H. Shebl, Mohamed Ali Al Tamimi, D. Boyd, H. Nehaid
Simulation Engineers and Geomodelers rely on reservoir rock geological descriptions to help identify baffles, barriers and pathways to fluid flow critical to accurate reservoir performance predictions. Part of the reservoir modelling process involves Petrographers laboriously describing rock thin sections to interpret the depositional environment and diagenetic processes controlling rock quality, which along with pressure differences, controls fluid movement and influences ultimate oil recovery. Supervised Machine Learning and a rock fabric labelled data set was used to train a neural net to recognize Modified Durham classification reservoir rock thin section images and their individual components (fossils and pore types) plus predict rock quality. The image recognition program's accuracy was tested on an unseen thin section image database.
{"title":"Automation of Carbonate Rock Thin Section Description Using Cognitive Image Recognition","authors":"H. Shebl, Mohamed Ali Al Tamimi, D. Boyd, H. Nehaid","doi":"10.2118/208149-ms","DOIUrl":"https://doi.org/10.2118/208149-ms","url":null,"abstract":"\u0000 Simulation Engineers and Geomodelers rely on reservoir rock geological descriptions to help identify baffles, barriers and pathways to fluid flow critical to accurate reservoir performance predictions. Part of the reservoir modelling process involves Petrographers laboriously describing rock thin sections to interpret the depositional environment and diagenetic processes controlling rock quality, which along with pressure differences, controls fluid movement and influences ultimate oil recovery. Supervised Machine Learning and a rock fabric labelled data set was used to train a neural net to recognize Modified Durham classification reservoir rock thin section images and their individual components (fossils and pore types) plus predict rock quality. The image recognition program's accuracy was tested on an unseen thin section image database.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81522718","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 degree of fluid compartmentalization has direct implications on the development costs of oil and gas reservoirs, since it may negatively impact gas water contacts (GWC) and fluid condensate gas ratios (CGR). In this case study on the Barik Formation in the giant Khazzan gas field in Block 61 in Oman we demonstrate how integrating independent approaches for assessing potential reservoir compartmentalization can be used to assess compartmentalization risk. The three disciplines that were integrated are structural geology (fault seal analysis, movement and stress stages of faults and fractures, traps geometry over geological time), petroleum systems (fluid chemistry and pressure, charge history) and sedimentology-stratigraphy including diagenesis (sedimentological and diagenetic controls on vertical and lateral facies and reservoir quality variation). Dynamic data from production tests were also analyzed and integrated with the observations above. Based on this work, Combined Common Risk Segment (CCRS) maps with a most likely and alternative scenarios for reservoir compartmentalization were constructed. While pressure data carry significant uncertainty due to the tight nature of the deeply buried rocks, it is clear pressures in gas-bearing sections fall onto a single pressure gradient across Block 61, while water pressures indicate variable GWCs. Overall, the GWCs appear to shallow across the field towards the NW, while water pressure appears to increase in that direction. The "apparent" gas communication with separate aquifers is difficult to explain conventionally. A range of scenarios for fluid distribution and reservoir connectivity are discussed. Fault seal compartmentalization and different trap spill points were found to be the most likely mechanism explaining fluid distribution and likely reservoir compartmentalization. Perched water may be another factor explaining variable GWCs. Hydrodynamic tilting due to the flow of formation water was deemed an unlikely scenario, and the risk of reservoir compartmentalization due to sedimentological and diagenetic flow barriers was deemed to be low.
{"title":"De-Risking Fluid Compartmentalization of the Barik Reservoir in the Khazzan Field, Oman - An Integrated Approach","authors":"A. Al Anboori, S. Dee, Khalil Al Rashdi, H. Volk","doi":"10.2118/207687-ms","DOIUrl":"https://doi.org/10.2118/207687-ms","url":null,"abstract":"\u0000 The degree of fluid compartmentalization has direct implications on the development costs of oil and gas reservoirs, since it may negatively impact gas water contacts (GWC) and fluid condensate gas ratios (CGR). In this case study on the Barik Formation in the giant Khazzan gas field in Block 61 in Oman we demonstrate how integrating independent approaches for assessing potential reservoir compartmentalization can be used to assess compartmentalization risk. The three disciplines that were integrated are structural geology (fault seal analysis, movement and stress stages of faults and fractures, traps geometry over geological time), petroleum systems (fluid chemistry and pressure, charge history) and sedimentology-stratigraphy including diagenesis (sedimentological and diagenetic controls on vertical and lateral facies and reservoir quality variation). Dynamic data from production tests were also analyzed and integrated with the observations above.\u0000 Based on this work, Combined Common Risk Segment (CCRS) maps with a most likely and alternative scenarios for reservoir compartmentalization were constructed. While pressure data carry significant uncertainty due to the tight nature of the deeply buried rocks, it is clear pressures in gas-bearing sections fall onto a single pressure gradient across Block 61, while water pressures indicate variable GWCs. Overall, the GWCs appear to shallow across the field towards the NW, while water pressure appears to increase in that direction. The \"apparent\" gas communication with separate aquifers is difficult to explain conventionally. A range of scenarios for fluid distribution and reservoir connectivity are discussed.\u0000 Fault seal compartmentalization and different trap spill points were found to be the most likely mechanism explaining fluid distribution and likely reservoir compartmentalization. Perched water may be another factor explaining variable GWCs. Hydrodynamic tilting due to the flow of formation water was deemed an unlikely scenario, and the risk of reservoir compartmentalization due to sedimentological and diagenetic flow barriers was deemed to be low.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82371866","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}
