[22]
梁佳雯. 基于轻量级网络的遥感图像实时语义分割算法研究[D]. 四川成都: 电子科技大学, 2021.LIANG Jiawen. Research on Real-time Semantic Segmentation for Remote Sensing Image Based on Light Weight Network[D]. University of Electronic Science and Technology of China, Chendou, Sichuan, 2021.
[23]
聂聪颖, 唐晶磊. 基于显著特征和全局特征融合的植物识别方法[J]. 计算机工程与设计, 2021, 42(4): 976-984.NIE Congying, TANG Jinglei. Plant recognition method based on fusion of salient feature and global feature[J]. Computer Engineering and Design, 2021, 42(4): 976-984.
[24]
王新杰. 基于深度学习的视频目标跟踪算法研究[D]. 北京: 北京交通大学, 2020.WANG Xinjie. Research on Video Object Tracking Algorithm Based on Deep Learning[D]. Beijing Jiaotong University, Beijing, 2020.
[25]
李明悦, 何乐生, 雷晨, 等. 基于注意力特征融合的SqueezeNet细粒度图像分类模型[J]. 云南大学学报(自然科学版), 2021, 43(5): 868-876.LI Mingyue, HE Lesheng, LEI Chen, et al. Fine-grained image classification model based on attention feature fusion with SqueezeNet[J]. Journal of Yunnan University(Natural Sciences Edition), 2021, 43(5): 868-876.
[26]
候博翔. 基于骨架映射图的人体动作识别与检测[D]. 山东济南：山东大学, 2019.HOU Boxiang. Human Action Recognition and Detection Based on Images Mapped from Skeleton Sequence[D]. Shangdong University, Jinan, Shandong, 2019.
