Method and device for predicting medium and long term yield of shale oil, medium and program product

Abstract

The invention relates to a method and a device for predicting medium and long-term yield of shale oil, a medium and a program product. The shale oil medium-and-long-term yield prediction method comprises the following steps: creating an initial yield prediction model based on main control factors; obtaining yield data and geological information of the well to be detected; inputting the yield data and the geological information into an initial yield prediction model to obtain first yield prediction data of the to-be-detected well; performing recursion processing on the historical yield data to create a medium and long term yield prediction chart; determining second yield prediction data of the to-be-detected well based on the medium and long term yield prediction chart; the production duration corresponding to the second yield prediction data is longer than the production duration corresponding to the first yield prediction data.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a method, device, medium and program product for predicting medium- and long-term shale oil production. Background Art

[0002] Shale oil is different from conventional sandstone oil and gas reservoirs. Natural production capacity can only be obtained from volumetric shale, and the complex volumetric fracture network formed makes the flow characteristics of shale oil extremely complex. Existing production capacity evaluation methods have certain limitations. Currently, the commonly used shale oil and gas production capacity evaluation methods mainly include empirical methods, modern production decline methods, analytical methods and numerical simulation methods. However, the above methods have problems such as low production capacity determination efficiency and poor data accuracy. Summary of the Invention

[0003] In view of this, the present invention provides a method, device, medium and program product for predicting medium- and long-term shale oil production.

[0004] Specifically, the present invention is implemented through the following technical solutions:

[0005] According to a first aspect of the present invention, there is provided a method for predicting medium- and long-term shale oil production, the method for predicting medium- and long-term shale oil production comprising: obtaining historical production data and theoretical production data of a sample well; performing data processing on the historical production data and the theoretical production data to obtain a plurality of production influencing factors of the sample well, the production influencing factors being factors affecting the production of the sample well; creating a plurality of production influence curves according to the plurality of production influencing factors, the plurality of production influence curves corresponding one-to-one to the plurality of production influencing factors, the production influence curve being used to represent the influence degree of the production influencing factor on the production of the sample well; determining a main control factor among the plurality of production influencing factors based on the plurality of production influence curves; creating an initial production prediction model based on the main control factor; obtaining production data and geological information of a well to be detected; inputting the production data and the geological information into the initial production prediction model to obtain a first production prediction data of the well to be detected; performing recursive processing on the historical production data to create a medium- and long-term production prediction chart; determining a second production prediction data of the well to be detected based on the medium- and long-term production prediction chart; the production duration corresponding to the second production prediction data is greater than the production duration corresponding to the first production prediction data.

[0006] The method for predicting medium- and long-term shale oil production in this technical solution ensures the data accuracy of the first production prediction data and the second production prediction data, and at the same time improves the confirmation efficiency of the first production prediction data and the second production prediction data, and improves the production prediction efficiency of the well to be detected.

[0007] According to a second aspect of the present invention, there is provided a device for predicting medium- and long-term shale oil production. The device for predicting medium- and long-term shale oil production includes: a processing module configured to obtain historical production data and theoretical production data of sample wells; the processing module is further configured to perform data processing on the historical production data and the theoretical production data to obtain multiple production influencing factors of the sample wells, where the production influencing factors are factors affecting the production of the sample wells; the processing module is further configured to create multiple production influence curves based on the multiple production influencing factors, the multiple production influence curves corresponding one-to-one to the multiple production influencing factors, and the production influence curves being used to represent the influence degree of the production influencing factors on the production of the sample wells; the processing module is further configured to determine the main control factors among the multiple production influencing factors based on the multiple production influence curves; the processing module is further configured to create an initial production prediction model based on the main control factors; the processing module is further configured to obtain production data and geological information of the well to be detected; the processing module is further configured to input the production data and the geological information into the initial production prediction model to obtain first production prediction data of the well to be detected; the processing module is further configured to perform recursive processing on the historical production data to create a medium- and long-term production prediction chart; the processing module is further configured to determine second production prediction data of the well to be detected based on the medium- and long-term production prediction chart; the processing module is further configured to ensure that the production duration corresponding to the second production prediction data is greater than the production duration corresponding to the first production prediction data.

