Research on Architecture of Intelligent Logging Interpretation Software Platform
-
摘要:
智能化测井解释技术为油气开发提供了新的技术途径，但实际生产过程中由于受配置环境等因素影响算法运行效率低，为此开展了适用于智能化测井解释的分布式架构技术研究。从测井软件平台的应用开发角度出发，借鉴大数据相关技术在互联网行业应用的成功案例，采用分布式处理的技术思路，开展了系统设计与优化、人工智能支持模块开发及智能算法应用测试等工作，初步形成了基于测井软件平台的线上集群分布式处理机制，为智能算法与测井软件的高效融合提供了技术积累。算法测试结果表明，该机制能够减轻软件运行高迭代性智能算法时的内存、环境等压力，缩短大体量数据处理解释所需的时间。分布式架构可作为智能化测井解释软件的可行方案，也为智能化测井解释提供了技术支撑。
Abstract:Intelligent logging interpretation technology provides new technical method for oil and gas development. However, in the actual production process, the algorithm can be inefficient due to configuration environment and other factors. Therefore, the distributed architecture technology suitable for intelligent logging interpretation was studied. From the perspective of application and development of logging software platform, the successful application cases of big data-related technologies in the internet industry were used for reference, and the technical idea of distributed processing was adopted to carry out system design and optimization, artificial intelligence support module development, and intelligent algorithm application testing, etc. As a result, an online cluster distributed processing mechanism based on a logging software platform was initially formed. It provided technical accumulation for the efficient fusion of intelligent algorithms and logging software. The algorithm test results showed that this mechanism could effectively reduce the pressure of memory and environment when the software runs the highly iterative intelligent algorithm and effectively shorten the time required for processing and interpretation of large volume data. Distributed architecture can be used as a feasible solution for intelligent logging interpretation software, and the research results provide technical support for intelligent logging interpretation.
-
-
表 1 小数据集测试记录
Table 1 Small data set test records
类别 处理方法 处理时间/s 本地 线上 传统算法 泥质砂岩水淹分析 0.68 1.29 岩性分析 0.92 1.78 智能算法 AdaBoost地层预测 2.05 3.28 随机森林分类算法 4.00 4.66 
下载: 导出CSV
表 2 大数据集测试记录
Table 2 Big data set test records
方法类别 处理方法 处理时间/s 本地 线上 传统算法 泥质砂岩水淹分析 13.390 7.930 岩性分析 21.240 8.150 智能算法 AdaBoost地层预测 29.421 9.980 随机森林分类算法 35.030 11.540
下载: 导出CSV
-
[1] 刘卓,张宇,张宏洋. 国内外数字油田技术发展趋势及策略[J]. 石油科技论坛,2020,39(4):62–67. LIU Zhuo, ZHANG Yu, ZHANG Hongyang. Trends and strategies of Chinese and foreign digital oilfield technological development[J]. Petroleum Science and Technology Forum, 2020, 39(4): 62–67.
[2] 尹成芳,侯亮,郭晓霞. 2022国外测井技术发展现状与趋势[J]. 世界石油工业,2022,29(6):54–62. YIN Chengfang, HOU Liang, GUO Xiaoxia. Present status and trends in development of foreign well logging technologies in 2022[J]. World Petroleum Industry, 2022, 29(6): 54–62.
[3] 郭广山,郭建宏,孙立春,等. 基于随机森林算法的煤层含气量三维精细建模[J]. 中国海上油气,2022,34(4):156–163. GUO Guangshan, GUO Jianhong, SUN Lichun, et al. 3D fine modeling of coal seam gas content based on random forest algorithm[J]. China Offshore Oil and Gas, 2022, 34(4): 156–163.
[4] 张涛,李艳萍,刘晓宇,等. 基于自适应粒子群优化最小二乘支持向量机的深层变质岩测井岩性识别[J]. 地球物理学进展,2023,38(1):382–392. ZHANG Tao, LI Yanping, LIU Xiaoyu, et al. Lithology interpretation of deep metamorphic rocks with well logging based on APSO-LSSVM algorithm[J]. Progress in Geophysics, 2023, 38(1): 382–392.
[5] 潘少伟,王朝阳,张允,等. 基于长短期记忆神经网络补全测井曲线和混合优化XGBoost的岩性识别[J]. 中国石油大学学报(自然科学版),2022,46(3):62–71. PAN Shaowei, WANG Zhaoyang, ZHANG Yun, et al. Lithology identification based on LSTM neural networks completing log and hybrid optimized XGBoost[J]. Journal of China University of Petroleum(Edition of Natural Science), 2022, 46(3): 62–71.
