Research Progress and the Prospect of Intelligent Drilling and Completion Technologies
-
摘要:
智能钻完井技术是钻完井工程与人工智能、大数据、云计算等先进技术的有机融合,可实现油气钻完井过程的精细表征、决策优化和闭环调控,有望大幅提升钻完井效率、储层钻遇率和油气采收率,是油气领域的研究前沿和热点。从工程实际出发构建了油气钻完井人工智能应用场景,根据钻完井工程与人工智能技术的融合深度划分了智能钻完井技术的发展层次;分析了国内外智能钻完井理论与技术的研究现状,结合人工智能技术和钻完井工程的发展趋势提出了中长期发展规划,并凝练了智能钻完井技术研究面临的难题和重点攻关方向,以期为推进我国智能钻完井技术的基础理论研究和推广应用提供参考。
Abstract:Intelligent drilling and completion technologies are the integration of drilling and completion engineering with Artificial Intelligence (AI), Big Data, cloud computing, and other advanced technologies. They can achieve fine characterization, optimal decision-making, and closed-loop control of oil and gas drilling and completion and are expected to significantly improve drilling and completion efficiency, reservoir drilling rate, and oil and gas recovery efficiency. Therefore, they are the research frontier and hot spot in the oil and gas field. In this paper, the application scenario system of AI in oil and gas drilling and completion was constructed from the engineering practice. Then, the development level of intelligent drilling and completion technologies was divided according to the integration degree of drilling and completion engineering with AI. Furthermore, the research status of intelligent drilling and completion theories and technologies both in China and abroad was discussed, with a medium- and long-term development plan being proposed according to the development trend of AI and drilling and completion engineering. Finally, the problems and key directions of intelligent drilling and completion technologies were summarized. The paper serves as a reference for accelerating the basic theoretical research and application of intelligent drilling and completion technologies in China.
-
目前全球油气勘探开发已进入常规油气稳定上产、非常规油气快速发展阶段[1],页岩油作为非常规油气资源的重要组成部分和典型代表,拥有巨大可采的资源基础、逐步成熟的开发技术和不断攀升的工业产量,正成为全球非常规油气开发的亮点,是继页岩气突破后的又一热点领域[2-6]。目前,以北美二叠(Permian)、巴肯(Bakken)、鹰滩(Eagle Ford)等为代表的页岩油已实现了规模效益开发,进而推动了美国能源独立,改变了世界能源格局。我国页岩油资源丰富,自2010年开始开发页岩油以来已取得了重大突破和显著进展,但整体仍面临资源品质差、单井产量低、投资成本高等开发难题,如何实现页岩油开发大幅降本增效,推动页岩油规模效益开发,对于保障我国能源安全具有重要意义。为此,分析了我国页岩油开发在降本增效方面所面临的挑战,进而剖析了在低油价时期,美国通过理念转变、技术创新、管理创新、市场运作等多方聚力,实现二叠盆地页岩油大幅降本增效、规模效益开发的成功经验与启示,提出了页岩油甜点识别与评价新方法、差异化压裂优化设计和全生命周期开发优化等3项关键技术,以实现我国页岩油开发降本增效、规模效益开发的目的。
1. 我国页岩油开发降本增效面临的挑战
我国页岩油资源丰富,估算中高成熟度页岩油地质资源量约132×108 t,是我国未来石油勘探开发最为主要的接替资源[7-8]。目前,我国页岩油开发在储集层类型、源储关系、甜点主控因素以及页岩油聚集类型等方面已形成较为系统的认识,并提出了以水平井规模重复“压采”开发为主导的一体化开发模式,主要包括“一体化”设计、“平台式”长水平段水平井钻井、“规模化”体积压裂、“重复式”改造、“控制式”采油、“工厂化”作业、“集中式”地面建设等关键技术[8-15],有力地支撑了我国陆相页岩油藏勘探开发,已累计建成300×104 t以上产能。但是,与北美页岩油开发相比,我国页岩油开发在资源品质、开发技术、配套设施和市场化程度等方面存在诸多挑战。
1)页岩油资源品质。我国页岩油藏主要为陆相页岩油藏,各页岩油区块虽然整体资源规模较大,但具有平面上有利区分布面积相对偏小、纵向上主力层薄且分散,储层岩石类型多、物性较差、非均质性强,含油饱和度差异大,原油密度、气油比、压力系数分布范围宽,岩石脆性、地应力差变化大等特点。我国和北美典型页岩油藏的主要特征对比见表1[5,16]。
