Thad Nosar, Pooya Khodaparast, Wei Zhang, A. Mehrabian
Equivalent circulation density of the fluid circulation system in drilling rigs is determined by the frictional pressure losses in the wellbore annulus. Flow loop experiments are commonly used to simulate the annular wellbore hydraulics in the laboratory. However, proper scaling of the experiment design parameters including the drill pipe rotation and eccentricity has been a weak link in the literature. Our study uses the similarity laws and dimensional analysis to obtain a complete set of scaling formulae that would relate the pressure loss gradients of annular flows at the laboratory and wellbore scales while considering the effects of inner pipe rotation and eccentricity. Dimensional analysis is conducted for commonly encountered types of drilling fluid rheology, namely, Newtonian, power-law, and yield power-law. Appropriate dimensionless groups of the involved variables are developed to characterize fluid flow in an eccentric annulus with a rotating inner pipe. Characteristic shear strain rate at the pipe walls is obtained from the characteristic velocity and length scale of the considered annular flow. The relation between lab-scale and wellbore scale variables are obtained by imposing the geometric, kinematic, and dynamic similarities between the laboratory flow loop and wellbore annular flows. The outcomes of the considered scaling scheme is expressed in terms of closed-form formulae that would determine the flow rate and inner pipe rotation speed of the laboratory experiments in terms of the wellbore flow rate and drill pipe rotation speed, as well as other parameters of the problem, in such a way that the resulting Fanning friction factors of the laboratory and wellbore-scale annular flows become identical. Findings suggest that the appropriate value for lab flow rate and pipe rotation speed are linearly related to those of the field condition for all fluid types. The length ratio, density ratio, consistency index ratio, and power index determine the proportionality constant. Attaining complete similarity between the similitude and wellbore-scale annular flow may require the fluid rheology of the lab experiments to be different from the drilling fluid. The expressions of lab flow rate and rotational speed for the yield power-law fluid are identical to those of the power-law fluid case, provided that the yield stress of the lab fluid is constrained to a proper value.
{"title":"Scaling Formulae for the Wellbore Hydraulics Similitude with Drill Pipe Rotation and Eccentricity","authors":"Thad Nosar, Pooya Khodaparast, Wei Zhang, A. Mehrabian","doi":"10.2118/204637-ms","DOIUrl":"https://doi.org/10.2118/204637-ms","url":null,"abstract":"\u0000 Equivalent circulation density of the fluid circulation system in drilling rigs is determined by the frictional pressure losses in the wellbore annulus. Flow loop experiments are commonly used to simulate the annular wellbore hydraulics in the laboratory. However, proper scaling of the experiment design parameters including the drill pipe rotation and eccentricity has been a weak link in the literature. Our study uses the similarity laws and dimensional analysis to obtain a complete set of scaling formulae that would relate the pressure loss gradients of annular flows at the laboratory and wellbore scales while considering the effects of inner pipe rotation and eccentricity.\u0000 Dimensional analysis is conducted for commonly encountered types of drilling fluid rheology, namely, Newtonian, power-law, and yield power-law. Appropriate dimensionless groups of the involved variables are developed to characterize fluid flow in an eccentric annulus with a rotating inner pipe. Characteristic shear strain rate at the pipe walls is obtained from the characteristic velocity and length scale of the considered annular flow. The relation between lab-scale and wellbore scale variables are obtained by imposing the geometric, kinematic, and dynamic similarities between the laboratory flow loop and wellbore annular flows.\u0000 The outcomes of the considered scaling scheme is expressed in terms of closed-form formulae that would determine the flow rate and inner pipe rotation speed of the laboratory experiments in terms of the wellbore flow rate and drill pipe rotation speed, as well as other parameters of the problem, in such a way that the resulting Fanning friction factors of the laboratory and wellbore-scale annular flows become identical. Findings suggest that the appropriate value for lab flow rate and pipe rotation speed are linearly related to those of the field condition for all fluid types. The length ratio, density ratio, consistency index ratio, and power index determine the proportionality constant. Attaining complete similarity between the similitude and wellbore-scale annular flow may require the fluid rheology of the lab experiments to be different from the drilling fluid. The expressions of lab flow rate and rotational speed for the yield power-law fluid are identical to those of the power-law fluid case, provided that the yield stress of the lab fluid is constrained to a proper value.","PeriodicalId":11320,"journal":{"name":"Day 3 Tue, November 30, 2021","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82961228","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. Chertov, Franck Ivan Salazar Suarez, M. Kaznacheev, L. Belyakova
In the paper, we document one iteration of the continuous improvement of well performance undertaken in the Oriente Basin in Ecuador. In the past, it had been observed that well economics was sometimes degraded by the issues related to proppant flowback from hydraulic fractures. Proppant flowback resulted in extra costs from well cleanouts, pump replacement, and damage to fracture conductivity. After evaluation of proppant flowback cases using the combined modeling workflow that simulates fracture growth, proppant placement, and early production of solids and fluids, it had been proposed to modify fracture designs and well startup strategy. In this paper, we review the first results of implementation of these modifications in the field and evaluate the significance of improvements.
