Day 1 Mon, May 06, 2019最新文献

{"title":"Self-Supervised Subsea SLAM for Autonomous Operations","authors":"F. Marques, Pedro Costa, Filipa Castro, Manuel Parente","doi":"10.4043/29602-MS","DOIUrl":"https://doi.org/10.4043/29602-MS","url":null,"abstract":"\u0000 The Earth’s surface is mostly water-covered and the ocean is the source of a significant slice on natural resources and renewable energies. However, only a small fraction of the ocean has been surveyed. Being able to estimate the 3D model of the environment from a single video eases the task of surveying the underwater environment, saves costs and opens doors to autonomous exploration of unknown environments. In order to estimate the 3D structure of a vehicle’s surrounding environment, we propose a deep learning based Simultaneous Localization and Mapping (SLAM) method. With our method, it is possible to predict a depth map of a given video frame while, at the same time, estimate the movement of the vehicle between different frames. Our method is completely self-supervised, meaning that it only requires a dataset of videos, without ground truth, to be trained. We propose a novel learning based depth map prior using Generative Adversarial Networks (GANs) to improve the depth map prediction results. We evaluate the performance of our method on the KITTI dataset and on a private dataset of subsea inspection videos. We show that our method outperforms state of the art SLAM methods in both depth prediction and pose estimation tasks. In particular, our method achieves a mean Absolute Trajectory Error of 1.6 feet in our private subsea test dataset.","PeriodicalId":11149,"journal":{"name":"Day 1 Mon, May 06, 2019","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80679678","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}

{"title":"Practice of Riser-Soil Interactions at Touch Down Zones for Steel Catenary Risers","authors":"Jinbo Chen, J. Newlin, Meng Luo, Heping Zhang, C. Hadley, Shuang Hu","doi":"10.4043/29553-MS","DOIUrl":"https://doi.org/10.4043/29553-MS","url":null,"abstract":"\u0000 Riser-soil interactions have significant influence on the fatigue assessment of steel catenary risers (SCRs) near the touch down zones (TDZs), and can be critical in realizing a competitive SCR design and in extending a SCR design life. The motivation of the paper is to share the proprietary model test data and research/ design experience accumulated over the past three decades on the riser-soil interactions with the riser engineering community in order to deepen the understanding of this complex problem and to realize economical SCR designs. The objectives are (i) to present a fully nonlinear hysteresis model that captures the loading history of the riser-soil interactions at TDZs in the vertical direction for SCRs, and (ii) to propose a simplified equivalent linear elastic vertical stiffness for SCRs at TDZs for quick fatigue assessments. The paper begins with the mathematical formulation of the nonlinear model and the equivalent linear model for riser-soil interactions. Then the proposed model is verified through the consistent predictions from time-domain and frequency-domain simulations of an SCR from a Tension Leg Platform (TLP), the close agreement between the proposed model predictions and small scale pipe-soil interaction model test results, reduced scale sectional SCR model test results, and the latest study in the literature.","PeriodicalId":11149,"journal":{"name":"Day 1 Mon, May 06, 2019","volume":"511 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86851635","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}

{"title":"Elimination of False Positives in VIV Identification Using Machine Learning","authors":"P. Agarwal, K. Bhalla, R. Campbell","doi":"10.4043/29503-MS","DOIUrl":"https://doi.org/10.4043/29503-MS","url":null,"abstract":"\u0000 Vortex-induced-vibration (VIV) is an important consideration while drilling at sites with moderate to high current speeds. Planning for drilling operations often includes determination of limits on maximum drilling riser motion amplitude using model simulations. These limits can then be used to raise alarms in the field by comparing motions measured in the field using one or more motion sensors. The determination of such alarm limits is challenging as VIV is a highly nonlinear process, and small changes in the speed or shape of current profile can result in quite different VIV fatigue results for drilling risers, especially in deep water depths.\u0000 We use feed-forward neural network, which is a powerful machine learning algorithm, to develop a classifier for distinguishing damaging and non-damaging VIV events. The neural network uses acceleration and angular rate data from only three motions sensors located on the upper flex joint, the lower flex joint and the BOP stack. To train the neural network, riser motions and fatigue damage data are generated from SHEAR7 runs on the model of the drilling riser. Thousands of current profiles measured from a current mooring at a deepwater site (water depth > 6,000 ft) are used as inputs to SHEAR7 model in order to capture full variability in VIV response from the actual field environment.\u0000 Results show that the neural network classifier almost always predicts damaging and non-damaging VIV correctly. The precision, recall, and F1 score (a combination of precision and recall) for the neural network classifier are all close to 100%. A high precision, recall, and F1 score for a classifier implies that it has no false positives and no false negatives. Here, a false negative is defined as the situation when damaging VIV occurred but was identified as a non-damaging VIV event and an alarm is not raised. False positive is the situation when an alarm is raised for damaging VIV when the event was actually not so damaging.\u0000 On the other hand, the baseline \"constant\" classifier of conservatively chosen limits (from the same data) for upper and lower flex joint angles results in very low precision and F1 scores, implying too many false positives. While the baseline classifier does not predict any false negatives, it is very expensive because of too many false positives. Furthermore, it carries the risk of being ignored by users due to too many false alarms.\u0000 This work demonstrates that machine learning techniques can accurately predict damaging VIV events in the field using minimal number of sensors. Such accurate predictions were not possible using traditional methods.","PeriodicalId":11149,"journal":{"name":"Day 1 Mon, May 06, 2019","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81150105","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}