表 1 我国和北美典型页岩油藏主要特征对比Table 1. Comparison on the main characteristics of typical shale oil reservoirs in China and the North America油藏名称 有利面积/(104 km2) 资源量/(108t) 厚度/m 孔隙度,% 渗透率/mD 岩性 储集层宏观分布特征 美国Bakken 7.0 566.0 5~55 5~13 0.1~1.0 白云质-泥质粉砂岩 平面分布范围广,纵向分布层系集中 美国Eagle ford 4.0 30~90 2~12 <0.1 泥灰岩 鄂尔多斯盆地延长组(长7段) 2.0~5.0 35.5~40.6 20~80 2~12 0.01~1.0 粉细砂岩 分布整体范围较广,但单层厚度薄、纵向不集中、横向不连续 松辽盆地扶余油层 1.5~2.0 19.0~21.3 5~30 2~15 0.6~1.0 粉细砂岩 准噶尔盆地芦草沟组 0.7~1.5 15.0~20.0 80~200 3~178 <0.1,占90% 灰质粉砂岩,灰质白云岩 油藏名称 原油密度/(g·L–1) 原油黏度/(mPa·s) 气油比 压力系数 初期日产油/t 单井最终可采油量/(104m3) 美国Bakken 0.81~0.83 0.15~0.45 100~1 000 1.20~1.80 35.0~250.0 1.80~10.20 美国Eagle ford 0.82~0.87 0.17~0.58 500~15 000 1.35~1.80 13.0~65.0 0.50~3.10 鄂尔多斯盆地延长组(长7段) 0.80~0.86 1.00~2.00 73~112 0.75~0.85 2.0~35.0 0.50~2.36 松辽盆地扶余油层 0.78~0.87 0.80~5.16 27~46 0.90~1.30 1.4~55.0 0.30~2.89 准噶尔盆地芦草沟组 0.88~0.92 73.00~112.00 15~17 1.10~1.75 2.4~67.0 0.50~3.70 2)页岩油开发技术。我国陆相页岩油开发既不同于常规油藏开发具备成熟的配套技术和良好经济效益,也不同于北美页岩油资源品质优良、水平井分段压裂开发技术成熟且可复制等有利条件,需要根据我国页岩油的地质特点,借鉴北美页岩油开发的一些成功经验,研究形成我国页岩油有效开发配套技术。我国和北美页岩油开发关键技术的适应性分析结果(见表2)表明,对于长水平段水平井,必须考虑水平段长度与优质油层钻遇率的匹配情况,不能不考虑陆相页岩油优质储层平面变化快的特点,一味追求增加水平段长度;对于小井距,在水平段长度一定的情况下,井距越小,井控储量越小,单一依靠提高采出程度无法实现单井产量和经济效益的大幅提高,优化井距时必须考虑单井控制储量和油层动用程度之间的匹配;对于立体式开发,必须充分考虑含油层系整体动用程度与经济效益的关系;对于密切割压裂,也不能刻意追求大液量、大砂量和大排量,需做好压裂设计优化,力争做到缝控储量最大化与压裂成本相对最小的匹配。
表 2 我国和北美页岩油开发关键技术适应性分析Table 2. Adaptability analysis of key technologies for the unconventional oilfields development in China and North America关键技术 页岩油主要地质特点 技术适应性要求 我国 北美 长水平段水平井 陆相,非均质性强 海相,相对较均质 水平段长度与优质油层钻遇率匹配 小井距 低储量丰度 高储量丰度 单井控制储量与油层动用程度匹配 立体布井 多为薄互层 厚层分布广 含油层系整体动用程度与经济效益匹配 复杂缝网 脆性差异大 脆性指数大 缝控储量与压裂成本匹配 3)页岩油开发配套能力。一是我国钻井完井能力和效率有了明显提升,如长庆油田页岩油开发在水平井钻井提速、压裂提效、单井提产等方面取得了重要进展,水平井(平均井深3 500 m,其中水平段平均长度1 500 m)最短钻井周期仅9.88 d,平均试油压裂周期缩短至19.5 d,但不同地区钻井完井能力和效率存在差异,部分地区有待进一步提升;二是目前页岩油采用多水平井平台开发模式,对井场规模、压裂液用量、环境保护等方面提出了更高的要求,但受地形地貌、水资源匮乏等因素影响,在实际开发中一些先进理念和创新技术的规模化应用受到制约。
4)页岩油开发市场化程度。自2011年我国开始页岩油开发以来,钻井、压裂、材料等方面的市场化程度逐步提高,其中大庆油田、吉林油田通过下放管理权限,采用多轮次招投标、签订产量与效益挂钩的服务合同等方式,开发成本明显下降,但整体而言,页岩油开发市场化程度仍有提升空间。
2. 美国二叠盆地页岩油开发降本增效的启示
二叠盆地(Permian)是美国三大核心页岩油产区之一,且在国际油价低于 40 美元/桶时,是唯一还能实现增产的页岩油产区,是页岩油成本最低的核心生产区[17-18]。调研认为,层层堆叠巨厚的页岩油资源、不断革新的开发理念和技术、逐步提升的高效钻井压裂能力、开放的市场机制和优惠政策,共同促成了二叠盆地页岩油开发不断将降本增效做向极致,实现了低油价环境下的逆袭。
1)层层堆叠巨厚的页岩油资源是基础。二叠盆地产层厚度大(390~550 m),主力产油层多,像千层饼一样层层堆叠,可以划分出 10~15 层甚至更多,且横向分布稳定,连续性好,这一特点与鹰滩、巴肯以及我国主要页岩油区块有明显区别,这也是二叠盆地页岩油开发降本增效能取得突破的资源基础[1]。
2)不断革新的开发理念和技术是关键。二叠盆地页岩油开发技术可以分为战略和战术2个层面:战略层面上,在低油价时期,页岩油开发向核心区转移,以使开发商专注高回报油区,利用有限的投资获得优质高产井;战术层面上,采用“大井丛、小井距、密切割、立体式”的开发模式,实现对页岩油核心区优质资源的充分动用和采出程度最大化。例如,加拿大Encana能源公司对二叠盆地堆叠式页岩油资源采取了立体开发模式,在面积0.131 km2的井场,分A、B两层设计部署了64口水平井,A层和B层水平井的井距分别为150和85~130 m,A、B两层垂向井距85 m。该开发模式可以提高设备、基础设施的利用率及人员工作效率,同时使用多台钻机的做法能够缩短钻井周期而且有利于服务共享。该立体开发模式不仅降低了开发成本,而且提高了油藏采收率,估算开发成本仅28美元/桶[1-2]。
3)逐步提升的高效钻井压裂能力是核心。北美页岩油开发在水平井钻井及分段压裂技术之后并未出现较大的技术革命,但渐进式技术革新不断提高单井生产效率。钻井方面,水平井水平段长度逐年增长,从2013年的平均1 676 m增长到2016年的2 438 m,超过3 048 m也屡见不鲜;虽然水平段越来越长,但通过采取缩短造斜段长度、强化钻井参数、水平段旋转导向钻进等技术措施,钻井周期却越来越短,目前钻井周期已缩短至10 d以内。压裂方面,随着水平段改造段数、簇数的增加,压裂液用量、支撑剂用量也在大幅增加,但压裂效率却在不断提高,目前已具有每天压裂6~7段的施工能力。钻井和压裂能力的不断提高,在大井丛、工厂化作业的背景下,形成了大幅提高单井产量、采出程度和经济效益的核心能力[17-18]。
4)开放的市场机制和优惠政策是保障。美国先后出台了一系列支持非常规油气发展的相关政策,据不完全统计,有32项扶持政策和15年的补贴政策,为从事页岩油气开发的相关公司提供了政策保障;同时,美国开放的市场经济体制限制了垄断,使大量有特色专项技术的中小企业得以自由进入能源领域。此外,美国活跃的金融市场为企业开展页岩油气开发与合作提供了资金支持,一些风险投资基金、银行等金融机构,纷纷为页岩油气开发投资、贷款,形成了页岩油气产业与金融业的有效融合[17-18]。
3. 我国页岩油有效开发关键技术研究
从北美页岩油高效开发的成功经验以及目前我国页岩油开发效果来看,先进的开发理念是实现页岩油规模效益开发的根源,先进、适用、低成本的工程技术是提高产量和效益的关键,只有理念转变、技术创新、管理创新和市场运作等多个方面共同发力,才能取得显著的降本增效效果,实现页岩油规模效益开发。
单从页岩油开发工程技术而言,目前“水平井+密切割体积压裂”已成为页岩油开发的主体技术[19-22],但面临着较大的降本增效压力。为此,结合近年来我国页岩油开发取得的主要进展和高效开发面临的技术需求,进行了页岩油甜点识别与评价方法、差异化压裂优化设计和全生命周期开发优化等3项关键技术研究,在推动我国页岩油开发降本增效方面起到了一定作用。
3.1 页岩油甜点识别与评价方法
