R. Alfajri, Sakti Parsaulian Siregar, Liston Sitanggang, Andar Parulian Hutasoit
Digital oil field is a terminology that frequently appeared in the last few years. In the era of industry 4.0 and the proliferation of digital technology, oil and gas companies need to adapt in order to gain advantage in business process development, and this term is the answer. In digital oil field, data is significantly valuable. Therefore, robust database and real time data monitoring need to be developed. Pertamina EP has established a robust, easy-to-access, and web-based database application called Operational Data Repository (ODR). This application handles end-to-end business process from exploration all the way to commercial. Several modules were integrated for this application and the main modules consist of exploration, exploitation, production, finance, safety and commercial. For every module in ODR, the first task to carry is to create and input master data. After database is created, calculation according to module's purpose is performed. Once the system is there, automatic data acquisition and monitoring will enter the picture. Exploration module in ODR handles database of Pertamina EP exploration activities. This module include lithology, biostratigraphy, and geochemical data of exploration project in Pertamina EP. This module ensures that initial data of a structure is preserved and available. Exploitation module deals with oil and gas reserves and resources reporting process, well proposal for annual work plan, and surface project monitoring. This module rules development phase from subsurface to surface. Production module shows daily operational activities, production data, and quadrant mapping of wells productivity. Data from this module is taken for evaluating production and operation performance. Finance module handles company's financial report, including revenue, expense, and tax. Safety module handles work permit, hazard identification, risk assessment and control for every project and work plan. Safety is a very important aspect in a company and this module ensures that documents needed to perform work safely is well-documented and easy to submit and access. Last but not least is commercial module. This module consists of gas sales agreement documents (GSA), metering system location, and customer complaints monitoring. ODR has already been well-established, therefore Pertamina EP started its pilot project for automatic data acquisition for eight wells and currently on monitoring phase. This paper describes Pertamina EP first step to digital oil field, which is developing virtual warehouse to store company's data. The step is strengthened with attempting for automatic data acquisition that will be integrated to the ODR for the next phase.
{"title":"Operational Data Repository as the First Step to Digital Oil Field","authors":"R. Alfajri, Sakti Parsaulian Siregar, Liston Sitanggang, Andar Parulian Hutasoit","doi":"10.2118/205718-ms","DOIUrl":"https://doi.org/10.2118/205718-ms","url":null,"abstract":"\u0000 Digital oil field is a terminology that frequently appeared in the last few years. In the era of industry 4.0 and the proliferation of digital technology, oil and gas companies need to adapt in order to gain advantage in business process development, and this term is the answer. In digital oil field, data is significantly valuable. Therefore, robust database and real time data monitoring need to be developed.\u0000 Pertamina EP has established a robust, easy-to-access, and web-based database application called Operational Data Repository (ODR). This application handles end-to-end business process from exploration all the way to commercial. Several modules were integrated for this application and the main modules consist of exploration, exploitation, production, finance, safety and commercial. For every module in ODR, the first task to carry is to create and input master data. After database is created, calculation according to module's purpose is performed. Once the system is there, automatic data acquisition and monitoring will enter the picture.\u0000 Exploration module in ODR handles database of Pertamina EP exploration activities. This module include lithology, biostratigraphy, and geochemical data of exploration project in Pertamina EP. This module ensures that initial data of a structure is preserved and available. Exploitation module deals with oil and gas reserves and resources reporting process, well proposal for annual work plan, and surface project monitoring. This module rules development phase from subsurface to surface. Production module shows daily operational activities, production data, and quadrant mapping of wells productivity. Data from this module is taken for evaluating production and operation performance. Finance module handles company's financial report, including revenue, expense, and tax. Safety module handles work permit, hazard identification, risk assessment and control for every project and work plan. Safety is a very important aspect in a company and this module ensures that documents needed to perform work safely is well-documented and easy to submit and access. Last but not least is commercial module. This module consists of gas sales agreement documents (GSA), metering system location, and customer complaints monitoring. ODR has already been well-established, therefore Pertamina EP started its pilot project for automatic data acquisition for eight wells and currently on monitoring phase.\u0000 This paper describes Pertamina EP first step to digital oil field, which is developing virtual warehouse to store company's data. The step is strengthened with attempting for automatic data acquisition that will be integrated to the ODR for the next phase.","PeriodicalId":10970,"journal":{"name":"Day 1 Tue, October 12, 2021","volume":"100 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80593721","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 Electro-Mechanical Pipe Cutter (MPC) is a non-ballistic & non-chemical wireline deployed alternative cutter tool for parting downhole tubular in the process of well abandonment, pipe recovery and retrieving of packer elements. This case study showcases its application in two wells with different challenges in cutting 4.5" tubing viz., (i) with multiple control lines to facilitate fishing operations and (ii) under compression in a highly deviated trajectory. In Well A, Brunei offshore, the position of the tubing and orientation of the control lines were challenging for ballistic option, along with the possibility of scarring the 9-7/8" casing during the cutting operation. Thus, 3-1/8" OD MPC was used for this job to cut near the coupling, ensuring optimum stand off from casing wall aiming to achieve cutting the control lines in tension. Dual cut were designed to allow the room for a safe cut zone. The primary cut was