Oil and gas drilling is a field practice with risks and uncertainties. Uncertainty and ambiguity of formation conditions often cause downhole accidents such as borehole wall instability, stuck drilling, blowout, etc., and also pose a threat to drilling safety.Due to the incorrect understanding of the objective environment and the wrong decision of subjective consciousness; it caused complex underground conditions and serious accidents. Collapse stuck is the worst kind of accident in stuck stuck. The procedures to deal with this kind of accident are the most complicated, the most time-consuming, the most risky, and even the whole or part of the wellbore may be scrapped, so we should try our best to avoid this accident during the drilling process.Artificial Neural Networks (ANNs for short) is a mathematical model of algorithms that imitate the behavioral characteristics of animal neural networks and perform distributed parallel information processing. This kind of network depends on the complexity of the system and adjusts the interconnection relationship between a large numbers of internal nodes to achieve the purpose of processing information, and has the ability of self-learning and self-adaptation. This paper analyzes the causes of collapse stuck, the mechanical mechanism of drilling fluid wettability on the stability of mud shale formation wall.A surface wetting reversal agent added to the drilling fluid system was used to change the wettability of the shale surface.The mechanism analysis and research results of changing the wettability to change the mechanical properties of the shale fracture surface were applied to the actual production of the collapsed drilling rig.Through the change of drilling parameters, the risk of stuck drilling is predicted in advance, the drilling speed is increased, the drilling time loss caused by stuck drilling is reduced, and the drilling cycle and cost are saved.
{"title":"Treatment and Prevention of Stuck Pipe Based on Artificial Neural Networks Analysis","authors":"Qi Zhu","doi":"10.4043/31693-ms","DOIUrl":"https://doi.org/10.4043/31693-ms","url":null,"abstract":"\u0000 Oil and gas drilling is a field practice with risks and uncertainties. Uncertainty and ambiguity of formation conditions often cause downhole accidents such as borehole wall instability, stuck drilling, blowout, etc., and also pose a threat to drilling safety.Due to the incorrect understanding of the objective environment and the wrong decision of subjective consciousness; it caused complex underground conditions and serious accidents.\u0000 Collapse stuck is the worst kind of accident in stuck stuck. The procedures to deal with this kind of accident are the most complicated, the most time-consuming, the most risky, and even the whole or part of the wellbore may be scrapped, so we should try our best to avoid this accident during the drilling process.Artificial Neural Networks (ANNs for short) is a mathematical model of algorithms that imitate the behavioral characteristics of animal neural networks and perform distributed parallel information processing.\u0000 This kind of network depends on the complexity of the system and adjusts the interconnection relationship between a large numbers of internal nodes to achieve the purpose of processing information, and has the ability of self-learning and self-adaptation.\u0000 This paper analyzes the causes of collapse stuck, the mechanical mechanism of drilling fluid wettability on the stability of mud shale formation wall.A surface wetting reversal agent added to the drilling fluid system was used to change the wettability of the shale surface.The mechanism analysis and research results of changing the wettability to change the mechanical properties of the shale fracture surface were applied to the actual production of the collapsed drilling rig.Through the change of drilling parameters, the risk of stuck drilling is predicted in advance, the drilling speed is increased, the drilling time loss caused by stuck drilling is reduced, and the drilling cycle and cost are saved.","PeriodicalId":11217,"journal":{"name":"Day 4 Fri, March 25, 2022","volume":"19 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84083796","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. A. Md Yusof, Iqmal Irsyad Mohammad Fuad, Nur Asyraf Md Akhir, Mohamad Arif Ibrahim, M. A. Mohamed, D. A. Maharsi
CO2 sequestration in saline aquifer is a promising approach to effectively secure the anthropogenic CO2 gas. Complex fluid-rock interaction processes take place during the injection of CO2 would disrupt the thermodynamic equilibrium of CO2 injectivity at near wellbore. In this study, a comprehensive investigation on the CO2 injectivity change of different injection flow rates and brine salinity was performed using core flooding experiments, permeability change prediction using (Kozeny-Carman and Hagen-Poiseuille models) and artificial neural network model (ANN). Core flooding experiments revealed CO2 injectivity impairment increased with increasing brine salinity, with Hagen-Poiseuille being the most fitted model with R2 of 0.935. However, all porosity-permeability models failed to give a good prediction at changing injection flow rate with R2 is well below 0.4. The adopted ANN model showed good agreement with the experimental data at varying brine salinity and injection flow rates. The utilization of ANN for such prediction procedure can reduce the number of experiment, operating cost and provide reasonable predictions compared to existing analytical models.