[6] 张家臣,邓金根,谭强,等. 基于XGBoost的测井曲线重构方法[J]. 石油地球物理勘探,2022,57(3):697–705. ZHANG Jiachen, DENG Jingen, TAN Qiang, et al. Reconstruction of well logs based on XGBoost[J]. Oil Geophysical Prospecting, 2022, 57(3): 697–705.
[7] 王民,杨金路,王鑫,等. 基于随机森林算法的泥页岩岩相测井识别[J]. 地球科学,2023,48(1):130–142. WANG Min, YANG Jinlu, WANG Xin, et al. Identification of shale lithofacies by well logs based on random forest algorithm[J]. Earth Science, 2023, 48(1): 130–142.
[8] 康正明,秦浩杰,张意,等. 基于LSTM神经网络的随钻方位电磁波测井数据反演[J]. 石油钻探技术,2023,51(2):116–124. KANG Zhengming, QIN Haojie, ZHANG Yi, et al. Data inversion of azimuthal electromagnetic wave logging while drilling based on LSTM neural network[J]. Petroleum Drilling Techniques, 2023, 51(2): 116–124.
[9] 杨耀忠,邴绍强,马承杰,等. 基于集成学习的油藏井筒一体化智能诊断模型[J]. 石油钻采工艺,2022,44(3):383–389. YANG Yaozhong, BING Shaoqiang, MA Chengjie, et al. Oil reservoir-well-integrated intelligent diagnostic model based on ensemble learning[J]. Oil Drilling & Production Technology, 2022, 44(3): 383–389.
[10] 王清媛,黄全舟. 浅析机器学习在石油测井领域的研究进展[J]. 清洗世界,2021,37(3):120–122. WANG Qingyuan, HUANG Quanzhou. Research progress of machine learning in petroleum logging[J]. Cleaning World, 2021, 37(3): 120–122.
[11] 宋梦馨,冯梅. 石油专业软件云平台构建及应用实践[J]. 信息系统工程,2019(12):25–27. SONG Mengxin, FENG Mei. Construction and application practice of petroleum professional software cloud platform[J]. China CIO News, 2019(12): 25–27.
[12] 王保宁. 云计算在中石油信息化服务平台建设中的应用研究[J]. 电脑知识与技术,2019,15(34):80–81. WANG Baoning. Research on the application of cloud computing in the construction of CNPC information service platform[J]. Computer Knowledge and Technology, 2019, 15(34): 80–81.
[13] 马涛,张仲宏,王铁成,等. 勘探开发梦想云平台架构设计与实现[J]. 中国石油勘探,2020,25(5):71–81. MA Tao, ZHANG Zhonghong, WANG Tiecheng, et al. Architecture design and implementation of E&P Dream Cloud platform[J]. China Petroleum Exploration, 2020, 25(5): 71–81.
[14] 李国军, 周军, 钟吉彬, 等. 测井智能解释软件平台设计[C]//第六届数字油田国际学术会议论文集. 西安: 长安大学, 2019: 173-178. LI Guojun, ZHOU Jun, ZHONG Jibin, et al. Design of intelligent logging interpretation software platform[C]//Proceedings of the 6th International Conference on Digital Oilfield. Xi’an: Chang’an University, 2019: 173-178.
[15] 石玉江,刘国强,钟吉彬,等. 基于大数据的测井智能解释系统开发与应用[J]. 中国石油勘探,2021,26(2):113–126. SHI Yujiang, LIU Guoqiang, ZHONG Jibin, et al. Development and application of intelligent logging interpretation system based on big data[J]. China Petroleum Exploration, 2021, 26(2): 113–126.
[16] ANONYMOUS. Schlumberger unveils new version Techlog 2011 at annual symposium[J]. Ocean News & Technology, 2011, 17(6): 55.
[17] 蒋云鹏, 付鑫, 董红, 等. 人工智能技术在X区块水淹层快速解释中的初步应用[C]//第七届数字油田国际学术会议论文集. 西安: 长安大学, 2021: 66-72. JIANG Yunpeng, FU Xin, DONG Hong, et al. Preliminary application of artificial intelligence technology in rapid interpretation of flooded layer in Block X[C]//Proceedings of the 7th International Conference on Digital Oilfield. Xi’an: Chang’an University, 2021: 66-72.
[18] 姜世一,孙盼科,张林,等. 基于径向基—多层感知器神经网络联合的复杂岩相智能识别与表征[J]. 天然气工业,2022,42(9):47–62. JIANG Shiyi, SUN Panke, ZHANG Lin, et al. Intelligent identification and characterization of complex lithofacies based on radial basis-multilayer perception neural network joint model[J]. Natural Gas Industry, 2022, 42(9): 47–62.