performed near middle of the joint at ∼1985m, with the tubing in tension. The cut was initiated at a very slow feed (0.2 mm/min) and motor rates (4000rpm), which was gradually increased once the cutting was stable. After the accomplishment of the tubing cut, the parameters were again reduced to carefully cutting through control line. The tubing was successfully retrieved with smooth cut without any over pull indicating it to be completely free. The flawless cutting operation was performed in less than one hour with outmost efficiency. In another highly inclined Well B, Brunei offshore, MPC was chosen over ballistic because it was needed to be conveyed by tractor and ballistic shock has potential to damage it during the operation. Also the advantage of MPC to perform multiple cuts in one run, made it a preferred choice. In this well, multiple cuts were performed to weaken the joint connection of the tubing to allow the rig to pull it free. It was to overcome the adversity posed by high inclination and the pipe under compression. Three cuts were performed at ∼2996 m, each 20 cm apart with an OD of nearly 4.609". After completion of the job, the circulation was performed with surface return, indicating successful execution and the tubing was retrieved on surface showing a clean cut. This case study shows the appropriate planning and execution of the mechanical pipe cutter can provide an efficient, environment friendly and safe alternative to cut tubing and control line in the challenging condition especially when an explosive and chemical cutter options are not considered suitable.
{"title":"Flawless Cutting of Tubing and Control Lines by Mechanical Pipe Cutter in Challenging Well Condition Provides an Environmental Friendly Alternative: A Case Study from Brunei","authors":"Nurul Amali Kadir, Saikat Das, Jittbodee Khunthongkeaw, Jamal Dayem, Ashraf Abdul-Hamid, Shaherol Hassan, Nurdiyana Noridin","doi":"10.2118/205655-ms","DOIUrl":"https://doi.org/10.2118/205655-ms","url":null,"abstract":"\u0000 The Electro-Mechanical Pipe Cutter (MPC) is a non-ballistic & non-chemical wireline deployed alternative cutter tool for parting downhole tubular in the process of well abandonment, pipe recovery and retrieving of packer elements. This case study showcases its application in two wells with different challenges in cutting 4.5\" tubing viz., (i) with multiple control lines to facilitate fishing operations and (ii) under compression in a highly deviated trajectory.\u0000 In Well A, Brunei offshore, the position of the tubing and orientation of the control lines were challenging for ballistic option, along with the possibility of scarring the 9-7/8\" casing during the cutting operation. Thus, 3-1/8\" OD MPC was used for this job to cut near the coupling, ensuring optimum stand off from casing wall aiming to achieve cutting the control lines in tension. Dual cut were designed to allow the room for a safe cut zone. The primary cut was performed near middle of the joint at ∼1985m, with the tubing in tension. The cut was initiated at a very slow feed (0.2 mm/min) and motor rates (4000rpm), which was gradually increased once the cutting was stable. After the accomplishment of the tubing cut, the parameters were again reduced to carefully cutting through control line. The tubing was successfully retrieved with smooth cut without any over pull indicating it to be completely free. The flawless cutting operation was performed in less than one hour with outmost efficiency.\u0000 In another highly inclined Well B, Brunei offshore, MPC was chosen over ballistic because it was needed to be conveyed by tractor and ballistic shock has potential to damage it during the operation. Also the advantage of MPC to perform multiple cuts in one run, made it a preferred choice. In this well, multiple cuts were performed to weaken the joint connection of the tubing to allow the rig to pull it free. It was to overcome the adversity posed by high inclination and the pipe under compression. Three cuts were performed at ∼2996 m, each 20 cm apart with an OD of nearly 4.609\". After completion of the job, the circulation was performed with surface return, indicating successful execution and the tubing was retrieved on surface showing a clean cut.\u0000 This case study shows the appropriate planning and execution of the mechanical pipe cutter can provide an efficient, environment friendly and safe alternative to cut tubing and control line in the challenging condition especially when an explosive and chemical cutter options are not considered suitable.","PeriodicalId":10970,"journal":{"name":"Day 1 Tue, October 12, 2021","volume":"67 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74116428","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}
Well integrity (WI) impairments in oil and gas (O&G) wells are one of the most formidable challenges in the petroleum industry. Managing WI for different groups of well services necessitates precise assessment of risk level. When WI classification and risk assessment are performed using traditional methods such as spreadsheets, failures of well barriers will result in complicated and challenging WI management, especially in mature O&G fields. Industrial practices, then, started moving toward likelihood/ severity matrices which turned out later to be misleading in many cases due to possibility of having skewness in failure data. Developing a reliable model for classifying level of WI impairment is becoming more crucial for the industry. Artificial intelligence (AI) includes advanced algorithms that use machine learning (ML) and computing powers efficiently for predictive analytics. The main objective of this work is to develop ML models for the detection of integrity anomalies and early recognition of well failures. Most common ML algorithms in data science include; random forest, logistic regression, quadratic discriminant analysis, and boosting techniques. This model establishment comes after initial data gathering, pre-processing, and feature engineering. These models can iterate different failure scenarios considering all barrier elements that could contribute to the WI envelope. Thousands of WI data arrays can be literally collected and fed into ML models after being processed and structured properly. The new model presented in this paper can detect different WI anomalies and accurate analysis of failures can be achieved. This emphasizes that managing overall risks of WI failures is a robust and practical approach for direct implementation in mature fields. It also, creates additional enhancement for WI management. This perspective will improve efficiency of operations in addition to having the privilege of universality, where it can be applicable for different well groups. The rising wave of digitalization is anticipated to improve field operations, business performance, and production safety.