页岩油甜点是实现规模效益开发的物质基础。针对我国陆相页岩油储层岩性、物性、含油性具有强烈的非均质性,常规测井响应特征弱化,单一测井信息多解性强的挑战,研究形成了基于常规测井曲线的页岩油测井多信息融合甜点识别与评价方法,主要识别评价流程为:1)测井曲线敏感性分析,确定敏感性测井曲线;2)转化为相同定性指向的标准化曲线;3)赋予各曲线点对应RGB颜色值;4)计算确定RGB空间特征值L;5)将融合的RGB颜色值(即L端点对应的颜色值)在对应测井深度上显示,并依据融合的RGB空间特征值设定显示宽度(如图1所示);6)获得测井信息融合可视化结果。该方法具有“多种测井信息融合、测井识别分辨率高、评价结果可视化显示”的特点,在鄂尔多斯盆地长7段页岩油、准噶尔盆地芦草沟组页岩油、松辽盆地扶余页岩油的储层评价中进行了应用,解释结果与目前的地质认识一致,与生产动态特征匹配程度较高,可以快速直观地识别页岩油甜点,判别烃源岩品质及源储配置关系,分析评价水平井水平段钻遇储层情况,从而为优化压裂设计物质基础。
基于常规测井曲线的页岩油测井多信息融合甜点识别与评价方法提高了测井识别的分辨率,可部分替代核磁、成像等特殊测井方法,达到认识复杂地质特征的目的,在解决油田开发实际问题的同时,还可以大幅降低测井作业成本[23-27]。
3.2 页岩油差异化压裂优化设计
2011年以来,我国页岩油开发呈现水平井水平段越来越长、压裂规模越来越大、分段分簇越来越密集的态势,单井产量明显提高,但这导致压裂成本大幅增加,单井投资居高不下,造成页岩油无法规模效益开发。为此,按照效益倒逼的理念,基于页岩油甜点识别与预测结果,提出了差异化压裂优化设计方法,以达到控制单井投资基本不变,明显改善单井开发效果,整体降本增效的目的。
假设某页岩油开发区块一口水平段长度1 500 m的水平井,分别钻遇I、II、III类储层各500 m,其孔隙度、渗透率、饱和度、可动油饱和度存在明显差异(见表3),应用自主研发的页岩油产能评价软件对该井差异化压裂设计下的单井初产量及累计产量进行了预测,结果见图2和图3。预测结果表明,若采用分类压裂,即充分压裂I类优质储层,适度压裂II类储层,少压或不压III类储层(情况1),单井初产量、累计产量及净现值最高;若不考虑储层类别,采用笼统的均匀布缝和压裂(情况2),在与情况1压裂规模相当的情况下,单井初产量、累计产量及净现值较低;若水平段均钻遇II类储层,且采用笼统的均匀布缝和压裂(情况3),单井初产量、累计产量最低。由此可见,优质储层钻遇率和优质储层充分压裂改造是获得单井高产和较好经济效益的主要控制因素,也说明差异化压裂具有明显的降本增效作用。
表 3 某页岩油开发区块不同类型储层属性参数对比Table 3. Comparison on the attribute parameters of different reservoirs in a shale oil development block储层类型 储层厚度/m 孔隙度,% 渗透率/mD 含油饱和度,% 可动油饱和度,% Ⅰ类 12 12 0.20 0.65 0.50 Ⅱ类 12 8 0.12 0.50 0.35 Ⅲ类 12 5 0.06 0.35 0.20 3.3 页岩油全生命周期开发优化
页岩油开发初期,基本都采用“初期高产、快速收回投资”的压力衰竭式开发方式,尤其是在高油价时期,美国大部分石油公司都采取放喷的方式,以使油井在短时间内达到最大产量,从而尽快回收前期投入成本。这一做法会导致油井产量迅速递减(L形递减)和单井最终可采储量(EUR)损失,需持续钻新井开发新区块来弥补。在低油价和提高资源利用率的双重作用影响下,压力衰竭式开发变得难以为继,国内外石油公司逐步转变开发理念,更加注重长期效益,秉持“成本是设计出来的”的理念,提出了以全生命周期开发方式优选为核心的开发方案编制方法,高度重视方案整体优化、开发全过程优化,从源头上降本增效。主要做法为:1)通过全生命周期开发方式优选,实现管控投资的前提下,最大限度地提高页岩油采收率,以获得最大的经济效益;2)从最初的放喷生产转变为控压生产,以求获取最大的单井 EUR,例如,北美某页岩油区块采取控压生产后,产量和井口压力的递减率都得到了有效控制,单井前5年的累积采收率可增加 30%~50%,净现值也得到了大幅提高;3)采用体积压裂注气吞吐等开发技术,有效补充地层能量,大幅提高页岩油采收率,获得更高的经济效益。例如,国内某页岩油开发区块,采用压力衰竭式开发方式时的采收率不到10.0%,采用体积压裂注气吞吐开发后,预测采收率可提高至26.9%。
4. 结 论
1)北美品质好的页岩油资源、不断革新的开发理念和技术、逐步提升的钻井压裂能力、开放的市场机制和优惠政策共同促成了页岩油开发成本不断降低,实现了页岩油规模效益开发。
2)我国页岩油开发在资源品质、开发技术、配套设施和市场化程度等方面存在诸多挑战,只有理念转变、技术创新、管理创新和市场运作等多个方面共同发力,才能取得显著的降本增效效果,实现页岩油规模效益开发。
3)提出了页岩油开发降本增效的3项关键技术:基于常规测井曲线的页岩油测井多信息融合甜点识别与评价方法,可在测井成本保持不变的情况下,对页岩油储层进行更为精细和快速的识别和评价;差异化压裂优化设计可在压裂投资保持不变的情况下,明显提高单井产量,达到整体降本增效的目的;全生命周期开发方式优化并应用控压生产、注气吞吐等技术,可实现降本增效。
-
表 1 国内外典型的智能完井系统
Table 1 Typical intelligent well completion system at home and abroad
智能完井系统 年份 公司 驱动方式 技术特点 SCRAMS 1997 哈里伯顿 液压 只需1根液压管线和1根电缆管线即可完成流量控制 MultiNodeTM 2014 贝克休斯 电力 单根特制电缆将井下所有节点连接到地面控制系统 Simply Intelligent 2014 威德福 液压 可以实现分辨率为0.5 m的全井温度以及井下剖面监测 Manara 2015 斯伦贝谢 电力 能够实现井下永久监控,并对分支井眼的不同目的层进行流量控制 EIC-Riped 2017 中国石油 电力 信号传输距离4 km,可做到100级流量调节 SureCONNECT 2020 贝克休斯 电力 无需干预的井筒产液监测控制,实现数据驱动的生产智能决策 -
[1] 匡立春,刘合,任义丽,等. 人工智能在石油勘探开发领域的应用现状与发展趋势[J]. 石油勘探与开发,2021,48(1):1–11. doi: 10.11698/PED.2021.01.01 KUANG Lichun, LIU He, REN Yili, et al. Application and development trend of artificial intelligence in petroleum exploration and development[J]. Petroleum Exploration and Development, 2021, 48(1): 1–11. doi: 10.11698/PED.2021.01.01
[2] 贾承造. 全国油气勘探开发形势与发展前景[J]. 中国石油石化,2022(20):14–17. JIA Chengzao. National oil and gas exploration and development situation and development prospects[J]. China Petrochem, 2022(20): 14–17.
