Recently, machine learning methods have enjoyed resurgence in the oil and gas industry and provide applications to a wide variety of problems (Noshi et al. 2018). However, few address the important problem of field planning, which is the area of focus of this paper. This paper introduces a machine learning-based framework for field planning and specifically addresses the problem of well location planning. Unsupervised learning is used to understand characteristics of the data, followed by the creation of a regression model trained on available data in a marginal oilfield to develop a prediction tool for well productivity. This data-based prediction tool is used in a workflow to optimize well locations under uncertainty, and then in another workflow, using an adaptation from modern portfolio theory (MPT) (Markowitz 1952), to evaluate recommended well locations. The latter workflow enables the operator to select a portfolio of wells to maximize returns at a given risk tolerance. Both workflows are applicable to plays where drainage areas for wells are small; consequently, a well can be assumed to produce independently of other wells. This assumption is true for both early-stage shale plays and conventional fields in tight rocks. As compared to traditional reservoirs, a very large number of wells are drilled in shale plays, generating a very large amount of data that existing productivity prediction tools, such as reservoir simulators, find difficult to consume and use in practical timeframes. The presented framework is attractive for shales because it can easily handle large datasets. The framework accounts explicitly for risk resulting from uncertainty in well productivity and uses data typically acquired in the field, but not used currently for field planning.
最近，机器学习方法在石油和天然气行业重新兴起，并为各种各样的问题提供了应用(Noshi et al. 2018)。然而，很少有人解决现场规划的重要问题，这是本文的重点领域。本文介绍了一种基于机器学习的现场规划框架，并具体解决了井位规划问题。无监督学习用于了解数据的特征，然后根据边缘油田的可用数据创建回归模型，以开发油井产能预测工具。这种基于数据的预测工具用于在不确定情况下优化井位的工作流程，然后在另一个工作流程中，使用现代投资组合理论(MPT) (Markowitz 1952)来评估推荐的井位。后一种工作流程使作业者能够在给定的风险承受能力下选择油井组合，以实现收益最大化。这两种工作流程都适用于排水面积较小的井;因此，可以假设一口井独立于其他井进行生产。这一假设既适用于早期页岩油气藏，也适用于致密岩层中的常规油田。与传统油藏相比，在页岩气藏中钻了大量的井，产生了大量的数据，而现有的产能预测工具(如油藏模拟器)很难在实际时间内消化和使用。所提出的框架对页岩具有吸引力，因为它可以轻松处理大型数据集。该框架明确考虑了油井产能不确定性带来的风险，并使用了通常在现场获得的数据，但目前尚未用于现场规划。
{"title":"A Machine Learning Application for Field Planning","authors":"Amit Kumar","doi":"10.4043/29224-MS","DOIUrl":"https://doi.org/10.4043/29224-MS","url":null,"abstract":"\u0000 Recently, machine learning methods have enjoyed resurgence in the oil and gas industry and provide applications to a wide variety of problems (Noshi et al. 2018). However, few address the important problem of field planning, which is the area of focus of this paper.\u0000 This paper introduces a machine learning-based framework for field planning and specifically addresses the problem of well location planning. Unsupervised learning is used to understand characteristics of the data, followed by the creation of a regression model trained on available data in a marginal oilfield to develop a prediction tool for well productivity. This data-based prediction tool is used in a workflow to optimize well locations under uncertainty, and then in another workflow, using an adaptation from modern portfolio theory (MPT) (Markowitz 1952), to evaluate recommended well locations. The latter workflow enables the operator to select a portfolio of wells to maximize returns at a given risk tolerance.\u0000 Both workflows are applicable to plays where drainage areas for wells are small; consequently, a well can be assumed to produce independently of other wells. This assumption is true for both early-stage shale plays and conventional fields in tight rocks.\u0000 As compared to traditional reservoirs, a very large number of wells are drilled in shale plays, generating a very large amount of data that existing productivity prediction tools, such as reservoir simulators, find difficult to consume and use in practical timeframes. The presented framework is attractive for shales because it can easily handle large datasets.\u0000 The framework accounts explicitly for risk resulting from uncertainty in well productivity and uses data typically acquired in the field, but not used currently for field planning.","PeriodicalId":10948,"journal":{"name":"Day 2 Tue, May 07, 2019","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73021237","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 development concepts for the Johan Castberg Field matured, new locations required soil data. A harder layer has been identified from previous soil data and mapped on seismic profiles as Seismic Unit II. This layer may cause refusal of suction anchor penetration and should ideally be avoided. Predictions of the depth to this layer both along and between seismic profiles were used to optimize suction anchor locations to be investigated during the 2018 soil investigation. This campaign was furthermore optimized by taking earlier laboratory testing into consideration. The Nkt factors were given special attention and found not to vary much in the topmost soil layers. Greater emphasis could therefore be put on acquiring CPTU data, and to use these previously determined Nkt factors to find the soil strength. The predictions of the depths to the top of Seismic Unit II were in general agreement with the data acquired during the 2018 investigation. The emphasis on collecting CPTU data and combining these with experience from the previous soil testing results saved both ship time and laboratory costs.
