Andrew Paré, Nicolas Cosca, Alec Berarducci, Glenna Crookston, Ryan Paynter
Three-mile laterals have become more common over the last five years of onshore US drilling. They are especially commonplace in the Appalachian and Permian basins and are used to overcome limited surface access for drill pads and for economic reasons. These long laterals pose significant wellbore positioning and anti-collision challenges. Horizontal position error grows at 2% (or more) of the lateral length per degree of wellbore azimuth error. This work addresses these wellbore positioning challenges with a new and significant improvement in magnetic field determination. With this procedure, multi-well pads with tightly spaced three-mile laterals can be drilled without compromising anti-collision standards or horizontal placement goals. Most commonly in the US land market, tightly spaced laterals are 1-2 miles in length and make use of In-Field Referencing (IFR-1) magnetic models built from airborne geophysical surveys to ensure proper positioning and avoid well collisions. For more challenging pad designs, such as three-mile laterals, a new method has been developed to combine an IFR-1 magnetic model with a near-well magnetic theodolite measurement to build a more precise magnetic model and positioning tool code. Specifically, the declination error terms in the ISCWSA (Industry Steering Committee on Wellbore Survey Accuracy) Error Model can shrink beyond the IFR-1 tool code specifications. This reduces the horizontal uncertainty in the ellipse of uncertainty (EOU) by upwards of 40% when compared to the MWD tool code standard. A study was conducted on a typical well and pad design for three-mile laterals in the Marcellus Shale in Pennsylvania. We find that the horizontal uncertainty with the MWD tool code at two and three miles of reach to be 206 feet and 303 feet, respectively. With the new tool code enabled by this body of work, we calculate the horizontal uncertainty at two and three miles of reach to be 120 feet and 174 feet, respectively. These results clearly show that this technique enables three-mile laterals to be drilled more safely and more tightly together. It is preferable for well pad design and lateral spacing to be determined by drilling and reservoir economics rather than collision concerns. Well planners and reservoir engineers can now safely access more of the reservoir from a single pad with longer laterals. This work is novel because it combines a ground based, near-well, magnetic measurement with an airborne derived IFR-1 model. This allows for a greater reduction in positioning uncertainty than has been available in the past. The application of this method to three-mile laterals is also new and has a profound impact on being able to plan optimally spaced wells and avoiding collisions.
{"title":"Drilling Three-Mile Laterals Tighter and Safer with a New Magnetic Reference Technique","authors":"Andrew Paré, Nicolas Cosca, Alec Berarducci, Glenna Crookston, Ryan Paynter","doi":"10.2118/212465-ms","DOIUrl":"https://doi.org/10.2118/212465-ms","url":null,"abstract":"\u0000 Three-mile laterals have become more common over the last five years of onshore US drilling. They are especially commonplace in the Appalachian and Permian basins and are used to overcome limited surface access for drill pads and for economic reasons. These long laterals pose significant wellbore positioning and anti-collision challenges. Horizontal position error grows at 2% (or more) of the lateral length per degree of wellbore azimuth error. This work addresses these wellbore positioning challenges with a new and significant improvement in magnetic field determination. With this procedure, multi-well pads with tightly spaced three-mile laterals can be drilled without compromising anti-collision standards or horizontal placement goals.\u0000 Most commonly in the US land market, tightly spaced laterals are 1-2 miles in length and make use of In-Field Referencing (IFR-1) magnetic models built from airborne geophysical surveys to ensure proper positioning and avoid well collisions. For more challenging pad designs, such as three-mile laterals, a new method has been developed to combine an IFR-1 magnetic model with a near-well magnetic theodolite measurement to build a more precise magnetic model and positioning tool code. Specifically, the declination error terms in the ISCWSA (Industry Steering Committee on Wellbore Survey Accuracy) Error Model can shrink beyond the IFR-1 tool code specifications. This reduces the horizontal uncertainty in the ellipse of uncertainty (EOU) by upwards of 40% when compared to the MWD tool code standard.\u0000 A study was conducted on a typical well and pad design for three-mile laterals in the Marcellus Shale in Pennsylvania. We find that the horizontal uncertainty with the MWD tool code at two and three miles of reach to be 206 feet and 303 feet, respectively. With the new tool code enabled by this body of work, we calculate the horizontal uncertainty at two and three miles of reach to be 120 feet and 174 feet, respectively. These results clearly show that this technique enables three-mile laterals to be drilled more safely and more tightly together. It is preferable for well pad design and lateral spacing to be determined by drilling and reservoir economics rather than collision concerns. Well planners and reservoir engineers can now safely access more of the reservoir from a single pad with longer laterals.\u0000 This work is novel because it combines a ground based, near-well, magnetic measurement with an airborne derived IFR-1 model. This allows for a greater reduction in positioning uncertainty than has been available in the past. The application of this method to three-mile laterals is also new and has a profound impact on being able to plan optimally spaced wells and avoiding collisions.","PeriodicalId":255336,"journal":{"name":"Day 3 Thu, March 09, 2023","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116733817","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 ability to create a digital avatar of real-world equipment opens the possibility to create various levels of digital and virtual twins. Pairing these with real-time data can be a powerful tool to understand the life cycle, track operations, and collect data to predict the health of equipment. We have been testing new software methods to enable the use of existing technology to generate avatars for equipment. While many companies are also doing this with complex hardware, we have been using new software methods so that hardware requirements could be as simple as a common cell phone. We have applied these techniques to drill bits. The result is an application that creates a three-dimensional reconstructed model of a bit. This creates an avatar of the drilling bit that can be used for many purposes including equipment tracking and data extraction. Results from the three-dimensional reconstruction and the automating of a simple linear pipeline that converts bit videos to three-dimensional models is demonstrated. The renderings were compared to photos at the same locations and the results were virtually indistinguishable. The models can then be used for virtual twin generation. Multiple scans over the lifespan of the drill bit will allow access to a new way of thinking about virtual twins. One example is the ability to update a model with a snapshot in time and use AI to infer the life of the bit. These models can also be used to run additional analysis since the model can be infused with some contextual information.