{"title":"Turret-Moored FPSO Yaw Motions in a Squall-Prone Region","authors":"M. Naciri, Murthy Chitrapu","doi":"10.4043/29234-MS","DOIUrl":"https://doi.org/10.4043/29234-MS","url":null,"abstract":"\u0000 The design of mooring systems in West of Africa is often dominated by squall events. These are episodes of rapidly increasing wind speeds accompanied with sudden and significant wind direction changes. The response of weathervaning systems (offloading tankers moored to an export system or turret moored FPSO’s) to such transient and violent environments is very complex and the subject of an on-going joint industry project. One important parameter in numerical simulations of weathervaning units to squall events is the yaw motion damping model. There is quite a large body of references and insights in yaw damping under steady environmental conditions but hardly any when it comes to responses in squall owing to the transient nature of the event and to its complexity.\u0000 Field measurements of the yaw motions of a turret moored unit offshore Angola with concurrent on-board wind measurements are presented. Both quantities are sampled at 1-minute intervals. Time series of aft and fore drafts are also available on a daily basis. These measurements span one decade. A systematic scan of the wind speed time series has been performed to identify, based on the World Meteorological Organization definition, all squall events passing through the asset. The main particulars of the turret-moored FPSO are described along with its station-keeping system and the associated horizontal slow drift motion response time scales.\u0000 Systematic analysis of measured yaw motions and velocities has been performed seeking correlations with the hull loading condition at the time of the squall event, its heading prior to the squall and the squall maximum speed and direction range. The main objective of these analyses is to provide factual information that can be used to firm up the yaw damping models used for mooring analyses in squall-prone areas.","PeriodicalId":11149,"journal":{"name":"Day 1 Mon, May 06, 2019","volume":"65 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74069586","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}

{"title":"Libra@35 - Bringing the Project Break Even to US$ 35/bbl","authors":"Osmond Coelho Junior, Ana Luiza Silva Costa, Luísa Gontijo Bisinoto, Mariane Duarte Guimarães","doi":"10.4043/29336-MS","DOIUrl":"https://doi.org/10.4043/29336-MS","url":null,"abstract":"\u0000 Having a resilient break-even price is essential for deep-water development projects due to all the technical uncertainties inherent to the O&G business and, because of the oil price volatility, especially in recent times. To cope with this permanent threat, the Libra Consortium envisaged, structured and implemented a consortium corporate program called Libra@35. The programs’ main objective is to reduce the projects break-even prices to US$ 35/bbl, by improving the recovery factor and /or reducing costs. This paper describes the Libra@35 methodology and procedures, explaining how the program has helped Libra optimize its projects on a continuous basis through a structured and rigorous methodology. Additionally, it presents the beneficial results and impacts achieved to date. To finalize, the paper discloses the Consortium's future objectives for this successful Program and how it is structured to assist in shaping Libra's projects of tomorrow.","PeriodicalId":11149,"journal":{"name":"Day 1 Mon, May 06, 2019","volume":"28 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82576691","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}

{"title":"Water Injection Well Performance and Fracture Propagation in a Channel Sand Reservoir: An Offshore Ghana Case Study","authors":"Jongsoo Hwang, Prateek Bhardwaj, M. Sharma, S. Sathyamoorthy, K. Amaning, A. Singh","doi":"10.4043/29311-MS","DOIUrl":"https://doi.org/10.4043/29311-MS","url":null,"abstract":"\u0000 This study explains the large injectivity changes observed in the field, how to remedy it, and how to ensure fracture containment in channel sand reservoirs. The case study field is located offshore Ghana and is a channel sand reservoir. Water injection was initiated for pressure maintenance and waterflooding under fracturing conditions. The injection wells are designed to ensure high and sustainable injection rates while maintaining the integrity of the cap rock.\u0000 The injection bottom-hole pressure (BHP) was history-matched to investigate the impact of stress profiles, reservoir shapes, injection water quality, poroelastic and thermally induced stress changes. The injectivity decline was found to be a result of changes in stresses caused by the channel boundaries and, to a lesser extent, near-wellbore formation damage. The rapid increase in pore pressure and the resulting decrease in injectivity is unique to these kinds of channel sands. Once the origin of the decreasing injectivity was identified, remedial actions were recommended and predictions for future injectivity were made ensuring containment of fractures.","PeriodicalId":11149,"journal":{"name":"Day 1 Mon, May 06, 2019","volume":"54 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80136955","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}