{"title":"Combined Proppant Placement and Early Production Modeling Achieve Increased Fracture Performance in Ecuador's Oriente Basin","authors":"M. Chertov, Franck Ivan Salazar Suarez, M. Kaznacheev, L. Belyakova","doi":"10.2118/204677-ms","DOIUrl":"https://doi.org/10.2118/204677-ms","url":null,"abstract":"\u0000 In the paper, we document one iteration of the continuous improvement of well performance undertaken in the Oriente Basin in Ecuador. In the past, it had been observed that well economics was sometimes degraded by the issues related to proppant flowback from hydraulic fractures. Proppant flowback resulted in extra costs from well cleanouts, pump replacement, and damage to fracture conductivity. After evaluation of proppant flowback cases using the combined modeling workflow that simulates fracture growth, proppant placement, and early production of solids and fluids, it had been proposed to modify fracture designs and well startup strategy. In this paper, we review the first results of implementation of these modifications in the field and evaluate the significance of improvements.","PeriodicalId":11320,"journal":{"name":"Day 3 Tue, November 30, 2021","volume":"67 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83253340","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}
Nadir Husein, Jianhua Xu, Igor Novikov, R. Gazizov, A. Buyanov, Guangyu Wang, D. Lysova, Vishwajit Upadhye
From year to year, well drilling is becoming more technologically advanced and more complex, therefore we observe the active development of drilling technologies, well completion and production intensification. It forms the trend towards the complex well geometry and growth of the length of horizontal sections and therefore an increase of the hydraulic fracturing stages at each well. It's obvious, that oil producing companies frequently don't have proved analytical data on the actual distribution of formation fluid in the inflow profiles for some reasons. Conventional logging methods in horizontal sections require coiled tubing (CT) or downhole tractors, and the well preparation such as drilling the ball seat causing technical difficulties, risks of downhole equipment getting lost or stuck in the well. Sometimes the length of horizontal sections is too long to use conventional logging methods due to their limitations. In this regard, efficient solution of objectives related to the production and development of fields with horizontal wells is complicated due to the shortage of instruments allowing to justify the horizontal well optimal length and the number of MultiFrac stages, difficulties in evaluating the reservoir management system efficiency, etc. A new method of tracer based production profiling technologies are increasingly applied in the global oil industry. This approach benefits through excluding well intervention operations for production logging, allows continuous production profiling operations without the necessity of well shut-in, and without involving additional equipment and personal to be located at wellsite.
{"title":"An Alternative Tool for Production Logging in Horizontal Wells","authors":"Nadir Husein, Jianhua Xu, Igor Novikov, R. Gazizov, A. Buyanov, Guangyu Wang, D. Lysova, Vishwajit Upadhye","doi":"10.2118/204805-ms","DOIUrl":"https://doi.org/10.2118/204805-ms","url":null,"abstract":"\u0000 From year to year, well drilling is becoming more technologically advanced and more complex, therefore we observe the active development of drilling technologies, well completion and production intensification. It forms the trend towards the complex well geometry and growth of the length of horizontal sections and therefore an increase of the hydraulic fracturing stages at each well. It's obvious, that oil producing companies frequently don't have proved analytical data on the actual distribution of formation fluid in the inflow profiles for some reasons. Conventional logging methods in horizontal sections require coiled tubing (CT) or downhole tractors, and the well preparation such as drilling the ball seat causing technical difficulties, risks of downhole equipment getting lost or stuck in the well. Sometimes the length of horizontal sections is too long to use conventional logging methods due to their limitations.\u0000 In this regard, efficient solution of objectives related to the production and development of fields with horizontal wells is complicated due to the shortage of instruments allowing to justify the horizontal well optimal length and the number of MultiFrac stages, difficulties in evaluating the reservoir management system efficiency, etc.\u0000 A new method of tracer based production profiling technologies are increasingly applied in the global oil industry. This approach benefits through excluding well intervention operations for production logging, allows continuous production profiling operations without the necessity of well shut-in, and without involving additional equipment and personal to be located at wellsite.","PeriodicalId":11320,"journal":{"name":"Day 3 Tue, November 30, 2021","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81861154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Asif, Jon E. Hansen, AbdulMuqtadir Khan, M. Sheshtawy