{"title":"Experimental Investigation, Porosity-Permeability Modelling, and Artificial Neural Network Prediction of CO2 Injectivity Change for Sequestration","authors":"M. A. Md Yusof, Iqmal Irsyad Mohammad Fuad, Nur Asyraf Md Akhir, Mohamad Arif Ibrahim, M. A. Mohamed, D. A. Maharsi","doi":"10.4043/31666-ms","DOIUrl":"https://doi.org/10.4043/31666-ms","url":null,"abstract":"\u0000 CO2 sequestration in saline aquifer is a promising approach to effectively secure the anthropogenic CO2 gas. Complex fluid-rock interaction processes take place during the injection of CO2 would disrupt the thermodynamic equilibrium of CO2 injectivity at near wellbore. In this study, a comprehensive investigation on the CO2 injectivity change of different injection flow rates and brine salinity was performed using core flooding experiments, permeability change prediction using (Kozeny-Carman and Hagen-Poiseuille models) and artificial neural network model (ANN). Core flooding experiments revealed CO2 injectivity impairment increased with increasing brine salinity, with Hagen-Poiseuille being the most fitted model with R2 of 0.935. However, all porosity-permeability models failed to give a good prediction at changing injection flow rate with R2 is well below 0.4. The adopted ANN model showed good agreement with the experimental data at varying brine salinity and injection flow rates. The utilization of ANN for such prediction procedure can reduce the number of experiment, operating cost and provide reasonable predictions compared to existing analytical models.","PeriodicalId":11217,"journal":{"name":"Day 4 Fri, March 25, 2022","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81783063","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}
On the 11th of February 2015 a pump room explosion on the Floating Production Storage and Offloading (FPSO) Cidade de São Mateus killed nine persons, injured twenty-six more and crippled the unit, requiring that it be removed to a yard to effect repairs. In 2020 the FPSO Owner confirmed that the FPSO Charter and the Services Agreements with the respective Oil and Gas Company had reached their final terms and the unit remained in lay-up in Singapore. Seven years on from this event, although the causes leading up to the incident are well understood within some sections of the oil and gas industry, along with the availability of various high-quality publications on the subject, there remains no consolidated guidance from Classification Societies, regulatory authorities, insurers nor industry advisory groups on how to prevent a reoccurrence of a similar event. Indeed, some FSO/FPSO operators have not implemented the required changes within their existing fleet or within their subsequently developed facilities. This paper provides a synopsis of the incident onboard the FPSO Cidade de São Mateus (CdSM) and the root causes of the accident. From those findings, it describes the design and operational measures some Floating Storage and Offloading (FSO)/FPSO owner/operators and oil and gas companies have implemented to further reduce the potential risks associated with the use of pump rooms. These measures are subsequently visualised by way of a bow-tie diagram. An overview of current Classification Society rules and regulatory authority requirements relating to pump rooms are shown and discussed. Furthermore, the paper demonstrates some of the flaws that still exist in the engineering and operation of contemporary FSO/FPSO pump rooms. As a continuation from those defects, several FPSO pump room incidents that have occurred after 2015, which could have led to a similar catastrophic pump room explosion to that of CdSM, are explained. Finally, the paper contains a recommended basis for design and operational guidance to owners and operators of FSO/FPSOs with pump rooms.
2015年2月11日，浮式生产储卸(FPSO) Cidade de s o Mateus的泵房发生爆炸，造成9人死亡，26人受伤，并导致该装置瘫痪，需要将其移至院子进行维修。2020年，FPSO所有者确认，与各自的石油和天然气公司签订的FPSO租约和服务协议已达成最终条款，该装置仍在新加坡停工。事故发生7年后，尽管油气行业的一些部门对事故原因已经有了很好的了解，也有了关于该主题的各种高质量出版物，但船级社、监管机构、保险公司和行业咨询团体仍然没有关于如何防止类似事件再次发生的统一指导。事实上，一些FSO/FPSO运营商并没有在他们现有的船队或随后开发的设施中实施所需的改变。本文简要介绍了FPSO Cidade de s o Mateus (CdSM)上发生的事故以及事故的根本原因。根据这些发现，本文描述了一些浮式储卸(FSO)/FPSO所有者/运营商以及油气公司为进一步降低与泵房使用相关的潜在风险而实施的设计和操作措施。这些措施随后通过领结图的方式可视化。当前船级社的规则和有关泵房监管当局的要求的概述显示和讨论。此外，本文还展示了当代浮式储油船/浮式储油船泵房在工程和操作中仍然存在的一些缺陷。作为这些缺陷的延续，2015年之后发生了几起FPSO泵室事故，这些事故可能导致与CdSM类似的灾难性泵室爆炸。最后，本文为带有泵房的FSO/ fpso的船东和运营商提供了设计和操作指导的建议基础。
