Method for predicting liquid content of gas, and method and system for measuring liquid content and gas content

Abstract

The invention relates to a gas liquid content prediction method and a liquid amount and gas amount measurement method and system, and relates to the technical field of well logging. The prediction method comprises the following steps: acquiring physical attribute parameters and geological formation information corresponding to the oil well output liquid, and equipment characteristic parameters for carrying out gas-liquid separation on the oil well output liquid; and on the basis of the physical attribute parameters corresponding to the oil well output liquid, the geological formation information, the equipment characteristic parameters and a preset regression model, predicting the gas liquid content after gas-liquid separation. According to the embodiment of the invention, accurate prediction of the liquid content of the gas after gas-liquid separation can be realized.

Description

Technical Field

[0001] The present disclosure relates to the technical field of logging, and particularly to a method for predicting the liquid content in gas, a method and a system for measuring liquid volume and gas volume. Background Art

[0002] In traditional oilfield wellhead measurement technologies, there are generally many defects and challenges. Most measurement methods mainly rely on physical measurement devices, such as flow meters, pressure sensors, and thermometers, etc., to monitor the basic parameters of the fluids in oil and gas wells.

[0003] Although these technologies can provide some real-time data, their accuracy is often limited by the accuracy boundaries of the technologies themselves, the stability of the devices, and variable environmental factors, etc. Further, before the collected raw data can support oilfield decision-making, it usually needs to go through multiple links such as data transmission, processing, and analysis, which inevitably brings the lag of data analysis, thus affecting the efficiency and accuracy of decision-making. Especially in complex oil and gas well environments, these factors may have a negative impact on the operation efficiency and economic benefits of the oilfield.

[0004] Based on the above background, it is necessary to propose an oilfield gas-liquid separation and fluid measurement method, with a view to achieving a qualitative leap in aspects such as improving measurement accuracy, enhancing data processing efficiency, and optimizing operation decisions. Especially in achieving accurate measurement and automatic correction of the liquid content in gas, it provides strong support for the high efficiency and economy of oilfield production. Summary of the Invention

[0005] The present disclosure proposes a technical solution for a method for predicting the liquid content in gas, a method and a system for measuring liquid volume and gas volume.

[0006] According to one aspect of the present disclosure, there is provided a method for predicting the liquid content in gas, including:

[0007] Obtaining the physical property parameters of the oil well produced fluid, the geological formation information, and the equipment characteristic parameters for gas-liquid separation of the oil well produced fluid;

[0008] Predicting the liquid content in the gas after gas-liquid separation based on the physical property parameters of the oil well produced fluid, the geological formation information, the equipment characteristic parameters, and a preset regression model.

[0009] Preferably, the method for predicting the liquid content in the gas after gas-liquid separation based on the physical property parameters of the oil well produced fluid, the geological formation information, the equipment characteristic parameters, and a preset regression model includes:

[0010] Training the preset regression model based on the physical property parameters of the oil well produced fluid, the geological formation information, and the equipment characteristic parameters;

[0011] Based on the trained preset regression model, use the physical property parameters corresponding to the liquid content in the gas after gas-liquid separation to be predicted and the equipment characteristic parameters of the geological formation information to predict the liquid content in the gas.

[0012] Preferably, in the method of training the preset regression model based on the physical property parameters corresponding to the produced fluid of the oil well, the geological formation information, and the equipment characteristic parameters, it includes:

[0013] Divide the physical property parameters corresponding to the produced fluid of the oil well, the geological formation information, and the equipment characteristic parameters to obtain reservoir characteristics and mechanical equipment characteristics;

[0014] Respectively extract the reservoir characteristics according to multiple set first weight values to obtain multiple first selected reservoir characteristics; and respectively extract the mechanical equipment characteristics according to multiple set second weight values corresponding to the multiple set first weight values to obtain the first selected mechanical equipment characteristics corresponding to the multiple first selected reservoir characteristics;

[0015] Respectively train the preset regression model based on the first selected mechanical equipment characteristics corresponding to the multiple first selected reservoir characteristics to obtain multiple corresponding trained first preset regression models;

[0016] Based on the set model evaluation criterion, select the optimal initial model from the multiple trained first preset regression models;

[0017] Based on the trained optimal initial model, use the physical property parameters corresponding to the liquid content in the gas after gas-liquid separation to be predicted and the equipment characteristic parameters of the geological formation information to predict the liquid content in the gas.

[0018] Preferably, before predicting the liquid content in the gas based on the trained optimal initial model, using the physical property parameters corresponding to the liquid content in the gas after gas-liquid separation to be predicted and the equipment characteristic parameters of the geological formation information, it further includes:

[0019] Obtain multiple first set neighborhood values and multiple second set neighborhood values, and respectively adjust the first weight value and the second weight value corresponding to the optimal initial model based on the multiple first set neighborhood values and the multiple second set neighborhood values to obtain corresponding multiple first adjusted weight values and multiple second adjusted weight values;

[0020] Extract the reservoir characteristics according to multiple first adjustment weight values respectively to obtain multiple second selected reservoir characteristics; and extract the mechanical equipment characteristics according to the multiple set second adjustment weight values corresponding to the multiple set first adjustment weight values respectively to obtain the second selected mechanical equipment characteristics corresponding to the multiple second selected reservoir characteristics;

[0021] Train the preset regression model respectively based on the second selected mechanical equipment characteristics corresponding to the multiple second selected reservoir characteristics to obtain multiple corresponding trained second preset regression models;

[0022] Select the optimal regression model from the multiple trained second preset regression models based on the set model evaluation criterion;

[0023] Based on the trained optimal regression model, predict the liquid content in the gas after gas-liquid separation by using the physical property parameters and geological formation information corresponding to the liquid content in the gas to be predicted and the equipment characteristic parameters; and / or

[0024] Adjust the first weight value and the second weight value corresponding to the optimal initial model respectively based on the multiple first set neighborhood values and the multiple second set neighborhood values to obtain the sum of the corresponding multiple first adjustment weight values and multiple second adjustment weight values configured to be 1.