Hydrocarbon development from tight gas sandstone reservoirs is revolutionizing the current oil and gas market. The most effective development strategy for ultralow- to low-permeability reservoirs involves multistage fracturing. A cemented casing or liner completed with the plug-and-perf method allows nearly full control of fracture initiation depth. In uncemented completions equipped with fracturing sleeves and packers, clearly identifying the fracture initiation points is difficult due to lack of visibility behind the completion and long openhole intervals between packers. Also, the number of fractures initiated in each treatment is uncertain. A lateral was completed with access to 3,190 ft of openhole section across five fracturing stages in a high-temperature and high-pressure tight-gas interval. All stages were successfully stimulated, fracture cleanup flowback was conducted, and entry ports were milled out. A high-definition spectral noise log (SNL) was then conducted along with numerical temperature modeling. Additional logging was done with a set of conventional multiphase sensors. A multi-array production log suite was also performed. Finally, the bottom four stages were isolated with a high-temperature isolation plug based on the integrated diagnosis. The SNL helped to analyze the isolation packer integrity behind the liner. The initiation of multiple fractures was observed, with as many as nine fractures seen in a single-stage interval. A correlation was found between the openhole interval length and the number of fractures. A correlation of fracture gradient (FG) and initiation depths was made for the lateral in a strike-slip fault regime. The fractures were initiated at depths with low calculated FG, confirming the conventional understanding and increasing confidence in rock property calculations from openhole log data. SNL and temperature modeling aided quantitative assessment of flowing fractures and stagewise production behind the liner. Multi-array production logging results quantified the flow and flow profile inside the horizontal liner. The production flow assessments from both techniques were in good agreement. The integration of several datasets was conducted in a single run, which provided a comprehensive understanding of well completion and production. High water producing intervals were isolated. Downstream separator setup after the isolation showed a water cut reduction by 95%. The integration of the post-fracturing logs with the openhole logs and fracturing data is unique. The high-resolution SNL provided valuable insight on fracture initiation points and the integrity of completion packers. Fracturing efficiency, compared to the proppant placed, provides treatment optimization for similar completions in the future.
{"title":"Integration of Post-Fracturing Spectral Noise Log, Temperature Modeling, and Production Log Diagnoses Water Production and Resolves Uncertainties in Openhole Multistage Fracturing","authors":"A. Asif, Jon E. Hansen, AbdulMuqtadir Khan, M. Sheshtawy","doi":"10.2118/204668-ms","DOIUrl":"https://doi.org/10.2118/204668-ms","url":null,"abstract":"\u0000 Hydrocarbon development from tight gas sandstone reservoirs is revolutionizing the current oil and gas market. The most effective development strategy for ultralow- to low-permeability reservoirs involves multistage fracturing. A cemented casing or liner completed with the plug-and-perf method allows nearly full control of fracture initiation depth. In uncemented completions equipped with fracturing sleeves and packers, clearly identifying the fracture initiation points is difficult due to lack of visibility behind the completion and long openhole intervals between packers. Also, the number of fractures initiated in each treatment is uncertain.\u0000 A lateral was completed with access to 3,190 ft of openhole section across five fracturing stages in a high-temperature and high-pressure tight-gas interval. All stages were successfully stimulated, fracture cleanup flowback was conducted, and entry ports were milled out. A high-definition spectral noise log (SNL) was then conducted along with numerical temperature modeling. Additional logging was done with a set of conventional multiphase sensors. A multi-array production log suite was also performed. Finally, the bottom four stages were isolated with a high-temperature isolation plug based on the integrated diagnosis.\u0000 The SNL helped to analyze the isolation packer integrity behind the liner. The initiation of multiple fractures was observed, with as many as nine fractures seen in a single-stage interval. A correlation was found between the openhole interval length and the number of fractures. A correlation of fracture gradient (FG) and initiation depths was made for the lateral in a strike-slip fault regime. The fractures were initiated at depths with low calculated FG, confirming the conventional understanding and increasing confidence in rock property calculations from openhole log data. SNL and temperature modeling aided quantitative assessment of flowing fractures and stagewise production behind the liner. Multi-array production logging results quantified the flow and flow profile inside the horizontal liner. The production flow assessments from both techniques were in good agreement. The integration of several datasets was conducted in a single run, which provided a comprehensive understanding of well completion and production. High water producing intervals were isolated. Downstream separator setup after the isolation showed a water cut reduction by 95%.\u0000 The integration of the post-fracturing logs with the openhole logs and fracturing data is unique. The high-resolution SNL provided valuable insight on fracture initiation points and the integrity of completion packers. Fracturing efficiency, compared to the proppant placed, provides treatment optimization for similar completions in the future.","PeriodicalId":11320,"journal":{"name":"Day 3 Tue, November 30, 2021","volume":"38 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89475730","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}
Historically, the oil and gas industry has been slow and extremely cautious to adopt emerging technologies. But in the Age of Artificial Intelligence (AI), the industry has broken from tradition. It has not only embraced AI; it is leading the pack. AI has not only changed what it now means to work in the oil industry, it has changed how companies create, capture, and deliver value. Thanks, or no thanks to automation, traditional oil industry skills and talents are now being threatened, and in most cases, rendered obsolete. Oil and gas industry day-to-day work is progressively gravitating towards software and algorithms, and today’s workers are resigning themselves to the fact that computers and robots will one day "take over" and do much of their work. The adoption of AI and how it might affect career prospects is currently causing a lot of anxiety among industry professionals. This paper details how artificial intelligence, automation, and robotics has redefined what it now means to work in the oil industry, as well as the new challenges and responsibilities that the AI revolution presents. It takes a deep-dive into human-robot interaction, and underscores what AI can, and cannot do. It also identifies several traditional oilfield positions that have become endangered by automation, addresses the premonitions of professionals in these endangered roles, and lays out a roadmap on how to survive and thrive in a digitally transformed world. The future of work is evolving, and new technologies are changing how talent is acquired, developed, and retained. That robots will someday "take our jobs" is not an impossible possibility. It is more of a reality than an exaggeration. Automation in the oil industry has achieved outcomes that go beyond human capabilities. In fact, the odds are overwhelming that AI that functions at a comparable level to humans will soon become ubiquitous in the industry. The big question is: How long will it take? The oil industry of the future will not need large office complexes or a large workforce. Most of the work will be automated. Drilling rigs, production platforms, refineries, and petrochemical plants will not go away, but how work is done at these locations will be totally different. While the industry will never entirely lose its human touch, AI will be the foundation of the workforce of the future. How we react to the AI revolution today will shape the industry for generations to come. What should we do when AI changes our job functions and workforce? Should we be training AI, or should we be training humans?
{"title":"Artificial Intelligence and Robotics in the Oil Industry: Will it Take My Job?","authors":"Armstrong Lee Agbaji","doi":"10.2118/204643-ms","DOIUrl":"https://doi.org/10.2118/204643-ms","url":null,"abstract":"\u0000 Historically, the oil and gas industry has been slow and extremely cautious to adopt emerging technologies. But in the Age of Artificial Intelligence (AI), the industry has broken from tradition. It has not only embraced AI; it is leading the pack. AI has not only changed what it now means to work in the oil industry, it has changed how companies create, capture, and deliver value. Thanks, or no thanks to automation, traditional oil industry skills and talents are now being threatened, and in most cases, rendered obsolete. Oil and gas industry day-to-day work is progressively gravitating towards software and algorithms, and today’s workers are resigning themselves to the fact that computers and robots will one day \"take over\" and do much of their work. The adoption of AI and how it might affect career prospects is currently causing a lot of anxiety among industry professionals.\u0000 This paper details how artificial intelligence, automation, and robotics has redefined what it now means to work in the oil industry, as well as the new challenges and responsibilities that the AI revolution presents. It takes a deep-dive into human-robot interaction, and underscores what AI can, and cannot do. It also identifies several traditional oilfield positions that have become endangered by automation, addresses the premonitions of professionals in these endangered roles, and lays out a roadmap on how to survive and thrive in a digitally transformed world.\u0000 The future of work is evolving, and new technologies are changing how talent is acquired, developed, and retained. That robots will someday \"take our jobs\" is not an impossible possibility. It is more of a reality than an exaggeration. Automation in the oil industry has achieved outcomes that go beyond human capabilities. In fact, the odds are overwhelming that AI that functions at a comparable level to humans will soon become ubiquitous in the industry. The big question is: How long will it take?\u0000 The oil industry of the future will not need large office complexes or a large workforce. Most of the work will be automated. Drilling rigs, production platforms, refineries, and petrochemical plants will not go away, but how work is done at these locations will be totally different. While the industry will never entirely lose its human touch, AI will be the foundation of the workforce of the future. How we react to the AI revolution today will shape the industry for generations to come. What should we do when AI changes our job functions and workforce? Should we be training AI, or should we be training humans?","PeriodicalId":11320,"journal":{"name":"Day 3 Tue, November 30, 2021","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89706209","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}
J. Correia, Cátia Rodrigues, R. Esteves, R. C. Bezerra de Melo, José Gutiérrez, André M. Pereira, J. Ventura
Environmental and safety sensing is becoming of high importance in the oil and gas upstream industry. However, present solutions to feed theses sensors are expensive and dangerous and there is so far no technology able to generate electrical energy in the operational conditions of oil and gas extraction wells. In this paper it is presented, for the first time in a relevant environment, a pioneering energy harvesting technology based on nanomaterials that takes advantage of fluid movement in oil extraction wells. A device was tested to power monitoring systems with locally harvested energy in harsh conditions environment (pressures up to 50 bar and temperatures of 50ºC). Even though this technology is in an early development stage this work opens a wide range of possible applications in deep underwater environments and in Oil and Gas extraction wells where continuous flow conditions are present.
