Pub Date : 2023-12-12DOI: 10.1007/s13202-023-01724-0
Shabeeb Alajmei
{"title":"Prediction of proppant distribution as a function of perforation orientations","authors":"Shabeeb Alajmei","doi":"10.1007/s13202-023-01724-0","DOIUrl":"https://doi.org/10.1007/s13202-023-01724-0","url":null,"abstract":"","PeriodicalId":16723,"journal":{"name":"Journal of Petroleum Exploration and Production Technology","volume":"54 23","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139006922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-11DOI: 10.1007/s13202-023-01725-z
Di Shi, Xin Chang, Liping Li, Mingyang Wu, Rui Song, Yintong Guo, Jupeng Tang, Jianjun Liu
{"title":"Differences in the permeability assessment of the fractured reservoir rocks using the conventional and the rough discrete fracture network modeling","authors":"Di Shi, Xin Chang, Liping Li, Mingyang Wu, Rui Song, Yintong Guo, Jupeng Tang, Jianjun Liu","doi":"10.1007/s13202-023-01725-z","DOIUrl":"https://doi.org/10.1007/s13202-023-01725-z","url":null,"abstract":"","PeriodicalId":16723,"journal":{"name":"Journal of Petroleum Exploration and Production Technology","volume":"5 12","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138980961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-09DOI: 10.1007/s13202-023-01721-3
Nabanita Pradhan, S. Datta Gupta
{"title":"Identification of challenging gas-bearing reservoir based on machine learning (ML) and computed conversion-based AVO analysis: a study from Jaisalmer Sub-basin, India","authors":"Nabanita Pradhan, S. Datta Gupta","doi":"10.1007/s13202-023-01721-3","DOIUrl":"https://doi.org/10.1007/s13202-023-01721-3","url":null,"abstract":"","PeriodicalId":16723,"journal":{"name":"Journal of Petroleum Exploration and Production Technology","volume":"9 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138585797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bedding planes are abundant in shale oil reservoirs, but the intrinsic mechanism of fracture-height containment by these weak interfaces remains unclear. To investigate the effects of interface properties, stress conditions, and fracturing fluid viscosity on the vertical propagation of fracture heights in laminated shale oil reservoirs, a three-dimensional hydro-mechanical coupling numerical model was developed. The model is based on the 3D discrete lattice algorithm (DLA), which replaces the balls and contacts in the conventional synthetic rock mass model (SRM) with a lattice consisting of spring-connected nodes, resulting in improved computational efficiency. Additionally, the interaction between hydraulic fractures and bedding planes is automatically computed using a smooth joint model (SJM), without making any assumptions about fracture trajectories or interaction conditions. The results indicate that a higher adhesive strength of the laminated surface promotes hydraulic fracture propagation across the interface. Increasing the friction coefficient of the laminated surface from 0.15 to 0.91 resulted in a twofold increase in the fracture height. Furthermore, as the difference between vertical and horizontal principal stresses increased, the longitudinal extension distance of the fracture height significantly increased, while the activated area of the laminar surface decreased dramatically. Moreover, increasing the viscosity of the fracturing fluid led to a decrease in filtration loss along the laminar surface of the fracture and a rapid increase in net pressure, making the hydraulic fracture more likely to cross the laminar surface directly. Therefore, for heterogeneous shale oil reservoirs, a reverse-sequence fracturing technique has been proposed to enhance the length and height of the fracture. This technique involves using a high-viscosity fracturing fluid to increase the fracture height before the main construction phase, followed by a low-viscosity slickwater fracturing fluid to activate the bedding planes and promote fracture complexity. To validate the numerical modeling results, five sets of laboratory hydraulic fracturing physical simulations were conducted in Jurassic terrestrial shale. The findings revealed that as the vertical stress difference ratio increased from 0.25 to 0.6, the vertical fracture area increased by 1.98 times. Additionally, increasing both the injection displacement and the viscosity of the fracturing fluid aided in fracture height crossing of the laminar facies. These results from numerical simulation and experimental studies offer valuable insights for hydraulic fracturing design in laminated shale oil reservoirs.