{"title":"Software-Based Three-Dimensional Scan of a Drill Bit; Advances in Technology and Applications","authors":"Crispin Chatar, Kishore Mulchandani","doi":"10.2118/212528-ms","DOIUrl":"https://doi.org/10.2118/212528-ms","url":null,"abstract":"\u0000 The ability to create a digital avatar of real-world equipment opens the possibility to create various levels of digital and virtual twins. Pairing these with real-time data can be a powerful tool to understand the life cycle, track operations, and collect data to predict the health of equipment. We have been testing new software methods to enable the use of existing technology to generate avatars for equipment. While many companies are also doing this with complex hardware, we have been using new software methods so that hardware requirements could be as simple as a common cell phone. We have applied these techniques to drill bits. The result is an application that creates a three-dimensional reconstructed model of a bit. This creates an avatar of the drilling bit that can be used for many purposes including equipment tracking and data extraction.\u0000 Results from the three-dimensional reconstruction and the automating of a simple linear pipeline that converts bit videos to three-dimensional models is demonstrated. The renderings were compared to photos at the same locations and the results were virtually indistinguishable. The models can then be used for virtual twin generation. Multiple scans over the lifespan of the drill bit will allow access to a new way of thinking about virtual twins. One example is the ability to update a model with a snapshot in time and use AI to infer the life of the bit. These models can also be used to run additional analysis since the model can be infused with some contextual information.","PeriodicalId":255336,"journal":{"name":"Day 3 Thu, March 09, 2023","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123605420","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}
Alexander M. Mitkus, Timothy Gee, Tannor Ziehm, Andrew Paré, Kenneth McCarthy, Paul Reynerson, Marc E. Willerth
Geosteering solves for a drill bit's stratigraphic location to optimally guide a wellbore through a target formation. Geosteering solutions focus on correlating a subject well's real-time measurements to a type log representative of the stratigraphic column. Traditionally, this is done by matching localized sections of each log with a combination of shifts and stretches applied. This is a single-solution-at-a-time approach where only the best correlation is represented, as determined subjectively by a human or via algorithmic minimization of differences between measurements (Maus et al 2020). A method that considers the full space of possible stratigraphic interpretations and assigns a complexity-related correctness likelihood to each would give geosteerers greater confidence in selecting the correct interpretation. This would be a prohibitively large space to explore via traditional optimization and inversion methods, but it is possible through application of a Viterbi algorithm to a Bayesian state space matrix. A set of 1440 synthetic geosteering trials was generated by producing a geologically realistic layer cake, passing a well trajectory through it, and simulating realistically corrupted gamma measurements (reflecting sampling rate, calibration error, and measurement noise). This gives a true solution for accuracy comparison, and a realistic log that can be interpreted as follows: a Bayesian state space matrix is constructed which captures the likelihood of correlation between subject well and type log measurements. Prior knowledge is used to inform a state-transition probability matrix. The Viterbi algorithm is then applied to the state space matrix and state-transition probability matrix to determine the highest likelihood interpretation. The trial data was split 80/20 into training and test sets. For the training data, three metrics were used to tune the algorithm: mean distance from true solution; misfit ratio against true solution, and algorithm runtime. On the remaining test data, highest-likelihood paths were compared to the interpretations generated by an existing residual-minimizing automated geosteering algorithm (Gee et al 2019). Performance was analyzed separately in the vertical, curve, and lateral, and solutions were spot-checked for reasonable behavior. Compared to the existing automated method, the Bayesian method produced interpretations with comparable performance in 59% of laterals, and significantly improved performance in 34% of laterals. It also returned results 30 times faster. These results held over several sets of tuning parameters suggesting robustness. A well-tuned Bayesian algorithm has been shown to outperform existing automated methods on performance and accuracy, signifying a potential step change in the space of automated geosteering. Viterbi is an established algorithm with many applications, but the splitting of stratigraphic mappings into a Bayesian state space and application of Viterbi is novel an
地质导向解决了钻头的地层位置问题，以最佳方式引导井眼穿过目标地层。地质导向解决方案的重点是将目标井的实时测量数据与具有代表性的地层柱类型测井数据相关联。传统上，这是通过将每个原木的局部部分与移位和拉伸相匹配来完成的。这是一种一次单一解决方案的方法，其中仅表示最佳相关性，由人类主观确定或通过算法最小化测量之间的差异(Maus等，2020)。如果一种方法考虑了所有可能的地层解释，并为每种解释分配了与复杂性相关的正确可能性，那么地质导向员在选择正确解释时就会有更大的信心。通过传统的优化和反演方法，这将是一个令人望而却步的大空间，但通过将Viterbi算法应用于贝叶斯状态空间矩阵，这是可能的。通过制作地质上真实的层饼，通过井眼轨迹，模拟真实损坏的伽马测量(反映采样率、校准误差和测量噪声)，生成了1440组合成地质导向试验。这为精度比较提供了一个真正的解决方案，并且可以解释如下的现实日志:构建贝叶斯状态空间矩阵，该矩阵捕获主题井和类型日志测量之间的相关性的可能性。使用先验知识来通知状态转移概率矩阵。然后将Viterbi算法应用于状态空间矩阵和状态转移概率矩阵，确定最高似然解释。试验数据按80/20分成训练集和测试集。对于训练数据，使用三个指标来调整算法:与真解的平均距离;与真解的不匹配比率，以及算法运行时间。在剩余的测试数据上，将最高似然路径与现有残差最小化自动地质导向算法生成的解释进行比较(Gee et al, 2019)。分别分析了垂直、曲线和水平段的性能，并对解决方案进行了抽查，以确定其合理性能。与现有的自动化方法相比，贝叶斯方法在59%的分支井的解释效果相当，在34%的分支井的解释效果显著提高。它的返回速度也快了30倍。这些结果适用于几组调优参数，表明鲁棒性。经过优化的贝叶斯算法在性能和精度上都优于现有的自动化方法，这标志着自动地质导向领域的潜在变化。Viterbi是一种已建立的算法，有许多应用，但将地层映射分解为贝叶斯状态空间和Viterbi的应用是新颖的，可以实现高效、概率的解查找。可以考虑整个可能解的空间，并隐式给出解的似然。该技术还解释了生成的解决方案的复杂性。
