CN114861984A - For predicting high CO content 2 Method and processor for condensing volume of oil ring of gas reservoir - Google Patents

For predicting high CO content 2 Method and processor for condensing volume of oil ring of gas reservoir Download PDF

Info

Publication number
CN114861984A
CN114861984A CN202210375387.3A CN202210375387A CN114861984A CN 114861984 A CN114861984 A CN 114861984A CN 202210375387 A CN202210375387 A CN 202210375387A CN 114861984 A CN114861984 A CN 114861984A
Authority
CN
China
Prior art keywords
volume
prediction model
oil ring
target
determining
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.)
Pending
Application number
CN202210375387.3A
Other languages
Chinese (zh)
Inventor
陈浩
蒋东梁
张一琦
邢建鹏
杨冉
秦起超
唐建东
左名圣
刘希良
芮振华
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.)
China University of Petroleum Beijing
Original Assignee
China University of Petroleum Beijing
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 China University of Petroleum Beijing filed Critical China University of Petroleum Beijing
Priority to CN202210375387.3A priority Critical patent/CN114861984A/en
Publication of CN114861984A publication Critical patent/CN114861984A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/10—Numerical modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/70—Combining sequestration of CO2 and exploitation of hydrocarbons by injecting CO2 or carbonated water in oil wells

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Software Systems (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • General Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Educational Administration (AREA)
  • General Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Data Mining & Analysis (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Primary Health Care (AREA)
  • Computing Systems (AREA)
  • Operations Research (AREA)
  • Mathematical Physics (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the application provides a method for predicting high CO content 2 A method, apparatus and processor for condensing the volume of an oil ring of a gas reservoir. The method comprises the following steps: establishing an oil ring volume prediction database; determining a parameter correlation between each influencing parameter and the corresponding oil ring volume; determining the influence parameters with the parameter association degree larger than the preset parameter association degree as the main control parameters; inputting the parameter value corresponding to the main control parameter into the volume prediction model of the oil ring to obtain the volume predictionMeasuring the predicted volume output by the model; determining a target kernel function of the volume prediction model according to the prediction volume to obtain a target volume prediction model; high CO content to be predicted 2 And inputting the main control parameters of the condensate gas reservoir into the target volume prediction model to obtain a predicted value aiming at the volume of the oil ring output by the target volume prediction model. By the technical scheme, the prediction accuracy can be improved, the prediction process is simple, convenient and quick, and the prediction time is greatly shortened.