[0025] Preferably, the physical property parameters corresponding to the oil well produced fluid include one or more of the fluid temperature, fluid pressure, fluid density and fluid initial flow rate corresponding to the oil well produced fluid; and / or,

[0026] The geological formation information corresponding to the oil well produced fluid includes one or more of the reservoir thickness, permeability and formation pressure; and / or,

[0027] The equipment characteristic parameters for gas-liquid separation of the oil well produced fluid include one or more of the working pressure, working temperature, fluid inlet flow rate into the equipment or device, separator type, and separator size corresponding to the equipment or device for gas-liquid separation of the oil well produced fluid; and / or

[0028] The sum of the multiple set first weight values and the multiple set second weight values corresponding to the multiple set first weight values is configured to be 1; and / or,

[0029] Before predicting the liquid content in the gas after gas-liquid separation based on the physical property parameters corresponding to the oil well produced fluid, the geological formation information, the equipment characteristic parameters, and the preset regression model, normalize the physical property parameters corresponding to the oil well produced fluid, the geological formation information, and the equipment characteristic parameters to obtain the corresponding normalized physical property parameters, normalized geological formation information, and normalized equipment characteristic parameters.

[0030] According to one aspect of the present disclosure, a method for measuring liquid volume is provided, including: the prediction method as described above; and,

[0031] Obtain the total liquid volume measured by the equipment for gas-liquid separation of the oil well produced fluid; and correct the total liquid volume based on the predicted liquid content in the gas to determine the correct total liquid volume corresponding to the oil well produced fluid; and / or,

[0032] Obtain the water content measured by the equipment for gas-liquid separation of the oil well produced fluid; and determine the water content ratio corresponding to the oil well produced fluid based on the water content and the correct total liquid volume.

[0033] According to one aspect of the present disclosure, a method for measuring gas volume is provided, including: the prediction method as described above and / or the method for measuring liquid volume as described above; and,

[0034] Obtain the gas content measured by the equipment for gas-liquid separation of the oil well produced fluid; and correct the gas content based on the predicted liquid content in the gas to obtain the correct gas content.

[0035] According to one aspect of the present disclosure, a prediction system for liquid content in gas is provided, including:

[0036] A first acquisition unit for acquiring the physical property parameters corresponding to the oil well produced fluid, the geological formation information, and the equipment characteristic parameters of the equipment for gas-liquid separation of the oil well produced fluid;

[0037] A prediction unit for predicting the liquid content in the gas after gas-liquid separation based on the physical property parameters corresponding to the oil well produced fluid, the geological formation information, the equipment characteristic parameters, and the preset regression model; and / or

[0038] Including: a processor;

[0039] A memory for storing instructions executable by the processor;

[0040] Wherein, the processor is configured to call the instructions stored in the memory to execute the prediction method as described above; and / or

[0041] Comprising: a computer-readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the above-described prediction method.

[0042] According to one aspect of the present disclosure, there is provided a liquid volume measurement system, comprising: the prediction system as described above; and

[0043] a second acquisition unit configured to acquire the total amount of liquid measured by a device for gas-liquid separation of the produced fluid of the oil well;

[0044] a first correction unit configured to correct the total amount of liquid based on the predicted liquid content in the gas to determine the correct total amount of liquid corresponding to the produced fluid of the oil well; and / or

[0045] a third acquisition unit configured to acquire the water content measured by a device for gas-liquid separation of the produced fluid of the oil well;

[0046] a determination unit configured to determine the water cut ratio corresponding to the produced fluid of the oil well based on the water content and the correct total amount of liquid; and / or

[0047] Comprising: a processor;

[0048] a memory for storing processor-executable instructions;

[0049] wherein the processor is configured to call the instructions stored in the memory to execute the liquid volume measurement method according to claim 6; and / or

[0050] Comprising: a computer-readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the above-described liquid volume measurement method.

[0051] According to one aspect of the present disclosure, there is provided a gas volume measurement system, characterized by comprising: the prediction system as described above and / or the liquid volume measurement system as described above; and

[0052] a fourth acquisition unit configured to acquire the gas content measured by a device for gas-liquid separation of the produced fluid of the oil well;

[0053] a second correction unit configured to correct the gas content based on the predicted liquid content in the gas to obtain the correct gas content; and / or

[0054] Comprising: a processor;

[0055] a memory for storing processor-executable instructions;

[0056] wherein the processor is configured to call the instructions stored in the memory to execute the above-described gas volume measurement method; and / or

[0057] Including: a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the above-described method for measuring gas volume.

[0058] In an embodiment of the present disclosure, a technical solution for a method for predicting liquid content in gas, a method and a system for measuring liquid volume and gas volume are proposed. To solve the problem that the current measurement of the liquid content in the gas after gas-liquid separation using a traditional sensor is inaccurate.

[0059] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and do not limit the present disclosure.

[0060] Other features and aspects of the present disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification. These drawings show embodiments consistent with the present disclosure and, together with the specification, are used to explain the technical solutions of the present disclosure.

[0062] Figure 1 A flowchart showing a method for predicting liquid content in gas according to an embodiment of the present disclosure;

[0063] Figure 2 A schematic structural diagram corresponding to a gas-liquid separation device according to an embodiment of the present disclosure;

[0064] Figure 3 A block diagram of an electronic device 800 shown according to an exemplary embodiment;

[0065] Figure 4 A block diagram of an electronic device 1900 shown according to an exemplary embodiment. DETAILED DESCRIPTION

[0066] The following will detail various exemplary embodiments, features and aspects of the present disclosure with reference to the accompanying drawings. The same reference numerals in the drawings denote elements having the same or similar functions. Although various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0067] The special word "exemplary" herein means "serving as an example, embodiment or illustration". Any embodiment described as "exemplary" herein need not be construed as superior to or better than other embodiments.

[0068] As used herein, the term "and / or" is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent three cases: A exists alone, both A and B exist simultaneously, and B exists alone. Additionally, the term "at least one" as used herein means any one of multiple types or any combination of at least two of multiple types. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set composed of A, B, and C.

[0069] In addition, for a better illustration of the present disclosure, numerous specific details are provided in the following specific implementation manners. Those skilled in the art should understand that the present disclosure can still be implemented without certain specific details. In some instances, methods, means, elements, and circuits well-known to those skilled in the art are not described in detail to highlight the gist of the present disclosure.

[0070] It can be understood that, without violating the principle logic, the above-mentioned various method embodiments mentioned in the present disclosure can be combined with each other to form combined embodiments. Due to space limitations, the present disclosure will not elaborate further.