{"title":"How a Bayesian Approach Can Overcome Noisy Data and Interpretation Ambiguity in Automated Geosteering","authors":"Alexander M. Mitkus, Timothy Gee, Tannor Ziehm, Andrew Paré, Kenneth McCarthy, Paul Reynerson, Marc E. Willerth","doi":"10.2118/212544-ms","DOIUrl":"https://doi.org/10.2118/212544-ms","url":null,"abstract":"\u0000 Geosteering solves for a drill bit's stratigraphic location to optimally guide a wellbore through a target formation. Geosteering solutions focus on correlating a subject well's real-time measurements to a type log representative of the stratigraphic column. Traditionally, this is done by matching localized sections of each log with a combination of shifts and stretches applied. This is a single-solution-at-a-time approach where only the best correlation is represented, as determined subjectively by a human or via algorithmic minimization of differences between measurements (Maus et al 2020). A method that considers the full space of possible stratigraphic interpretations and assigns a complexity-related correctness likelihood to each would give geosteerers greater confidence in selecting the correct interpretation. This would be a prohibitively large space to explore via traditional optimization and inversion methods, but it is possible through application of a Viterbi algorithm to a Bayesian state space matrix.\u0000 A set of 1440 synthetic geosteering trials was generated by producing a geologically realistic layer cake, passing a well trajectory through it, and simulating realistically corrupted gamma measurements (reflecting sampling rate, calibration error, and measurement noise). This gives a true solution for accuracy comparison, and a realistic log that can be interpreted as follows: a Bayesian state space matrix is constructed which captures the likelihood of correlation between subject well and type log measurements. Prior knowledge is used to inform a state-transition probability matrix. The Viterbi algorithm is then applied to the state space matrix and state-transition probability matrix to determine the highest likelihood interpretation.\u0000 The trial data was split 80/20 into training and test sets. For the training data, three metrics were used to tune the algorithm: mean distance from true solution; misfit ratio against true solution, and algorithm runtime. On the remaining test data, highest-likelihood paths were compared to the interpretations generated by an existing residual-minimizing automated geosteering algorithm (Gee et al 2019). Performance was analyzed separately in the vertical, curve, and lateral, and solutions were spot-checked for reasonable behavior.\u0000 Compared to the existing automated method, the Bayesian method produced interpretations with comparable performance in 59% of laterals, and significantly improved performance in 34% of laterals. It also returned results 30 times faster. These results held over several sets of tuning parameters suggesting robustness. A well-tuned Bayesian algorithm has been shown to outperform existing automated methods on performance and accuracy, signifying a potential step change in the space of automated geosteering.\u0000 Viterbi is an established algorithm with many applications, but the splitting of stratigraphic mappings into a Bayesian state space and application of Viterbi is novel an","PeriodicalId":255336,"journal":{"name":"Day 3 Thu, March 09, 2023","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121562634","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}
Deep R. Joshi, M. Kamyab, Daniel Cardoso Braga, C. Cheatham
This paper shares an implementation of a cloud-based framework that tracks the well position and, in real-time, recommends corrective actions to ensure that the well efficiently follows the well plan. This directional guidance framework can differentiate between vertical, curve, and lateral sections and modify the recommendations accordingly. This paper will share the methods and results from the case studies to validate the directional guidance framework. This cloud-based directional guidance workflow kicks in as soon as the drilling starts. In real-time, the system tracks the bit position and identifies the active section (vertical, curve, lateral, tangent) for the well. Vertical and lateral sections use recommendations previously reported using particle swarm optimization in SPE-206170 (Cardoso Braga et al., 2021). Equations for curve sections are provided that fit the proposed wellbore trajectory to a 3D spheroid using the current motor yield as calculated using the three most recent slides. A real-time assessment of the estimated actual landing point is presented, and warnings of missing the planned landing point are provided. The drilling guidance algorithm was tested for individual sections (vertical, tangent, curve, lateral) on three wells. The recommendations were evaluated to ensure they met each section's optimization goals. The optimization goals for the straight sections are to maximize the ROP, maximize the footage in the window, and minimize tortuosity. Weighting factors for each goal adjust the optimum recommendations based on user requirements. The optimization goals for the curve section are to minimize the distance between the planned landing point and the recommended landing points Then, the guidance system was tested on the complete wells to ensure that the algorithm could correctly identify the section and use the appropriate method. The recommendations from all three wells were evaluated to confirm that the recommendations met the specific criteria applied. Close attention was paid to the transition zones between various sections. The directional guidance workflow resulted in real-time recommendations throughout the well profile for all sections. It was consistently able to output specific steps that the directional driller can take to optimally get closer to the plan. This paper follows up on the previous publications on directional guidance by the authors (SPE 206170 (Cardoso Braga et al., 2021) and SPE 204065 (Cardoso Braga et al., 2021).). It completes the loop on automated directional guidance by adding the missing piece of directional guidance in the curve section and handling transitions between straight (vertical, lateral, tangent) and curve sections. This enables cloud-based automated directional guidance for the entirety of the drilling process.