Description

For predicting high CO content 2 Method and processor for condensing volume of oil ring of gas reservoir
Technical Field
The application relates to the field of data processing, in particular to a method for predicting high CO content 2 A method, apparatus and processor for condensing the volume of an oil ring of a gas reservoir.
Background
The condensate gas reservoir can simultaneously produce condensate gas and condensate oil, and has higher economic value. Wherein, the content of CO is high 2 The condensate gas reservoir has a good carbon negative effect, can greatly supplement clean energy, and is an important component of carbon capture, carbon utilization and carbon storage technology for realizing zero emission in the future. And the volume of the condensate gas reservoir oil ring is an important basis for evaluating and developing the condensate gas reservoir. Therefore, the main factors which clearly influence the volume of the condensate gas reservoir oil ring have important significance for accurately predicting the size of the condensate gas reservoir oil ring volume.
High CO content compared with conventional gas reservoir 2 The condensate gas reservoir belongs to offshore deepwater gas reservoirs. High content of CO 2 CO in condensate gas reservoirs 2 Can be dissolved in crude oil and can extract certain components in the crude oil. At the same time, high CO content 2 The condensate gas is stored in the development process and can generate reverse condensationAnd (5) separating the phenomenon. Therefore, it is difficult to accurately predict high CO content by large-scale drilling 2 Oil ring volume of condensate gas reservoir. At present, the method of conventional theoretical formula, physical simulation, numerical simulation and the like is generally adopted to predict the high CO content 2 Oil ring volume of condensate reservoir. However, the methods for prediction are complicated in process, high in required time cost and low in prediction accuracy.
Disclosure of Invention
The embodiment of the application aims to provide a method for predicting high CO content 2 A method, apparatus and processor for condensing the volume of an oil ring of a gas reservoir.
In order to achieve the above object, the present application provides, in a first aspect, a method for predicting high CO content 2 A method of condensing the volume of a gas reservoir oil ring, comprising:
establishing an oil ring volume prediction database, wherein the oil ring volume prediction database comprises a plurality of pairs of high CO content 2 Influence parameters influencing the volume of the condensate gas reservoir oil ring;
determining a parameter correlation between each influencing parameter and the corresponding oil ring volume;
determining the influence parameters with the parameter association degree larger than the preset parameter association degree as main control parameters;
inputting the parameter value corresponding to the main control parameter into a volume prediction model of the oil ring to obtain a predicted volume output by the volume prediction model;
determining a target kernel function of the volume prediction model according to the prediction volume to obtain a target volume prediction model;
high CO content to be predicted 2 And inputting the main control parameters of the condensate gas reservoir into the target volume prediction model to obtain a predicted value aiming at the volume of the oil ring output by the target volume prediction model.
In an embodiment of the present application, the number of the volume prediction models is multiple, each of the volume prediction models uses a different kernel function, and determining a target kernel function of the volume prediction model according to the prediction volume to obtain the target volume prediction model includes: dividing the main control parameters into a training set and a prediction set; respectively inputting the main control parameters in the training set and the main control parameters in the prediction set into the volume prediction models aiming at each volume prediction model; obtaining a prediction volume output by a volume prediction model according to the main control parameters in the prediction set; determining a volume error value between the actual volume of each master control parameter and the corresponding predicted volume; and determining the volume prediction model with the minimum mean value of the volume error values as a target volume prediction model, and determining the kernel function used by the target volume prediction model as a target kernel function.
In an embodiment of the present application, the evaluation index includes at least one of a mean relative error, a mean-square relative error, a mean absolute error, and a coefficient, and determining an objective kernel function of the volume prediction model according to the prediction volume to obtain the objective volume prediction model further includes: determining an index value of each evaluation index according to each volume error value; determining the mean value of the index values of each evaluation index; determining the total index mean value of all the evaluation indexes included in each volume prediction model, wherein the total index mean value is determined according to the mean value of the index value of each evaluation index; and determining the volume prediction model corresponding to the minimum index total mean value as a target volume prediction model, and determining the kernel function used by the target volume prediction model as a target kernel function.
In the examples of the present application, the high CO content to be predicted 2 The method comprises the following steps of inputting main control parameters of a condensate gas reservoir into a target volume prediction model to obtain a predicted value aiming at the volume of an oil ring output by the target volume prediction model: determining the high CO content according to a preset state equation and main control parameters 2 The simulated volume of the condensate gas reservoir oil ring; determining a first error value between the simulated volume and the actual volume and a second error value between the predicted value for the oil ring volume and the actual volume; and determining the training completion degree of the target volume prediction model according to the first error value and the second error value.
In an embodiment of the present application, determining the training completion of the target volume prediction model based on the first error value and the second error value comprises: determining the training completion degree of the target volume prediction model as a first completion degree under the condition that the first error value is larger than the second error value; determining the training completion degree of the target volume prediction model as a second completion degree under the condition that the first error value is smaller than or equal to a second error value and the second error value is smaller than or equal to a preset error; and determining the training completion degree of the target volume prediction model as a third completion degree under the condition that the first error value is smaller than or equal to the second error value and the second error value is larger than the preset error.
In an embodiment of the application, the method further comprises: determining a high CO content to be predicted according to a predicted value output by a target volume prediction model and aiming at the volume of an oil ring 2 A target exploitation mode of the condensate gas reservoir; will be directed to high CO content to be predicted 2 Switching the exploitation mode of the condensate gas reservoir to a target exploitation mode; wherein the target mining mode comprises any one of the following mining modes: exploiting the gas reservoir only without exploiting the oil reservoir, opening the oil reservoir first and then exploiting the gas reservoir, opening the oil reservoir first and then exploiting the oil reservoir, and exploiting the oil reservoir and the gas reservoir simultaneously.
In embodiments of the present application, the influencing parameter comprises high CO content 2 At least one of a formation parameter, a gasoline ratio parameter, and a gas composition parameter of the condensate gas reservoir oil ring, wherein the formation parameter comprises a formation temperature parameter and a formation pressure parameter.
In a second aspect, the present application provides a method for predicting high CO content 2 An apparatus for condensing the volume of a gas reservoir oil ring, comprising:
the database establishing module is used for establishing an oil ring volume prediction database which comprises a plurality of pairs of high CO content 2 Influence parameters influencing the volume of the condensate gas reservoir oil ring;
the main control parameter determining module is used for determining the parameter association degree between each influence parameter and the corresponding oil ring volume, and determining the influence parameters with the parameter association degree larger than the preset parameter association degree as the main control parameters;
the prediction model determining module is used for inputting the parameter values corresponding to the main control parameters into the volume prediction model of the oil ring to obtain the prediction volume output by the volume prediction model, and determining the target kernel function of the volume prediction model according to the prediction volume to obtain the target volume prediction model;
oil ring volume predictionModule for converting the high CO content to be predicted 2 And inputting the main control parameters of the condensate gas reservoir into the target volume prediction model to obtain a predicted value which is output by the target volume prediction model and aims at the volume of the oil ring.
In an embodiment of the application, the apparatus further comprises: a mining type determination module for determining the high CO content to be predicted according to the predicted value output by the target volume prediction model and aiming at the volume of the oil ring 2 The target exploitation mode of the condensate gas reservoir aims at the high CO content to be predicted 2 And switching the exploitation mode of the condensate gas reservoir to a target exploitation mode.
A third aspect of the present application provides a processor configured to perform the above method for predicting high CO content 2 A method for condensing the volume of an oil ring of a gas reservoir.
By the technical scheme, high CO content is influenced 2 Inputting the main control parameter of the volume of the condensate gas reservoir oil ring into a volume prediction model to train the volume prediction model, determining a target kernel function to obtain a target volume prediction model corresponding to the target kernel function, and predicting the high CO content through the target volume prediction model 2 The volume of the condensate gas reservoir oil ring is predicted, and the prediction accuracy of the volume of the oil ring can be improved. And the prediction process is simple, convenient and quick, and the prediction time of the volume of the oil ring can be greatly shortened.
Additional features and advantages of embodiments of the present application will be described in detail in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the embodiments of the disclosure, but are not intended to limit the embodiments of the disclosure. In the drawings:
FIG. 1 schematically shows a method for predicting high CO content according to an embodiment of the present application 2 A schematic flow diagram of a method of condensing the oil ring volume of a gas reservoir;
FIG. 2 schematically shows a method for predicting high CO content according to an embodiment of the present application 2 A schematic of the parameter correlation of the method for condensing the gas reservoir oil ring volume;
FIG. 3 schematically shows a method for predicting high CO content according to an embodiment of the present application 2 A prediction result schematic diagram of a volume prediction model using a linear SVM of the method for condensing the volume of the oil ring of the gas reservoir;
FIG. 4 schematically shows a method for predicting high CO content according to an embodiment of the present application 2 A prediction result schematic diagram of a volume prediction model using a quadratic Support Vector Machine (SVM) of the method for condensing the volume of the oil ring of the gas reservoir;