{"title":"Vertical height growth mechanism of hydraulic fractures in laminated shale oil reservoirs based on 3D discrete lattice modeling","authors":"Xin Chang, Xingyi Wang, Chunhe Yang, Yintong Guo, Kai Wei, Qiang Li, Chengbai Jiang","doi":"10.1007/s13202-023-01733-z","DOIUrl":"https://doi.org/10.1007/s13202-023-01733-z","url":null,"abstract":"<p>Bedding planes are abundant in shale oil reservoirs, but the intrinsic mechanism of fracture-height containment by these weak interfaces remains unclear. To investigate the effects of interface properties, stress conditions, and fracturing fluid viscosity on the vertical propagation of fracture heights in laminated shale oil reservoirs, a three-dimensional hydro-mechanical coupling numerical model was developed. The model is based on the 3D discrete lattice algorithm (DLA), which replaces the balls and contacts in the conventional synthetic rock mass model (SRM) with a lattice consisting of spring-connected nodes, resulting in improved computational efficiency. Additionally, the interaction between hydraulic fractures and bedding planes is automatically computed using a smooth joint model (SJM), without making any assumptions about fracture trajectories or interaction conditions. The results indicate that a higher adhesive strength of the laminated surface promotes hydraulic fracture propagation across the interface. Increasing the friction coefficient of the laminated surface from 0.15 to 0.91 resulted in a twofold increase in the fracture height. Furthermore, as the difference between vertical and horizontal principal stresses increased, the longitudinal extension distance of the fracture height significantly increased, while the activated area of the laminar surface decreased dramatically. Moreover, increasing the viscosity of the fracturing fluid led to a decrease in filtration loss along the laminar surface of the fracture and a rapid increase in net pressure, making the hydraulic fracture more likely to cross the laminar surface directly. Therefore, for heterogeneous shale oil reservoirs, a reverse-sequence fracturing technique has been proposed to enhance the length and height of the fracture. This technique involves using a high-viscosity fracturing fluid to increase the fracture height before the main construction phase, followed by a low-viscosity slickwater fracturing fluid to activate the bedding planes and promote fracture complexity. To validate the numerical modeling results, five sets of laboratory hydraulic fracturing physical simulations were conducted in Jurassic terrestrial shale. The findings revealed that as the vertical stress difference ratio increased from 0.25 to 0.6, the vertical fracture area increased by 1.98 times. Additionally, increasing both the injection displacement and the viscosity of the fracturing fluid aided in fracture height crossing of the laminar facies. These results from numerical simulation and experimental studies offer valuable insights for hydraulic fracturing design in laminated shale oil reservoirs.</p>","PeriodicalId":16723,"journal":{"name":"Journal of Petroleum Exploration and Production Technology","volume":"41 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138553179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01DOI: 10.1007/s13202-023-01726-y
Maryam Hajinorouz, Seyed Enayatollah Alavi
Most of oil reservoirs in the world have faced decrease in production and they are in the second half of their life cycle. Therefore, tertiary and enhanced oil recovery (EOR) techniques are needed for continuous production from these reservoirs. As choosing the most appropriate EOR methods for a reservoir is a challenging task for reservoir engineers, screening of EOR approaches is of high importance before any full field simulation and experiments. Enhanced oil recovery screening is a multiple criteria decision-making (MCDM) problem and hence, a systematic statistical algorithm based on MCDM can be used for this purpose. In this study, for the first time, a new EOR screening method is proposed by using VIKOR and Monte-Carlo algorithms. The approach used a large database of successful EOR projects around the world and was applied to 12 various EOR methods including a wide range of conditions and properties. Pre-processing was performed on the gathered database and then based on reservoir engineering analyses and using a pairwise comparison matrix, initial weights were considered for the parameters in each EOR method. Afterward, these weights were used in the proposed VIKOR MCDM calculation algorithm and the corresponding numerical values of EOR techniques for each reservoir were obtained. Finally, the EOR method with the highest corresponding value was selected as the most suitable method. Results demonstrated that by using the presented approach, a high classification accuracy of 98% was obtained for different cases, which shows the proficiency and robustness of the developed screening algorithm. In addition, the reliability of the developed method was validated using data obtained from 11 oil reservoirs in the southwest of Iran. Also, the results were compared with the results of previous studies and they were in a very good match. The developed approach is less expensive and faster than full field simulation method and can be used as an efficient EOR screening approach for reservoirs with different properties in the world.