[0071] In addition, the present disclosure also provides a prediction device or system for gas liquid content, a measurement device or system for liquid volume and gas volume, an electronic device, a computer-readable storage medium, and a program. The above can all be used to implement any one of the prediction methods for gas liquid content, and the measurement methods for liquid volume and gas volume provided by the present disclosure. The corresponding technical solutions and descriptions can be referred to the corresponding records in the method section and will not be elaborated further.

[0072] Figure 1 The flowchart showing the prediction method for gas liquid content according to an embodiment of the present disclosure. Figure 2 The structural schematic diagram corresponding to the gas-liquid separation device according to an embodiment of the present disclosure is shown. As Figure 1 and Figure 2 shown, the present application mainly aims to predict the water volume and oil volume (gas liquid content) carried away during the gas-liquid separation process. The prediction method for the gas liquid content includes: Step S101: Obtain the physical property parameters of the oil well produced fluid, the geological formation information, and the device characteristic parameters for gas-liquid separation of the oil well produced fluid; Step S102: Based on the physical property parameters of the oil well produced fluid, the geological formation information, the device characteristic parameters, and a preset regression model, predict the gas liquid content after gas-liquid separation. This is to solve the problem that the current measurement of the gas liquid content after gas-liquid separation using traditional sensors is inaccurate.

[0073] In embodiments of the present disclosure and other possible embodiments, one end of the inlet pipeline 1 of the well effluent is connected to the outlet of the well effluent, the other end of the inlet pipeline 1 is connected to one end of the gas-liquid separation device 2, the other end of the gas-liquid separation device 2 is connected to one end of the liquid pipeline 3, the gas-liquid separation device 2 is also provided with a gas comprehensive flowmeter 9 on the gas pipeline 8 connected thereto, the liquid pipeline 3 is provided with a liquid comprehensive flowmeter 4, the other end of the liquid pipeline 3 is connected to the water content measurement tank 5, the water content measurement tank 5 is provided with a water content sensor 7, one end of the gas pipeline 8 is connected to the gas-liquid separation device 2, and the other ends of the water content measurement tank 5 and the gas pipeline 8 are connected to the outlet pipeline 6.

[0074] In embodiments of the present disclosure and other possible embodiments, the liquid comprehensive flowmeter 4 is used to measure the total amount of liquid measured by the equipment for gas-liquid separation of the well effluent; the water content sensor 7 is used to measure the water content measured by the equipment for gas-liquid separation of the well effluent; the gas comprehensive flowmeter 9 is used to measure the gas content measured by the equipment for gas-liquid separation of the well effluent.

[0075] Step S101: Obtain the physical property parameters, geological formation information, and equipment characteristic parameters of the equipment for gas-liquid separation of the well effluent corresponding to the well effluent.

[0076] In embodiments of the present disclosure, the physical property parameters corresponding to the well effluent include one or several of the fluid temperature, fluid pressure, fluid density, and fluid initial velocity corresponding to the well effluent; and / or, the geological formation information corresponding to the well effluent includes one or several of the reservoir thickness, permeability, and formation pressure; and / or, the equipment characteristic parameters of the equipment for gas-liquid separation of the well effluent include one or several of the working pressure, working temperature, fluid inlet velocity into the equipment or device, separator type, and separator size corresponding to the equipment or device for gas-liquid separation of the well effluent.

[0077] In embodiments of the present disclosure and other possible embodiments, the physical property parameters and geological formation information corresponding to the well effluent are configured as well operation data, including but not limited to the physical property parameters of the fluid (well effluent) (including fluid temperature T, fluid pressure P, fluid density ρ, and fluid initial velocity V), the geological formation information corresponding to the fluid (well effluent) (reservoir thickness H, permeability K, formation pressure P r ), and parameters related to the equipment characteristics of the gas-liquid separation device (device working pressure P w , device working temperature T w , fluid inlet velocity into the device V w , separator type Type, and separator size Size).

[0078] d i =(T, P, ρ, V, H, K, P r , P w , T w , Type, Size)

[0079] Among them, d i is the i-th data in the dataset (original characteristic parameters, original dataset), and T, P, ρ, V, H, K, P r , P w , T w , Type, and Size are the above-mentioned parameter characterization values respectively.

[0080] In the embodiments of the present disclosure, before predicting the liquid content in the gas after gas-liquid separation based on the physical property parameters corresponding to the oil well produced fluid, the geological formation information, the equipment characteristic parameters, and the preset regression model, the physical property parameters corresponding to the oil well produced fluid, the geological formation information, and the equipment characteristic parameters are normalized to obtain the corresponding normalized physical property parameters, normalized geological formation information, and normalized equipment characteristic parameters.

[0081] In the embodiments of the present disclosure and other possible embodiments, the obtained original data d i (dataset, original characteristic parameters, original dataset) will be parsed and calculated. In this application, data normalization is first used for processing to ensure that all subsequent characteristic parameters are kept in the same dimension and to prevent a certain characteristic parameter from occupying too large or too small a proportion.

[0082] Among them, data normalization is expressed as follows:

[0083]

[0084] Among them, is the processed characteristic parameter, d i is the original characteristic parameter, μ D is the mean value of the parameters in the original dataset, and σ D is the standard deviation of the parameters in the original dataset.

[0085] In an embodiment of the present disclosure, the method for training a preset regression model based on the physical property parameters of the oil well produced fluid, the geological formation information, and the equipment characteristic parameters includes: dividing the physical property parameters of the oil well produced fluid, the geological formation information, and the equipment characteristic parameters to obtain reservoir characteristics and mechanical equipment characteristics; respectively extracting the reservoir characteristics according to a plurality of set first weight values to obtain a plurality of first selected reservoir characteristics; and respectively extracting the mechanical equipment characteristics according to a plurality of set second weight values corresponding to the plurality of set first weight values to obtain first selected mechanical equipment characteristics corresponding to the plurality of first selected reservoir characteristics; respectively training the preset regression model based on the first selected mechanical equipment characteristics corresponding to the plurality of first selected reservoir characteristics to obtain a corresponding plurality of first preset regression models after training; selecting an optimal initial model from the plurality of first preset regression models after training based on a set model evaluation criterion; and predicting the liquid content in the gas after gas-liquid separation by using the physical property parameters of the liquid content in the gas to be predicted, the geological formation information, and the equipment characteristic parameters based on the optimal initial model after training.