{"title":"Challenges from Soil Variability, Johan Castberg Field, Barents Sea","authors":"C. Forsberg, E. Solhjell, V. Karlsen, V. Vangen","doi":"10.4043/29605-MS","DOIUrl":"https://doi.org/10.4043/29605-MS","url":null,"abstract":"\u0000 As development concepts for the Johan Castberg Field matured, new locations required soil data. A harder layer has been identified from previous soil data and mapped on seismic profiles as Seismic Unit II. This layer may cause refusal of suction anchor penetration and should ideally be avoided. Predictions of the depth to this layer both along and between seismic profiles were used to optimize suction anchor locations to be investigated during the 2018 soil investigation. This campaign was furthermore optimized by taking earlier laboratory testing into consideration. The Nkt factors were given special attention and found not to vary much in the topmost soil layers. Greater emphasis could therefore be put on acquiring CPTU data, and to use these previously determined Nkt factors to find the soil strength.\u0000 The predictions of the depths to the top of Seismic Unit II were in general agreement with the data acquired during the 2018 investigation. The emphasis on collecting CPTU data and combining these with experience from the previous soil testing results saved both ship time and laboratory costs.","PeriodicalId":10948,"journal":{"name":"Day 2 Tue, May 07, 2019","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78839711","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}
Underwriting the costly insurance of complex oil and gas projects — with every one unique — requires careful risk assessment of numerous factors via long-standing criteria. But two risk-mitigation factors not currently considered are (a) the increased operational visibility; and (b) predictive maintenance made possible by today’s advanced asset management technologies. Those technologies include the digital twin, data analytics, and secure Internet of Things (IoT) connectivity. With these technologies, E&P operators can now better quantify the probabilities of untoward events and mitigate their risks, improving their HSE posture, and potentially reducing the cost of their insurance premiums. In fact, one E&P OEM using digitalization to better quantify risks related to project errors and omissions led to a $750,000 premium reduction from its insurer, one of the world’s largest insurance companies.
{"title":"The Evolution of Asset Management: Harnessing Digitalization and Data Analytics","authors":"J. Nixon, Emil Pena","doi":"10.4043/29347-MS","DOIUrl":"https://doi.org/10.4043/29347-MS","url":null,"abstract":"\u0000 Underwriting the costly insurance of complex oil and gas projects — with every one unique — requires careful risk assessment of numerous factors via long-standing criteria. But two risk-mitigation factors not currently considered are (a) the increased operational visibility; and (b) predictive maintenance made possible by today’s advanced asset management technologies. Those technologies include the digital twin, data analytics, and secure Internet of Things (IoT) connectivity. With these technologies, E&P operators can now better quantify the probabilities of untoward events and mitigate their risks, improving their HSE posture, and potentially reducing the cost of their insurance premiums. In fact, one E&P OEM using digitalization to better quantify risks related to project errors and omissions led to a $750,000 premium reduction from its insurer, one of the world’s largest insurance companies.","PeriodicalId":10948,"journal":{"name":"Day 2 Tue, May 07, 2019","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79691662","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}
In 2011 78% of upstream oil & gas megaprojects faced either cost or schedule overruns according to an industry study by the Independent Project Analysis (Merrow, 2012). In 2014, research by EY found 64% of projects faced cost overruns (EY, 2014) and 73% of projects faced schedule overruns. In 2017 the UK Oil & Gas Authority (OGA) published a study of lessons learned from UKCS oil & gas projects between 2011-2016, which reported "since 2011 fewer than 25% of oil and gas projects have been delivered on time with projects averaging 10 months’ delay and coming in around 35% over budget." (OGA, 2017) This level of cost and schedule underperformance was not sustainable in the high oil price economic environment and is inconceivable in the lower oil price environment in which we now operate. Both the EY and the OGA reports identify factors for these overruns and lessons that can be learned. These include organisational learnings, project management failings, inadequate planning and cognitive biases within the team. One of the key lessons identified in the OGA report was that high-quality Front-End Loading (FEL) is critical to project success. A successful FEL should develop sufficient strategic information to allow decisions to be made that maximise the chance of a successful project. As part of its unique approach to field development, which brings projects to market faster and with more certainty, we have created a methodology, based on the approach developed by Professor Ronald A. Howard at Stanford University, to deliver a high quality FEL. This methodology is underpinned by a number of unique tools and techniques and draws on best practice from a variety of industries, including aerospace, smart cities and software development. The methodology paves the way for a digital project execution and the evolution of an operational digital twin.
