IP Library › Granted Patent US 12,412,001
Granted Patent B2
US 12,412,001 · App. 17/499,026 · Granted Sep 9, 2025

Generating well model flow tables for artificial intelligent models

Inventors: Obiomalotaoso Leonard Isichei (Abqaiq, SA); Ayman Alkhalaf (Dammam, SA); Said Almalki (Dhahran, SA); Najmul Hasan Ansari (Dhahran, SA)
Assignee: Saudi Arabian Oil Company
G06F30/12G06F8/315G06F30/27G06N20/00
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,412,001
App. No.
17/499,026
Granted
Sep 9, 2025
Kind
B2
Abstract

Systems and methods include a computer-implemented method for well models. Historical well data for past operations of a well is received. An expanded minimum/maximum range of values for the historical well data is generated for parameters used in a well model. Object-oriented object instances are generated using the historical well data and the expanded range. Each object instance is an object that includes a specific combination of parameters within the expanded range. The well model is executed using the instances, generating result objects, each representing a result of the well model. A hybrid well model variant of the well model is generated using the object instances and result objects to model combinations of the object instances and the result objects. A data object encapsulating the object instances and result objects is passed by an object-oriented application to a machine learning model in an absence of database tables.

Claims (54)

1. A computer-implemented method, comprising:

receiving historical well data corresponding to a well, wherein the historical well data comprises information about past operations of the well;

generating an expanded range of values for parameters used in a well model for the well, wherein the expanded range of values expands a range of values corresponding to the historical well data;

generating, using the historical well data and the expanded range of values, object-oriented object instances representing the historical well data, wherein each object-oriented object instance is an object configured to be used by the well model and comprising a combination of parameters within the expanded range of values;

executing the well model using the object-oriented object instances to generate result objects, wherein each result object is an object-oriented object instance representing a result of the well model;

generating, using the object-oriented object instances and the result objects, a hybrid well model variant of the well model that models combinations of the object-oriented object instances and the result objects;

passing, by an object-oriented application, a data object encapsulating the object-oriented object instances and the result objects to a machine learning model, wherein passing the data object occurs in an absence of database tables;

executing the machine learning model using the data object;

generating, in response to the executing, an electric submersible pump (ESP) optimization dashboard displaying suggestions for production improvements for a well; and

implementing user-selected suggestions to change settings on ESPs used in the well.

2. The computer-implemented method of claim 1 , further comprising:

determining that the well model for the well is valid comprises determining that data for the well model is complete.

3. The computer-implemented method of claim 1 , wherein the historical well data comprises well parameters of wellhead platform (WHP), gas-oil ratio (GOR), water cut (WC), productivity index (PI), and static bottom hole pressure (SBHP).

4. The computer-implemented method of claim 1 , wherein generating the expanded range of values for parameters used in a well model for the well includes and setting a minimum of the expanded range of values to a predetermined percentage less than a minimum of the range of values corresponding to the historical well data and setting a maximum of the expanded range of values to a predetermined percentage more than a maximum of the range of values corresponding to the historical well data.

5. The computer-implemented method of claim 4 , wherein the predetermined percentage is 50%.

6. The computer-implemented method of claim 1 , wherein the object-oriented application is implemented in Python.

7. The computer-implemented method of claim 1 , wherein the

settings on ESPs comprise a pump frequency.

8. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:

receiving historical well data corresponding to a well, wherein the historical well data comprises information about past operations of the well;

generating an expanded range of values for parameters used in a well model for the well, wherein the expanded range of values expands a range of values corresponding to the historical well data;

generating, using the historical well data and the expanded range of values, object-oriented object instances representing the historical well data, wherein each object-oriented object instance is an object configured to be used by the well model and comprising a combination of parameters within the expanded range of values;

executing the well model using the object-oriented object instances to generate result objects, wherein each result object is an object-oriented object instance representing a result of the well model;

generating, using the object-oriented object instances and the result objects, a hybrid well model variant of the well model that models combinations of the object-oriented object instances and the result objects;

passing, by an object-oriented application, a data object encapsulating the object-oriented object instances and the result objects to a machine learning model, wherein passing the data object occurs in an absence of database tables;

executing the machine learning model using the data object;

generating, in response to the executing, an electric submersible pump (ESP) optimization dashboard displaying suggestions for production improvements for a well; and

implementing user-selected suggestions to change settings on ESPs used in the well.