[0086] In the embodiments of the present disclosure and other possible embodiments, the separation and calibration of reservoir-mechanical dual characteristics. Intelligent identification and classification of data characteristics from different sources. First, the acquired data is classified into two major categories: reservoir characteristics and mechanical equipment characteristics, and further subdivided into multiple subcategories of each. Specifically, the reservoir characteristics may include one or several of fluid temperature, fluid pressure, fluid density, initial fluid velocity, reservoir thickness, permeability, and formation pressure. And the mechanical equipment characteristics include one or several of the device working pressure (working pressure), device working temperature (working temperature), fluid inlet velocity of the device, separator type, and separator size. Through such classification and calibration work, we lay a foundation for subsequent feature selection and analysis work, ensuring that feature adjustment and weight allocation can be carried out targeted in the model construction and optimization stage.

[0087] C = {c 1 , c 2}

[0088]

[0089] Among them, C represents the feature category set, c 1 , c 2 respectively represent reservoir characteristics and mechanical equipment characteristics, The processed data The function that maps to the correct feature category, d' i The data set classified according to the feature category set.

[0090] In embodiments of the present disclosure and other possible embodiments, an integrated learning network architecture based on a competition mechanism is constructed and optimized. The separation and calibration of reservoir-mechanical dual characteristics are completed. In this application, an integrated learning network architecture based on a competition mechanism is proposed for the first time, that is, based on reservoir-mechanical dual characteristics, an integrated learning network architecture guided by a competition mechanism is constructed. This architecture will consist of three sub-integrated learning networks, each having differences in feature selection, and is used to predict the amount of water and oil carried away during the gas-liquid separation process.

[0091] In the stage of constructing the sub-integrated learning network, different feature selection strategies are adopted according to the competition operator.

[0092] Among them, the competition operator is expressed as follows:

[0093]

[0094] Among them, Net i represents the i-th sub-integrated network (the i-th preset regression model), c 1 , c 2 are the reservoir feature and the mechanical equipment feature respectively, (c 1 , c 2 ) represents the feature proportion vector.

[0095] Specifically, in embodiments of the present disclosure and other possible embodiments, those skilled in the art can configure the respective numbers and values of the multiple set first weight values and the multiple set second weight values corresponding to the multiple set first weight values. For example, the respective numbers of the multiple set first weight values and the multiple set second weight values corresponding to the multiple set first weight values are configured to be 3. The 3 set first weight values are respectively configured to be 1 / 3, 1 / 2, and 2 / 3, and the multiple set second weight values corresponding to the 3 set first weight values are respectively configured to be 2 / 3, 1 / 2, and 1 / 3.

[0096] In an embodiment of the present disclosure, the sum of the multiple set first weight values and the multiple set second weight values corresponding to the multiple set first weight values is configured to be 1. For example, the 3 set first weight values are respectively configured to be 1 / 3, 1 / 2, and 2 / 3, and the 3 set second weight values corresponding to the 3 set first weight values are respectively configured to be 2 / 3, 1 / 2, and 1 / 3. Among them, the sums of the set first weight value and the corresponding set second weight value are respectively 1 / 3 + 2 / 3, 1 / 2 + 1 / 2, and 2 / 3 + 1 / 3.

[0097] More specifically, in the embodiments of the present disclosure and other possible embodiments, the reservoir characteristics are extracted according to three set first weight values of 1 / 3, 1 / 2, and 2 / 3 respectively to obtain three first selected reservoir characteristics. And the mechanical equipment characteristics are extracted according to three set second weight values of 2 / 3, 1 / 2, and 1 / 3 corresponding to the three set first weight values respectively to obtain the first selected mechanical equipment characteristics corresponding to the three first selected reservoir characteristics. At the same time, the preset regression model is trained respectively based on the first selected mechanical equipment characteristics corresponding to the three first selected reservoir characteristics to obtain three corresponding trained first preset regression models.

[0098] In the embodiments of the present disclosure and other possible embodiments, those skilled in the art can configure the set model evaluation criterion according to actual needs. For example, the set model evaluation criterion can be configured as the root mean square error. In the above steps, the construction of sub-integration networks with three different feature ratios is completed. That is, after establishing the feature selection strategy, each sub-network will perform model training based on the selected features. In this application, the least squares error (MSE) minimization is used as the splitting criterion (when the regression model is configured as a regression tree), and the root mean square error is used to evaluate the prediction performance of the sub-network.

[0099] In the embodiments of the present disclosure and other possible embodiments, the method for selecting the optimal initial model from the multiple trained first preset regression models based on the set model evaluation criterion includes: calculating multiple model evaluation parameters corresponding to the multiple trained first preset regression models respectively based on the set model evaluation criterion; configuring the trained first preset regression model corresponding to the optimal model evaluation parameter among the multiple model evaluation parameters as the optimal initial model.

[0100] For example, if the set model evaluation criterion is configured as the root mean square error, then calculate the multiple root mean square errors corresponding to the multiple trained first preset regression models respectively; configure the trained first preset regression model corresponding to the minimum root mean square error among the multiple root mean square errors as the optimal initial model.

[0101] In the embodiments of the present disclosure and other possible embodiments, evaluate the initial three sub-networks (3 trained first preset regression models) Net 1 , Net 2 and Net 3 , the ratio of reservoir characteristics to mechanical equipment characteristics of which are respectively configured as Then select the initial optimal model according to the RMSE formula.

[0102] Among them, RMSE is expressed as follows: k opt = argminRMSE(Netk ), k = 1, 2, 3.

[0103] Among them, k opt is the serial number of the initial optimal model, and Net k represents the k-th sub-ensemble network (the k-th first preset regression model after training).

