B. Al-Otaibi, Issa Abu Shiekah, M. Jha, G. de Bruijn, P. Male, Shahad Al-Omair, H. Ibrahim
After 40 years of depletion drive, a mature, giant and multi-layer carbonate reservoir is developed through waterflooding. Oil production, sustained through infill drilling and new development patterns, is often associated with increasingly higher water production compared to earlier development phases. A field re-development plan has been established to alleviate the impact of reservoir heterogeneities on oil recovery, driven by the analysis of the historical performance of production and injection of a range of well types. The field is developed through historical opportunistic development concepts utilizing evolving technology trends. Therefore, the field has initially wide spacing vertical waterflooding patterns followed by horizontal wells, subjected to seawater or produced water injection, applying a range of wells placement or completion technologies and different water injection operating strategies. Systematic categorization, grouping and analyzing of a rich data set of wells performance have been complemented and integrated with insights from coarse full field and conceptual sector dynamic modeling activities. This workflow efficiently paved the way to optimize the field development aiming for increased oil recovery and cost saving opportunities. Integrated analysis of evolving historical development decisions revealed and ranked the primary subsurface and operational drivers behind the limited sweep efficiency and increased watercut. This helped mapping the impact of fundamental subsurface attributes from well placement, completion, or water injection strategies. Excellent vertical wells performance during the primary depletion and the early stage of water flooding was slowly outperformed by a more sustainable horizontal well production and injection strategy. This is consistent with a conceptual model in which the reservoir is dominated by extensive high conductive features that contributed in the early life of the field to good oil production before becoming the primary source of premature water breakthrough after a limited fraction of pore volume water was injected. The next level of analysis provided actual field evidence to support informed decisions to optimize the front runner horizontal wells development concept to cover wells length, orientation, vertical placement in the stratigraphy, spacing, pattern strategy and completion design. The findings enabled delivering updated field development plan covering the field life cycle to sustain and increase field oil production through adding ~ 200 additional wells and introducing more structured water flooding patterns in addition to establishing improved wells reservoir management practices. This integrated study manifests the power, efficiency and value from data driven analysis to capture lessons learned from evolving wells and development concepts applied in a complex brown field over six decades. The workflow enabled the delivery of an updated field development plan and prod
{"title":"60 Years Field Performance Data-Driven Analytics to Generate Updated Waterflood Field Development Plan in a North Kuwait Giant Carbonate Reservoir","authors":"B. Al-Otaibi, Issa Abu Shiekah, M. Jha, G. de Bruijn, P. Male, Shahad Al-Omair, H. Ibrahim","doi":"10.2118/207231-ms","DOIUrl":"https://doi.org/10.2118/207231-ms","url":null,"abstract":"\u0000 After 40 years of depletion drive, a mature, giant and multi-layer carbonate reservoir is developed through waterflooding. Oil production, sustained through infill drilling and new development patterns, is often associated with increasingly higher water production compared to earlier development phases. A field re-development plan has been established to alleviate the impact of reservoir heterogeneities on oil recovery, driven by the analysis of the historical performance of production and injection of a range of well types.\u0000 The field is developed through historical opportunistic development concepts utilizing evolving technology trends. Therefore, the field has initially wide spacing vertical waterflooding patterns followed by horizontal wells, subjected to seawater or produced water injection, applying a range of wells placement or completion technologies and different water injection operating strategies. Systematic categorization, grouping and analyzing of a rich data set of wells performance have been complemented and integrated with insights from coarse full field and conceptual sector dynamic modeling activities. This workflow efficiently paved the way to optimize the field development aiming for increased oil recovery and cost saving opportunities.\u0000 Integrated analysis of evolving historical development decisions revealed and ranked the primary subsurface and operational drivers behind the limited sweep efficiency and increased watercut. This helped mapping the impact of fundamental subsurface attributes from well placement, completion, or water injection strategies. Excellent vertical wells performance during the primary depletion and the early stage of water flooding was slowly outperformed by a more sustainable horizontal well production and injection strategy. This is consistent with a conceptual model in which the reservoir is dominated by extensive high conductive features that contributed in the early life of the field to good oil production before becoming the primary source of premature water breakthrough after a limited fraction of pore volume water was injected. The next level of analysis provided actual field evidence to support informed decisions to optimize the front runner horizontal wells development concept to cover wells length, orientation, vertical placement in the stratigraphy, spacing, pattern strategy and completion design. The findings enabled delivering updated field development plan covering the field life cycle to sustain and increase field oil production through adding ~ 200 additional wells and introducing more structured water flooding patterns in addition to establishing improved wells reservoir management practices.\u0000 This integrated study manifests the power, efficiency and value from data driven analysis to capture lessons learned from evolving wells and development concepts applied in a complex brown field over six decades. The workflow enabled the delivery of an updated field development plan and prod","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":"26 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84297913","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}