9. The non-transitory, computer-readable medium of claim 8 , the operations further comprising:

determining that the well model for the well is valid comprises determining that data for the well model is complete.

10. The non-transitory, computer-readable medium of claim 8 , wherein the historical well data comprises well parameters of wellhead platform (WHP), gas-oil ratio (GOR), water cut (WC), productivity index (PI), and static bottom hole pressure (SBHP).

11. The non-transitory, computer-readable medium of claim 8 , wherein generating the expanded range of values for parameters used in a well model for the well comprises and setting a minimum of the expanded range of values to a predetermined percentage less than a minimum of the range of values corresponding to the historical well data and setting a maximum of the expanded range of values to a predetermined percentage more than a maximum of the range of values corresponding to the historical well data.

12. The non-transitory, computer-readable medium of claim 11 , wherein the predetermined percentage is 50%.

13. The non-transitory, computer-readable medium of claim 8 , wherein the object-oriented application is implemented in Python.

14. The non-transitory, computer-readable medium of claim 8 , wherein the

settings on ESPs comprise a pump frequency.

15. A computer-implemented system, comprising:

one or more processors; and

a non-transitory computer-readable storage medium coupled to the one or more processors and storing programming instructions for execution by the one or more processors, the programming instructions instructing the one or more processors to perform operations comprising:

receiving historical well data corresponding to a well, wherein the historical well data comprises information about past operations of the well;

generating an expanded range of values for parameters used in a well model for the well, wherein the expanded range of values expands a range of values corresponding to the historical well data;

generating, using the historical well data and the expanded range of values, object-oriented object instances representing the historical well data, wherein each object-oriented object instance is an object configured to be used by the well model and comprising a combination of parameters within the expanded range of values;

executing the well model using the object-oriented object instances to generate result objects, wherein each result object is an object-oriented object instance representing a result of the well model;

generating, using the object-oriented object instances and the result objects, a hybrid well model variant of the well model that models combinations of the object-oriented object instances and the result objects;

passing, by an object-oriented application, a data object encapsulating the object-oriented object instances and the result objects to a machine learning model, wherein passing the data object occurs in an absence of database tables;

executing the machine learning model using the data object;

generating, in response to the executing, an electric submersible pump (ESP) optimization dashboard displaying suggestions for production improvements for a well; and

implementing user-selected suggestions to change settings on ESPs used in the well.

16. The computer-implemented system of claim 15 , the operations further comprising:

determining that the well model for the well is valid comprises determining that data for the well model is complete.

17. The computer-implemented system of claim 15 , wherein the historical well data comprises well parameters of wellhead platform (WHP), gas-oil ratio (GOR), water cut (WC), productivity index (PI), and static bottom hole pressure (SBHP).

18. The computer-implemented system of claim 15 , wherein generating the expanded range of values for parameters used in a well model for the well comprises and setting a minimum of the expanded range of values to a predetermined percentage less than a minimum of the range of values corresponding to the historical well data and setting a maximum of the expanded range of values to a predetermined percentage more than a maximum of the range of values corresponding to the historical well data.