根据独立项目分析公司(Merrow, 2012)的一项行业研究，2011年，78%的上游油气大型项目面临成本或进度超支的问题。2014年，安永的研究发现，64%的项目面临成本超支(安永，2014年)，73%的项目面临进度超支。2017年，英国石油和天然气管理局(OGA)发布了一份研究报告，总结了2011-2016年间英国油气项目的经验教训，报告称:“自2011年以来，只有不到25%的油气项目按时交付，项目平均延迟10个月，超出预算约35%。”(OGA, 2017)在高油价的经济环境中，这种成本和进度表现不佳的水平是不可持续的，在我们现在运营的低油价环境中是不可想象的。安永和OGA的报告都指出了这些超支的因素和可以吸取的教训。这些问题包括组织学习、项目管理失败、计划不足和团队内部的认知偏差。OGA报告中确定的一个关键教训是，高质量的前端加载(FEL)对项目的成功至关重要。一个成功的FEL应该开发足够的战略信息，以便做出决策，使项目成功的机会最大化。作为其独特的现场开发方法的一部分，它将项目更快、更确定地推向市场，我们基于斯坦福大学Ronald a . Howard教授开发的方法创建了一种方法，以提供高质量的FEL。该方法以许多独特的工具和技术为基础，并借鉴了包括航空航天、智慧城市和软件开发在内的各个行业的最佳实践。该方法为数字项目的执行和可操作数字孪生的发展铺平了道路。
{"title":"Field Development: Agile Value Optimisation","authors":"D. McLachlan, J. Isherwood, Max Peile","doi":"10.4043/29607-MS","DOIUrl":"https://doi.org/10.4043/29607-MS","url":null,"abstract":"\u0000 In 2011 78% of upstream oil & gas megaprojects faced either cost or schedule overruns according to an industry study by the Independent Project Analysis (Merrow, 2012). In 2014, research by EY found 64% of projects faced cost overruns (EY, 2014) and 73% of projects faced schedule overruns. In 2017 the UK Oil & Gas Authority (OGA) published a study of lessons learned from UKCS oil & gas projects between 2011-2016, which reported \"since 2011 fewer than 25% of oil and gas projects have been delivered on time with projects averaging 10 months’ delay and coming in around 35% over budget.\" (OGA, 2017) This level of cost and schedule underperformance was not sustainable in the high oil price economic environment and is inconceivable in the lower oil price environment in which we now operate.\u0000 Both the EY and the OGA reports identify factors for these overruns and lessons that can be learned. These include organisational learnings, project management failings, inadequate planning and cognitive biases within the team. One of the key lessons identified in the OGA report was that high-quality Front-End Loading (FEL) is critical to project success. A successful FEL should develop sufficient strategic information to allow decisions to be made that maximise the chance of a successful project.\u0000 As part of its unique approach to field development, which brings projects to market faster and with more certainty, we have created a methodology, based on the approach developed by Professor Ronald A. Howard at Stanford University, to deliver a high quality FEL. This methodology is underpinned by a number of unique tools and techniques and draws on best practice from a variety of industries, including aerospace, smart cities and software development. The methodology paves the way for a digital project execution and the evolution of an operational digital twin.","PeriodicalId":10948,"journal":{"name":"Day 2 Tue, May 07, 2019","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76609989","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 presents the design challenges encountered in a flexible riser application with an external turret moored FSO in a shallow water depth around 55m, and the solutions obtained for an improved lazy wave flexible riser system. Extensive dynamic analyses were performed with parametric variations and a model test was also carried out to validate the predicted dynamic responses. The lazy wave flexible riser system is preferred for shallow water applications due to it being cost effective in terms of both fabrication and installation, and high reliability in operational performance. The system relies on the balance of the riser system weight and buoyancy applied, and it is required to accommodate large excursions and dynamic motions of the mono-hull vessel induced by the environmental loadings. The riser system weight varies due to pipe contents changes and heavy marine growth. When the water becomes shallower, the challenges escalate to maintain the riser system to remaining in suspension without clashing with the sea bed or vessel. An enhanced Lazy Wave Flexible Riser solution, a patented technology of BHGE, was adopted. In this technology, the ballast modules were used innovatively to maintain the configuration in suspension by automatically compensating the riser weight variation during entire service period. The paper also summarizes preliminary benefits of the improved lazy wave flexible riser technology over the potential alternative technologies for such shallow water application, for example, the traditional S configuration and the latest middle-water-jacket configuration. Both alternatives involve significant high cost in fabrication and installation.