We at ADNOC Logistics & Services have identified the need for a Fully Integrated Inspection and Monitoring Solution to meet our operational, safety and security objectives. It also helped us in our journey toward becoming a world-class integrated logistics services provider. We have a mandate to manage complex logistics operations while being flexible in services delivery by adopting the latest technology and leveraging strategic partnerships. ADNOC L&S adopted autonomous drone technology from Percepto in most of its critical operations. The artificial Intelligence in the drones automatically detects abnormal changes in working environment as well as unsafe acts and conditions and helps employees be more aware of them especially during routine activities. Finally, it helps management take immediate action to address unsafe conditions as soon as they occur. Visual inspections play a big role today in asset management. In fact, they're considered a best practice for ensuring safer and more productive operations. Being able to conduct visual inspections routinely leads to early detection of issues and damages that might become failures. In this way, visual inspections ultimately help minimize incidents. Yet visual inspections are not limited to preventing and minimizing incidents, but organizations also get value from real time monitoring of procedures such as planned shutdowns of specific assets such as a flare stack inspection. During construction, having the ability to monitor work that is being conducted in real time helps minimize the overall downtime. This can translate into saving hundreds of thousands and even millions of dollars. Inspections are vital and even crucial for business continuity. Yet, today visual inspection is far from being optimized. The end to end process is not at all efficient. And surprisingly, most companies and most sites still conduct visual inspections manually, not automatically. This type of inspection is labor intensive, takes a lot of time, and can even put employees at risk. Overall, manual inspection is an inefficient process. Consider the siloed workflows that comprise the overall inspection. You start with having to fetch the data and collect it. This involves sending people to the site with special equipment. It can also involve climbing up high structures or putting people into potentially dangerous positions. All of this is manual time-consuming work. When this is done, the data needs to be somehow transferred to people who are going to be analyzing it. They need to have a particular type of expertise and experience in managing visual data. Once they go over the data, they need to create or define some insights and share their findings with the relevant stakeholders. Yet again, this is a labor intensive and lengthy process. It's also costly. Fortunately, it does not have to work this way, as there is lots of room for automation. Each of the siloed workflows from autonomous capture visual data manage
{"title":"Eyes on Air","authors":"Sulaiman Saif Shehhi, Mohamed Ahmed Al Maflahi","doi":"10.2118/207455-ms","DOIUrl":"https://doi.org/10.2118/207455-ms","url":null,"abstract":"\u0000 We at ADNOC Logistics & Services have identified the need for a Fully Integrated Inspection and Monitoring Solution to meet our operational, safety and security objectives. It also helped us in our journey toward becoming a world-class integrated logistics services provider. We have a mandate to manage complex logistics operations while being flexible in services delivery by adopting the latest technology and leveraging strategic partnerships.\u0000 ADNOC L&S adopted autonomous drone technology from Percepto in most of its critical operations. The artificial Intelligence in the drones automatically detects abnormal changes in working environment as well as unsafe acts and conditions and helps employees be more aware of them especially during routine activities. Finally, it helps management take immediate action to address unsafe conditions as soon as they occur.\u0000 Visual inspections play a big role today in asset management. In fact, they're considered a best practice for ensuring safer and more productive operations. Being able to conduct visual inspections routinely leads to early detection of issues and damages that might become failures. In this way, visual inspections ultimately help minimize incidents. Yet visual inspections are not limited to preventing and minimizing incidents, but organizations also get value from real time monitoring of procedures such as planned shutdowns of specific assets such as a flare stack inspection.\u0000 During construction, having the ability to monitor work that is being conducted in real time helps minimize the overall downtime. This can translate into saving hundreds of thousands and even millions of dollars.\u0000 Inspections are vital and even crucial for business continuity. Yet, today visual inspection is far from being optimized. The end to end process is not at all efficient. And surprisingly, most companies and most sites still conduct visual inspections manually, not automatically. This type of inspection is labor intensive, takes a lot of time, and can even put employees at risk. Overall, manual inspection is an inefficient process.\u0000 Consider the siloed workflows that comprise the overall inspection. You start with having to fetch the data and collect it. This involves sending people to the site with special equipment. It can also involve climbing up high structures or putting people into potentially dangerous positions. All of this is manual time-consuming work. When this is done, the data needs to be somehow transferred to people who are going to be analyzing it. They need to have a particular type of expertise and experience in managing visual data. Once they go over the data, they need to create or define some insights and share their findings with the relevant stakeholders. Yet again, this is a labor intensive and lengthy process. It's also costly. Fortunately, it does not have to work this way, as there is lots of room for automation. Each of the siloed workflows from autonomous capture visual data manage","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89528370","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}
