WO2017171576A1 - Procédé de prédiction de la performance d'un puits pénétrant - Google Patents

Procédé de prédiction de la performance d'un puits pénétrant Download PDF

Info

Publication number
WO2017171576A1
WO2017171576A1 PCT/RU2016/000182 RU2016000182W WO2017171576A1 WO 2017171576 A1 WO2017171576 A1 WO 2017171576A1 RU 2016000182 W RU2016000182 W RU 2016000182W WO 2017171576 A1 WO2017171576 A1 WO 2017171576A1
Authority
WO
WIPO (PCT)
Prior art keywords
well
historical
performance characteristics
parameters
new
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/RU2016/000182
Other languages
English (en)
Inventor
Pavel Evgenievich SPESIVTSEV
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Schlumberger Canada Ltd
Services Petroliers Schlumberger SA
Schlumberger Technology BV
Schlumberger Technology Corp
Original Assignee
Schlumberger Canada Ltd
Services Petroliers Schlumberger SA
Schlumberger Technology BV
Schlumberger Technology Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Schlumberger Canada Ltd, Services Petroliers Schlumberger SA, Schlumberger Technology BV, Schlumberger Technology Corp filed Critical Schlumberger Canada Ltd
Priority to PCT/RU2016/000182 priority Critical patent/WO2017171576A1/fr
Publication of WO2017171576A1 publication Critical patent/WO2017171576A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • E—FIXED CONSTRUCTIONS
    • E21—EARTH OR ROCK DRILLING; MINING
    • E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
    • E21B41/00—Equipment or details not covered by groups E21B15/00 - E21B40/00
    • E—FIXED CONSTRUCTIONS
    • E21—EARTH OR ROCK DRILLING; MINING
    • E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
    • E21B43/00—Methods or apparatus for obtaining oil, gas, water, soluble or meltable materials or a slurry of minerals from wells
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]