{"title":"Guidance for Design and Operation of Pump Rooms Following the Explosion on the FPSO Cidade de São Mateus","authors":"M. Duddy, A. Ronza, Noorhafizal Zakariah","doi":"10.4043/31639-ms","DOIUrl":"https://doi.org/10.4043/31639-ms","url":null,"abstract":"\u0000 On the 11th of February 2015 a pump room explosion on the Floating Production Storage and Offloading (FPSO) Cidade de São Mateus killed nine persons, injured twenty-six more and crippled the unit, requiring that it be removed to a yard to effect repairs. In 2020 the FPSO Owner confirmed that the FPSO Charter and the Services Agreements with the respective Oil and Gas Company had reached their final terms and the unit remained in lay-up in Singapore.\u0000 Seven years on from this event, although the causes leading up to the incident are well understood within some sections of the oil and gas industry, along with the availability of various high-quality publications on the subject, there remains no consolidated guidance from Classification Societies, regulatory authorities, insurers nor industry advisory groups on how to prevent a reoccurrence of a similar event. Indeed, some FSO/FPSO operators have not implemented the required changes within their existing fleet or within their subsequently developed facilities.\u0000 This paper provides a synopsis of the incident onboard the FPSO Cidade de São Mateus (CdSM) and the root causes of the accident. From those findings, it describes the design and operational measures some Floating Storage and Offloading (FSO)/FPSO owner/operators and oil and gas companies have implemented to further reduce the potential risks associated with the use of pump rooms. These measures are subsequently visualised by way of a bow-tie diagram. An overview of current Classification Society rules and regulatory authority requirements relating to pump rooms are shown and discussed. Furthermore, the paper demonstrates some of the flaws that still exist in the engineering and operation of contemporary FSO/FPSO pump rooms. As a continuation from those defects, several FPSO pump room incidents that have occurred after 2015, which could have led to a similar catastrophic pump room explosion to that of CdSM, are explained. Finally, the paper contains a recommended basis for design and operational guidance to owners and operators of FSO/FPSOs with pump rooms.","PeriodicalId":11217,"journal":{"name":"Day 4 Fri, March 25, 2022","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89437275","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}
Sajith Kumar Govindan Nampoothiri, D. Pawar, K. W. Mak
Mechanically Lined Pipe (MLP) is a pipe with a layer of corrosion resistant alloy (CRA) mechanically bonded to carbon steel pipe. MLP is mostly used in offshore pipelines for HPHT (high pressure and high temperature) conditions with corrosive contents. These type of pipe joints are largely used for HPHT offshore pipelines conveying corrosive fluids, but mostly limited to ‘non-buckle’ zones due to the concerns of liner wrinkling, fatigue damage and triple point failure resulting from high strain and stress ranges in the lateral buckle zones. Recently, MLP's have been used for the entire length, including in the buckle zones of a dual HPHT multi-phase infield flowlines. Planned buckles have been designed at specific intervals to ensure controlled lateral buckling. Extensive qualification procedures are required to be undertaken to validate the use of these types of pipe at the buckle zones with high strains and stress ranges during repeated shut down cycles. The qualification procedure for MLP at the buckle zone are discussed in this paper. The paper also presents an optimized formula, calibrated based on the qualification procedure and Finite Element (FE) analysis for determining the optimized onset strain for liner wrinkling. Initially, a thorough review of the concerns in the industry for employing MLP at the lateral buckle zone was undertaken and include the requirements for qualification/testing currently specified in the industry, such as bend test/liner wrinkling, and and full-scale fatigue tests. Liner wrinkling is caused by excessive compressive strain that occurs during de-pressurisation of the flowline. To assess the risks of wrinkling, the compressive strain for the onset of liner wrinkling is evaluated using analytical calculations. This is followed by a comprehensive discussion on the qualification steps adopted for addressing the fatigue, triple point failure and wrinkle that enabled to use MLP at buckling and fatigue sensitive zones. The qualification procedure undertaken has demonstrated better fatigue performance and wrinkling onset strains considerably higher than those evaluated analytically. The findings from the qualification and material tests are used to calibrate the ABAQUS FE analysis simulations to obtain optimised wrinkling onset criteria. An optimized wrinkling onset criteria for a range of D/t ratios defined based on Finite Element (FE) analysis results. In summary, this paper provides reliable guidance for the qualification of MLP at the lateral buckle zones. The paper also presents the methodology and results for determining an optimized strain for the onset of liner wrinkling based on ABAQUS FE analysis.