{"title":"Energy Harvesting Under Harsh Conditions for the Oil & Gas Upstream Industry","authors":"J. Correia, Cátia Rodrigues, R. Esteves, R. C. Bezerra de Melo, José Gutiérrez, André M. Pereira, J. Ventura","doi":"10.2118/204877-ms","DOIUrl":"https://doi.org/10.2118/204877-ms","url":null,"abstract":"\u0000 Environmental and safety sensing is becoming of high importance in the oil and gas upstream industry. However, present solutions to feed theses sensors are expensive and dangerous and there is so far no technology able to generate electrical energy in the operational conditions of oil and gas extraction wells. In this paper it is presented, for the first time in a relevant environment, a pioneering energy harvesting technology based on nanomaterials that takes advantage of fluid movement in oil extraction wells. A device was tested to power monitoring systems with locally harvested energy in harsh conditions environment (pressures up to 50 bar and temperatures of 50ºC). Even though this technology is in an early development stage this work opens a wide range of possible applications in deep underwater environments and in Oil and Gas extraction wells where continuous flow conditions are present.","PeriodicalId":11320,"journal":{"name":"Day 3 Tue, November 30, 2021","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75379402","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}
Ashabikash Roy Chowdhury, M. Forshaw, Narender Atwal, M. Gatzen, Salman Habib, Jonathan Afolabi
In the increasingly complex and cost sensitive drilling environment of today, data gathered using downhole and surface real-time sensor systems must work in unison with physics-based models to facilitate early indication of drilling hazards, allowing timely action and mitigation. Identification of opportunities for reduction of invisible lost time (ILT) is similarly critical. Many similar systems gather and analyze either surface or downhole data on a standalone basis but lack the integrated approach towards using the data in a holistic decision-making manner. These systems can either paint an incomplete picture of prevailing drilling conditions or fail to ensure system messages result in parameter changes at rigsite. This often results in a hit or miss approach in identification and mitigation of drilling problems. The automated software system architecture is described, detailing the physics-based models which are deployed in real-time consuming surface and downhole sensor data and outputting continuous, operationally relevant simulation results. Measured data from either surface, for torque & drag, or downhole for ECD & ESD is then automatically compared both for deviation of actual-to-plan, and for infringement of boundary conditions such as formation pressure regime. The system is also equipped to model off-bottom induced pressures; swab & surge, and dynamically advise on safe, but optimum tripping velocities for the operation at hand. This has dual benefits; both the avoidance of costly NPT associated with swab & surge, as well as being able to visually highlight running speed ILT. All processing applications are coupled with highly intuitive user interfaces. Three successful deployments all onshore in the Middle East are detailed. First a horizontal section where real-time model vs. actual automatic comparison of torque & drag samples, validated with PWD data allowed early identification of poor hole cleaning. Secondly, a vertical section where again the model vs. actual algorithmic automatically identified inadequate hole cleaning in a case where conventional human monitoring did not. Finally, a case is exhibited where real-time modelling of swab and surge, as well as intuitive visualization of the trip speeds within those boundary conditions led to a significant increase in average tripping speeds when compared to offset wells, reducing AFE for the operator. Common for all three deployments was an integrated well services approach, with a single service company providing the majority of services for well construction, as well as an overarching remote operations team who were primary users of the software solutions deployed.
{"title":"Innovative Approach of Drilling Risk Identification and Mitigation Using Drilling Automation Services: Case Studies","authors":"Ashabikash Roy Chowdhury, M. Forshaw, Narender Atwal, M. Gatzen, Salman Habib, Jonathan Afolabi","doi":"10.2118/204723-ms","DOIUrl":"https://doi.org/10.2118/204723-ms","url":null,"abstract":"\u0000 In the increasingly complex and cost sensitive drilling environment of today, data gathered using downhole and surface real-time sensor systems must work in unison with physics-based models to facilitate early indication of drilling hazards, allowing timely action and mitigation. Identification of opportunities for reduction of invisible lost time (ILT) is similarly critical. Many similar systems gather and analyze either surface or downhole data on a standalone basis but lack the integrated approach towards using the data in a holistic decision-making manner. These systems can either paint an incomplete picture of prevailing drilling conditions or fail to ensure system messages result in parameter changes at rigsite. This often results in a hit or miss approach in identification and mitigation of drilling problems.\u0000 The automated software system architecture is described, detailing the physics-based models which are deployed in real-time consuming surface and downhole sensor data and outputting continuous, operationally relevant simulation results. Measured data from either surface, for torque & drag, or downhole for ECD & ESD is then automatically compared both for deviation of actual-to-plan, and for infringement of boundary conditions such as formation pressure regime. The system is also equipped to model off-bottom induced pressures; swab & surge, and dynamically advise on safe, but optimum tripping velocities for the operation at hand. This has dual benefits; both the avoidance of costly NPT associated with swab & surge, as well as being able to visually highlight running speed ILT. All processing applications are coupled with highly intuitive user interfaces.\u0000 Three successful deployments all onshore in the Middle East are detailed. First a horizontal section where real-time model vs. actual automatic comparison of torque & drag samples, validated with PWD data allowed early identification of poor hole cleaning. Secondly, a vertical section where again the model vs. actual algorithmic automatically identified inadequate hole cleaning in a case where conventional human monitoring did not. Finally, a case is exhibited where real-time modelling of swab and surge, as well as intuitive visualization of the trip speeds within those boundary conditions led to a significant increase in average tripping speeds when compared to offset wells, reducing AFE for the operator. Common for all three deployments was an integrated well services approach, with a single service company providing the majority of services for well construction, as well as an overarching remote operations team who were primary users of the software solutions deployed.","PeriodicalId":11320,"journal":{"name":"Day 3 Tue, November 30, 2021","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77597143","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}
Abdulmalek Ahmed, A. Mahmoud, S. Elkatatny, R. Gajbhiye, A. Majed
Cementing is an important operation for the integrity of the wellbore due to its role in providing several functions. To perform these functions, a high performance cement is required. Different types of additives and materials have been added to the cement slurry to improve its performance. Tire waste material is considered one of the greatest wastes globally. It is a dangerous material to the environment and human. Subsequently, it has been included in many industrial processes to reduce its hazards. This work evaluated the application of tire waste material in oil and gas industry to improve the properties of Saudi class G oil well cement. Two cement slurries were formulated under high pressure and high temperature of 3000 psi and 292 °F, respectively. The first slurry was the base cement without tire waste and the second slurry contained the tire waste. The effect of using the two slurries on the cement properties such as density variation, compressive strength plastic viscosity, Poisson's ratio and porosity was evaluated. The results showed that, when tire waste material was used, lower density variation was accomplished. Using tire waste was efficient to decrease the density variation to an extremely low proportion of 0.5%. Adding tire waste to the cement composition decreased its plastic viscosity by 53.1%. The tire waste cement sample had a higher Poisson's ratio than the base cement sample by 14.3%. Utilizing the tire waste improved the cement's compressive strength by 48.3%. The cement porosity was declined by 23.1% after adding the tire waste. Beside the property's enhancement in the cement, the application of tire waste has also an economical advantage, since it is inexpensive material which is influential in our daily life.
{"title":"Application of Tire Waste Material to Enhance the Properties of Saudi Class G Oil Well Cement","authors":"Abdulmalek Ahmed, A. Mahmoud, S. Elkatatny, R. Gajbhiye, A. Majed","doi":"10.2118/204788-ms","DOIUrl":"https://doi.org/10.2118/204788-ms","url":null,"abstract":"\u0000 Cementing is an important operation for the integrity of the wellbore due to its role in providing several functions. To perform these functions, a high performance cement is required. Different types of additives and materials have been added to the cement slurry to improve its performance. Tire waste material is considered one of the greatest wastes globally. It is a dangerous material to the environment and human. Subsequently, it has been included in many industrial processes to reduce its hazards. This work evaluated the application of tire waste material in oil and gas industry to improve the properties of Saudi class G oil well cement.\u0000 Two cement slurries were formulated under high pressure and high temperature of 3000 psi and 292 °F, respectively. The first slurry was the base cement without tire waste and the second slurry contained the tire waste. The effect of using the two slurries on the cement properties such as density variation, compressive strength plastic viscosity, Poisson's ratio and porosity was evaluated.\u0000 The results showed that, when tire waste material was used, lower density variation was accomplished. Using tire waste was efficient to decrease the density variation to an extremely low proportion of 0.5%. Adding tire waste to the cement composition decreased its plastic viscosity by 53.1%. The tire waste cement sample had a higher Poisson's ratio than the base cement sample by 14.3%. Utilizing the tire waste improved the cement's compressive strength by 48.3%. The cement porosity was declined by 23.1% after adding the tire waste. Beside the property's enhancement in the cement, the application of tire waste has also an economical advantage, since it is inexpensive material which is influential in our daily life.","PeriodicalId":11320,"journal":{"name":"Day 3 Tue, November 30, 2021","volume":"36 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81367062","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}
J. Cornelio, Syamil Mohd Razak, Atefeh Jahandideh, B. Jafarpour, Young Cho, Hui-Hai Liu, R. Vaidya
Transfer learning is a machine learning concept whereby the knowledge gained (e.g., a model developed) in one task can be transferred (applied) to solve a different but related task. In the context of unconventional reservoirs, the concept can be used to transfer a machine learning model that is learned from data in one field (or shale play) to another, thereby significantly reducing the data needs and efforts to build a new model from scratch. In this work, we study the feasibility of developing deep learning models that can capture and transfer common features in a rich dataset pertaining to a mature unconventional play to enable production prediction in a new unconventional play with limited available data. The focus in this work is on method development using simulated data that correspond to the Bakken and Eagle Ford Shale Plays as two different unconventional plays in the US. We use formation and completion parameter ranges that correspond to the Bakken play with their simulated production responses to explore different approaches for training neural network models that enable transfer learning to predict production responses of input parameters corresponding to the Eagle Ford play (previously unseen input parameters). We explore different schemes by accessing the internal components of the model to extrapolate and categorize salient features that are represented in the trained neural network. Ultimately, our goal is to use these new mechanisms to enable effective sharing and reuse of discovered features from one unconventional well to another. To extract salient trends from formation and completion input parameters and their corresponding simulated production responses, we use deep learning architectures that consist of convolutional encoder-decoder networks. The architecture is then trained with rich simulated data from one field to generate a robust mapping between the input and the output feature spaces. The "learned" parameters from this network can then be "transferred" to develop a different predictive model for another field that may lack sufficient historical data. The results show that using standard training approaches, a neural network model that is trained with sufficiently large data samples from Bakken could produce reliable prediction models for typical wells that may be found in that field. The same neural network, however, could not produce reliable predictions for a typical Eagle Ford well. Furthermore, we observe that a neural network trained with insufficient data samples from Eagle Ford produces a poor prediction model for typical wells that may be found in Eagle Ford. However, when extrapolated feature components of the Bakken neural network were integrated into the training process of the Eagle Ford neural network, the resulting predictions for typical Eagle Ford wells improved significantly. Moreover, we observe that the ability to transfer learning can improve when specialized training strategies are adopted to
{"title":"Investigating Transfer Learning for Characterization and Performance Prediction in Unconventional Reservoirs","authors":"J. Cornelio, Syamil Mohd Razak, Atefeh Jahandideh, B. Jafarpour, Young Cho, Hui-Hai Liu, R. Vaidya","doi":"10.2118/204563-ms","DOIUrl":"https://doi.org/10.2118/204563-ms","url":null,"abstract":"\u0000 Transfer learning is a machine learning concept whereby the knowledge gained (e.g., a model developed) in one task can be transferred (applied) to solve a different but related task. In the context of unconventional reservoirs, the concept can be used to transfer a machine learning model that is learned from data in one field (or shale play) to another, thereby significantly reducing the data needs and efforts to build a new model from scratch. In this work, we study the feasibility of developing deep learning models that can capture and transfer common features in a rich dataset pertaining to a mature unconventional play to enable production prediction in a new unconventional play with limited available data. The focus in this work is on method development using simulated data that correspond to the Bakken and Eagle Ford Shale Plays as two different unconventional plays in the US. We use formation and completion parameter ranges that correspond to the Bakken play with their simulated production responses to explore different approaches for training neural network models that enable transfer learning to predict production responses of input parameters corresponding to the Eagle Ford play (previously unseen input parameters).