Capitalization of lessons learned on Asset Integrity Management during Front End Loading phases of a green field Project Development, by defining plan for implementation of a diagnostic digital tool for reducing downtime and introduce predictive maintenance during Operation. Eni developed a platform of Digital applications for enhanced Operations management by implementing an Integrated Asset Management (IAM) system. Advanced Analytics tool is part of it and is designed for monitoring, foreseeing and preventing production upsets and anomalies; the tool is set up by verification of areas of interest and criticalities, with identification of main equipment data sets and by the implementation and validation of predictive models. Starting from historical data, data scientists supported by experts develop algorithms capable of finding interdependencies between a set of input variables and an output variable (phenomenon to be predicted/monitored), thus detecting anomalies and criticalities. Main areas of benefit are envisaged on Production continuity, capable of predicting problems on static and rotating equipment and giving information on the most impacting variables on the incipient problems. The tool will support technicians to help them preventing failures and out-of-specs events which may cause loss of production or asset integrity issues, with the activation of predictive maintenance and the aim to strive a continuous monitoring and improvement of plant operational performances. An Energy Efficiency predictive model will also be set up, capable of forecasting the future energy performances of the asset through the prediction of the Stationary Combustion of Carbon Dioxide (CO2) emission index (t CO2/kbbl) and providing the list of the main influencing equipment and variables. The plan for implementation of the tool from the Early phases of development help the organization on prioritizing the implementation of Digital tools as part of the execution and realization of the Asset to be delivered to the Operational personnel, by easing the transition and avoiding subsequent retrofitting carrying brownfield works and additional costs. The implementation of Advanced Analytics tool has been embedded in a new green field initiative of a Development Project since Front End Loading phases, thus fostering digital implementation and minimizing deployment costs by including those as part of the Investment Proposal presented to Joint Venture Partners and Authorities.
{"title":"Asset Integrity Management - Implementation Plan During Front End Loading Phases","authors":"G. Ferrario, Salvatore Grimaldi","doi":"10.2118/207756-ms","DOIUrl":"https://doi.org/10.2118/207756-ms","url":null,"abstract":"\u0000 Capitalization of lessons learned on Asset Integrity Management during Front End Loading phases of a green field Project Development, by defining plan for implementation of a diagnostic digital tool for reducing downtime and introduce predictive maintenance during Operation.\u0000 Eni developed a platform of Digital applications for enhanced Operations management by implementing an Integrated Asset Management (IAM) system. Advanced Analytics tool is part of it and is designed for monitoring, foreseeing and preventing production upsets and anomalies; the tool is set up by verification of areas of interest and criticalities, with identification of main equipment data sets and by the implementation and validation of predictive models. Starting from historical data, data scientists supported by experts develop algorithms capable of finding interdependencies between a set of input variables and an output variable (phenomenon to be predicted/monitored), thus detecting anomalies and criticalities.\u0000 Main areas of benefit are envisaged on Production continuity, capable of predicting problems on static and rotating equipment and giving information on the most impacting variables on the incipient problems. The tool will support technicians to help them preventing failures and out-of-specs events which may cause loss of production or asset integrity issues, with the activation of predictive maintenance and the aim to strive a continuous monitoring and improvement of plant operational performances. An Energy Efficiency predictive model will also be set up, capable of forecasting the future energy performances of the asset through the prediction of the Stationary Combustion of Carbon Dioxide (CO2) emission index (t CO2/kbbl) and providing the list of the main influencing equipment and variables. The plan for implementation of the tool from the Early phases of development help the organization on prioritizing the implementation of Digital tools as part of the execution and realization of the Asset to be delivered to the Operational personnel, by easing the transition and avoiding subsequent retrofitting carrying brownfield works and additional costs.\u0000 The implementation of Advanced Analytics tool has been embedded in a new green field initiative of a Development Project since Front End Loading phases, thus fostering digital implementation and minimizing deployment costs by including those as part of the Investment Proposal presented to Joint Venture Partners and Authorities.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89208158","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}
H. Saradva, Siddharth Jain, Christna Golaco, A. Guillen, K. Thakur