[3] 李根生,宋先知,田守嶒. 智能钻井技术研究现状及发展趋势[J]. 石油钻探技术,2020,48(1):1–8. doi: 10.11911/syztjs.2020001 LI Gensheng, SONG Xianzhi, TIAN Shouceng. Intelligent drilling technology research status and development trends[J]. Petroleum Drilling Techniques, 2020, 48(1): 1–8. doi: 10.11911/syztjs.2020001
[4] 闫铁,许瑞,刘维凯,等. 中国智能化钻井技术研究发展[J]. 东北石油大学学报,2020,44(4):15–21. doi: 10.3969/j.issn.2095-4107.2020.04.003 YAN Tie, XU Rui, LIU Weikai, et al. Research and development of intelligent drilling technology in China[J]. Journal of Northeast Petroleum University, 2020, 44(4): 15–21. doi: 10.3969/j.issn.2095-4107.2020.04.003
[5] 李宗田,肖勇,李宁, 等. 低油价下的页岩油气开发工程技术新进展[J]. 断块油气田,2021,28(5):577–585. doi: 10.6056/dkyqt202105001 LI Zongtian, XIAO Yong, LI Ning, et al. New progress in shale oil and gas development engineering technology under low oil prices [J]. Fault-Block Oil & Gas Field, 2021, 28(5): 577–585. doi: 10.6056/dkyqt202105001
[6] LI Gensheng, SONG Xianzhi, TIAN Shouceng, et al. Intelligent drilling and completion: a review[J]. Engineering, 2022, 18: 33–48. doi: 10.1016/j.eng.2022.07.014
[7] 杨传书,李昌盛,孙旭东,等. 人工智能钻井技术研究方法及其实践[J]. 石油钻探技术,2021,49(5):7–13. doi: 10.11911/syztjs.2020136 YANG Chuanshu, LI Changsheng, SUN Xudong, et al. Research method and practice of artificial intelligence drilling technology[J]. Petroleum Drilling Techniques, 2021, 49(5): 7–13. doi: 10.11911/syztjs.2020136
[8] 王敏生,光新军. 智能钻井技术现状与发展方向[J]. 石油学报,2020,41(4):505–512. WANG Minsheng, GUANG Xinjun. Status and development trends of intelligent drilling technology[J]. Acta Petrolei Sinica, 2020, 41(4): 505–512.
[9] 彭超,邓津辉,谭忠健,等. 基于测井资料的渤中34-9油田火成岩地层抗钻特性评价[J]. 石油钻采工艺,2022,44(2):186–190. PENG Chao, DENG Jinhui, TAN Zhongjian, et al. Well logging-based anti-drilling property evaluation of igneous rock in Bozhong 34-9 Oilfield[J]. Oil Drilling & Production Technology, 2022, 44(2): 186–190.
[10] HEGDE C, DAIGLE H, GRAY K E. Performance comparison of algorithms for real-time rate-of-penetration optimization in drilling using data-driven models[J]. SPE Journal, 2018, 23(5): 1706–1722. doi: 10.2118/191141-PA
[11] 孟昭. PDC钻头井下工况评价方法研究[D]. 北京: 中国石油大学(北京), 2020. MENG Zhao. Study on evaluation method of PDC bit downhole working condition[D]. Beijing: China University of Petroleum (Beijing), 2020.
[12] REN Chuanjie, HUANG Wenjun, GAO Deli. Predicting rate of penetration of horizontal drilling by combining physical model with machine learning method in the China Jimusar Oil Field[R]. SPE 212294, 2022.
[13] PACIS F J, ALYAEV S, AMBRUS A, et al. Transfer learning approach to prediction of rate of penetration in drilling[C]//Computational Science–ICCS 2022. Cham: Springer, 2022: 358−371.
[14] WEI Jun, LIAO Hualin, WANG Huajian, et al. Experimental investigation on the dynamic tensile characteristics of conglomerate based on 3D SHPB system[J]. Journal of Petroleum Science and Engineering, 2022, 213: 110350. doi: 10.1016/j.petrol.2022.110350
[15] WANG Han, CHEN Dong, YE Zhihui, et al. Intelligent planning of drilling trajectory based on computer vision[R]. SPE 197362, 2019.
[16] SNYDER J, SALMON G. Intelligent rotary steerable system, coupled with an instrumented bit, delivers section plan in deepwater GOM project[R]. SPE 204680, 2021.
