Research of Defoaming Detection in Shale Foam Drainage Wells Based on Machine Vision
DOI:
https://doi.org/10.54691/djwae728Keywords:
Foam drainage gas production; Shale gas; Foam height; Detecting system; Machine vision.Abstract
Shale gas is generally faced with the problem of bottom-hole accumulation in the middle and late stage of exploitation. Foam drainage gas production technology is one of the means to solve the problem of bottom-hole accumulation and restore the normal production of gas Wells. When the foam mixture reaches the ground, it needs to be defoamed. At present, the defoaming effect is mainly evaluated by regular manual sampling from the separator sampling port. In order to reduce the work intensity, realize automatic detection and improve the detection accuracy, a set of anti-foam detection system based on machine vision was developed and field test was carried out. The results show that: The defoaming detection system meets the requirements of field conditions, and the system has strong stability and reliability; The defoaming detection model based on DeepLabV3+ has high accuracy, and the processed images are similar to the manual sampling results; The minimum difference between the foam height measurement system and the manual measurement is 0mm, the maximum difference is 8.60mm, and the data with the difference of 5mm and below account for 94.4%, that is, the accuracy rate reaches 94.4%. It is concluded that the development and test of the defoaming detection system has verified the feasibility of using machine vision technology for defoaming detection, and has practical significance for promoting the intelligent development of the defoaming detection process and improving the efficiency of shale gas extraction.
Downloads
References
[1] ZHAO Kang, CHEN Minfeng, WANG Yiwen, et al. Production decline rule and recoverable reserves prediction of TY water-bearing shale gas reservoir[J] Fault-Block Oil & Gas Field, 2024, 31(3):395-402.
[2] CHEN Chao, CHEN Xuezhong, CHEN Man, et al. Research and application of intelligent integrated composite drainage and production process system for shale gas wells[J]. Fault-Block Oil & Gas Field, 2024, 31(6):1129-1136.
[3] CHEN Xiaolu, LYU Zhenhu, LU Zongyu, et al. Research and application of key technologies for volume fracturing of deep tight conglomerate reservoirs in Mahu Oilfield[J]. Fault-Block Oil & Gas Field, 2024, 31(6):1098-1104.
[4] JIANG Yixin, LIU Cheng, GAO Haohong, et al. Foam drainage gas recovery technology and its application in the shale gas wells of Zhaotong National Shale Gas Demonstration Area[J]. Natural Gas Industry, 2021, 41(S1): 164-170.
[5] FEI Haihong. Technique of Gas Recovery by Water Drainage for Zhujiadun Gas Pool in Yancheng, Jiangsu[J]. Fault-Block Oil & Gas Field, 2006, (6):73-75+93-94.
[6] ZHAI Zhongbo, CHEN Gang, ZHU Zhixian, et al. Onset time of lift-assisted foam drainage gas recovery in adjacent wells [J]. Natural Gas Exploration and Development, 2024, 47(2): 68-72.
[7] LI Jiaxin, ZHANG Ningbo, ZHOU Chengxiang. Application of foam drainage-gas recovery technology in shale gas wells: A case study of southern Pingqiao[J]. Reservoir Evaluation and Development, 2020, 10(5):91-97.
[8] QU Chaochao, LIU Zhengzhong, YIN Hongyao, et al. A new anti-condensate foaming agent for drainage gas recovery[J]. Acta Petrolei Sinica, 2020, 41(7): 865-874.
[9] HAN Yong, GAO Shiju, MOU Chunguo, et al. Optimization research of the solid defoaming process in Sulige Field[J]. Drilling and Production Technology, 2020, 43(6): 62-64.
[10] JIANG Zeyin, LI Wei, LUO Xin, et al. Foam drainage gas recovery technology for shale-gas platform wells[J]. Natural Gas Industry, 2020, 40(4): 85-90.
[11] LIANG Zheng, DENG Xiong, LV Zhizhong, et al. Project design of monitoring system of defoaming effect for foaming drainage gas recovery[J]. Oil Field Equipment, 2009, 38(8): 17-20.
[12] ZHENG Rui, LIANG Jing, LI Ying, et al. The cloud monitoring system of wellhead foam content used for foam drainage gas recovery wells[J]. Natural Gas Industry, 2021, 41(S1): 171-176.
[13] GUO Liang, WANG Ruiyu, CHENG Changxu, et al. Application of foam content monitoring system in foam drainage shale gas wells[J]. Natural Gas Industry, 2023, 43(12): 63-70.
[14] ZHANG Jinsong, QU Zhe, YUE Mengkun, et al. Machine vision system for high-temperature wind tunnel: Principle, design and application(in Chinese). Sci Sin Tech, 2020, 50(6):742-762.
[15] WU Jinlong, WU Hongqi, LI Hao, et al. Segmentation of Buckwheat by UAV Based on Improved Lightweight DeepLabV3+ at Seedling Stage[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(5):186-195.
[16] HU Jinwei, XI Zhenghao, XU Guozhong, et al. An improved automated testing model for maceral groups in coals based on DeeplabV3+[J]. Coal Geology & Exploration, 2023, 51(10):27-36.
[17] FANG Jiaji, LAI Yibo, TANG Zhengtao, et al. Lightweight power line semantic segmentation method based on DeepLabv3+[J]. Computer Era, 2023, (9):19-23+28.
[18] JING Zhuangwei, GUAN Haiyan, PENG Daifeng, et al. Survey of research in image semantic segmentation based on deep neural network[J]. Computer Engineering, 2020, 46(10):1-17.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Frontiers in Science and Engineering

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.