Definitions

  • the present invention is related to the field of software technology and data analysis in the petroleum industry. More specifically, the present techniques are directed to systems and methods for predicting the future performance of new or planned oil and gas wells and determining parameters for the location, drilling and completion of a well based on the predicted performance of the well.
  • the prediction of the future performance of the new or planned well is important for making the economical evaluation of the well. If the poor production performance is predicted, then such parameters as the well location, drilling and completion strategies should be improved based on the predicted performance of the well. Once the parameters are changed, they can be used to get the updated production prediction using the presented invention to estimate if the changes lead to the positive impact on the economical parameters.
  • the production predictions provided by the present invention allow to solve the production optimization problem for new or planned wells. Predicting performance of the new wells is also critical for the large scale field development planning and for the financial forecasts of the field development projects. In the present invention, the prediction is based on the past observations and is done without performing numerical simulations that are usually CPU-time expensive. Hence, the predictions are provided significantly faster than using the traditional simulation-based approaches.
  • Disclosed is a method for predicting performance of a well penetrating an underground hydrocarbon bearing formation which doesn't require numerical simulations and includes machine learning and pattern recognition techniques implemented into the computer system and performed over all available historical data.
  • the method includes storing a well data comprising historical well parameters and historical well performance characteristics obtained from a plurality of operating wells in a knowledge database in a memory storage and performing, by a cognitive system, an analysis of said well data, wherein said analysis produces relationships between said historical well parameters and said historical well performance characteristics.
  • the method includes inputting, into the cognitive system, new well parameters characterizing an underground hydrocarbon bearing formation and a new well penetrating the formation and predicting, by the cognitive system, performance characteristics of said new well and a corresponding uncertainty of the prediction based on the produced relationships.
  • the method may also include planning at least one strategy of a group consisting of well location, drilling and completion strategies using the predicted performance characteristics, and implementing the planned strategies using hydrocarbon bearing formation equipment.
  • Fig. 1 shows a flowchart in accordance with one or more embodiments of the disclosure
  • Fig. 2 illustrates a computing system in accordance with one or more embodiments
  • Fig.3 shows an example of the method and a computing system in accordance with one embodiment.
  • the proposed invention provides the solution of the petroleum engineering problem without carrying out the time consuming numerical simulations.
  • Fig. 1 shows a flowchart in accordance with one or more embodiments.
  • the disclosed method comprises storing by a computing system in a knowledge database in tangible memory storage a well data comprising historical well parameters and historical well performance characteristics obtained from a plurality of operating wells drilled in hydrocarbon bearing formations (Block 1).
  • the well data stored in the knowledge database additionally comprises information from publications such as results of studies on optimal strategies of well drilling, completion, and production.
  • the well data stored in the knowledge database additionally comprises results of numerical simulations executed beforehand and providing the relations between at least part of the new well parameters and a simulated well performance. It is especially important in situations where the historical well parameters and the historical well performance characteristics are not enough or missing in the knowledge database.
  • the historical well parameters obtained from the plurality of operating wells comprise at least one of a group consisting of petrophysical properties of the hydrocarbon bearing formations, fluid properties, configuration of the wells.
  • the historical well performance characteristics obtained from the plurality of operating wells comprise at least one of a group consisting of flowrates of hydrocarbons, peak surface rates, pressure and temperature distribution in the wells and hydrocarbon bearing formations, duration of well cleanup or flowback.
  • the information from different sources can be assigned a relevance factor that will determine the overall contribution of this source to the prediction.
  • an analysis of said well data stored in the knowledge database is performed by a cognitive system of the computing system, wherein said analysis produces relationships between said historical well parameters and said historical well performance characteristics.
  • the cognitive system can have a form of hardware with the pre- installed software or a software only distributed for installation on commonly used hardware with the installed commonly used operation systems.
  • the cognitive system analyses the available information and establishes links and relations between the input historical well parameters of the problem (such as petrophysical properties of the underground hydrocarbon bearing formation, fluid properties, configuration of wells to deliver the hydrocarbons to surface) and the output parameters of the problem that is the historical performance of wells (e.g. surface flowrates of oil, water, and gas, peak surface rates, pressure and temperature distribution in the wells and hydrocarbon bearing formation, duration of well cleanup or flowback).
  • the cognitive system performs the data processing and analytics, and pattern recognition to improve the predictability of the well performance.
  • the historical well parameters can be combined in metrics containing numbers thus representing digital fingerprints of the historical wells.
  • the digital fingerprinting allows to convert the vast amounts of data in form of spatially and temporarily distributed arrays of parameters to a reduced and more compact form containing smaller amount of numbers. For example, instead of comparing two spatial logs of absolute permeability for the new and historical wells one will have to compare the two average values for the new and historical well over the measured interval.
  • the digital fingerprinting allows to execute the rapid search over the historical wells by comparison and analysis of the finger prints of the historical and new wells.