{"title":"A new approach based on VIKOR and Monte-Carlo algorithms for determining the most efficient enhanced oil recovery methods: EOR screening","authors":"Maryam Hajinorouz, Seyed Enayatollah Alavi","doi":"10.1007/s13202-023-01726-y","DOIUrl":"https://doi.org/10.1007/s13202-023-01726-y","url":null,"abstract":"<p>Most of oil reservoirs in the world have faced decrease in production and they are in the second half of their life cycle. Therefore, tertiary and enhanced oil recovery (EOR) techniques are needed for continuous production from these reservoirs. As choosing the most appropriate EOR methods for a reservoir is a challenging task for reservoir engineers, screening of EOR approaches is of high importance before any full field simulation and experiments. Enhanced oil recovery screening is a multiple criteria decision-making (MCDM) problem and hence, a systematic statistical algorithm based on MCDM can be used for this purpose. In this study, for the first time, a new EOR screening method is proposed by using VIKOR and Monte-Carlo algorithms. The approach used a large database of successful EOR projects around the world and was applied to 12 various EOR methods including a wide range of conditions and properties. Pre-processing was performed on the gathered database and then based on reservoir engineering analyses and using a pairwise comparison matrix, initial weights were considered for the parameters in each EOR method. Afterward, these weights were used in the proposed VIKOR MCDM calculation algorithm and the corresponding numerical values of EOR techniques for each reservoir were obtained. Finally, the EOR method with the highest corresponding value was selected as the most suitable method. Results demonstrated that by using the presented approach, a high classification accuracy of 98% was obtained for different cases, which shows the proficiency and robustness of the developed screening algorithm. In addition, the reliability of the developed method was validated using data obtained from 11 oil reservoirs in the southwest of Iran. Also, the results were compared with the results of previous studies and they were in a very good match. The developed approach is less expensive and faster than full field simulation method and can be used as an efficient EOR screening approach for reservoirs with different properties in the world.</p>","PeriodicalId":16723,"journal":{"name":"Journal of Petroleum Exploration and Production Technology","volume":"53 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138528009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-25DOI: 10.1007/s13202-023-01722-2
Binbin Diao, Deli Gao, Sen Zhang, Zhe Liu
In order to realize the efficient development of unconventional oil and gas, the measurement accuracy of wellbore spacing in the drilling of parallel horizontal wells is more and more required. Although the Rotating Magnet Ranging System or Magnetic Guidance Tool is used to achieve a good ranging effect in the drilling of dual horizontal wells, the position measurement of the magnetic sub leads to a large ranging error. A new ranging algorithm for the Two Sensor Packages-Rotating Magnet Ranging System is presented in this paper. The algorithm takes the magnetic signal generated by the rotation of the magnetic sub at a fixed position, the tilt measurement data of the two wells, the length of the magnetic sub, and the distance between the two fluxgate sensors as input parameters to avoid measuring the position of the magnetic sub and to reduce the influence of the degree of non-parallelism and the length of the magnetic sub. The simulation and experiment demonstrate that the inclination and azimuth angles of the two wells have a significant impact on the magnetic ranging results when the ranging well sections are not parallel and that the distance between the bottom of the drill bit and the center of the magnetic sub cannot be ignored. Moreover, the accuracy of the relative distance calculated by this new algorithm can reach 97%, and the error of direction calculation is less than 3°. Applying this algorithm in the field can successfully aid in controlling the spacing of cluster horizontal wells more accurately.