Giulia Ness, K. Sorbie, Ali Hassan Al Mesmari, S. Masalmeh
Wells producing from an oilfield in Abu Dhabi were investigated to understand the CaCO3 scaling risk at current production conditions, and to predict how the downhole and topside scaling potential will change during a planned CO2 WAG project. The results of this study will be used to design the correct scale inhibitor treatment for each production phase. A rigorous scale prediction procedure for pH dependent scales previously published by the authors was applied using a commercial integrated PVT and aqueous modelling software package to produce scale prediction profiles through the system. This procedure was applied to run many sensitivity studies and determine the impact of field data variables on the final scale predictions. These results were used to examine the scaling potential of current and future fluids by creating a diagnostic "what if" chart. Some of the main variables investigated include changes in operating pressure, CO2 and H2S concentrations and variable water cut. Scale prediction profiles through the entire system from reservoir to stock tank conditions were obtained using the above modelling procedure. The main findings in this study are: (i) That CaCO3 scale is not predicted to form at separator conditions under any of the current or future scenarios investigated for these wells. This is due to the high separator pressure which holds enough CO2 in solution to keep the pH low and prevent scale precipitation. (ii) The water at stock tank conditions was found to be the critical point in the system where the CaCO3 scaling risk is severe, and where preventative action must be taken. (iii) Implementing CO2 WAG does not affect CaCO3 scaling risk at separator conditions where fluids remain undersaturated. However, the additional CO2 dissolves more CaCO3 rock in the reservoir producing higher alkalinity fluids which result in more CaCO3 scale precipitation at stock tank conditions. (iv) Fluids entering the wellbore are likely to precipitate some CaCO3 (albeit at a fairly low saturation ratio, SR) due to a significant pressure drop and the relatively high temperature, and this is not associated with the-bubble point in this case. This downhole scaling potential becomes slightly worse by an increase in CO2 concentration during CO2 WAG operations.(v) Scale inhibitor may or may not be required to treat downhole fluids depending on the wellbore pressure drop, but it is always necessary to treat fluids downstream of the separator due to the very high scaling potential at stock tank conditions. By applying a rigorous scale prediction procedure, it was possible to study the impact of CO2 WAG on the risk of CaCO3 scale precipitation downhole and topside for this field. These results highlight the current threat downhole and at stock tank conditions in particular and show how this will worsen with the implementation of CO2 WAG and this will require a chemical treatment review.
{"title":"The Evolution of CaCO3 Scaling Potential in ADNOC Reservoirs Under Water Flooding and CO2 WAG Scenarios","authors":"Giulia Ness, K. Sorbie, Ali Hassan Al Mesmari, S. Masalmeh","doi":"10.2118/208193-ms","DOIUrl":"https://doi.org/10.2118/208193-ms","url":null,"abstract":"\u0000 Wells producing from an oilfield in Abu Dhabi were investigated to understand the CaCO3 scaling risk at current production conditions, and to predict how the downhole and topside scaling potential will change during a planned CO2 WAG project. The results of this study will be used to design the correct scale inhibitor treatment for each production phase.\u0000 A rigorous scale prediction procedure for pH dependent scales previously published by the authors was applied using a commercial integrated PVT and aqueous modelling software package to produce scale prediction profiles through the system. This procedure was applied to run many sensitivity studies and determine the impact of field data variables on the final scale predictions. These results were used to examine the scaling potential of current and future fluids by creating a diagnostic \"what if\" chart. Some of the main variables investigated include changes in operating pressure, CO2 and H2S concentrations and variable water cut.\u0000 Scale prediction profiles through the entire system from reservoir to stock tank conditions were obtained using the above modelling procedure. The main findings in this study are: (i) That CaCO3 scale is not predicted to form at separator conditions under any of the current or future scenarios investigated for these wells. This is due to the high separator pressure which holds enough CO2 in solution to keep the pH low and prevent scale precipitation. (ii) The water at stock tank conditions was found to be the critical point in the system where the CaCO3 scaling risk is severe, and where preventative action must be taken. (iii) Implementing CO2 WAG does not affect CaCO3 scaling risk at separator conditions where fluids remain undersaturated. However, the additional CO2 dissolves more CaCO3 rock in the reservoir producing higher alkalinity fluids which result in more CaCO3 scale precipitation at stock tank conditions. (iv) Fluids entering the wellbore are likely to precipitate some CaCO3 (albeit at a fairly low saturation ratio, SR) due to a significant pressure drop and the relatively high temperature, and this is not associated with the-bubble point in this case. This downhole scaling potential becomes slightly worse by an increase in CO2 concentration during CO2 WAG operations.(v) Scale inhibitor may or may not be required to treat downhole fluids depending on the wellbore pressure drop, but it is always necessary to treat fluids downstream of the separator due to the very high scaling potential at stock tank conditions.\u0000 By applying a rigorous scale prediction procedure, it was possible to study the impact of CO2 WAG on the risk of CaCO3 scale precipitation downhole and topside for this field. These results highlight the current threat downhole and at stock tank conditions in particular and show how this will worsen with the implementation of CO2 WAG and this will require a chemical treatment review.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":"45 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90176573","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}