  • the digital fingerprint (metrics) can contain such values, as mean value of permeability, density of fluids at standard conditions, and other parameters relevant to the domain of oil and gas.
  • the new well parameters characterizing the underground hydrocarbon bearing formation and the new well penetrating the formation may comprise at least one of a group consisting of petrophysical properties of the hydrocarbon bearing formations, fluid properties, configuration of the new well.
  • the comparison of the parameters of the new well with the historical well parameters is performed by the cognitive system using data analytics techniques such as a machine learning or a pattern recognition.
  • the cognitive system of the computing system predicts the output parameters - performance characteristics of said new well and provides the associated uncertainties.
  • the predicted performance characteristics of the new well can comprise a hydrocarbon production from the well, a flow rate of a particular hydrocarbon from the well, pressure and temperature distribution in said new well and in said hydrocarbon bearing formation, a duration of the well cleanup or flowback, cumulative values of surface rates and peak values of the surface rates of hydrocarbons.
  • Workflow may also include planning well location, drilling and completion strategies using the predicted performance characteristics (Block 6), and implementing the planned strategies using hydrocarbon bearing formation equipment (Block 7).
  • the computing system may be of virtually any type regardless of the platform being used.
  • the computing system may be one or more mobile devices (e.g., laptop computer, smartphone, smartwatch, personal digital assistant, tablet computer, or other mobile device), desktop computers, servers, blades in a server chassis, or any other type of computing device or devices that includes at least the minimum processing power, memory, and input and output device(s) to perform one or more embodiments of the invention.
  • mobile devices e.g., laptop computer, smartphone, smartwatch, personal digital assistant, tablet computer, or other mobile device
  • desktop computers e.g., servers, blades in a server chassis, or any other type of computing device or devices that includes at least the minimum processing power, memory, and input and output device(s) to perform one or more embodiments of the invention.
  • FIG. 2 shows an example of the computing system in accordance with some embodiments.
  • the computing system may include a cognitive system 8 comprising a processor to perform the data analytics and generation of predictions, a memory storage 9 and a user interface 10.
  • the cognitive system 8 simulates the process of human thought using a numerical model.
  • Cognitive systems use data mining, machine learning, pattern recognition and language processing techniques to perform the analysis of data (see Smart Machines: IBM's Watson and the Era of Cognitive Computing by John E. Kelly III, Columbia Business School Publishing, 160 p., 2013 for more details on the cognitive systems). These features enable the cognitive systems to efficiently perform the analytics on the data available in the petroleum industry and provide data driven predictions for the new or planned wells.
  • the computing system comprises the memory storage 9 (e.g., random access memory (RAM), cache memory, flash memory, etc.), one or more storage device(s) (e.g., a hard disk, an optical drive such as a compact disk (CD) drive or digital versatile disk (DVD) drive, a flash memory stick, etc.), and numerous other elements and functionalities.
  • Software instructions in the form of computer readable program code to perform one or more embodiments may be stored, in whole or in part, temporarily or permanently, on a non-transitory computer readable medium such as a CD, DVD, storage device, a diskette, a tape, flash memory, physical memory, or any other computer readable storage medium.
  • the software instructions may correspond to computer readable program code that when executed by a processor(s), is configured to perform one or more embodiments of the method.
  • the computing system also comprises a user interface 10.
  • the conventional user interface provides a means for one or more users to provide information to the system and retrieve information therefrom.
  • the interface can be Windows-based graphical user interface (GUI) including a keyboard, a mouse and a display.
  • GUI graphical user interface
  • one or more elements of the aforementioned computing system may be located at a remote location and connected to the other elements over a network. Further, embodiments may be implemented on a distributed system having multiple nodes, where each portion of an embodiment may be located on a different node within the distributed system.
  • the node corresponds to a distinct computing device. Alternatively, the node may correspond to a computer processor with associated physical memory or to a computer processor or micro-core of a computer processor with shared memory and/or resources.
  • Figure 3 shows an example computing system in accordance with some embodiments of the disclosure.
  • horizontal wells after a multi-stage hydraulic fracturing treatment.
  • such wells share certain similarity in the design. They consist of a vertical segment connected with a horizontal part with fractures distributed along the horizontal interval.
  • the number of fractures is considered to be equally distributed and proportional to the length of the horizontal part.
  • the historical data is available for several wells with the horizontal part length from 2000 m to 5000 m.
  • the cognitive system 8 learns that the gas flowrate during the initial production stage is linearly proportional to the length of the horizontal interval given that the inflow points are equally distributed.
  • the data available for the cognitive system 8 include the following:
  • a new well with the horizontal part length of 3000 m long is planned for drilling. Before the drilling starts, the future performance of this well should be evaluated.
  • the information characterizing the new well is provided to the cognitive system 8 through an interface 10.
  • the cognitive system 8 will predict the performance of 38000 m 3 /day after the well flowback by the simple linear interpolation inside of the known range of parameters.
  • the proposed system will yield the output based on the past data analysis without performing numerical simulations.
  • the process is schematically illustrated in Fig. 3.
  • the forecast will be associated with uncertainties related to the differences in configuration between the analyzed and predicted wells.
  • the cognitive system will also apply the advanced data analysis algorithms to process the differences in configuration between the predicted wells and wells with available data. This analysis will be complemented with the information available from other sources such as publications (e.g. full academic journal papers, technical reports, books, etc).