19. The computer-implemented system of claim 18 , wherein the predetermined percentage is 50%.

20. The computer-implemented system of claim 15 , wherein the object-oriented application is implemented in Python.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 13, 2021
From: ISICHEI, OBIOMALOTAOSO LEONARD; ALKHALAF, AYMAN; ALMALKI, SAID; ANSARI, NAJMUL HASAN
To: SAUDI ARABIAN OIL COMPANY
Reel/Frame 057776/0863 →
Continuity (1)
Related Publication 20230114355A1 · Apr 13, 2023
References Cited (115)
US 4757314A · Aubin · 1988 [cited by applicant]
US 5871047A · Spath et al. · 1999 [cited by applicant]
US 5975204A · Tubel et al. · 1999 [cited by applicant]
US 6046685A · Tubel · 2000 [cited by applicant]
US 6356844B2 · Thomas et al. · 2002 [cited by applicant]
US 7259688B2 · Hirsch et al. · 2007 [cited by applicant]
US 7478024B2 · Gurpinar et al. · 2009 [cited by applicant]
US 7584165B2 · Buchan · 2009 [cited by applicant]
US 7828065B2 · Ross et al. · 2010 [cited by applicant]
US 8280635B2 · Ella et al. · 2012 [cited by applicant]
US 8761911B1 · Chapman et al. · 2014 [cited by applicant]
US 9745833B2 · Carvajal et al. · 2017 [cited by applicant]
US 10055684B2 · Fleming et al. · 2018 [cited by applicant]
US 10133831B2 · Carvajal et al. · 2018 [cited by applicant]
US 10317331B2 · Guner et al. · 2019 [cited by applicant]
US 10345764B2 · Early et al. · 2019 [cited by applicant]
US 10508521B2 · Shammari et al. · 2019 [cited by applicant]
US 10586173B2 · Hammond et al. · 2020 [cited by applicant]
US 10839069B2 · Shen et al. · 2020 [cited by applicant]
US 10962968B2 · Al-Maghlouth et al. · 2021 [cited by applicant]
US 20040044499A1 · House · 2004 [cited by applicant]
US 20050044451A1 · Fry et al. · 2005 [cited by applicant]
US 20060010352A1 · Mukherjee et al. · 2006 [cited by applicant]
US 20060086497A1 · Ohmer et al. · 2006 [cited by applicant]
US 20070016389A1 · Ozgen et al. · 2007 [cited by applicant]
US 20070198223A1 · Ella et al. · 2007 [cited by applicant]
US 20070198234A1 · Zangi et al. · 2007 [cited by applicant]
US 20070252717A1 · Fielder · 2007 [cited by applicant]
US 20080251260A1 · Ross et al. · 2008 [cited by applicant]
US 20100023269A1 · Yusti et al. · 2010 [cited by applicant]
US 20100299125A1 · Ding et al. · 2010 [cited by applicant]
US 20130035920A1 · Al-Shammari · 2013 [cited by applicant]
US 20130151020A1 · Manninen et al. · 2013 [cited by applicant]
US 20130175030A1 · Ige et al. · 2013 [cited by applicant]
US 20130304680A1 · Bailey et al. · 2013 [cited by applicant]
US 20140244552A1 · Liu et al. · 2014 [cited by applicant]
US 20140261791A1 · Grabau et al. · 2014 [cited by applicant]
US 20160123111A1 · Kim · 2016 [cited by applicant]
US 20160217379A1 · Patri et al. · 2016 [cited by applicant]
US 20170096889A1 · Blanckaert et al. · 2017 [cited by applicant]
US 20170114619A1 · Conn et al. · 2017 [cited by applicant]
US 20170284191A1 · Martin et al. · 2017 [cited by applicant]
US 20170363088A1 · Nguyen et al. · 2017 [cited by applicant]
US 20180165604A1 · Minkin et al. · 2018 [cited by applicant]
US 20180171761A1 · Schneider et al. · 2018 [cited by applicant]
US 20180188403A1 · Halsey et al. · 2018 [cited by applicant]
US 20180230780A1 · Klenner et al. · 2018 [cited by applicant]
US 20180372909A1 · Mishkhes et al. · 2018 [cited by applicant]
US 20190287005A1 · Subramaniyan et al. · 2019 [cited by applicant]
US 20200011169A1 · Haghshenas et al. · 2020 [cited by applicant]
US 20200141412A1 · Nguyen et al. · 2020 [cited by applicant]
US 20200150634A1 · Gray et al. · 2020 [cited by applicant]
US 20210231003A1 · Alkhalaf · 2021 [cited by applicant]
US 20210254451A1 · Halder et al. · 2021 [cited by applicant]
CN 102754105 · 2012 [cited by applicant]
CN 203322437 · 2013 [cited by applicant]
CN 103842615 · 2014 [cited by applicant]
CN 105493100 · 2016 [cited by applicant]
CN 105706089 · 2016 [cited by applicant]
CN 109558967 · 2019 [cited by applicant]
EP 2951720 · 2015 [cited by applicant]