[17] 吴思源,李守定,陈冬,等. 大闭环伺服控制随钻智能导向钻井方法[J]. 地球物理学报,2021,64(11):4215–4226. doi: 10.6038/cjg2021O0449 WU Siyuan, LI Shouding, CHEN Dong, et al. An intelligent-while-drilling steering method of global closed-loop servo control[J]. Chinese Journal of Geophysics, 2021, 64(11): 4215–4226. doi: 10.6038/cjg2021O0449
[18] 田岚. 石油天然气钻井工程风险识别与评价方法[J]. 钻采工艺,2010,33(2):31–33. TIAN Lan. Risk identification and evaluation method in drilling engineering[J]. Drilling & Production Technology, 2010, 33(2): 31–33.
[19] NOSHI C I, NOYNAERT S F, SCHUBERT J J. Casing failure data analytics: A novel data mining approach in predicting casing failures for improved drilling performance and production optimization[R]. SPE 191570, 2018.
[20] AGWU O E, AKPABIO J U, ALABI S B, et al. Artificial intelligence techniques and their applications in drilling fluid engineering: a review[J]. Journal of Petroleum Science and Engineering, 2018, 167: 300–315. doi: 10.1016/j.petrol.2018.04.019
[21] 胜亚楠. 钻井工程风险评估与控制技术研究[D]. 青岛: 中国石油大学(华东), 2019. SHENG Yanan. Research on risk assessment and control technology of drilling engineering[D]. Qingdao: China University of Petroleum(East China), 2019.
[22] FANG Chunfei, WANG Zheng, SONG Xianzhi, et al. A novel cementing quality evaluation method based on convolutional neural network[J]. Applied Sciences, 2022, 12(21): 10997. doi: 10.3390/app122110997
[23] 郑双进,程霖,龙震宇,等. 基于GA-SVR算法的顺北区块固井质量预测[J]. 石油钻采工艺,2021,43(4):467–473. ZHENG Shuangjin, CHENG Lin, LONG Zhenyu, et al. Predicting the cementing quality in Shunbei Block based on GA-SVR algorithm[J]. Oil Drilling & Production Technology, 2021, 43(4): 467–473.
[24] WUTHERICH K, SRINIVASAN S, RAMSEY L, et al. Engineered diversion: using well heterogeneity as an advantage to designing stage specific diverter strategies[R]. SPE 189827, 2018.
[25] SOROUSH H, BELYADI H, KANG H, et al. Early prediction and prevention of tip screen-out using deep learning[R]. ARMA-2022 − 0052, 2022.
[26] GUO Wei, ZHANG Xiaowei, KANG Lixia, et al. Investigation of flowback behaviours in hydraulically fractured shale gas well based on physical driven method[J]. Energies, 2022, 15(1): 325. doi: 10.3390/en15010325
[27] 宋俊强,李晓山,王硕,等. 致密油藏压裂水平井产量预测[J]. 新疆石油地质,2022,43(5):580–586. SONG Junqiang, LI Xiaoshan, WANG Shuo, et al. Production prediction of fractured horizontal wells in tight oil reservoirs[J]. Xinjiang Petroleum Geology, 2022, 43(5): 580–586.
[28] 于潇伟,和鹏飞,金庭浩. 中国某海油气田智能完井方案设计研究[J]. 石油化工应用,2021,40(9):89–93. doi: 10.3969/j.issn.1673-5285.2021.09.019 YU Xiaowei, HE Pengfei, JIN Tinghao. Study on intelligent well completion scheme design of an offshore oil and gas field in China[J]. Petrochemical Industry Application, 2021, 40(9): 89–93. doi: 10.3969/j.issn.1673-5285.2021.09.019
[29] 舒成龙. 基于井下压力和温度数据的水平井智能完井产液状况分析[D]. 青岛: 中国石油大学(华东), 2015. SHU Chenglong. Fluid production analysis of intelligent completion horizontal wells based on wellbore pressure and temperature data[D]. Qingdao: China University of Petroleum (East China), 2015.
[30] SHISHAVAN R A, HUBBELL C, PEREZ H, et al. Combined rate of penetration and pressure regulation for drilling optimization by use of high-speed telemetry[J]. SPE Drilling & Completion, 2015, 30(1): 17–26.
[31] RITTO T G, SOIZE C, SAMPAIO R. Robust optimization of the rate of penetration of a drill-string using a stochastic nonlinear dynamical model[J]. Computational Mechanics, 2010, 45(5): 415–427. doi: 10.1007/s00466-009-0462-8
[32] BOURGOYNE A T, Jr, YOUNG F S, Jr. A multiple regression approach to optimal drilling and abnormal pressure detection[J]. SPE Journal, 1974, 14(4): 371–384.
[33] HEGDE C, SOARES C, GRAY K. Rate of penetration (ROP) modeling using hybrid models: deterministic and machine learning[R]. URTEC-2896522-MS, 2018.
[34] ETESAMI D, ZHANG W J, HADIAN M. A formation-based approach for modeling of rate of penetration for an offshore gas field using artificial neural networks[J]. Journal of Natural Gas Science and Engineering, 2021, 95: 104104. doi: 10.1016/j.jngse.2021.104104
[35] PAYETTE G S, SPIVEY B J, WANG L, et al. A real-time well-site based surveillance and optimization platform for drilling: Technology, basic workflows and field results[R]. SPE 184615, 2017.
[36] 宋先知,裴志君,王潘涛,等. 基于支持向量机回归的机械钻速智能预测[J]. 新疆石油天然气,2022,18(1):14–20. doi: 10.12388/j.issn.1673-2677.2022.01.002 SONG Xianzhi, PEI Zhijun, WANG Pantao, et al. Intelligent prediction for rate of penetration based on support vector machine regression[J]. Xinjiang Oil & Gas, 2022, 18(1): 14–20. doi: 10.12388/j.issn.1673-2677.2022.01.002
[37] ZANG Chuanzhen, LU Zongyu, YE Shanlin, et al. Drilling parameters optimization for horizontal wells based on a multiobjective genetic algorithm to improve the rate of penetration and reduce drill string drag[J]. Applied Sciences, 2022, 12(22): 11704. doi: 10.3390/app122211704
[38] ZHANG Chengkai, SONG Xianzhi, SU Yinao, et al. Real-time prediction of rate of penetration by combining attention-based gated recurrent unit network and fully connected neural networks [J]. Journal of Petroleum Science and Engineering, 2022, 213: 110396. doi: 10.1016/j.petrol.2022.110396
[39] 宋先知, 裴志君, 李根生, 等. 机械钻速预测方法及装置: CN202110786598.1[P]. 2022-02-18. SONG Xianzhi, PEI Zhijun, LI Gensheng, et al. Mechanical penetration rate prediction method and device: CN202110786598.1[P]. 2022-02-18.
