The control room acts as a central nervous system facility. This is where important decisions, using complex systems, are made every day. The actions of control room operators have a direct impact on uptime, production yields, quality, and industrial plant safety. In addition, long working hours per shift result in fatigue, irregularity of circadian rhythms and sleep cycles, and decreased cognitive performance at the end of day and night shifts. Fatigue causes decreased alertness, attention span, poor memory, and concentration and affect other mental factors. ADNOC Gas Processing established Fatigue Risk Management Taskforce (FRMT) to adapt practices to the specific conditions and create a safer working environment, leading to happier and healthier employees and an overall community. In industries that run continuous and heavy-duty plants such as Oil, gas, and petrochemical, shift work ensures production flow. After the outbreak of Covid-19, business needs to adapt quickly so that their activities can run. The finding suggests that the workers' cognitive performance is reduced, shown by the increase of triggered alarm by the average of 14.39% higher than before the outbreak of Covid-19. However, with the ability to adapt and implement control and monitoring measures, the number of alarm rate gradually decreased. The study framework was proven to be a valuable tool that decision-makers can use, especially to measure the performance of control room workers and their psychological fatigue affected by the Covid-19 pandemic.
{"title":"Resilience Control Room Operator During Pandemic Covid-19","authors":"Salem All Dhanhani, Ivan Novendri","doi":"10.2118/207235-ms","DOIUrl":"https://doi.org/10.2118/207235-ms","url":null,"abstract":"\u0000 The control room acts as a central nervous system facility. This is where important decisions, using complex systems, are made every day. The actions of control room operators have a direct impact on uptime, production yields, quality, and industrial plant safety. In addition, long working hours per shift result in fatigue, irregularity of circadian rhythms and sleep cycles, and decreased cognitive performance at the end of day and night shifts. Fatigue causes decreased alertness, attention span, poor memory, and concentration and affect other mental factors.\u0000 ADNOC Gas Processing established Fatigue Risk Management Taskforce (FRMT) to adapt practices to the specific conditions and create a safer working environment, leading to happier and healthier employees and an overall community. In industries that run continuous and heavy-duty plants such as Oil, gas, and petrochemical, shift work ensures production flow. After the outbreak of Covid-19, business needs to adapt quickly so that their activities can run. The finding suggests that the workers' cognitive performance is reduced, shown by the increase of triggered alarm by the average of 14.39% higher than before the outbreak of Covid-19. However, with the ability to adapt and implement control and monitoring measures, the number of alarm rate gradually decreased. The study framework was proven to be a valuable tool that decision-makers can use, especially to measure the performance of control room workers and their psychological fatigue affected by the Covid-19 pandemic.","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":"81668773","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}
After two years of development, the GAIA Explorer is now ready to assist Geoscientists at Total! This knowledge platform works like a little Google, but with a focus solely on Geosciences - for the time being. The main goal of the GAIA Explorer is to save time finding the right information. Therefore, it is particularly useful for datarooms or after business acquisitions to quickly digest the knowledge, but also for feeding databases, exploration syntheses, reservoir studies, or even staff onboarding specially when remote working. With this additional time, Geoscientists can focus on tasks with added value, such as to synthesize, find analogies or propose alternative scenarios. This new companion automatically organizes and extracts knowledge from a large number of unstructured technical documents by using Machine Learning (ML). All the models relie on Google Cloud Platform (GCP) and have been trained on our own datasets, which cover main petroleum domains such as geosciences and operations. First, the layout of more than 75,000 document pages were analyzed for training a segmentation model, which extracts three types of content (text, images and tables). Secondly, the text content extracted from about 6,500 documents labelled amongst 30 classes was used to train a model for document classification. Thirdly, more than 55,000 images were categorized amongst 45 classes to customize a model of image classification covering a large panel of figures such as maps, logs, seismic sections, or core pictures. Finally, all the terms (n-grams) extracted from objects are compared with an inhouse thesaurus to automatically tag related topics such as basin, field, geological formation, acquisition, measure. All these elementary bricks are connected and used for feeding a knowledge database that can be quickly and exhaustively searched. Today, the GAIA Explorer searches within texts, images and tables from a corpus (document collection), which can be made up of both technical and operational reports, meeting presentations and academic publications. By combining queries (keywords or natural language) with a large array of filters (by classes and topics), the outcomes are easily refined and exploitable. Since the release of a production version in February 2021 at Total, about 180 users for 30 projects regularly use the tool for exploration and development purposes. This first version is following a continuous training cycle including active learning and, preliminary user feedback is good and admits that some information would have been difficult to locate without the GAIA Explorer. In the future, the GAIA Explorer could be significantly improved by implementing knowledge graph based on an ontology dedicated specific to petroleum domains. Along with the help of Specialists in related activities such as drilling, project or contract, the tool could cover the complete range of upstream topics and be useful for other business with time.