Sharjah National Oil Corporation (SNOC) operates 4 onshore fields the largest of which has been in production since the 1980's. The majority of wells in the biggest field have a complex network of multilaterals drilled using an underbalanced coiled tubing technique for production enhancement in early 2000s. The scope of this project was to maximize the productivity from these wells in the late life by modelling the dynamic flow behaviour in a simulator and putting that theory to the test by recompleting the wells. A comprehensive multilateral wellbore flow study was undertaken using dynamic multiphase flow simulator to predict the expected improvement in well deliverability of these mature wells, each having 4-6 laterals (Saradva et al. 2019). The well laterals have openhole fishbone completions with one parent lateral having subsequent numerous sub-laterals reaching further into the reservoir with each lateral between 500-2000ft drilled to maximize the intersection with fractures. Complexity in simulation further increased due to complex geology, compositional simulation, condensate banking and liquid loading with the reservoir pressure less than 10% of original. The theory that increasing wellbore diameter by removing the tubing reduces frictional pressure loss was put to test on 2 pilot wells in the 2020-21 workover campaign. The results obtained from the simulator and the actual production increment in the well aligned within 10% accuracy. A production gain of 20-30% was observed on both the wells and results are part of a dynamic simulation predicting well performance over their remaining life. Given the uncertainties in the current PVT, lateral contribution and the fluid production ratios, a broad range sensitivity was performed to ensure a wide range of applicability of the study. This instils confidence in the multiphase transient simulator for subsurface modelling and the workflow will now be used to expand the applicability to other well candidates on a field level. This will result in the opportunity to maximize the production and net revenues from these gas wells by reducing the impact of liquid loading. This paper discusses the detailed comparison of the actual well behaviour with the simulation outcomes which are counterproductive to the conventional gas well development theory of utilizing velocity strings to reduce liquid loading. Two key outcomes from the project are observed, the first is that liquid loading in multilaterals is successfully modelled in a dynamic multiphase transient simulator instead of a typical nodal analysis package, all validated from a field pilot. The second is the alternative to the conventional theory of using smaller tubing sizes to alleviate gas wells liquid loading, that high velocity achieved through wellhead compression would allow higher productivity than a velocity string in low pressure late life gas condensate wells.
沙迦国家石油公司(SNOC)经营着4个陆上油田，其中最大的油田自20世纪80年代以来一直在生产。在21世纪初，为了提高产量，该油田的大多数井都采用了欠平衡连续油管技术，采用了复杂的多边井网。该项目的范围是通过在模拟器中模拟动态流动行为，并通过重新完井对该理论进行测试，从而最大限度地提高这些井在后期的产能。使用动态多相流模拟器进行了全面的多边井筒流动研究，以预测这些成熟井的产能预期改善，每口井有4-6个分支(Saradva et al. 2019)。分支井采用鱼骨裸眼完井，其中一条母分支井随后有许多延伸至储层的子分支井，每个分支井的钻深在500-2000ft之间，以最大限度地扩大裂缝相交。由于复杂的地质条件、成分模拟、凝析油堆积以及储层压力低于原储层10%的液体加载等因素，进一步增加了模拟的复杂性。在2020-21年的修井活动中，通过移除油管来增加井筒直径以减少摩擦压力损失的理论在两口试验井中进行了测试。仿真结果与井中实际产量增量的拟合精度在10%以内。这两口井的产量增加了20-30%，这是动态模拟的一部分，预测了井的剩余寿命。考虑到当前PVT、横向贡献和产液比的不确定性，为了确保研究的广泛适用性，研究人员进行了广泛的灵敏度测试。这为地下建模的多相瞬态模拟器注入了信心，该工作流程现在将用于扩大在油田层面上的其他候选井的适用性。这将通过减少液体载荷的影响，使这些气井的产量和净收入最大化。本文讨论了实际井眼动态与模拟结果的详细对比，这与利用速度串降低液载的常规气井开发理论相悖。该项目取得了两个重要成果，首先是在动态多相瞬态模拟器中成功模拟了多边井中的液体载荷，而不是典型的节点分析包，所有这些都经过了现场试验验证。第二种是使用更小的油管尺寸来减轻气井液体负荷的传统理论的替代方案，通过井口压缩获得的高速度将比低压晚期凝析气井中的速度管柱具有更高的产能。
{"title":"Mature Field Revitalization: Extending Late Life of Mature Gas Condensate Wells by Modelling Complex Multilateral Wellbore Flow Dynamics and Validating Results With a Field Pilot","authors":"H. Saradva, Siddharth Jain, Christna Golaco, A. Guillen, K. Thakur","doi":"10.2118/207501-ms","DOIUrl":"https://doi.org/10.2118/207501-ms","url":null,"abstract":"\u0000 Sharjah National Oil Corporation (SNOC) operates 4 onshore fields the largest of which has been in production since the 1980's. The majority of wells in the biggest field have a complex network of multilaterals drilled using an underbalanced coiled tubing technique for production enhancement in early 2000s. The scope of this project was to maximize the productivity from these wells in the late life by modelling the dynamic flow behaviour in a simulator and putting that theory to the test by recompleting the wells.\u0000 A comprehensive multilateral wellbore flow study was undertaken using dynamic multiphase flow simulator to predict the expected improvement in well deliverability of these mature wells, each having 4-6 laterals (Saradva et al. 2019). The well laterals have openhole fishbone completions with one parent lateral having subsequent numerous sub-laterals reaching further into the reservoir with each lateral between 500-2000ft drilled to maximize the intersection with fractures. Complexity in simulation further increased due to complex geology, compositional simulation, condensate banking and liquid loading with the reservoir pressure less than 10% of original.\u0000 The theory that increasing wellbore diameter by removing the tubing reduces frictional pressure loss was put to test on 2 pilot wells in the 2020-21 workover campaign. The results obtained from the simulator and the actual production increment in the well aligned within 10% accuracy. A production gain of 20-30% was observed on both the wells and results are part of a dynamic simulation predicting well performance over their remaining life. Given the uncertainties in the current PVT, lateral contribution and the fluid production ratios, a broad range sensitivity was performed to ensure a wide range of applicability of the study.\u0000 This instils confidence in the multiphase transient simulator for subsurface modelling and the workflow will now be used to expand the applicability to other well candidates on a field level. This will result in the opportunity to maximize the production and net revenues from these gas wells by reducing the impact of liquid loading. This paper discusses the detailed comparison of the actual well behaviour with the simulation outcomes which are counterproductive to the conventional gas well development theory of utilizing velocity strings to reduce liquid loading.\u0000 Two key outcomes from the project are observed, the first is that liquid loading in multilaterals is successfully modelled in a dynamic multiphase transient simulator instead of a typical nodal analysis package, all validated from a field pilot. The second is the alternative to the conventional theory of using smaller tubing sizes to alleviate gas wells liquid loading, that high velocity achieved through wellhead compression would allow higher productivity than a velocity string in low pressure late life gas condensate wells.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88636944","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}