[40] RASHIDI B, HARELAND G, WU Zebing. Performance, simulation and field application modeling of rollercone bits[J]. Journal of Petroleum Science and Engineering, 2015, 133: 507–517. doi: 10.1016/j.petrol.2015.06.003
[41] HELMY M W, KHALAF F, DARWISH T A. Well design using a computer model[J]. SPE Drilling & Completion, 1998, 13(1): 42–46.
[42] ATASHNEZHAD A, WOOD D A, FEREIDOUNPOUR A, et al. Designing and optimizing deviated wellbore trajectories using novel particle swarm algorithms[J]. Journal of Natural Gas Science and Engineering, 2014, 21: 1184–1204. doi: 10.1016/j.jngse.2014.05.029
[43] 刘绘新,孟英峰. 定向井最优井身轨迹研究[J]. 天然气工业,2004,24(2):64–67. doi: 10.3321/j.issn:1000-0976.2004.02.019 LIU Huixin, MENG Yingfeng. Study on optimal hole trajectory of directional drilling[J]. Natural Gas Industry, 2004, 24(2): 64–67. doi: 10.3321/j.issn:1000-0976.2004.02.019
[44] ABBAS A K, ALAMEEDY U, ALSABA M, et al. Wellbore trajectory optimization using rate of penetration and wellbore stability analysis[R]. SPE 193755, 2018.
[45] BISWAS K, VASANT P M, GAMEZ VINTANED J A, et al. Cellular automata-based multi-objective hybrid grey wolf optimization and particle swarm optimization algorithm for wellbore trajectory optimization[J]. Journal of Natural Gas Science and Engineering, 2021, 85: 103695. doi: 10.1016/j.jngse.2020.103695
[46] YU Le, PORWAL A, HOLDEN E J, et al. Towards automatic lithological classification from remote sensing data using support vector machines[J]. Computers & Geosciences, 2012, 45: 229–239.
[47] 王延江,杨培杰,史清江,等. 基于支撑向量机的井眼轨迹预测新方法[J]. 石油大学学报(自然科学版),2005,29(5):50–53. WANG Yanjiang, YANG Peijie, SHI Qingjiang, et al. Novel wellbore trajectory prediction method based on support vector machine[J]. Journal of the University of Petroleum, China(Edition of Natural Science), China, 2005, 29(5): 50–53.
[48] 孟庆华,刘清友. 基于小波–神经网络的井眼轨迹预测数学模型研究[J]. 机械设计,2008,25(9):25–27. MENG Qinghua, LIU Qingyou. Study on mathematical model of well bore locus prediction based on wavelet-neural network[J]. Journal of Machine Design, 2008, 25(9): 25–27.
[49] 张红,涂忆柳,冯定,等. 基于Kriging代理模型的造斜率预测方法研究[J]. 科学技术与工程,2017,17(3):61–68. doi: 10.3969/j.issn.1671-1815.2017.03.008 ZHANG Hong, TU Yiliu, FENG Ding, et al. Research on prediction method of build-up rate of deflecting tools based on Kriging surrogate model[J]. Science Technology and Engineering, 2017, 17(3): 61–68. doi: 10.3969/j.issn.1671-1815.2017.03.008
[50] 陈冬, 王涵, 叶智慧, 等. 一种基于随钻数据的地质模型重构方法及装置: CN202211215676.3[P]. 2023-01-06. CHEN Dong, WANG Han, YE Zhihui, et al. A geological model reconstruction method and device based on data while drilling: CN202211215676.3[P]. 2023-01-06.
[51] 刘昊. 一种基于强化学习的井下全闭环智能导钻方法研究[D]. 北京: 中国石油大学(北京), 2020. LIU Hao. Research on a fully closed-loop intelligent drilling guide d method based on reinforcement learning[D]. Beijing: China University of Petroleum(Beijing), 2020.
[52] 李旭,宋少博,高立军,等. 贝克休斯AutoTrak旋转导向指令成功率与涡轮转数配比研究[J]. 西部探矿工程,2022,34(9):90–91. doi: 10.3969/j.issn.1004-5716.2022.09.032 LI Xu, SONG Shaobo, GAO Lijun, et al. Research on the ratio between the success rate of rotation guidance command and turbine speed of Baker Hughes AutoTrak[J]. West-China Exploration Engineering, 2022, 34(9): 90–91. doi: 10.3969/j.issn.1004-5716.2022.09.032
[53] BA S, KIM J, GOEL P, et al. Expanding downlink capabilities using autonomous directional drilling with rotary steerable systems[R]. SPE 211067, 2022.
[54] ABBAS A K, BASHIKH A A, ABBAS H, et al. Intelligent decisions to stop or mitigate lost circulation based on machine learning[J]. Energy, 2019, 183: 1104–1113. doi: 10.1016/j.energy.2019.07.020
[55] 戴永寿,岳炜杰,孙伟峰,等. “三高” 油气井早期溢流在线监测与预警系统[J]. 中国石油大学学报(自然科学版),2015,39(3):188–194. DAI Yongshou, YUE Weijie, SUN Weifeng, et al. Online monitoring and warning system for early kick foreboding on “three high” wells[J]. Journal of China University of Petroleum(Edition of Natural Science), 2015, 39(3): 188–194.
[56] SIRUVURI C, NAGARAKANTI S, SAMUEL R. Stuck pipe prediction and avoidance: a convolutional neural network app-roach[R]. SPE 98378, 2006.
[57] 刘建明,李玉梅,张涛,等. 一种基于PCA-RF的卡钻预测方法[J]. 北京信息科技大学学报(自然科学版),2021,36(1):18–22. LIU Jianming, LI Yumei, ZHANG Tao, et al. Research on PCA-RF-based sticking prediction method[J]. Journal of Beijing Information Science & Technology University, 2021, 36(1): 18–22.
[58] DUAN Shiming, SONG Xianzhi, CUI Yi, et al. Intelligent kick warning based on drilling activity classification[J]. Geoenergy Science and Engineering, 2023, 222: 211408. doi: 10.1016/j.geoen.2022.211408
[59] LIANG Haibo, ZOU Jialing, LIANG Wenlong. An early intelligent diagnosis model for drilling overflow based on GA–BP algorithm[J]. Cluster Computing, 2019, 22(5): 10649–10668.
