B. Daireaux, H. Brackel, Robert Ewald, Petter Markussen, Maria Johansen, M. Parak, Ghanshyam Yadav, Anar Ismayilov
Drilling operations rely on the collaboration of many participants, and the efficiency of this collaboration depends on timely exchange of information. The complexity and variability of this information make it difficult to achieve interoperability between the involved systems. Recent industry efforts aim at facilitating the many aspects of interoperability. A central element is semantic interoperability: the ability to correctly interpret the real-time signals available on the rig. This contribution presents an implementation of semantic interoperability using OPC UA technology. It translates the principles developed through joint industry efforts into actual drilling operations. The process used the steps of characterizing the drilling real-time data with semantic graphs, and then developing methods to transfer this characterization to an operational real-time environment. A semantic interoperability API (application programming interface) uses the semantic modelling capabilities of OPC UA. Its objectives are to facilitate the acquisition and identification of real-time signals (for data consumers) and their precise description (by data providers). The different components of the API reflect the diversity of scenarios one can expect to encounter on a rig: from WITS-like data streams with minimal semantics to fully characterized signals. The high-level interface makes use of semantical techniques, such as reasoning, to enable advanced features like validation or graph queries. The implementation phase resulted in a series of open-source solutions that cover all the stages of semantic interoperability. The server part integrates real-time sources and exposes their semantics. Data providers can use dedicated applications to accurately describe their own data, while data consumers have access to both predefined mechanisms and to more advanced programming interfaces to identify and interpret the available signals. To facilitate the adoption of this technology, test applications are available that allow interested users to experiment and validate their own interfaces against realistic drilling data. Finally, demonstrations involving several participants took place. The paper discusses both the testing procedures, the results and insights gained. The solutions described in this contribution build on newly developed interoperability strategies: they make on-going industry efforts available to the community via modern technologies, such as OPC UA, semantic modelling, or reasoning. Our hope is that the adoption of the developed technology should greatly facilitate the deployment of next generation drilling automation systems.
{"title":"Towards the Correct Interpretation of Real-Time Signals on the Well-Site","authors":"B. Daireaux, H. Brackel, Robert Ewald, Petter Markussen, Maria Johansen, M. Parak, Ghanshyam Yadav, Anar Ismayilov","doi":"10.2118/212509-ms","DOIUrl":"https://doi.org/10.2118/212509-ms","url":null,"abstract":"\u0000 \u0000 \u0000 Drilling operations rely on the collaboration of many participants, and the efficiency of this collaboration depends on timely exchange of information. The complexity and variability of this information make it difficult to achieve interoperability between the involved systems. Recent industry efforts aim at facilitating the many aspects of interoperability. A central element is semantic interoperability: the ability to correctly interpret the real-time signals available on the rig. This contribution presents an implementation of semantic interoperability using OPC UA technology. It translates the principles developed through joint industry efforts into actual drilling operations.\u0000 \u0000 \u0000 \u0000 The process used the steps of characterizing the drilling real-time data with semantic graphs, and then developing methods to transfer this characterization to an operational real-time environment.\u0000 A semantic interoperability API (application programming interface) uses the semantic modelling capabilities of OPC UA. Its objectives are to facilitate the acquisition and identification of real-time signals (for data consumers) and their precise description (by data providers). The different components of the API reflect the diversity of scenarios one can expect to encounter on a rig: from WITS-like data streams with minimal semantics to fully characterized signals. The high-level interface makes use of semantical techniques, such as reasoning, to enable advanced features like validation or graph queries.\u0000 \u0000 \u0000 \u0000 The implementation phase resulted in a series of open-source solutions that cover all the stages of semantic interoperability. The server part integrates real-time sources and exposes their semantics. Data providers can use dedicated applications to accurately describe their own data, while data consumers have access to both predefined mechanisms and to more advanced programming interfaces to identify and interpret the available signals.