[0104] In the embodiments of the present disclosure, before predicting the liquid content in the gas after gas-liquid separation by using the physical property parameters corresponding to the liquid content in the gas after gas-liquid separation to be predicted and the equipment characteristic parameters of the geological formation information based on the trained optimal initial model, it further includes: obtaining a plurality of first set neighborhood values Δr and a plurality of second set neighborhood values Δe, and respectively adjusting the first weight value c 1 and the second weight value c 2 corresponding to the optimal initial model to obtain a plurality of corresponding first adjusted weight values c 1 ±Δr and a plurality of second adjusted weight values c 2 ±Δe; respectively extracting the reservoir characteristics according to a plurality of first adjusted weight values c 1 ±Δr to obtain a plurality of second selected reservoir characteristics; and respectively extracting the mechanical equipment characteristics according to the plurality of set second adjusted weight values c 2 ±Δe corresponding to the plurality of set first adjusted weight values to obtain the second selected mechanical equipment characteristics corresponding to the plurality of second selected reservoir characteristics; respectively training the preset regression model based on the second selected mechanical equipment characteristics corresponding to the plurality of second selected reservoir characteristics to obtain a plurality of corresponding second preset regression models after training; selecting the optimal regression model from the plurality of second preset regression models after training based on the set model evaluation criterion; predicting the liquid content in the gas by using the physical property parameters corresponding to the liquid content in the gas after gas-liquid separation to be predicted and the equipment characteristic parameters of the geological formation information based on the optimal regression model after training.

[0105] In the embodiments of the present disclosure and other possible embodiments, the selection of the initial optimal model is completed in the above steps, and in this step, further dynamic feature ratio competition selection is performed within the neighborhood (the first set neighborhood value Δr and the second set neighborhood value Δe) according to the ratio experiment formula.

[0106] Among them, the ratio experiment formula is expressed as follows:

[0107] S = {(c 1 ±Δr, c 2 ±Δe)|Δr, Δe ∈ D}

[0108] Among them, S is the neighborhood oscillating sub-network corresponding to the initial optimal model (multiple trained second preset regression models), c 1 , c 2 are the reservoir characteristics and mechanical equipment characteristics respectively, and D is the set of allowable adjustment ratio ranges; multiple first-set neighborhood values Δr and multiple second-set neighborhood values Δe.

[0109] In the embodiments of the present disclosure and other possible embodiments, in this step, for each pair (c 1 , c 2 ) in the neighborhood oscillating sub-network corresponding to the optimal initial model, a Net network (multiple trained second preset regression models) is established, and its RMSE (set model evaluation criterion) is calculated, and the model with the smallest RSME is selected as an integrated learning network architecture (trained optimal regression model) of a competition mechanism proposed in this application.

[0110] Step S102: Predict the liquid content in the gas after gas-liquid separation based on the physical property parameters of the oil well produced fluid, the geological formation information, the equipment characteristic parameters, and the preset regression model.

[0111] In the embodiments of the present disclosure, the method for predicting the liquid content in the gas after gas-liquid separation based on the physical property parameters of the oil well produced fluid, the geological formation information, the equipment characteristic parameters, and the preset regression model includes: training the preset regression model based on the physical property parameters of the oil well produced fluid, the geological formation information, and the equipment characteristic parameters; based on the trained preset regression model, predicting the liquid content in the gas by using the physical property parameters and geological formation information of the equipment characteristic parameters corresponding to the liquid content in the gas to be predicted after gas-liquid separation.

[0112] In the embodiments of the present disclosure and other possible embodiments, the physical property parameters of the oil well produced fluid, the geological formation information, and the equipment characteristic parameters are configured as the physical property parameters of the oil well produced fluid and the geological formation information in historical data. For example, the physical property parameters of the oil well produced fluid and the geological formation information in historical data are configured as oil well operation data, including but not limited to the physical property parameters of the fluid (the produced fluid of the oil well) (including fluid temperature T, fluid pressure P, fluid density ρ, and initial fluid velocity V), and the geological formation information corresponding to the fluid (the produced fluid of the oil well) (reservoir thickness H, permeability K, formation pressure P r ).

[0113] In the embodiments of the present disclosure and other possible embodiments, during the process of training a preset regression model based on the physical property parameters corresponding to the oil well produced fluid, the geological formation information, and the equipment characteristic parameters, it includes: the true liquid content in the gas after gas-liquid separation (label) corresponding to the physical property parameters of the oil well produced fluid, the geological formation information, and the equipment characteristic parameters.

[0114] In the embodiments of the present disclosure and other possible embodiments, those skilled in the art can select or configure the preset regression model according to actual needs. For example, the preset regression model can be configured as one or several of linear regression (LinearRegression), logistic regression (Logistic Regression), polynomial regression (Polynomial Regression), stepwise regression (Stepwise Regression), ridge regression (Ridge Regression), lasso regression (LassoRegression), elastic net regression (ElasticNet Regression), regression tree, etc.

[0115] In the embodiments of the present disclosure and other possible embodiments, before predicting the liquid content in the gas after gas-liquid separation based on the trained preset regression model, using the physical property parameters corresponding to the liquid content in the gas to be predicted after gas-liquid separation, the geological formation information, and the equipment characteristic parameters, perform the same normalization processing on the physical property parameters corresponding to the liquid content in the gas to be predicted after gas-liquid separation, the geological formation information, and the equipment characteristic parameters as during training, to obtain the normalized physical property parameters, normalized geological formation information, and normalized equipment characteristic parameters corresponding to the liquid content in the gas to be predicted after gas-liquid separation.

[0116] In addition, the present disclosure also proposes a method for measuring the liquid volume, including: the prediction method as described above; and, obtaining the total liquid volume measured by the equipment for gas-liquid separation of the oil well produced fluid; and correcting the total liquid volume based on the predicted liquid content in the gas to determine the correct total liquid volume corresponding to the oil well produced fluid; and / or, obtaining the water content measured by the equipment for gas-liquid separation of the oil well produced fluid; and determining the water content ratio corresponding to the oil well produced fluid based on the water content and the correct total liquid volume.

[0117] In the embodiments of the present disclosure and other possible embodiments, through the above steps, this application can accurately predict the liquid content (oil + water) in the gas separated by the gas separation device. In this step, the predicted value is used to perform more accurate measurements of the gas content in the reservoir and the water flow according to the measurement correction formula.

[0118] Among them, the measurement correction formula is expressed as follows:

[0119] V corrected = V measured + V gas-liquid ;

[0120]

[0121] wherein, V corrected represents the total amount of correct liquid (oil and water), V measured represents the total amount of measured liquid, V gas-liquid represents the total liquid content (predicted value) in the gas during separation, P water represents the water content ratio of the correct liquid, V water represents the water content.