{"title":"Application of an Enhanced Lazy Wave Flexible Riser System in Extreme Shallow Water with an External Turret Moored FPSO","authors":"Yucheng Hou, Jiabei Yuan, Z. Tan, J. Witz","doi":"10.4043/29327-MS","DOIUrl":"https://doi.org/10.4043/29327-MS","url":null,"abstract":"\u0000 This paper presents the design challenges encountered in a flexible riser application with an external turret moored FSO in a shallow water depth around 55m, and the solutions obtained for an improved lazy wave flexible riser system. Extensive dynamic analyses were performed with parametric variations and a model test was also carried out to validate the predicted dynamic responses.\u0000 The lazy wave flexible riser system is preferred for shallow water applications due to it being cost effective in terms of both fabrication and installation, and high reliability in operational performance. The system relies on the balance of the riser system weight and buoyancy applied, and it is required to accommodate large excursions and dynamic motions of the mono-hull vessel induced by the environmental loadings. The riser system weight varies due to pipe contents changes and heavy marine growth. When the water becomes shallower, the challenges escalate to maintain the riser system to remaining in suspension without clashing with the sea bed or vessel. An enhanced Lazy Wave Flexible Riser solution, a patented technology of BHGE, was adopted. In this technology, the ballast modules were used innovatively to maintain the configuration in suspension by automatically compensating the riser weight variation during entire service period.\u0000 The paper also summarizes preliminary benefits of the improved lazy wave flexible riser technology over the potential alternative technologies for such shallow water application, for example, the traditional S configuration and the latest middle-water-jacket configuration. Both alternatives involve significant high cost in fabrication and installation.","PeriodicalId":10948,"journal":{"name":"Day 2 Tue, May 07, 2019","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90693474","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}
Across the energy industry, leading companies are eager to embrace digital innovation and all the predictive benefits it offers. Yet some of the largest companies still rely on sporadic, manual inspections to ensure the smooth operation of their machinery, equipment, instrumentation and systems. One international oil and gas company realized even the most skilled plant technicians could miss certain warning signals. If equipment like heat exchangers, pumps or critical valves are checked only periodically, manufacturers can risk equipment failure, outages or worse — health and safety incidents. Thanks to advancements in the quality and affordability of sensors as well as wireless technologies and cloud-based applications to gather and analyze data being streamed from devices in the field, companies like this one can gain better insights from equipment and take proactive measures to prevent failures and plant shutdowns. The company worked with third-party technology vendors to implement a predictive reliability and maintenance program that will save millions of dollars a year in operational costs by instrumenting and monitoring heat exchangers in one of the company's refineries. The program is designed to digitally transform the company's heat exchanger maintenance activities and free refinery personnel from laborious manual monitoring, enabling them to focus on other functions and operational needs. A typical refinery will have 200-400 heat exchangers, the majority of which are manually monitored, with months passing between inspections. If undetected, heat exchanger fouling can cause degraded performance, reduced energy efficiency, process slowdowns and unscheduled shutdowns. Installation of more sensors to drive plant monitoring applications is an option, but the cost and disruption of installing new, conventional wired temperature sensors to an existing facility is prohibitive. One of the vendors developed and installed