FIG. 5 schematically shows a method for predicting high CO content according to an embodiment of the present application 2 A prediction result schematic diagram of a volume prediction model using a cubic SVM of the method for condensing the volume of the oil ring of the gas reservoir;
FIG. 6 schematically shows a method for predicting high CO content according to an embodiment of the present application 2 A prediction result schematic diagram of a volume prediction model using a Gaussian SVM of the method for condensing the volume of the oil ring of the gas reservoir;
FIG. 7 schematically shows a method for predicting high CO content according to an embodiment of the present application 2 A block diagram of a device for condensing the oil ring volume of a gas reservoir;
FIG. 8 schematically illustrates a method for predicting high CO content according to another embodiment of the present application 2 A block diagram of a device for condensing the oil ring volume of a gas reservoir;
fig. 9 schematically shows an internal structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the specific embodiments described herein are only used for illustrating and explaining the embodiments of the present application and are not used for limiting the embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
FIG. 1 schematically shows a method for predicting high CO content according to an embodiment of the present application 2 Condensate gas reservoir oil ring bodyFlow diagram of the product method. In one embodiment of the present application, as shown in FIG. 1, a method for predicting high CO content is provided 2 A method of condensing the volume of a gas reservoir oil ring, comprising the steps of:
step 101, establishing an oil ring volume prediction database, wherein the oil ring volume prediction database comprises a plurality of pairs of high CO content 2 The volume of the condensate gas reservoir oil ring has an influencing parameter.
A parameter correlation between each influencing parameter and the corresponding oil ring volume is determined, step 102.
And 103, determining the influence parameters with the parameter association degree larger than the preset parameter association degree as the main control parameters.
And 104, inputting the parameter values corresponding to the main control parameters into a volume prediction model of the oil ring to obtain a predicted volume output by the volume prediction model.
And 105, determining a target kernel function of the volume prediction model according to the prediction volume to obtain a target volume prediction model.
106, the high CO content to be predicted 2 And inputting the main control parameters of the condensate gas reservoir into the target volume prediction model to obtain a predicted value aiming at the volume of the oil ring output by the target volume prediction model.
High content of CO 2 Condensate reservoirs are a special class of reservoir types. For high content of CO 2 The influencing parameters influencing the volume of the condensate gas reservoir oil ring can comprise formation parameters, gasoline ratio parameters, gas composition parameters and the like. The formation parameters may include temperature T, pressure P, etc. The gas composition parameter may be referred to as including CO 2 、N 2 、CH 4 、IC 4 、NC 4 、IC 5 、NC 5 、C 6 、C 7 ～C 13 And C 14 + and the like.
By multiple pairs of high CO 2 The volume of the condensate gas reservoir oil ring has influence parameters, and the processor can establish an oil ring volume prediction database. The established oil ring volume prediction database can be shown in table 1. Each of the influencing parameters in the oil ring volume prediction database may contain a parameter value corresponding thereto. Each ginsengThe numerical values may include units corresponding to the influencing parameters.
TABLE 1 oil Ring volume prediction database
Figure BDA0003590177360000061
Figure BDA0003590177360000071
After building the oil ring volume prediction database, the processor may determine a parameter correlation between each impact parameter and the corresponding oil ring volume. The volume of the oil ring corresponding to each influencing variable can be determined by numerical simulation. The volume of the oil ring corresponding to each influencing parameter may refer to a high CO content 2 Simulated volume of condensate reservoir oil ring.
Wherein, the numerical simulation can predict the high CO content by taking PVTsim software as a carrier and simulating a state equation 2 Oil ring volume of condensate reservoir. The simulation equation of state may be referred to as a PR-P equation of state. The PR-P equation of state can be expressed as:
Figure BDA0003590177360000072
wherein p refers to equilibrium pressure, R refers to a gas universal constant which can be 0.008314MPa · m3/(kmol · K), T refers to temperature, V refers to volumetric specific volume, a (T) refers to a temperature function; b and c refer to correction coefficients.
As shown in table 2, the simulated volume corresponding to the equation of state can be obtained by performing numerical simulation using different equations of state. Under the same master control parameters, the average error value between the simulated volume determined by the PR-P equation of state and the actual volume determined by physical simulation is small. That is, the simulated volume determined by the PR-P equation of state is closest to the actual volume. Therefore, when determining the parameter correlation degree, the simulated volume obtained by numerical simulation can be used as the main sequence of the gray correlation analysis. Where the average error value is (actual volume-simulated volume)/actual volume.
TABLE 2 average error value between simulated and actual volumes
Figure BDA0003590177360000081
The processor may determine a parameter correlation between each impact parameter and the corresponding oil ring volume by a gray correlation analysis. The gray correlation analysis is a method for measuring the degree of correlation between the influence parameters according to the degree of similarity or difference between the influence parameters. Multiple pairs of high CO content were assigned by taking the oil ring volume as the main sequence for grey correlation 2 And (4) arranging the influence parameters with influence on the volume of the condensate gas reservoir oil ring according to the sequence so as to analyze the relation between the main sequence of the correlation analysis and the plurality of influence parameters.
If the oil ring volumes corresponding to the respective influence parameters are the main sequence in which gray is associated, the magnitude of the parameter association degree between the oil ring volumes corresponding to the respective influence parameters can be determined. As shown in fig. 2, the gas cap composition may refer to a gas composition parameter. Formation conditions may refer to formation parameters. The hydrocarbon conversion may refer to a hydrocarbon ratio parameter. Wherein the gas composition parameter is CO 2 、C1(CH 4 ) And C 14 And + the correlation between T and P in the formation parameters and GOR in the gas-oil ratio parameters and the corresponding oil ring volume is larger.
In the case of determining a parameter association degree between each influence parameter and the corresponding oil ring volume, the processor may determine, as the master parameter, an influence parameter whose parameter association degree is greater than a preset parameter association degree. Wherein, the preset parameter association degree may be 0.6. For example, as shown in FIG. 2, the primary parameter may be CO in the gas composition parameter 2 、C 14 + and C1 (CH) 4 ) T and P in formation parameters and GOR in gas oil ratio parameters.
To more accurately determine the influence of high CO content 2 The main control parameters of the volume of the condensate gas reservoir oil ring can also comprehensively consider the parameter value corresponding to each influence parameter. Wherein each timeThe parameter value corresponding to each influence parameter may mean that each influence parameter is highly CO-containing 2 Corresponding content in condensate gas reservoir. For example, as shown in FIG. 2, gas composition parameter C 14 + have a smaller value, i.e. they are highly CO-rich 2 The content of CO in the condensate gas reservoir is small, so that the CO in the gas composition parameter can be adjusted 2 And C1 (CH) 4 ) T and P in formation parameters and GOR in gas-oil ratio parameters as influences on high CO content 2 The main control parameter of the volume of the condensate gas reservoir oil ring.
The volume prediction model of the oil ring may be referred to as a support vector machine. The processor can input the parameter value corresponding to the main control parameter into the volume prediction model of the oil ring to obtain the predicted volume output by the volume prediction model. The prediction volume may refer to a prediction result output by the volume prediction model. The processor may then determine a target kernel function of the volume prediction model from the prediction volume to obtain a target volume prediction model. In the case of determining a target volume prediction model, the processor may predict the high CO content to be predicted 2 And inputting the main control parameters of the condensate gas reservoir into the target volume prediction model to obtain a predicted value aiming at the volume of the oil ring output by the target volume prediction model. The predicted value for the oil ring volume may refer to a prediction result output by the target volume prediction model.
By the technical scheme, high CO content is influenced 2 Inputting the main control parameter of the volume of the condensate gas reservoir oil ring into a volume prediction model to train the volume prediction model, determining a target kernel function to obtain a target volume prediction model corresponding to the target kernel function, and predicting the high CO content through the target volume prediction model 2 The volume of the condensate gas reservoir oil ring is predicted, and the prediction accuracy of the volume of the oil ring can be improved. And the prediction process is simple, convenient and quick, and the prediction time of the volume of the oil ring can be greatly shortened.
In one embodiment, the number of the volume prediction models is multiple, each volume prediction model uses a different kernel function, and determining a target kernel function of the volume prediction model according to the prediction volume to obtain the target volume prediction model includes: dividing the main control parameters into a training set and a prediction set; respectively inputting the main control parameters in the training set and the main control parameters in the prediction set into the volume prediction models aiming at each volume prediction model; obtaining a prediction volume output by a volume prediction model according to the main control parameters in the prediction set; determining a volume error value between the actual volume of each master control parameter and the corresponding predicted volume; and determining the volume prediction model with the minimum mean value of the volume error values as a target volume prediction model, and determining the kernel function used by the target volume prediction model as a target kernel function.
The number of the volume prediction models may include a plurality. Each volume prediction model may use a different kernel function. The kernel function may refer to a linear kernel function, a quadratic kernel function, a cubic kernel function, a gaussian kernel function, and the like. To train the volume prediction model, the processor may divide the master parameters into a training set and a prediction set. For each volume prediction model, the processor may input the master parameters in the training set to the volume prediction model to train the volume prediction model. The processor may input the master parameters in the prediction set to the volume prediction model to determine a predicted volume corresponding to the master parameters in the prediction set from the trained volume prediction model.