[0122] In addition, the present disclosure also provides a method for measuring gas volume, including: the prediction method as described above and / or the method for measuring liquid volume as described above; and obtaining the gas content measured by the device for gas-liquid separation of the produced fluid of the oil well; and correcting the gas content based on the predicted liquid content in the gas to obtain the correct gas content.

[0123] Among them, the measurement correction formula is expressed as follows:

[0124] V gas-corrected = V gas-measured - V gas-liquid ;

[0125] wherein, V gas-corrected represents the correct gas content, V gas-measured represents the measured gas content.

[0126] The execution subject of the prediction of liquid content in gas, the measurement methods of liquid volume and gas volume can be a device or system for predicting liquid content in gas, a device or system for measuring liquid volume and gas volume. For example, the prediction of liquid content in gas, the measurement methods of liquid volume and gas volume can be executed by a terminal device, a server or other processing devices. Among them, the terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementation manners, the prediction method of the liquid content in gas can be implemented by a processor calling computer-readable instructions stored in a memory.

[0127] Those skilled in the art can understand that in the above method of the specific implementation manner, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined according to its function and possible internal logic.

[0128] In addition, the present disclosure also provides a prediction system for gas liquid content, including: a first acquisition unit, configured to acquire physical property parameters of the oil well produced fluid, geological formation information, and equipment characteristic parameters for gas-liquid separation of the oil well produced fluid; and a prediction unit, configured to predict the gas liquid content after gas-liquid separation based on the physical property parameters of the oil well produced fluid, the geological formation information, the equipment characteristic parameters, and a preset regression model.

[0129] In addition, the present disclosure also provides a prediction system for gas liquid content, including: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-mentioned prediction method.

[0130] In addition, the present disclosure also provides a prediction system for gas liquid content, including: a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the above-mentioned prediction method is implemented.

[0131] In addition, the present disclosure also provides a measurement system for liquid volume, including: the above-mentioned prediction system; and a second acquisition unit, configured to acquire the total liquid volume measured by the equipment for gas-liquid separation of the oil well produced fluid; and a first correction unit, configured to correct the total liquid volume based on the predicted gas liquid content to determine the correct total liquid volume corresponding to the oil well produced fluid.

[0132] In addition, the present disclosure also provides a measurement system for liquid volume, including: the above-mentioned prediction system; and a third acquisition unit, configured to acquire the water content measured by the equipment for gas-liquid separation of the oil well produced fluid; and a determination unit, configured to determine the water content ratio corresponding to the oil well produced fluid based on the water content and the correct total liquid volume.

[0133] In addition, the present disclosure also provides a measurement system for liquid volume, including: the above-mentioned prediction system; and a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-mentioned measurement method for liquid volume.

[0134] In addition, the present disclosure also provides a measurement system for liquid volume, including: the above-mentioned prediction system; and a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the above-mentioned measurement method for liquid volume is implemented.

[0135] In addition, the present disclosure also provides a gas volume measurement system, including: the prediction system as described above; and / or the liquid volume measurement system as described above; and a fourth acquisition unit configured to acquire the gas content measured by a device for gas-liquid separation of the produced fluid of the oil well; and a second correction unit configured to correct the gas content based on the predicted liquid content in the gas to obtain the correct gas content.

[0136] In addition, the present disclosure also provides a gas volume measurement system, including: the prediction system as described above; and / or the liquid volume measurement system as described above; and a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-described gas volume measurement method.

[0137] In addition, the present disclosure also provides a gas volume measurement system, including: the prediction system as described above; and / or the liquid volume measurement system as described above; and a computer-readable storage medium having computer program instructions stored thereon, where the computer program instructions, when executed by a processor, implement the above-described gas volume measurement method.

[0138] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be elaborated here.

[0139] The embodiments of the present disclosure also provide a computer-readable storage medium having computer program instructions stored thereon, where the computer program instructions, when executed by a processor, implement the above method. The computer-readable storage medium can be a non-volatile computer-readable storage medium.

[0140] The embodiments of the present disclosure also provide an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the above method. Among them, the electronic device can be provided as a terminal, a server or other forms of devices.

[0141] This application aims to address a series of technical challenges in the traditional oilfield wellhead gas-liquid separation and fluid measurement, mainly focusing on improving the accuracy and real-time performance of the oil-gas separation process and oilfield fluid measurement. In previous technical applications, the gas-liquid separation at the oilfield wellhead and subsequent fluid measurement were usually affected by various factors such as equipment accuracy, environmental variables, and changes in material properties. It was difficult to obtain accurate and real-time measurement data, which might lead to the accumulation of errors and inaccurate decisions. Especially in the determination of the liquid content in gas, due to technical and equipment limitations, the usual methods were difficult to achieve accurate measurement and dynamic adjustment. The present invention provides a method that can achieve more accurate and real-time wellhead fluid measurement and has the ability of self-learning and continuous optimization. It can ensure that a large amount of real-time data generated at the oilfield wellhead can be quickly and locally processed and analyzed without relying on a remote data center, thus greatly improving the timeliness and accuracy of data processing. Furthermore, it provides the ability to automatically learn and optimize models. By continuously learning the operation data of the wellhead, it automatically optimizes the data processing and analysis models, thereby continuously improving the accuracy of measurement and analysis. Especially in achieving precise quantification and dynamic adjustment of the liquid content in gas through a machine learning model, the method of the present invention can significantly reduce measurement errors, enhance the reliability and stability of oilfield operations, and provide more accurate and timely data support for operation decisions, further promoting the digitalization and intelligent development of oilfields, and ultimately achieving the goal of improving oilfield production efficiency and economic benefits.

[0142] The oilfield wellhead gas-liquid separation and fluid measurement method and its system architecture proposed in this application. In this method, various physical parameters during the oil-gas separation process are first obtained in real time at each oil well wellhead, including but not limited to fluid temperature, fluid pressure, fluid density flow rate, reservoir thickness, formation permeability, formation pressure, and the content of separated gas and liquid. In addition, the working parameters of the gas-liquid separation device, such as working pressure, working temperature, fluid flow rate, separator type, separator size, etc., are also accurately measured and recorded.