{"title":"An algorithm to improve magnetic ranging accuracy for cluster horizontal wells with narrow spacings","authors":"Binbin Diao, Deli Gao, Sen Zhang, Zhe Liu","doi":"10.1007/s13202-023-01722-2","DOIUrl":"https://doi.org/10.1007/s13202-023-01722-2","url":null,"abstract":"<p>In order to realize the efficient development of unconventional oil and gas, the measurement accuracy of wellbore spacing in the drilling of parallel horizontal wells is more and more required. Although the Rotating Magnet Ranging System or Magnetic Guidance Tool is used to achieve a good ranging effect in the drilling of dual horizontal wells, the position measurement of the magnetic sub leads to a large ranging error. A new ranging algorithm for the Two Sensor Packages-Rotating Magnet Ranging System is presented in this paper. The algorithm takes the magnetic signal generated by the rotation of the magnetic sub at a fixed position, the tilt measurement data of the two wells, the length of the magnetic sub, and the distance between the two fluxgate sensors as input parameters to avoid measuring the position of the magnetic sub and to reduce the influence of the degree of non-parallelism and the length of the magnetic sub. The simulation and experiment demonstrate that the inclination and azimuth angles of the two wells have a significant impact on the magnetic ranging results when the ranging well sections are not parallel and that the distance between the bottom of the drill bit and the center of the magnetic sub cannot be ignored. Moreover, the accuracy of the relative distance calculated by this new algorithm can reach 97%, and the error of direction calculation is less than 3°. Applying this algorithm in the field can successfully aid in controlling the spacing of cluster horizontal wells more accurately.</p>","PeriodicalId":16723,"journal":{"name":"Journal of Petroleum Exploration and Production Technology","volume":"23 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138527997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-21DOI: 10.1007/s13202-023-01719-x
Harish C. Srivastava, Saurabh Mittal, Tony Kalra, Rajinder Parshad
Conventionally, volcanic margins have been considered devoid of hydrocarbon, but many discoveries and research in recent past have proved the presence of hydrocarbon prospects within them. However, hydrocarbon exploration within volcanic margin is constrained by seismic imaging. Further, identification of continent to oceanic boundary (COB) is critical to hydrocarbon search as hydrocarbon is found mostly over continental crust. Seaward dipping reflectors, associated with volcano-sedimentary sequences, located along rifted continental margins and represented by highly dipping strong amplitude seismic reflectors, play an important role to study volcanic margins. Keeping in view the problems of hydrocarbon exploration within volcanics, seaward dipping reflectors (SDRs) in Indian context have been studied in detail in this paper. It facilitates mapping of continent-oceanic boundary (COB). It has impact on hydrocarbon prospectivity in volcanic margins as it can provide formidable seal and secondary induced maturity. In India, several discoveries have been made in volcanic margins along west coast, from weathered, fractured basalt and sub-basalt sediments. In the present work, long offset regional seismic data (18 dip lines and 1 cross line), along east coast, have been interpreted. SDRs help in hydrocarbon prospectivity assessment for both discrimination of interbedded sediments and preferential accumulation of hydrocarbon. Mapping of linear features not only helped to demarcate COB but also their presence at 6–10 km depth. For the first time, such comprehensive study on SDRs has been done along Indian peninsular region with indications for hydrocarbon prospectivity at deeper levels along Indian peninsular region.