{"title":"The Gaia Explorer, a Powerful Search Platform","authors":"Xavier Du Bernard, Jonathan Gallon, J. Massot","doi":"10.2118/207837-ms","DOIUrl":"https://doi.org/10.2118/207837-ms","url":null,"abstract":"\u0000 After two years of development, the GAIA Explorer is now ready to assist Geoscientists at Total! This knowledge platform works like a little Google, but with a focus solely on Geosciences - for the time being. The main goal of the GAIA Explorer is to save time finding the right information. Therefore, it is particularly useful for datarooms or after business acquisitions to quickly digest the knowledge, but also for feeding databases, exploration syntheses, reservoir studies, or even staff onboarding specially when remote working. With this additional time, Geoscientists can focus on tasks with added value, such as to synthesize, find analogies or propose alternative scenarios.\u0000 This new companion automatically organizes and extracts knowledge from a large number of unstructured technical documents by using Machine Learning (ML). All the models relie on Google Cloud Platform (GCP) and have been trained on our own datasets, which cover main petroleum domains such as geosciences and operations. First, the layout of more than 75,000 document pages were analyzed for training a segmentation model, which extracts three types of content (text, images and tables). Secondly, the text content extracted from about 6,500 documents labelled amongst 30 classes was used to train a model for document classification. Thirdly, more than 55,000 images were categorized amongst 45 classes to customize a model of image classification covering a large panel of figures such as maps, logs, seismic sections, or core pictures. Finally, all the terms (n-grams) extracted from objects are compared with an inhouse thesaurus to automatically tag related topics such as basin, field, geological formation, acquisition, measure. All these elementary bricks are connected and used for feeding a knowledge database that can be quickly and exhaustively searched.\u0000 Today, the GAIA Explorer searches within texts, images and tables from a corpus (document collection), which can be made up of both technical and operational reports, meeting presentations and academic publications. By combining queries (keywords or natural language) with a large array of filters (by classes and topics), the outcomes are easily refined and exploitable. Since the release of a production version in February 2021 at Total, about 180 users for 30 projects regularly use the tool for exploration and development purposes. This first version is following a continuous training cycle including active learning and, preliminary user feedback is good and admits that some information would have been difficult to locate without the GAIA Explorer.\u0000 In the future, the GAIA Explorer could be significantly improved by implementing knowledge graph based on an ontology dedicated specific to petroleum domains. Along with the help of Specialists in related activities such as drilling, project or contract, the tool could cover the complete range of upstream topics and be useful for other business with time.","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":"82626866","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}
Jueyong Feng, Hongtao Liu, Kun Huang, Ju Liu, Maotang Yao, Shiyong Qin, Jiangyu Liu, Bohong Wu
The buried depth of gas reservoir B is more than 6700m, the thickness of reservoir is about 180m, the porosity of reservoir matrix is mainly 5.0% - 7.0%, with an average of 6.3%, and the permeability of reservoir matrix is mainly 0.01-0.1mD, The average production capacity of the three wells is 0.08mD, the formation pressure is 116-126MPa, the formation temperature is 124-131°C, the wax content of the condensate oil is high, and the average wax content is 16.9%. In the early stage, the natural productivity of the three wells was low, and the daily gas production was 120000-180000 cubic meters after stimulation. During the production process, the wellhead temperature was 20°C-25°C, the wax freezing temperature was 35°C, and the wellbore wax plugging was serious, The wellbore was blocked, the gas well was forced to shut down, and the reserves of 100 billion cubic meters were unable to be used, so it was necessary to explore new wax control technology. Through investigation, a new type of solid particle paraffin inhibitor is introduced, which can enter the artificial fracture with proppant during fracturing. When the condensate gas passes through the fracture, it washes the solid paraffin inhibitor which enters with proppant, and becomes the condensate gas containing paraffin control components.Therefore,it is not easy to form wax after entering the wellbore, which makes the problem of wellbore paraffin formation change from "passive control" to "active control". Referring to the relevant experimental standards, the conductivity, crushing test, solid paraffin inhibitor and fracturing fluid compatibility test were carried out. The existing test standards of wax freezing point are all for waxy oil under normal pressure, but not for condensate gas. A set of innovative experimental method is designed to successfully test the wax freezing point of condensate gas containing wax control components, and obtain the wax control effect under different ratios of wax control agent and proppant, so as to optimize the amount of wax control agent used in the experiment. The results show that the solid paraffin inhibitor has good dispersibility and suspension, and has little influence on the conductivity of sand filled fractures. The paraffin control effect on condensate oil and gas in this block is good. The wax freezing point can be reduced by about 12°C-18°C, and the optimal dosage is proppant 1%-2%. Field test was carried out in B gas reservoir. After fracturing, 5mm nozzle was used for production, tubing pressure was 83.6MPa, wellhead temperature was 28.8°C, daily oil production was 10.72 cubic meters, daily gas production was 217000 cubic meters, wellhead temperature was lower than wax freezing temperature in this area. At present, it has been in production for 6 months, and there is no wax deposit in wellbore. The successful test of solid paraffin inhibitor in the fracturing of Kuqa ultra deep high pressure and high wax content tight condensate gas reser