H. Denli, HassanJaved Chughtai, Brian Hughes, Robert Gistri, Peng Xu
Deep learning has recently been providing step-change capabilities, particularly using transformer models, for natural language processing applications such as question answering, query-based summarization, and language translation for general-purpose context. We have developed a geoscience-specific language processing solution using such models to enable geoscientists to perform rapid, fully-quantitative and automated analysis of large corpuses of data and gain insights. One of the key transformer-based model is BERT (Bidirectional Encoder Representations from Transformers). It is trained with a large amount of general-purpose text (e.g., Common Crawl). Use of such a model for geoscience applications can face a number of challenges. One is due to the insignificant presence of geoscience-specific vocabulary in general-purpose context (e.g. daily language) and the other one is due to the geoscience jargon (domain-specific meaning of words). For example, salt is more likely to be associated with table salt within a daily language but it is used as a subsurface entity within geosciences. To elevate such challenges, we retrained a pre-trained BERT model with our 20M internal geoscientific records. We will refer the retrained model as GeoBERT. We fine-tuned the GeoBERT model for a number of tasks including geoscience question answering and query-based summarization. BERT models are very large in size. For example, BERT-Large has 340M trained parameters. Geoscience language processing with these models, including GeoBERT, could result in a substantial latency when all database is processed at every call of the model. To address this challenge, we developed a retriever-reader engine consisting of an embedding-based similarity search as a context retrieval step, which helps the solution to narrow the context for a given query before processing the context with GeoBERT. We built a solution integrating context-retrieval and GeoBERT models. Benchmarks show that it is effective to help geologists to identify answers and context for given questions. The prototype will also produce a summary to different granularity for a given set of documents. We have also demonstrated that domain-specific GeoBERT outperforms general-purpose BERT for geoscience applications.
{"title":"Geoscience Language Processing for Exploration","authors":"H. Denli, HassanJaved Chughtai, Brian Hughes, Robert Gistri, Peng Xu","doi":"10.2118/207766-ms","DOIUrl":"https://doi.org/10.2118/207766-ms","url":null,"abstract":"\u0000 Deep learning has recently been providing step-change capabilities, particularly using transformer models, for natural language processing applications such as question answering, query-based summarization, and language translation for general-purpose context. We have developed a geoscience-specific language processing solution using such models to enable geoscientists to perform rapid, fully-quantitative and automated analysis of large corpuses of data and gain insights.\u0000 One of the key transformer-based model is BERT (Bidirectional Encoder Representations from Transformers). It is trained with a large amount of general-purpose text (e.g., Common Crawl). Use of such a model for geoscience applications can face a number of challenges. One is due to the insignificant presence of geoscience-specific vocabulary in general-purpose context (e.g. daily language) and the other one is due to the geoscience jargon (domain-specific meaning of words). For example, salt is more likely to be associated with table salt within a daily language but it is used as a subsurface entity within geosciences.\u0000 To elevate such challenges, we retrained a pre-trained BERT model with our 20M internal geoscientific records. We will refer the retrained model as GeoBERT. We fine-tuned the GeoBERT model for a number of tasks including geoscience question answering and query-based summarization.\u0000 BERT models are very large in size. For example, BERT-Large has 340M trained parameters. Geoscience language processing with these models, including GeoBERT, could result in a substantial latency when all database is processed at every call of the model. To address this challenge, we developed a retriever-reader engine consisting of an embedding-based similarity search as a context retrieval step, which helps the solution to narrow the context for a given query before processing the context with GeoBERT.\u0000 We built a solution integrating context-retrieval and GeoBERT models. Benchmarks show that it is effective to help geologists to identify answers and context for given questions. The prototype will also produce a summary to different granularity for a given set of documents. We have also demonstrated that domain-specific GeoBERT outperforms general-purpose BERT for geoscience applications.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77237528","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}
A. Alsaeedi, M. Elabrashy, M. Alzeyoudi, M. Albadi, Sandeep Soni, Jose Isambertt, Deepak Tripathi, Ankit Shah
Integrated asset modeling, application of big data, and automation are among the top emerging trends in the oil and gas industry. The value associated with such implementation projects is very closely linked with the efficient use of the project management approach and a robust strategy to handle the technological challenges. This paper puts light on such initiatives implemented in a giant gas field. In this giant gas condensate field, a vast amount of data is generated and monitored on a daily basis. The frequent need to deliver the dynamic production target was driving this project implementation so that a value-driven system can be established while achieving the business KPIs. A phased approach was used to target multiple requirements into business deliverables where the early offline phases provided a robust base for full online integration. This project followed the agile approach focusing on getting insights from multiple stakeholders and domain experts and