\u0000 To facilitate the adoption of this technology, test applications are available that allow interested users to experiment and validate their own interfaces against realistic drilling data.\u0000 Finally, demonstrations involving several participants took place. The paper discusses both the testing procedures, the results and insights gained.\u0000 \u0000 \u0000 \u0000 The solutions described in this contribution build on newly developed interoperability strategies: they make on-going industry efforts available to the community via modern technologies, such as OPC UA, semantic modelling, or reasoning.\u0000 Our hope is that the adoption of the developed technology should greatly facilitate the deployment of next generation drilling automation systems.\u0000","PeriodicalId":103776,"journal":{"name":"Day 2 Wed, March 08, 2023","volume":"44 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133319168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abdulbaset Ali, Harnoor Singh, Daniel Kelly, Donald G. Hender, Alan Clarke, Mohammad Mahdi Ghiasi, Ronald Haynes, Lesley James
There is considerable value in automatically quantifying cutter damage from drill bit pictures. Current approaches do not classify cutter damage by type, i.e., broken, chipped, lost, etc. We, therefore, present a computer vision model using deep learning neural networks to automate multi-type damage detection in Polycrystalline Diamond Compact (PDC) drill bit cutters. The automated bit damage detection approach presented in this paper is based on training a computer vision model on different cutter damage types aimed at detecting and classifying damaged cutters directly. Prior approaches detected cutters first and then classified the damage type for the detected cutters. The You Only Look Once version 5 (YOLOv5) algorithm was selected based on the findings of an earlier published study. Different models of YOLOv5 were trained with different architecture sizes with various optimizers using two-dimensional (2D) drill bit images provided by the SPE Drilling Uncertainty Prediction technical section (DUPTS) and labeled by the authors with training from industry subject matter experts. To achieve the modeling goal, the images were first annotated and labeled to create training, validation, and testing sub-datasets. Then, by changing brightness and color, the images allocated for the training phase were augmented to generate more samples for the model development. The categories defined for labeling the DUPTS dataset were bond failure, broken cutter, chipped cutter, lost cutter, worn cutter, green cutter, green gauge, core out, junk damage, ring out, and top view. These categories can be updated once the IADC upgrade committee finishes upgrading IADC dull bit grading cones. Trained models were validated using the validation dataset of 2D images. It showed that the large YOLOv5 with stochastic gradient descent (SGD) optimizer achieved the highest metrics with a short training cycle compared to the Adam optimizer. In addition, the model was tested using an unseen data set collected from the local office of a drill bit supplier. Testing results illustrated a high level of performance. However, it was observed that inconsistency and quality of rig site drill bit photos reduce model accuracy. Therefore, it is suggested that companies produce large sets of quality images for developing better models. This study successfully demonstrates the integration of computer vision and machine learning for drill bit grading by categorizing/classifying damaged cutters by type directly in one stage rather than detecting the cutters first and then classifying them in a second stage. To guarantee the deployed model's robustness and consistency the model deployment has been tested in different environments that include cloud platform, container on a local machine, and cloud platform as a service (PaaS) with an online web app. In addition, the model can detect ring out and cored damages from the top view drill bit images, and to the best of the authors’ knowledge, this ha
从钻头图像中自动量化刀具损坏具有相当大的价值。目前的方法没有按类型对刀具损坏进行分类,即破碎、切屑、丢失等。因此,我们提出了一种使用深度学习神经网络的计算机视觉模型,用于自动检测聚晶金刚石(PDC)钻头切削齿的多类型损伤。本文提出的自动钻头损伤检测方法是基于对不同类型刀具损伤的计算机视觉模型的训练,目的是直接检测和分类损坏的刀具。先前的方法首先检测刀具,然后对检测到的刀具进行损伤类型分类。You Only Look Once version 5 (YOLOv5)算法的选择是基于先前发表的一项研究的结果。使用SPE钻井不确定性预测技术部分(DUPTS)提供的二维(2D)钻头图像,使用各种优化器对YOLOv5的不同模型进行了不同结构尺寸的训练,并由作者进行了行业主题专家的培训。为了实现建模目标,首先对图像进行注释和标记,以创建训练、验证和测试子数据集。然后,通过改变亮度和颜色,增强分配给训练阶段的图像,生成更多的样本用于模型开发。为标记DUPTS数据集定义的类别包括粘接失效、刀具破损、刀具切屑、刀具丢失、刀具磨损、刀具未加工、刀具未加工、出芯、垃圾损坏、出环和顶视图。一旦IADC升级委员会完成IADC钝位分级锥体的升级,这些类别就可以更新。使用二维图像验证数据集对训练好的模型进行验证。结果表明,与Adam优化器相比,带有随机梯度下降(SGD)优化器的大型YOLOv5在较短的训练周期内获得了最高的指标。此外,使用从钻头供应商当地办事处收集的未见数据集对该模型进行了测试。测试结果显示了高水平的性能。然而,现场钻头照片的不一致性和质量降低了模型的准确性。因此,建议公司生产大量高质量的图像集,以开发更好的模型。该研究成功地展示了计算机视觉和机器学习在钻头分级中的集成,在一个阶段直接按类型对损坏的刀具进行分类/分类,而不是先检测刀具然后在第二阶段对其进行分类。为了保证部署模型的鲁棒性和一致性,模型部署已经在不同的环境中进行了测试,包括云平台、本地机器上的容器和云平台即服务(PaaS),并使用在线web应用程序。此外,该模型可以从顶视图钻头图像中检测出环和岩心损坏,据作者所知,这是之前没有任何研究解决的问题。与目前冗长的人工损伤评估实践相比,所开发的深度学习计算机视觉算法的新颖之处在于能够快速有效地检测不同的刀具损伤类型。此外,经过训练的模型还可以检测出钻头多个刀片上经常发生的损坏,例如出环和取心。此外,还开发了一个用户友好的界面,该界面生成pdf和CSV文件格式的结果,用于进一步的数据分析、可视化和文档编制。此外,模型开发中使用的所有技术都是开源的,我们使我们的web应用程序实现开放访问。