{"title":"Application of Solid Paraffin Inhibitor in Fracturing of Kuqa Ultra Deep High Pressure and High Wax Content Tight Condensate Gas Reservoir","authors":"Jueyong Feng, Hongtao Liu, Kun Huang, Ju Liu, Maotang Yao, Shiyong Qin, Jiangyu Liu, Bohong Wu","doi":"10.2118/207797-ms","DOIUrl":"https://doi.org/10.2118/207797-ms","url":null,"abstract":"\u0000 The buried depth of gas reservoir B is more than 6700m, the thickness of reservoir is about 180m, the porosity of reservoir matrix is mainly 5.0% - 7.0%, with an average of 6.3%, and the permeability of reservoir matrix is mainly 0.01-0.1mD, The average production capacity of the three wells is 0.08mD, the formation pressure is 116-126MPa, the formation temperature is 124-131°C, the wax content of the condensate oil is high, and the average wax content is 16.9%. In the early stage, the natural productivity of the three wells was low, and the daily gas production was 120000-180000 cubic meters after stimulation. During the production process, the wellhead temperature was 20°C-25°C, the wax freezing temperature was 35°C, and the wellbore wax plugging was serious, The wellbore was blocked, the gas well was forced to shut down, and the reserves of 100 billion cubic meters were unable to be used, so it was necessary to explore new wax control technology.\u0000 Through investigation, a new type of solid particle paraffin inhibitor is introduced, which can enter the artificial fracture with proppant during fracturing. When the condensate gas passes through the fracture, it washes the solid paraffin inhibitor which enters with proppant, and becomes the condensate gas containing paraffin control components.Therefore,it is not easy to form wax after entering the wellbore, which makes the problem of wellbore paraffin formation change from \"passive control\" to \"active control\". Referring to the relevant experimental standards, the conductivity, crushing test, solid paraffin inhibitor and fracturing fluid compatibility test were carried out. The existing test standards of wax freezing point are all for waxy oil under normal pressure, but not for condensate gas. A set of innovative experimental method is designed to successfully test the wax freezing point of condensate gas containing wax control components, and obtain the wax control effect under different ratios of wax control agent and proppant, so as to optimize the amount of wax control agent used in the experiment.\u0000 The results show that the solid paraffin inhibitor has good dispersibility and suspension, and has little influence on the conductivity of sand filled fractures. The paraffin control effect on condensate oil and gas in this block is good. The wax freezing point can be reduced by about 12°C-18°C, and the optimal dosage is proppant 1%-2%. Field test was carried out in B gas reservoir. After fracturing, 5mm nozzle was used for production, tubing pressure was 83.6MPa, wellhead temperature was 28.8°C, daily oil production was 10.72 cubic meters, daily gas production was 217000 cubic meters, wellhead temperature was lower than wax freezing temperature in this area. At present, it has been in production for 6 months, and there is no wax deposit in wellbore.\u0000 The successful test of solid paraffin inhibitor in the fracturing of Kuqa ultra deep high pressure and high wax content tight condensate gas reser","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":"89456671","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}
Nabila Lazreq, A. Alam, Taliwati Ao, A. Negi, W.D. Von Gotten
Tight Oil Unconventional Reservoirs are challenging when it comes to development and enhancement of production. Transverse Multistage Hydraulic fracturing technique is widely used to maximize production from unconventional reservoirs, however it can be quite challenging when it comes down to execution across longer Tight Oil Horizontal laterals. The paper describes in full the various aspect of technical and operational planning in order to successfully execute highest number of Frac Stages in a well in UAE across a lateral length of 5300 ft This paper will describe an Integrated Field development Study that included building of Geomechanical Model for in-situ stress characterization and rock elastic properties for 3D Hydraulic Fracture Modelling. The fully 3D Hydraulic Fracture model assisted in geometrically spacing, finalizing and optimizing the number of Frac Stages across the horizontal Lateral. In order to optimize the design, specialized cores studies were conducted as part of the process such as Steady State measurements of permeability. In this paper the testing part will be describe in full and how the study was incorporated in the state-of-art Frac Simulator to ensure optimized frac design and realistic deliverable. The paper focusses on the operation planning, execution and efficiency. This includes frac stages execution, pump down plug and perf, number of cluster optimization & cluster spacing, milling, cleanout and flowback. Also in order to quantify the contribution from each stage, tracer services was utilized which will be detailed in the paper. Finally the paper will also cover the Well Testing strategy, which is one of the crucial aspect of the well deliverability. API Lab and Composition Analysis of Oil & Gas Samples were also conducted post fracturing as part of the study. The overall planning and execution of this well will become a guide and will be utilized for future well and frac design, which will be discussed in the paper. This integrated approach will be utilized in planning and designing future wells. The post fracturing data and production data collected from the well will help in further Frac Stage optimization which will lead to overall cost optimization