\u0000 We explore different schemes by accessing the internal components of the model to extrapolate and categorize salient features that are represented in the trained neural network. Ultimately, our goal is to use these new mechanisms to enable effective sharing and reuse of discovered features from one unconventional well to another. To extract salient trends from formation and completion input parameters and their corresponding simulated production responses, we use deep learning architectures that consist of convolutional encoder-decoder networks. The architecture is then trained with rich simulated data from one field to generate a robust mapping between the input and the output feature spaces. The \"learned\" parameters from this network can then be \"transferred\" to develop a different predictive model for another field that may lack sufficient historical data.\u0000 The results show that using standard training approaches, a neural network model that is trained with sufficiently large data samples from Bakken could produce reliable prediction models for typical wells that may be found in that field. The same neural network, however, could not produce reliable predictions for a typical Eagle Ford well. Furthermore, we observe that a neural network trained with insufficient data samples from Eagle Ford produces a poor prediction model for typical wells that may be found in Eagle Ford. However, when extrapolated feature components of the Bakken neural network were integrated into the training process of the Eagle Ford neural network, the resulting predictions for typical Eagle Ford wells improved significantly. Moreover, we observe that the ability to transfer learning can improve when specialized training strategies are adopted to","PeriodicalId":11320,"journal":{"name":"Day 3 Tue, November 30, 2021","volume":"38 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85993043","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. Desouky, Zeeshan Tariq, Murtada Al jawad, Hamed Alhoori, M. Mahmoud, A. Abdulraheem
Propped hydraulic fracturing is a stimulation technique used in tight formations to create conductive fractures. To predict the fractured well productivity, the conductivity of those propped fractures should be estimated. It is common to measure the conductivity of propped fractures in the laboratory under controlled conditions. Nonetheless, it is costly and time-consuming which encouraged developing many empirical and analytical propped fracture conductivity models. Previous empirical models, however, were based on limited datasets producing questionable correlations. We propose herein new empirical models based on an extensive data set utilizing machine learning (ML) methods. In this study, an artificial neural network (ANN) was utilized. A dataset comprised of 351 data points of propped hydraulic fracture experiments on different shale types with different mineralogy under various confining stresses was collected and studied. Several statistical and data science approaches such as box and whisker plots, correlation crossplots, and Z-score techniques were used to remove the outliers and extreme data points. The performance of the developed model was evaluated using powerful metrics such as correlation coefficient and root mean squared error. After several executions and function evaluations, an ANN was found to be the best technique to predict propped fracture conductivity for different mineralogy. The proposed ANN models resulted in less than 7% error between actual and predicted values. In this study, in addition to the development of an optimized ANN model, explicit empirical correlations are also extracted from the weights and biases of the fine-tuned model. The proposed model of propped fracture conductivity was then compared with the commonly available correlations. The results revealed that the proposed mineralogy based propped fracture conductivity models made the predictions with a high correlation coefficient of 94%. This work clearly shows the potential of computer-based ML techniques in the determination of mineralogy based propped fracture conductivity. The proposed empirical correlation can be implemented without requiring any ML-based software.
{"title":"Development of Machine Learning Based Propped Fracture Conductivity Correlations in Shale Formations","authors":"M. Desouky, Zeeshan Tariq, Murtada Al jawad, Hamed Alhoori, M. Mahmoud, A. Abdulraheem","doi":"10.2118/204606-ms","DOIUrl":"https://doi.org/10.2118/204606-ms","url":null,"abstract":"\u0000 Propped hydraulic fracturing is a stimulation technique used in tight formations to create conductive fractures. To predict the fractured well productivity, the conductivity of those propped fractures should be estimated. It is common to measure the conductivity of propped fractures in the laboratory under controlled conditions. Nonetheless, it is costly and time-consuming which encouraged developing many empirical and analytical propped fracture conductivity models. Previous empirical models, however, were based on limited datasets producing questionable correlations. We propose herein new empirical models based on an extensive data set utilizing machine learning (ML) methods.\u0000 In this study, an artificial neural network (ANN) was utilized. A dataset comprised of 351 data points of propped hydraulic fracture experiments on different shale types with different mineralogy under various confining stresses was collected and studied. Several statistical and data science approaches such as box and whisker plots, correlation crossplots, and Z-score techniques were used to remove the outliers and extreme data points. The performance of the developed model was evaluated using powerful metrics such as correlation coefficient and root mean squared error.\u0000 After several executions and function evaluations, an ANN was found to be the best technique to predict propped fracture conductivity for different mineralogy. The proposed ANN models resulted in less than 7% error between actual and predicted values. In this study, in addition to the development of an optimized ANN model, explicit empirical correlations are also extracted from the weights and biases of the fine-tuned model. The proposed model of propped fracture conductivity was then compared with the commonly available correlations. The results revealed that the proposed mineralogy based propped fracture conductivity models made the predictions with a high correlation coefficient of 94%.\u0000 This work clearly shows the potential of computer-based ML techniques in the determination of mineralogy based propped fracture conductivity. The proposed empirical correlation can be implemented without requiring any ML-based software.","PeriodicalId":11320,"journal":{"name":"Day 3 Tue, November 30, 2021","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91020289","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：