[60] YIN Qishuai, YANG Jin, TYAGI M, et al. Downhole quantitative evaluation of gas kick during deepwater drilling with deep learning using pilot-scale rig data[J]. Journal of Petroleum Science and Engineering, 2022, 208(Part A): 109136.
[61] 宋先知,姚学喆,李根生,等. 基于LSTM-BP神经网络的地层孔隙压力计算方法[J]. 石油科学通报,2022,7(1):12–23. doi: 10.3969/j.issn.2096-1693.2022.01.002 SONG Xianzhi, YAO Xuezhe, LI Gensheng, et al. A novel method to calculate formation pressure based on the LSTM-BP neural network[J]. Petroleum Science Bulletin, 2022, 7(1): 12–23. doi: 10.3969/j.issn.2096-1693.2022.01.002
[62] ZHU Zhaopeng, SONG Xianzhi, ZHANG Rui, et al. A hybrid neural network model for predicting bottomhole pressure in managed pressure drilling[J]. Applied Sciences, 2022, 12(13): 6728. doi: 10.3390/app12136728
[63] 许争鸣. 深层高温高压钻井环空气液固三相流动规律研究[D]. 北京: 中国石油大学(北京), 2019. XU Zhengming. Study on the flowing characteristics of gas-liquid-solid in annulus during high-temperature and high-pressure deep well drilling[D]. Beijing: China University of Petroleum(Beijing), 2019.
[64] 连志龙,周英操,申瑞臣,等. 无意外风险钻井(NDS)技术探讨[J]. 石油钻采工艺,2009,31(1):90–94. doi: 10.3969/j.issn.1000-7393.2009.01.023 LIAN Zhilong, ZHOU Yingcao, SHEN Ruichen, et al. A discussion on technology of no drilling surprises (NDS)[J]. Oil Drilling & Production Technology, 2009, 31(1): 90–94. doi: 10.3969/j.issn.1000-7393.2009.01.023
[65] 杨传书. 钻井风险评价系统DrillRisk的研发与应用[J]. 石油钻探技术,2017,45(5):60–67. doi: 10.11911/syztjs.201705011 YANG Chuanshu. Development and application of risk-assessment system for drilling operations[J]. Petroleum Drilling Techniques, 2017, 45(5): 60–67. doi: 10.11911/syztjs.201705011
[66] 朱玉玺,倪红梅,王瑞仙,等. 人工神经网络在固井质量预测中的应用[J]. 大庆石油学院学报,2002,26(2):52–55. ZHU Yuxi, NI Hongmei, WANG Ruixian, et al. Application of artificial neutral network to forecasting cementing quality[J]. Journal of Northeast Petroleum University, 2002, 26(2): 52–55.
[67] 倪红梅,王维刚. 免疫神经网络在固井质量预测中的应用研究[J]. 计算机仿真,2009,26(7):267–269. doi: 10.3969/j.issn.1006-9348.2009.07.068 NI Hongmei, WANG Weigang. Application of immune neural network in cementing quality prediction[J]. Computer Simulation, 2009, 26(7): 267–269. doi: 10.3969/j.issn.1006-9348.2009.07.068
[68] VOLETI D K, REDDICHARLA N, GUNTUPALLI S, et al. Smart way for consistent cement bond evaluation and reducing human bias using machine learning[R]. SPE 202742, 2020.
[69] SANTOS L, DAHI TALEGHANI A. Machine learning framework to generate synthetic cement evaluation logs for wellbore integrity analysis[R]. ARMA-2021-1769, 2021.
[70] REOLON D, DI MAGGIO F, MORIGGI S, et al. Unlocking data analytics for the automatic evaluation of cement bond scena-rios[R]. SPWLA-5060, 2020.
[71] VIGGEN E M, LØVSTAKKEN L, MÅSØY S E, et al. Better automatic interpretation of cement evaluation logs through feature engineering[J]. SPE Journal, 2021, 26(5): 2894–2913. doi: 10.2118/204057-PA
[72] LEHMAN L V, JACKSON K, NOBLETT B. Big data yields completion optimization: Using drilling data to optimize completion efficiency in a low permeability formation[R]. SPE 181273, 2016.
[73] SCANLAN W P, PIERSKALLA K J, SOBERNHEIM D W, et al. Optimization of Bakken well completions in a multivariate wor-ld[R]. SPE 189868, 2018.
[74] KESHAVARZI R, JAHANBAKHSHI R. Investigation of hydraulic and natural fracture interaction: Numerical modeling or artificial intelligence?[R]. ISRM-ICHF-2013 − 025, 2013.
[75] YANG Ruiyue, QIN Xiaozhou, LIU Wei, et al. A physics-constrained data-driven workflow for predicting coalbed methane well production using artificial neural network[J]. SPE Journal, 2022, 27(3): 1531–1552. doi: 10.2118/205903-PA
[76] HARPEL J, RAMSEY L, WUTHERICH K. Improving the effectiveness of diverters in hydraulic fracturing of the wolfcamp shale[R]. SPE 191600, 2018.
[77] HU Jinqiu, KHAN F, ZHANG Laibin, et al. Data-driven early warning model for screenout scenarios in shale gas fracturing operation[J]. Computers & Chemical Engineering, 2020, 143: 107116.
[78] 盛茂, 李雨峰, 李根生, 等. 模型建立方法、裂缝起裂事件诊断方法和装置: CN202110792084.7[P]. 2021-09-24. SHENG Mao, LI Yufeng, LI Gensheng, et al. Model establishment method, fracture initiation event diagnosis method and device: CN202110792084.7[P]. 2021-09-24.
[79] DURDYYEV G. New technologies and protocols concerning horizontal well drilling and completion[D]. Turin: Politecnico di Torino, 2021.
[80] ZHOU Qiumei, DILMORE R, KLEIT A, et al. Evaluating fracture-fluid flowback in Marcellus using data-mining technologies[J]. SPE Production & Operations, 2016, 31(2): 133–146.
[81] FU Yingkun, DEHGHANPOUR H, EZULIKE D O, et al. Estimating effective fracture pore volume from flowback data and evaluating its relationship to design parameters of multistage-fracture completion[J]. SPE Production & Operations, 2017, 32(4): 423–439.
[82] MAITY D, CIEZOBKA J. An interpretation of proppant transport within the stimulated rock volume at the hydraulic-fracturing test site in the Permian Basin[J]. SPE Reservoir Evaluation & Engineering, 2019, 22(2): 477–491.