{"title":"Unlocking Tight Oil: Multistage Horizontal Well Fracturing in Unconventional Reservoir, a Successful UAE Case History","authors":"Nabila Lazreq, A. Alam, Taliwati Ao, A. Negi, W.D. Von Gotten","doi":"10.2118/208088-ms","DOIUrl":"https://doi.org/10.2118/208088-ms","url":null,"abstract":"\u0000 Tight Oil Unconventional Reservoirs are challenging when it comes to development and enhancement of production. Transverse Multistage Hydraulic fracturing technique is widely used to maximize production from unconventional reservoirs, however it can be quite challenging when it comes down to execution across longer Tight Oil Horizontal laterals. The paper describes in full the various aspect of technical and operational planning in order to successfully execute highest number of Frac Stages in a well in UAE across a lateral length of 5300 ft\u0000 This paper will describe an Integrated Field development Study that included building of Geomechanical Model for in-situ stress characterization and rock elastic properties for 3D Hydraulic Fracture Modelling. The fully 3D Hydraulic Fracture model assisted in geometrically spacing, finalizing and optimizing the number of Frac Stages across the horizontal Lateral. In order to optimize the design, specialized cores studies were conducted as part of the process such as Steady State measurements of permeability. In this paper the testing part will be describe in full and how the study was incorporated in the state-of-art Frac Simulator to ensure optimized frac design and realistic deliverable.\u0000 The paper focusses on the operation planning, execution and efficiency. This includes frac stages execution, pump down plug and perf, number of cluster optimization & cluster spacing, milling, cleanout and flowback. Also in order to quantify the contribution from each stage, tracer services was utilized which will be detailed in the paper. Finally the paper will also cover the Well Testing strategy, which is one of the crucial aspect of the well deliverability. API Lab and Composition Analysis of Oil & Gas Samples were also conducted post fracturing as part of the study. The overall planning and execution of this well will become a guide and will be utilized for future well and frac design, which will be discussed in the paper.\u0000 This integrated approach will be utilized in planning and designing future wells. The post fracturing data and production data collected from the well will help in further Frac Stage optimization which will lead to overall cost optimization","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":"89887418","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 present an example of improved approaches for how to interact with data and leverage artificial intelligence for the subsurface. Currently, subsurface workflows typically rely on a lot of time-consuming manual input and analysis, but the promise of artificial intelligence is that, once properly trained, an AI can take care of the more routine tasks, leaving the domain expert free to work on more complex and creative parts of the job. Artificial intelligence work on subsurface datasets in recent years has typically taken the form of research and proof of concept type work, with a lot of one-off solutions showing up in the literature using new and innovative ideas (e.g. Hussein et al, 2021; Misra et al, 2019). Oftentimes this work requires a good degree of data science knowledge and programming skills on the part of the scientist, putting many of the approaches outlined in these and a multitude of other papers out of reach for many subsurface experts in the Oil and Gas industry. In order for Artificial Intelligence to become applied as part of regular workflows in the subsurface, the industry needs tools built to help subsurface experts access AI techniques in a more practical, targeted way. We present herein a practical guide to help in developing applied artificial Intelligence tools to roll out within your organization or to the industry more broadly.
在本文中，我们提出了一个改进方法的例子，用于如何与数据交互并在地下利用人工智能。目前，地下工作流程通常依赖于大量耗时的人工输入和分析，但人工智能的前景是，一旦经过适当的训练，人工智能可以处理更多的常规任务，让领域专家自由地从事更复杂和创造性的工作。近年来，地下数据集上的人工智能工作通常采取研究和概念验证型工作的形式，许多一次性解决方案出现在文献中，使用了新的和创新的想法(例如Hussein等人，2021;Misra et al, 2019)。通常情况下，这项工作需要科学家具备良好的数据科学知识和编程技能，这使得这些论文和其他许多论文中概述的许多方法对于石油和天然气行业的许多地下专家来说都是遥不可及的。为了使人工智能成为地下常规工作流程的一部分，该行业需要开发工具来帮助地下专家以更实用、更有针对性的方式访问人工智能技术。我们在此提供了一个实用指南，以帮助开发应用人工智能工具，以便在您的组织或更广泛的行业中推广。
{"title":"Applied Artificial Intelligence in the Subsurface","authors":"M. Dykstra, Ben Lasscock","doi":"10.2118/207242-ms","DOIUrl":"https://doi.org/10.2118/207242-ms","url":null,"abstract":"\u0000 In this paper we present an example of improved approaches for how to interact with data and leverage artificial intelligence for the subsurface. Currently, subsurface workflows typically rely on a lot of time-consuming manual input and analysis, but the promise of artificial intelligence is that, once properly trained, an AI can take care of the more routine tasks, leaving the domain expert free to work on more complex and creative parts of the job.\u0000 Artificial intelligence work on subsurface datasets in recent years has typically taken the form of research and proof of concept type work, with a lot of one-off solutions showing up in the literature using new and innovative ideas (e.g. Hussein et al, 2021; Misra et al, 2019). Oftentimes this work requires a good degree of data science knowledge and programming skills on the part of the scientist, putting many of the approaches outlined in these and a multitude of other papers out of reach for many subsurface experts in the Oil and Gas industry. In order for Artificial Intelligence to become applied as part of regular workflows in the subsurface, the industry needs tools built to help subsurface experts access AI techniques in a more practical, targeted way.\u0000 We present herein a practical guide to help in developing applied artificial Intelligence tools to roll out within your organization or to the industry more broadly.","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":"80846703","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}
Irma Kusumawati, Samuel Edward Bremner, N. McIntosh, Ingrid Rajkovic, Tanja Nylend
The incorporation of a sulfate removal system onto a stimulation vessel has been shown to positively affect vessel utilization, increase efficiency in field development, and reduce freshwater consumption. Stimulation vessels have fixed storage and transportation volumes as well as a fixed total mass that can be loaded. Fresh water occupies the highest proportion of space and mass in most stimulation treatments, which imposes limitations on all other products that can be loaded out. Particularly for acid stimulation treatments, a compromise between the volumes of raw acid and fresh water must be made in order to achieve the best operational efficiency possible. Any method that can reduce, eliminate, or replace fresh water as a component in stimulation fluids will have a significant impact on vessel efficiency. One option is the use of seawater as the base fluid. However, seawater can cause problems for well production due to the high sulfate content in the water leading to the formation of mineral scale. The solution to this problem has been the installation of a sulfate removal system on the stimulation vessel. Driven by membrane nanofiltration, this system can produce up to 100 m3/hr of low sulfate water from seawater for well stimulation operations. By removing the scaling risk from seawater, this system enables the stimulation vessel to maximize the products it loads with the ability to produce low sulfate water as and when it is needed. The sulfate removal system can reduce SO4 content to 4.3 mg/l and reduce other ions present in seawater. With an output of 100 m3/hr and being installed independently from stimulation systems, the unit is able to produce water regardless of ongoing activities. In stimulation jobs, multistage ball drop operations are the most time-critical operations. In the analysis of hundreds of stages stimulated with water from the new nanofiltration system, the average stage completion time was 6 hours, which included ball loading, dropping, and displacement; diagnostic injection testing; and the main treatment. With an average water requirement of 600 m3, the vessel can keep up with water demand and remove water capacity from the utilization equation. The use of a compact nanofiltration system for SO4 removal has improved stimulation vessel operations where scale production is a key concern for operators. In addition to increasing vessel utilization and intervention efficiency, the system will lead to the elimination of approximately 68,000 m3 of fresh water being pumped every year for stimulation operations in the North Sea.
{"title":"Infinite Water: Implementation of Nanofiltration for Optimization of Vessel Stimulation Operations in the Offshore Greater Ekofisk Area, North Sea","authors":"Irma Kusumawati, Samuel Edward Bremner, N. McIntosh, Ingrid Rajkovic, Tanja Nylend","doi":"10.2118/207331-ms","DOIUrl":"https://doi.org/10.2118/207331-ms","url":null,"abstract":"\u0000 The incorporation of a sulfate removal system onto a stimulation vessel has been shown to positively affect vessel utilization, increase efficiency in field development, and reduce freshwater consumption.\u0000 Stimulation vessels have fixed storage and transportation volumes as well as a fixed total mass that can be loaded. Fresh water occupies the highest proportion of space and mass in most stimulation treatments, which imposes limitations on all other products that can be loaded out. Particularly for acid stimulation treatments, a compromise between the volumes of raw acid and fresh water must be made in order to achieve the best operational efficiency possible.\u0000 Any method that can reduce, eliminate, or replace fresh water as a component in stimulation fluids will have a significant impact on vessel efficiency. One option is the use of seawater as the base fluid. However, seawater can cause problems for well production due to the high sulfate content in the water leading to the formation of mineral scale. The solution to this problem has been the installation of a sulfate removal system on the stimulation vessel. Driven by membrane nanofiltration, this system can produce up to 100 m3/hr of low sulfate water from seawater for well stimulation operations. By removing the scaling risk from seawater, this system enables the stimulation vessel to maximize the products it loads with the ability to produce low sulfate water as and when it is needed.\u0000 The sulfate removal system can reduce SO4 content to 4.3 mg/l and reduce other ions present in seawater. With an output of 100 m3/hr and being installed independently from stimulation systems, the unit is able to produce water regardless of ongoing activities. In stimulation jobs, multistage ball drop operations are the most time-critical operations. In the analysis of hundreds of stages stimulated with water from the new nanofiltration system, the average stage completion time was 6 hours, which included ball loading, dropping, and displacement; diagnostic injection testing; and the main treatment. With an average water requirement of 600 m3, the vessel can keep up with water demand and remove water capacity from the utilization equation.\u0000 The use of a compact nanofiltration system for SO4 removal has improved stimulation vessel operations where scale production is a key concern for operators. In addition to increasing vessel utilization and intervention efficiency, the system will lead to the elimination of approximately 68,000 m3 of fresh water being pumped every year for stimulation operations in the North Sea.","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":"75539378","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}
Ameera Al Harrasi, Muna Maskari, G. Urdaneta, A. Al-Jumah, Salim Badi, I. Busaidi, Khalfan Harthy, Osama Abazeed, M. Moradi
Several techniques have been applied to improve fluid conformance of injection wells to increase water flooding performance and eventually field oil recovery. Normal outflow control devices (OCDs) are effective solutions for this problem in reservoirs with static properties, however, they fail in reservoirs with complex/dynamic properties including fractures. There, the continuously increasing contrast in the injectivity of a section with the fractures compared to the rest of the well causes diverting a great portion of the injected fluid into the thief zone thus creating short-circuit to the nearby producer wells. This paper summarizes the integrated technical learnings from the successful application of the installation of the first Autonomous Outflow Control (AOCD) technology in a new long horizontal injector well. It shows the result of extending this technology to other injectors in both water and polymer phases in the field, it details the facts and observations and the insights the multidisciplinary authors have captured. This autonomously reactive control on the injection fluid conformance resulted in an increased sweep and ultimate oil recovery while reducing the total volume of injected fluid.
{"title":"Autonomous Outflow Control Technology AOCD in New Water/Polymer Injectors in Heavy Oil Fields from South Sultanate of Oman","authors":"Ameera Al Harrasi, Muna Maskari, G. Urdaneta, A. Al-Jumah, Salim Badi, I. Busaidi, Khalfan Harthy, Osama Abazeed, M. Moradi","doi":"10.2118/207361-ms","DOIUrl":"https://doi.org/10.2118/207361-ms","url":null,"abstract":"\u0000 Several techniques have been applied to improve fluid conformance of injection wells to increase water flooding performance and eventually field oil recovery. Normal outflow control devices (OCDs) are effective solutions for this problem in reservoirs with static properties, however, they fail in reservoirs with complex/dynamic properties including fractures. There, the continuously increasing contrast in the injectivity of a section with the fractures compared to the rest of the well causes diverting a great portion of the injected fluid into the thief zone thus creating short-circuit to the nearby producer wells.\u0000 This paper summarizes the integrated technical learnings from the successful application of the installation of the first Autonomous Outflow Control (AOCD) technology in a new long horizontal injector well. It shows the result of extending this technology to other injectors in both water and polymer phases in the field, it details the facts and observations and the insights the multidisciplinary authors have captured.\u0000 This autonomously reactive control on the injection fluid conformance resulted in an increased sweep and ultimate oil recovery while reducing the total volume of injected fluid.","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":"77935510","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}
Ola Balbaa, Hesham Mohamed, S. Elkholy, Mohamed ElRashidy, R. Munger, M. Najwani
While drilling highly depleted gas reservoirs with a very narrow drilling window, Common drilling methods like utilizing loss of circulation pills, wellbore strengthening materials and managed pressure drilling (MPD) are being used in several reservoirs, yet it cannot be successful or cost effective if applied in a traditional manner. Innovative approaches to enable drilling wells in highly depleted reservoir in the Mediterranean deep water were adopted. The approaches incorporated design changes to the well and Bottom hole assembly (BHA), optimized drilling practices, and unconventional use of MPD while drilling and cementing production liner. Well design change in comparison to offset wells to allow drilling the reservoir in one hole section. Several design changes were considered in the BHA and drilling fluids to prevent as well as mitigate losses and differential sticking risks. From the BHA viewpoint, one of the key successful prevention measures was maximizing the standoff to reduce the contact area with the formation, this was achieved through utilizing spiral heavy wall drill pipe (HWDP) instead of drill collars in addition to a modeled placement of stabilizers and roller reamers. While on the drilling fluid side, Calcium carbonate material was added to strengthen wellbore, prevent losses and avoid formation damage. Particle size up to 1000 micron and concentration up to 40ppb was used to strengthen the depleted sands dynamically while drilling. Furthermore, as mitigation to stuck pipe, Jar and accelerator placement was simulated to achieve optimum impulse and impact force while maintaining the Jar above potential sticking zone. Whereas to address the consequence of a stuck pipe event, disconnect subs were placed in BHA to allow for recovering the drill string efficiently. MPD was first introduced in the Mediterranean in 2007 and continued to develop this well-known technique to mitigate various drilling challenges. For this well, MPD was one of the key enabling factors to safely drill, run and cement the production liner. Surface back pressure MPD allowed using the lowest possible mud weight in the hole and maintaining downhole pressure constant in order to manage the narrow drilling window between the formation pressure and fracture pressure (less than 0.4 ppg). MPD was also applied for the first time for running and cementing the production liner to prevent losses and achieve good cement quality which is a key to successful well production.
{"title":"New Approaches for Drilling Highly Depleted Reservoir in Deep Water Wells","authors":"Ola Balbaa, Hesham Mohamed, S. Elkholy, Mohamed ElRashidy, R. Munger, M. Najwani","doi":"10.2118/207779-ms","DOIUrl":"https://doi.org/10.2118/207779-ms","url":null,"abstract":"\u0000 While drilling highly depleted gas reservoirs with a very narrow drilling window, Common drilling methods like utilizing loss of circulation pills, wellbore strengthening materials and managed pressure drilling (MPD) are being used in several reservoirs, yet it cannot be successful or cost effective if applied in a traditional manner.\u0000 Innovative approaches to enable drilling wells in highly depleted reservoir in the Mediterranean deep water were adopted. The approaches incorporated design changes to the well and Bottom hole assembly (BHA), optimized drilling practices, and unconventional use of MPD while drilling and cementing production liner.\u0000 Well design change in comparison to offset wells to allow drilling the reservoir in one hole section. Several design changes were considered in the BHA and drilling fluids to prevent as well as mitigate losses and differential sticking risks. From the BHA viewpoint, one of the key successful prevention measures was maximizing the standoff to reduce the contact area with the formation, this was achieved through utilizing spiral heavy wall drill pipe (HWDP) instead of drill collars in addition to a modeled placement of stabilizers and roller reamers. While on the drilling fluid side, Calcium carbonate material was added to strengthen wellbore, prevent losses and avoid formation damage. Particle size up to 1000 micron and concentration up to 40ppb was used to strengthen the depleted sands dynamically while drilling. Furthermore, as mitigation to stuck pipe, Jar and accelerator placement was simulated to achieve optimum impulse and impact force while maintaining the Jar above potential sticking zone. Whereas to address the consequence of a stuck pipe event, disconnect subs were placed in BHA to allow for recovering the drill string efficiently.\u0000 MPD was first introduced in the Mediterranean in 2007 and continued to develop this well-known technique to mitigate various drilling challenges. For this well, MPD was one of the key enabling factors to safely drill, run and cement the production liner.\u0000 Surface back pressure MPD allowed using the lowest possible mud weight in the hole and maintaining downhole pressure constant in order to manage the narrow drilling window between the formation pressure and fracture pressure (less than 0.4 ppg). MPD was also applied for the first time for running and cementing the production liner to prevent losses and achieve good cement quality which is a key to successful well production.","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":"76293258","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 Age of AI is defining a new set of challenges for leaders and the integration of digitalization and analytics into management decision-making is now a strategic priority for the oil industry. The fundamental challenge currently confronting the industry is to find leaders who can lead in the digital age. As the industry grapples with the AI revolution, pressure is mounting on leaders to react swiftly to the disruption that comes in its wake. Leadership and management methodologies currently employed by most organizations will not suffice in the digital age because leadership in this new age requires a different set of skills and organizational alignment. Yet, many organizations continue to struggle to put leaders in place with the knowledge and expertise to take on the challenges of leading in an AI-enabled world. This paper addresses the challenges and responsibilities that the AI revolution presents to oil industry leaders and provides practical insights to confront them. It details the concept of ambidexterity and why it is difficult for oil industry managers to achieve. It also outlines what it takes to implement an ambidextrous strategy in the industry and presents a framework for leaders as they drive transformation and explore strategies that will shape the industry's transition to net-zero energy. With social media now shaping business decision-making, the paper also discusses its impact and presents a unique approach for leadership to be strategically positioned to reconfigure their organizations to ensure they survive and thrive in the social age. Artificial Intelligence in the oil industry is not just about managing operations and reducing operating cost. It is also about developing a completely new way of doing business. Leadership in the digital age will be held accountable to a different standard. They would not only be judged by their ability to drive strategy and deliver financial results; they would also be judged on their ability to leverage AI resources and drive deep analytics mindset across their organization, while dealing with energy transition and social media. The workforce of the future will be dominated by technologically sophisticated people connected to multiple platforms. Managing this workforce will require a new kind of managerial wisdom. The big gains from digital transformation will not be realized unless industry executives rethink the criteria with which leadership and management success is judged. Becoming a transformational digital leader requires the ability to define a strategic vision for transformation, understand the promise and peril of social media, cultivate employees to succeed with AI, and use AI responsibly. The future belongs to leaders with these abilities and capabilities.
