Design of AI-Based Detection System for Rock Cuttings Fluorescence of Logging
-
摘要:
针对当前荧光录井检测方法存在激活光源单一、定量评估精度较差及检测计算方法复杂等问题，研制了一种基于人工智能的录井岩屑荧光智能检测系统，以便快速检测出含油物质。针对不同岩屑样本的特性，可以根据岩屑类型和面积自由调节灯源波长，并配合工业相机对岩屑样本进行拍摄，采集易于深度学习算法检测的高清图像；使用嵌入于移动端的改进DeepLab v3+算法进行岩屑荧光检测，计算出荧光占比，并在移动设备屏幕上展示出计算结果和检测效果图。不同岩屑样本的测试结果表明，系统对岩屑荧光检测的平均交并比达到72.73%，能够在保证准确性与时效性的同时，实现对岩样中荧光区域的有效量化。基于改进DeepLab v3+算法的岩屑荧光智能监测系统解决了人工探测岩屑荧光过程中存在的不确定因素，能够满足荧光录井技术对岩屑荧光检测的现场应用要求。
Abstract:Existing fluorescent logging detection methods have problems such as single activation light source, limited quantitative evaluation accuracy, and complex detection calculation. To address these issues, an artificial intelligence (AI)-based detection system for rock cuttings fluorescence of logging was developed, so as to detect oily substances rapidly. In order to adapt to the characteristics of different cuttings samples, the lamp source wavelength could be freely adjusted according to the type and area of cuttings, and the cuttings samples could be shot with industrial cameras to collect high-definition images easily detected by deep learning algorithms. An improved DeepLab v3+ algorithm embedded in a mobile device was used to detect cuttings fluorescence, calculate the fluorescence ratio, and display the results and detection images on the mobile device screen. Tests of various cuttings samples show that the system achieves an average intersection over union of 72.73% in detecting cuttings fluorescence, ensuring both accuracy and timeliness while quantifying fluorescent areas in the rock samples. The intelligent detection system for cuttings fluorescence based on the improved DeepLab v3+ algorithm eliminates uncertainties present in manual fluorescence detection processes of cuttings and meets the practical needs of fluorescent logging technology for cuttings fluorescence detection.
-
Keywords:
- fluorescent logging /
- cuttings /
- deep learning /
- image segmentation /
- intelligent detection
-
-
![]()
图 1 岩屑荧光智能检测系统架构
Figure 1. Architecture of intelligent detection system for cuttings fluorescence
![]()
图 2 不同波长和类型灯源下岩屑的荧光效果
Figure 2. Fluorescence effects of cuttings under different wavelengths and types of light sources
表 1 改进前后DeepLab v3+算法对比
Table 1 Comparison of DeepLab v3+ algorithms before and after improvement
算法模型 主干网络 平均交
并比,%参数量/
MB浮点计算
量/GFLOPs检测速
度/fpsDeepLab v3+ Xception 73.15 54.70 83.09 10 DeepLab v3+ Resnet50 77.65 38.72 62.70 34 Improved
DeepLab v3+Mobilenetv3 72.73 2.58 13.50 62 
下载: 导出CSV
表 2 岩屑荧光检测系统测试结果
Table 2 Test results of cuttings fluorescence detection system
取样井 深度/m 样本像素
总数荧光像素
总数荧光岩屑
占比，%系统检测荧
光占比，%2 976 870 850 8 513 3～4 3.93 WZ11-1N-A6S1 3 019 755 133 6 474 3～4 3.35 3 027 821 493 22 557 9～10 10.63 WZ11-4N-B31 4 214 616 363 115 296 50～60 63.07 4 309 604 559 41 969 20～30 24.62 WC13-2-B4H 1 641 834 315 11 038 0～5 5.21 WC19-1-A4S2 3 500 805 420 264 0～1 0.12 3 520 615 942 622 0～1 0.38 3 530 693 679 748 0～1 0.45 3 560 744 152 41 798 10～20 21.28
下载: 导出CSV
-
[1] 吕心愿. 定量荧光录井在石油勘探中的应用[J]. 中国石油和化工标准与质量,2019,39(12):165–166. doi: 10.3969/j.issn.1673-4076.2019.12.080 LYU Xinyuan. Application of quantitative fluorescence logging in petroleum exploration[J]. China Petroleum and Chemical Standard and Quality, 2019, 39(12): 165–166. doi: 10.3969/j.issn.1673-4076.2019.12.080
[2] 王志战. 中国石化录井技术新进展与发展方向思考[J]. 石油钻探技术,2023,51(4):124–133. doi: 10.11911/syztjs.2023027 WANG Zhizhan. Thoughts for new progress and development directions of Sinopec’s surface logging technology[J]. Petroleum Drilling Techniques, 2023, 51(4): 124–133. doi: 10.11911/syztjs.2023027
[3] 吴胜和,蔡正旗,施尚明. 油矿地质学[M]. 4版. 北京:石油工业出版社,2011:22-69. WU Shenghe, CAI Zhengqi, SHI Shangming. Oil geology[M]. 4th ed. Beijing: Petroleum Industry Press, 2011: 22-69.