EP 3073051 · 2016 [cited by applicant]
EP 3376361 · 2018 [cited by applicant]
FR 2950993 · 2011 [cited by applicant]
WO WO2007107815 · 2007 [cited by applicant]
WO WO2013090416 · 2013 [cited by applicant]
WO WO2015047594 · 2015 [cited by applicant]
WO WO2016010813 · 2016 [cited by applicant]
WO WO2016022069 · 2016 [cited by applicant]
WO WO2016153895 · 2016 [cited by applicant]
WO WO2016186627 · 2016 [cited by applicant]
WO WO2017040457 · 2017 [cited by applicant]
WO WO2017074883 · 2017 [cited by applicant]
WO WO2017111964 · 2017 [cited by applicant]
WO WO2017151838 · 2017 [cited by applicant]
WO WO2017161126 · 2017 [cited by applicant]
WO WO2017165949 · 2017 [cited by applicant]
WO WO2018033524 · 2018 [cited by applicant]
WO WO2018132786 · 2018 [cited by applicant]
WO WO2021073763 · 2021 [cited by applicant]
A. Alkhalaf, O. Isichei, N. Ansari, R. Milad, “Utilizing Machine Learning for a Data Driven Approach to Flow Rate Prediction”, pp. 1-9, 2019 (Year: 2019). [cited by examiner]
O. Akinnikawe, S. Lyne, J. Roberts, Synthetic Well Log Generation Using machine learning Techniques, pp. 23-25, Jul. 2018 (Year: 2018). [cited by examiner]
Akinnikawe et al., “Synthetic Well Log Generation Using Machine Learning Techniques,” Unconventional Resources Technology Conference, Houston, Texas, Jul. 23-25, 2018, 16 pages. [cited by applicant]
AlAjmi et al., “Profiling Downhole Casing Integrity Using Artificial Intelligence,” SPE-173422-MS, Society of Petroleum Engineers, SPE Digital Energy Conference and Exhibition in the Woodlands, Texas, Mar. 3-5, 2015, 13… [cited by applicant]
Al-Ajmi et al., “Risk based statistical approach to predict casing leaks,” SPE 183948, Presented at SPE Middle East Oil & Gas Show and Conference, Manama, Kingdom of Bahrain, Mar. 6-9, 2017; Society of Petroleum Enginee… [cited by applicant]
Al-Hajri et al., “Calculating Casing Leak Cross Flow Rate Using Surface Injection Data,” SPE-188107-MS, Society of Petroleum Engineers (SPE), presented at the SPE Kingdom of Saudi Arabia Annual Technical Symposium and E… [cited by applicant]
Alkhalaf et al., “Machine Learning Approach to Classify Water Cut Measurements using DAS Fiber Optic Data,” SPE-197349-MS, Society of Petroleum Engineers, Nov. 2019, 9 pages. [cited by applicant]
Alkhalaf et al., “Utilizing Machine Learning for a Data Driven Approach to Flow Rate Prediction,” SPE-197266-MS, Society of Petroleum Engineers, Nov. 2019, XP055792195, 9 pages. [cited by applicant]
Al-Mulhim et al., “Integrated Production Logging Approach for Successful Leak Detection Between Two Formations: A Case Study,” SPE 174835, Presented at the SPE Annual Technical Conference and Exhibition, Houston, TX, Se… [cited by applicant]
Al-Shehri, “Oil and Gas Wells: Enhanced Wellbore Casing Integrity Management through Corrosion Rate Prediction Using an Augmented Intelligent Approach,” Sustainability, 2019, 11:818, 17 pages. [cited by applicant]
Alzate et al., “Generating Synthetic Well Logs by Artificial Neural Networks (ANN) Using MISO-ARMAX Model in Cupiagua Field,” SPE-169388, presented at the SPE Latin American and Caribbean Petroleum Engineering Conferenc… [cited by applicant]
Ardian et al., “Recovering Well Productivity in Banyu Urip Field,” SPE 165793, Oct. 22, 2013, 7 pages. [cited by applicant]
Banks, “Take Control: Smart Valves Step Forward,” (XP055401051), Offshore-Technology.com, Jun. 18, 2008; 6 pages, <http://www.offshore-technology.com/features/feature2034/>, 6 pages. [cited by applicant]
Batista et al., “A complexity-invariant distance measure for time series,” Data Mining and Knowledge Discovery, Apr. 2013, 28(3): 634-669. [cited by applicant]
Batista et al., “m(6)A RNA Modification Controls Cell Fate Transition in Mammalian Embryonic Stem Cells,” Cell Stem Cell vol. 15, No. 1-13, Dec. 4, 2014, 14 pages. [cited by applicant]
Box et al., Time series analysis: forecasting and control, 3rd ed., Prentice-Hall International, Inc., 1994, 598 pages. [cited by applicant]