本文分享了一个基于云的框架的实现，该框架可以跟踪井的位置，并实时建议纠正措施，以确保井有效地遵循井计划。该定向指导框架可以区分垂直、曲线和横向剖面，并相应地修改建议。本文将分享案例研究的方法和结果，以验证定向指导框架。一旦钻井开始，这种基于云的定向导向工作流程就会启动。该系统实时跟踪钻头位置，并识别井的活动段(垂直、曲线、水平段、切线段)。垂直和横向剖面采用SPE-206170中先前报道的粒子群优化建议(Cardoso Braga等，2021)。根据最新的三次滑动计算得出的当前电机产量，给出了曲线段的方程，将所提出的井眼轨迹拟合为三维球体。提出了对估计实际着陆点的实时评估，并提供了错过计划着陆点的警告。在三口井的各个井段(垂直、切线、曲线、水平段)上测试了钻井导向算法。对这些建议进行了评估，以确保它们满足每个部分的优化目标。直线段的优化目标是最大限度地提高机械钻速，最大限度地提高窗口进尺，并最大限度地减少弯曲度。每个目标的加权因子根据用户需求调整最佳建议。曲线段的优化目标是使规划着陆点与推荐着陆点之间的距离最小，然后在整口井上对制导系统进行了测试，以确保该算法能够正确识别曲线段并使用合适的方法。对所有三口井的建议进行了评估，以确认建议符合应用的具体标准。对各个剖面之间的过渡地带给予了密切关注。定向导向工作流程可在所有井段的整个井剖面中提供实时建议。它始终能够输出定向司钻可以采取的特定步骤，以最优地接近计划。本文对作者之前发表的关于定向引导的文章(SPE 206170 (Cardoso Braga et al.， 2021)和SPE 204065 (Cardoso Braga et al.， 2021)进行了后续研究。它通过在曲线段添加缺失的定向导引片，并处理直线(垂直、横向、切线)和曲线段之间的转换，完成自动定向导向的循环。这使得整个钻井过程都可以实现基于云的自动定向导向。
{"title":"Real-Time Directional Guidance Through Cloud-Based Well Path Optimization","authors":"Deep R. Joshi, M. Kamyab, Daniel Cardoso Braga, C. Cheatham","doi":"10.2118/212525-ms","DOIUrl":"https://doi.org/10.2118/212525-ms","url":null,"abstract":"\u0000 This paper shares an implementation of a cloud-based framework that tracks the well position and, in real-time, recommends corrective actions to ensure that the well efficiently follows the well plan. This directional guidance framework can differentiate between vertical, curve, and lateral sections and modify the recommendations accordingly. This paper will share the methods and results from the case studies to validate the directional guidance framework.\u0000 This cloud-based directional guidance workflow kicks in as soon as the drilling starts. In real-time, the system tracks the bit position and identifies the active section (vertical, curve, lateral, tangent) for the well. Vertical and lateral sections use recommendations previously reported using particle swarm optimization in SPE-206170 (Cardoso Braga et al., 2021). Equations for curve sections are provided that fit the proposed wellbore trajectory to a 3D spheroid using the current motor yield as calculated using the three most recent slides. A real-time assessment of the estimated actual landing point is presented, and warnings of missing the planned landing point are provided.\u0000 The drilling guidance algorithm was tested for individual sections (vertical, tangent, curve, lateral) on three wells. The recommendations were evaluated to ensure they met each section's optimization goals. The optimization goals for the straight sections are to maximize the ROP, maximize the footage in the window, and minimize tortuosity. Weighting factors for each goal adjust the optimum recommendations based on user requirements. The optimization goals for the curve section are to minimize the distance between the planned landing point and the recommended landing points Then, the guidance system was tested on the complete wells to ensure that the algorithm could correctly identify the section and use the appropriate method. The recommendations from all three wells were evaluated to confirm that the recommendations met the specific criteria applied. Close attention was paid to the transition zones between various sections. The directional guidance workflow resulted in real-time recommendations throughout the well profile for all sections. It was consistently able to output specific steps that the directional driller can take to optimally get closer to the plan.\u0000 This paper follows up on the previous publications on directional guidance by the authors (SPE 206170 (Cardoso Braga et al., 2021) and SPE 204065 (Cardoso Braga et al., 2021).). It completes the loop on automated directional guidance by adding the missing piece of directional guidance in the curve section and handling transitions between straight (vertical, lateral, tangent) and curve sections. This enables cloud-based automated directional guidance for the entirety of the drilling process.","PeriodicalId":255336,"journal":{"name":"Day 3 Thu, March 09, 2023","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121693285","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. Naschenveng, Lucas Isaac, F. Laroca, Cláudio Franceschi, A. Neves, Fábio Canté, Adrian G. Ledroz, A. Carrasquilla
Data quality assurance applied to well positioning optimizes contingency plans to reduce the time to drill a relief well and provides greater reliability in autonomous and remote drilling operations. In addition, it provides the highest degree of agreement with the well design, making it possible to reach the best productive zones of the reservoir and avoid geological risks. This data quality assurance procedure supports the construction of high-productivity wells in the offshore pre-salt fields in Brazil. The objective of this work is to present the results of the Definitive Survey Methodology in pre-salt wells, to improve the survey quality assurance and the reduction of uncertainty ellipses - during operation and in real-time - using two survey tools with different physical principles. The Definitive Survey Methodology promotes the verification of error models of the survey tools and reduces the Ellipses of Uncertainty (EOU), well to well, creating an external directional data quality assurance, which goes beyond specific internal quality controls used by service companies. The methodology consists of the use of three tests that compare independent surveys. The first and second tests are statistical, Relative Instrument Performance (RIP), and Chi-square, in which the reliability of the used error models is verified. The RIP test is a comparison that produces results with quantitative values about the agreement of overlapping surveys. The Chi-square test is a quality fit test that compares two surveys and their compliances with their error models. The third test is a qualitative geometric test that compares the uncertainty ellipses of different survey tools at the same depth, allowing a quick interpretation of graphic representations and can be applied during or after drilling. The methodology was applied in four pre-salt wells named in this paper as Well_A, Well_B, Well_C, and Well_D. The final measured depths of the wells range from 5078m to 6801m. The tools used were: gyro while drilling (GWD) for all inclinations in real-time (inrun), GWD outrun memory mode (OMM), drop gyros, and measurement while drilling (MWD). The methodology resulted in a reduction of 74.55% (Well_A), 50.93% (Well_B), 33.69% (Well_C), and 60.05% (Well_D) of the ellipse of uncertainty at the top of the reservoir. The use of the Definitive Survey Methodology enhances the quality of the directional data, verifying the error models used well to well. The reduction of uncertainties provided by the gyroscopic tool ensures the reliability of the contingency plan and the entry into the top of the reservoir. Consequently, by optimizing the positioning of the wells, it is expected to make the most of the natural resources in the long term, while also building safer contingency plans, and making the extraction activity of this natural resource more sustainable.
{"title":"Definitive Survey Methodology – Update to an Old Concept for Higher Reliability","authors":"A. Naschenveng, Lucas Isaac, F. Laroca, Cláudio Franceschi, A. Neves, Fábio Canté, Adrian G. Ledroz, A. Carrasquilla","doi":"10.2118/212492-ms","DOIUrl":"https://doi.org/10.2118/212492-ms","url":null,"abstract":"\u0000 Data quality assurance applied to well positioning optimizes contingency plans to reduce the time to drill a relief well and provides greater reliability in autonomous and remote drilling operations. In addition, it provides the highest degree of agreement with the well design, making it possible to reach the best productive zones of the reservoir and avoid geological risks. This data quality assurance procedure supports the construction of high-productivity wells in the offshore pre-salt fields in Brazil. The objective of this work is to present the results of the Definitive Survey Methodology in pre-salt wells, to improve the survey quality assurance and the reduction of uncertainty ellipses - during operation and in real-time - using two survey tools with different physical principles.\u0000 The Definitive Survey Methodology promotes the verification of error models of the survey tools and reduces the Ellipses of Uncertainty (EOU), well to well, creating an external directional data quality assurance, which goes beyond specific internal quality controls used by service companies. The methodology consists of the use of three tests that compare independent surveys. The first and second tests are statistical, Relative Instrument Performance (RIP), and Chi-square, in which the reliability of the used error models is verified. The RIP test is a comparison that produces results with quantitative values about the agreement of overlapping surveys. The Chi-square test is a quality fit test that compares two surveys and their compliances with their error models. The third test is a qualitative geometric test that compares the uncertainty ellipses of different survey tools at the same depth, allowing a quick interpretation of graphic representations and can be applied during or after drilling.\u0000 The methodology was applied in four pre-salt wells named in this paper as Well_A, Well_B, Well_C, and Well_D. The final measured depths of the wells range from 5078m to 6801m. The tools used were: gyro while drilling (GWD) for all inclinations in real-time (inrun), GWD outrun memory mode (OMM), drop gyros, and measurement while drilling (MWD). The methodology resulted in a reduction of 74.55% (Well_A), 50.93% (Well_B), 33.69% (Well_C), and 60.05% (Well_D) of the ellipse of uncertainty at the top of the reservoir.\u0000 The use of the Definitive Survey Methodology enhances the quality of the directional data, verifying the error models used well to well. The reduction of uncertainties provided by the gyroscopic tool ensures the reliability of the contingency plan and the entry into the top of the reservoir. Consequently, by optimizing the positioning of the wells, it is expected to make the most of the natural resources in the long term, while also building safer contingency plans, and making the extraction activity of this natural resource more sustainable.","PeriodicalId":255336,"journal":{"name":"Day 3 Thu, March 09, 2023","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124423638","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 Assisted Cement Log Machine Learning (ML) tool – or Annular barrier AI tool - developed by Equinor - is being used to interpret cement logs by predicting a predefined set of annular condition codes used in the cement log interpretation process. (Reference to SPE paper: Assisted Cement Interpretation project). Annular conditions are usually separated into High, Medium and Low probability for hydraulic isolation. The internally developed annular condition code descriptions at Equinor are separated into 30 specific classes, which supports more nuanced and objective expert interpretations. The paper will discuss how this framework has positively impacted the performance of the trained ML model. In addition, we report how this tool is being used to speed up and increase consistency in the log interpretation process, and how it can be used to efficiently share expert knowledge when training new professionals into Equinor's Cased Hole Logging Group. Furthermore, the paper will discuss ongoing research to improve the capabilities of this tool, like supporting the use of cement logs from additional service vendors, and how it could be potentially expanded to extract relevant information from historical reports to improve formation bond predictions. The ML model is trained using selected and calculated features from cement logs, and the tool predicts an annular condition code according to the cement classification system for each depth segment in the log. Training and prediction are done in the cloud and accessible through an Application Programmable Interface (API) which makes it convenient to integrate the tool with any cement log interpretation software. Through the API, the interpretation software uploads a cement log and swiftly receives predictions for the complete log, including hydraulic isolation probabilities and confidence curves, which are used as decision support for the final expert interpretation. The ML model is regularly retrained with an ever-growing data set from real operations performed by Equinor. The uploaded data undergoes an automatic quality assurance before it is used as training data, and the model's performance is evaluated at each retraining. To improve the cement log interpretation consistency in the industry and to ensure that our work can benefit the industry as widely as possible, the results will be made available as open source. This paper will discuss the challenges making such an ML tool open source, and the how the idea of Federated Learning could be used to share this solution in the industry.