unique cost-effective sensors to provide accurate measurements from the refinery's heat exchangers without thermowell process penetration. These sensors allow for remote monitoring of heat exchanger data in real time. As part of the ongoing program, the data is transmitted through a secure, wireless architecture and transferred to the cloud using cloud-computing technologies. Using advanced analytics, the data is then interpreted to provide plant personnel with actionable data to optimize operational performance. There have been significant savings in sensor installation (a fraction of the cost of conventional sensors) and commissioning time (one week versus the typical six weeks). The plant has also seen savings in staff time. The company can detect small variations well before any fouling issues start. The program is proving that, by understanding the health of the heat exchangers, the company can help prevent unplanned outages and reduce the number of scheduled repairs. Facilities can reduce energy and capa
{"title":"Case Study: How Digital Transformation Paved the Way for One Refinery's Predictive Maintenance Strategy","authors":"Peter Zornio, Mike Boudreaux","doi":"10.4043/29556-MS","DOIUrl":"https://doi.org/10.4043/29556-MS","url":null,"abstract":"\u0000 Across the energy industry, leading companies are eager to embrace digital innovation and all the predictive benefits it offers. Yet some of the largest companies still rely on sporadic, manual inspections to ensure the smooth operation of their machinery, equipment, instrumentation and systems.\u0000 One international oil and gas company realized even the most skilled plant technicians could miss certain warning signals. If equipment like heat exchangers, pumps or critical valves are checked only periodically, manufacturers can risk equipment failure, outages or worse — health and safety incidents.\u0000 Thanks to advancements in the quality and affordability of sensors as well as wireless technologies and cloud-based applications to gather and analyze data being streamed from devices in the field, companies like this one can gain better insights from equipment and take proactive measures to prevent failures and plant shutdowns.\u0000 \u0000 \u0000 The company worked with third-party technology vendors to implement a predictive reliability and maintenance program that will save millions of dollars a year in operational costs by instrumenting and monitoring heat exchangers in one of the company's refineries. The program is designed to digitally transform the company's heat exchanger maintenance activities and free refinery personnel from laborious manual monitoring, enabling them to focus on other functions and operational needs.\u0000 A typical refinery will have 200-400 heat exchangers, the majority of which are manually monitored, with months passing between inspections. If undetected, heat exchanger fouling can cause degraded performance, reduced energy efficiency, process slowdowns and unscheduled shutdowns. Installation of more sensors to drive plant monitoring applications is an option, but the cost and disruption of installing new, conventional wired temperature sensors to an existing facility is prohibitive.\u0000 One of the vendors developed and installed unique cost-effective sensors to provide accurate measurements from the refinery's heat exchangers without thermowell process penetration. These sensors allow for remote monitoring of heat exchanger data in real time. As part of the ongoing program, the data is transmitted through a secure, wireless architecture and transferred to the cloud using cloud-computing technologies. Using advanced analytics, the data is then interpreted to provide plant personnel with actionable data to optimize operational performance.\u0000 \u0000 \u0000 \u0000 There have been significant savings in sensor installation (a fraction of the cost of conventional sensors) and commissioning time (one week versus the typical six weeks). The plant has also seen savings in staff time. The company can detect small variations well before any fouling issues start.\u0000 The program is proving that, by understanding the health of the heat exchangers, the company can help prevent unplanned outages and reduce the number of scheduled repairs. Facilities can reduce energy and capa","PeriodicalId":10948,"journal":{"name":"Day 2 Tue, May 07, 2019","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87056836","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}
Coral South Floating Liquefied Natural Gas (FLNG) unit is designed to offload its product to LNG Carriers (LNGC) moored in a Side-by-Side (SBS) configuration, using Marine Loading Arms (MLA) technology. With such a method, multiple design aspects require accurate hydrodynamic simulations at an early stage of engineering phase for a large number of environmental conditions, including wind sea and swell: sizing of FLNG mooring outfitting, design of the MLAs for the candidate LNGC fleet and availability of LNG offloading. Complex phenomena like multi-body hydrodynamic coupling and LNG sloshing in partially filled tanks must be accounted for, and non-linear berthing characteristics require time-domain simulations. However the computing time for all the environmental conditions described in the available 23-year hindcast databases combined with all the possibilities of FLNG heading obtained with thruster assistance, for multiple LNGC and loading conditions, is not compatible with the project engineering phase timeframe, so the simulations must be first performed on a suitable-size sample of environmental conditions, creating a database which can then be used for predicting the data related to any environment. The selected sample of environmental conditions must meet the constraints of computing time while keeping a sufficient resolution to be reliable. In other projects, the time-domain quantities subject to operability criteria, derived from this limited number of simulations, were used to predict the behavior for any unknown environment by interpolation. This approach presented some limitations like the overfitting of maxima dependent on the wave realization (seed), which is seen as a noise, and was not best suited for generalizing the results to non-simulated environments out of the sample. In this paper, the improved methodology used for the Coral South FLNG project is presented. A Radial Basis Function (RBF) Artificial Neural Network (ANN) is used to model the variables impacting the SBS offloading operability. The ANN learns from the results of simulations performed on a sample defined with a K-means clustering algorithm. The RBF is modified to be adapted to the specifics of the driving parameters, of which some are periodic (wave direction) and the rest non-periodic. A proper smoothing of seed-dependent maxima and accurate estimations for unknown environments (generalizations) are achieved. The learning process does not require significant computing time and fewer preliminary time-domain simulations are needed. This design methodology represents a significant improvement for the calculations performed during the project's engineering phase, but it may also be applied later once offshore, to assist in decision making relative to the weekly forecasted SBS LNG offloading operations. When Coral South FLNG operates, the learning database may be completed with on-site measurements to further improve its accuracy. The principle may also be extend
Coral South浮式液化天然气(FLNG)装置旨在将其产品卸载到并排(SBS)配置的液化天然气运输船(LNGC)上，使用海洋装载臂(MLA)技术。使用这种方法，多个设计方面需要在工程早期阶段对大量环境条件进行精确的流体动力学模拟，包括风海和涌浪，FLNG系泊设备的尺寸，候选LNG船队的mla设计以及LNG卸载的可用性。复杂的现象，如多体流体动力耦合和液化天然气晃动在部分填充的储罐必须考虑，非线性靠泊特性需要时域模拟。然而，在现有的23年后发数据库中描述的所有环境条件的计算时间，以及在推进器辅助下获得的FLNG航向的所有可能性，对于多个LNGC和加载条件，与项目工程阶段时间框架不兼容，因此必须首先在适当规模的环境条件样本上进行模拟。创建一个数据库，该数据库可用于预测与任何环境相关的数据。所选择的环境条件样本必须满足计算时间的限制，同时保持足够的分辨率以保证可靠性。在其他项目中，从有限数量的模拟中得出的符合可操作性标准的时域量被用来通过插值来预测任何未知环境的行为。这种方法存在一些局限性，例如依赖于波实现(种子)的最大值的过拟合，这被视为噪声，并且不适合将结果推广到样本外的非模拟环境。本文介绍了在珊瑚南FLNG项目中使用的改进方法。采用径向基函数(RBF)人工神经网络(ANN)对影响SBS卸载可操作性的变量进行建模。人工神经网络从用k均值聚类算法定义的样本上进行的模拟结果中学习。对RBF进行了修改，以适应驱动参数的具体情况，其中一些是周期性的(波方向)，其余是非周期性的。实现了种子相关最大值的适当平滑和对未知环境的精确估计(推广)。学习过程不需要大量的计算时间，并且需要较少的初步时域模拟。这种设计方法对项目工程阶段的计算进行了重大改进，但它也可以在海上应用，以帮助制定与每周预测的SBS LNG卸载作业相关的决策。当Coral South FLNG投入使用时，学习数据库可能会通过现场测量来完成，以进一步提高其准确性。该原则也可以推广到其他受环境条件限制的海上作业。