Das et al., “Preventing leaks through RUL prediction modeling: case integrity in HP/HT environment,” SPE 184417, Presented at the SPE Health, Safety, Security, Environment, & Social Responsibility Conference, New Orlean… [cited by applicant]
Falcone et al., “Model Predicts More Accurate PI Over a Field's Life,” Oil and Gas Journal, Pennwell Houston, Texas, vol. 99, No. 12, Mar. 19, 2001, 5 pages. [cited by applicant]
Fulcher et al., “Highly comparative future-based time-series classification,” IEEE Transactions in Knowledge and Data Engineering, May 2014, 26:3026-3037. [cited by applicant]
Gryzlov et al., “Novel Methods for Production Data Forecast Utilizing Machine Learning and Dynamic Mode Decomposition,” SPE-202792-MS, Society of Petroleum Engineers, Nov. 2020, XP055792220, 12 pages. [cited by applicant]
Husain et al., “Quantifying the Intelligent Field Added Values,” (SPE 167439) Oct. 30, 2013; 9 pages, <https://www.onepetro.org/download/conference-paper/SPE-167439-MS?id=conference-paper/SPE-167439-MS>. [cited by applicant]
Hwang and Elsinger, “Detecting Production Tubing Leak by Time Resolved Geochemical Analysis of Oils,” SPE 29478, Society of Petroleum Engineers, presented at the Production Operations Symposium in Oklahoma City, OK, Apr… [cited by applicant]
Mohaghegh et al., “Virtual Magnetic Imaging Logs: Generation of Synthetic MRI Logs from Conventional Well Logs,” SPE 51075, presented at the 1998 SPE Eastern Regional Meeting, Pittsburg, PA, Nov. 9-11, 1998, 10 pages. [cited by applicant]
Richman and Moorman, “Physiological time-series analysis using approximate entropy and sample entropy,” American Journal of Physiol. Health Circ. Physiol, Jul. 2000, vol. 278: H2039-H2049, 11 pages. [cited by applicant]
Sawyer et al., “A simulation-based spreadsheet program for history matching and forecasting shale gas production” Society of Petroleum Engineers, Oct. 1999, 8 pages. [cited by applicant]
Schreiber and Schmitz, “Discrimination power of measures for nonlinearity in a time series,” Physical Review E, May 1997, 55(5): 5443-5447. [cited by applicant]
Singh et al., “Detecting Subsurface Fluid Leaks in Real-Time Using Injection and Production Rates,” Advances in Water Resources 2017, 110: 147-165, 19 pages. [cited by applicant]
Siu et al., “Re-Engineering the Well Calibration Procedure for a Large Number of High Productivity Wells,” SPE 66385, Proceedings of SPE Reservoir Simulation Symposium, Jan. 1, 2001, 14 pages. [cited by applicant]
Storey, “Building a Maintenance Management Program for Valves,” Control Engineering, Web page, Apr. 17, 2014; 3 pages <http://www.controleng.com/industry-news/single-article/building-a-maintenance-management-program-for… [cited by applicant]
Tursinbayeva et al., “Improving TCO Well Integrity Process through Successful Deployment of Well Integrity Portal,” SPE-189022-MS, Society of Petroleum Engineers (SPE), presented at the SPE Annual Caspian Technology Con… [cited by applicant]
Walker and Duncan, “Estimation of the Probability of an Event as a Function of Several Independent Variables,” Biometrika, Jun. 1967, 54(1/2): 167-179. [cited by applicant]
Watfa, “Downhole Casing Corrosion Monitoring and Interpretation Techniques to Evaluate Corrosion in Multiple Casing Strings,” SPE Production Engineering, Aug. 1991, 8 pages. [cited by applicant]
Yang et al., “Downhole leak detection: introducing a new wireline array noise tool,” SPE 194264, Presented at the SPE/ICoTA Well Intervention Conference and Exhibition, The Woodlands, TX, Mar. 26-27, 2019; Society of Pe… [cited by applicant]
Yang et al., “Intelligent Oilfield—Cloud Based Big Data Service in Upstream Oil and Gas,” IPTC-19418-MS, International Petroleum Technology Conference, Mar. 2019, XP055792661, 15 pages. [cited by applicant]
Yentes et al., “The Appropriate Use of Approximate Entropy and Sample Entropy with Short Data Sets,” Annals of Biomedical Engineering, Feb. 2013, 41(2): 349-365. [cited by applicant]