AbdulMuqtadir Khan, Abdullah Binziad, Abdullah Subaii, D. Bannikov, Maksim Ponomarev, Sergey Parkhonyuk
Vertical wells require diagnostic techniques after minifrac pumping to interpret fracture height growth. This interpretation provides vital input to hydraulic fracturing redesign workflows. The temperature log is the most widely used technique to determine fracture height through cooldown analysis. A data science approach is proposed to leverage available measurements, automate the interpretation process, and enhance operational efficiency while keeping confidence in the fracturing design. Data from 55 wells were ingested to establish proof of concept.The selected geomechanical rock texture parameters were based on the fracturing theory of net-pressure-controlled height growth. Interpreted fracture height from input temperature cooldown analysis was merged with the structured dataset. The dataset was constructed at a high vertical depth of resolution of 0.5 to 1 ft. Openhole log data such as gamma-ray and bulk density helped to characterize the rock type, and calculated mechanical properties from acoustic logs such as in-situ stress and Young's modulus characterize the fracture geometry development. Moreover, injection rate, volume, and net pressure during the calibration treatment affect the fracture height growth. A machine learning (ML) workflow was applied to multiple openhole log parameters, which were integrated with minifrac calibration parameters along with the varying depth of the reservoir. The 55 wells datasets with a cumulative 120,000 rows were divided into training and testing with a ratio of 80:20. A comparative algorithm study was conducted on the test set with nine algorithms, and CatBoost showed the best results with an RMSE of 4.13 followed by Random Forest with 4.25. CatBoost models utilize both categorical and numerical data. Stress, gamma-ray, and bulk density parameters affected the fracture height analyzed from the post-fracturing temperature logs. Following successful implementation in the pilot phase, the model can be extended to horizontal wells to validate predictions from commercial simulators where stress calculations were unreliable or where stress did not entirely reflect changes in rock type. By coupling the geometry measurement technology with data analysis, a useful automated model was successfully developed to enhance operational efficiency without compromising any part of the workflow. The advanced algorithm can be used in any field where precise fracture placement of a hydraulic fracture contributes directly to production potential. Also, the model can play a critical role in cube development to optimize lateral landing and lateral density for exploration fields.
{"title":"Fracture Height Prediction Model Utilizing Openhole Logs, Mechanical Models, and Temperature Cooldown Analysis with Machine Learning Algorithms","authors":"AbdulMuqtadir Khan, Abdullah Binziad, Abdullah Subaii, D. Bannikov, Maksim Ponomarev, Sergey Parkhonyuk","doi":"10.2118/207975-ms","DOIUrl":"https://doi.org/10.2118/207975-ms","url":null,"abstract":"\u0000 Vertical wells require diagnostic techniques after minifrac pumping to interpret fracture height growth. This interpretation provides vital input to hydraulic fracturing redesign workflows. The temperature log is the most widely used technique to determine fracture height through cooldown analysis. A data science approach is proposed to leverage available measurements, automate the interpretation process, and enhance operational efficiency while keeping confidence in the fracturing design.\u0000 Data from 55 wells were ingested to establish proof of concept.The selected geomechanical rock texture parameters were based on the fracturing theory of net-pressure-controlled height growth. Interpreted fracture height from input temperature cooldown analysis was merged with the structured dataset. The dataset was constructed at a high vertical depth of resolution of 0.5 to 1 ft. Openhole log data such as gamma-ray and bulk density helped to characterize the rock type, and calculated mechanical properties from acoustic logs such as in-situ stress and Young's modulus characterize the fracture geometry development. Moreover, injection rate, volume, and net pressure during the calibration treatment affect the fracture height growth.\u0000 A machine learning (ML) workflow was applied to multiple openhole log parameters, which were integrated with minifrac calibration parameters along with the varying depth of the reservoir. The 55 wells datasets with a cumulative 120,000 rows were divided into training and testing with a ratio of 80:20. A comparative algorithm study was conducted on the test set with nine algorithms, and CatBoost showed the best results with an RMSE of 4.13 followed by Random Forest with 4.25. CatBoost models utilize both categorical and numerical data. Stress, gamma-ray, and bulk density parameters affected the fracture height analyzed from the post-fracturing temperature logs. Following successful implementation in the pilot phase, the model can be extended to horizontal wells to validate predictions from commercial simulators where stress calculations were unreliable or where stress did not entirely reflect changes in rock type.\u0000 By coupling the geometry measurement technology with data analysis, a useful automated model was successfully developed to enhance operational efficiency without compromising any part of the workflow. The advanced algorithm can be used in any field where precise fracture placement of a hydraulic fracture contributes directly to production potential. Also, the model can play a critical role in cube development to optimize lateral landing and lateral density for exploration fields.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90302097","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}