[19] 刘凯,邹正银,王志章,等. 基于机器学习的火山岩岩性智能识别及预测[J]. 特种油气藏,2022,29(1):38–45. LIU Kai, ZOU Zhengyin, WANG Zhizhang, et al. Intelligent identification and prediction of lithology of volcanic reservoirs based on machine learning[J]. Special Oil & Gas Reservoirs, 2022, 29(1): 38–45.
[20] 韩玉娇. 基于AdaBoost机器学习算法的大牛地气田储层流体智能识别[J]. 石油钻探技术,2022,50(1):112–118. HAN Yujiao. Intelligent fluid identification based on the AdaBoost machine learning algorithm for reservoirs in Daniudi Gas Field[J]. Petroleum Drilling Techniques, 2022, 50(1): 112–118.
[21] 窦帅,李子扬,朱家佳,等. 分布式计算系统中的算法集成方法[J]. 计算机系统应用,2021,30(3):110–116. DOU Shuai, LI Ziyang, ZHU Jiajia, et al. Algorithm integration in distributed computing system[J]. Computer Systems & Applications, 2021, 30(3): 110–116.
[22] 胡常礼,邵剑飞. 基于分布式计算框架的机器学习系统分析[J]. 电视技术,2021,45(11):115–118. HU Changli, SHAO Jianfei. Analysis of machine learning system based on distributed computing framework[J]. Video Engineering, 2021, 45(11): 115–118.
[23] 毛娜. 基于Hadoop的石油大数据平台设计[J]. 信息技术,2022(2):145–150. MAO Na. Design of oil big data platform based on Hadoop[J]. Information Technology, 2022(2): 145–150.
-
期刊类型引用(13)
1. 王信，谭春，王志彬，罗玉财，周燚，张民立，王威，贾东民. 河探1井超高密度钻井液技术. 钻井液与完井液. 2023(02): 193-201 . 
百度学术
2. 黄熠，刘和兴，刘智勤，彭巍，徐超. 南海西部浅层大位移水平井钻井关键技术与实践. 中国海上油气. 2023(06): 115-123 . 百度学术
3. 伍鹏常. JS203-4HF井套管遇卡原因分析及处理工艺. 西部探矿工程. 2021(02): 55-58 . 百度学术
4. 彭巍，刘智勤，管申，徐超，郑浩鹏. 涠洲W油田多压力系统储层定向井钻井液优化技术. 中国海上油气. 2021(02): 164-171 . 百度学术
5. 张健. 新型抗高温高密度有机盐钻井液体系研究. 能源化工. 2021(06): 62-66 . 百度学术
6. 徐明磊，佟乐，杨双春，张同金，ELAMAN，刘阳. 环保型耐高温无固相钻井液体系研究进展. 应用化工. 2020(08): 2063-2067+2074 . 百度学术
7. 彭巍，刘智勤，王小龙，徐超，任冠龙. 超高井斜水平井钻井技术在复杂断块油田的应用. 承德石油高等专科学校学报. 2019(02): 13-15+75 . 百度学术
8. 刘智勤，余意，徐一龙，郑浩鹏，杨玉豪. 莺-琼盆地新型高温高压水基钻井液技术. 地球科学. 2019(08): 2729-2735 . 百度学术
9. 郝少军，徐珍焱，郭子枫，安小絮，张芸，王波，江林. 昆2加深井超高温聚胺有机盐钻井液技术. 钻井液与完井液. 2019(04): 449-453 . 百度学术
10. 凡帆，刘伟，贾俊. 长北区块无土相防水锁低伤害钻井液技术. 石油钻探技术. 2019(05): 34-39 . 本站查看
11. 向雄，杨洪烈，刘喜亮，由福昌，周姗姗. 南海西部超浅层气田水平井EZFLOW无固相弱凝胶钻井液研究与应用. 石油钻探技术. 2018(02): 38-43 . 本站查看
12. 张珍. ZX105井卡套管事故原因分析及处理工艺. 钻井液与完井液. 2018(03): 84-88 . 百度学术
13. 林四元，李中，黄熠，罗鸣，郭伟. 高性能水基钻井液在莺歌海盆地高温高压井的应用. 钻井液与完井液. 2018(02): 44-48 . 百度学术
其他类型引用(2)
计量
- 文章访问数: 226
- HTML全文浏览量: 137
- PDF下载量: 97
- 被引次数: 15