[0008] The device for predicting medium- and long-term shale oil production in this technical solution ensures the data accuracy of the first production prediction data and the second production prediction data, and at the same time improves the confirmation efficiency of the first production prediction data and the second production prediction data, thereby improving the production prediction efficiency of the well to be detected.

[0009] According to a third aspect of the present invention, there is provided a device for predicting medium- and long-term shale oil production, including a processor and a memory. A program or instruction is stored in the memory, and when the program or instruction is executed by the processor, the steps of the method for predicting medium- and long-term shale oil production in any possible implementation manner of the first aspect are implemented. Therefore, the device for predicting medium- and long-term shale oil production has all the beneficial effects of the method for predicting medium- and long-term shale oil production in any of the above technical solutions, which will not be elaborated here.

[0010] According to a fourth aspect of the present invention, there is provided a storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the method for predicting medium- and long-term shale oil production in any possible implementation manner of the first aspect are implemented.

[0011] According to a fifth aspect of the present invention, there is provided a computer program product, including a computer program, and when the program is executed by a processor, the steps of the method for predicting medium- and long-term shale oil production in any possible implementation manner of the first aspect are implemented.

[0012] The technical solution provided by the present invention has at least the following beneficial effects:

[0013] It ensures the data accuracy of the first production prediction data, improves the confirmation efficiency of the first production prediction data, and enhances the production prediction efficiency of the sample wells. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present invention and used together with the specification to explain the principles of the present invention.

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0016] Figure 1 One of the flow diagrams of a method for predicting medium- and long-term shale oil production provided by an embodiment of the present invention;

[0017] Figure 2 Another flow diagram of a method for predicting medium- and long-term shale oil production provided by an embodiment of the present invention;

[0018] Figure 3 Another flow diagram of a method for predicting medium- and long-term shale oil production provided by an embodiment of the present invention;

[0019] Figure 4 Another flow diagram of a method for predicting medium- and long-term shale oil production provided by an embodiment of the present invention;

[0020] Figure 5 Another flow diagram of a method for predicting medium- and long-term shale oil production provided by an embodiment of the present invention;

[0021] Figure 6 Another flow diagram of a method for predicting medium- and long-term shale oil production provided by an embodiment of the present invention;

[0022] Figure 7 One of the structural block diagrams of a device for predicting medium- and long-term shale oil production provided by an embodiment of the present invention;

[0023] Figure 8 One of the effect diagrams of a device for predicting medium- and long-term shale oil production provided by an embodiment of the present invention;

[0024] Figure 9 Another effect diagram of a device for predicting medium- and long-term shale oil production provided by an embodiment of the present invention;

[0025] Figure 10 The third effect diagram of a prediction device for medium - and long - term shale oil production provided by an embodiment of the present invention;

[0026] Figure 11 The fourth effect diagram of a prediction device for medium - and long - term shale oil production provided by an embodiment of the present invention;

[0027] Figure 12 The fifth effect diagram of a prediction device for medium - and long - term shale oil production provided by an embodiment of the present invention;

[0028] Figure 13 The sixth effect diagram of a prediction device for medium - and long - term shale oil production provided by an embodiment of the present invention;

[0029] Figure 14 The seventh effect diagram of a prediction device for medium - and long - term shale oil production provided by an embodiment of the present invention;

[0030] Figure 15 The second structural block diagram of a prediction device for medium - and long - term shale oil production provided by an embodiment of the present invention. Detailed implementation manners

[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0032] The execution subject of the technical solution of the prediction method for medium - and long - term shale oil production provided by the present invention can be a prediction device, and can also be determined according to actual usage requirements, without specific limitation here. To more clearly describe the prediction method for medium - and long - term shale oil production provided by the present invention, the following will be described with the prediction device as the execution subject.