{"title":"Design of Mechanically Lined Pipe MLP for Lateral Buckle Zones – MLP Qualification and Calibrated Wrinkling Criteria Using FEA","authors":"Sajith Kumar Govindan Nampoothiri, D. Pawar, K. W. Mak","doi":"10.4043/31541-ms","DOIUrl":"https://doi.org/10.4043/31541-ms","url":null,"abstract":"\u0000 Mechanically Lined Pipe (MLP) is a pipe with a layer of corrosion resistant alloy (CRA) mechanically bonded to carbon steel pipe. MLP is mostly used in offshore pipelines for HPHT (high pressure and high temperature) conditions with corrosive contents. These type of pipe joints are largely used for HPHT offshore pipelines conveying corrosive fluids, but mostly limited to ‘non-buckle’ zones due to the concerns of liner wrinkling, fatigue damage and triple point failure resulting from high strain and stress ranges in the lateral buckle zones.\u0000 Recently, MLP's have been used for the entire length, including in the buckle zones of a dual HPHT multi-phase infield flowlines. Planned buckles have been designed at specific intervals to ensure controlled lateral buckling. Extensive qualification procedures are required to be undertaken to validate the use of these types of pipe at the buckle zones with high strains and stress ranges during repeated shut down cycles. The qualification procedure for MLP at the buckle zone are discussed in this paper. The paper also presents an optimized formula, calibrated based on the qualification procedure and Finite Element (FE) analysis for determining the optimized onset strain for liner wrinkling.\u0000 Initially, a thorough review of the concerns in the industry for employing MLP at the lateral buckle zone was undertaken and include the requirements for qualification/testing currently specified in the industry, such as bend test/liner wrinkling, and and full-scale fatigue tests.\u0000 Liner wrinkling is caused by excessive compressive strain that occurs during de-pressurisation of the flowline. To assess the risks of wrinkling, the compressive strain for the onset of liner wrinkling is evaluated using analytical calculations. This is followed by a comprehensive discussion on the qualification steps adopted for addressing the fatigue, triple point failure and wrinkle that enabled to use MLP at buckling and fatigue sensitive zones.\u0000 The qualification procedure undertaken has demonstrated better fatigue performance and wrinkling onset strains considerably higher than those evaluated analytically. The findings from the qualification and material tests are used to calibrate the ABAQUS FE analysis simulations to obtain optimised wrinkling onset criteria. An optimized wrinkling onset criteria for a range of D/t ratios defined based on Finite Element (FE) analysis results. In summary, this paper provides reliable guidance for the qualification of MLP at the lateral buckle zones. The paper also presents the methodology and results for determining an optimized strain for the onset of liner wrinkling based on ABAQUS FE analysis.","PeriodicalId":11217,"journal":{"name":"Day 4 Fri, March 25, 2022","volume":"38 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89149070","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}
When a tube ruptures in a shell and tube heat exchanger, the effect of liquid hammering may induce very high transient pressure on shell side due to the leaked mass from tube side travelling to shell side. This article describes a novel technical approach to adequately translate the volume displacement effect by the leaked mass from tube side onto the shell side holdup volume in the unit. The transient pressure from the liquid hammering effect is then accurately predicted by a first principle simulator, and proper mitigation measures may be identified to meet safety requirement while minimizing capital cost. While assuming tube side pressure at tube sheet location remains constant, the mass flow rate profile through the ruptured tube as function of downstream (shell side) local pressure is determined according to industry standards and/or project standards. This profile is then transformed to volumetric flow rate profile displacing shell side hold up volume as function of time in milliseconds time scale. The resulting volumetric profile is then applied to a first principle simulator to predict the transient pressure as a result of liquid hammering effect. The mitigation measure, if any, may be at the same time tested and refined by the simulator. The constraints imposed by the project are iteratively evaluated, and adjusted if necessary, to achieve the best reconciliation among factors of capital cost, safety requirement and project schedule etc. In this article, a compressor discharge after cooler of double shells, with one stacked on top of another, is used for the discussion. Furthermore, the scope of the model extends to include the surrounding piping, and include any considerable lead line length to the relief device. The details of the exchanger geometry, including internal components such as the baffles, bundle type, nozzle etc. are modeled with adequate resolution. The pressure wave propagation along the path of shell side flow in milliseconds time scale are simulated and the localized peak pressures are reported. The high peak pressure necessitates a mitigation measure to be implemented, while maintaining the proposed shell side design pressure to stay for this particular unit. Note that this type of study, for safety concerns, it could result in elevated shell side design pressure, even after considering mitigation measure, leading to major changes to associated supply and return piping, resulting in cost and schedule delays. The technical approach illustrated in this article describes the work flow to transform the mapping of mass flow rate as a function of pressure to volumetric flow rate as a function of time in milliseconds time scale, a technique considered as the first time to be introduced into the practice. The approach increases the fidelity of the study greatly, resulting in reduced capital cost as much as possible, while largely mitigating safety concerns. The approach also affords us to test multiple configurations o
{"title":"Safer Design by Tube Rupture Analysis","authors":"M. Kulkarni, Tongyuan Song","doi":"10.4043/31337-ms","DOIUrl":"https://doi.org/10.4043/31337-ms","url":null,"abstract":"\u0000 When a tube ruptures in a shell and tube heat exchanger, the effect of liquid hammering may induce very high transient pressure on shell side due to the leaked mass from tube side travelling to shell side. This article describes a novel technical approach to adequately translate the volume displacement effect by the leaked mass from tube side onto the shell side holdup volume in the unit. The transient pressure from the liquid hammering effect is then accurately predicted by a first principle simulator, and proper mitigation measures may be identified to meet safety requirement while minimizing capital cost.\u0000 While assuming tube side pressure at tube sheet location remains constant, the mass flow rate profile through the ruptured tube as function of downstream (shell side) local pressure is determined according to industry standards and/or project standards. This profile is then transformed to volumetric flow rate profile displacing shell side hold up volume as function of time in milliseconds time scale. The resulting volumetric profile is then applied to a first principle simulator to predict the transient pressure as a result of liquid hammering effect. The mitigation measure, if any, may be at the same time tested and refined by the simulator.\u0000 The constraints imposed by the project are iteratively evaluated, and adjusted if necessary, to achieve the best reconciliation among factors of capital cost, safety requirement and project schedule etc.\u0000 In this article, a compressor discharge after cooler of double shells, with one stacked on top of another, is used for the discussion. Furthermore, the scope of the model extends to include the surrounding piping, and include any considerable lead line length to the relief device. The details of the exchanger geometry, including internal components such as the baffles, bundle type, nozzle etc. are modeled with adequate resolution. The pressure wave propagation along the path of shell side flow in milliseconds time scale are simulated and the localized peak pressures are reported.\u0000 The high peak pressure necessitates a mitigation measure to be implemented, while maintaining the proposed shell side design pressure to stay for this particular unit. Note that this type of study, for safety concerns, it could result in elevated shell side design pressure, even after considering mitigation measure, leading to major changes to associated supply and return piping, resulting in cost and schedule delays.\u0000 The technical approach illustrated in this article describes the work flow to transform the mapping of mass flow rate as a function of pressure to volumetric flow rate as a function of time in milliseconds time scale, a technique considered as the first time to be introduced into the practice. The approach increases the fidelity of the study greatly, resulting in reduced capital cost as much as possible, while largely mitigating safety concerns.\u0000 The approach also affords us to test multiple configurations o","PeriodicalId":11217,"journal":{"name":"Day 4 Fri, March 25, 2022","volume":"386 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80774548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The equivalent circulating density (ECD) is crucial in avoiding fluid losses or kicks while drilling. It's more critical in wells where the pore pressure gradient is close to the fracture pressure gradient. The conservation of mass and momentum determine the ECD, but this method does not account for other factors like torque, rotating speed, weight on bit, etc. These may affect the ECD directly or indirectly. The aim of this study is a practicality to predict the ECD using various machine learning techniques and to determine their effectiveness. The complete drilling dataset of an oil well from Texas was acquired. Over 16000 data points were obtained after the removal of the null values. The data was prepared by scaling it and conducting principal component analysis (PCA). PCA reduced the dimensionality of the dataset while retaining the information. Following this, five different machine learning regression techniques were used to predict the equivalent circulation density, namely, XGBoost, Random Forest, Support Vector Machine, Decision Tree, and Elastic net regression. The performance of these techniques was judged by comparing their R2 scores, mean squared errors (MSE), and root mean squared errors (RMSE). The results showed that ECD prediction through all the above machine learning techniques is a vital reality. Random forest regression emerged superior from the different methods used, illustrating the highest R2 score and the lowest MSE and RMSE. Its R2 for our model was 0.992, which is an excellent fit. It was followed by SVM, which had the second-lowest RMSE and an R2 of 0.987, close to the random forest technique. Elastic Net, Decision tree, and XG Boost in the respective order were at the bottom of the pool. Machine learning is a powerful tool at our disposal to effectively predict quantities in real-time that directly or indirectly depend on several parameters. It can even be effective when no direct correlation between the quantities is known. Thus, machine learning can significantly enhance our ability to optimize drilling operations by having quicker and more accurate predictions. The work shown in this study, if implemented, can provide the crew more time to respond to situations such as the occurrence of kicks and thus will lead to safer operations.
{"title":"Assessment of Machine Learning Techniques for Real-Time Prediction of Equivalent Circulating Density","authors":"Vishnu Roy, Anurag Pandey, Anika Saxena, Shivanjali Sharma","doi":"10.4043/31523-ms","DOIUrl":"https://doi.org/10.4043/31523-ms","url":null,"abstract":"\u0000 The equivalent circulating density (ECD) is crucial in avoiding fluid losses or kicks while drilling. It's more critical in wells where the pore pressure gradient is close to the fracture pressure gradient. The conservation of mass and momentum determine the ECD, but this method does not account for other factors like torque, rotating speed, weight on bit, etc. These may affect the ECD directly or indirectly. The aim of this study is a practicality to predict the ECD using various machine learning techniques and to determine their effectiveness.\u0000 The complete drilling dataset of an oil well from Texas was acquired. Over 16000 data points were obtained after the removal of the null values. The data was prepared by scaling it and conducting principal component analysis (PCA). PCA reduced the dimensionality of the dataset while retaining the information. Following this, five different machine learning regression techniques were used to predict the equivalent circulation density, namely, XGBoost, Random Forest, Support Vector Machine, Decision Tree, and Elastic net regression. The performance of these techniques was judged by comparing their R2 scores, mean squared errors (MSE), and root mean squared errors (RMSE).\u0000 The results showed that ECD prediction through all the above machine learning techniques is a vital reality. Random forest regression emerged superior from the different methods used, illustrating the highest R2 score and the lowest MSE and RMSE. Its R2 for our model was 0.992, which is an excellent fit. It was followed by SVM, which had the second-lowest RMSE and an R2 of 0.987, close to the random forest technique. Elastic Net, Decision tree, and XG Boost in the respective order were at the bottom of the pool.\u0000 Machine learning is a powerful tool at our disposal to effectively predict quantities in real-time that directly or indirectly depend on several parameters. It can even be effective when no direct correlation between the quantities is known. Thus, machine learning can significantly enhance our ability to optimize drilling operations by having quicker and more accurate predictions. The work shown in this study, if implemented, can provide the crew more time to respond to situations such as the occurrence of kicks and thus will lead to safer operations.","PeriodicalId":11217,"journal":{"name":"Day 4 Fri, March 25, 2022","volume":"139 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78947091","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}
Subsea storage is one of main technology in "Subsea Factory" concept that could significantly lower down the field life cycle cost especially in subsea development. An established qualification approach should enable Project Management Team (PMT) to evaluate the technology maturity, aims to reduce significant availability impact during deployment and operational phase. This paper describes the qualification approach adopted to qualify the subsea storage technology to achieve technology readiness level (TRL) 4 as per API 17Q framework, prior to pilot testing at offshore installation. One of important step is to evaluates whether the subsystem and critical components of subsea storage has an impact on Design, Operations and Maintenance. In this context, the evaluation considers the credible failure mode, mechanism, cause, and effect in relation to Risk Priority Number (RPN). Failure Mode, Effect and Criticality Analysis (FMECA) has been applied to evaluate the subsystem and critical component. The higher RPN indicates that the susceptible subsystem and critical components require special attention for improvement. The results pointed out that material for both top and bottom centre pipe flanges should have an ability to operate in cyclical loading and suitable for inspection, maintenance, and replacement program. These results suggest that recommended method of FMECA can be adopted during TRL assessment. Focus also should be on unlisted components which are not part of this assessment including design adequacy and stringent quality assurance and control management system, operations integrity, and maintenance comprehensiveness.
{"title":"Technology Qualification: FMECA for Mitigating Potential Failure in Subsea Storage System","authors":"Mohd Azizul Hakim Zainal Abidin, A. Suleiman","doi":"10.4043/31608-ms","DOIUrl":"https://doi.org/10.4043/31608-ms","url":null,"abstract":"\u0000 Subsea storage is one of main technology in \"Subsea Factory\" concept that could significantly lower down the field life cycle cost especially in subsea development. An established qualification approach should enable Project Management Team (PMT) to evaluate the technology maturity, aims to reduce significant availability impact during deployment and operational phase. This paper describes the qualification approach adopted to qualify the subsea storage technology to achieve technology readiness level (TRL) 4 as per API 17Q framework, prior to pilot testing at offshore installation. One of important step is to evaluates whether the subsystem and critical components of subsea storage has an impact on Design, Operations and Maintenance. In this context, the evaluation considers the credible failure mode, mechanism, cause, and effect in relation to Risk Priority Number (RPN).\u0000 Failure Mode, Effect and Criticality Analysis (FMECA) has been applied to evaluate the subsystem and critical component. The higher RPN indicates that the susceptible subsystem and critical components require special attention for improvement. The results pointed out that material for both top and bottom centre pipe flanges should have an ability to operate in cyclical loading and suitable for inspection, maintenance, and replacement program.\u0000 These results suggest that recommended method of FMECA can be adopted during TRL assessment. Focus also should be on unlisted components which are not part of this assessment including design adequacy and stringent quality assurance and control management system, operations integrity, and maintenance comprehensiveness.","PeriodicalId":11217,"journal":{"name":"Day 4 Fri, March 25, 2022","volume":"83 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88490472","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. R. Amir Rashidi, Edgar Peter Dabbi, A. I. Azahree, Zainol Affendi Abu Bakar, Dylon Tan Jen Huang, C. Pedersen, Pankaj K. Tiwari, M. T. M Sallehud-Din, M. Shamsudin, M. K. Hamid, R. Tewari, Parimal A. Patil
A depleted gas field situated in offshore Sarawak has been identified by PETRONAS as a potential CO2 storage development site. As part of the monitoring program, CO2 seepage risk and impact on the marine environment needs to be investigated and predicted. This study focuses on understanding the environmental risks associated with the potential seepage of CO2 gas at the depleted field within the 140 m water column through methods of numerical modelling. Leakage scenarios involving existing plugged and abandoned (P&A) wells as CO2 leakage pathways were modelled with leakage rates of 6 tonnes/year, representing a realistic rate and 500 tonnes/year which represents a more improbable and conservative scenario. The modelling period covers three representative climatic periods for the prevailing monsoons in the South China Sea (northwest, southwest and inter-monsoon). Simulation results showed that with the lower rate, changes to the seawater acidity within the far field region were negligible or undetectable. Under the high seepage rate, the pH plume footprint was predicted to extend beyond 200 m distance from the source point. However, the probability was estimated to be less than 1% while the vertical extent of the plume was limited up to 2 m above the seabed. For both scenarios, the CO2 gas were predicted to be fully dissolved within 5 m above the seabed. Therefore, it can be concluded that there is relatively low risk of impact at the storage field in terms of potential increase in seawater acidity if CO2 seepage occurs during the storage period.