developing a lesson-learnt repository in all the project phases. The online integration solution is a critical differentiator in the workforce and process efficiency improvement. The multiple technical solution workflows helped in reducing manual efforts and streamlining the methodology in a standardized fashion. In addition, the standard project management practices, such as initializing the phases in a planned manner, followed by an interactive execution, monitoring, and controlling stages, ensured delivering project outcomes in an efficient way. This implementation also established a robust collaborative team effort to identify various different roles and responsibilities for stakeholders. This helped in the end phase when the project sustainability was essential. A strong team base maintained and updated the integrated system while delivering daily well and facility surveillance objectives and KPIs from users ranging from planning, engineering, operation, and management team. A special focus on IT team involvement throughout the project phase led to a successful data integration and diagnostic, as the core of the solution was a data-driven analytical framework integrated with multiple corporate and real-time data sources. In addition, this solution was equipped with various one-of-its-kind solution features such as business intelligence, advanced surveillance, dynamic-reservoir integration, manage-by-exception workflows, intelligence alerts, along with a strong digital framework and data architecture. The unique hybrid and agile project management approach focusing on delivering emerging trends and technologies to end-users in the most efficient way paved the way for achieving asset digitalization and standardization goals.
{"title":"Big Data IAOM Project Management and Workflow Automation in a Giant Gas Field Digitization Drive","authors":"A. Alsaeedi, M. Elabrashy, M. Alzeyoudi, M. Albadi, Sandeep Soni, Jose Isambertt, Deepak Tripathi, Ankit Shah","doi":"10.2118/207737-ms","DOIUrl":"https://doi.org/10.2118/207737-ms","url":null,"abstract":"\u0000 Integrated asset modeling, application of big data, and automation are among the top emerging trends in the oil and gas industry. The value associated with such implementation projects is very closely linked with the efficient use of the project management approach and a robust strategy to handle the technological challenges. This paper puts light on such initiatives implemented in a giant gas field.\u0000 In this giant gas condensate field, a vast amount of data is generated and monitored on a daily basis. The frequent need to deliver the dynamic production target was driving this project implementation so that a value-driven system can be established while achieving the business KPIs. A phased approach was used to target multiple requirements into business deliverables where the early offline phases provided a robust base for full online integration. This project followed the agile approach focusing on getting insights from multiple stakeholders and domain experts and developing a lesson-learnt repository in all the project phases.\u0000 The online integration solution is a critical differentiator in the workforce and process efficiency improvement. The multiple technical solution workflows helped in reducing manual efforts and streamlining the methodology in a standardized fashion. In addition, the standard project management practices, such as initializing the phases in a planned manner, followed by an interactive execution, monitoring, and controlling stages, ensured delivering project outcomes in an efficient way. This implementation also established a robust collaborative team effort to identify various different roles and responsibilities for stakeholders. This helped in the end phase when the project sustainability was essential. A strong team base maintained and updated the integrated system while delivering daily well and facility surveillance objectives and KPIs from users ranging from planning, engineering, operation, and management team. A special focus on IT team involvement throughout the project phase led to a successful data integration and diagnostic, as the core of the solution was a data-driven analytical framework integrated with multiple corporate and real-time data sources. In addition, this solution was equipped with various one-of-its-kind solution features such as business intelligence, advanced surveillance, dynamic-reservoir integration, manage-by-exception workflows, intelligence alerts, along with a strong digital framework and data architecture.\u0000 The unique hybrid and agile project management approach focusing on delivering emerging trends and technologies to end-users in the most efficient way paved the way for achieving asset digitalization and standardization goals.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90909787","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 proposes a minimum structure for drilling two appraisal wells. Conductors will be driven into seabed by a crane vessel or drilling-rig crane through a pre-installed lightweight guide-frame placed on seabed. After driving the conductors to required depth, the frame is raised and joined to the conductors at appropriate elevation by bolted and grouted connections. Six tie members connected between the frame and seabed by specially-designed small mat foundations will ensure stability of the structure against environmental loads. A small deck will be installed on the top of conductors to provide space for essential equipment required for prolonged well testing after departure of drilling rig. The platform will be accessed by small boats through a boat landing and ladder. In case of positive drilling outcome, a riser and flexible pipeline will be added to connect with the nearest subsea tie-in point. A detailed structural design of the minimum facility is performed to withstand omnidirectional environmental loads due to 10.0m high wave along with associated wind and current loads. Susceptibility of the structure against dynamic effect of wave loads is also investigated. Demonstration of structural adequacy against wave-induced fatigue loads and reserve strength against extreme environmental loads show the robustness of the minimum structure to perform against design environmental loads.