{"title":"Application of Machine Learning Algorithms for Managing Well Integrity in Gas Lift Wells","authors":"A. Ragab, M. S. Yakoot, O. Mahmoud","doi":"10.2118/205736-ms","DOIUrl":"https://doi.org/10.2118/205736-ms","url":null,"abstract":"\u0000 Well integrity (WI) impairments in oil and gas (O&G) wells are one of the most formidable challenges in the petroleum industry. Managing WI for different groups of well services necessitates precise assessment of risk level. When WI classification and risk assessment are performed using traditional methods such as spreadsheets, failures of well barriers will result in complicated and challenging WI management, especially in mature O&G fields.\u0000 Industrial practices, then, started moving toward likelihood/ severity matrices which turned out later to be misleading in many cases due to possibility of having skewness in failure data. Developing a reliable model for classifying level of WI impairment is becoming more crucial for the industry. Artificial intelligence (AI) includes advanced algorithms that use machine learning (ML) and computing powers efficiently for predictive analytics.\u0000 The main objective of this work is to develop ML models for the detection of integrity anomalies and early recognition of well failures. Most common ML algorithms in data science include; random forest, logistic regression, quadratic discriminant analysis, and boosting techniques. This model establishment comes after initial data gathering, pre-processing, and feature engineering. These models can iterate different failure scenarios considering all barrier elements that could contribute to the WI envelope. Thousands of WI data arrays can be literally collected and fed into ML models after being processed and structured properly.\u0000 The new model presented in this paper can detect different WI anomalies and accurate analysis of failures can be achieved. This emphasizes that managing overall risks of WI failures is a robust and practical approach for direct implementation in mature fields. It also, creates additional enhancement for WI management. This perspective will improve efficiency of operations in addition to having the privilege of universality, where it can be applicable for different well groups. The rising wave of digitalization is anticipated to improve field operations, business performance, and production safety.","PeriodicalId":10970,"journal":{"name":"Day 1 Tue, October 12, 2021","volume":"2016 21","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91549085","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}
M. Thiyahuddin, A. Rahman, Emily Hazelwood, A. Sparks, M. Benfield, M. H. Mohd, C. Tan, Yusri Yusuf, M. A. A. Rahman
In Malaysia, numerous offshore oil and gas platforms are approaching the end of their operational lifespans and will soon be scheduled for decommissioning. Traditional decommissioning typically involves the complete removal of the platform from the seabed, consequently resulting in the destruction of the established marine life communities present on the structure. A Rigs-to-Reefs strategy provides an alternative to the complete removal of obsolete, non-productive offshore oil and gas platforms, by converting the platform into a permanent artificial reef by utilizing one of the following three methods: partial removal or topple-in-place (in-situ), or tow and place (ex-situ). In-situ reefing provides a means of conserving the marine communities found on the platform by decommissioning the platform jacket in place as an artificial reef. However, not all platforms are good candidates for a Rigs-to-Reef conversion. Thus, pre-decommissioning biological assessments should be undertaken to determine the most appropriate decommissioning strategy on a case-by-case basis. In this study, a biological assessment was developed to catalog the marine life assemblages present on two offshore oil and gas platforms in Malaysia using remotely operated vehicles. Given the limited amount of biological data available on the marine ecosystems found on Malaysia’s platforms, this data may be useful for minimizing adverse impacts of platform removal, while enhancing benefits to the marine environment.