{"title":"Leadership and Managerial Decision-Making in an AI-Enabled Oil and Gas Industry","authors":"Armstrong Lee Agbaji","doi":"10.2118/207613-ms","DOIUrl":"https://doi.org/10.2118/207613-ms","url":null,"abstract":"\u0000 The Age of AI is defining a new set of challenges for leaders and the integration of digitalization and analytics into management decision-making is now a strategic priority for the oil industry. The fundamental challenge currently confronting the industry is to find leaders who can lead in the digital age. As the industry grapples with the AI revolution, pressure is mounting on leaders to react swiftly to the disruption that comes in its wake. Leadership and management methodologies currently employed by most organizations will not suffice in the digital age because leadership in this new age requires a different set of skills and organizational alignment. Yet, many organizations continue to struggle to put leaders in place with the knowledge and expertise to take on the challenges of leading in an AI-enabled world.\u0000 This paper addresses the challenges and responsibilities that the AI revolution presents to oil industry leaders and provides practical insights to confront them. It details the concept of ambidexterity and why it is difficult for oil industry managers to achieve. It also outlines what it takes to implement an ambidextrous strategy in the industry and presents a framework for leaders as they drive transformation and explore strategies that will shape the industry's transition to net-zero energy. With social media now shaping business decision-making, the paper also discusses its impact and presents a unique approach for leadership to be strategically positioned to reconfigure their organizations to ensure they survive and thrive in the social age.\u0000 Artificial Intelligence in the oil industry is not just about managing operations and reducing operating cost. It is also about developing a completely new way of doing business. Leadership in the digital age will be held accountable to a different standard. They would not only be judged by their ability to drive strategy and deliver financial results; they would also be judged on their ability to leverage AI resources and drive deep analytics mindset across their organization, while dealing with energy transition and social media. The workforce of the future will be dominated by technologically sophisticated people connected to multiple platforms. Managing this workforce will require a new kind of managerial wisdom.\u0000 The big gains from digital transformation will not be realized unless industry executives rethink the criteria with which leadership and management success is judged. Becoming a transformational digital leader requires the ability to define a strategic vision for transformation, understand the promise and peril of social media, cultivate employees to succeed with AI, and use AI responsibly. The future belongs to leaders with these abilities and capabilities.","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":"73334439","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}
Ahmed S. Rizk, Moussa Tembely, W. Alameri, E. Al-Shalabi
Estimation of petrophysical properties is essential for accurate reservoir predictions. In recent years, extensive work has been dedicated into training different machine-learning (ML) models to predict petrophysical properties of digital rock using dry rock images along with data from single-phase direct simulations, such as lattice Boltzmann method (LBM) and finite volume method (FVM). The objective of this paper is to present a comprehensive literature review on petrophysical properties estimation from dry rock images using different ML workflows and direct simulation methods. The review provides detailed comparison between different ML algorithms that have been used in the literature to estimate porosity, permeability, tortuosity, and effective diffusivity. In this paper, various ML workflows from the literature are screened and compared in terms of the training data set, the testing data set, the extracted features, the algorithms employed as well as their accuracy. A thorough description of the most commonly used algorithms is also provided to better understand the functionality of these algorithms to encode the relationship between the rock images and their respective petrophysical properties. The review of various ML workflows for estimating rock petrophysical properties from dry images shows that models trained using features extracted from the image (physics-informed models) outperformed models trained on the dry images directly. In addition, certain tree-based ML algorithms, such as random forest, gradient boosting, and extreme gradient boosting can produce accurate predictions that are comparable to deep learning algorithms such as deep neural networks (DNNs) and convolutional neural networks (CNNs). To the best of our knowledge, this is the first work dedicated to exploring and comparing between different ML frameworks that have recently been used to accurately and efficiently estimate rock petrophysical properties from images. This work will enable other researchers to have a broad understanding about the topic and help in developing new ML workflows or further modifying exiting ones in order to improve the characterization of rock properties. Also, this comparison represents a guide to understand the performance and applicability of different ML algorithms. Moreover, the review helps the researchers in this area to cope with digital innovations in porous media characterization in this fourth industrial age – oil and gas 4.0.
{"title":"A Critical Literature Review on Rock Petrophysical Properties Estimation from Images Based on Direct Simulation and Machine Learning Techniques","authors":"Ahmed S. Rizk, Moussa Tembely, W. Alameri, E. Al-Shalabi","doi":"10.2118/208125-ms","DOIUrl":"https://doi.org/10.2118/208125-ms","url":null,"abstract":"\u0000 Estimation of petrophysical properties is essential for accurate reservoir predictions. In recent years, extensive work has been dedicated into training different machine-learning (ML) models to predict petrophysical properties of digital rock using dry rock images along with data from single-phase direct simulations, such as lattice Boltzmann method (LBM) and finite volume method (FVM). The objective of this paper is to present a comprehensive literature review on petrophysical properties estimation from dry rock images using different ML workflows and direct simulation methods. The review provides detailed comparison between different ML algorithms that have been used in the literature to estimate porosity, permeability, tortuosity, and effective diffusivity. In this paper, various ML workflows from the literature are screened and compared in terms of the training data set, the testing data set, the extracted features, the algorithms employed as well as their accuracy. A thorough description of the most commonly used algorithms is also provided to better understand the functionality of these algorithms to encode the relationship between the rock images and their respective petrophysical properties.\u0000 The review of various ML workflows for estimating rock petrophysical properties from dry images shows that models trained using features extracted from the image (physics-informed models) outperformed models trained on the dry images directly. In addition, certain tree-based ML algorithms, such as random forest, gradient boosting, and extreme gradient boosting can produce accurate predictions that are comparable to deep learning algorithms such as deep neural networks (DNNs) and convolutional neural networks (CNNs). To the best of our knowledge, this is the first work dedicated to exploring and comparing between different ML frameworks that have recently been used to accurately and efficiently estimate rock petrophysical properties from images. This work will enable other researchers to have a broad understanding about the topic and help in developing new ML workflows or further modifying exiting ones in order to improve the characterization of rock properties. Also, this comparison represents a guide to understand the performance and applicability of different ML algorithms. Moreover, the review helps the researchers in this area to cope with digital innovations in porous media characterization in this fourth industrial age – oil and gas 4.0.","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":"73727147","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：