{"title":"Automatic Classification of PDC Cutter Damage Using a Single Deep Learning Neural Network Model","authors":"Abdulbaset Ali, Harnoor Singh, Daniel Kelly, Donald G. Hender, Alan Clarke, Mohammad Mahdi Ghiasi, Ronald Haynes, Lesley James","doi":"10.2118/212503-ms","DOIUrl":"https://doi.org/10.2118/212503-ms","url":null,"abstract":"\u0000 There is considerable value in automatically quantifying cutter damage from drill bit pictures. Current approaches do not classify cutter damage by type, i.e., broken, chipped, lost, etc. We, therefore, present a computer vision model using deep learning neural networks to automate multi-type damage detection in Polycrystalline Diamond Compact (PDC) drill bit cutters.\u0000 The automated bit damage detection approach presented in this paper is based on training a computer vision model on different cutter damage types aimed at detecting and classifying damaged cutters directly. Prior approaches detected cutters first and then classified the damage type for the detected cutters. The You Only Look Once version 5 (YOLOv5) algorithm was selected based on the findings of an earlier published study. Different models of YOLOv5 were trained with different architecture sizes with various optimizers using two-dimensional (2D) drill bit images provided by the SPE Drilling Uncertainty Prediction technical section (DUPTS) and labeled by the authors with training from industry subject matter experts. To achieve the modeling goal, the images were first annotated and labeled to create training, validation, and testing sub-datasets. Then, by changing brightness and color, the images allocated for the training phase were augmented to generate more samples for the model development. The categories defined for labeling the DUPTS dataset were bond failure, broken cutter, chipped cutter, lost cutter, worn cutter, green cutter, green gauge, core out, junk damage, ring out, and top view. These categories can be updated once the IADC upgrade committee finishes upgrading IADC dull bit grading cones.\u0000 Trained models were validated using the validation dataset of 2D images. It showed that the large YOLOv5 with stochastic gradient descent (SGD) optimizer achieved the highest metrics with a short training cycle compared to the Adam optimizer. In addition, the model was tested using an unseen data set collected from the local office of a drill bit supplier. Testing results illustrated a high level of performance. However, it was observed that inconsistency and quality of rig site drill bit photos reduce model accuracy. Therefore, it is suggested that companies produce large sets of quality images for developing better models. This study successfully demonstrates the integration of computer vision and machine learning for drill bit grading by categorizing/classifying damaged cutters by type directly in one stage rather than detecting the cutters first and then classifying them in a second stage. To guarantee the deployed model's robustness and consistency the model deployment has been tested in different environments that include cloud platform, container on a local machine, and cloud platform as a service (PaaS) with an online web app. In addition, the model can detect ring out and cored damages from the top view drill bit images, and to the best of the authors’ knowledge, this ha","PeriodicalId":103776,"journal":{"name":"Day 2 Wed, March 08, 2023","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127128660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Katsikas, George N. Manditsios, Fotis N. Dalmiras, G. Sakalis, George Antonopoulos, Andreas Doulgeridis, Dimitrios Mouzakis
Shipping operates in a challenging economic environment characterized among other by increasing environmental regulations aiming to contribute to the global GHG emissions reduction targets set. Smart monitoring tools are key solutions for shipping companies to adapt effectively and comply with the new environmental regulations set by local, regional, and international regulatory parties, including the International Maritime Organization (IMO) and other stakeholders. The combination of high frequency data and the employment of advanced analytical technologies offers the shipping industry a great advantage. Continuous data monitoring enables reactive energy performance improvement / optimization, while it allows building up realistic performance models that are used for optimizing the commercial management of the vessels and serve as a basis for new projects. Vessel operational profile monitoring along with voyage planning through optimized speeds and weather routing, effective monitoring of hull & propeller bio-fouling, trim optimization, assessment of innovative solutions installation (i.e., waste heat recovery systems, energy saving devices, new painting schemes, etc.) are practices widely used nowadays to address GHG emissions reduction plan and performance optimization. Current study examines the importance of vessel continuous monitoring on the evaluation of the aforementioned measures, based on established methodologies, along with the development of new algorithms and mathematical models.