Instead of relying on analytical functions to approximate property relationships, this innovative hybrid neural network technique offers highly adaptive, full-function (!) predictions that can be applied to different subsurface data types ranging from (1.) core-to-log prediction (permeability), (2.) multivariate property maps (oil-saturated thickness maps), and, (3.) petrophysical properties from 3D seismic data (i.e., hydrocarbon pore volume, instantaneous velocity). For each scenario a separate example is shown. In case study 1, core measurements are used as the target array and well log data serve training. To analyze the uncertainty of predicted estimates, a second oilfield case study applies 100 iterations of log data from 350 wells to obtain P10-P50-P90 probabilities by randomly removing 40% (140 wells) for validation purposes. In a third case study elastic logs and a low-frequency model are used to predict seismic properties. KNN generates a high level of freedom operator with only one (or more) hidden layer(s). Iterative parameterization precludes that high correlation coefficients arise from overtraining. Because the key advantage of the Kolmogorov neural network (KNN) is to permit non-linear, full-function approximations of reservoir properties, the KNN approach provides a higher-fidelity solution in comparison to other linear or non-linear neural net regressions. KNN offers a fast-track alternative to classic reservoir property predictions from model-based seismic inversions by combining (a) Kolmogorov's Superposition Theorem and (b) principles of genetic inversion (Darwin's "Survival of the fittest") together with Tikhonov regularization and gradient theory. In practice, this is accomplished by minimizing an objective function on multiple and simultaneous outputs from full-function (via look-up table) Kolmogorov neural network runs. All case studies produce high correlations between actual and predicted properties when compared to other stochastic or deterministic inversions. For instance, in the log to seismic prediction better (simulated) resolution of neural network results can be discerned compared to traditional inversion results. Moreover, all blind tests match the overall shape of prominent log curve deflections with a higher degree of fidelity than from inversion. An important fringe benefit of KNN application is the observed increase in seismic resolution that by comparison falls between the seismic resolution of a model-based inversion and the simulated resolution from seismic stochastic inversion.
{"title":"New-Age Kolmogorov Full-Function Neural Network KNN Offers High-Fidelity Reservoir Predictions via Estimation of Core, Well Log, Map and Seismic Properties","authors":"I. Priezzhev, D. Danko, U. Strecker","doi":"10.2118/207575-ms","DOIUrl":"https://doi.org/10.2118/207575-ms","url":null,"abstract":"\u0000 Instead of relying on analytical functions to approximate property relationships, this innovative hybrid neural network technique offers highly adaptive, full-function (!) predictions that can be applied to different subsurface data types ranging from (1.) core-to-log prediction (permeability), (2.) multivariate property maps (oil-saturated thickness maps), and, (3.) petrophysical properties from 3D seismic data (i.e., hydrocarbon pore volume, instantaneous velocity). For each scenario a separate example is shown. In case study 1, core measurements are used as the target array and well log data serve training. To analyze the uncertainty of predicted estimates, a second oilfield case study applies 100 iterations of log data from 350 wells to obtain P10-P50-P90 probabilities by randomly removing 40% (140 wells) for validation purposes. In a third case study elastic logs and a low-frequency model are used to predict seismic properties. KNN generates a high level of freedom operator with only one (or more) hidden layer(s). Iterative parameterization precludes that high correlation coefficients arise from overtraining. Because the key advantage of the Kolmogorov neural network (KNN) is to permit non-linear, full-function approximations of reservoir properties, the KNN approach provides a higher-fidelity solution in comparison to other linear or non-linear neural net regressions. KNN offers a fast-track alternative to classic reservoir property predictions from model-based seismic inversions by combining (a) Kolmogorov's Superposition Theorem and (b) principles of genetic inversion (Darwin's \"Survival of the fittest\") together with Tikhonov regularization and gradient theory. In practice, this is accomplished by minimizing an objective function on multiple and simultaneous outputs from full-function (via look-up table) Kolmogorov neural network runs. All case studies produce high correlations between actual and predicted properties when compared to other stochastic or deterministic inversions. For instance, in the log to seismic prediction better (simulated) resolution of neural network results can be discerned compared to traditional inversion results. Moreover, all blind tests match the overall shape of prominent log curve deflections with a higher degree of fidelity than from inversion. An important fringe benefit of KNN application is the observed increase in seismic resolution that by comparison falls between the seismic resolution of a model-based inversion and the simulated resolution from seismic stochastic inversion.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":"129 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85750922","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. Ismailova, A. Abdukarimov, B. Mombekov, D. Delikesheva, L. Zerpa, Zhasulan Dairov
Wax deposition on inner surfaces of pipelines is a costly problem for the petroleum industry. This flow assurance problem is of particular interest during the production and transportation of waxy oils in cold environments. An understanding of known mechanisms and available thermodynamic models will be useful for the management and planning of mitigation strategies for wax deposition. This paper presents a critical review of wax prediction models used for estimation of wax deposition based on chemical hydrocarbon compositions and thermobaric condition. The comparative analysis is applied to highlight the effective mechanisms guiding the wax deposition, and how this knowledge can be used to model and provide solutions to reducing wax deposition issues. One group of thermodynamic models assume that the precipitated wax is a solid solution. These models are divided into two categories: ideal (Erickson and Pedersen models) and non-ideal solutions (Won and Coutinho models). In the other group of models, the wax phase consists of many solid phases (Lira-Galeana model). The authors summarized the limitations of the models, evaluated, and identified ways to represent the overview of existing thermodynamical models for predicting wax precipitation. Within the strong demand from industry, the results of this manuscript can aid to aspire engineers and researcher.