{"title":"CO2 Leakage Marine Dispersion Modelling for an Offshore Depleted Gas Field for CO2 Storage","authors":"M. R. Amir Rashidi, Edgar Peter Dabbi, A. I. Azahree, Zainol Affendi Abu Bakar, Dylon Tan Jen Huang, C. Pedersen, Pankaj K. Tiwari, M. T. M Sallehud-Din, M. Shamsudin, M. K. Hamid, R. Tewari, Parimal A. Patil","doi":"10.4043/31447-ms","DOIUrl":"https://doi.org/10.4043/31447-ms","url":null,"abstract":"\u0000 A depleted gas field situated in offshore Sarawak has been identified by PETRONAS as a potential CO2 storage development site. As part of the monitoring program, CO2 seepage risk and impact on the marine environment needs to be investigated and predicted. This study focuses on understanding the environmental risks associated with the potential seepage of CO2 gas at the depleted field within the 140 m water column through methods of numerical modelling. Leakage scenarios involving existing plugged and abandoned (P&A) wells as CO2 leakage pathways were modelled with leakage rates of 6 tonnes/year, representing a realistic rate and 500 tonnes/year which represents a more improbable and conservative scenario. The modelling period covers three representative climatic periods for the prevailing monsoons in the South China Sea (northwest, southwest and inter-monsoon). Simulation results showed that with the lower rate, changes to the seawater acidity within the far field region were negligible or undetectable. Under the high seepage rate, the pH plume footprint was predicted to extend beyond 200 m distance from the source point. However, the probability was estimated to be less than 1% while the vertical extent of the plume was limited up to 2 m above the seabed. For both scenarios, the CO2 gas were predicted to be fully dissolved within 5 m above the seabed. Therefore, it can be concluded that there is relatively low risk of impact at the storage field in terms of potential increase in seawater acidity if CO2 seepage occurs during the storage period.","PeriodicalId":11217,"journal":{"name":"Day 4 Fri, March 25, 2022","volume":"95 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86255805","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}
C. Shrivastava, K. Bondabou, Mahdi Ammar, Simone Di Santo, Tetsushi Yamada, Sophie Androvandi
Analysis of drill-cuttings collected on the rig has always been the most basic, yet most direct means of understanding the subsurface within its own limitations. However, automation enabled by digital transformation of this aspect of mud logging has greatly increased the importance of this data. A futuristic preview is being presented for the repositioning and value showcasing of most basic and widely available data, i.e., cuttings with digital enablement. Cost-efficient characterization with lean sample preparation, reducing the adverse environmental imprint to near real-time formation evaluation leading to enhanced well placement and completion design is reshaping the old-school mudlogging with direct detection and quantification of minerals, total organic carbon (TOC), kerogen content and elemental composition; often minimizing the requirement for time-and-cost intensive wireline logging. Labor-intensive sample collection is getting automated, and subjective and descriptive interpretation per experience of mud-logger is giving way to digital, objective interpretation, ready to be integrated with logging-while-drilling data in real-time. In addition to the X-Ray Fluorescence & Diffraction; newer technologies like Diffused Reflectance Infrared Fourier Transform Spectroscopy (DRIFTS) are being incorporated in wellsite set-up with reduced footprint on rig and minimized usage of chemicals. Unique automated process can analyze high resolution digital images to deliver plethora of information in minimum time; often augmented with the help of artificial intelligence. A futuristic view with building blocks of the automated interpretation process is presented. Examples from different steps needed to achieve automation are provided, from sample preparation to digital analysis through machine learning for a holistic futuristic vision to highlight digital enablement in delivering the well-objectives in cost-efficient and timely manner honoring the changing market dynamics. This foundational cutting analysis (Geology 101) vision would drive further adavnces in this field.