{"title":"Challenges to Taking Advantage of High Frequency Data Analytics to Address Environmental Challenges in Maritime Sector","authors":"S. Katsikas, George N. Manditsios, Fotis N. Dalmiras, G. Sakalis, George Antonopoulos, Andreas Doulgeridis, Dimitrios Mouzakis","doi":"10.5957/some-2023-006","DOIUrl":"https://doi.org/10.5957/some-2023-006","url":null,"abstract":"Shipping operates in a challenging economic environment characterized among other by increasing environmental regulations aiming to contribute to the global GHG emissions reduction targets set. Smart monitoring tools are key solutions for shipping companies to adapt effectively and comply with the new environmental regulations set by local, regional, and international regulatory parties, including the International Maritime Organization (IMO) and other stakeholders. The combination of high frequency data and the employment of advanced analytical technologies offers the shipping industry a great advantage. Continuous data monitoring enables reactive energy performance improvement / optimization, while it allows building up realistic performance models that are used for optimizing the commercial management of the vessels and serve as a basis for new projects. Vessel operational profile monitoring along with voyage planning through optimized speeds and weather routing, effective monitoring of hull & propeller bio-fouling, trim optimization, assessment of innovative solutions installation (i.e., waste heat recovery systems, energy saving devices, new painting schemes, etc.) are practices widely used nowadays to address GHG emissions reduction plan and performance optimization. Current study examines the importance of vessel continuous monitoring on the evaluation of the aforementioned measures, based on established methodologies, along with the development of new algorithms and mathematical models.","PeriodicalId":103776,"journal":{"name":"Day 2 Wed, March 08, 2023","volume":"455 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131855762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
T. Chase, Aaron Garcia, K. Marchman, M. Mendoza, Chris von Eberstein, Jacob Tritz, Noah Tritz, Chris Jordan, L. Smith
As the design of deepwater wells continues to evolve for unlocking new reserves from deeper and challenging reservoir conditions, longer and heavier casing strings are required to achieve various well objectives and operational efficiency. The mechanical requirements resulting from the landing and cementing of these heavy casing strings pushes the limits on current equipment. Landing and cementing such heavy casing designs presents numerous challenges to conduct the operation safely and efficiently, requiring the implementation of non-conventional alternatives to manage the loads for enabling the existing rigs to step-out of the normal drilling envelopes. For drilling the first deepwater 20,000 psi development well in Gulf of Mexico, the Operator required the large diameter nested liner strings to be deployed deeper than any offset well, for ensuring pressure containment while drilling and sufficient diameter for the larger production casing / completion equipment. As a result, the load of landing the 16″ nested liner string was expected to exceed 2.5 million lbf, which was outside of the operational capability of any existing equipment, including drilling rig, landing string and cementing head. The planning team assessed alternatives for running the liner with an existing drillship and the landing equipment available including pipe, cementing head and handling equipment. Rigorous measures had to be put in place in order to determine the technical requirements to qualify the equipment for the operation and better understand and mitigate the risks involved. These challenges were overcome by considerable planning in landing string design, handling equipment implementation, assessing rig load path and shearing capability for the heavy landing string, equipment design review and testing, and equipment inspections and qualifications. Specific areas of focus included: the use of heavy-duty, high yield, thick wall landing string through the BOP stack, upgrading the shearing and sealing capability of the rig's BOP stack, use of buoyed landing string above the BOP stack and the associated handling equipment, an increased load rating of cementing equipment by re-evaluating design and material, customized inspection criteria for all equipment to be used, and a thorough evaluation of landing string accessories to validate structural integrity. All parties involved provided significant effort to ensure that the equipment used in this string was fit for purpose. The stringent planning, ratings re-evaluation, and equipment qualifications helped ensure the successful landing of a potential world-record 2.49 million lbf hookload 16 in. liner string under challenging weather conditions. The successful landing of this string paves the way for future wells where similar design challenges will be faced.