{"title":"A Comparative Evaluation of Thermodynamic Models for Prediction of Wax Deposition","authors":"J. Ismailova, A. Abdukarimov, B. Mombekov, D. Delikesheva, L. Zerpa, Zhasulan Dairov","doi":"10.2118/207984-ms","DOIUrl":"https://doi.org/10.2118/207984-ms","url":null,"abstract":"\u0000 Wax deposition on inner surfaces of pipelines is a costly problem for the petroleum industry. This flow assurance problem is of particular interest during the production and transportation of waxy oils in cold environments. An understanding of known mechanisms and available thermodynamic models will be useful for the management and planning of mitigation strategies for wax deposition. This paper presents a critical review of wax prediction models used for estimation of wax deposition based on chemical hydrocarbon compositions and thermobaric condition. The comparative analysis is applied to highlight the effective mechanisms guiding the wax deposition, and how this knowledge can be used to model and provide solutions to reducing wax deposition issues. One group of thermodynamic models assume that the precipitated wax is a solid solution. These models are divided into two categories: ideal (Erickson and Pedersen models) and non-ideal solutions (Won and Coutinho models). In the other group of models, the wax phase consists of many solid phases (Lira-Galeana model).\u0000 The authors summarized the limitations of the models, evaluated, and identified ways to represent the overview of existing thermodynamical models for predicting wax precipitation.\u0000 Within the strong demand from industry, the results of this manuscript can aid to aspire engineers and researcher.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":"49 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87588297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Major Overhauls (MOH) of major Rotating Equipment is an essential activity to ensure equipment and overall plant's productivity and reliability requirements are met. This submission summarizes Maintenance cost reduction and MOH extension benefits on an integrally geared centrifugal Instrument Air (IA) compressor through a first of its kind Predictive Maintenance (PdM) solution project in ADNOC. Appropriate planning for Major Overhauls (MOH) in accordance with OEM, company standards and international best practices are crucial steps. Digitalization continues to transform the industry, with enhancements to maintenance practices a fundamental aspect. Centralized Predictive Analytics & Diagnostics (CPAD) project is a first of its kind in ADNOC as it ventures into on one of the largest predictive maintenance projects in the oil & gas industry. CPAD enables Predictive Maintenance (PdM) through Advanced Pattern Recognition (APR) and Machine Learning (ML) technologies to effectively monitor & assess equipment performance and overall healthiness. Equipment performance is continuously assessed through the developed asset management predictive analytics tool. Through this tool, models associated with the equipment were evaluated to detect performance deviation from historical normal operating behavior. Any deviation from the historical norm would be flagged to indicate condition degradation and/or performance drop. Moreover, the software is configured to alert for subtle changes in the system behavior that are often an early warning sign of failure. This allows for early troubleshooting, planning and appropriate intervention by maintenance teams. Using the predictive analytics software solution, an MOH interval extension was implemented for an integrally geared centrifugal IA compressor installed at an ADNOC Gas Processing site. The compressor was due for MOH at its traditional fixed maintenance interval of 40,000 running hours in Nov 2019. Through this approach, the actual performance and condition of the compressor was assessed. Its process and equipment parameters (i.e. casing vibrations, bearing vibrations, bearing temperatures and lube oil supply temperature/pressure, etc.) were reviewed, which did not flag any abnormality. The compressor's performance had not deviated from the historical norm; indicating that the equipment was in a healthy condition and had no signs of performance degradation. With this insight, a 15 months extension of the MOH was achieved. Furthermore, a 30% maintenance cost reduction throughout the compressor's life cycle is projected while ensuring equipment's reliability and integrity are upheld. A total of 7 days maintenance down time including work force and materials planning for the MOH activities was deferred. The equipment remained in operation until its rescheduled date for MOH. Through the deployment of predictive analytics solutions, informed decisions can be made by maintenance professionals to challenge traditiona
{"title":"Predictive Asset Analytics: The Future of Maintenance","authors":"Hagar Rabia","doi":"10.2118/207616-ms","DOIUrl":"https://doi.org/10.2118/207616-ms","url":null,"abstract":"\u0000 Major Overhauls (MOH) of major Rotating Equipment is an essential activity to ensure equipment and overall plant's productivity and reliability requirements are met. This submission summarizes Maintenance cost reduction and MOH extension benefits on an integrally geared centrifugal Instrument Air (IA) compressor through a first of its kind Predictive Maintenance (PdM) solution project in ADNOC.\u0000 Appropriate planning for Major Overhauls (MOH) in accordance with OEM, company standards and international best practices are crucial steps. Digitalization continues to transform the industry, with enhancements to maintenance practices a fundamental aspect. Centralized Predictive Analytics & Diagnostics (CPAD) project is a first of its kind in ADNOC as it ventures into on one of the largest predictive maintenance projects in the oil & gas industry. CPAD enables Predictive Maintenance (PdM) through Advanced Pattern Recognition (APR) and Machine Learning (ML) technologies to effectively monitor & assess equipment performance and overall healthiness. Equipment performance is continuously assessed through the developed asset management predictive analytics tool. Through this tool, models associated with the equipment were evaluated to detect performance deviation from historical normal operating behavior. Any deviation from the historical norm would be flagged to indicate condition degradation and/or performance drop. Moreover, the software is configured to alert for subtle changes in the system behavior that are often an early warning sign of failure. This allows for early troubleshooting, planning and appropriate intervention by maintenance teams.