Landscapes

  • Engineering & Computer Science (AREA)
  • Geology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mining & Mineral Resources (AREA)
  • Physics & Mathematics (AREA)
  • Geochemistry & Mineralogy (AREA)
  • Fluid Mechanics (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Environmental & Geological Engineering (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Le procédé selon l'invention comprend le stockage de données de puits comprenant des paramètres de puits historiques et des caractéristiques de performance de puits historiques obtenues à partir d'une pluralité de puits en fonctionnement dans une base de données de connaissances dans un stockage de mémoire et la réalisation, par un système cognitif, d'une analyse desdites données de puits, ladite analyse produisant des relations entre lesdits paramètres de puits historiques et lesdites caractéristiques de performance de puits historiques. Le procédé comprend en outre l'entrée, dans le système cognitif, de nouveaux paramètres de puits caractérisant une formation souterraine de gisement d'hydrocarbures et un nouveau puits pénétrant dans la formation. Sur la base des relations produites, le système cognitif prédit des caractéristiques de performance dudit nouveau puits et une incertitude correspondante de la prédiction. Le procédé peut également comprendre la planification d'au moins une stratégie d'un groupe constitué de stratégies de localisation, de forage et de complétion de puits à l'aide des caractéristiques de performance prédites, et la mise en œuvre des stratégies planifiées à l'aide d'un équipement de formation de gisement d'hydrocarbures.
PCT/RU2016/000182 2016-03-31 2016-03-31 Procédé de prédiction de la performance d'un puits pénétrant Ceased WO2017171576A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/RU2016/000182 WO2017171576A1 (fr) 2016-03-31 2016-03-31 Procédé de prédiction de la performance d'un puits pénétrant

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/RU2016/000182 WO2017171576A1 (fr) 2016-03-31 2016-03-31 Procédé de prédiction de la performance d'un puits pénétrant

Publications (1)

Publication Number Publication Date
WO2017171576A1 true WO2017171576A1 (fr) 2017-10-05

Family

ID=59966230

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/RU2016/000182 Ceased WO2017171576A1 (fr) 2016-03-31 2016-03-31 Procédé de prédiction de la performance d'un puits pénétrant

Country Status (1)

Country Link
WO (1) WO2017171576A1 (fr)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112049624A (zh) * 2019-06-06 2020-12-08 中国石油天然气股份有限公司 油井动态储量的预测方法、装置、设备及存储介质
WO2022256583A1 (fr) * 2021-06-03 2022-12-08 Conocophillips Company Identification par empreinte et apprentissage automatique pour prédictions de production
US11741359B2 (en) 2020-05-29 2023-08-29 Saudi Arabian Oil Company Systems and procedures to forecast well production performance for horizontal wells utilizing artificial neural networks
US11867054B2 (en) 2020-05-11 2024-01-09 Saudi Arabian Oil Company Systems and methods for estimating well parameters and drilling wells

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5251286A (en) * 1992-03-16 1993-10-05 Texaco, Inc. Method for estimating formation permeability from wireline logs using neural networks
EP0881357B1 (fr) * 1997-05-06 2004-10-27 Halliburton Energy Services, Inc. Procédé pour contrôler le développement d'un gisement de gaz ou d'huile
WO2009015031A1 (fr) * 2007-07-20 2009-01-29 Schlumberger Canada Limited Appareil, procédé et système pour un flux de travaux stochastique dans des opérations d'exploitation de champs pétrolifères
US20090194274A1 (en) * 2008-02-01 2009-08-06 Schlumberger Technology Corporation Statistical determination of historical oilfield data

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5251286A (en) * 1992-03-16 1993-10-05 Texaco, Inc. Method for estimating formation permeability from wireline logs using neural networks
EP0881357B1 (fr) * 1997-05-06 2004-10-27 Halliburton Energy Services, Inc. Procédé pour contrôler le développement d'un gisement de gaz ou d'huile
WO2009015031A1 (fr) * 2007-07-20 2009-01-29 Schlumberger Canada Limited Appareil, procédé et système pour un flux de travaux stochastique dans des opérations d'exploitation de champs pétrolifères
US20090194274A1 (en) * 2008-02-01 2009-08-06 Schlumberger Technology Corporation Statistical determination of historical oilfield data