{"title":"Sub-basalt hydrocarbon prospect assessment in Peninsular India using seaward dipping reflectors","authors":"Harish C. Srivastava, Saurabh Mittal, Tony Kalra, Rajinder Parshad","doi":"10.1007/s13202-023-01719-x","DOIUrl":"https://doi.org/10.1007/s13202-023-01719-x","url":null,"abstract":"<p>Conventionally, volcanic margins have been considered devoid of hydrocarbon, but many discoveries and research in recent past have proved the presence of hydrocarbon prospects within them. However, hydrocarbon exploration within volcanic margin is constrained by seismic imaging. Further, identification of continent to oceanic boundary (COB) is critical to hydrocarbon search as hydrocarbon is found mostly over continental crust. Seaward dipping reflectors, associated with volcano-sedimentary sequences, located along rifted continental margins and represented by highly dipping strong amplitude seismic reflectors, play an important role to study volcanic margins. Keeping in view the problems of hydrocarbon exploration within volcanics, seaward dipping reflectors (SDRs) in Indian context have been studied in detail in this paper. It facilitates mapping of continent-oceanic boundary (COB). It has impact on hydrocarbon prospectivity in volcanic margins as it can provide formidable seal and secondary induced maturity. In India, several discoveries have been made in volcanic margins along west coast, from weathered, fractured basalt and sub-basalt sediments. In the present work, long offset regional seismic data (18 dip lines and 1 cross line), along east coast, have been interpreted. SDRs help in hydrocarbon prospectivity assessment for both discrimination of interbedded sediments and preferential accumulation of hydrocarbon. Mapping of linear features not only helped to demarcate COB but also their presence at 6–10 km depth. For the first time, such comprehensive study on SDRs has been done along Indian peninsular region with indications for hydrocarbon prospectivity at deeper levels along Indian peninsular region.</p>","PeriodicalId":16723,"journal":{"name":"Journal of Petroleum Exploration and Production Technology","volume":"21 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138528032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-15DOI: 10.1007/s13202-023-01711-5
Dandi Alvayed, Mohammed Sofian Ali Khalid, Moaz Dafaalla, Ahmed Ali, Ahmed Farid Ibrahim, Ruud Weijermars
{"title":"Correction to: Probabilistic estimation of hydraulic fracture half-lengths: validating the Gaussian pressure-transient method with the traditional rate transient analysis-method (Wolfcamp case study)","authors":"Dandi Alvayed, Mohammed Sofian Ali Khalid, Moaz Dafaalla, Ahmed Ali, Ahmed Farid Ibrahim, Ruud Weijermars","doi":"10.1007/s13202-023-01711-5","DOIUrl":"https://doi.org/10.1007/s13202-023-01711-5","url":null,"abstract":"","PeriodicalId":16723,"journal":{"name":"Journal of Petroleum Exploration and Production Technology","volume":"1 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138528004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-09DOI: 10.1007/s13202-023-01720-4
Pedro Esteves Aranha, Nara Angelica Policarpo, Marcio Augusto Sampaio
Abstract Predicting oil well behavior regarding the integrity of its equipment during production and anticipating behavioral changes and anomalies are among the main challenges in oil production. In this context, this study focuses on the development of predictive models for real-time monitoring of well behavior using sensor data from production wells. An unsupervised Novelty and Outlier Detection model has been introduced with a specific focus on predicting instances of unexpected subsurface safety valve closures in subsea wells. This model effectively classifies anomalies observed in these systems by leveraging real-world pressure and temperature data sourced from published literature. The methodology involves the implementation of a floating window for assembling training and test sets. Additionally, a comprehensive investigation is conducted into the impact of hyperparameters and the model’s threshold value (cp threshold). The results highlight the effectiveness of the developed model, observed through the accuracy achieved around 99.9% in predicting spurious closure events of the Downhole Safety Valve. On the same dataset, previous works reported 99.9% accuracy by using long short-term memory (LSTM) autoencoder, 87.1% by using random forest, and 60% with the Decision Tree method. Looking at F1-SCORE values, the developed model performs the best, followed by the LSTM model, both of which are significantly superior to the Decision Tree and random forest models. Furthermore, the model’s applicability is validated through testing in ultradeep water subsea wells within the pre-salt area of the Santos Basin. The significance lies in the potential for this research to enhance anomaly prediction in offshore wells, consequently reducing the costly interventions due to equipment malfunctions. Timely detection and corrective actions, facilitated by the model, can mitigate production loss and safeguard well integrity, addressing critical concerns in the oil and gas industry.
