Remote metering method and system for liquid production capacity of screw pump well

Abstract

The invention belongs to the technical field of oil well liquid production capacity metering, particularly relates to a remote metering method and system for the liquid production capacity of a screw pump well, and aims to solve the problems of low prediction accuracy and narrow range in the prior art. The method comprises the following steps: based on standardized data, calculating a liquid production capacity by using a rotating speed method to obtain a first liquid production capacity, calculating the liquid production capacity by using an IPR curve method to obtain a second liquid production capacity, calculating the liquid production capacity by using an electric energy method to obtain a third liquid production capacity, and calculating the liquid production capacity by using a big data method to obtain a fourth liquid production capacity; the error rate of each liquid production capacity and the actual liquid production capacity is calculated, the liquid production capacity corresponding to the minimum error rate serves as the first determined liquid production capacity, and the method corresponding to the first liquid production capacity serves as the first determined method; calculating a correction coefficient based on the first determined liquid production capacity and the actual liquid production capacity; and calculating the current liquid production capacity of the screw pump well by using a first determination method, and multiplying the correction coefficient by the current liquid production capacity to obtain the current corrected liquid production capacity. According to the invention, the accuracy of metering the liquid production capacity of the screw pump well is improved.

Description

Technical Field

[0001] This invention belongs to the field of oil well production measurement technology, and specifically relates to a remote measurement method and system for production of screw pump wells. Background Technology

[0002] Currently, there are two main methods for remotely measuring the liquid output of screw pumps: differential pressure method and current method.

[0003] The differential pressure method involves real-time acquisition of production data such as oil pressure and back pressure from screw pump wells, and calculating the production rate based on a multiphase flow throttling mathematical model. This includes the conventional differential pressure method and the European flowmeter standard model method. The conventional differential pressure method establishes a throttling model for the nozzle based on the flow characteristics of the fluid passing through it, thus obtaining the basic relationships between the main flow parameters of the oil-gas mixture passing through the nozzle. The European flowmeter standard model method applies Bernoulli's equation and the principle of flow continuity to establish a multiphase flow throttling calculation method. It is then modified and fitted with the screw pump's own energy consumption and lift mathematical models to obtain a production rate calculation law applicable to specific well conditions, calculating the production rate of the screw pump well under standard surface conditions. Both methods require accurate determination of the fluid temperature within the wellbore to infer the fluid velocity and mass flow rate. When the gas content in a single well increases, the fluid velocity becomes unstable, resulting in significant measurement errors. Furthermore, this method requires numerous parameters for calculation, limiting its application range. The current-based method, based on operational condition diagnosis, establishes the relationship between current and pump efficiency using the least squares method according to the actual operating conditions of the screw pump. Then, based on the actual pump efficiency under the operating conditions, the threshold method is used to determine the numerical relationship between pump efficiency and measured electrical parameters, thereby calculating the screw pump well production. Because the production of screw pumps varies greatly under different operating conditions, the remote online measurement method for screw pump well production is based on operational condition diagnosis. Through the measurement and analysis of electrical parameters, the average current of the motor is first analyzed and identified. The current threshold method is used to determine the operating conditions of the screw pump well. Then, the least squares method is used to establish the relationship curve between the dimensionless current of the motor and the pump efficiency of the screw pump, obtaining the actual pump efficiency of the screw pump, and thus calculating the actual production of the screw pump. The above method requires continuous and accurate acquisition of the screw pump torque, analysis of second-level, minute-level, hourly, and daily data of the screw pump well, determination of the well operating conditions based on manually set thresholds, and prediction of production and dynamic fluid level based on the well operating conditions. The method has limited maturity, and the fluid volume of oil wells under the same operating conditions may vary greatly, resulting in low accuracy in predicting oil well production.

[0004] Therefore, existing remote metering methods for screw pump well production have problems such as low prediction accuracy and narrow range. Summary of the Invention

[0005] To address the aforementioned problems in the prior art, namely the low prediction accuracy and narrow range of existing remote metering methods for screw pump well production, this invention provides a remote metering method for screw pump well production, characterized in that the method includes:

[0006] Collect metering data from screw pump wells; perform outlier data removal and missing data interpolation on the metering data to obtain first data; and perform standardization on the first data to obtain standardized data.

[0007] Based on standardized data and real-time collected rotational speed, the first liquid production volume is calculated using the rotational speed method; based on the standardized data and real-time collected pump inlet pressure, the second liquid production volume is calculated using the IPR curve method; based on the standardized data and real-time collected rotational speed and submerged pressure, the third liquid production volume is calculated using the electrical energy method; and based on the standardized data, the fourth liquid production volume is calculated using the big data method.

[0008] The error rates between the first liquid production volume, the second liquid production volume, the third liquid production volume, and the fourth liquid production volume and the actual liquid production volume measured by the tank truck are calculated respectively. The liquid production volume corresponding to the minimum error rate is taken as the first determined liquid production volume, and the method corresponding to the first liquid production volume is taken as the first determining method.

[0009] A correction factor is calculated based on the first determined production volume and the actual production volume; the current production volume of the screw pump well is calculated using the first determination method, and the current corrected production volume is obtained by multiplying the production volume by the correction factor.

[0010] In a preferred embodiment, the method for calculating the first product volume using the rotation speed method includes:

[0011] First, the theoretical displacement and volumetric efficiency of the screw pump well are calculated based on the standardized data; then, the first production volume is calculated based on the volumetric efficiency of the screw pump well and the collected real-time rotation speed.

[0012] In a preferred embodiment, the method for calculating the first product volume using the rotation speed method includes:

[0013] First, calculate the theoretical displacement of the screw pump well based on the standardized data: Q th =1440*4eDTn*10 -9 ;

[0014] Then, the volumetric efficiency of the screw pump well is calculated based on its theoretical displacement:

[0015] Then, based on the volumetric efficiency and theoretical displacement of the screw pump well, the first production rate is calculated:

[0016] Where n represents the historical operating speed of the screw pump, n1 represents the actual test speed of the screw pump, D represents the diameter of the rotor cross-section circle of the screw pump, T represents the stator lead of the screw pump, e represents the eccentricity of the pump, and Q th Q represents the theoretical displacement of the screw pump at a rotational speed n. re η represents the historical displacement of the screw pump at speed n. 容 This refers to the volumetric efficiency of the screw pump well.

[0017] In a preferred embodiment, the method for calculating the second product volume using the IPR curve method includes:

[0018] First, calculate the bottom hole flowing pressure of the screw pump well based on the standardized data: P wf =P r +ρg(h z -h r );

[0019] Then, based on the bottom hole flowing pressure, the maximum fluid production rate is calculated:

[0020] Finally, the second production volume is calculated based on the maximum production volume and the collected pump inlet pressure:

[0021] Among them, P wf For the bottom hole flowing pressure, P r h is the pump inlet pressure. z For medium to deep oil reservoirs; h r For pump depth, P d Let ρ be the average formation pressure, ρ be the well fluid density, g be the acceleration due to gravity, and Q be the average formation pressure. text This is historical fluid production data for screw pump wells, Q. max Q1 is used to calculate the maximum liquid output of the screw pump, and Q2 is the second liquid output.

[0022] In a preferred embodiment, the method for calculating the third product volume using an electrical energy method includes:

[0023] Calculate the unitized liquid yield based on the standardized data:

[0024] Then, based on the standardized data, the unitized power consumption is calculated:

[0025] Then, the unitized liquid production rate and unitized power consumption are fitted to obtain the regression formula for the unitized liquid production rate: Q u =f(E u );

[0026] Finally, based on the regression fitting formula of liquid production volume - power consumption, and the real-time power consumption, rotation speed, submerged pressure, and suction inlet pressure collected in real time, the third liquid production volume is calculated: Q3 = Q u *n1*P s1 =f(E u1 )*n1*P s1 ;

[0027] Among them, Q u E represents the unitized product yield. u Q represents the unitized power consumption. x E represents the liquid production rate. u Power consumption; n is the historical rotational speed; P s The pressure of historical setbacks; f(E) u E represents the functional relationship between unitized power consumption and unitized liquid production. u1 P represents the unitized power consumption collected in real time, where n1 is the rotational speed collected in real time. s1 Q3 represents the real-time submerged pressure, and Q3 represents the third production volume.

[0028] In a preferred embodiment, the method for calculating the fourth product volume using a big data approach includes:

[0029] The parameters affecting the production volume in the standardized data are used as influencing parameters; the Pearson correlation coefficient between each influencing parameter and the production volume of the screw pump well is calculated, and the influencing parameters whose Pearson correlation coefficient is greater than the first threshold are used as characteristic parameters.

[0030] Each feature parameter is treated as a sample. There are n samples in total, and the p values ​​of each sample are treated as p variables.

[0031] The XGBoost model is obtained by training n samples, p variables corresponding to each sample, and the actual liquid production volume corresponding to each sample using the XGBoost intelligent algorithm.

[0032] The fourth production volume can be obtained by substituting the feature parameters into the XGBoost model.

[0033] A second aspect of the present invention provides a remote metering method for the production volume of a screw pump well, the system comprising:

[0034] The data acquisition module is used to acquire metering data from screw pump wells; the metering data is processed by removing abnormal data and interpolating missing data to obtain first data, and the first data is processed by standardization to obtain standardized data;

[0035] The liquid production calculation module is used to calculate the liquid production volume using the rotational speed method based on standardized data and real-time collected rotational speed data to obtain a first liquid production volume; to calculate the liquid production volume using the IPR curve method based on the standardized data and real-time collected pump inlet pressure data to obtain a second liquid production volume; to calculate the liquid production volume using the electrical energy method based on the standardized data and real-time collected rotational speed and submerged pressure data to obtain a third liquid production volume; and to calculate the liquid production volume using the big data method based on the standardized data and real-time collected data to obtain a fourth liquid production volume.

[0036] The method determination module is used to calculate the error rate between the first liquid production volume, the second liquid production volume, the third liquid production volume and the fourth liquid production volume and the actual liquid production volume measured by the tank truck, respectively. The liquid production volume corresponding to the minimum error rate is used as the first determined liquid production volume, and the method corresponding to the first liquid production volume is used as the first determined method.

[0037] The corrected production volume calculation module is used to calculate a correction coefficient based on the first determined production volume and the actual production volume; calculate the current production volume of the screw pump well using the first determination method; and multiply the production volume by the correction coefficient to obtain the current corrected production volume.

[0038] The beneficial effects of this invention are:

[0039] (1) This invention preprocesses the data collected from screw pump wells, filters out abnormal and duplicate data, and performs data normalization, which greatly reduces the impact of the quality of collected data on the accuracy of production volume measurement; it organically combines the rotation speed method, IPR curve method, electrical energy method and big data method to form a comprehensive production volume measurement method for pumping wells, which further improves the accuracy of production volume measurement of screw pump wells, and also improves the level of on-site production management.

[0040] (2) This invention takes into account the influence of geological factors on the production volume measurement and introduces a surface production volume verification method. The production volume initially calculated by the measurement model is verified by means of coefficient calibration, and finally a more accurate wellhead surface production volume is obtained.

[0041] (3) The remote online production metering system for screw pump wells of the present invention utilizes business models and data fusion technology to accurately measure the production of screw pump wells. The system is designed with three core application functions to meet the application needs of researchers, technicians, managers and other different positions. Attached Figure Description

[0042] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0043] Figure 1 This is a schematic diagram of a remote metering method for the production of fluid in a screw pump well according to an embodiment of the present invention;

[0044] Figure 2 This is a schematic diagram of a missing data interpolation process according to an embodiment of the present invention;

[0045] Figure 3 This is a scatter plot showing the relationship between liquid production and power consumption under unitized conditions according to an embodiment of the present invention.

[0046] Figure 4 This is a schematic diagram of the basic process of calculating screw pump well production using big data method according to an embodiment of the present invention;

[0047] Figure 5 This is a schematic diagram of a remote metering system for well production of screw pumps according to an embodiment of the present invention;

[0048] Figure 6 This is a schematic diagram of the structure of a computer system used to implement the methods, systems, and devices of this application. Detailed Implementation

[0049] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0050] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0051] This invention provides a method for remote metering of fluid production in screw pump wells, the method comprising:

[0052] Collect metering data from screw pump wells; perform outlier data removal and missing data interpolation on the metering data to obtain first data; and perform standardization on the first data to obtain standardized data.

[0053] Based on standardized data and real-time collected rotational speed, the first liquid production volume is calculated using the rotational speed method; based on the standardized data and real-time collected pump inlet pressure, the second liquid production volume is calculated using the IPR curve method; based on the standardized data and real-time collected rotational speed and submerged pressure, the third liquid production volume is calculated using the electrical energy method; and based on the standardized data, the fourth liquid production volume is calculated using the big data method.

[0054] The error rates between the first liquid production volume, the second liquid production volume, the third liquid production volume, and the fourth liquid production volume and the actual liquid production volume measured by the tank truck are calculated respectively. The liquid production volume corresponding to the minimum error rate is taken as the first determined liquid production volume, and the method corresponding to the first liquid production volume is taken as the first determining method.

[0055] A correction factor is calculated based on the first determined production volume and the actual production volume; the current production volume of the screw pump well is calculated using the first determination method, and the current corrected production volume is obtained by multiplying the production volume by the correction factor.

[0056] To more clearly explain the remote metering method for well production of screw pumps of the present invention, the following is in conjunction with... Figure 1 The steps in the embodiments of the present invention will be described in detail below.

[0057] The method for remote metering of fluid production in a screw pump well according to the first embodiment of the present invention is described in detail below:

[0058] Collect metering data from screw pump wells; perform outlier data removal and missing data interpolation on the metering data to obtain first data; and perform standardization on the first data to obtain standardized data.

[0059] In this embodiment, abnormal data removal includes: the density of useful data in oil fields is generally low; data errors or loss caused by malfunctions in data acquisition sensors; and manually entered data. Potential errors can affect data quality, necessitating data preprocessing. The goal of data preprocessing is to address potentially dirty data according to specific rules, ensuring it meets subsequent business needs. For erroneous data: This type of error arises from an inadequate business system that fails to properly validate input before writing it to the backend database. Examples include inputting numerical data as full-width numeric characters, incorrect date formats, or dates exceeding the data bounds. This type of data also needs to be categorized. Issues like full-width characters or invisible characters before or after data are identified using SQL statements, then extracted after correction in the business system. Errors such as incorrect date formats or dates exceeding the data bounds can cause data processing tools to fail. These errors need to be retrieved from the business system database using SQL. For example, sensor data values ​​often have a defined operating range; data exceeding this range is discarded. For duplicate data: This issue often occurs in dimension tables. All fields of duplicate data records are exported, confirmed, and then processed.

[0060] In this embodiment, the missing data interpolation process includes: for missing information, such as data omissions due to manual input or data loss caused by sensor malfunctions, filtering out this type of data, sorting and statistically analyzing it according to the missing content, and submitting it for supplementation. For example... Figure 2 This diagram illustrates the missing data interpolation process. First, Support Vector Regression (GA-SVR) is trained using other data from the variable containing the missing data as input to predict the values ​​of the missing data. Then, GA-SVR is used for multivariate prediction of the missing data; that is, GA-SVR is trained using data from variables related to the variable containing the missing data as input to predict the values ​​of the missing data. Finally, a dynamic weighted combination of the univariate and multivariate prediction results is established to obtain the missing data imputation result.

[0061] In this embodiment, data standardization includes: Standardization is a fundamental task in screw pump well data mining. Different evaluation indicators often have different dimensions and orders of magnitude. If directly input into the model for training, the error of each layer's output will increase, which will affect the model's diagnostic results. To ensure the reliability of the diagnostic results and eliminate the influence of dimensions between different data indicators, it is necessary to standardize the original screw pump production data. After standardization, each indicator has the same order of magnitude, making it suitable for comprehensive comparative analysis and evaluation. Commonly used data standardization methods include: min-max standardization, atan function transformation, log function transformation, Z-score standardization, etc. This invention utilizes min-max standardization to standardize the production data of mechanically operated wells.

[0062]

[0063] In the formula The parameter value is the standardized value of the data at point i; x i Let x be the measured parameter value at point i. min The minimum value among all parameter values; x max It is the maximum value among all parameter values.

[0064] Based on standardized data and real-time collected rotational speed data, the production volume is calculated using the rotational speed method to obtain the first production volume; based on the standardized data and real-time collected pump inlet pressure data, the production volume is calculated using the IPR curve method to obtain the second production volume; based on the standardized data and real-time collected rotational speed and submerged pressure data, the production volume is calculated using the electrical energy method to obtain the third production volume; based on the standardized data and real-time collected data, the production volume is calculated using the big data method to obtain the fourth production volume. This invention organically combines the four methods—rotational speed method, IPR curve method, electrical energy method, and big data method—to accurately and effectively measure the production volume of screw pump wells.

[0065] The rotational speed method is based on the proportional relationship between the pumping capacity of a screw pump and its theoretical capacity and volumetric efficiency. It is based on the fact that when the pump inlet pressure is lower than the crude oil saturation pressure, the free gas released from the crude oil occupies a certain space in the pump chamber of the screw pump, which reduces the volumetric efficiency of the liquid. By calculating the corresponding volumetric efficiency, the liquid production value at a specific rotational speed can be calculated.

[0066] In this embodiment, the method for calculating the first product volume using the rotation speed method includes:

[0067] The method for calculating the theoretical displacement and volumetric efficiency of the screw pump well based on the standardized data is as follows: Q th =1440*4eDTn*10 -9 ;

[0068] Methods for calculating the first product volume include:

[0069] Where n represents the historical operating speed of the screw pump, n1 represents the actual test speed of the screw pump, D represents the diameter of the rotor cross-section circle of the screw pump, T represents the stator lead of the screw pump, e represents the eccentricity of the pump, and Q th Q represents the theoretical displacement of the screw pump at a rotational speed n. re η represents the historical displacement of the screw pump at speed n. 容 This refers to the volumetric efficiency of the screw pump well.

[0070] The IPR curve, or inflow dynamic curve, describes the relationship between oil well production and bottom hole flowing pressure. This invention, assuming a functional model for the crude oil flow coefficient, establishes a novel, universally applicable oil well inflow dynamic curve equation, thereby enabling the measurement of fluid production in screw pump wells. The method for calculating the second fluid production using the IPR curve method includes:

[0071] First, calculate the bottom hole flowing pressure of the screw pump well based on the standardized data: P wf =P r +ρg(h z -h r );

[0072] Then, based on the standardized data, the average formation pressure and bottom hole flowing pressure are used to calculate the maximum production rate:

[0073] Finally, based on the standardized data, maximum production volume, and the collected pump inlet pressure, the second production volume is calculated:

[0074] Among them, P wf For the bottom hole flowing pressure, P r h is the pump inlet pressure. z For medium to deep oil reservoirs; h r For pump depth, P d Let ρ be the average formation pressure, ρ be the well fluid density, g be the acceleration due to gravity, and Q be the average formation pressure. text This is historical fluid production data for screw pump wells, Q. max Q1 is used to calculate the maximum liquid output of the screw pump, and Q2 is the second liquid output.

[0075] The electrical energy method assumes that, under similar operating conditions such as fluid supply and motor efficiency, the power consumption of a screw pump unit should be proportional to the volume of fluid it lifts. However, in actual field conditions and measurements, due to variations in rotational speed, fluid supply capacity, and their impact on pump efficiency, measurement results show no significant correlation between fluid volume and power consumption. This invention unitizes power consumption and fluid production, converting them into power consumption and fluid production per unit rotational speed and submerged pressure. The results show a strong positive correlation between the two. Figure 3 The figure shows a scatter plot of the relationship between liquid production and power consumption per unit rotational speed and submersion pressure. Methods for calculating the third liquid production rate using the electrical energy method include:

[0076] First, calculate the yield under unitized conditions:

[0077] Then calculate the power consumption under normalized conditions:

[0078] Then, the unitized liquid production rate and unitized power consumption are fitted to obtain the regression formula for the unitized liquid production rate: Q u =f(E u );

[0079] Finally, based on the regression formula for production volume and power consumption, real-time power consumption, rotation speed, and submersion pressure, the third production volume is calculated: Q3 = Q u *n1*P s1 =f(E u )*n1*P s1 ;

[0080] Among them, Q u E represents the unitized product yield. u Q represents the unitized power consumption. x E represents the liquid production rate. u Power consumption; n is the historical rotational speed; P s The pressure of historical setbacks; f(E) u E represents the functional relationship between unitized power consumption and unitized liquid production. u1 P represents the unitized power consumption collected in real time, where n1 is the rotational speed collected in real time; s1 Q3 represents the real-time submerged pressure, and Q3 represents the third production volume.

[0081] Methods for calculating the fourth production volume using big data methods include:

[0082] The parameters affecting the fluid production in the standardized data are used as influencing parameters; the Pearson correlation coefficient between each influencing parameter and the fluid production of the screw pump well is calculated, and the influencing parameters whose Pearson correlation coefficient is greater than the first threshold are used as feature parameters.

[0083] Each feature parameter is treated as a sample. There are n samples in total, and the p values ​​of each sample are treated as p variables.

[0084] The XGBoost model is obtained by training n samples, p variables corresponding to each sample, and the actual liquid production volume corresponding to each sample using the XGBoost intelligent algorithm.

[0085] The fourth production volume can be obtained by substituting the feature parameters into the XGBoost model.

[0086] like Figure 4The diagram illustrates the basic process for calculating screw pump well production using big data methods. Based on screw pump well static data, equipment static data, and historical operating data, Pearson correlation coefficient analysis was used to analyze the correlation between screw pump well attribute data and production. Principal component analysis (PCA) was used to reduce data dimensionality and determine the main control parameters. The relationship between the changing patterns of screw pump well production data and production was quantitatively studied. XGBoost was selected to establish a screw pump well production prediction model that widely applies time-series data learning and prediction. This method can fully consider the trend changes and time correlations of screw pump production dynamic data, further explore the changing patterns between dynamic data, and calculate the screw pump well fluid production in real time.

[0087] ① Feature parameter selection;

[0088] Many factors influence the production of screw pump wells, primarily those related to the reservoir and the lifting equipment. These include: static well data (reservoir rock properties, wellbore trajectory, etc.); dynamic production data (time, oil pressure, casing pressure, pump speed, pump inlet pressure, pump inlet temperature, water cut, well fluid viscosity, dynamic fluid level, etc.); and equipment operation data (production duration, current, voltage, active power, power factor, instantaneous power consumption, system efficiency, pump efficiency). To accurately understand the main characteristic parameters affecting the daily fluid production of the electric pump, this invention employs Pearson correlation coefficient analysis to analyze the correlation between variables and uses principal component analysis (PCA) to perform dimensionality reduction and production characteristic analysis on the data.

[0089] Pearson correlation coefficient: The Pearson correlation coefficient reflects the direction and degree of change between two variables. Its value ranges from -1 to +1, where 0 indicates no correlation, a positive value indicates a positive correlation, and a negative value indicates a negative correlation. A larger value indicates a stronger correlation. The formula for calculating the Pearson correlation coefficient of two n-dimensional vectors x and y is as follows:

[0090]

[0091] In the formula, and are the average values ​​of the elements in x and y, respectively. Clearly, the Pearson correlation coefficient r xy It is a real number in [-1, 1], when r xy When the value is greater than 0, the two variables are positively correlated; otherwise, they are negatively correlated. xy The larger the | value, the higher the correlation between x and y. After preprocessing and standardizing the production dynamics data of screw wells, the Pearson correlation coefficients between each pair of N attribute data were analyzed to assess the correlation between the attribute data.

[0092] Principal Component Analysis (PCA) is a statistical analysis method that reduces multiple variables into a few comprehensive indicators. From a mathematical perspective, it is a dimensionality reduction technique. Screw pump production forecasting is a complex system involving multiple factors. Using a large number of factors affecting production as model input parameters would undoubtedly increase the difficulty and complexity of the analysis. By utilizing the correlations between various factors affecting production, fewer dimensionality-reduced principal components can replace the original numerous influencing factors, and these principal components retain as much information as possible from the original factors, thus simplifying the problem.

[0093] The present invention uses n samples for principal component analysis, each sample has p variables, forming an n×p data matrix;

[0094] Let their combined indices after dimensionality reduction, i.e., principal components Z1 and Z2, be... Z3, ..., Z m ,but:

[0095] Z1 = l 11 x1+l 12 x2+…+l 1p x p ;

[0096] Z2=l 21 x1+l 22 x2+…+l 2p x p ;

[0097] Z3=l 31 x1+l 32 x2+…+l 3p x p ;

[0098] …

[0099] Z m =l m1 x1+l m2 x2+…+l mp x p ;

[0100] coefficient l ij The principles for determining:

[0101] 1)Z i With Z j (i≠j; i, j=1,2,…,m) are mutually uncorrelated;

[0102] 2) Z1 is x1, x2, ..., x n The linear combination with the largest variance, Z2, is x1, x2, ..., x2 that is uncorrelated with Z1.n The one with the largest variance among all linear combinations, Z m It is related to Z1, Z2, ..., Z m-1 The unrelated x1, x2, ..., x n The one with the largest variance among all linear combinations.

[0103] To quantitatively describe the relationship between screw pump well production and production parameters, principal component analysis (PCA) was used to calculate the weights of parameters such as output speed, pump inlet pressure, pump motor temperature, oil pressure, output voltage, output current, and daily power consumption. Based on the PCA feature selection method, the importance of each feature parameter to the daily fluid production of the screw pump well was analyzed, and the importance calculation results of each different feature were obtained.

[0104] ② Model evaluation;

[0105] To evaluate the generalization ability of the prediction model on the test set, i.e., the prediction performance of the screw pump well production prediction model, the main evaluation indicators used are: mean absolute percentage error (MAPE), mean absolute error (MAD), root mean square error (RMSE), Hill's inequality coefficient (TIC), and coefficient of determination (R²). The regression model evaluation indicators are shown in Table 1. Table 1

[0106] In the above table, y t The value represents the actual output of the t-th sample or at time t, in m³ / d; N represents the number of samples; y per d represents the predicted value of the prediction model at time i or at the i-th sample, m3 / d; This represents the average actual output, in m³ / d.

[0107] ③ Establishment of production planning model;

[0108] XGBoost is an improvement on the gradient boosting algorithm. It uses Newton's method to find the extremum of the loss function, expands the loss function to second-order Taylor expansion, and adds a regularization term to the loss function. The objective function during training consists of two parts: the gradient boosting loss and the regularization term. The loss function is defined as follows:

[0109] Where: n is the number of training function samples; l is the loss for a single sample, assumed to be a convex function; y i ′ represents the model's prediction of the training samples; y i These are the true label values ​​of the training samples.

[0110] The regularization term defines the degree of responsibility of the model, as described below:

[0111]

[0112] Where: γ and λ are manually set parameters, ω is a large vector formed by the values ​​of all leaf nodes in the decision tree; T k This represents the number of leaf nodes.

[0113] The process of screw pump well production prediction and early warning based on big data is as follows: combining data mining technology with professional knowledge, identifying the main control parameters for screw pump well production prediction, using the normalized main control parameters affecting production as input variables, applying the XGBoost intelligent algorithm to establish a production prediction deep learning model, using a large amount of sample data to train the established model and optimize the model parameters, and realizing production prediction and early warning based on the trained model.

[0114] The first, second, third, and fourth production volumes of each single well are calculated separately and compared with the actual production volume measured by the tanker truck to calculate the error rate. The production volume corresponding to the minimum error rate of each single well is taken as the first determined production volume of that well, and the method corresponding to the first production volume is taken as the first determined method of that well. The screw pump well production is measured using the principle of "one method per well".

[0115] A correction factor is calculated based on the first determined production volume and the actual production volume; the current production volume of the screw pump well is calculated using the first determination method, and the current corrected production volume is obtained by multiplying the production volume by the correction factor.

[0116] Methods for calculating correction factors include:

[0117] Where K is the correction coefficient, q g q represents the yield of liquid obtained using the first determining method. y This represents the actual liquid production. Q = K * q g ;

[0118] Q represents the current corrected product yield; K represents the correction factor; q g The amount of liquid produced using the first determination method.

[0119] Although the steps in the above embodiments are described in the above order, those skilled in the art will understand that in order to achieve the effect of this embodiment, different steps do not need to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple variations are all within the protection scope of this invention.

[0120] The second embodiment of the screw pump well production remote metering method of the present invention includes a system comprising:

[0121] The data acquisition module is used to collect dynamic and static data and historical metering data of the screw pump well; abnormal data removal and missing data interpolation processing are performed on the collected dynamic and static data and historical metering data of the screw pump well to obtain first data; and the first data is standardized to obtain standardized data.

[0122] The liquid production calculation module is used to calculate the liquid production based on the standardized data and real-time acquired data. The first liquid production is obtained by calculating the liquid production using the rotation speed method; the second liquid production is obtained by calculating the liquid production using the IPR curve method; the third liquid production is obtained by calculating the liquid production using the electrical energy method; and the fourth liquid production is obtained by calculating the liquid production using the big data method.

[0123] The method determination module is used to calculate the error rate between the first production volume, the second production volume, the third production volume and the fourth production volume of each single well and the actual production volume measured by the tank truck. The production volume corresponding to the minimum error rate is taken as the first determined production volume, and the method corresponding to the first production volume is taken as the first determined method.

[0124] The corrected production volume calculation module is used to calculate a correction coefficient based on the first determined production volume and the actual production volume; calculate the current production volume of the screw pump well using the first determination method; and multiply the production volume by the correction coefficient to obtain the current corrected production volume.

[0125] like Figure 5 As shown, the remote metering system for production volume of screw pump wells of the present invention relies on a digital twin architecture that integrates mechanism simulation and real-time data-driven processes. It applies technologies such as artificial lift theory, cloud and edge computing, artificial intelligence, and the Internet of Things. It has functions such as data acquisition, production volume metering, and production volume verification. It can comprehensively perceive the operation of screw pump lift wells, improve the production of screw pump wells, and provide strong data support for reservoir analysis and decision-making.

[0126] The remote metering system for screw pump well production encapsulates the business layer and MVC framework layer using a service-oriented interface approach. It utilizes WCF and WebService technologies for data retrieval and push, employing C# for backend service programs, Python for intelligent algorithms of various models, Vue for frontend pages, Echarts for report curves, and Oracle for data storage. This forms a digital, automated, collaborative, and intelligent management platform. Furthermore, the system adopts a modular design, allowing users to configure it according to their actual needs. It is flexible, adaptable, and highly scalable, enabling both precise management of a single well throughout its entire lifecycle and macro-level control and optimization of process solutions for entire blocks, further improving the intelligent management level of screw pump wells.

[0127] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the system described above can be found in the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0128] It should be noted that the remote metering system for producing fluid in screw pump wells provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be further decomposed or combined. For example, the modules in the above embodiments can be merged into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the various modules or steps and are not considered as an improper limitation of the present invention.

[0129] An electronic device according to a third embodiment of the present invention includes:

[0130] At least one processor; and

[0131] A memory communicatively connected to at least one of the processors; wherein,

[0132] The memory stores instructions that can be executed by the processor to implement the above-described remote metering method for producing fluid in screw pump wells.

[0133] A computer-readable storage medium according to a fourth embodiment of the present invention stores computer instructions, which are executed by the computer to implement the above-described remote metering method for producing fluid in screw pump wells.

[0134] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the electronic devices and storage media described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0135] Those skilled in the art will recognize that the modules and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. The programs corresponding to the software modules and method steps can be placed in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the art. To clearly illustrate the interchangeability of electronic hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the invention.

[0136] The following is for reference. Figure 6 It shows a schematic diagram of the structure of a computer system for implementing the methods, systems, and devices of this application. Figure 6 The server shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0137] like Figure 6 As shown, the computer system includes a Central Processing Unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in Read Only Memory (ROM) 602 or programs loaded from storage section 608 into Random Access Memory (RAM) 603. The RAM 603 also stores various programs and data required for system operation. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An Input / Output (I / O) interface 605 is also connected to the bus 604.

[0138] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0139] Specifically, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs the functions defined in the methods of this application. It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0140] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0141] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions 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 using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0142] The terms “first”, “second”, etc., are used to distinguish similar objects, not to describe or indicate a specific order or sequence.

[0143] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent in such process, method, article, or apparatus / device.

[0144] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for remote metering of fluid production in a screw pump well, characterized in that, The method includes: Collect metering data from screw pump wells; perform outlier data removal and missing data interpolation on the metering data to obtain first data; and perform standardization on the first data to obtain standardized data. Based on standardized data and real-time collected rotational speed, the first liquid production volume is calculated using the rotational speed method; based on the standardized data and real-time collected pump inlet pressure, the second liquid production volume is calculated using the IPR curve method; based on the standardized data and real-time collected rotational speed and submerged pressure, the third liquid production volume is calculated using the electrical energy method; and based on the standardized data, the fourth liquid production volume is calculated using the big data method. The error rates between the first liquid production volume, the second liquid production volume, the third liquid production volume, and the fourth liquid production volume and the actual liquid production volume measured by the tank truck are calculated respectively. The liquid production volume corresponding to the minimum error rate is taken as the first determined liquid production volume, and the method corresponding to the first liquid production volume is taken as the first determining method. A correction factor is calculated based on the first determined production volume and the actual production volume; the current production volume of the screw pump well is calculated using the first determination method, and the current corrected production volume is obtained by multiplying the production volume by the correction factor.

2. The remote metering method for producing fluid in a screw pump well according to claim 1, characterized in that, Methods for calculating the first product volume using the rotation speed method include: First, calculate the theoretical displacement of the screw pump well based on the standardized data: Q th =1440*4eDTn*10 -9 ; Then, the volumetric efficiency of the screw pump well is calculated based on its theoretical displacement: Then, based on the volumetric efficiency and theoretical displacement of the screw pump well, the first production rate is calculated: Where n represents the historical operating speed of the screw pump, n1 represents the actual test speed of the screw pump, D represents the diameter of the rotor cross-section circle of the screw pump, T represents the stator lead of the screw pump, e represents the eccentricity of the pump, c represents a constant, and Q th Q represents the theoretical displacement of the screw pump at a rotational speed n. re η represents the historical displacement of the screw pump at speed n. 容 This refers to the volumetric efficiency of the screw pump well.

3. The remote metering method for producing fluid in a screw pump well according to claim 1, characterized in that, Methods for calculating the second production volume using the IPR curve method include: First, calculate the bottom hole flowing pressure based on the standardized data; P wf =P r +ρg(h x -h r ); Then, the maximum fluid production rate is calculated based on the bottom hole flowing pressure: Finally, the second production volume is calculated based on the maximum production volume and the collected pump inlet pressure: Among them, P wf For the bottom hole flowing pressure, P r h is the pump suction inlet pressure. z For medium to deep oil reservoirs; h r For pump depth, P d Let ρ be the average formation pressure, ρ be the well fluid density, g be the acceleration due to gravity, and Q be the average formation pressure. text Q represents the historical fluid production of screw pump wells. max Q1 is used to calculate the maximum liquid output of the screw pump, and Q2 is the second liquid output.

4. The remote metering method for producing fluid in a screw pump well according to claim 1, characterized in that, Methods for calculating the third production volume using electrical energy methods include: Calculate the unitized liquid yield based on the standardized data: Then, based on the standardized data, the unitized power consumption is calculated: Then, the unitized liquid production rate and unitized power consumption were fitted to obtain the regression formula for unitized liquid production rate and power consumption: Q u =f(E u ); Finally, based on the regression formula for production volume and power consumption, real-time power consumption, rotation speed, and submersion pressure, the third production volume is calculated: Q3=Q u *n1*P s1 =f(E u1 )*n1*P s1 ; Among them, Q u E represents the unitized product yield. u Q represents the unitized power consumption. x E represents the liquid production rate. u Power consumption; n is the historical rotational speed; P s The pressure of historical setbacks; f(E) u E represents the functional relationship between unitized power consumption and unitized liquid production. u1 P represents the unitized power consumption collected in real time, where n1 is the rotational speed collected in real time. s1 Q3 represents the real-time submerged pressure, and Q3 represents the third production volume.

5. The remote metering method for producing fluid in a screw pump well according to claim 1, characterized in that, Methods for calculating the fourth production volume using big data methods include: The parameters affecting the production volume in the standardized data are used as influencing parameters; the Pearson correlation coefficient between each influencing parameter and the production volume of the screw pump well is calculated, and the influencing parameters whose Pearson correlation coefficient is greater than the first threshold are used as characteristic parameters. Each feature parameter is treated as a sample. There are n samples in total, and the p values ​​of each sample are treated as p variables. The XGBoost model is obtained by training n samples, p variables corresponding to each sample, and the actual liquid production volume corresponding to each sample using the XGBoost intelligent algorithm. The fourth production volume can be obtained by substituting the feature parameters into the XGBoost model.

6. A method for remote metering of fluid production in a screw pump well, characterized in that, The system includes: The data acquisition module is used to acquire metering data from screw pump wells; the metering data is processed by removing abnormal data and interpolating missing data to obtain first data, and the first data is processed by standardization to obtain standardized data; The liquid production calculation module is used to calculate the liquid production volume using the rotational speed method based on standardized data and real-time collected rotational speed data to obtain a first liquid production volume; to calculate the liquid production volume using the IPR curve method based on the standardized data and real-time collected pump inlet pressure data to obtain a second liquid production volume; to calculate the liquid production volume using the electrical energy method based on the standardized data and real-time collected rotational speed and submerged pressure data to obtain a third liquid production volume; and to calculate the liquid production volume using the big data method based on the standardized data and real-time collected data to obtain a fourth liquid production volume. The method determination module is used to calculate the error rate between the first liquid production volume, the second liquid production volume, the third liquid production volume and the fourth liquid production volume and the actual liquid production volume measured by the tank truck, respectively. The liquid production volume corresponding to the minimum error rate is used as the first determined liquid production volume, and the method corresponding to the first liquid production volume is used as the first determined method. The corrected production volume calculation module is used to calculate a correction coefficient based on the first determined production volume and the actual production volume; calculate the current production volume of the screw pump well using the first determination method; and multiply the production volume by the correction coefficient to obtain the current corrected production volume.

Images