{"title":"Prediction of Coral South FLNG Side-by-Side Offloading Operability Using Radial Basis Function Artificial Neural Networks","authors":"E. Auburtin, Thiago Miliante, Diego Lima","doi":"10.4043/29263-MS","DOIUrl":"https://doi.org/10.4043/29263-MS","url":null,"abstract":"\u0000 Coral South Floating Liquefied Natural Gas (FLNG) unit is designed to offload its product to LNG Carriers (LNGC) moored in a Side-by-Side (SBS) configuration, using Marine Loading Arms (MLA) technology. With such a method, multiple design aspects require accurate hydrodynamic simulations at an early stage of engineering phase for a large number of environmental conditions, including wind sea and swell: sizing of FLNG mooring outfitting, design of the MLAs for the candidate LNGC fleet and availability of LNG offloading.\u0000 Complex phenomena like multi-body hydrodynamic coupling and LNG sloshing in partially filled tanks must be accounted for, and non-linear berthing characteristics require time-domain simulations. However the computing time for all the environmental conditions described in the available 23-year hindcast databases combined with all the possibilities of FLNG heading obtained with thruster assistance, for multiple LNGC and loading conditions, is not compatible with the project engineering phase timeframe, so the simulations must be first performed on a suitable-size sample of environmental conditions, creating a database which can then be used for predicting the data related to any environment.\u0000 The selected sample of environmental conditions must meet the constraints of computing time while keeping a sufficient resolution to be reliable. In other projects, the time-domain quantities subject to operability criteria, derived from this limited number of simulations, were used to predict the behavior for any unknown environment by interpolation. This approach presented some limitations like the overfitting of maxima dependent on the wave realization (seed), which is seen as a noise, and was not best suited for generalizing the results to non-simulated environments out of the sample. In this paper, the improved methodology used for the Coral South FLNG project is presented. A Radial Basis Function (RBF) Artificial Neural Network (ANN) is used to model the variables impacting the SBS offloading operability. The ANN learns from the results of simulations performed on a sample defined with a K-means clustering algorithm. The RBF is modified to be adapted to the specifics of the driving parameters, of which some are periodic (wave direction) and the rest non-periodic. A proper smoothing of seed-dependent maxima and accurate estimations for unknown environments (generalizations) are achieved. The learning process does not require significant computing time and fewer preliminary time-domain simulations are needed.\u0000 This design methodology represents a significant improvement for the calculations performed during the project's engineering phase, but it may also be applied later once offshore, to assist in decision making relative to the weekly forecasted SBS LNG offloading operations. When Coral South FLNG operates, the learning database may be completed with on-site measurements to further improve its accuracy. The principle may also be extend","PeriodicalId":10948,"journal":{"name":"Day 2 Tue, May 07, 2019","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87471637","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}
The purpose of this project was to confirm the occurrence of and to characterize hydrocarbon gas diffusion through a swollen reduced-scale packer of oil swellable material. The extent and origin of extrusion at the ends of the scaled packer is a key measurement. A quantitative and qualitative analysis was performed to determine if the miscible gas mixture damaged the structure or compromised the capability of the elastomer / swellable packer to hold pressure. Two packers were swollen (separate fixtures) in diesel under conditions similar to downhole pressure and temperature. The test fixtures were limited to an internal pressure of 2000 psi. A 1900 psi differential pressure was applied across the two test samples using the swell fluid. A temperature of 72ºC was maintained for the test. A miscible hydrocarbon gas was then introduced (1900 psi) to one of the test samples to completely displace diesel from the high-pressure side of the test fixture. Pressure and temperature were maintained for approximately 35 days during which regular computed tomography scans were conducted to detect any changes in the density of the swellable rubber element.