[83] 盛茂,李根生,田守嶒,等. 人工智能在油气压裂增产中的研究现状与展望[J]. 钻采工艺,2022,45(4):1–8. SHENG Mao, LI Gensheng, TIAN Shouceng, et al. Research status and prospect of artificial intelligence in reservoir fracturing stimulation[J]. Drilling & Production Technology, 2022, 45(4): 1–8.
[84] NEJAD A M, SHELUDKO S, SHELLEY R F, et al. A case history: evaluating well completions in the Eagle Ford Shale using a data-driven approach[R]. SPE 173336, 2015.
[85] YANG Ruiyue, LIU Wei, QIN Xiaozhou, et al. A physics-constrained data-driven workflow for predicting coalbed methane well production using a combined gated recurrent unit and multi-layer perception neural network model[R]. SPE 205903, 2021.
[86] TARIQ Z, ABDULRAHEEM A, KHAN M R, et al. New inflow performance relationship for a horizontal well in a naturally fractured solution gas drive reservoirs using artificial intelligence technique[R]. OTC 28367, 2018.
[87] BELLO O, YANG D, LAZARUS S, et al. Next generation downhole big data platform for dynamic data-driven well and reservoir management[R]. SPE 186033, 2017.
[88] WANG Xiaoqiu, WANG Zhiming, ZENG Quanshu. A novel autonomous inflow control device: design, stracture optimization, and fluid sensitivity analysis[R]. IPTC 17758, 2014.
[89] 王小秋,汪志明,赵麟. 基于膨胀材料的新型AICD结构设计及其性能实验研究[J]. 石油科学通报,2018,3(3):302–312. WANG Xiaoqiu, WANG Zhiming, ZHAO Lin. A novel AICD structure design and its performance analysis[J]. Petroleum Science Bulletin, 2018, 3(3): 302–312.
[90] 陈玉婷, 赵晨晖, 冯超, 等. 深水高产油气田智能完井与防砂一体化技术的应用[J]. 石油工程建设, 2020, 46(增刊1): 229-232. CHEN Yuting, ZHAO Chenhui, FENG Chao, et al. Integrated application of intelligent well completion and sand control technology for high yield oil and gas fields in deepwater[J]. Petroleum Engineering Construction, 2020, 46(supplement 1): 229-232.
[91] HEGDE C, MILLWATER H, PYRCZ M, et al. Rate of penetration (ROP) optimization in drilling with vibration control[J]. Journal of Natural Gas Science and Engineering, 2019, 67: 71–81. doi: 10.1016/j.jngse.2019.04.017
[92] LOSOYA E Z, GILDIN E, NOYNAERT S F, et al. An open-source enabled drilling simulation consortium for academic and commercial applications[R]. SPE 198943, 2020.
[93] 宋先知, 裴志君, 王潘涛, 等. 基于多目标的油气钻井策略预测方法及装置: CN202110232999.2[P]. 2021-05-14. SONG Xianzhi, PEI Zhijun, WANG Pantao, et al. Prediction method and device of oil and gas drilling strategy based on multi-objective: CN202110232999.2[P]. 2021-05-14.
[94] 徐宝昌, 张学智. 耦合井筒与钻柱的钻井过程全局动态建模与仿真[C]//第40届中国控制会议论文集(15). 上海: 中国自动化学会控制理论专业委员会, 2021: 688 − 693. XU Baochang, ZHANG Xuezhi. Global dynamic modeling and simulation of drilling process coupled with wellbore and drill string[C]//Proceedings of the 40th China control conference (15). Shanghai: Control theory professional committee of China automation society, 2021: 688−693.
[95] MAYANI M G, ROMMETVEIT R, OEDEGAARD S I, et al. Drilling automated realtime monitoring using digital twin[R]. SPE 192807, 2018.
[96] CAYEUX E. Mathematical modelling of the drilling process for real-time applications in drilling simulation, interpretation and assistance[D]. Stavanger: University of Stavanger, 2019.
[97] 肖立志. 机器学习数据驱动与机理模型融合及可解释性问题[J]. 石油物探,2022,61(2):205–212. doi: 10.3969/j.issn.1000-1441.2022.02.002 XIAO Lizhi. The fusion of data-driven machine learning with mechanism models and interpretability issues[J]. Geophysical Prospecting for Petroleum, 2022, 61(2): 205–212. doi: 10.3969/j.issn.1000-1441.2022.02.002
[98] RAI R, SAHU C K. Driven by data or derived through physics? A review of hybrid physics guided machine learning techniques with cyber-physical system (CPS) focus[J]. IEEE Access, 2020, 8: 71050–71073. doi: 10.1109/ACCESS.2020.2987324
[99] 杨顺辉,郭珍珍,张洪宝,等. 基于集成迁移学习的机械钻速预测[J]. 计算机系统应用,2022,31(10):270–278. YANG Shunhui, GUO Zhenzhen, ZHANG Hongbao, et al. Rate of penetration prediction using ensemble transfer learning[J]. Computer Systems & Applications, 2022, 31(10): 270–278.
[100] CHEN Yuntian, ZHANG Dongxiao. Physics-constrained deep learning of geomechanical logs[J]. IEEE Transactions on Geosci-ence and Remote Sensing, 2020, 58(8): 5932–5943. doi: 10.1109/TGRS.2020.2973171
[101] 陈良臣,傅德印. 面向小样本数据的机器学习方法研究综述[J]. 计算机工程,2022,48(11):1–13. CHEN Liangchen, FU Deyin. Survey on machine learning methods for small sample data[J]. Computer Engineering, 2022, 48(11): 1–13.
[102] GILPIN L H, BAU D, YUAN B Z, et al. Explaining explanations: an overview of interpretability of machine learning[C]//2018 IEEE 5th international conference on data science and advanced analytics (DSAA). Turin: IEEE, 2018: 80−89.
[103] CHOI E, BAHADORI M T, SCHUETZ A, et al. RETAIN: Interpretable predictive model in healthcare using reverse time attention mechanism[EB/OL]. (2016-08-19)[2023-01-15]. https://arxiv. org/abs/1608.05745v1.
[104] BARR KUMARAKULASINGHE N, BLOMBERG T, LIU Jintai, et al. Evaluating local interpretable model-agnostic explanations on clinical machine learning classification models[C]//2020 IEEE 33rd international symposium on computer-based medical systems (CBMS). Rochester: IEEE, 2020: 7-12.