{"title":"Minimum Structure for Well Appraisal in Marginal Fields at 35m Water Depth without Jacket & Mudline Suspension System","authors":"P. Chatterjee","doi":"10.2118/207262-ms","DOIUrl":"https://doi.org/10.2118/207262-ms","url":null,"abstract":"\u0000 This paper proposes a minimum structure for drilling two appraisal wells. Conductors will be driven into seabed by a crane vessel or drilling-rig crane through a pre-installed lightweight guide-frame placed on seabed. After driving the conductors to required depth, the frame is raised and joined to the conductors at appropriate elevation by bolted and grouted connections. Six tie members connected between the frame and seabed by specially-designed small mat foundations will ensure stability of the structure against environmental loads. A small deck will be installed on the top of conductors to provide space for essential equipment required for prolonged well testing after departure of drilling rig. The platform will be accessed by small boats through a boat landing and ladder. In case of positive drilling outcome, a riser and flexible pipeline will be added to connect with the nearest subsea tie-in point. A detailed structural design of the minimum facility is performed to withstand omnidirectional environmental loads due to 10.0m high wave along with associated wind and current loads. Susceptibility of the structure against dynamic effect of wave loads is also investigated. Demonstration of structural adequacy against wave-induced fatigue loads and reserve strength against extreme environmental loads show the robustness of the minimum structure to perform against design environmental loads.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73551626","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}
Major Overhauls (MOH) of major Rotating Equipment is an essential activity to ensure equipment and overall plant's productivity and reliability requirements are met. This submission summarizes Maintenance cost reduction and MOH extension benefits on an integrally geared centrifugal Instrument Air (IA) compressor through a first of its kind Predictive Maintenance (PdM) solution project in ADNOC. Appropriate planning for Major Overhauls (MOH) in accordance with OEM, company standards and international best practices are crucial steps. Digitalization continues to transform the industry, with enhancements to maintenance practices a fundamental aspect. Centralized Predictive Analytics & Diagnostics (CPAD) project is a first of its kind in ADNOC as it ventures into on one of the largest predictive maintenance projects in the oil & gas industry. CPAD enables Predictive Maintenance (PdM) through Advanced Pattern Recognition (APR) and Machine Learning (ML) technologies to effectively monitor & assess equipment performance and overall healthiness. Equipment performance is continuously assessed through the developed asset management predictive analytics tool. Through this tool, models associated with the equipment were evaluated to detect performance deviation from historical normal operating behavior. Any deviation from the historical norm would be flagged to indicate condition degradation and/or performance drop. Moreover, the software is configured to alert for subtle changes in the system behavior that are often an early warning sign of failure. This allows for early troubleshooting, planning and appropriate intervention by maintenance teams. Using the predictive analytics software solution, an MOH interval extension was implemented for an integrally geared centrifugal IA compressor installed at an ADNOC Gas Processing site. The compressor was due for MOH at its traditional fixed maintenance interval of 40,000 running hours in Nov 2019. Through this approach, the actual performance and condition of the compressor was assessed. Its process and equipment parameters (i.e. casing vibrations, bearing vibrations, bearing temperatures and lube oil supply temperature/pressure, etc.) were reviewed, which did not flag any abnormality. The compressor's performance had not deviated from the historical norm; indicating that the equipment was in a healthy condition and had no signs of performance degradation. With this insight, a 15 months extension of the MOH was achieved. Furthermore, a 30% maintenance cost reduction throughout the compressor's life cycle is projected while ensuring equipment's reliability and integrity are upheld. A total of 7 days maintenance down time including work force and materials planning for the MOH activities was deferred. The equipment remained in operation until its rescheduled date for MOH. Through the deployment of predictive analytics solutions, informed decisions can be made by maintenance professionals to challenge traditiona
{"title":"Predictive Asset Analytics: The Future of Maintenance","authors":"Hagar Rabia","doi":"10.2118/207616-ms","DOIUrl":"https://doi.org/10.2118/207616-ms","url":null,"abstract":"\u0000 Major Overhauls (MOH) of major Rotating Equipment is an essential activity to ensure equipment and overall plant's productivity and reliability requirements are met. This submission summarizes Maintenance cost reduction and MOH extension benefits on an integrally geared centrifugal Instrument Air (IA) compressor through a first of its kind Predictive Maintenance (PdM) solution project in ADNOC.