{"title":"Improve Well Integrity Using an Annular Barrier AI tool","authors":"Eirik Time, E. Berg, Siddharth Mishra","doi":"10.2118/212479-ms","DOIUrl":"https://doi.org/10.2118/212479-ms","url":null,"abstract":"\u0000 The Assisted Cement Log Machine Learning (ML) tool – or Annular barrier AI tool - developed by Equinor - is being used to interpret cement logs by predicting a predefined set of annular condition codes used in the cement log interpretation process. (Reference to SPE paper: Assisted Cement Interpretation project).\u0000 Annular conditions are usually separated into High, Medium and Low probability for hydraulic isolation. The internally developed annular condition code descriptions at Equinor are separated into 30 specific classes, which supports more nuanced and objective expert interpretations. The paper will discuss how this framework has positively impacted the performance of the trained ML model.\u0000 In addition, we report how this tool is being used to speed up and increase consistency in the log interpretation process, and how it can be used to efficiently share expert knowledge when training new professionals into Equinor's Cased Hole Logging Group. Furthermore, the paper will discuss ongoing research to improve the capabilities of this tool, like supporting the use of cement logs from additional service vendors, and how it could be potentially expanded to extract relevant information from historical reports to improve formation bond predictions.\u0000 The ML model is trained using selected and calculated features from cement logs, and the tool predicts an annular condition code according to the cement classification system for each depth segment in the log. Training and prediction are done in the cloud and accessible through an Application Programmable Interface (API) which makes it convenient to integrate the tool with any cement log interpretation software. Through the API, the interpretation software uploads a cement log and swiftly receives predictions for the complete log, including hydraulic isolation probabilities and confidence curves, which are used as decision support for the final expert interpretation. The ML model is regularly retrained with an ever-growing data set from real operations performed by Equinor. The uploaded data undergoes an automatic quality assurance before it is used as training data, and the model's performance is evaluated at each retraining.\u0000 To improve the cement log interpretation consistency in the industry and to ensure that our work can benefit the industry as widely as possible, the results will be made available as open source. This paper will discuss the challenges making such an ML tool open source, and the how the idea of Federated Learning could be used to share this solution in the industry.","PeriodicalId":255336,"journal":{"name":"Day 3 Thu, March 09, 2023","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124102680","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 authors present a method for automated, high-fidelity detection of rig events characterized by complex temporal signals, such as downlinking, or wave-induced heave affecting floating rigs. These can adversely impact other systems utilizing relevant data streams, for example downlinking via mud pulse telemetry can interfere with detection of pressure changes that might indicate hole cleaning problems. Identifying these events using classification techniques applied to time-domain data is difficult, hence spectral (frequency domain) techniques, combined with Machine Learning (ML), were applied to solving this problem. Surface measurements from a variety of wells, fields, regions, service companies and operators were used to develop and validate the detection methods. Data was preprocessed using time-frequency analysis, and then input to discriminative classifiers to identify rig events of interest. For downlinking state detection, high recall and precision scores (both >93%) were achieved on independent holdout well data, and thus false positive rates were low. Successful detection was demonstrated on wells separate from the training data, hence the method is expected to generalize to new well operations. The detection method enhances situational awareness, and can actively support other software in improved automated decision-making by providing operational context in real-time, such as suppression of false warnings from monitoring pressure or modelled ECD for detecting signs of poor hole cleaning. These techniques are not limited to downlinking or heave detection, and can be applied more generally to scenarios with complex periodic signals.
{"title":"Automated Detection of Rig Events from Real-Time Surface Data Using Spectral Analysis and Machine Learning","authors":"T. S. Robinson, O. Revheim","doi":"10.2118/212481-ms","DOIUrl":"https://doi.org/10.2118/212481-ms","url":null,"abstract":"\u0000 The authors present a method for automated, high-fidelity detection of rig events characterized by complex temporal signals, such as downlinking, or wave-induced heave affecting floating rigs. These can adversely impact other systems utilizing relevant data streams, for example downlinking via mud pulse telemetry can interfere with detection of pressure changes that might indicate hole cleaning problems. Identifying these events using classification techniques applied to time-domain data is difficult, hence spectral (frequency domain) techniques, combined with Machine Learning (ML), were applied to solving this problem. Surface measurements from a variety of wells, fields, regions, service companies and operators were used to develop and validate the detection methods. Data was preprocessed using time-frequency analysis, and then input to discriminative classifiers to identify rig events of interest.\u0000 For downlinking state detection, high recall and precision scores (both >93%) were achieved on independent holdout well data, and thus false positive rates were low. Successful detection was demonstrated on wells separate from the training data, hence the method is expected to generalize to new well operations. The detection method enhances situational awareness, and can actively support other software in improved automated decision-making by providing operational context in real-time, such as suppression of false warnings from monitoring pressure or modelled ECD for detecting signs of poor hole cleaning. These techniques are not limited to downlinking or heave detection, and can be applied more generally to scenarios with complex periodic signals.","PeriodicalId":255336,"journal":{"name":"Day 3 Thu, March 09, 2023","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128537208","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}