{"title":"Analyzing Swellable Packer Model Under Miscible Gas Differential Pressure Utilizing Computerized Tomography Scanning","authors":"R. Pounds, Chad Glaesman","doi":"10.4043/29521-MS","DOIUrl":"https://doi.org/10.4043/29521-MS","url":null,"abstract":"\u0000 The purpose of this project was to confirm the occurrence of and to characterize hydrocarbon gas diffusion through a swollen reduced-scale packer of oil swellable material. The extent and origin of extrusion at the ends of the scaled packer is a key measurement. A quantitative and qualitative analysis was performed to determine if the miscible gas mixture damaged the structure or compromised the capability of the elastomer / swellable packer to hold pressure.\u0000 Two packers were swollen (separate fixtures) in diesel under conditions similar to downhole pressure and temperature. The test fixtures were limited to an internal pressure of 2000 psi. A 1900 psi differential pressure was applied across the two test samples using the swell fluid. A temperature of 72ºC was maintained for the test. A miscible hydrocarbon gas was then introduced (1900 psi) to one of the test samples to completely displace diesel from the high-pressure side of the test fixture. Pressure and temperature were maintained for approximately 35 days during which regular computed tomography scans were conducted to detect any changes in the density of the swellable rubber element.","PeriodicalId":10948,"journal":{"name":"Day 2 Tue, May 07, 2019","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85096784","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}
In this paper, we demonstrate the potential of neural networks in the automation of shallow geohazard detection and identification on seismic images. We discuss technical considerations and method limitations. The method used in this paper trains a neural network prediction model to automatically detect features in seismic images by estimating model parameters from a large set of input training images that have been manually interpreted. In this case, the independent variable is the seismic image and the dependent variable is the human interpretation. We used a separate test data set that was not used in training the model to validate our results. The novel approach and workflow presented in this paper is a significant advancement in geohazard detection and identification projects. The time taken to complete such a project using a conventional approach is significantly reduced – our model interprets entire seismic volumes in seconds with consistency, minimal human input and comparable accuracy.
{"title":"Automatic Geohazard Detection Using Neural Networks","authors":"Adeyemi Arogunmati, M. Moocarme","doi":"10.4043/29326-MS","DOIUrl":"https://doi.org/10.4043/29326-MS","url":null,"abstract":"\u0000 In this paper, we demonstrate the potential of neural networks in the automation of shallow geohazard detection and identification on seismic images. We discuss technical considerations and method limitations. The method used in this paper trains a neural network prediction model to automatically detect features in seismic images by estimating model parameters from a large set of input training images that have been manually interpreted. In this case, the independent variable is the seismic image and the dependent variable is the human interpretation. We used a separate test data set that was not used in training the model to validate our results. The novel approach and workflow presented in this paper is a significant advancement in geohazard detection and identification projects. The time taken to complete such a project using a conventional approach is significantly reduced – our model interprets entire seismic volumes in seconds with consistency, minimal human input and comparable accuracy.","PeriodicalId":10948,"journal":{"name":"Day 2 Tue, May 07, 2019","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88467720","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}
With continued pressure to reduce costs of offshore developments, coupled with more stringent environmental regulations and a continued focus on safe operations; operators, drilling contractors, and service companies alike, continue to explore different avenues to remove waste within their operations by removing inefficiencies in a safe and environmentally responsible way. If we take a closer look at other industries, we can find technologies that exist today that can be adopted and adapted to support the offshore O&G industry in these efforts to remove waste. Hybrid power systems, remote operations, digitalization, big data analytics, and automation are just a few of the tools that can drive this sustainable environment. In this paper we will explore these technologies and how their adoption can positively impact the entire offshore environment. The intent is to elicit new thoughts, and ideas of how we can collaborate, as an industry, in creating a safe and sustainable Smart Offshore Ecosystem.
{"title":"Smart Offshore Ecosystem – Enabling a Safe and Sustainable Offshore Environment Utilizing Smart Technology","authors":"J. Thigpen","doi":"10.4043/29258-MS","DOIUrl":"https://doi.org/10.4043/29258-MS","url":null,"abstract":"\u0000 With continued pressure to reduce costs of offshore developments, coupled with more stringent environmental regulations and a continued focus on safe operations; operators, drilling contractors, and service companies alike, continue to explore different avenues to remove waste within their operations by removing inefficiencies in a safe and environmentally responsible way.\u0000 If we take a closer look at other industries, we can find technologies that exist today that can be adopted and adapted to support the offshore O&G industry in these efforts to remove waste. Hybrid power systems, remote operations, digitalization, big data analytics, and automation are just a few of the tools that can drive this sustainable environment. In this paper we will explore these technologies and how their adoption can positively impact the entire offshore environment. The intent is to elicit new thoughts, and ideas of how we can collaborate, as an industry, in creating a safe and sustainable Smart Offshore Ecosystem.","PeriodicalId":10948,"journal":{"name":"Day 2 Tue, May 07, 2019","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87651504","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：