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112049624A (zh) * 2019-06-06 2020-12-08 中国石油天然气股份有限公司 油井动态储量的预测方法、装置、设备及存储介质
CN112049624B (zh) * 2019-06-06 2024-04-30 中国石油天然气股份有限公司 油井动态储量的预测方法、装置、设备及存储介质
US11867054B2 (en) 2020-05-11 2024-01-09 Saudi Arabian Oil Company Systems and methods for estimating well parameters and drilling wells
US12385393B2 (en) 2020-05-11 2025-08-12 Saudi Arabian Oil Company Systems and methods for estimating well parameters and drilling wells
US12428957B2 (en) 2020-05-11 2025-09-30 Saudi Arabian Oil Company Systems and methods for estimating well parameters and drilling wells
US11741359B2 (en) 2020-05-29 2023-08-29 Saudi Arabian Oil Company Systems and procedures to forecast well production performance for horizontal wells utilizing artificial neural networks
WO2022256583A1 (fr) * 2021-06-03 2022-12-08 Conocophillips Company Identification par empreinte et apprentissage automatique pour prédictions de production

Similar Documents

Publication Publication Date Title
Ning et al. A comparative machine learning study for time series oil production forecasting: ARIMA, LSTM, and Prophet
Mo et al. A Taylor expansion‐based adaptive design strategy for global surrogate modeling with applications in groundwater modeling
US10198535B2 (en) Methods and systems for machine-learning based simulation of flow
Alarifi et al. Productivity index prediction for oil horizontal wells using different artificial intelligence techniques
Amirian et al. Artificial neural network modeling and forecasting of oil reservoir performance
Mohaghegh Subsurface analytics: Contribution of artificial intelligence and machine learning to reservoir engineering, reservoir modeling, and reservoir management
RU2752074C2 (ru) Компьютерный способ и вычислительная система для прогнозирования расходных характеристик потока в стволе скважины, проникающей в подземный углеводородный пласт
US11741359B2 (en) Systems and procedures to forecast well production performance for horizontal wells utilizing artificial neural networks
Fedutenko et al. Time-dependent neural network based proxy modeling of SAGD process
Calvette et al. Forecasting smart well production via deep learning and data driven optimization
Sudakov et al. Artificial neural network surrogate modeling of oil reservoir: A case study
CN118885863B (zh) 一种钻井难点预测与难点解决方案生成方法、装置及设备
Ma et al. Enhancing subsurface multiphase flow simulation with Fourier neural operator
Jung et al. Optimization of gas lift allocation for improved oil production under facilities constraints
Da Silva et al. Development of proxy models for petroleum reservoir simulation: a systematic literature review and state-of-the-art
Behl et al. Data-driven reduced-order models for volve field using reservoir simulation and physics-informed machine learning techniques
Foroud et al. Surrogate-based optimization of horizontal well placement in a mature oil reservoir
Fedutenko et al. Time-dependent proxy modeling of SAGD process
Hassani et al. A proxy modeling approach to optimization horizontal well placement
Petrosyants et al. Speeding up the reservoir simulation by real time prediction of the initial guess for the Newton-Raphson’s iterations
US20230140905A1 (en) Systems and methods for completion optimization for waterflood assets
Sarkar et al. Surrogate models for development of unconventional shale reservoirs by an integrated numerical approach of hydraulic fracturing, flow and geomechanics, and machine learning
Ma et al. Integration of artificial intelligence and production data analysis for shale heterogeneity characterization in SAGD reservoirs
Voskresenskii et al. Leveraging the power of spatial-temporal information with graph neural networks as the key to unlocking more accurate flow rate predictions
Zhang et al. Parameter optimization study of gas hydrate reservoir development based on a surrogate model assisted particle swarm algorithm

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16897235

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16897235

Country of ref document: EP

Kind code of ref document: A1