The processor may obtain a predicted volume output by the volume prediction model according to the master parameters in the prediction set. The processor may then determine a volume error value between the actual volume of each master parameter and the corresponding predicted volume. Wherein the actual volume of each master parameter can be determined by means of physical simulation. In particular, CO can be introduced by reacting CO 2 Charging to CO 2 Charging the experimental apparatus to observe CO 2 High CO content during filling 2 Oil-gas phase change and high CO content of condensate gas reservoir 2 The volume change of the oil ring of the condensate gas reservoir can be used for accurately measuring the high CO content by a high-precision measuring instrument 2 The actual volume of the condensate reservoir oil ring. The corresponding predicted volume refers to the predicted volume output by the volume prediction model under the same master control parameters.
After determining the actual volume and the predicted volume for each master parameter, the processor may determine a volume error value between the actual volume and the corresponding predicted volume for each master parameter. The processor may then average the volume error values for all master parameters. The processor may determine a mean value of the smallest volume error values and determine the volume prediction model having the smallest mean value of the volume error values as the target volume prediction model. The processor may determine a kernel function corresponding to the target volume prediction model as a target kernel function.
As shown in fig. 3-6, are the predicted results of the volume prediction model using different kernel functions. The kernel function used by the volume prediction model may be referred to as linear SVM (linear kernel function), quadratic SVM (quadratic kernel function), cubic SVM (cubic kernel function), and gaussian SVM (gaussian kernel function). The predicted oil ring volume may refer to a predicted volume output by a volume prediction model for different kernel functions. The actual oil ring volume may refer to an actual volume obtained by physical simulation.
The volume error value between the predicted and actual oil ring volumes in fig. 3-6 can be visualized by the 45 ° line. Each master parameter may include a predicted oil ring volume and an actual oil ring volume. The predicted and actual oil ring volumes for each master parameter can be represented by data points. If the volume error value between the predicted oil ring volume and the actual oil ring volume is smaller, the data point corresponding to the volume error value is closer to the 45 ° line. Therefore, the prediction accuracy of the volume prediction model can be judged by the distribution of the data points. As shown in fig. 3 to 6, the prediction accuracy of the volume prediction model using the cubic SVM (cubic kernel function) is high.
In one embodiment, the evaluation index includes at least one of a mean relative error, a mean square relative error, a mean absolute error, and a coefficient, and determining an objective kernel function of the volume prediction model from the prediction volume to obtain the objective volume prediction model further includes: determining an index value of each evaluation index according to each volume error value; determining the mean value of the index values of each evaluation index; determining the total index mean value of all the evaluation indexes included in each volume prediction model, wherein the total index mean value is determined according to the mean value of the index value of each evaluation index; and determining the volume prediction model corresponding to the minimum index total mean value as a target volume prediction model, and determining a kernel function used by the target volume prediction model as a target kernel function.
In the case of determining a volume error value between the actual volume of each master parameter and the corresponding predicted volume, the processor may determine an indicator value for each evaluation index from each volume error value. Wherein the evaluation index may include at least one of a mean relative error, a mean square relative error, a mean absolute error, and a coefficient. The processor may then determine a mean value of the indicator values for each of the evaluation indices.
Taking the evaluation index as the relative error of mean square as an example, the mean value calculation formula of the index value of the evaluation index can be
Figure BDA0003590177360000111
Where MSE may refer to the mean of the index values when the evaluation index is the mean square relative error.
Figure BDA0003590177360000112
May be referred to as a volume error value,
Figure BDA0003590177360000113
may refer to an index value and n may refer to the number of volume error values. Therefore, an index value corresponding to each evaluation index can be determined from each volume error value, and a mean value of the corresponding index values can be determined from a plurality of index values.
The processor may determine an index total mean of all evaluation indexes included in each volume prediction model. The total index mean may be determined according to a mean of index values of each evaluation index. The processor may determine the volume prediction model corresponding to the minimum index overall mean as a target volume prediction model, and determine a kernel function used by the target volume prediction model as a target kernel function.
If the kernel functions used by the volume prediction model include a linear SVM (linear kernel function), a quadratic SVM (secondary kernel function), a cubic SVM (tertiary kernel function), and a gaussian SVM (gaussian kernel function), the total index mean values of all the evaluation indexes corresponding to the volume prediction models using different kernel functions are shown in table 3. Where MRE and refer to the mean of the index values when the evaluation index is the average relative error, MSE may refer to the mean of the index values when the evaluation index is the mean square error, R-Squared may refer to the mean of the index values when the evaluation index is the solution coefficient, and MAE may refer to the mean of the index values when the evaluation index is the average absolute error. In table 3, the total index mean value corresponding to the volume prediction model using the cubic kernel function is the smallest, and therefore, the cubic kernel function may be determined as the target kernel function, and the volume prediction model using the cubic kernel function may be used as the target volume prediction model.
TABLE 3 Total mean of indices for volume prediction model using different kernel functions
Kernel function MRE MSE R-Squared MAE Total mean value of index
Linear kernel function 1.018 0.280 1.036 1.005 0.835
Quadratic kernel function 1.093 0.350 1.195 1.093 0.933
Cubic kernel function 0.775 0.320 0.601 0.638 0.584
Gaussian kernel function 1.100 0.370 1.209 1.100 0.945
In one embodiment, the high CO content to be predicted 2 The method comprises the following steps of inputting main control parameters of a condensate gas reservoir into a target volume prediction model to obtain a predicted value aiming at the volume of an oil ring output by the target volume prediction model: determining the high CO content according to a preset state equation and main control parameters 2 The simulated volume of the condensate gas reservoir oil ring; determining a first error value between the simulated volume and the actual volume and a second error value between the predicted value for the oil ring volume and the actual volume; and determining the training completion degree of the target volume prediction model according to the first error value and the second error value.
The processor can determine the high CO content according to a preset state equation and main control parameters 2 Simulated volume of condensate reservoir oil ring. Wherein, presetThe equation of state of (a) may be referred to as a PR-P equation of state. The PR-P equation of state can be expressed as:
Figure BDA0003590177360000131
wherein p refers to equilibrium pressure, R refers to a gas universal constant which can be 0.008314MPa · m3/(kmol · K), T refers to temperature, V refers to volumetric specific volume, a (T) refers to a temperature function; b and c refer to correction coefficients.
The processor may determine a first error value between the simulated volume and the actual volume and a second error value between the predicted value for the oil ring volume and the actual volume. Here, the predicted value for the oil ring volume may refer to a prediction result output by the target volume detection model. The actual volume may be determined by means of physical simulation. In the case where the first error value and the second error value are determined, the processor may determine a training completion of the target volume prediction model based on the first error value and the second error value. Wherein, the training completion degree may refer to a training effect of the target volume prediction model.
In one embodiment, determining the training completion of the target volume prediction model based on the first error value and the second error value comprises: determining the training completion degree of the target volume prediction model as a first completion degree under the condition that the first error value is larger than the second error value; determining the training completion degree of the target volume prediction model as a second completion degree under the condition that the first error value is smaller than or equal to a second error value and the second error value is smaller than or equal to a preset error; and determining the training completion degree of the target volume prediction model as a third completion degree under the condition that the first error value is smaller than or equal to the second error value and the second error value is larger than the preset error.
If the first error value is greater than the second error value, it may be indicated that an error between a predicted value for the volume of the oil ring output by the target volume detection model and the actual volume is small, and a training effect of the target detection model is good. At this time, the processor may determine that the training completion of the target volume prediction model is the first completion. That is, the first degree of completion may refer to a training effect for a target volume prediction model corresponding to when an error between a predicted value and an actual volume of the oil ring volume is small.
If the first error value is less than or equal to the second error value, and the second error value is less than or equal to the preset error, it may be indicated that an error between the predicted value for the volume of the oil ring output by the target volume detection model and the actual volume is large, but the predicted value for the volume of the oil ring can meet engineering requirements. At this time, the processor may determine that the training completion of the target volume prediction model is the second completion. That is, the second completeness may refer to a training effect of the target volume prediction model corresponding to a case where the error between the predicted value of the oil ring volume and the actual volume is large, but the predicted value of the oil ring volume can satisfy the engineering requirement. Wherein the preset error may be 10%.
If the first error value is less than or equal to the second error value and the second error value is greater than the preset error, it may be indicated that an error between the predicted value for the volume of the oil ring output by the target volume detection model and the actual volume is large, and the predicted value for the volume of the oil ring may not meet the engineering requirement. At this point, the processor may determine that the training of the target volume prediction model is complete to a third degree. That is, the third completeness may refer to a training effect of the target volume prediction model when the first error value is less than or equal to the second error value and the predicted value of the oil ring volume may not meet the engineering requirement. Wherein the preset error may be 10%.