\u0000 Using the predictive analytics software solution, an MOH interval extension was implemented for an integrally geared centrifugal IA compressor installed at an ADNOC Gas Processing site. The compressor was due for MOH at its traditional fixed maintenance interval of 40,000 running hours in Nov 2019. Through this approach, the actual performance and condition of the compressor was assessed. Its process and equipment parameters (i.e. casing vibrations, bearing vibrations, bearing temperatures and lube oil supply temperature/pressure, etc.) were reviewed, which did not flag any abnormality. The compressor's performance had not deviated from the historical norm; indicating that the equipment was in a healthy condition and had no signs of performance degradation. With this insight, a 15 months extension of the MOH was achieved. Furthermore, a 30% maintenance cost reduction throughout the compressor's life cycle is projected while ensuring equipment's reliability and integrity are upheld. A total of 7 days maintenance down time including work force and materials planning for the MOH activities was deferred. The equipment remained in operation until its rescheduled date for MOH.\u0000 Through the deployment of predictive analytics solutions, informed decisions can be made by maintenance professionals to challenge traditiona","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":"61 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88711677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yuanjun Li, R. Horne, A. Al Shmakhy, Tania Felix Menchaca
The problem of missing data is a frequent occurrence in well production history records. Due to network outage, facility maintenance or equipment failure, the time series production data measured from surface and downhole gauges can be intermittent. The fragmentary data are an obstacle for reservoir management. The incomplete dataset is commonly simplified by omitting all observations with missing values, which will lead to significant information loss. Thus, to fill the missing data gaps, in this study, we developed and tested several missing data imputation approaches using machine learning and deep learning methods. Traditional data imputation methods such as interpolation and counting most frequent values can introduce bias to the data as the correlations between features are not considered. Thus, in this study, we investigated several multivariate imputation algorithms that use the entire set of available data streams to estimate the missing values. The methods use a full suite of well measurements, including wellhead and downhole pressures, oil, water and gas flow rates, surface and downhole temperatures, choke settings, etc. Any parameter that has gaps in its recorded history can be imputed from the other available data streams. The models were tested on both synthetic and real datasets from operating Norwegian and Abu Dhabi reservoirs. Based on the characteristics of the field data, we introduced different types of continuous missing distributions, which are the combinations of single-multiple missing sections in a long-short time span, to the complete dataset. We observed that as the missing time span expands, the stability of the more successful methods can be kept to a threshold of 30% of the entire dataset. In addition, for a single missing section over a shorter period, which could represent a weather perturbation, most methods we tried were able to achieve high imputation accuracy. In the case of multiple missing sections over a longer time span, which is typical of gauge failures, other methods were better candidates to capture the overall correlation in the multivariate dataset. Most missing data problems addressed in our industry focus on single feature imputation. In this study, we developed an efficient procedure that enables fast reconstruction of the entire production dataset with multiple missing sections in different variables. Ultimately, the complete information can support the reservoir history matching process, production allocation, and develop models for reservoir performance prediction.
{"title":"Reconstruction of Missing Segments in Well Data History Using Data Analytics","authors":"Yuanjun Li, R. Horne, A. Al Shmakhy, Tania Felix Menchaca","doi":"10.2118/208137-ms","DOIUrl":"https://doi.org/10.2118/208137-ms","url":null,"abstract":"\u0000 The problem of missing data is a frequent occurrence in well production history records. Due to network outage, facility maintenance or equipment failure, the time series production data measured from surface and downhole gauges can be intermittent. The fragmentary data are an obstacle for reservoir management. The incomplete dataset is commonly simplified by omitting all observations with missing values, which will lead to significant information loss. Thus, to fill the missing data gaps, in this study, we developed and tested several missing data imputation approaches using machine learning and deep learning methods.\u0000 Traditional data imputation methods such as interpolation and counting most frequent values can introduce bias to the data as the correlations between features are not considered. Thus, in this study, we investigated several multivariate imputation algorithms that use the entire set of available data streams to estimate the missing values. The methods use a full suite of well measurements, including wellhead and downhole pressures, oil, water and gas flow rates, surface and downhole temperatures, choke settings, etc. Any parameter that has gaps in its recorded history can be imputed from the other available data streams.\u0000 The models were tested on both synthetic and real datasets from operating Norwegian and Abu Dhabi reservoirs. Based on the characteristics of the field data, we introduced different types of continuous missing distributions, which are the combinations of single-multiple missing sections in a long-short time span, to the complete dataset. We observed that as the missing time span expands, the stability of the more successful methods can be kept to a threshold of 30% of the entire dataset. In addition, for a single missing section over a shorter period, which could represent a weather perturbation, most methods we tried were able to achieve high imputation accuracy. In the case of multiple missing sections over a longer time span, which is typical of gauge failures, other methods were better candidates to capture the overall correlation in the multivariate dataset.\u0000 Most missing data problems addressed in our industry focus on single feature imputation. In this study, we developed an efficient procedure that enables fast reconstruction of the entire production dataset with multiple missing sections in different variables. Ultimately, the complete information can support the reservoir history matching process, production allocation, and develop models for reservoir performance prediction.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75274322","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. Ogienagbon, M. Khalifeh, Xinxiang Yang, E. Kuru