{"title":"Designing and Qualifying Equipment for a Potential World-Record Deepwater Casing Landing Operation","authors":"T. Chase, Aaron Garcia, K. Marchman, M. Mendoza, Chris von Eberstein, Jacob Tritz, Noah Tritz, Chris Jordan, L. Smith","doi":"10.2118/212545-ms","DOIUrl":"https://doi.org/10.2118/212545-ms","url":null,"abstract":"\u0000 As the design of deepwater wells continues to evolve for unlocking new reserves from deeper and challenging reservoir conditions, longer and heavier casing strings are required to achieve various well objectives and operational efficiency. The mechanical requirements resulting from the landing and cementing of these heavy casing strings pushes the limits on current equipment. Landing and cementing such heavy casing designs presents numerous challenges to conduct the operation safely and efficiently, requiring the implementation of non-conventional alternatives to manage the loads for enabling the existing rigs to step-out of the normal drilling envelopes.\u0000 For drilling the first deepwater 20,000 psi development well in Gulf of Mexico, the Operator required the large diameter nested liner strings to be deployed deeper than any offset well, for ensuring pressure containment while drilling and sufficient diameter for the larger production casing / completion equipment. As a result, the load of landing the 16″ nested liner string was expected to exceed 2.5 million lbf, which was outside of the operational capability of any existing equipment, including drilling rig, landing string and cementing head. The planning team assessed alternatives for running the liner with an existing drillship and the landing equipment available including pipe, cementing head and handling equipment. Rigorous measures had to be put in place in order to determine the technical requirements to qualify the equipment for the operation and better understand and mitigate the risks involved.\u0000 These challenges were overcome by considerable planning in landing string design, handling equipment implementation, assessing rig load path and shearing capability for the heavy landing string, equipment design review and testing, and equipment inspections and qualifications. Specific areas of focus included: the use of heavy-duty, high yield, thick wall landing string through the BOP stack, upgrading the shearing and sealing capability of the rig's BOP stack, use of buoyed landing string above the BOP stack and the associated handling equipment, an increased load rating of cementing equipment by re-evaluating design and material, customized inspection criteria for all equipment to be used, and a thorough evaluation of landing string accessories to validate structural integrity. All parties involved provided significant effort to ensure that the equipment used in this string was fit for purpose.\u0000 The stringent planning, ratings re-evaluation, and equipment qualifications helped ensure the successful landing of a potential world-record 2.49 million lbf hookload 16 in. liner string under challenging weather conditions. The successful landing of this string paves the way for future wells where similar design challenges will be faced.","PeriodicalId":103776,"journal":{"name":"Day 2 Wed, March 08, 2023","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129138401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As we begin a new decade, drilling systems automation has left its primary residence of PowerPoint slides and is now seeing wider adoption. In areas, the industry sees positive return-on-investment for automation technology development; both financially, from reduction in well construction cost, and in helping meet increasingly prominent ESG targets through emissions reduction. This paper describes a long-term case study covering the introduction of multiple automated monitoring, advisory and control systems into an already highly optimized jack-up in the North Sea. These resulted in adding incremental value, delivering a multitude of operations significantly below AFE, as well creating a trend of increasing performance spanning a full field development campaign. In addition to quantifying resulting operational cost-out, the paper addresses several points related to challenges of adoption: –Necessity for un-biased operational needs to drive technology development. The industry is often drawn to high-end solutions to complex problems when in fact there are low-hanging fruits, such as simple business-process-automation for reporting, which are highly desired by end-users.–The notion that while there is a lot of rigor in technology development processes, there is not enough focus on the critical human element of adoption. Linked to this is the common misconception that automated systems require less training, when in-fact the opposite is true.–End-user resistance on initial introduction of a black-box system for automated directional drilling. Retroactive software development moves to more grey- or white-box systems, with an associated positive response in user acceptance.–Critically of interoperability between operator, OFS and OEM systems. How this will become more important as both closed-loop control systems, and linkages to enterprise level systems, proliferate. This long-term case study definitively demonstrates that automated systems add value. However, due to the human-component, management-of-change must be carefully considered as we scale adoption.
{"title":"Introducing Automated Advisory and Control Applications to a North Sea Jack-Up, Technology, Human-Centric Challenges and Resulting Performance Improvements at Scale","authors":"M. Forshaw, S. Hovda, John Macpherson","doi":"10.2118/212463-ms","DOIUrl":"https://doi.org/10.2118/212463-ms","url":null,"abstract":"\u0000 As we begin a new decade, drilling systems automation has left its primary residence of PowerPoint slides and is now seeing wider adoption. In areas, the industry sees positive return-on-investment for automation technology development; both financially, from reduction in well construction cost, and in helping meet increasingly prominent ESG targets through emissions reduction.\u0000 This paper describes a long-term case study covering the introduction of multiple automated monitoring, advisory and control systems into an already highly optimized jack-up in the North Sea. These resulted in adding incremental value, delivering a multitude of operations significantly below AFE, as well creating a trend of increasing performance spanning a full field development campaign.