{"title":"Accurate Frequency Division Inversion Based on Seismic-Well Fusion in Seismic Data Superposition Area","authors":"Wenbo Gao, Mingchun Wang, Wenxiong Chen, Xin Zhou, Y. Mao","doi":"10.4043/29382-MS","DOIUrl":"https://doi.org/10.4043/29382-MS","url":null,"abstract":"\u0000 Recently, the western part of Bohai has obtained significant commercial oil discoveries in Guantao group for the first time. The old seismic data is wide, but the bandwidth is narrow. The new data bandwidth is large, but the coverage is small. Besides, the impedance difference of sand and mudstone is small. The traditional impedance inversion can't distinguish them effectively. It's very important for the next evaluation to get seismic data that can reflect reservoir effectively.\u0000 We propose to use geophysical technology to fuse high-frequency and low frequency information of new data into old data. First, the reflection coefficient of the drilling bypass is extracted. Second combined it's high frequency information with the low frequency information of the reflection coefficient which is calculated by the drilled wells. After that, the fusion coefficient is used as the sample information to invert the frequency attributes of the old data. Finally, the high frequency, the low frequency information of frequency inversion and the intermediate frequency information of the old data are fused to obtain the broadband inversion data.\u0000 In the new and old seismic data superposition area, the frequency band characteristics of the comparison inversion data and the new data are found to be quite similar. Frequency band features are also very similar. It shows that the inversion data are true and reliable. Comparison between drilled wells and the inversion data, compared to the old seismic data, the inversion data of the Guantao formation reservoir thickness is more than 8m can be effectively reflected, and the old seismic data have seismic response when the reservoir thickness is more than 15m, and the response of some reservoirs is not obvious. The seismic resolution of the inversion data is improved effectively. To sum up, the frequency division attribute inversion based on seismic well fusion can effectively improve the bandwidth of the difference data in the rear area of seismic data, and improve the resolution of seismic data.","PeriodicalId":11149,"journal":{"name":"Day 1 Mon, May 06, 2019","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78005370","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}

{"title":"Extracting Value from Data Using an Industrial Data Platform to Provide a Foundational Digital Twin","authors":"F. Laborie, Ole Christian Røed, Geir Engdahl, Audrey Camp","doi":"10.4043/29576-MS","DOIUrl":"https://doi.org/10.4043/29576-MS","url":null,"abstract":"\u0000 Oil & Gas data currently exists within a world of data silos. Lack of data is not the challenge. A wide variety of data is collected, including sensor values, P&IDs, ERP, and depth-based trajectories. Rather, the challenge pertains to data usefulness. The root of the problem is a combination of factors, including poor data infrastructure, incompatible operational data systems, and restricted data access. All this translates to a low maturity of digitalization across the Oil & Gas industry. To date, digitalization efforts have been limited to pilot projects, proofs of concept and case studies, with no large-scale operationalized projects.\u0000 Aker BP, one of Europe's largest independent Oil & Gas companies, has broken through the typical roadblocks by deploying an industrial data platform across all five of its operational assets. The platform aggregates and processes data from sensors and contextualizes it, structuring it in relation to process diagrams, production information, 3D-models, and event data (maintenance, incidents). Everything linked in the real world is also linked in the platform. This has dramatically reduced the cost of integration and maintenance, while simultaneously enabling scalability, speed of development, and data openness throughout the Aker BP organization. The data platform handles live and historical data for close to 200,000 sensors, with a peak transfer of 800,000 data points per second. Internal and external experts are able to apply state-of-the-art algorithms to visualize and solve critical business problems. A range of third-party applications and data scientists also use the 1+ trillion data points in the platform to create value and support Aker BP's strategy for day-to-day operations and long-term digital transformation.\u0000 To realize the promise of digitalization, unlocking the value of data must be made a priority within the Oil & Gas industry. This paper will describe the implementation of the industrial data platform, explaining how data streamed from many, disparate, underlying systems is contextualized in the data platform to provide a holistic view of all processes and operations, thus creating a foundational digital twin for each asset, ready to empower machine learning applications for optimization and automatization, as well as human-facing applications, such as advanced visualizations and apps for the digital field worker.","PeriodicalId":11149,"journal":{"name":"Day 1 Mon, May 06, 2019","volume":"42 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75121078","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}