Formation of microannuli at the interface of cement-casing can create well integrity issues. X-ray CT and Optical microscopy are technological trends that may have potential for direct visualization of microannuli. CT has an advantage of providing non-destructive visualization of microannuli, but its resolution suffers with increase in casing thickness. Conversely, Optical microscopy has the potential of providing higher resolution needed to detect smaller sized microannuli; however, information about microannuli is limited to only a few sections where samples have been sliced. The objective of the current article is to describe a methodology to examine the interface of cement-casing. Experimental work was combined with literature review. This includes both direct visualization methods, evaluation of current trends to better understand the characteristics and geometric variation of relevant leakage paths. We generate test specimens consisting of cement plugs, various steel casing thickness and nano-coated aluminium casings. Hydraulic sealability tests were conducted by injecting water at the cement-casing interface. Flow rates are then interpreted in terms of microannuli aperture and direct visualization of the cement plug-casing interface by CT and Optical microscopy was implemented. The experimental findings of this article will form a basis for studying geometry and size of microannuli as well as modelling of fluid migration.
{"title":"Manuscript Title: Characterization of Microannuli at the Cement-Casing Interface: Development of Methodology","authors":"A. Ogienagbon, M. Khalifeh, Xinxiang Yang, E. Kuru","doi":"10.2118/207581-ms","DOIUrl":"https://doi.org/10.2118/207581-ms","url":null,"abstract":"\u0000 Formation of microannuli at the interface of cement-casing can create well integrity issues. X-ray CT and Optical microscopy are technological trends that may have potential for direct visualization of microannuli. CT has an advantage of providing non-destructive visualization of microannuli, but its resolution suffers with increase in casing thickness. Conversely, Optical microscopy has the potential of providing higher resolution needed to detect smaller sized microannuli; however, information about microannuli is limited to only a few sections where samples have been sliced. The objective of the current article is to describe a methodology to examine the interface of cement-casing. Experimental work was combined with literature review. This includes both direct visualization methods, evaluation of current trends to better understand the characteristics and geometric variation of relevant leakage paths. We generate test specimens consisting of cement plugs, various steel casing thickness and nano-coated aluminium casings. Hydraulic sealability tests were conducted by injecting water at the cement-casing interface. Flow rates are then interpreted in terms of microannuli aperture and direct visualization of the cement plug-casing interface by CT and Optical microscopy was implemented. The experimental findings of this article will form a basis for studying geometry and size of microannuli as well as modelling of fluid migration.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83468271","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}
R. Jeughale, K. Andrews, S. A. Al Ali, T. Toki, Hisaya Tanaka, Ryosuke Sato, J. Luzardo, G. Sarap, Saumit Chatterjee, Z. Meki
Drilling and completion operations in depleted reservoirs, are challenging due to narrow margin between pore and fracture pressures. Therefore, Ultra-Low Density Reservoir Drilling Fluid (RDF) with optimum parameters is required to drill these wells safely. Design and effective field application of a sound engineered fluid solution to fulfill these operational demands are described. Ultra-Low Density RDF NAF with minimal fluid invasion characteristics was developed after extensive lab testing, to cover the fluid density from 7.2 – 8.0 ppg. The fluid properties were optimized based on reservoir requirements and challenging bottom-hole conditions. The design criteria benchmarks and field application details are presented. Fluids were stress tested for drill solids, reservoir water and density increase contamination. Multi-segment collaboration and teamwork were key during job planning and on-site job execution, to achieve operational success. For the first time in UAE, a major Offshore Operator successfully applied an Ultra-Low Density RDF-NAF, which provided remarkable stability and performance. The fluid was tested in the lab with polymeric viscosifier alone and in combination with organophilic clay. In order to gain rheology during the initial mixing, about 3.0 ppb of organophilic clay were introduced to system along with the polymeric viscosifier. Later, all the new fluid batches were built with polymeric additives alone to achieve target properties. A total of 10,250 ft of 8 ½" horizontal section was drilled to section TD with record ROP compared to previous wells in the same field, with no fluids related complications. With limited support from the solid control equipment, the team managed to keep the density ranging from 7.5 ppg to 7.8 ppg at surface condition, using premixed dilution. Bridging was monitored through actual testing on location and successfully maintained the target PSD values throughout the section by splitting the flow on three shaker screen size combination. Due to non-operation related issues, hole was kept static for 20 days. After such long static time, 8 ½" drilling BHA was run to bottom smoothly precautionary breaking circulation every 5 stands. Finally, after successful logging operation, 6 5/8" LEL liner was set to TD and the well completed as planned. Success of this field application indicates that an Ultra-Low density fluid can be designed, run successfully and deliver exemplary performance. Lessons learned are compared with conceptual design for future optimization. Laboratory test results are presented, which formed the basis of a seamless planned field application.