[0143] Next, this application introduces a unique integrated learning network architecture that uses three sub-integrated learning networks with different feature selection strategies. The first sub-network mainly focuses on mechanical equipment features, the second sub-network achieves a balance between mechanical equipment features and reservoir features, and the third sub-network mainly focuses on reservoir features. In the initial stage, these three sub-networks respectively learn and train the well data and output the prediction results of the liquid content in gas. By comparing the prediction accuracies of these three sub-networks, the more decisive feature categories are determined.

[0144] After identifying the more important feature categories, this application allocates more data analysis resources to these feature categories and further subdivides its feature selection strategy. For example, if mechanical equipment features are identified as more important feature categories, then multiple new integrated learning networks will be constructed. When selecting features for each subtree, these networks will tend to select more mechanical equipment features. Through this method, this application achieves self-optimization and continuous learning of the model.

[0145] After obtaining a relatively accurate prediction of the gas liquid content, this application further realizes the continuous optimization of the model and the precise support for oilfield operations through fine prediction and error correction steps, as well as dynamic feedback and model update steps. Among them, in the fine prediction and error correction link, the fluid parameter data collected in real time is compared with the output result of the prediction model to calculate the prediction error of the model, and then the model parameters are adjusted and optimized in real time through techniques such as backpropagation; while in the dynamic feedback and model update link, by continuously collecting various data of oilfield operations, the training data set of the model is updated regularly to ensure that the model can accurately reflect the actual operating state of the oilfield and continuously provide accurate data support. Through the above series of steps, this application provides a highly automated, precise and self-optimizing technical solution for gas-liquid separation and fluid measurement at the oilfield wellhead.

[0146] Figure 3 It is a block diagram of an electronic device 800 shown according to an exemplary embodiment. For example, the electronic device 800 can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant and other terminals.

[0147] Referring to Figure 3 , the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0148] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, telephone call, data communication, camera operation, and recording operation. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0149] The memory 804 is configured to store various types of data to support the operation of the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, and the like. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0150] The power supply component 806 provides power to various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

[0151] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can not only sense the boundaries of touch or swipe actions but also detect the duration and pressure associated with the touch or swipe operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the electronic device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each of the front camera and the rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

[0152] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC) that is configured to receive external audio signals when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 further includes a speaker for outputting audio signals.

[0153] The I / O interface 812 provides an interface between the processing component 802 and a peripheral interface module, which can be a keyboard, a click wheel, buttons, etc. These buttons can include, but are not limited to: a home button, a volume button, a power-on button, and a lock button.

[0154] The sensor assembly 814 includes one or more sensors for providing an assessment of the status of various aspects of the electronic device 800. For example, the sensor assembly 814 can detect the on / off state of the electronic device 800, the relative positioning of components, such as the display and keypad of the electronic device 800. The sensor assembly 814 can also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and a change in the temperature of the electronic device 800. The sensor assembly 814 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 can also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 can also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0155] The communication component 816 is configured to facilitate communication between the electronic device 800 and other devices in a wired or wireless manner. The electronic device 800 can access a wireless network based on communication standards, such as WiFi, 2G, or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0156] In an exemplary embodiment, the electronic device 800 can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above-described method.

[0157] In an exemplary embodiment, a non-transitory computer-readable storage medium is also provided, such as a memory 804 including computer program instructions, which can be executed by a processor 820 of the electronic device 800 to complete the above-described method.

[0158] Figure 4 is a block diagram of an electronic device 1900 shown in accordance with an exemplary embodiment. For example, the electronic device 1900 can be provided as a server. Referring to Figure 4, the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by a memory 1932 for storing instructions executable by the processing component 1922, such as application programs. The application programs stored in the memory 1932 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0159] The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.

[0160] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as the memory 1932 including computer program instructions, and the above computer program instructions can be executed by the processing component 1922 of the electronic device 1900 to complete the above method.

[0161] The present disclosure may be a system, a method, and / or a computer program product. The computer program product may include a computer-readable storage medium having thereon computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0162] A computer-readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically encoded device, such as a punched card or raised structures in grooves storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage medium used herein is not construed as an instantaneous signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0163] The computer-readable program instructions described herein can be downloaded to various computing / processing devices from a computer-readable storage medium or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0164] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state-setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the state information of the computer-readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions to implement various aspects of the present disclosure.

[0165] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0166] These computer-readable program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to produce a machine such that the instructions, when executed by the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in one or more boxes of the flowchart and / or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium that causes a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises a manufacture including instructions for implementing various aspects of the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0167] The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other devices to produce a computer-implemented process such that the instructions executed on the computer, other programmable data processing apparatus, or other devices implement the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0168] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of code, or a portion of an instruction, and the module, segment of code, or portion of an instruction may include one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the boxes may occur out of the order noted in the figures. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functionality involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by special-purpose hardware-based systems that perform the specified functions or acts, or by combinations of special-purpose hardware and computer instructions.

[0169] The embodiments of the present disclosure have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, the practical application, or the technical improvement of the technology in the market, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein.

Claims

1. A method for predicting the liquid content in gas, characterized in that, it includes: obtaining the physical property parameters corresponding to the oil well produced fluid, the geological formation information, and the equipment characteristic parameters for gas-liquid separation of the oil well produced fluid; predicting the liquid content in the gas after gas-liquid separation based on the physical property parameters corresponding to the oil well produced fluid, the geological formation information, the equipment characteristic parameters, and a preset regression model.

2. The prediction method according to claim 1, characterized in that, the method for predicting the liquid content in the gas after gas-liquid separation based on the physical property parameters corresponding to the oil well produced fluid, the geological formation information, the equipment characteristic parameters, and a preset regression model includes: training the preset regression model based on the physical property parameters corresponding to the oil well produced fluid, the geological formation information, and the equipment characteristic parameters; predicting the liquid content in the gas based on the physical property parameters corresponding to the liquid content in the gas to be predicted after gas-liquid separation, the geological formation information, and the equipment characteristic parameters by using the trained preset regression model.