{"title":"Marine Life Assemblage Assessment at Oil & Gas Platform in the South China Sea Offshore Malaysia","authors":"M. Thiyahuddin, A. Rahman, Emily Hazelwood, A. Sparks, M. Benfield, M. H. Mohd, C. Tan, Yusri Yusuf, M. A. A. Rahman","doi":"10.2118/205812-ms","DOIUrl":"https://doi.org/10.2118/205812-ms","url":null,"abstract":"\u0000 In Malaysia, numerous offshore oil and gas platforms are approaching the end of their operational lifespans and will soon be scheduled for decommissioning. Traditional decommissioning typically involves the complete removal of the platform from the seabed, consequently resulting in the destruction of the established marine life communities present on the structure. A Rigs-to-Reefs strategy provides an alternative to the complete removal of obsolete, non-productive offshore oil and gas platforms, by converting the platform into a permanent artificial reef by utilizing one of the following three methods: partial removal or topple-in-place (in-situ), or tow and place (ex-situ). In-situ reefing provides a means of conserving the marine communities found on the platform by decommissioning the platform jacket in place as an artificial reef. However, not all platforms are good candidates for a Rigs-to-Reef conversion. Thus, pre-decommissioning biological assessments should be undertaken to determine the most appropriate decommissioning strategy on a case-by-case basis. In this study, a biological assessment was developed to catalog the marine life assemblages present on two offshore oil and gas platforms in Malaysia using remotely operated vehicles. Given the limited amount of biological data available on the marine ecosystems found on Malaysia’s platforms, this data may be useful for minimizing adverse impacts of platform removal, while enhancing benefits to the marine environment.","PeriodicalId":10970,"journal":{"name":"Day 1 Tue, October 12, 2021","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77608516","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 concept of digital transformation is based on two principles: data driven—exploiting every bit of data source—and user focused. The objective is not only to consolidate data from multiple systems, but to apply an analytics approach to extract insights that are the product of the aggregation of multiple sources then present it to the user (field manager, production and surveillance engineer, region manager, and country) with criteria's of simplicity, specificity, novelty—and most importantly, clarity. The idea is to liberate the data across the whole upstream community and intended for production operations people by providing a one-stop production digital platform that taps into unstructured data and is transformed into structured to be used as input to engineering models and as a result provide data analytics and generate insights. There is three main key objectives: To have only one source of truth using cloud-based technology To incorporate artificial intelligence models to fill the data gaps of production and operations parameters such as pressure and temperature To incorporate multiple solutions for the upstream community that helps during the slow, medium, and fast loops of upstream operations. The new "way of working" helps multiple disciplines such as subsurface team, facilities, and operations, HSSE and business planning, combining business process management and technical workflows to generates insights and create value that impact the profit and losses (P&L) sheet of the operators. The "new ways of working" tackle values pillars such as production optimization, reduced unplanned deferment, cost avoidance, and improved process cycle efficiency. The use of big data and artificial intelligence algorithms are key to understand the production of the wells and fields, as well as anchoring on processing the data with automated engineering models, thus enabling better decision making including the span of time scale such as fast, medium, or slow loop actions.
{"title":"Digital Solutions Suite: Big Data, Artificial Intelligence, and Digital Barrel","authors":"Roberto Fuenmayor","doi":"10.2118/205547-ms","DOIUrl":"https://doi.org/10.2118/205547-ms","url":null,"abstract":"\u0000 The concept of digital transformation is based on two principles: data driven—exploiting every bit of data source—and user focused. The objective is not only to consolidate data from multiple systems, but to apply an analytics approach to extract insights that are the product of the aggregation of multiple sources then present it to the user (field manager, production and surveillance engineer, region manager, and country) with criteria's of simplicity, specificity, novelty—and most importantly, clarity.\u0000 The idea is to liberate the data across the whole upstream community and intended for production operations people by providing a one-stop production digital platform that taps into unstructured data and is transformed into structured to be used as input to engineering models and as a result provide data analytics and generate insights.\u0000 There is three main key objectives:\u0000 To have only one source of truth using cloud-based technology To incorporate artificial intelligence models to fill the data gaps of production and operations parameters such as pressure and temperature To incorporate multiple solutions for the upstream community that helps during the slow, medium, and fast loops of upstream operations.\u0000 The new \"way of working\" helps multiple disciplines such as subsurface team, facilities, and operations, HSSE and business planning, combining business process management and technical workflows to generates insights and create value that impact the profit and losses (P&L) sheet of the operators.\u0000 The \"new ways of working\" tackle values pillars such as production optimization, reduced unplanned deferment, cost avoidance, and improved process cycle efficiency. The use of big data and artificial intelligence algorithms are key to understand the production of the wells and fields, as well as anchoring on processing the data with automated engineering models, thus enabling better decision making including the span of time scale such as fast, medium, or slow loop actions.","PeriodicalId":10970,"journal":{"name":"Day 1 Tue, October 12, 2021","volume":"2014 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73807067","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}
Zein Mirza Joydi, I. Fikri, Dewayani Wuri Sekar, Prasthio Andry
Southern part of Sumatra is known for its high deliverability hydrocarbon gas formation with flow rate up to 200 MMSCFD produced from a single well. The fractured network present mainly in its granite basement formation posed as the primary hydrocarbon contributor aside to the carbonate zone. High formation pressure with massive gas reservoir as its driving mechanism combined with total loss circulation due to geological fault in the same section, lead to operation with various hazard combined which demands potent solution. Advanced technologies required to execute the operation in safest and efficient manner. Downhole Casing Valve (DCV) is one of Managed Pressure Drilling (MPD) equipment used to support operation with deep and high-pressure formation, installed alongside with casing to provide sealing of the well at depth. Equipped with flapper type valve and full borehole size, DCV which is surface controlled, enables operator to seal the well in the absence of any string. The seal created by DCV allows the string to be pulled out preventing to kill a live well. The South Sumatra blocks depicts enormous potential gas reservoir. Located in the fault of basement where total loss circulation will occur in highest probable manner. Utilization of chemical mixed mud was impractical considering the total loss circulation. Thus, pressure exerted from fluid column and pumping flow rate from string needs to be compensated by surface backpressure. In addition, to accommodate deep footage penetration of the section, hard basement formation, complex completion running sequence, and multiple tripping for BHA changes, requirement of DCV shifted from nice-to-have into a must-have segment. Without the need of killing the well nor changing the mud system, DCV allows tripping operation to be completed safely and efficiently by sealing the well with its flapper, saving costs and time on each tripping operation. DCV utilization successfully supports drilling high-pressure gas reservoir through basement fault until target depth reached safely and efficiently.