\u0000 In addition to quantifying resulting operational cost-out, the paper addresses several points related to challenges of adoption: –Necessity for un-biased operational needs to drive technology development. The industry is often drawn to high-end solutions to complex problems when in fact there are low-hanging fruits, such as simple business-process-automation for reporting, which are highly desired by end-users.–The notion that while there is a lot of rigor in technology development processes, there is not enough focus on the critical human element of adoption. Linked to this is the common misconception that automated systems require less training, when in-fact the opposite is true.–End-user resistance on initial introduction of a black-box system for automated directional drilling. Retroactive software development moves to more grey- or white-box systems, with an associated positive response in user acceptance.–Critically of interoperability between operator, OFS and OEM systems. How this will become more important as both closed-loop control systems, and linkages to enterprise level systems, proliferate.\u0000 This long-term case study definitively demonstrates that automated systems add value. However, due to the human-component, management-of-change must be carefully considered as we scale adoption.","PeriodicalId":103776,"journal":{"name":"Day 2 Wed, March 08, 2023","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117211029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jairo Alexander Diaz Lopez, E. Omdal, James S. Rutherford, H. J. Skadsem
The drilling of extended-reach wells is an increasingly common practice for improving the recovery from mature fields, and for producing distant oil and gas resources using existing infrastructure. From a geomechanical point of view, the drilling and completion of extended-reach wells may become technically very challenging, as these wells often have long sections drilled at high inclinations that can be prone to borehole instability problems such as pack-offs or collapse of the wellbore wall. The case of an extended-reach well drilled in the Ekofisk field in the North Sea where borehole stability issues were observed and eventually resulted in the loss of the well is presented. A wellbore stability assessment is performed with well-specific stress and formation strength data that explores the possible failures that may have resulted in the loss of the well. In particular, a plane of weakness model is used to model possible shear failure along the bedding of the overburden shale formations. The uncertainty in the rock matrix strength is accounted for, as well as the cohesion, friction factor and orientation of the bedding plane, on the mud window using a Monte Carlo approach. This paper focuses in particular on how the properties of the bedding plane affect the minimum required mud weight, and compare to the actual mud weight used in operation. The generated mud window acknowledging failure along the weakness planes suggests that this type of failure was a relevant failure mechanism over the 13 1/2-in section of the well, as the mud weight employed was not high enough to avoid it. Accounting for uncertainty and the failure along the weakness planes in extended-reach wells to be drilled in the Ekofisk area may generate safer mud windows that in turn may reduce the occurrence of wellbore instability in the field.
{"title":"Rock Mechanics Analysis of Observed Borehole Instabilities in an Ekofisk Field Extended-Reach Well","authors":"Jairo Alexander Diaz Lopez, E. Omdal, James S. Rutherford, H. J. Skadsem","doi":"10.2118/212454-ms","DOIUrl":"https://doi.org/10.2118/212454-ms","url":null,"abstract":"\u0000 The drilling of extended-reach wells is an increasingly common practice for improving the recovery from mature fields, and for producing distant oil and gas resources using existing infrastructure. From a geomechanical point of view, the drilling and completion of extended-reach wells may become technically very challenging, as these wells often have long sections drilled at high inclinations that can be prone to borehole instability problems such as pack-offs or collapse of the wellbore wall.\u0000 The case of an extended-reach well drilled in the Ekofisk field in the North Sea where borehole stability issues were observed and eventually resulted in the loss of the well is presented. A wellbore stability assessment is performed with well-specific stress and formation strength data that explores the possible failures that may have resulted in the loss of the well. In particular, a plane of weakness model is used to model possible shear failure along the bedding of the overburden shale formations. The uncertainty in the rock matrix strength is accounted for, as well as the cohesion, friction factor and orientation of the bedding plane, on the mud window using a Monte Carlo approach. This paper focuses in particular on how the properties of the bedding plane affect the minimum required mud weight, and compare to the actual mud weight used in operation.\u0000 The generated mud window acknowledging failure along the weakness planes suggests that this type of failure was a relevant failure mechanism over the 13 1/2-in section of the well, as the mud weight employed was not high enough to avoid it. Accounting for uncertainty and the failure along the weakness planes in extended-reach wells to be drilled in the Ekofisk area may generate safer mud windows that in turn may reduce the occurrence of wellbore instability in the field.","PeriodicalId":103776,"journal":{"name":"Day 2 Wed, March 08, 2023","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121027618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Kokarakis, E. J. Kokarakis, E. Ladakis, H. Petrakakos
The present study investigates the negative impact of a marine polluter on the marine environment. Plastics degraded into micro and macroplastics harm the environment in many ways. Finding their way to the oceans cause increase in temperature at the surface and cooling in deeper waters. Degrading macroplastics releases potent greenhouse gases. More importantly, they are implicated to cause climate change. Plastic in the ocean affects its ability to act as a carbon sink by decelerating the “biogeochemical cycle of carbon”. The ocean is the largest natural sink for anthropogenic greenhouse gases. Various short- and long-term measures are also proposed to curb the flow of plastic waste into the Oceans.