As shown in Table 4, the high CO content was obtained by using the target volume prediction model pair A, B and C 2 The volume of the oil ring of the condensate gas reservoir is predicted to obtain a predicted value aiming at the volume of the oil ring, and the actual volume is determined through a physical simulation mode. Errors between the predicted value and the actual volume of the oil ring volume are respectively 8.52%, 5.95% and 8.75%, and are all less than 10%. Therefore, the target volume prediction model can meet engineering requirements.
TABLE 4 high CO content 2 Oil ring volume prediction for condensate gas reservoirs
Figure BDA0003590177360000141
In one embodiment, the method further comprises: determining a high CO content to be predicted according to a predicted value output by a target volume prediction model and aiming at the volume of an oil ring 2 A target exploitation mode of the condensate gas reservoir; will be directed to high CO content to be predicted 2 Switching the exploitation mode of the condensate gas reservoir to a target exploitation mode; wherein the target mining mode comprises any one of the following mining modes: exploiting the gas reservoir only without exploiting the oil reservoir, opening the oil reservoir first and then exploiting the gas reservoir, opening the oil reservoir first and then exploiting the oil reservoir, and exploiting the oil reservoir and the gas reservoir simultaneously.
According to different high CO content 2 The volume of the oil ring of the condensate gas reservoir can be preset with a corresponding target exploitation mode. The target exploitation mode can comprise that only the gas reservoir is exploited and the oil reservoir is not exploited, the oil reservoir is exploited before the oil reservoir is opened, the gas reservoir is exploited before the oil reservoir is opened, and the oil reservoir is exploited simultaneously. After determining the predicted value for the oil ring volume output by the target volume prediction model, the processor may determine the high CO content for the prediction from the predicted value for the oil ring volume 2 A targeted exploitation of condensate gas reservoirs. The processor may then target the high CO to be predicted 2 And switching the exploitation mode of the condensate gas reservoir to a target exploitation mode.
In one embodiment, the high CO content to be predicted is treated according to the target mining mode 2 If the high CO content to be predicted is to be obtained in the process of exploiting the condensate gas reservoir 2 If the steam-oil ratio parameters mainly influencing the condensate gas reservoir are abnormal, an abnormal exploitation alarm prompt can be sent out through an alarm or display equipment, so that an exploitation worker can adjust an exploitation mode according to prompt contents. Wherein the alarm may be an audible and visual alarm. The display device can display interface pop-up windows, alarm short messages, alarm mails and the like.
In one embodiment, the influencing parameter comprises high CO content 2 At least one of a formation parameter, a gasoline ratio parameter, and a gas composition parameter of a condensate gas reservoir oil ring, wherein the formation parameter comprises a formation temperature parameterNumber and formation pressure parameters.
The formation parameters may include temperature T, pressure P, etc. The gas composition parameter may be referred to as including CO 2 、N 2 、CH 4 、IC 4 、NC 4 、IC 5 、NC 5 、C 6 、C 7 ～C 13 And C 14 + and the like. High CO content by multiple influences 2 And (3) an influence parameter of the volume of the oil ring of the condensate gas reservoir, and the processor can establish an oil ring volume prediction database.
By the technical scheme, high CO content is influenced 2 Inputting the main control parameter of the volume of the condensate gas reservoir oil ring into a volume prediction model to train the volume prediction model, determining a target kernel function to obtain a target volume prediction model corresponding to the target kernel function, and predicting the high CO content through the target volume prediction model 2 The volume of the condensate gas reservoir oil ring is predicted, and the prediction accuracy of the volume of the oil ring can be improved. And the prediction process is simple, convenient and quick, and the prediction time of the volume of the oil ring can be greatly shortened.
FIG. 1 is a diagram for predicting high CO content in one embodiment 2 A schematic flow diagram of a method for condensing the oil ring volume of a gas reservoir. It should be understood that, although the steps in the flowchart of fig. 1 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 1 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in FIG. 7, a method for predicting high CO content is provided 2 The device for measuring the volume of the condensate gas reservoir oil ring comprises a database establishing module, a main control parameter determining module and a prediction modelA determination module and an oil ring volume prediction module, wherein:
a database establishing module 701, configured to establish an oil ring volume prediction database, where the oil ring volume prediction database includes a plurality of pairs of high CO content 2 The volume of the condensate gas reservoir oil ring has an influencing parameter.
A main control parameter determining module 702, configured to determine a parameter association degree between each influence parameter and a corresponding oil ring volume, and determine, as a main control parameter, an influence parameter whose parameter association degree is greater than a preset parameter association degree.
The prediction model determining module 703 is configured to input a parameter value corresponding to the main control parameter to the volume prediction model of the oil ring to obtain a predicted volume output by the volume prediction model, and determine a target kernel function of the volume prediction model according to the predicted volume to obtain a target volume prediction model.
An oil ring volume prediction module 704 for predicting the high CO content to be predicted 2 And inputting the main control parameters of the condensate gas reservoir into the target volume prediction model to obtain a predicted value aiming at the volume of the oil ring output by the target volume prediction model.
Influence of high CO content 2 The parameters affecting the volume of the oil ring of the condensate gas reservoir may include formation parameters, gasoline ratio parameters, gas composition parameters and the like. The formation parameters may include temperature T, pressure P, etc. The gas composition parameter may be referred to as including CO 2 、N 2 、CH 4 、IC 4 、NC 4 、IC 5 、NC 5 、C 6 、C 7 ～C 13 And C 14 + and the like. High CO content by multiple influences 2 The database building module 701 may build an oil ring volume prediction database based on the influence parameters of the volume of the oil ring of the condensate gas reservoir.
After building the oil ring volume prediction database, the master parameter determination module 702 may determine a parameter correlation between each impact parameter and the corresponding oil ring volume. The volume of the oil ring corresponding to each influencing variable can be determined by numerical simulation. The volume of the oil ring corresponding to each influencing parameter may refer to a high CO content 2 Simulated volume of condensate reservoir oil ring. Master controlThe parameter determination module 702 can determine a parameter correlation between each impact parameter and the corresponding oil ring volume by a gray correlation analysis. After determining the parameter association degree between the oil ring volumes corresponding to each influence parameter, the master parameter determination module 702 may determine an influence parameter having a parameter association degree greater than a preset parameter association degree as a master parameter.
The prediction model determining module 703 may input a parameter value corresponding to the main control parameter to the volume prediction model of the oil ring to obtain a predicted volume output by the volume prediction model. The prediction volume may refer to a prediction result output by the volume prediction model. Then, the prediction model determining module 703 may determine a target kernel function of the volume prediction model according to the prediction volume to obtain a target volume prediction model.
In the case of determining a target volume prediction model, the oil ring volume prediction module 704 may predict the high CO content to be predicted 2 And inputting the main control parameters of the condensate gas reservoir into the target volume prediction model to obtain a predicted value aiming at the volume of the oil ring output by the target volume prediction model. The predicted value for the oil ring volume may refer to a prediction result output by the target volume prediction model.
In one embodiment, as shown in FIG. 8, for predicting high CO content 2 The device for condensing the volume of the oil ring of the gas reservoir further comprises a mining type determining module 705 for determining the high CO content to be predicted according to the predicted value output by the target volume prediction model and aiming at the volume of the oil ring 2 The target exploitation mode of the condensate gas reservoir aims at the high CO content to be predicted 2 And switching the exploitation mode of the condensate gas reservoir to a target exploitation mode.
The production type determination module 705 may determine the high CO content for prediction from the predicted value for the oil ring volume output by the target volume prediction model 2 The target exploitation mode of the condensate gas reservoir aims at the high CO content to be predicted 2 And switching the exploitation mode of the condensate gas reservoir to a target exploitation mode. According to different high CO content 2 The volume of the oil ring of the condensate gas reservoir can be preset with a corresponding target exploitation mode. Wherein the target production mode may include only producing the gas reservoir and not producing oilThe method comprises the steps of reservoir exploitation, gas reservoir exploitation after the reservoir exploitation, gas reservoir exploitation before the gas reservoir exploitation, and simultaneous reservoir and gas reservoir exploitation.
Through the technical scheme, the prediction accuracy of the volume of the oil ring can be improved. And the prediction process is simple, convenient and quick, and the prediction time of the volume of the oil ring can be greatly shortened.
For predicting high CO content 2 The device for condensing the volume of the oil ring of the gas reservoir comprises a processor and a memory, wherein the database establishing module, the main control parameter determining module, the prediction model determining module, the oil ring volume predicting module, the mining type determining module and the like are stored in the memory as program units, and the processor executes the program modules stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more, and the prediction of high CO content is realized by adjusting the kernel parameters 2 A method for condensing the volume of an oil ring of a gas reservoir.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
An embodiment of the present application provides a storage medium having a program stored thereon, the program implementing the above method for predicting high CO content when executed by a processor 2 A method for condensing the volume of an oil ring of a gas reservoir.
The embodiment of the application provides a processor, which is used for running a program, wherein the program is executed during running to predict high CO content 2 A method for condensing the volume of an oil ring of a gas reservoir.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor a01, a network interface a02, a memory (not shown), and a database (not shown) connected by a system bus. Wherein the processor A01 of the computer device is used for providing calculation and controlCapability. The memory of the computer device comprises an internal memory a03 and a non-volatile storage medium a 04. The nonvolatile storage medium a04 stores an operating system B01, a computer program B02, and a database (not shown in the figure). The internal memory a03 provides an environment for the operation of the operating system B01 and the computer programs B02 in the non-volatile storage medium a 04. The database of the computer device is used for storing data such as influencing parameters. The network interface a02 of the computer device is used for communication with an external terminal through a network connection. The computer program B02 is adapted to be executed by the processor A01 to implement a method for predicting high CO content 2 A method for condensing the volume of an oil ring of a gas reservoir.
Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
An embodiment of the present application provides an apparatus, where the apparatus includes a processor, a memory, and a program that is stored in the memory and is executable on the processor, and the processor implements the following steps when executing the program: establishing an oil ring volume prediction database, wherein the oil ring volume prediction database comprises a plurality of pairs of high CO content 2 Influence parameters influencing the volume of the condensate gas reservoir oil ring; determining a parameter correlation between each influencing parameter and the corresponding oil ring volume; determining the influence parameters with the parameter association degree larger than the preset parameter association degree as main control parameters; inputting the parameter value corresponding to the main control parameter into a volume prediction model of the oil ring to obtain a predicted volume output by the volume prediction model; determining a target kernel function of the volume prediction model according to the prediction volume to obtain a target volume prediction model; high CO content to be predicted 2 And inputting the main control parameters of the condensate gas reservoir into the target volume prediction model to obtain a predicted value aiming at the volume of the oil ring output by the target volume prediction model.
In one embodiment, the number of the volume prediction models is multiple, each volume prediction model uses a different kernel function, and determining a target kernel function of the volume prediction model according to the prediction volume to obtain the target volume prediction model includes: dividing the main control parameters into a training set and a prediction set; respectively inputting the main control parameters in the training set and the main control parameters in the prediction set into the volume prediction models aiming at each volume prediction model; obtaining a prediction volume output by a volume prediction model according to the main control parameters in the prediction set; determining a volume error value between the actual volume of each master control parameter and the corresponding predicted volume; and determining the volume prediction model with the minimum mean value of the volume error values as a target volume prediction model, and determining the kernel function used by the target volume prediction model as a target kernel function.
In one embodiment, the evaluation index includes at least one of a mean relative error, a mean square relative error, a mean absolute error, and a coefficient, and determining an objective kernel function of the volume prediction model from the prediction volume to obtain the objective volume prediction model further includes: determining an index value of each evaluation index according to each volume error value; determining the mean value of the index values of each evaluation index; determining the total index mean value of all evaluation indexes included in each volume prediction model, wherein the total index mean value is determined according to the mean value of the index value of each evaluation index; and determining the volume prediction model corresponding to the minimum index total mean value as a target volume prediction model, and determining the kernel function used by the target volume prediction model as a target kernel function.
In one embodiment, the high CO content to be predicted 2 The method comprises the following steps of inputting main control parameters of a condensate gas reservoir into a target volume prediction model to obtain a predicted value aiming at the volume of an oil ring output by the target volume prediction model: determining the high CO content according to a preset state equation and main control parameters 2 The simulated volume of the condensate gas reservoir oil ring; determining a first error value between the simulated volume and the actual volume and a second error value between the predicted value for the oil ring volume and the actual volume; and determining the training completion degree of the target volume prediction model according to the first error value and the second error value.
In one embodiment, determining the training completion of the target volume prediction model based on the first error value and the second error value comprises: determining the training completion degree of the target volume prediction model as a first completion degree under the condition that the first error value is larger than the second error value; determining the training completion degree of the target volume prediction model as a second completion degree under the condition that the first error value is smaller than or equal to a second error value and the second error value is smaller than or equal to a preset error; and determining the training completion degree of the target volume prediction model as a third completion degree under the condition that the first error value is smaller than or equal to the second error value and the second error value is larger than the preset error.
In one embodiment, the method further comprises: determining a high CO content to be predicted according to a predicted value output by a target volume prediction model and aiming at the volume of an oil ring 2 A target mining mode of the condensate gas reservoir; will be directed to high CO content to be predicted 2 Switching the exploitation mode of the condensate gas reservoir to a target exploitation mode; wherein the target mining mode comprises any one of the following mining modes: exploiting the gas reservoir only without exploiting the oil reservoir, opening the oil reservoir first and then exploiting the gas reservoir, opening the oil reservoir first and then exploiting the oil reservoir, and exploiting the oil reservoir and the gas reservoir simultaneously.
In one embodiment, the influencing parameter comprises high CO content 2 At least one of a formation parameter, a gasoline ratio parameter, and a gas composition parameter of the condensate gas reservoir oil ring, wherein the formation parameter comprises a formation temperature parameter and a formation pressure parameter.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: establishing an oil ring volume prediction database, wherein the oil ring volume prediction database comprises a plurality of pairs of high CO content 2 Influence parameters influencing the volume of the condensate gas reservoir oil ring; determining a parameter correlation between each influencing parameter and the corresponding oil ring volume; determining the influence parameters with the parameter association degree larger than the preset parameter association degree as the main control parameters; inputting the parameter value corresponding to the main control parameter into a volume prediction model of the oil ring to obtain a predicted volume output by the volume prediction model; determining a target kernel function of the volume prediction model according to the prediction volume to obtain a target volume prediction model; high CO content to be predicted 2 And inputting the main control parameters of the condensate gas reservoir into the target volume prediction model to obtain a predicted value aiming at the volume of the oil ring output by the target volume prediction model.
In one embodiment, the number of the volume prediction models is multiple, each volume prediction model uses a different kernel function, and determining a target kernel function of the volume prediction model according to the prediction volume to obtain the target volume prediction model includes: dividing the main control parameters into a training set and a prediction set; respectively inputting the main control parameters in the training set and the main control parameters in the prediction set into the volume prediction models aiming at each volume prediction model; acquiring a predicted volume output by a volume prediction model according to the main control parameters in the prediction set; determining a volume error value between the actual volume of each master control parameter and the corresponding predicted volume; and determining the volume prediction model with the minimum mean value of the volume error values as a target volume prediction model, and determining the kernel function used by the target volume prediction model as a target kernel function.
In one embodiment, the evaluation index includes at least one of a mean relative error, a mean square relative error, a mean absolute error, and a coefficient, and determining an objective kernel function of the volume prediction model from the prediction volume to obtain the objective volume prediction model further includes: determining an index value of each evaluation index according to each volume error value; determining the mean value of the index values of each evaluation index; determining the total index mean value of all the evaluation indexes included in each volume prediction model, wherein the total index mean value is determined according to the mean value of the index value of each evaluation index; and determining the volume prediction model corresponding to the minimum index total mean value as a target volume prediction model, and determining the kernel function used by the target volume prediction model as a target kernel function.
In one embodiment, the high CO content to be predicted 2 The method comprises the following steps of inputting main control parameters of the condensate gas reservoir into a target volume prediction model to obtain a predicted value which is output by the target volume prediction model and aims at the volume of an oil ring: determining the high CO content according to a preset state equation and main control parameters 2 The simulated volume of the condensate gas reservoir oil ring; determining a first error between a simulated volume and an actual volumeA value and a second error value between the predicted value and the actual volume for the oil ring volume; and determining the training completion degree of the target volume prediction model according to the first error value and the second error value.
In one embodiment, determining the training completion of the target volume prediction model based on the first error value and the second error value comprises: determining the training completion degree of the target volume prediction model as a first completion degree under the condition that the first error value is larger than the second error value; determining the training completion degree of the target volume prediction model as a second completion degree under the condition that the first error value is smaller than or equal to a second error value and the second error value is smaller than or equal to a preset error; and determining the training completion degree of the target volume prediction model as a third completion degree under the condition that the first error value is smaller than or equal to the second error value and the second error value is larger than the preset error.
In one embodiment, the method further comprises: determining a high CO content to be predicted according to a predicted value output by a target volume prediction model and aiming at the volume of an oil ring 2 A target exploitation mode of the condensate gas reservoir; will be directed to high CO content to be predicted 2 Switching the exploitation mode of the condensate gas reservoir to a target exploitation mode; wherein the target mining mode comprises any one of the following mining modes: exploiting the gas reservoir only without exploiting the oil reservoir, opening the oil reservoir first and then exploiting the gas reservoir, opening the oil reservoir first and then exploiting the oil reservoir, and exploiting the oil reservoir and the gas reservoir simultaneously.
In one embodiment, the influencing parameter comprises high CO content 2 At least one of a formation parameter, a gasoline ratio parameter, and a gas composition parameter of the condensate gas reservoir oil ring, wherein the formation parameter comprises a formation temperature parameter and a formation pressure parameter.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims (10)