{"title":"Unsupervised machine learning model for predicting anomalies in subsurface safety valves and application in offshore wells during oil production","authors":"Pedro Esteves Aranha, Nara Angelica Policarpo, Marcio Augusto Sampaio","doi":"10.1007/s13202-023-01720-4","DOIUrl":"https://doi.org/10.1007/s13202-023-01720-4","url":null,"abstract":"Abstract Predicting oil well behavior regarding the integrity of its equipment during production and anticipating behavioral changes and anomalies are among the main challenges in oil production. In this context, this study focuses on the development of predictive models for real-time monitoring of well behavior using sensor data from production wells. An unsupervised Novelty and Outlier Detection model has been introduced with a specific focus on predicting instances of unexpected subsurface safety valve closures in subsea wells. This model effectively classifies anomalies observed in these systems by leveraging real-world pressure and temperature data sourced from published literature. The methodology involves the implementation of a floating window for assembling training and test sets. Additionally, a comprehensive investigation is conducted into the impact of hyperparameters and the model’s threshold value (cp threshold). The results highlight the effectiveness of the developed model, observed through the accuracy achieved around 99.9% in predicting spurious closure events of the Downhole Safety Valve. On the same dataset, previous works reported 99.9% accuracy by using long short-term memory (LSTM) autoencoder, 87.1% by using random forest, and 60% with the Decision Tree method. Looking at F1-SCORE values, the developed model performs the best, followed by the LSTM model, both of which are significantly superior to the Decision Tree and random forest models. Furthermore, the model’s applicability is validated through testing in ultradeep water subsea wells within the pre-salt area of the Santos Basin. The significance lies in the potential for this research to enhance anomaly prediction in offshore wells, consequently reducing the costly interventions due to equipment malfunctions. Timely detection and corrective actions, facilitated by the model, can mitigate production loss and safeguard well integrity, addressing critical concerns in the oil and gas industry.","PeriodicalId":16723,"journal":{"name":"Journal of Petroleum Exploration and Production Technology","volume":" 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135242790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-08DOI: 10.1007/s13202-023-01718-y
Farshad Farahbod
Abstract The gas condensate is one of the most valuable products of gas refineries. In unit 700 of the Sarkhon gas refinery, first, the gas condensate is separated from the feed. Then, the vapor pressure of the gas condensate is stabilized by de-ethanizer and de-butanizer towers. The H-701 and H-702 furnaces act as reboilers of the towers. In this research, unit 700 is simulated by HYSYS software. The product of this unit is examined to achieve desirable conditions. In addition, the best conditions are obtained to reduce the gas loss in this unit. The desirable conditions are introduced according to the operational problems of this unit. In this study, the environmental and economic loss due to the loss of hydrocarbons from the de-butanizer tower is identified. Results of this research show that the best operating temperature and pressure of the first feed are 40 °C and 29 bar, respectively. Also, the best temperature and pressure of the second feed are 20 °C and 28 bar, respectively. Also, the best temperature and pressure of the output stream from the S-701 as a feed of the T-701 are 34.35 °C and 22.51 bar, respectively.
{"title":"Improvement of operating conditions and composition of streams in gas condensate stabilization unit with the aim of reducing flare gas in Sarkhon and Qeshm gas plant","authors":"Farshad Farahbod","doi":"10.1007/s13202-023-01718-y","DOIUrl":"https://doi.org/10.1007/s13202-023-01718-y","url":null,"abstract":"Abstract The gas condensate is one of the most valuable products of gas refineries. In unit 700 of the Sarkhon gas refinery, first, the gas condensate is separated from the feed. Then, the vapor pressure of the gas condensate is stabilized by de-ethanizer and de-butanizer towers. The H-701 and H-702 furnaces act as reboilers of the towers. In this research, unit 700 is simulated by HYSYS software. The product of this unit is examined to achieve desirable conditions. In addition, the best conditions are obtained to reduce the gas loss in this unit. The desirable conditions are introduced according to the operational problems of this unit. In this study, the environmental and economic loss due to the loss of hydrocarbons from the de-butanizer tower is identified. Results of this research show that the best operating temperature and pressure of the first feed are 40 °C and 29 bar, respectively. Also, the best temperature and pressure of the second feed are 20 °C and 28 bar, respectively. Also, the best temperature and pressure of the output stream from the S-701 as a feed of the T-701 are 34.35 °C and 22.51 bar, respectively.","PeriodicalId":16723,"journal":{"name":"Journal of Petroleum Exploration and Production Technology","volume":"103 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135390045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}