Abnormal torque and drag (T & D), which commonly includes overpull, underpull, and high-torque load, are indications of excess frictional effects between the drillstring and the wellbore walls. Numerous conditions can cause these effects, including tight hole, differential sticking, poor hole cleaning, key seats, etc. Failure to observe these anomalies will cause excessive wear on the drillstring and can eventually lead to severe stuck pipe conditions. A new workflow for monitoring T & D is presented in this paper. This workflow, developed for a real-time monitoring system, allows for monitoring various types of data from multiple sources to be received without delay, aligned, and synchronized. The workflow requires standard surface measurements and contextual data, which are available on most wells. Three main segments with respect to the computation phase are included in the workflow. These segments include T & D measurement points statistics, T & D modelling and calibration, and abnormal T & D alarms. The measurement points are selected from relevant operations and summarize the statistics at different granularities to meet the different objectives, such as the classical broomstick plot or alarm triggering. A hybrid T & D modelling framework was designed to predict the hook load and surface torque accordingly. This framework combines the mathematical capability of a stiff-string model using a finite element method and the experience acquired from obtaining the drilling data. As a result, the physical model can be automatically calibrated and driven by real-time data to compensate the hook load offset due to uncertain variables or inaccurate inputs. An alarm-triggering logic can be developed to capture anomalies based on a comparison between the measured and predicted values. The new workflow is fully automatic without a need for manual calibration and fixed thresholds. Furthermore, the workflow adjusts itself according to real-time observations, which makes it adaptive to the changing conditions of the well being drilled. The efficiency and reliability of the anomaly detection heavily rely on the input data quality in the perspective of stream computation. In this paper, two case studies are presented containing the results produced by streaming actual well data in a time series manner. The case studies demonstrate the usability and reasonableness obtained by the user when handling the actual operation scenarios. The work presented in this paper was developed to meet the increase in digital transformation by the oil and gas industry and demonstrates the best use of data for drilling optimization.
{"title":"An Innovative Workflow for Real-Time Torque and Drag Monitoring","authors":"K. Sun, Chao Mu, Tao Yu, Graeme L. J. Paterson","doi":"10.2118/212535-ms","DOIUrl":"https://doi.org/10.2118/212535-ms","url":null,"abstract":"\u0000 Abnormal torque and drag (T & D), which commonly includes overpull, underpull, and high-torque load, are indications of excess frictional effects between the drillstring and the wellbore walls. Numerous conditions can cause these effects, including tight hole, differential sticking, poor hole cleaning, key seats, etc. Failure to observe these anomalies will cause excessive wear on the drillstring and can eventually lead to severe stuck pipe conditions. A new workflow for monitoring T & D is presented in this paper. This workflow, developed for a real-time monitoring system, allows for monitoring various types of data from multiple sources to be received without delay, aligned, and synchronized.\u0000 The workflow requires standard surface measurements and contextual data, which are available on most wells. Three main segments with respect to the computation phase are included in the workflow. These segments include T & D measurement points statistics, T & D modelling and calibration, and abnormal T & D alarms. The measurement points are selected from relevant operations and summarize the statistics at different granularities to meet the different objectives, such as the classical broomstick plot or alarm triggering. A hybrid T & D modelling framework was designed to predict the hook load and surface torque accordingly. This framework combines the mathematical capability of a stiff-string model using a finite element method and the experience acquired from obtaining the drilling data. As a result, the physical model can be automatically calibrated and driven by real-time data to compensate the hook load offset due to uncertain variables or inaccurate inputs. An alarm-triggering logic can be developed to capture anomalies based on a comparison between the measured and predicted values.\u0000 The new workflow is fully automatic without a need for manual calibration and fixed thresholds. Furthermore, the workflow adjusts itself according to real-time observations, which makes it adaptive to the changing conditions of the well being drilled. The efficiency and reliability of the anomaly detection heavily rely on the input data quality in the perspective of stream computation. In this paper, two case studies are presented containing the results produced by streaming actual well data in a time series manner. The case studies demonstrate the usability and reasonableness obtained by the user when handling the actual operation scenarios.\u0000 The work presented in this paper was developed to meet the increase in digital transformation by the oil and gas industry and demonstrates the best use of data for drilling optimization.","PeriodicalId":255336,"journal":{"name":"Day 3 Thu, March 09, 2023","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131963443","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}
Generally, the expansion of cementitious materials has been regarded as a promising avenue for better sealability. The sealability performance of an expanding geopolymer is compared to an expansive commercial cement in terms of the shear bond strength and the hydraulic bond strength at curing conditions of 25°C and 34.5 bar. A Neat Class G and a neat geopolymer were characterized alongside its corresponding expansive versions. The impact of these expansive agents on cement and geopolymers is evaluated in terms of linear expansion using the annular ring test. In terms of its performance for P & A operation, the push-out test was used to characterize the shear bond strength between the casing-cement interfaces, whereas the hydraulic bond strength is measured with a custom-made setup which eliminates any pressure and thermal shocks. These materials were characterized in terms of its shear bond strength, hydraulic bond strength and linear expansion. The shear bond strength of Neat G and expansive cement were estimated to be 22.37 bar and 22.76 bar respectively. Whereas that of the neat geopolymer and expansive geopolymer were recorded at 7.47 bar and 10.14 bar respectively. On the basis of the hydraulic bond strength, expansive cement had the highest followed by expansive geopolymer. Both the neat recipes were observed to have the same values in terms of the hydraulic bond strength. This study reveals that geopolymers can be deployed as an alternative to Portland cement upon optimization.
{"title":"Expandable Geopolymers for Improved Zonal Isolation and Plugging","authors":"F. Gomado, M. Khalifeh, J. Aasen","doi":"10.2118/212493-ms","DOIUrl":"https://doi.org/10.2118/212493-ms","url":null,"abstract":"\u0000 Generally, the expansion of cementitious materials has been regarded as a promising avenue for better sealability. The sealability performance of an expanding geopolymer is compared to an expansive commercial cement in terms of the shear bond strength and the hydraulic bond strength at curing conditions of 25°C and 34.5 bar. A Neat Class G and a neat geopolymer were characterized alongside its corresponding expansive versions. The impact of these expansive agents on cement and geopolymers is evaluated in terms of linear expansion using the annular ring test. In terms of its performance for P & A operation, the push-out test was used to characterize the shear bond strength between the casing-cement interfaces, whereas the hydraulic bond strength is measured with a custom-made setup which eliminates any pressure and thermal shocks. These materials were characterized in terms of its shear bond strength, hydraulic bond strength and linear expansion. The shear bond strength of Neat G and expansive cement were estimated to be 22.37 bar and 22.76 bar respectively. Whereas that of the neat geopolymer and expansive geopolymer were recorded at 7.47 bar and 10.14 bar respectively. On the basis of the hydraulic bond strength, expansive cement had the highest followed by expansive geopolymer. Both the neat recipes were observed to have the same values in terms of the hydraulic bond strength. This study reveals that geopolymers can be deployed as an alternative to Portland cement upon optimization.","PeriodicalId":255336,"journal":{"name":"Day 3 Thu, March 09, 2023","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122014050","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 it comes to optimizing drilling, the focus is on running the bit into the well and performing the drilling efficiently. Included in this are methods for optimizing rate of penetration (ROP), determining the right time to change drilling bits, and managing bit run to reduce other drilling costs, such as tripping, hole conditioning, material consumption, and detecting drilling problems at the right time. The present study employs a new approach to drilling bit modeling that utilizes along-string measurement (ASM) data to continuously monitor the status of the drilling bit. A two-pronged approach is employed in the monitoring of drilling bit condition in addition to estimating rock drillability to keep track of change in lithology. First step involves developing a model for polycrystalline compact drilling (PDC) bits. It examines micro forces at the bit cutters and then upscales these forces to parameters applied to the drilling bits, such as weight and torque. Upscaling involves geometric remodeling of bits as equivalent cutters and equivalent blades. In the second part, a data-analytic approach is used to combine continuous measurement of downhole data with the developed experimental-based model. The real-time data is measured by using an along-string measurement system on the wired pipe. The results of this approach can be grouped into three categories. First, the drilling bit condition is estimated in real time in each equivalent cutter. A quantitative assessment could be undertaken based on model output, or a qualitative assessment could be carried out by analyzing specific energy. Having knowledge of the status of bit, the second conclusion is to monitor rock drillability according to variations in specific energy at the bit and publishing numerical value of rock drillability. In addition, the last corollary is to generate knowledge regarding drill string dynamics and the way to differentiate between vibration at the bit and at the drill string. In this paper, however, the first two outcomes are addressed. This approach is tested on a set of ASM data captured during drilling operations on the Norwegian continental shelf. The results are consistent with those reported from the field. Currently, the selection and evaluation of drilling bits requires knowledge of nearby well records. A drilling penetration rate model that requires calibration for a specific field may also be used to estimate bit condition in some cases. This research presents a new bit status simulator that overcomes the limitations of existing techniques by applying a delicate and intelligent application of ASM data to predict drilling events and mitigate them in real-time.
{"title":"Real-Time Prediction and Detection of Drilling Bit Issues Based on Along-String Measurements (ASM) Along Wired Pipes - A Case Study","authors":"Mostafa Gomar, B. Elahifar","doi":"10.2118/212488-ms","DOIUrl":"https://doi.org/10.2118/212488-ms","url":null,"abstract":"\u0000 When it comes to optimizing drilling, the focus is on running the bit into the well and performing the drilling efficiently. Included in this are methods for optimizing rate of penetration (ROP), determining the right time to change drilling bits, and managing bit run to reduce other drilling costs, such as tripping, hole conditioning, material consumption, and detecting drilling problems at the right time. The present study employs a new approach to drilling bit modeling that utilizes along-string measurement (ASM) data to continuously monitor the status of the drilling bit.\u0000 A two-pronged approach is employed in the monitoring of drilling bit condition in addition to estimating rock drillability to keep track of change in lithology. First step involves developing a model for polycrystalline compact drilling (PDC) bits. It examines micro forces at the bit cutters and then upscales these forces to parameters applied to the drilling bits, such as weight and torque. Upscaling involves geometric remodeling of bits as equivalent cutters and equivalent blades. In the second part, a data-analytic approach is used to combine continuous measurement of downhole data with the developed experimental-based model. The real-time data is measured by using an along-string measurement system on the wired pipe.\u0000 The results of this approach can be grouped into three categories. First, the drilling bit condition is estimated in real time in each equivalent cutter. A quantitative assessment could be undertaken based on model output, or a qualitative assessment could be carried out by analyzing specific energy. Having knowledge of the status of bit, the second conclusion is to monitor rock drillability according to variations in specific energy at the bit and publishing numerical value of rock drillability. In addition, the last corollary is to generate knowledge regarding drill string dynamics and the way to differentiate between vibration at the bit and at the drill string. In this paper, however, the first two outcomes are addressed. This approach is tested on a set of ASM data captured during drilling operations on the Norwegian continental shelf. The results are consistent with those reported from the field.\u0000 Currently, the selection and evaluation of drilling bits requires knowledge of nearby well records. A drilling penetration rate model that requires calibration for a specific field may also be used to estimate bit condition in some cases. This research presents a new bit status simulator that overcomes the limitations of existing techniques by applying a delicate and intelligent application of ASM data to predict drilling events and mitigate them in real-time.","PeriodicalId":255336,"journal":{"name":"Day 3 Thu, March 09, 2023","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123835997","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：