{"title":"Automation in Cuttings Analysis: Futuristic Preview of Digital Enablement for Geology 101","authors":"C. Shrivastava, K. Bondabou, Mahdi Ammar, Simone Di Santo, Tetsushi Yamada, Sophie Androvandi","doi":"10.4043/31399-ms","DOIUrl":"https://doi.org/10.4043/31399-ms","url":null,"abstract":"\u0000 Analysis of drill-cuttings collected on the rig has always been the most basic, yet most direct means of understanding the subsurface within its own limitations. However, automation enabled by digital transformation of this aspect of mud logging has greatly increased the importance of this data. A futuristic preview is being presented for the repositioning and value showcasing of most basic and widely available data, i.e., cuttings with digital enablement.\u0000 Cost-efficient characterization with lean sample preparation, reducing the adverse environmental imprint to near real-time formation evaluation leading to enhanced well placement and completion design is reshaping the old-school mudlogging with direct detection and quantification of minerals, total organic carbon (TOC), kerogen content and elemental composition; often minimizing the requirement for time-and-cost intensive wireline logging. Labor-intensive sample collection is getting automated, and subjective and descriptive interpretation per experience of mud-logger is giving way to digital, objective interpretation, ready to be integrated with logging-while-drilling data in real-time.\u0000 In addition to the X-Ray Fluorescence & Diffraction; newer technologies like Diffused Reflectance Infrared Fourier Transform Spectroscopy (DRIFTS) are being incorporated in wellsite set-up with reduced footprint on rig and minimized usage of chemicals. Unique automated process can analyze high resolution digital images to deliver plethora of information in minimum time; often augmented with the help of artificial intelligence. A futuristic view with building blocks of the automated interpretation process is presented.\u0000 Examples from different steps needed to achieve automation are provided, from sample preparation to digital analysis through machine learning for a holistic futuristic vision to highlight digital enablement in delivering the well-objectives in cost-efficient and timely manner honoring the changing market dynamics. This foundational cutting analysis (Geology 101) vision would drive further adavnces in this field.","PeriodicalId":11217,"journal":{"name":"Day 4 Fri, March 25, 2022","volume":"319 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91470935","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}
Yu Chen, Y. Li, Yingtao Feng, Hao Zhang, D. Wen, Ce Cui, Youmei Wang, Feng Huang, Min Xiong, Jing Zhao, Wei Wang, Xiong Xiang, M. Song, Hu Zhao, Enlou Fang, Wei Xiao, Jing Ji
Methane Hydrates is an ice-like crystalline substance formed by methane and water under high pressure and low temperature environment. Each 1 unit methane hydrates contains about 170 units (converted in standard conditions) of methane gas. The low temperature and high pressure environment in deep water leads to the existence of hydrate layer in the shallow formation, which poses a significant challenge to cementing. The conventional cement slurry systems have limitations when applied in such well condition, since the heat of hydration during cement setting is high and there is a high risk of gas liberation from methane hydrates, easily causing severe well security issues. The low temperature environment, unconsolidated formation and narrow safety window also increased the complexity of the cementing jobs by a high performance requirement of the cement slurry. A low hydration heat cement slurry and an indoor cementing simulation evaluation method were developed in order to ensure effective isolation of the hydrate layer. This paper will describe in detail about the cement slurry development, performance and evaluation process in the lab with a novel method in the industry. This technology was proven as a solution for deep water hydrate layer well cementing, which is a great reference for cementing industry.
{"title":"Novel Cementing Technology for Deepwater Hydrate Layer","authors":"Yu Chen, Y. Li, Yingtao Feng, Hao Zhang, D. Wen, Ce Cui, Youmei Wang, Feng Huang, Min Xiong, Jing Zhao, Wei Wang, Xiong Xiang, M. Song, Hu Zhao, Enlou Fang, Wei Xiao, Jing Ji","doi":"10.4043/31460-ms","DOIUrl":"https://doi.org/10.4043/31460-ms","url":null,"abstract":"\u0000 Methane Hydrates is an ice-like crystalline substance formed by methane and water under high pressure and low temperature environment. Each 1 unit methane hydrates contains about 170 units (converted in standard conditions) of methane gas. The low temperature and high pressure environment in deep water leads to the existence of hydrate layer in the shallow formation, which poses a significant challenge to cementing. The conventional cement slurry systems have limitations when applied in such well condition, since the heat of hydration during cement setting is high and there is a high risk of gas liberation from methane hydrates, easily causing severe well security issues. The low temperature environment, unconsolidated formation and narrow safety window also increased the complexity of the cementing jobs by a high performance requirement of the cement slurry. A low hydration heat cement slurry and an indoor cementing simulation evaluation method were developed in order to ensure effective isolation of the hydrate layer. This paper will describe in detail about the cement slurry development, performance and evaluation process in the lab with a novel method in the industry. This technology was proven as a solution for deep water hydrate layer well cementing, which is a great reference for cementing industry.","PeriodicalId":11217,"journal":{"name":"Day 4 Fri, March 25, 2022","volume":"50 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90871622","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：