1. For predicting high CO content 2 A method of condensing the volume of an oil ring of a gas reservoir, the method comprising:
establishing an oil ring volume prediction database which comprises a plurality of pairs of high CO contents 2 Influence parameters influencing the volume of the condensate gas reservoir oil ring;
determining a parameter correlation between each influencing parameter and the corresponding oil ring volume;
determining the influence parameters with the parameter association degree larger than the preset parameter association degree as main control parameters;
inputting the parameter value corresponding to the main control parameter into a volume prediction model of an oil ring to obtain a predicted volume output by the volume prediction model;
determining a target kernel function of the volume prediction model according to the prediction volume to obtain a target volume prediction model;
high CO content to be predicted 2 And inputting the main control parameters of the condensate gas reservoir into the target volume prediction model to obtain a predicted value output by the target volume prediction model and aiming at the volume of the oil ring.
2. The method for predicting high CO content according to claim 1 2 The method for determining the volume of the oil ring of the condensate gas reservoir is characterized in that the volume prediction models are multiple in number, each volume prediction model uses different kernel functions, and the step of determining the target kernel function of the volume prediction model according to the prediction volumes to obtain the target volume prediction model comprises the following steps:
dividing the master control parameters into a training set and a prediction set;
respectively inputting the main control parameters in the training set and the main control parameters in the prediction set to each volume prediction model;
obtaining a prediction volume output by the volume prediction model according to the main control parameters in the prediction set;
determining a volume error value between the actual volume of each master control parameter and the corresponding predicted volume;
and determining the volume prediction model with the minimum mean value of the volume error values as a target volume prediction model, and determining the kernel function used by the target volume prediction model as a target kernel function.
3. The method according to claim 2 for predicting high CO content 2 The method for estimating the volume of the oil ring of the condensate gas reservoir is characterized in that the evaluation index comprises at least one of a mean relative error, a mean square relative error, a mean absolute error and a coefficient, and the determining the target kernel function of the volume prediction model according to the prediction volume to obtain the target volume prediction model further comprises:
determining an index value of each evaluation index according to each volume error value;
determining the mean value of the index values of each evaluation index;
determining an index total mean value of all evaluation indexes included in each volume prediction model, wherein the index total mean value is determined according to the mean value of the index values of each evaluation index;
and determining a volume prediction model corresponding to the minimum index total mean value as a target volume prediction model, and determining a kernel function used by the target volume prediction model as a target kernel function.
4. The method for predicting high CO content according to claim 1 2 Method for condensing the volume of an oil ring of a gas reservoir, characterized in that said high CO content to be predicted is 2 The main control parameters of the condensate gas reservoir are input into the target volume prediction model, so that the predicted value of the oil ring volume output by the target volume prediction model comprises the following steps:
determining the high CO content according to a preset state equation and the main control parameter 2 The simulated volume of the condensate gas reservoir oil ring;
determining a first error value between the simulated volume and the actual volume and a second error value between a predicted value for an oil ring volume and the actual volume;
and determining the training completion degree of the target volume prediction model according to the first error value and the second error value.
5. The method of claim 4 for predicting high CO content 2 A method of condensing a gas reservoir oil ring volume, wherein determining a training completion of the target volume prediction model based on the first error value and the second error value comprises:
determining that the training completion of the target volume prediction model is a first completion if the first error value is greater than the second error value;
determining the training completion degree of the target volume prediction model as a second completion degree under the condition that the first error value is smaller than or equal to the second error value and the second error value is smaller than or equal to a preset error;
and determining the training completion degree of the target volume prediction model as a third completion degree under the condition that the first error value is smaller than or equal to the second error value and the second error value is larger than a preset error.
6. The method for predicting high CO content according to claim 1 2 A method of condensing a gas reservoir oil ring volume, the method further comprising:
determining the high CO content to be predicted according to the predicted value output by the target volume prediction model and aiming at the volume of the oil ring 2 A target exploitation mode of the condensate gas reservoir;
will be directed to high CO content to be predicted 2 Switching the exploitation mode of the condensate gas reservoir to the target exploitation mode;
wherein the target mining mode comprises any one of the following mining modes: exploiting the gas reservoir only without exploiting the oil reservoir, opening the oil reservoir first and then exploiting the gas reservoir, opening the oil reservoir first and then exploiting the oil reservoir, and exploiting the oil reservoir and the gas reservoir simultaneously.
7. The method for predicting high CO content according to claim 1 2 Method for condensing the volume of an oil ring of a gas reservoir, characterized in that said influencing parameter comprises said high CO content 2 At least one of a formation parameter, a gasoline ratio parameter, and a gas composition parameter of a condensate gas reservoir oil ring, wherein the earth has a gas composition and a gas compositionThe layer parameters include a formation temperature parameter and a formation pressure parameter.
8. For predicting high CO content 2 An apparatus for condensing a gas reservoir oil ring volume, the apparatus comprising:
the database establishing module is used for establishing an oil ring volume prediction database which comprises a plurality of pairs of high CO content 2 Influence parameters influencing the volume of the condensate gas reservoir oil ring;
the main control parameter determining module is used for determining the parameter association degree between each influence parameter and the corresponding oil ring volume, and determining the influence parameters with the parameter association degree larger than the preset parameter association degree as the main control parameters;
the prediction model determining module is used for inputting the parameter values corresponding to the main control parameters into a volume prediction model of the oil ring to obtain a prediction volume output by the volume prediction model, and determining a target kernel function of the volume prediction model according to the prediction volume to obtain a target volume prediction model;
an oil ring volume prediction module for predicting high CO content to be predicted 2 And inputting the main control parameters of the condensate gas reservoir into a target volume prediction model so as to obtain a predicted value aiming at the volume of the oil ring output by the target volume prediction model.
9. The method of claim 8 for predicting high CO content 2 An apparatus for condensing a gas reservoir oil ring volume, the apparatus further comprising:
a mining type determination module for determining the high CO content to be predicted according to the predicted value output by the target volume prediction model and aiming at the volume of the oil ring 2 The target exploitation mode of the condensate gas reservoir aims at the high CO content to be predicted 2 And switching the exploitation mode of the condensate gas reservoir to the target exploitation mode.
10. A processor configured to perform the method for predicting high CO content according to any one of claims 1 to 7 2 A method for condensing the volume of an oil ring of a gas reservoir.
CN202210375387.3A 2022-04-11 2022-04-11 For predicting high CO content 2 Method and processor for condensing volume of oil ring of gas reservoir Pending CN114861984A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210375387.3A CN114861984A (en) 2022-04-11 2022-04-11 For predicting high CO content 2 Method and processor for condensing volume of oil ring of gas reservoir