{"title":"Success Deployment and Operation of Downhole Casing Valve Improves Tripping and MPD Operation While Saving 5 Drilling Days Through Total Loss Circulation in Basement","authors":"Zein Mirza Joydi, I. Fikri, Dewayani Wuri Sekar, Prasthio Andry","doi":"10.2118/205605-ms","DOIUrl":"https://doi.org/10.2118/205605-ms","url":null,"abstract":"\u0000 Southern part of Sumatra is known for its high deliverability hydrocarbon gas formation with flow rate up to 200 MMSCFD produced from a single well. The fractured network present mainly in its granite basement formation posed as the primary hydrocarbon contributor aside to the carbonate zone. High formation pressure with massive gas reservoir as its driving mechanism combined with total loss circulation due to geological fault in the same section, lead to operation with various hazard combined which demands potent solution. Advanced technologies required to execute the operation in safest and efficient manner.\u0000 Downhole Casing Valve (DCV) is one of Managed Pressure Drilling (MPD) equipment used to support operation with deep and high-pressure formation, installed alongside with casing to provide sealing of the well at depth. Equipped with flapper type valve and full borehole size, DCV which is surface controlled, enables operator to seal the well in the absence of any string. The seal created by DCV allows the string to be pulled out preventing to kill a live well.\u0000 The South Sumatra blocks depicts enormous potential gas reservoir. Located in the fault of basement where total loss circulation will occur in highest probable manner. Utilization of chemical mixed mud was impractical considering the total loss circulation. Thus, pressure exerted from fluid column and pumping flow rate from string needs to be compensated by surface backpressure. In addition, to accommodate deep footage penetration of the section, hard basement formation, complex completion running sequence, and multiple tripping for BHA changes, requirement of DCV shifted from nice-to-have into a must-have segment. Without the need of killing the well nor changing the mud system, DCV allows tripping operation to be completed safely and efficiently by sealing the well with its flapper, saving costs and time on each tripping operation. DCV utilization successfully supports drilling high-pressure gas reservoir through basement fault until target depth reached safely and efficiently.","PeriodicalId":10970,"journal":{"name":"Day 1 Tue, October 12, 2021","volume":"43 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74215122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the advancement in machine learning (ML) applications, some recent research has been conducted to optimize fracturing treatments. There are a variety of models available using various objective functions for optimization and different mathematical techniques. There is a need to extend the ML techniques to optimize the choice of algorithm. For fracturing treatment design, the literature for comparative algorithm performance is sparse. The research predominantly shows that compared to the most commonly used regressors and classifiers, some sort of boosting technique consistently outperforms on model testing and prediction accuracy. A database was constructed for a heterogeneous reservoir. Four widely used boosting algorithms were used on the database to predict the design only from the output of a short injection/falloff test. Feature importance analysis was done on eight output parameters from the falloff analysis, and six were finalized for the model construction. The outputs selected for prediction were fracturing fluid efficiency, proppant mass, maximum proppant concentration, and injection rate. Extreme gradient boost (XGBoost), categorical boost (CatBoost), adaptive boost (AdaBoost), and light gradient boosting machine (LGBM) were the algorithms finalized for the comparative study. The sensitivity was done for a different number of classes (four, five, and six) to establish a balance between accuracy and prediction granularity. The results showed that the best algorithm choice was between XGBoost and CatBoost for the predicted parameters under certain model construction conditions. The accuracy for all outputs for the holdout sets varied between 80 and 92%, showing robust significance for a wider utilization of these models. Data science has contributed to various oil and gas industry domains and has tremendous applications in the stimulation domain. The research and review conducted in this paper add a valuable resource for the user to build digital databases and use the appropriate algorithm without much trial and error. Implementing this model reduced the complexity of the proppant fracturing treatment redesign process, enhanced operational efficiency, and reduced fracture damage by eliminating minifrac steps with crosslinked gel.
{"title":"Boosting Algorithm Choice in Predictive Machine Learning Models for Fracturing Applications","authors":"AbdulMuqtadir Khan","doi":"10.2118/205642-ms","DOIUrl":"https://doi.org/10.2118/205642-ms","url":null,"abstract":"\u0000 With the advancement in machine learning (ML) applications, some recent research has been conducted to optimize fracturing treatments. There are a variety of models available using various objective functions for optimization and different mathematical techniques. There is a need to extend the ML techniques to optimize the choice of algorithm.\u0000 For fracturing treatment design, the literature for comparative algorithm performance is sparse. The research predominantly shows that compared to the most commonly used regressors and classifiers, some sort of boosting technique consistently outperforms on model testing and prediction accuracy. A database was constructed for a heterogeneous reservoir. Four widely used boosting algorithms were used on the database to predict the design only from the output of a short injection/falloff test.\u0000 Feature importance analysis was done on eight output parameters from the falloff analysis, and six were finalized for the model construction. The outputs selected for prediction were fracturing fluid efficiency, proppant mass, maximum proppant concentration, and injection rate. Extreme gradient boost (XGBoost), categorical boost (CatBoost), adaptive boost (AdaBoost), and light gradient boosting machine (LGBM) were the algorithms finalized for the comparative study. The sensitivity was done for a different number of classes (four, five, and six) to establish a balance between accuracy and prediction granularity. The results showed that the best algorithm choice was between XGBoost and CatBoost for the predicted parameters under certain model construction conditions. The accuracy for all outputs for the holdout sets varied between 80 and 92%, showing robust significance for a wider utilization of these models.\u0000 Data science has contributed to various oil and gas industry domains and has tremendous applications in the stimulation domain. The research and review conducted in this paper add a valuable resource for the user to build digital databases and use the appropriate algorithm without much trial and error. Implementing this model reduced the complexity of the proppant fracturing treatment redesign process, enhanced operational efficiency, and reduced fracture damage by eliminating minifrac steps with crosslinked gel.","PeriodicalId":10970,"journal":{"name":"Day 1 Tue, October 12, 2021","volume":"494 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74804746","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 deep learning-based framework for proxy flow modeling to predict gridded dynamic petroleum reservoir properties (like pressure and saturation) and production rates for wells in a single framework. It approximates the solution of a full physics-based numerical reservoir simulator, but runs much more rapidly, allowing users to generate results for a much wider range of scenarios in a given time than could be done with a full physics simulator. The proxy can be used for reservoir management tasks like history matching, uncertainty quantification, and field development optimization. A deep-learning based methodology for accurate proxy-flow modeling is presented which combines U-Net (a variant of convolutional neural network) to predict gridded dynamic properties and deep neural network (DNN) models to forecast well production rates. First, gridded dynamic properties, such as reservoir pressure and phase saturations, are predicted from static properties like reservoir rock porosity and absolute permeability using a U-Net. Then, the static properties and the dynamic properties predicted by the U-Net are input to a DNN to predict production rates at the well perforations. The inclusion of U-net predicted pressure and saturations improves the quality of the well rate predictions. The proposed methodology is presented with the synthetic Brugge reservoir discretized into grid blocks. The U-Net input consists of three properties: dynamic gridded reservoir properties (such as pressure or fluid saturation) at the current state, static gridded porosity, and static gridded permeability. The U-Net has only one output property, the target gridded property (such as pressure or saturation) at the next time step. Training and testing datasets are generated by running 13 full physics flow simulations and dividing them in a 12:1 ratio. Nine U-Net models are calibrated to predict pressures/saturations, one for each of the nine grid layers present in the Brugge model. These outputs are then concatenated to obtain the complete pressure/saturation model for all nine layers. The constructed U-Net models match the distributions of generated pressures/saturations of the numerical reservoir simulator with a correlation coefficient value of approximately 0.99 and above 95% accuracy. The DNN models approximate well production rates accurately from U-Net predicted pressures and saturations along with static properties like transmissibility and horizontal permeability. For each well and each well perforation, the production rate is predicted with the DNN model. The use of the constructed proxy flow model generates reservoir predictions within a few minutes compared to the hours or days typically taken by a full physics flow simulator. The direct connection that is established between the gridded static and dynamic properties of the reservoir and well production rates using U-Net and DNN models has not been presented previously. Using only a small number
{"title":"A Proxy Flow Modelling Workflow to Estimate Gridded Dynamic Properties and Well Production Rates by Deep Learning Algorithms","authors":"Soumi Chaki, Yevgeniy Zagayevskiy, Wong Terry","doi":"10.2118/205556-ms","DOIUrl":"https://doi.org/10.2118/205556-ms","url":null,"abstract":"\u0000 This paper proposes a deep learning-based framework for proxy flow modeling to predict gridded dynamic petroleum reservoir properties (like pressure and saturation) and production rates for wells in a single framework. It approximates the solution of a full physics-based numerical reservoir simulator, but runs much more rapidly, allowing users to generate results for a much wider range of scenarios in a given time than could be done with a full physics simulator. The proxy can be used for reservoir management tasks like history matching, uncertainty quantification, and field development optimization. A deep-learning based methodology for accurate proxy-flow modeling is presented which combines U-Net (a variant of convolutional neural network) to predict gridded dynamic properties and deep neural network (DNN) models to forecast well production rates.\u0000 First, gridded dynamic properties, such as reservoir pressure and phase saturations, are predicted from static properties like reservoir rock porosity and absolute permeability using a U-Net. Then, the static properties and the dynamic properties predicted by the U-Net are input to a DNN to predict production rates at the well perforations. The inclusion of U-net predicted pressure and saturations improves the quality of the well rate predictions.\u0000 The proposed methodology is presented with the synthetic Brugge reservoir discretized into grid blocks. The U-Net input consists of three properties: dynamic gridded reservoir properties (such as pressure or fluid saturation) at the current state, static gridded porosity, and static gridded permeability. The U-Net has only one output property, the target gridded property (such as pressure or saturation) at the next time step. Training and testing datasets are generated by running 13 full physics flow simulations and dividing them in a 12:1 ratio. Nine U-Net models are calibrated to predict pressures/saturations, one for each of the nine grid layers present in the Brugge model. These outputs are then concatenated to obtain the complete pressure/saturation model for all nine layers. The constructed U-Net models match the distributions of generated pressures/saturations of the numerical reservoir simulator with a correlation coefficient value of approximately 0.99 and above 95% accuracy. The DNN models approximate well production rates accurately from U-Net predicted pressures and saturations along with static properties like transmissibility and horizontal permeability. For each well and each well perforation, the production rate is predicted with the DNN model. The use of the constructed proxy flow model generates reservoir predictions within a few minutes compared to the hours or days typically taken by a full physics flow simulator.\u0000 The direct connection that is established between the gridded static and dynamic properties of the reservoir and well production rates using U-Net and DNN models has not been presented previously. Using only a small number","PeriodicalId":10970,"journal":{"name":"Day 1 Tue, October 12, 2021","volume":"183 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80415627","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}
Xianmin Zhou, Ridha Al-Abdrabalnabi, S. Khan, M. Kamal
After water flooding in carbonate reservoirs, a significant fraction of the original oil as remaining oil is left in the swept zone. The remaining oil in the pore, trapped by viscous and capillary forces, is to target for improved and enhanced oil recovery. The mobilization of remaining oil can be predicted by a dimensionless parameter called capillary number. The interfacial tension and injection flow rate strongly affect the capillary number. Unfortunately, the interrelationship between capillary number, interfacial tension, injection flow rate, and the temperature has been poorly studied for carbonate reservoirs. This paper focuses on studying the remaining oil saturations at different orders of magnitude capillary numbers related to interfacial tension, injection flow rate, and temperature by seawater and surfactant flooding. Several core flooding experiments were performed by changing the injection rate and surfactant concentrations at evaluated conditions. Four displacement experiments of seawater/oil and surfactant solution/oil were performed using oil-wet carbonate cores to obtain the relationship between the residual oil saturation vs. the capillary number. The surfactant flooding experiments with different concentrations of 0.01 and 0.2 wt% were conducted when the remaining oil saturation was reached after water flooding. Three core flooding experiments were conducted at ambient conditions, and one was under evaluated conditions of a temperature of 100° and pore pressure of 3200 psi. Several injection rates were selected to experiment with a 0.2 wt% surfactant solution, which is to study the effect of injection rate on the capillary number and residual oil saturation. The experimental findings show that some remaining oil can be recovered from oil-wet carbonate cores if the capillary number increases by a critical Nc =2.1E-05 by surfactant flooding at reservoir conditions. After water flooding, the remaining oil saturation was decreased from 51% to 16% with 0.01wt% surfactant flooding. The reduction of interfacial tension from 6.77dyne/cm to 0.017dyne/cm led to an increased capillary number. It decreased the remaining oil saturation by about 5% OOIP when the capillary number increases three magnitudes. The effect of temperature and injection rate on the capillary number was observed based on experimental displacement results. Compared with results between the ambient and specified conditions, the effect of temperature on the capillary number is significant. Under the same capillary number, the remaining oil recovered by surfactant flooding at HPHT conditions was higher than that at ambient conditions. Also, the effect of the injection flow rate on the capillary number was observed by 0.2wt % surfactant flooding for all experiments. The capillary number increased with an increase in the injection rate for both ambient and evaluated conditions. This paper provides valuable results to evaluate the interrelationship between remaining o
{"title":"Interrelationship of Capillary Number, Interfacial Tension, Injection Flow Rate and Temperature by Surfactant Flooding for Oil-wet Carbonate Reservoirs","authors":"Xianmin Zhou, Ridha Al-Abdrabalnabi, S. Khan, M. Kamal","doi":"10.2118/205749-ms","DOIUrl":"https://doi.org/10.2118/205749-ms","url":null,"abstract":"\u0000 After water flooding in carbonate reservoirs, a significant fraction of the original oil as remaining oil is left in the swept zone. The remaining oil in the pore, trapped by viscous and capillary forces, is to target for improved and enhanced oil recovery. The mobilization of remaining oil can be predicted by a dimensionless parameter called capillary number. The interfacial tension and injection flow rate strongly affect the capillary number. Unfortunately, the interrelationship between capillary number, interfacial tension, injection flow rate, and the temperature has been poorly studied for carbonate reservoirs. This paper focuses on studying the remaining oil saturations at different orders of magnitude capillary numbers related to interfacial tension, injection flow rate, and temperature by seawater and surfactant flooding. Several core flooding experiments were performed by changing the injection rate and surfactant concentrations at evaluated conditions.\u0000 Four displacement experiments of seawater/oil and surfactant solution/oil were performed using oil-wet carbonate cores to obtain the relationship between the residual oil saturation vs. the capillary number. The surfactant flooding experiments with different concentrations of 0.01 and 0.2 wt% were conducted when the remaining oil saturation was reached after water flooding. Three core flooding experiments were conducted at ambient conditions, and one was under evaluated conditions of a temperature of 100° and pore pressure of 3200 psi. Several injection rates were selected to experiment with a 0.2 wt% surfactant solution, which is to study the effect of injection rate on the capillary number and residual oil saturation.\u0000 The experimental findings show that some remaining oil can be recovered from oil-wet carbonate cores if the capillary number increases by a critical Nc =2.1E-05 by surfactant flooding at reservoir conditions. After water flooding, the remaining oil saturation was decreased from 51% to 16% with 0.01wt% surfactant flooding. The reduction of interfacial tension from 6.77dyne/cm to 0.017dyne/cm led to an increased capillary number. It decreased the remaining oil saturation by about 5% OOIP when the capillary number increases three magnitudes. The effect of temperature and injection rate on the capillary number was observed based on experimental displacement results. Compared with results between the ambient and specified conditions, the effect of temperature on the capillary number is significant. Under the same capillary number, the remaining oil recovered by surfactant flooding at HPHT conditions was higher than that at ambient conditions. Also, the effect of the injection flow rate on the capillary number was observed by 0.2wt % surfactant flooding for all experiments. The capillary number increased with an increase in the injection rate for both ambient and evaluated conditions.\u0000 This paper provides valuable results to evaluate the interrelationship between remaining o","PeriodicalId":10970,"journal":{"name":"Day 1 Tue, October 12, 2021","volume":"15 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87055139","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}
Incidents can incur damage on people, environment, asset and even on Company's reputation. Therefore, effective learning from incidents plays a critical role in Company's HSE management system. Effective learning from incidents can also be one of predictors of an effective HSE management system and positive safety culture (Reason, 2016). This study was undertaken to discuss Mahakam's (now operated by PT. X) experience in the implementation of learning from incidents and its contribution to improve Company's safety performance. Learning cycle from Jacobsson is used as main reference to assess the effectiveness of learning from incidents system in the company (Jacobsson et al., 2011).
事故会对人员、环境、资产甚至公司声誉造成损害。因此，有效地从事件中学习对公司的HSE管理体系至关重要。从事故中有效学习也可以成为有效的HSE管理体系和积极的安全文化的预测因素之一(Reason, 2016)。本研究旨在讨论Mahakam(现由PT. X运营)在从事故中学习的实施经验及其对提高公司安全绩效的贡献。Jacobsson的学习周期是评估公司事件学习系统有效性的主要参考(Jacobsson et al.， 2011)。
{"title":"Successfully Learning from Failures: A Mahakam Legacy","authors":"Diah Kusumawati, W. Puspa, Nandi Kurniawan","doi":"10.2118/205630-ms","DOIUrl":"https://doi.org/10.2118/205630-ms","url":null,"abstract":"\u0000 \u0000 \u0000 Incidents can incur damage on people, environment, asset and even on Company's reputation. Therefore, effective learning from incidents plays a critical role in Company's HSE management system. Effective learning from incidents can also be one of predictors of an effective HSE management system and positive safety culture (Reason, 2016). This study was undertaken to discuss Mahakam's (now operated by PT. X) experience in the implementation of learning from incidents and its contribution to improve Company's safety performance. Learning cycle from Jacobsson is used as main reference to assess the effectiveness of learning from incidents system in the company (Jacobsson et al., 2011).\u0000","PeriodicalId":10970,"journal":{"name":"Day 1 Tue, October 12, 2021","volume":"218 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75501366","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：