[4] 任特. PDC钻头条件下石油录井中岩屑岩性识别方法研究[J]. 中国石油和化工标准与质量,2023,43(21):85–87. doi: 10.3969/j.issn.1673-4076.2023.21.029 REN Te. Study on cuttings lithology identification methods in petroleum logging under PDC bit conditions[J]. China Petroleum and Chemical Standard and Quality, 2023, 43(21): 85–87. doi: 10.3969/j.issn.1673-4076.2023.21.029
[5] 安文武,苏金龙,刘树坤,等. 定量荧光录井技术在石油勘探中的应用探讨[J]. 录井技术,2000,11(4):35–42. AN Wenwu, SU Jinlong, LIU Shukun, et al. The application discussion of quantitative fluorescence logging technology in oil exploration[J]. Mud Logging Engineering, 2000, 11(4): 35–42.
[6] HUO Fengcai, LI Ang, ZHAO Xiaoqing, et al. Novel lithology identification method for drilling cuttings under PDC bit condition[J]. Journal of Petroleum Science and Engineering, 2021, 205: 108898. doi: 10.1016/j.petrol.2021.108898
[7] 湛建利,丁群,桂传松,等. 录井岩样荧光面积定量化分析软件开发[J]. 录井工程,2022,33(2):30–34. doi: 10.3969/j.issn.1672-9803.2022.02.006 ZHAN Jianli, DING Qun, GUI Chuansong, et al. Development of fluorescence area quantitative analysis software for mud logging rock samples[J]. Mud Logging Engineering, 2022, 33(2): 30–34. doi: 10.3969/j.issn.1672-9803.2022.02.006
[8] 夏文鹤,谢万洋,唐印东,等. 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, et al. Intelligent and efficient lithology identification based on image features of returned cuttings[J]. Oil Geophysical Prospecting, 2023, 58(3): 495–506.
[9] 孙伟峰,冯剑寒,张德志,等. 结合LSTM自编码器与集成学习的井漏智能识别方法[J]. 石油钻探技术,2024,52(3):61–67. doi: 10.11911/syztjs.2024006 SUN Weifeng, FENG Jianhan, ZHANG Dezhi, et al. An intelligent lost circulation recognition method using LSTM-autoencoder and ensemble learning[J]. Petroleum Drilling Techniques, 2024, 52(3): 61–67. doi: 10.11911/syztjs.2024006
[10] 孙伟峰,刘凯,张德志,等. 结合钻井工况与Bi-GRU的溢流与井漏监测方法[J]. 石油钻探技术,2023,51(3):37–44. doi: 10.11911/syztjs.2023043 SUN Weifeng, LIU Kai, ZHANG Dezhi, et al. A kick and lost circulation monitoring method combining Bi-GRU and drilling conditions[J]. Petroleum Drilling Techniques, 2023, 51(3): 37–44. doi: 10.11911/syztjs.2023043
[11] CHEN L C, ZHU Yukun, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Computer Vision: ECCV 2018. Cham: Springer, 2018: 833-851.
[12] 王聪,李恒,薛晓军,等. 基于OTSU分割和融合的非均匀光照水下图像增强[J]. 光电子·激光,2022,33(1):30–36. WANG Cong, LI Heng, XUE Xiaojun, et al. Underwater image enhancement with nonuniform illumination based on OTSU segmentation and fusion[J]. Journal of Optoelectronics·Laser, 2022, 33(1): 30–36.
[13] HOWARD A, SANDLER M, CHEN Bo, et al. Searching for MobileNetV3[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2019: 1314-1324.