{"title":"Microplastics and their Impact on the Marine Environment","authors":"J. Kokarakis, E. J. Kokarakis, E. Ladakis, H. Petrakakos","doi":"10.5957/some-2023-040","DOIUrl":"https://doi.org/10.5957/some-2023-040","url":null,"abstract":"The present study investigates the negative impact of a marine polluter on the marine environment. Plastics degraded into micro and macroplastics harm the environment in many ways. Finding their way to the oceans cause increase in temperature at the surface and cooling in deeper waters. Degrading macroplastics releases potent greenhouse gases. More importantly, they are implicated to cause climate change. Plastic in the ocean affects its ability to act as a carbon sink by decelerating the “biogeochemical cycle of carbon”. The ocean is the largest natural sink for anthropogenic greenhouse gases. Various short- and long-term measures are also proposed to curb the flow of plastic waste into the Oceans.","PeriodicalId":103776,"journal":{"name":"Day 2 Wed, March 08, 2023","volume":"257 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115796941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dongyoung Yoon, P. Ashok, E. van Oort, Pradeepkumar V. Annaiyappa, Shungo Abe
Although mud pumps are critical rig equipment, their health monitoring currently still relies on human observation. This approach often fails to detect pump damage at an early stage, resulting in non-productive time (NPT) and increased well construction cost when pumps go down unexpectedly and catastrophically. Automated approaches to condition-based maintenance (CBM) of mud pumps to date have failed due to the lack of a generalized solution applicable to any pump type and/or operating conditions. This paper presents a field-validated generally applicable solution to mud pump CBM. Field tests were conducted during drilling operations in West Texas and Japan, to verify the feasibility of the developed pump CBM solution. An accelerometer and acoustic emission (AE) sensor were attached to pump modules, and data was collected during drilling operations. Anomaly detection deep-learning (DL) models were trained during run-time to pinpoint any abnormal behavior by the pump and its elements. The models were trained only with normal state data, and a damage score characterizing the extent of damage to the mud pump was calculated to identify the earliest signs of damage. The system correctly identifies the degradation of the pump and produces alerts to notify the rig crew of the damage level of key mud pump components. During the field tests, different hyper-parameters and features were compared to identify the most effective ones for identifying damage while at the same time delivering low false positive rates (i.e., false alarms during normal state pump operation). The developed CBM system thus provides a generalized solution for pump monitoring, capable of working for different pumps and different operating conditions, and only requires several hours of normal state data with no prior pump data information. This system eliminates the environmental, health and safety (EHS) concerns that can occur during human-based observations of mud pump health, and avoids unnecessary NPT associated with catastrophic pump failures. The final version of this system is expected to be a fully self-contained magnetically attachable box containing sensors and processor, generating simple indicators for recommending pro-active pump maintenance tasks when needed. This is the first successful attempt to validate a universally applicable DL-based CBM system for mud pumps in the field. The system allows more reliable continuous and automated pump monitoring by detecting damage in real-time, thereby enabling timely and pro-active mud pump maintenance and NPT avoidance.
{"title":"Field Validation of Scalable Condition-Based Maintenance (CBM) of Mud Pumps","authors":"Dongyoung Yoon, P. Ashok, E. van Oort, Pradeepkumar V. Annaiyappa, Shungo Abe","doi":"10.2118/212564-ms","DOIUrl":"https://doi.org/10.2118/212564-ms","url":null,"abstract":"\u0000 Although mud pumps are critical rig equipment, their health monitoring currently still relies on human observation. This approach often fails to detect pump damage at an early stage, resulting in non-productive time (NPT) and increased well construction cost when pumps go down unexpectedly and catastrophically. Automated approaches to condition-based maintenance (CBM) of mud pumps to date have failed due to the lack of a generalized solution applicable to any pump type and/or operating conditions. This paper presents a field-validated generally applicable solution to mud pump CBM.\u0000 Field tests were conducted during drilling operations in West Texas and Japan, to verify the feasibility of the developed pump CBM solution. An accelerometer and acoustic emission (AE) sensor were attached to pump modules, and data was collected during drilling operations. Anomaly detection deep-learning (DL) models were trained during run-time to pinpoint any abnormal behavior by the pump and its elements. The models were trained only with normal state data, and a damage score characterizing the extent of damage to the mud pump was calculated to identify the earliest signs of damage.\u0000 The system correctly identifies the degradation of the pump and produces alerts to notify the rig crew of the damage level of key mud pump components. During the field tests, different hyper-parameters and features were compared to identify the most effective ones for identifying damage while at the same time delivering low false positive rates (i.e., false alarms during normal state pump operation). The developed CBM system thus provides a generalized solution for pump monitoring, capable of working for different pumps and different operating conditions, and only requires several hours of normal state data with no prior pump data information. This system eliminates the environmental, health and safety (EHS) concerns that can occur during human-based observations of mud pump health, and avoids unnecessary NPT associated with catastrophic pump failures. The final version of this system is expected to be a fully self-contained magnetically attachable box containing sensors and processor, generating simple indicators for recommending pro-active pump maintenance tasks when needed.\u0000 This is the first successful attempt to validate a universally applicable DL-based CBM system for mud pumps in the field. The system allows more reliable continuous and automated pump monitoring by detecting damage in real-time, thereby enabling timely and pro-active mud pump maintenance and NPT avoidance.","PeriodicalId":103776,"journal":{"name":"Day 2 Wed, March 08, 2023","volume":"88 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116557426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper reviews particular challenges for offshore CO2 injector wells, and how these can be mitigated by improving tools, methods, and best practices. Further, challenges with assessment of leakage risk through existing wellbores is reviewed. Finally, a possible cost reduction path for offshore CO2 injection by simplifications in well design is given.
