人工智能测井:基础、原理、技术及应用  

Artificial intelligence logging:Fundamental,principle,technique,and application

作　　者：程希 任战利[4] CHENG Xi;REN Zhanli(School of Earth Sciences and Engineering,Xi’an Shiyou University,Xi’an 710065,China;State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation(Southwest Petroleum University),Chengdu 610500,China;Academician and Expert Worksta-tion,Xi’an Shiyou University,Xi’an 710065,China;Department of Geology,Northwest University,Xi’an 710069,China)

机构地区：[1]西安石油大学地球科学与工程学院,陕西西安710065 [2]油气藏地质及开发工程国家重点实验室(西南石油大学),四川成都610500 [3]西安石油大学院士专家工作站,陕西西安710065 [4]西北大学地质学系,陕西西安710069

出　　处：《煤田地质与勘探》2024年第8期145-164,共20页Coal Geology & Exploration

基　　金：油气藏地质及开发国家重点实验室(西南石油大学)开放基金项目(PLN2022-14);国家自然科学基金项目(42272152)。

摘　　要：【背景】油气勘探开发的智能化已成为油气工业发展趋势与研究热点。人工智能测井(Artificial intelligence logging,AIL)具有解决非常规油气资源及深地深海等复杂环境勘探开发难题的巨大潜力。然而,AIL技术发展的驱动模式,以及技术发展的基础、实现原理、技术组成以及应用场景还没有开展研究。【目的和方法】为构建完善的AIL测井体系生态,充分挖掘并展现AIL技术的潜力与价值,采用文献分析、理论研究、技术分析以及实例验证的方法。首先从多个维度出发,深入剖析了测井技术与人工智能(Artificial intelligence,AI)融合发展的关键因素,并据此定义了AIL。随后,系统探讨了AIL的基础理论框架、硬件算力需求以及数据物理模型,并通过知识发现的视角,详细阐述了测井方法、仪器、岩石物理及解释等环节在AIL体系中的功能实现机制。在技术层面,深入分析了包括测井大数据技术、智能与快速算法、测井知识图谱、数字孪生、智能仪器及测井物联网在内的多项关键技术,并指出物理模型与智能算法是推动AIL技术发展的核心驱动力。根据AI算法的原理与特性,系统梳理了AIL在测井方法、仪器、采集作业及解释等方面的关键技术,并构建了测井知识图谱树状图及其求解流程。【结果和结论】通过实证研究,验证了AIL在致密砂岩岩性识别及测井模拟中的优势,其精度达到93.8%,明显优于传统方法。在测井评价方面,AIL可同时实现储层和流体的识别,这充分说明了AIL技术的巨大发展潜力与应用优势。基于AIL技术的关键节点,展望了测井技术发展的第五个发展阶段,即智能测井。研究成果为AI在测井领域的深度融合与广泛应用提供坚实的理论基础与实践指导,对促进人工智能测井技术的推广及发展具有重要意义。[Background]Intelligent hydrocarbon exploration and exploitation have become a trend and hot research topic in the oil and gas industry.Artificial intelligence logging(AIL)exhibits considerable potential to address challenges in the explore-exploit of unconventional hydrocarbon resources,as well as resources in complex environments in the deep earth and deep ocean.However,the driving mode,fundamental,implementation principle,structure,and application scenarios of AIL remain understudied.[Objective and Methods]To build a comprehensive ecology of the AIL system and thoroughly explore and reveal the potential and value of AIL,this study employed methods like literature analysis,theoretical research,technical analysis,and verification using cases.First,this study delved into the critical factors influencing the integrated development of logging technology and AI from multiple dimensions,defining AIL accordingly.Subsequently,it systematically explored the general theoretical framework,hardware arithmetic requirements,and data and physical models of AI.From the perspective of knowledge discovery,this study detailed the function implementation mechanisms of logging technology,instrumentation,petrophysics,and interpretation in the AIL system.Furthermore,it conducted an in-depth analysis of several critical technologies including log-related big data techniques,intelligent and fast algorithms,log knowledge graph,digital twins,intelligent instrumentation,and the Internet of things(IoT)of logs.Accordingly,this study posited that physical models and intelligent algorithms emerge as the core force driving the development of AIL.Based on the principles and characteristics of AI algorithms,this study systematically organized critical AIL technologies in terms of logging technology,instrumentation,acquisition operations,and interpretation,constructing the dendrogram and solving process of log knowledge graph.[Results and Conclusions]The empirical research reveals that AIL enjoys advantages in terms of the lithologic identificati

关 键 词：人工智能测井 测井大数据 机器学习 地层参数反演 复杂岩性识别 

分 类 号：P631[天文地球—地质矿产勘探]