[14] 张益明,张繁昌,丁继才,等. 基于混合深度学习网络的致密砂岩甜点预测[J]. 石油物探,2021,60(6):995–1002. doi: 10.3969/j.issn.1000-1441.2021.06.013 ZHANG Yiming, ZHANG Fanchang, DING Jicai, et al. Sweet spot prediction in tight sand reservoirs by a hybrid deep-learning network[J]. Geophysical Prospecting for Petroleum, 2021, 60(6): 995–1002. doi: 10.3969/j.issn.1000-1441.2021.06.013
[15] 李昂. PDC的钻头条件下岩屑图像含油岩性识别方法研究[D]. 大庆:东北石油大学,2022. LI Ang. Research on lithology identification method of cuttings image under PDC bit condition[D]. Daqing: Northeast Petroleum University, 2022.
[16] 姚树新,程浩然,熊钊,等. 基于岩屑定量数字化分析的吉木萨尔页岩油储层表征方法[J]. 石油钻采工艺,2022,44(1):117–122. YAO Shuxin, CHENG Haoran, XIONG Zhao, et al. Method characterizing shale oil reservoirs in Jimsar based on quantitative digital analysis of cuttings[J]. Oil Drilling & Production Technology, 2022, 44(1): 117–122.
[17] 夏文鹤,唐印东,李皋,等. 砂样图像岩屑自动分割提取方法[J]. 岩石矿物学杂志,2023,42(6):894–906. XIA Wenhe, TANG Yindong, LI Gao, et al. Automatic segmentation and extraction method for rock debris in sandstone sample images[J]. Acta Petrologica et Mineralogica, 2023, 42(6): 894–906.
[18] 曹凯奇,张凌浩,徐虹,等. 基于改进DeepLab V3+的引导式道路提取方法及在震源点位优化中的应用[J]. 西安石油大学学报(自然科学版),2024,39(2):128–142. doi: 10.3969/j.issn.1673-064X.2024.02.016 CAO Kaiqi, ZHANG Linghao, XU Hong, et al. Guided road extraction method based on improved DeepLab V3+ and its application in optimization of source positions[J]. Journal of Xi'an Shiyou University(Natural Science Edition), 2024, 39(2): 128–142. doi: 10.3969/j.issn.1673-064X.2024.02.016
[19] 朱丽娟,冯春,刘芯言,等. 融合注意力与残差网络的石油管材失效宏观影像智能识别方法[J]. 石油管材与仪器,2024,10(1):33–40. ZHU Lijuan, FENG Chun, LIU Xinyan, et al. Intelligent analysis of macro failure image of oil country tubular goods[J]. Petroleum Tubular Goods & Instruments, 2024, 10(1): 33–40.
[20] HOWARD A G, ZHU Menglong, CHEN Bo, et al. MobileNets: Efficient convolutional neural networks for mobile vision applications[EB/OL]. (2017-04-17)[2023-04-28]. https://arxiv.org/abs/1704.04861.
[21] CHOLLET F. Xception: Deep learning with depthwise separable convolutions[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2017: 1800-1807.
[22] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2016: 770-778.
-
期刊类型引用(8)
1. 赵显威. 直井段偏移对后期定向钻井作业的影响探讨. 西部探矿工程. 2020(10): 77-78 . 
百度学术
2. 方勇. 定向钻井提速技术分析及应用. 中国石油和化工标准与质量. 2019(01): 206-207 . 百度学术
3. 路宗羽，赵飞，雷鸣，邹灵战，石建刚，卓鲁斌. 新疆玛湖油田砂砾岩致密油水平井钻井关键技术. 石油钻探技术. 2019(02): 9-14 . 本站查看
4. 李超，窦亮彬，李振兴，康恺，周鑫，韩田兴. 青西油田深井钻井提速技术与应用. 断块油气田. 2018(03): 376-380 . 百度学术
5. 高军，吴娜，董龙. 青西油田深井配套工艺技术研究与应用. 化工管理. 2018(23): 98 . 百度学术
6. 席博. 分析定向钻井技术常见问题及处理措施. 中国石油和化工标准与质量. 2017(06): 114-115 . 百度学术
7. 程天辉，王维韬，王树超. 塔里木泛哈拉哈塘地区扭力冲击钻井技术. 石油钻采工艺. 2017(01): 53-56 . 百度学术
8. 张瑜. 定向钻井技术常见问题与对策. 当代化工研究. 2016(02): 12-13 . 百度学术
其他类型引用(1)
计量
- 文章访问数: 135
- HTML全文浏览量: 20
- PDF下载量: 56
- 被引次数: 9