3. The prediction method according to claim 2, characterized in that, the method for training the preset regression model based on the physical property parameters corresponding to the oil well produced fluid, the geological formation information, and the equipment characteristic parameters includes: dividing the physical property parameters corresponding to the oil well produced fluid, the geological formation information, and the equipment characteristic parameters to obtain reservoir characteristics and mechanical equipment characteristics; extracting the reservoir characteristics respectively according to multiple set first weight values to obtain multiple first selected reservoir characteristics; and extracting the mechanical equipment characteristics corresponding to the multiple first selected reservoir characteristics respectively according to multiple set second weight values corresponding to the multiple set first weight values; training the preset regression model respectively based on the mechanical equipment characteristics corresponding to the multiple first selected reservoir characteristics to obtain multiple corresponding trained first preset regression models; selecting the optimal initial model from the multiple trained first preset regression models based on a set model evaluation criterion; predicting the liquid content in the gas based on the physical property parameters corresponding to the liquid content in the gas to be predicted after gas-liquid separation, the geological formation information, and the equipment characteristic parameters by using the trained optimal initial model; and / or, the sum of the multiple set first weight values and the multiple set second weight values corresponding to the multiple set first weight values is configured to be 1.

4. The prediction method according to claim 3, characterized in that, before predicting the liquid content in the gas based on the physical property parameters corresponding to the liquid content in the gas to be predicted after gas-liquid separation, the geological formation information, and the equipment characteristic parameters by using the trained optimal initial model, it further includes: obtaining multiple first set neighborhood values and multiple second set neighborhood values, and respectively adjusting the first weight value and the second weight value corresponding to the optimal initial model based on the multiple first set neighborhood values and the multiple second set neighborhood values to obtain corresponding multiple first adjusted weight values and multiple second adjusted weight values; Extract the reservoir characteristics according to multiple first adjustment weight values respectively to obtain multiple second selected reservoir characteristics; and extract the mechanical equipment characteristics according to multiple set second adjustment weight values corresponding to the multiple set first adjustment weight values respectively to obtain second selected mechanical equipment characteristics corresponding to the multiple second selected reservoir characteristics; Train the preset regression model respectively based on the second selected mechanical equipment characteristics corresponding to the multiple second selected reservoir characteristics to obtain multiple corresponding trained second preset regression models; Select the optimal regression model from the multiple trained second preset regression models based on the set model evaluation criterion; Based on the trained optimal regression model, predict the liquid content in the gas after gas-liquid separation by using the physical property parameters and geological formation information corresponding to the liquid content in the gas to be predicted and the equipment characteristic parameters; and / or Adjust the first weight value and the second weight value corresponding to the optimal initial model respectively based on the multiple first set neighborhood values and the multiple second set neighborhood values to obtain multiple corresponding first adjustment weight values and the sum of the multiple second adjustment weight values configured to be 1.

5. The prediction method according to any one of claims 1-4, characterized in that the physical property parameters corresponding to the oil well produced fluid include one or more of the fluid temperature, fluid pressure, fluid density and fluid initial flow rate corresponding to the oil well produced fluid; and / or, the geological formation information corresponding to the oil well produced fluid includes one or more of the reservoir thickness, permeability and formation pressure; and / or, the equipment characteristic parameters for gas-liquid separation of the oil well produced fluid include one or more of the working pressure, working temperature, fluid inlet equipment or device flow rate, separator type, and separator size corresponding to the equipment or device for gas-liquid separation of the oil well produced fluid; and / or Before predicting the liquid content in the gas after gas-liquid separation based on the physical property parameters corresponding to the oil well produced fluid, the geological formation information, the equipment characteristic parameters and the preset regression model, normalize the physical property parameters corresponding to the oil well produced fluid, the geological formation information and the equipment characteristic parameters to obtain corresponding normalized physical property parameters, normalized geological formation information and normalized equipment characteristic parameters.

6. A method for measuring liquid volume, characterized in that comprises: the prediction method according to any one of claims 1-5; and, Obtain the total liquid volume measured by the equipment for gas-liquid separation of the oil well produced fluid; and correct the total liquid volume based on the predicted liquid content in the gas to determine the correct total liquid volume corresponding to the oil well produced fluid; and / or, Obtain the water content measured by the equipment for gas-liquid separation of the oil well produced fluid; and determine the water cut ratio corresponding to the oil well produced fluid based on the water content and the correct total liquid volume.

7. A method for measuring gas volume, characterized in that comprises: the prediction method according to any one of claims 1-5 and / or the method for measuring liquid volume according to claim 6; and, Obtain the gas content measured by the equipment for gas-liquid separation of the produced fluid from the oil well; and correct the gas content based on the predicted liquid content in the gas to obtain the correct gas content.

8. A prediction system for liquid content in gas Characterized in that it includes: A first acquisition unit, configured to acquire the physical property parameters and geological formation information corresponding to the produced fluid from the oil well, and the equipment characteristic parameters of the equipment for gas-liquid separation of the produced fluid from the oil well; A prediction unit, configured to predict the liquid content in the gas after gas-liquid separation based on the physical property parameters corresponding to the produced fluid from the oil well, the geological formation information, the equipment characteristic parameters, and a preset regression model; and / or A processor; A memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the prediction method according to any one of claims 1 to 5; and / or A computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by the processor, the prediction method according to any one of claims 1 to 5 is implemented.

9. A measurement system for liquid volume Characterized in that it includes: The prediction system according to claim 8; and A second acquisition unit, configured to acquire the total liquid volume measured by the equipment for gas-liquid separation of the produced fluid from the oil well; A first correction unit, configured to correct the total liquid volume based on the predicted liquid content in the gas to determine the correct total liquid volume corresponding to the produced fluid from the oil well; and / or, A third acquisition unit, configured to acquire the water content measured by the equipment for gas-liquid separation of the produced fluid from the oil well; A determination unit, configured to determine the water content ratio corresponding to the produced fluid from the oil well based on the water content and the correct total liquid volume; and / or, A processor; A memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the measurement method for liquid volume according to claim 6; and / or A computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by the processor, the measurement method for liquid volume according to claim 6 is implemented.

10. A measurement system for gas volume Characterized in that it includes: The prediction system according to claim 8 and / or the measurement system for liquid volume according to claim 9; and A fourth acquisition unit, configured to acquire the gas content measured by the equipment for gas-liquid separation of the produced fluid from the oil well; A second correction unit, configured to correct the gas content based on the predicted liquid content in the gas to obtain the correct gas content; and / or, A processor; A memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the measurement method for gas volume according to claim 7; and / or A computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by the processor, the measurement method for gas volume according to claim 7 is implemented.

Images