{"title":"Problems to Solve to Achieve Cost Efficient CO2 Injection Wells","authors":"Henrik Manum, Line Kristin Borgerud, R. Stokke","doi":"10.2118/212485-ms","DOIUrl":"https://doi.org/10.2118/212485-ms","url":null,"abstract":"\u0000 This paper reviews particular challenges for offshore CO2 injector wells, and how these can be mitigated by improving tools, methods, and best practices. Further, challenges with assessment of leakage risk through existing wellbores is reviewed. Finally, a possible cost reduction path for offshore CO2 injection by simplifications in well design is given.","PeriodicalId":103776,"journal":{"name":"Day 2 Wed, March 08, 2023","volume":"871 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123020038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gudrun is a high-pressure, high-temperature (HPHT) field on the Norwegian Continental Shelf which has been in production since 2014. The initial development called for predrilling of the producers prior to commencement of production through depletion drive. In 2020 a second drilling campaign was initiated where the goal was to drill several infill producers and two water injection wells. The issue of drilling in heavily depleted reservoirs was highlighted as a major risk since depletion in some of the layers was expected to be in excess of 450 bar. The operational window was small and uncertain, and several risks were anticipated. Differential depletion in this highly layered reservoir, with the potential for penetrating both heavily depleted layers and non-depleted layers, meant that drilling and completion operations required wellbore pressures in excess of the minimum stress in the heavily depleted layers. There was thus a significant risk for lost circulation and escalation to possible well kick/underground blowout events. To mitigate these risks several actions were taken including Managed pressure drilling (MPD), splitting reservoir drilling into several sections, drilling of near vertical reservoir intervals and the use of active Wellbore Strengthening (WBS)/ Lost Circulation Material (LCM) particles in the mud. The use of optimal background WBS particles was complicated in the first two wells due to risk of plugging of lower completions upon production and so compromises were required to the particle sizes that could be used. This paper summarizes the experience from the successful drilling of these infill wells. It confirms that the use of WBS particles is critical in providing a robust drilling window against losses when the Fracture Gradient (FG) is reliant on near wellbore processes and elevated hoop stress around the wellbore to support downhole pressures that exceed minimum stress deeper in the "body" of the depleted layers. The experience on Gudrun also suggests that the FG is sensitive to the temperature of the mud when drilling the stiff Gudrun layers. The influence of depletion on the minimum horizontal stress, as determined from this drilling campaign, is also discussed and this is related to rock mechanical tests performed on core plugs from the field.
{"title":"Learnings from Successful Drilling in Heavily Depleted HPHT Reservoir with Up to 460 Bar Depletion","authors":"Trond Heggheim, J. Andrews","doi":"10.2118/212526-ms","DOIUrl":"https://doi.org/10.2118/212526-ms","url":null,"abstract":"\u0000 Gudrun is a high-pressure, high-temperature (HPHT) field on the Norwegian Continental Shelf which has been in production since 2014. The initial development called for predrilling of the producers prior to commencement of production through depletion drive. In 2020 a second drilling campaign was initiated where the goal was to drill several infill producers and two water injection wells. The issue of drilling in heavily depleted reservoirs was highlighted as a major risk since depletion in some of the layers was expected to be in excess of 450 bar. The operational window was small and uncertain, and several risks were anticipated. Differential depletion in this highly layered reservoir, with the potential for penetrating both heavily depleted layers and non-depleted layers, meant that drilling and completion operations required wellbore pressures in excess of the minimum stress in the heavily depleted layers. There was thus a significant risk for lost circulation and escalation to possible well kick/underground blowout events. To mitigate these risks several actions were taken including Managed pressure drilling (MPD), splitting reservoir drilling into several sections, drilling of near vertical reservoir intervals and the use of active Wellbore Strengthening (WBS)/ Lost Circulation Material (LCM) particles in the mud. The use of optimal background WBS particles was complicated in the first two wells due to risk of plugging of lower completions upon production and so compromises were required to the particle sizes that could be used. This paper summarizes the experience from the successful drilling of these infill wells. It confirms that the use of WBS particles is critical in providing a robust drilling window against losses when the Fracture Gradient (FG) is reliant on near wellbore processes and elevated hoop stress around the wellbore to support downhole pressures that exceed minimum stress deeper in the \"body\" of the depleted layers. The experience on Gudrun also suggests that the FG is sensitive to the temperature of the mud when drilling the stiff Gudrun layers. The influence of depletion on the minimum horizontal stress, as determined from this drilling campaign, is also discussed and this is related to rock mechanical tests performed on core plugs from the field.","PeriodicalId":103776,"journal":{"name":"Day 2 Wed, March 08, 2023","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128352950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}