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210375387.3A CN114861984A (en) 2022-04-11 2022-04-11 For predicting high CO content 2 Method and processor for condensing volume of oil ring of gas reservoir

Publications (1)

Publication Number Publication Date
CN114861984A true CN114861984A (en) 2022-08-05

Family

ID=82629922

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210375387.3A Pending CN114861984A (en) 2022-04-11 2022-04-11 For predicting high CO content 2 Method and processor for condensing volume of oil ring of gas reservoir

Country Status (1)

Country Link
CN (1) CN114861984A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116383573A (en) * 2023-03-20 2023-07-04 中海石油(中国)有限公司海南分公司 Condensate gas productivity evaluation method based on multi-region phase change mass transfer seepage coupling

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116383573A (en) * 2023-03-20 2023-07-04 中海石油(中国)有限公司海南分公司 Condensate gas productivity evaluation method based on multi-region phase change mass transfer seepage coupling
CN116383573B (en) * 2023-03-20 2023-10-10 中海石油(中国)有限公司海南分公司 Condensate gas productivity evaluation method based on multi-region phase change mass transfer seepage coupling

Similar Documents

Publication Publication Date Title
Mu et al. Hourly and daily urban water demand predictions using a long short-term memory based model
Robbins et al. Mean shift testing in correlated data
CN103197663B (en) Method and system of failure prediction
CN114492211B (en) Residual oil distribution prediction method based on autoregressive network model
Rauschenbach Modeling, control, and optimization of water systems
CN106033510A (en) Method and system for identifying user equipment
CN112182214A (en) Data classification method, device, equipment and medium
CN114861984A (en) For predicting high CO content 2 Method and processor for condensing volume of oil ring of gas reservoir
CN109696216A (en) Compensation method, device, storage medium, processor and the system of flow signal
CN105807136A (en) Harmonic emission level estimation method based on weighted support vector machine
Wang et al. An Improved Grey Prediction Model Based on Matrix Representations of the Optimized Initial Value.
Xu et al. A novel ensemble model using artificial neural network for predicting wave-induced forces on coastal bridge decks
CN113537614A (en) Construction method, system, equipment and medium of power grid engineering cost prediction model
CN109977131A (en) A kind of house type matching system
CN105426534A (en) Information determination method and device
CN113808015A (en) Spatial interpolation method, device and equipment for meteorological parameters of power transmission line region
CN116051118B (en) Analysis method and device of behavior time sequence model
CN113642029B (en) Method and system for measuring correlation between data sample and model decision boundary
CN116108645A (en) Engineering digital twin method based on meta universe
Gryzlov et al. Artificial intelligence and data analytics for virtual flow metering
CN115170304A (en) Method and device for extracting risk feature description
CN113780356A (en) Water quality prediction method and system based on ensemble learning model
CN114021445A (en) Ocean vortex mixed non-local prediction method based on random forest model
Vila et al. Optimal designs based on exact confidence regions for parameter estimation of a nonlinear regression model
CN113159419A (en) Group feature portrait analysis method, device and equipment and readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination