Method and device for predicting monthly yield of oil gas, electronic equipment and medium

Abstract

The embodiment of the invention discloses a method and a device for predicting monthly yield of oil and gas, electronic equipment and a medium. The method comprises the following steps: acquiring historical oil and gas monthly data generated by a target oil and gas area in a historical year, and determining historical monthly yield load factors corresponding to each month in the historical year based on the historical oil and gas monthly data; inputting each historical monthly yield load factor into a load factor prediction model to obtain a target monthly yield load factor corresponding to each month in a current year, the current year being associated with a historical year; and on the basis of each target monthly yield load factor and the average daily oil production corresponding to the current year, predicting the target monthly oil production corresponding to each month in the current year of the target oil and gas area. According to the technical scheme of the embodiment of the invention, the problems that the monthly oil and gas yield cannot be predicted and the prediction precision is low in a current oil and gas prediction mode are solved, the monthly oil and gas yield is predicted, and the prediction effect and the prediction precision are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas field development technology, and in particular to a method, device, electronic equipment and medium for predicting monthly oil and gas production. Background Art

[0002] Since 2000, the Petroleum Exploration and Development Research Institute has strengthened the research on upstream oil and gas production rules. In terms of annual and medium- and long-term production forecasts, it has formed two-year production composition methods, three-year production composition methods, and five-year production composition methods based on the classification forecasts of new and old areas and new and old wells, as well as the reserve-production ratio control forecast method based on the forecast of newly added recoverable reserves, and constructed a bottom-up (from oil and gas fields-production enterprises-basins) medium- and long-term oil and gas supply forecast model. In terms of monthly production forecasts, it has formed forecast models and methods such as the model forecast method of oil and gas fields and the Arps decline curve method.

[0003] However, there is no mature method to refer to for the monthly production arrangement of a regional oilfield company. In addition, affected by the downstream market, the monthly oil and gas production changes are not regular and cannot be predicted by the Arps decline curve. Therefore, it is urgent to develop a new monthly production forecasting model to forecast the monthly oil and gas production of regional companies (or oil and gas fields). Summary of the invention

[0004] The present invention provides a method, device, electronic equipment and medium for predicting monthly oil and gas production, so as to realize the prediction of monthly oil and gas production and greatly improve the prediction effect and prediction accuracy.

[0005] According to one aspect of the present invention, a method for predicting monthly oil and gas production is provided, comprising:

[0006] Acquire historical monthly oil and gas data generated by the target oil and gas region in the historical year, and determine the historical monthly production load factor corresponding to each month in the historical year based on the historical monthly oil and gas data;

[0007] Inputting each of the historical monthly production load factors into a load factor prediction model to obtain a target monthly production load factor corresponding to each month in a current year, wherein the current year is associated with the historical years;

[0008] Based on each of the target monthly production load factors and the average daily oil production corresponding to the current year, the target monthly oil production corresponding to each month in the current year of the target oil and gas region is predicted.

[0009] According to another aspect of the present invention, there is provided a device for predicting monthly oil and gas production, comprising:

[0010] A historical load factor determination module is used to obtain historical oil and gas monthly data generated in the target oil and gas area in the historical year, and determine the historical monthly production load factor corresponding to each month in the historical year based on the historical oil and gas monthly data;

[0011] A target load factor prediction module, for inputting each of the historical monthly production load factors into a load factor prediction model to obtain a target monthly production load factor corresponding to each month in a current year, wherein the current year is associated with the historical years;

[0012] The monthly oil production determination module is used to predict the target monthly oil production corresponding to each month in the current year of the target oil and gas region based on each target monthly production load factor and the average daily oil production corresponding to the current year.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting monthly oil and gas production described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting monthly oil and gas production as described in any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention obtains the historical monthly oil and gas data generated by the target oil and gas area in the historical year, and determines the historical monthly production load factors corresponding to each month in the historical year based on the historical oil and gas monthly data; inputs each historical monthly production load factor into the load factor prediction model to obtain the target monthly production load factor corresponding to each month in the current year, and the current year is associated with the historical year; based on each target monthly production load factor and the average daily oil production corresponding to the current year, the target monthly oil production corresponding to each month in the current year is predicted. The technical solution of the embodiment of the present invention solves the problem that the current oil and gas prediction method cannot predict the monthly oil and gas production and the prediction accuracy is low, and realizes the prediction of the monthly oil and gas production, greatly improving the prediction effect and prediction accuracy.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A flowchart of a method for predicting monthly oil and gas production provided in Example 1 of the present invention;

[0022] Figure 2 A flowchart of a method for predicting monthly oil and gas production provided in Example 2 of the present invention;

[0023] Figure 3 A comparison chart of predicted monthly production load factors provided in Example 2 of the present invention;

[0024] Figure 4 A schematic diagram of the structure of a device for predicting monthly oil and gas production provided in Embodiment 3 of the present invention;

[0025] Figure 5 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Embodiment 1

[0029] Figure 1 This is a flowchart of a method for predicting monthly oil and gas production provided by the first embodiment of the present invention. This embodiment can be applied to predicting the monthly oil production of an oil field in a future period of time. The method can be executed by a prediction device for monthly oil and gas production. The device can be implemented in the form of hardware and / or software. The prediction device for monthly oil and gas production can be configured in an electronic device. Figure 1 As shown, the method includes:

[0030] S110, obtaining historical monthly oil and gas data generated in the target oil and gas region in the historical year, and determining the historical monthly production load factor corresponding to each month in the historical year based on the historical monthly oil and gas data.

[0031] Among them, the target oil and gas area can be an oil region or an oil field. If the monthly oil production of an oil field is to be predicted within a certain period of time in the future, the oil field can be used as the target oil and gas area; the historical year refers to each year in the past, for example, the historical year is the past 5 or 10 years; the historical monthly data refers to some data related to oil and gas production in the oil and gas area in each month within the historical year. For example, the historical oil and gas monthly data can be the monthly oil and gas production value; the historical monthly load factor can be understood as the value calculated based on the historical oil and gas monthly data.

[0032] Specifically, the production data related to the production of the target oil and gas region in the historical year can be found from the log data related to the exploitation of the target oil and gas region, and the data corresponding to each month can be used as the historical oil and gas monthly data. Furthermore, the historical oil and gas monthly data can be processed to obtain the historical monthly production load factors corresponding to each month.

[0033] In an embodiment of the present invention, the acquisition of historical oil and gas monthly data generated by the target oil and gas area in the historical years includes: obtaining the average daily oil production of new wells, the average daily oil production of old wells and the average daily increased oil production corresponding to each month in the target oil and gas area in the historical years.

[0034] Among them, the average daily oil production of new wells refers to the average daily oil production of newly established oil drilling wells in a month; old wells refer to the average daily oil production of previously built oil drilling wells in a month; and the average daily increased oil production refers to the average daily increase in oil production in a month.

[0035] For example, the historical monthly data generated by the target oil and gas area in 2015 can be the average daily oil production of newly drilled wells in January, the average daily oil production of old wells in January, and the average daily increased oil production in January in 2015, and the average daily oil production of new wells, the average daily oil production of old wells, and the average daily increased oil production corresponding to each month from February to December can be obtained in this way.

[0036] In an embodiment of the present invention, the historical monthly production load factors corresponding to each month in the historical year are determined based on the historical monthly oil and gas data, including: calculating the monthly average daily oil production corresponding to each month based on the average daily oil production of new wells, the average daily oil production of old wells and the average daily increased oil production; for any year to be calculated in the historical years, calculating the annual average daily oil production of the target area in the year to be calculated based on the monthly average daily oil production corresponding to each month and the number of days in each month; determining the historical monthly production load factors corresponding to each month in the year to be calculated based on the ratio of the monthly average daily oil production corresponding to each month to the annual average daily oil production in the year to be calculated.

[0037] Among them, the monthly average daily oil production refers to the sum of the average daily oil production of different types of drilling wells within a month; the annual average daily oil production refers to the average daily oil production in a certain year.

[0038] It can be understood that after obtaining the average daily oil production of new wells, the average daily oil production of old wells and the average daily increase in oil production in a certain month, the three can be added together to obtain the monthly average daily oil production of the corresponding month. Further, for each year to be calculated in the historical year, the number of days in each month of the year can be multiplied by the corresponding monthly average daily oil production, and then the sum can be obtained to obtain the annual total oil production corresponding to the year to be calculated. The annual total oil production is further divided by the total number of days in the year to obtain the annual average daily oil production, where the total number of days in the year can be 365 days or 366 days. Finally, the ratio of the monthly average daily oil production of each month in the year to be calculated to the annual average daily oil production is used as the historical monthly production load factor of each month. According to the above method, the historical monthly production load factor corresponding to each month in each historical year can be calculated. For example, each historical year corresponds to 12 historical monthly production load factors.

[0039] S120. Input each of the historical monthly production load factors into a load factor prediction model to obtain a target monthly production load factor corresponding to each month in a current year, wherein the current year is associated with the historical years.

[0040] Among them, the load factor prediction model can be a machine learning model, which is used to predict the monthly production load factor corresponding to the current year. The current year refers to the year associated with the historical year, and the historical year refers to 2010 to 2020. Correspondingly, the current year can be 21, and the target monthly production load factor can be understood as the monthly production load factor corresponding to each month of 21.

[0041] In this embodiment, if the target monthly production load factor for the current year is to be predicted, the historical monthly production load factors in the historical years corresponding to the current year can be input into the load factor prediction model to obtain the load factor prediction model's prediction results for the monthly production load factors of each month in the current year, that is, the target monthly production load factor.

[0042] On the basis of the above technical solution, each of the historical monthly production load factors is input into the load factor prediction model to obtain the target monthly production load factor corresponding to each month in the current year, including: inputting each of the historical monthly production load factor data into the load factor prediction model to obtain the output value of the load factor prediction model; determining the output value as the target monthly production load factor corresponding to each month in the current year.

[0043] Specifically, the monthly production load factor can be used as an input value and input into the load factor prediction factor to obtain the output value of the load factor prediction model, and the output value of the model is used as the target monthly production load factor corresponding to each month in the current year. For example, the target monthly production load factor corresponding to each month can be the target monthly production load factor corresponding to each month from January to December of the current year.

[0044] In an embodiment of the present invention, the load factor prediction model is trained in the following manner: based on the historical monthly production load factors corresponding to each month in the historical year and the time information corresponding to the historical monthly production load factors, load factor time series data is generated; the load factor time series data is divided into a training set and a validation set according to a preset ratio, and each prediction model to be trained is trained based on the training set to obtain each initial prediction model; each initial prediction model is verified based on the validation set to obtain the error corresponding to each initial prediction model, and the load factor prediction model is determined based on the error.

[0045] Among them, time information refers to the month information and year information corresponding to each historical monthly production load factor, and each month in each year has a corresponding historical monthly load factor. For example, the time information corresponding to the historical monthly production load factor is May of 2013, that is, the historical monthly production load factor is the historical monthly production load factor of May of 2013; the load factor time series data refers to the time series data obtained after arranging the historical monthly production load factors according to the time information; the prediction model to be trained includes: at least two of the seasonal difference autoregressive sliding average model, the difference integrated moving average autoregressive model, the gray system theory model and the average value model. The initial training model refers to the model obtained after training the prediction model to be trained and correcting the parameters.

[0046] In practical applications, the load factor prediction model is a model obtained by training the historical monthly production load factor. It is understandable that some prediction models to be trained can be selected first, such as the seasonal difference autoregressive sliding average model, the difference integrated moving average autoregressive model, the grey system theory model and at least two of the average value model. After obtaining the historical monthly production load factor and the corresponding time information, the corresponding load factor time series data can be generated. The load factor time series data is divided into a training set and a validation set according to a preset ratio. The training set is used to train the prediction model to be trained to obtain the corresponding initial prediction model; each initial prediction model is then verified by the validation set to obtain the error of each initial prediction model, and the load factor prediction model is selected from each initial prediction model based on the error.

[0047] On the basis of the above technical solution, each of the initial prediction models is verified based on the verification set to obtain errors corresponding to each of the initial prediction models, and the load factor prediction model is determined based on the errors, including: determining the errors corresponding to each of the initial models, and determining the initial prediction model corresponding to the smallest error as the load factor prediction model.

[0048] The error includes at least one of error variance, mean square error, root mean square error, mean absolute error, maximum absolute error, minimum absolute error, mean relative error, maximum relative error and minimum relative error.

[0049] Specifically, the errors of each initial prediction model can be calculated, and the errors include: at least one of error variance, mean square error, root mean square error, mean absolute error, maximum absolute error, minimum absolute error, average relative error, maximum relative error and minimum relative error; based on the comparison results of various errors, the initial prediction model with smaller error is used as the load factor prediction model.

[0050] S130. Based on each of the target monthly production load factors and the average daily oil production corresponding to the current year, predict the target monthly oil production corresponding to each month in the current year in the target oil and gas region.

[0051] Among them, the average daily oil production corresponding to the current year refers to the average daily oil production planned for each day of the current year, and the target monthly oil production refers to the predicted oil production in each month of the current year.

[0052] Specifically, based on each of the target monthly production load factors and the average daily oil production corresponding to the current year, the target monthly oil production corresponding to each month in the current year of the target oil and gas region is predicted.

[0053] In an embodiment of the present invention, the target monthly oil production corresponding to each month in the current year of the target oil and gas region is predicted based on each target monthly production load factor and the average daily oil production corresponding to the current year, including:

[0054] Based on the planned total oil production of the target oil and gas area in the current year and the number of days in the current year, the average daily oil production corresponding to the current year is calculated; based on the average daily oil production and the target monthly production load factor corresponding to each month, the target monthly oil production corresponding to each month in the current year of the target oil and gas area is calculated.

[0055] It can be understood that the planned total oil production of the target oil and gas area in the current year is divided by the number of days in the current year to obtain the average daily oil production of the current year, and the average daily oil production of the current year is multiplied by the target monthly production load factor of each month to obtain the target monthly oil production of each month.

[0056] The technical solution of the embodiment of the present invention obtains the historical monthly oil and gas data generated by the target oil and gas area in the historical year, and determines the historical monthly production load factors corresponding to each month in the historical year based on the historical oil and gas monthly data; inputs each historical monthly production load factor into the load factor prediction model to obtain the target monthly production load factor corresponding to each month in the current year, and the current year is associated with the historical year; based on each target monthly production load factor and the average daily oil production corresponding to the current year, the target monthly oil production corresponding to each month in the current year is predicted. The technical solution of the embodiment of the present invention solves the problem that the current oil and gas prediction method cannot predict the monthly oil and gas production and the prediction accuracy is low, and realizes the prediction of the monthly oil and gas production, greatly improving the prediction effect and prediction accuracy.

[0057] Embodiment 2

[0058] Figure 2 This is a flowchart of a method for predicting monthly oil and gas production provided by Embodiment 2 of the present invention. This embodiment is a preferred embodiment of the above embodiment. Figure 2 As shown, the method includes:

[0059] Extract the historical monthly production data based on the oil field, including the production of old wells without measures, the production of measures and the production of new wells, calculate the monthly load factor, and obtain the time series data sequence; then divide the time series data sequence into a training set and a validation set, and train the old well production and total production on the training set based on the grey GM model, ARIMA model and S-ARIMA model respectively; finally, combine various machine learning algorithms and average value algorithms, calculate the error variance EV, mean square error MSE, root mean square error RMSE, mean absolute error MAE, maximum absolute error MAXMAE, minimum absolute error MINMAE, average relative error ARE, maximum relative error MAXARE, minimum relative error MINARE and other statistical indicators on the validation set, check the difference between the model prediction result and the true value, to measure whether the model prediction effect meets the expectations, and form a monthly production load factor prediction model based on the model evaluation results to further improve the accuracy of monthly production prediction, which includes the following steps:

[0060] S210. Extract the historical monthly production data based on the oil region as the basic unit.

[0061] This example extracts the monthly average daily production data of an oil field from January 2011 to December 2020: including the average daily oil production of new wells (tons / day), the average daily oil production of old wells (tons / day), and the average daily incremental oil production (tons / day); calculates the total average daily oil production (tons / day). The calculation formula is as follows:

[0062] Q da总 =Q da新 +Q da老 +Q da增

[0063] Where: Q da总 is the total average daily oil production, in t / d; Q da新 is the average daily oil production of new wells, in t / d; Q da老 is the average daily oil production of old wells, in t / d; Q da增 It is the average daily oil production increase, in t / d.

[0064] Multiply the calculated amounts in the above formula by the number of days in the month to get the monthly oil production of new wells (tons), monthly oil production of old wells (tons), monthly increased oil production (tons), and total monthly oil production (tons).

[0065] Q m总 =Q m新 +Q m老 +Q m增 =(Q da新 +Q da老 +Q da增 )*n

[0066] Where: Q m总 is the total monthly oil production, in t; Q m新 is the monthly oil production of the new well, in t; Q m老 is the monthly oil production of the old well, in t / d; Q m增 is the monthly oil production increase, in t; n is the number of days in the month, in d.

[0067] The annual production is obtained by summing up the monthly production data of the 12 months of the year: total annual production (tons), annual production of pure old wells (tons)

[0068] Q y总 =Q m1总 +Q m2总 +Q ma总 +...+Q m12总

[0069] Q y老 =Q m1老 +Q m2老 +Q m3老 +...+Q m12老

[0070] The annual production is divided by the number of days in the year to get the annual average daily production: total annual average daily production (tons / day), annual average daily production of pure old wells (tons / day)

[0071] Q ya总 =Q y总 / n

[0072] Q ya老 =Q y老 / n

[0073] Q y总 is the total annual average daily output (tons / day), Q y总 is the average annual daily output of pure old wells (tons / day), and n is the number of days in that year (take 365 or 366), as follows. Table 1 is the historical monthly production data of an oil field from 2011 to 2020, and Table 1 is the historical annual production data of an oil field from 2011 to 2020.

[0074] Table 1

[0075]

[0076]

[0077]

[0078]

[0079]

[0080]

[0081] Table 2

[0082]

[0083] S220. Calculate the monthly load factor to obtain a time series data sequence.

[0084] The monthly average daily production is divided by the annual average daily production to obtain the monthly production load factor: the monthly production load factor of pure old wells and the monthly production load factor of total production. The calculation formula is as follows:

[0085] R m总 =Q ma总 / Q ya总

[0086] R m老 =Q ma老 / Q ya老

[0087] In the above formula, Rm is the capacity load factor of a certain month, which is dimensionless, Qma is the average daily output of that month, in t / d, and Qya is the average daily output of the year, in t / d.

[0088] Based on the calculation results of the above formula, two groups of monthly production load factor time series data sequences of pure old wells and total production from 2011 to 2020 were obtained, with 120 data points in each group. Table 3 shows the monthly production load factors of old wells in an oil field from 2011 to 2020; Table 4 shows the monthly production load factors of total wells in an oil field from 2011 to 2020. Table 3

[0089]

[0090] Table 4

[0091]

[0092]

[0093] S230, dividing the time series data sequence into a training set and a validation set, and using a machine learning algorithm to train the old well production and the total production respectively.

[0094] The monthly production load factor time series data sequence obtained in S220 is used as the original data sequence of the training set. The same data processing method is used to obtain the monthly production load factor time series data sequence from January to December 2021. Each group of 12 data points is used as the validation set data sequence. The data sets are trained using the gray GM model, ARIMA model, and S-ARIMA model respectively. At the same time, the average method is used to directly obtain the predicted monthly production load factor for 2021.

[0095] Specifically, when using the GM gray model, ARIMA model, and average algorithm, the monthly production load factor (10 data points) of a certain month from 2011 to 2020 is taken to form a time series data to predict the monthly production load factor of that month in 2021; when using the S-ARIMA model, the monthly production load factor (120 data points) from 2011 to 2020 is taken to form a time series data to predict the monthly production load factor of 12 months in 2021. Among them, Table 5 is the monthly production load factor of old wells in an oil field in 2021, and Table 6 is the monthly production load factor of the total production of an oil field in 2021.

[0096] Table 5

[0097]

[0098] Table 6

[0099]

[0100]

[0101] In addition, the model training and parameter correction process is introduced: Taking the ARIMA model as an example, for the three parameters p, d, and q in the ARIMA model, each parameter has a different value range. The values ​​of the three parameters are determined by training the model. The specific steps are as follows:

[0102] ① Check whether the sequence is stationary. Use the ADF or PP method to perform a unit root test on the original sequence to see if it is stationary. If it is not stationary, the sequence needs to be adjusted to a stationary sequence through differential operations, that is, to estimate the d value in ARIMA (p, d, q) and build an ARIMA model.

[0103] ②Use AC and PAC coefficients to determine the lag order of the model. According to the possible form of the model and the AIC criterion, select the best lag order, that is, estimate the p and q values ​​in ARIMA (p, d, q) to form the best model.

[0104] ③ Parameter estimation and diagnostic test. Test the model parameters to see if they are significant, their own validity, and whether they are white noise sequences. If the model fails the test, the model needs to be modified until it passes the test.

[0105] S240, compare the machine learning algorithm and the average algorithm, and evaluate the model prediction results;

[0106] The model is directly used to calculate the error variance EV, mean square error MSE, root mean square error RMSE, mean absolute error MAE, maximum absolute error MAXMAE, minimum absolute error MINMAE, average relative error ARE, maximum relative error MAXARE, minimum relative error MINARE and other statistical indicators on the validation set, and the difference between the model prediction results and the true value is checked to measure whether the model prediction effect meets expectations. Among them, Table 7 shows the evaluation results of various prediction models for the monthly production load factor of the old well production of an oil field. Table 8 shows the evaluation results of various prediction models for the monthly production load factor of the total production of an oil field.

[0107] Table 7

[0108]

[0109] Table 8

[0110]

[0111] S250. Based on the above prediction results, a monthly oil and gas production prediction model is established using the predicted monthly production load factor.

[0112] Select one or more of the four algorithm models with the best evaluation indicators, multiply the predicted monthly production load factor by the annual average daily oil production of the predicted year and the number of days in the corresponding month, and get the predicted monthly production of the predicted year. The formula is as follows:

[0113] Q m总 =R m总 *Q ya总 *n

[0114] Q m老 =R m老 *Q ya老 *n

[0115] Where Q m is the monthly oil production, in t, R m is the monthly production load factor, dimensionless, Qya is the average daily production of the year, and n is the number of days in the month. The predicted monthly production results of an oil field in 2021 are shown in the following table: Among them, Table 9 is the monthly production forecast results of old wells in an oil field. Table 10 is the monthly production forecast results of the total production of an oil field. Figure 3 This is a comparison chart of predicted monthly production load factors.

[0116] Table 9

[0117]

[0118] Table 10

[0119]

[0120] The technical solution of the embodiment of the present invention obtains the historical monthly oil and gas data generated by the target oil and gas area in the historical year, and determines the historical monthly production load factors corresponding to each month in the historical year based on the historical oil and gas monthly data; inputs each historical monthly production load factor into the load factor prediction model to obtain the target monthly production load factor corresponding to each month in the current year, and the current year is associated with the historical year; based on each target monthly production load factor and the average daily oil production corresponding to the current year, the target monthly oil production corresponding to each month in the current year is predicted. The technical solution of the embodiment of the present invention solves the problem that the current oil and gas prediction method cannot predict the monthly oil and gas production and the prediction accuracy is low, and realizes the prediction of the monthly oil and gas production, greatly improving the prediction effect and prediction accuracy.

[0121] Embodiment 3

[0122] Figure 4 This is a schematic diagram of the structure of a prediction device for monthly oil and gas production provided by Embodiment 3 of the present invention. Figure 4 As shown, the device comprises:

[0123] The historical load factor determination module 310 is used to obtain the historical oil and gas monthly data generated by the target oil and gas region in the historical year, and determine the historical monthly production load factor corresponding to each month in the historical year based on the historical oil and gas monthly data;

[0124] A target load factor prediction module 320 is used to input each of the historical monthly production load factors into a load factor prediction model to obtain a target monthly production load factor corresponding to each month in a current year, wherein the current year is associated with the historical year;

[0125] The monthly oil production determination module 330 is used to predict the target monthly oil production corresponding to each month in the current year of the target oil and gas region based on each target monthly production load factor and the average daily oil production corresponding to the current year.

[0126] The technical solution of the embodiment of the present invention obtains the historical monthly oil and gas data generated by the target oil and gas area in the historical year, and determines the historical monthly production load factors corresponding to each month in the historical year based on the historical oil and gas monthly data; inputs each historical monthly production load factor into the load factor prediction model to obtain the target monthly production load factor corresponding to each month in the current year, and the current year is associated with the historical year; based on each target monthly production load factor and the average daily oil production corresponding to the current year, the target monthly oil production corresponding to each month in the current year is predicted. The technical solution of the embodiment of the present invention solves the problem that the current oil and gas prediction method cannot predict the monthly oil and gas production and the prediction accuracy is low, and realizes the prediction of the monthly oil and gas production, greatly improving the prediction effect and prediction accuracy.

[0127] Optionally, the historical load factor determination module 310 includes:

[0128] The oil production acquisition module is used to obtain the average daily oil production of new wells, the average daily oil production of old wells and the average daily increased oil production corresponding to each month in the target oil and gas area in the historical year.

[0129] Optionally, the historical load factor determination module 310 further includes:

[0130] A monthly average daily oil production calculation module, used to calculate the monthly average daily oil production corresponding to each month based on the average daily oil production of new wells, the average daily oil production of old wells and the average daily incremental oil production;

[0131] The annual average daily oil production calculation module is used to calculate the annual average daily oil production of the target area in any year to be calculated in the historical years based on the monthly average daily oil production corresponding to each month and the number of days in each month;

[0132] The historical monthly load factor calculation module is used to determine the historical monthly production load factor corresponding to each month in the year to be calculated based on the ratio of the monthly average daily oil production corresponding to each month in the year to be calculated to the annual average daily oil production.

[0133] Optionally, the prediction device for monthly oil and gas production includes a model training module, and the model training module includes:

[0134] A time series data generation module, used to generate load factor time series data based on the historical monthly production load factors corresponding to each month in the historical year and the time information corresponding to the historical monthly production load factors;

[0135] An initial model training module, used to divide the load factor time series data into a training set and a validation set according to a preset ratio, and train each prediction model to be trained based on the training set to obtain each initial prediction model;

[0136] an error determination module, used to verify each of the initial prediction models based on the verification set, obtain an error corresponding to each of the initial prediction models, and determine the load factor prediction model based on the error;

[0137] The prediction models to be trained include at least two of a seasonal difference autoregressive sliding average model, a difference integrated moving average autoregressive model, a grey system theory model and a mean value model.

[0138] Optionally, the error determination module includes:

[0139] A load factor prediction model determination unit, used to determine the errors corresponding to the initial models, and determine the initial prediction model corresponding to the smallest error as the load factor prediction model;

[0140] The error includes at least one of error variance, mean square error, root mean square error, mean absolute error, maximum absolute error, minimum absolute error, mean relative error, maximum relative error and minimum relative error.

[0141] Optionally, the target load factor prediction module 320 includes:

[0142] An input module, used for inputting each of the historical monthly production load factor data into the load factor prediction model to obtain an output value of the load factor prediction model;

[0143] The factor determination module is used to determine the output value as the target monthly production load factor corresponding to each month in the current year.

[0144] Optionally, the monthly oil production determination module 330 includes:

[0145] A current year average daily oil production determination module, used to calculate the average daily oil production corresponding to the current year based on the planned total oil production of the target oil and gas region in the current year and the number of days in the current year;

[0146] The target monthly oil production determination module is used to calculate the target monthly oil production corresponding to each month in the current year of the target oil and gas region based on the average daily oil production and the target monthly production load factor corresponding to each month.

[0147] The monthly oil and gas production prediction device provided in the embodiment of the present invention can execute the monthly oil and gas production prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0148] Embodiment 4

[0149] Figure 5 A schematic diagram of the structure of an electronic device provided for Embodiment 4 of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0150] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0151] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0152] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for predicting monthly oil and gas production.

[0153] In some embodiments, the method for predicting monthly oil and gas production may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for predicting monthly oil and gas production described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for predicting monthly oil and gas production in any other appropriate manner (e.g., by means of firmware).

[0154] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0155] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0156] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0157] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0158] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0159] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0160] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0161] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting monthly oil and gas production, characterized in that: include: Acquire historical monthly oil and gas data generated by the target oil and gas region in the historical year, and determine the historical monthly production load factor corresponding to each month in the historical year based on the historical monthly oil and gas data; Inputting each of the historical monthly production load factors into a load factor prediction model to obtain a target monthly production load factor corresponding to each month in a current year, wherein the current year is associated with the historical years; Based on each of the target monthly production load factors and the average daily oil production corresponding to the current year, the target monthly oil production corresponding to each month in the current year of the target oil and gas region is predicted.

2. The method according to claim 1, characterized in that The acquisition of historical oil and gas monthly data generated in the target oil and gas area in historical years includes: The average daily oil production of new wells, the average daily oil production of old wells and the average daily increased oil production corresponding to each month in the target oil and gas area in the historical year are obtained.

3. The method according to claim 2, characterized in that The determining of the historical monthly production load factors corresponding to each month in the historical year based on the historical oil and gas monthly data includes: Based on the average daily oil production of new wells, the average daily oil production of old wells and the average daily incremental oil production, the monthly average daily oil production corresponding to each month is calculated; For any year to be calculated in the historical years, based on the monthly average daily oil production corresponding to each month and the number of days in each month, calculate the annual average daily oil production of the target area in the year to be calculated; Based on the ratio of the monthly average daily oil production corresponding to each month in the year to be calculated to the annual average daily oil production, the historical monthly production load factor corresponding to each month in the year to be calculated is determined.

4. The method according to claim 3, characterized in that The load factor prediction model is trained as follows: Generate load factor time series data based on the historical monthly production load factors corresponding to each month in the historical year and the time information corresponding to the historical monthly production load factors; Dividing the load factor time series data into a training set and a validation set according to a preset ratio, and training each prediction model to be trained based on the training set to obtain each initial prediction model; Verifying each of the initial prediction models based on the verification set, obtaining an error corresponding to each of the initial prediction models, and determining the load factor prediction model based on the error; The prediction models to be trained include at least two of a seasonal difference autoregressive sliding average model, a difference integrated moving average autoregressive model, a grey system theory model and a mean value model.

5. The method according to claim 4, characterized in that The verifying each of the initial prediction models based on the verification set to obtain an error corresponding to each of the initial prediction models, and determining the load factor prediction model based on the error, comprises: Determine the errors corresponding to the initial models, and determine the initial prediction model corresponding to the smallest error as the load factor prediction model; The error includes at least one of error variance, mean square error, root mean square error, mean absolute error, maximum absolute error, minimum absolute error, mean relative error, maximum relative error and minimum relative error.

6. The method according to claim 1, characterized in that The inputting of each of the historical monthly production load factors into the load factor prediction model to obtain the target monthly production load factor corresponding to each month in the current year includes: Inputting each of the historical monthly production load factor data into the load factor prediction model to obtain an output value of the load factor prediction model; The output value is determined as the target monthly production load factor corresponding to each month in the current year.

7. The method according to claim 1, characterized in that The predicting of the target monthly oil production corresponding to each month in the current year of the target oil and gas region based on the target monthly production load factor and the average daily oil production corresponding to the current year includes: Calculate the average daily oil production corresponding to the current year based on the planned total oil production of the target oil and gas region in the current year and the number of days in the current year; Based on the average daily oil production and the target monthly production load factor corresponding to each month, the target monthly oil production corresponding to each month in the current year of the target oil and gas region is calculated.

8. A device for predicting monthly oil and gas production, characterized in that: include: A historical load factor determination module is used to obtain historical oil and gas monthly data generated in the target oil and gas area in the historical year, and determine the historical monthly production load factor corresponding to each month in the historical year based on the historical oil and gas monthly data; A target load factor prediction module, for inputting each of the historical monthly production load factors into a load factor prediction model to obtain a target monthly production load factor corresponding to each month in a current year, wherein the current year is associated with the historical years; The monthly oil production determination module is used to predict the target monthly oil production corresponding to each month in the current year of the target oil and gas region based on each target monthly production load factor and the average daily oil production corresponding to the current year.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting monthly oil and gas production according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting monthly oil and gas production according to any one of claims 1-7 when executed.

Images