{"title":"Structural Reinforcement and Leak Sealing with Composite Materials","authors":"George Di Cesar Silva, Thomas Fink, Pedro Almeida Bordieri, Mauro Missao Watanabe, M. J. Oliveira","doi":"10.4043/29571-MS","DOIUrl":"https://doi.org/10.4043/29571-MS","url":null,"abstract":"\u0000 \u0000 \u0000 This document presents the application steps of the repair and structural reinforcement system with high-performance polymer and composite material. Without the need to shut-down the offshore platform, this technology is based on ASME and ISO international standards with high safety and applicable in classified areas where hot-work permit is not obtainable.\u0000 \u0000 \u0000 \u0000 The methods and procedures are applied and carried out exclusively for each application, after a judicious risk assessment. Recently, a 14\" super duplex pipe carrying seawater line, operating at 8 bar pressure, on an oil platform located in Ghana showed active leak. In order to carry a conventional repair, (replacement of the problematic section or conventional hot welding) the shut-down of production would be necessary. Furthermore, the conventional method was not applicable due to the potentially explosive atmospheric conditions. Based on Part 4 of the ASME PCC-2 standard, the repair system was engineered to a 10-year lifespan and carried out with absolute safety. The procedure consists of a surface preparation, leak containment and structural reinforcement on the defective area of the pipe. All the steps in the aforementioned procedure were cold-work type and without the need to shut-down, therefore without loss of production. The equations used to calculate the thickness and length of the repair system with composite material, as well as the risk assessment, were in accordance to the referenced standards.\u0000 \u0000 \u0000 \u0000 The repair system was applied with success without the need to shut-down the production and was considered permanent by ABS. The hardness of the composite, measured after 24 hours, indicates full cure of the repair as predicted by the procedure and quality standards. Therefore, the leak was 100% sealed and the area was structurally reinforced in line with the engineering plan and without any loss of production.\u0000 \u0000 \u0000 \u0000 The integrity of aging offshore assets is a common global problem due to the constraint of concurrent activities in a production environment. This methodology using composite materials in association with asset integrity management without shutdown production has gained recognition to be a long-term solution. The implementation of the repair and structural reinforcement system with high-performance polymer and composite material provides cost reduction, significant health, safety and environmental advantages as it enables immediate attention for the defect, on top of the benefit to avoid the loss of production.\u0000","PeriodicalId":11149,"journal":{"name":"Day 1 Mon, May 06, 2019","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77920046","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}

{"title":"Advancing the Industry Practice in Offshore Wind Load Estimation - An Overview of On-Going SNAME OC-8 Activities","authors":"David P. Hodapp, A. Voogt, Wei Ma, B. Cheater, J. Brekke","doi":"10.4043/29646-MS","DOIUrl":"https://doi.org/10.4043/29646-MS","url":null,"abstract":"\u0000 In early 2014, the Society of Naval Architects and Marine Engineers (SNAME) OC-8 Panel was formed to address regulatory acceptance of wind tunnel testing for stability calculations of offshore floating production systems governed by the U.S. Code of Federal Regulations (CFR). Initially, this focused on updating the 1988 SNAME T&R Bulletin 5-4 \"Guidelines for Wind Tunnel Testing\" which has served as a de facto industry standard for nearly 25 years. The update was intended to leverage new technologies and lessons learned to improve the accuracy and repeatability of the results. As time progressed, the focus of the Panel broadened to encompass the empirical ‘building block’ method of wind load estimation (i.e., the basis of the CFR stability calculations) and computational fluid dynamics (CFD).\u0000 The need to step back and objectively assess the relative accuracy and repeatability of these estimation methods was recognized in 2016. In response, SNAME OC-8 organized a ‘first-of-its-kind’ comparative wind load study to benchmark the relative accuracy and repeatability of available wind load estimation methods (i.e., empirical ‘building block’ methods, wind tunnel testing, and CFD) for a representative semi-submersible hull. The study resulted in two important outcomes: 1) U.S. regulatory authorities participated in the workshop and expressed support for acceptance of wind tunnel test results pending the publication of a new industry guideline which could assure accuracy/ repeatability, and 2) key stakeholders from operators, engineering companies, classification societies, and regulatory bodies expressed support for the development of a new industry design guideline to broadly address wind load estimation (including the use of CFD) through the engineering design spiral.\u0000 The present paper summarizes the contributions of the SNAME OC-8 Panel since its inception. High- level findings/ take-aways from the 2017 comparative wind load study are discussed, and unanswered questions of importance are highlighted. The SNAME OC-8 Panel plans to deliver two new industry guidelines to improve the accuracy and repeatability of empirical ‘building block’, wind tunnel, and CFD wind load estimates; the on-going efforts of the Panel and its constituent subcommittees are further outlined in the latter portion of the paper.","PeriodicalId":11149,"journal":{"name":"Day 1 Mon, May 06, 2019","volume":"1979 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90275369","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}