{"title":"Development and First Application of an Ultra-Low Density Non-Aqueous Reservoir Drilling Fluid in the United Arab Emirates: A Viable Technical Solution to Drill Maximum Reservoir Contact Wells Across Depleted Reservoirs","authors":"R. Jeughale, K. Andrews, S. A. Al Ali, T. Toki, Hisaya Tanaka, Ryosuke Sato, J. Luzardo, G. Sarap, Saumit Chatterjee, Z. Meki","doi":"10.2118/207257-ms","DOIUrl":"https://doi.org/10.2118/207257-ms","url":null,"abstract":"\u0000 Drilling and completion operations in depleted reservoirs, are challenging due to narrow margin between pore and fracture pressures. Therefore, Ultra-Low Density Reservoir Drilling Fluid (RDF) with optimum parameters is required to drill these wells safely. Design and effective field application of a sound engineered fluid solution to fulfill these operational demands are described.\u0000 Ultra-Low Density RDF NAF with minimal fluid invasion characteristics was developed after extensive lab testing, to cover the fluid density from 7.2 – 8.0 ppg. The fluid properties were optimized based on reservoir requirements and challenging bottom-hole conditions. The design criteria benchmarks and field application details are presented. Fluids were stress tested for drill solids, reservoir water and density increase contamination. Multi-segment collaboration and teamwork were key during job planning and on-site job execution, to achieve operational success.\u0000 For the first time in UAE, a major Offshore Operator successfully applied an Ultra-Low Density RDF-NAF, which provided remarkable stability and performance. The fluid was tested in the lab with polymeric viscosifier alone and in combination with organophilic clay. In order to gain rheology during the initial mixing, about 3.0 ppb of organophilic clay were introduced to system along with the polymeric viscosifier. Later, all the new fluid batches were built with polymeric additives alone to achieve target properties. A total of 10,250 ft of 8 ½\" horizontal section was drilled to section TD with record ROP compared to previous wells in the same field, with no fluids related complications. With limited support from the solid control equipment, the team managed to keep the density ranging from 7.5 ppg to 7.8 ppg at surface condition, using premixed dilution.\u0000 Bridging was monitored through actual testing on location and successfully maintained the target PSD values throughout the section by splitting the flow on three shaker screen size combination. Due to non-operation related issues, hole was kept static for 20 days. After such long static time, 8 ½\" drilling BHA was run to bottom smoothly precautionary breaking circulation every 5 stands. Finally, after successful logging operation, 6 5/8\" LEL liner was set to TD and the well completed as planned.\u0000 Success of this field application indicates that an Ultra-Low density fluid can be designed, run successfully and deliver exemplary performance. Lessons learned are compared with conceptual design for future optimization. Laboratory test results are presented, which formed the basis of a seamless planned field application.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78930264","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}
Rylan Paul Dsouza, R. Cornwall, Alan David Brodie, Pedro Patela, H. Daghmouni, Mohammad Hariz Arakkalakkam, Venkata Praveen Kumar Boni, Asif Khan Haq Dad Khan
This paper describes an innovative solution for the safe and effective management of wells with unplanned sustained annulus pressure (SAP). The solution restores double barrier integrity in the well and provides reliable real time annulus pressure and temperature data. It also has the functionality to autonomously bleed-off the annulus pressure at a pre-determined set point. As a result, the nature and severity of the SAP can be better understood, and in many cases wells that would otherwise have been closed in awaiting workover can remain in production.
{"title":"Case Study of a Novel Autonomous Real-Time Monitoring, Control and Analysis System, to Maximize Production Uptime on Sustained Annulus Pressure Wells, While Improving HSE and Compliance with Double Barrier Well Integrity Policies","authors":"Rylan Paul Dsouza, R. Cornwall, Alan David Brodie, Pedro Patela, H. Daghmouni, Mohammad Hariz Arakkalakkam, Venkata Praveen Kumar Boni, Asif Khan Haq Dad Khan","doi":"10.2118/208114-ms","DOIUrl":"https://doi.org/10.2118/208114-ms","url":null,"abstract":"\u0000 This paper describes an innovative solution for the safe and effective management of wells with unplanned sustained annulus pressure (SAP). The solution restores double barrier integrity in the well and provides reliable real time annulus pressure and temperature data. It also has the functionality to autonomously bleed-off the annulus pressure at a pre-determined set point. As a result, the nature and severity of the SAP can be better understood, and in many cases wells that would otherwise have been closed in awaiting workover can remain in production.","PeriodicalId":10959,"journal":{"name":"Day 3 Wed, November 17, 2021","volume":"34 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80682962","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：