\u0000 Appropriate planning for Major Overhauls (MOH) in accordance with OEM, company standards and international best practices are crucial steps. Digitalization continues to transform the industry, with enhancements to maintenance practices a fundamental aspect. Centralized Predictive Analytics & Diagnostics (CPAD) project is a first of its kind in ADNOC as it ventures into on one of the largest predictive maintenance projects in the oil & gas industry. CPAD enables Predictive Maintenance (PdM) through Advanced Pattern Recognition (APR) and Machine Learning (ML) technologies to effectively monitor & assess equipment performance and overall healthiness. Equipment performance is continuously assessed through the developed asset management predictive analytics tool. Through this tool, models associated with the equipment were evaluated to detect performance deviation from historical normal operating behavior. Any deviation from the historical norm would be flagged to indicate condition degradation and/or performance drop. Moreover, the software is configured to alert for subtle changes in the system behavior that are often an early warning sign of failure. This allows for early troubleshooting, planning and appropriate intervention by maintenance teams.\u0000 Using the predictive analytics software solution, an MOH interval extension was implemented for an integrally geared centrifugal IA compressor installed at an ADNOC Gas Processing site. The compressor was due for MOH at its traditional fixed maintenance interval of 40,000 running hours in Nov 2019. Through this approach, the actual performance and condition of the compressor was assessed. Its process and equipment parameters (i.e. casing vibrations, bearing vibrations, bearing temperatures and lube oil supply temperature/pressure, etc.) were reviewed, which did not flag any abnormality. The compressor's performance had not deviated from the historical norm; indicating that the equipment was in a healthy condition and had no signs of performance degradation. With this insight, a 15 months extension of the MOH was achieved. Furthermore, a 30% maintenance cost reduction throughout the compressor's life cycle is projected while ensuring equipment's reliability and integrity are upheld. A total of 7 days maintenance down time including work force and materials planning for the MOH activities was deferred. The equipment remained in operation until its rescheduled date for MOH.\u0000 Through the deployment of predictive analytics solutions, informed decisions can be made by maintenance professionals to challenge traditiona","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88711677","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}
Analysis of 15 years results of remote occupational health care in oil and gas production industries. Continuous observation, statistical analysis of morbidity, mortality, and treatment results in industrial personnel at different endpoints depending on the variability of care models. Cost-efficacy analysis of several occupational health interventions. Targeted polls of Customers. Dynamics of new Customers. The best practices which provide the maximum efficacy include risk assessment and risk management, action planning for emergencies, telemedicine, education, registry maintenance. Each of all these gave a 10-100-fold rise in Customer satisfaction, seriously improved medical statistics. Telemedicine implies both: the delivery of highly specialized diagnostic technologies directly to the industrial production site, where a GP or paramedic is present, and it implements the direct replacement of medics with gadgets at the patient's bedside. Education involves hands-on training for both industrial personnel at remote sites and for medical professionals who provide care. The 2020-21 COVID19 pandemic was a great real stress test for remote health models when systemic integrated management procedures played a pivotal role in ensuring smooth industry operation due to the high quality of back medical services. Modern efficient models of medical care for remote industries are necessarily comprehensive, modular, adaptive, and rely on personnel health registers. Remote health practices gain a 5-15% rise in price every year, but it pays off in greater labor productivity and in improving the health of industry personnel.
{"title":"Offshore Health Innovations","authors":"K. Logunov, S. Antipov, A. Karpov","doi":"10.2118/207945-ms","DOIUrl":"https://doi.org/10.2118/207945-ms","url":null,"abstract":"\u0000 \u0000 \u0000 Analysis of 15 years results of remote occupational health care in oil and gas production industries.\u0000 \u0000 \u0000 \u0000 Continuous observation, statistical analysis of morbidity, mortality, and treatment results in industrial personnel at different endpoints depending on the variability of care models. Cost-efficacy analysis of several occupational health interventions. Targeted polls of Customers. Dynamics of new Customers.\u0000 \u0000 \u0000 \u0000 The best practices which provide the maximum efficacy include risk assessment and risk management, action planning for emergencies, telemedicine, education, registry maintenance. Each of all these gave a 10-100-fold rise in Customer satisfaction, seriously improved medical statistics. Telemedicine implies both: the delivery of highly specialized diagnostic technologies directly to the industrial production site, where a GP or paramedic is present, and it implements the direct replacement of medics with gadgets at the patient's bedside. Education involves hands-on training for both industrial personnel at remote sites and for medical professionals who provide care. The 2020-21 COVID19 pandemic was a great real stress test for remote health models when systemic integrated management procedures played a pivotal role in ensuring smooth industry operation due to the high quality of back medical services.\u0000 \u0000 \u0000 \u0000 Modern efficient models of medical care for remote industries are necessarily comprehensive, modular, adaptive, and rely on personnel health registers. Remote health practices gain a 5-15% rise in price every year, but it pays off in greater labor productivity and in improving the health of industry personnel.\u0000","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89683251","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：