[0033] See Figure 1 , an embodiment of the present invention provides a prediction method for medium - and long - term shale oil production, and the method may include the following steps:

[0034] S101. Obtain the historical production data and theoretical production data of the sample wells;

[0035] S102. Perform data processing on the historical production data and theoretical production data to obtain multiple production influencing factors of the sample wells;

[0036] S103. Create multiple production impact curves based on multiple production impact factors;

[0037] S104. Determine the main control factors among the multiple production impact factors based on the multiple production impact curves;

[0038] S105. Create an initial production prediction model based on the main control factors;

[0039] S106. Obtain the production data and geological information of the well to be detected;

[0040] S107. Input the production data and geological information into the initial production prediction model to obtain the first production prediction data of the well to be detected;

[0041] S108. Perform recursive processing on the historical production data to create a medium - and long - term production prediction chart;

[0042] S109. Determine the second production prediction data of the well to be detected based on the medium - and long - term production prediction chart.

[0043] In this embodiment, a method for predicting the medium - and long - term production of shale oil is proposed. The prediction device obtains the historical production data and theoretical production data of the sample well, where the sample well is an oil well for which the production needs to be estimated, the historical production data is the production data of the sample well in history, and the theoretical production data is the theoretical data corresponding to the historical production data.

[0044] Exemplarily, the sample well can specifically be a shale oil well.

[0045] Exemplarily, the historical production data can be the five - year historical production data of the sample well.

[0046] Exemplarily, the theoretical production data can be the five - year theoretical production data of the sample well, and the theoretical production data can be inferred and determined from the historical production data.

[0047] The prediction device processes the historical production data and the theoretical production data to obtain multiple production impact factors of the sample well, where the production impact factors are the factors that affect the production of the sample well.

[0048] Exemplarily, the multiple production impact factors can include parameters such as inner - zone permeability, porosity, ratio of outer - to - inner - zone permeability, ratio of outer - to - inner - zone diffusion coefficients, boundary distance, fracture - network volume ratio, cross - flow coefficient, etc.

[0049] The prediction device creates multiple production impact curves according to the multiple production impact factors, where the multiple production impact curves correspond one - to - one with the multiple production impact factors, and the production impact curves are used to represent the degree of influence of the production impact factors on the production of the sample well.

[0050] Exemplarily, the production impact curve can be a production impact degree graph.

[0051] The prediction device determines the main control factor among multiple production impact factors based on multiple production impact curves, where the main control factor is the factor among the multiple production impact factors.

[0052] Exemplarily, the main control factor is the factor that has the greatest impact on production among the multiple production impact factors.

[0053] The prediction device creates an initial production prediction model based on the main control factor, where the initial production prediction model is used to predict the production of the oil well.

[0054] Exemplarily, the initial production prediction model can be a mathematical model.

[0055] Exemplarily, the initial production prediction model can be a deep learning model.

[0056] The prediction device obtains the production data and geological information of the well to be detected, where the well to be detected is the oil well that needs to be predicted, the production data is the production data of the well to be detected, and the geological information is the information of the geology near the well to be detected.

[0057] The prediction device inputs the production data and geological information into the initial production prediction model to obtain the first production prediction data of the well to be detected, where the first production prediction data is the initial production prediction data of the well to be detected.

[0058] The prediction device performs recursive processing on the historical production data to create a medium- and long-term production prediction chart, where the medium- and long-term production prediction chart is used to query the chart of the medium- and long-term predicted production data of the well to be detected.

[0059] The prediction device determines the second production prediction data of the well to be detected based on the medium- and long-term production prediction chart, where the second production prediction data is the medium- and long-term production prediction data of the well to be detected, and the production duration corresponding to the second production prediction data is greater than the production duration corresponding to the first production prediction data.

[0060] Exemplarily, the second production prediction data can be the production prediction data of the well to be detected for 2 years or 3 years, and the first production prediction data can be the production prediction data of the well to be detected for half a year.

[0061] The prediction method for the medium- and long-term production of shale oil in this embodiment ensures the data accuracy of the first production prediction data and the second production prediction data, and at the same time improves the confirmation efficiency of the first production prediction data and the second production prediction data, and improves the production prediction efficiency of the well to be detected.

[0062] See Figure 2, an embodiment of the present invention provides a method for predicting medium- and long-term shale oil production, which processes historical production data and theoretical production data to obtain multiple production influencing factors of the sample wells, including:

[0063] S201. Create a first production curve of the sample well based on the historical production data;

[0064] S202. Create a second production curve of the sample well based on the theoretical production data;

[0065] S203. Perform curve fitting on the first production curve and the second production curve to determine multiple production influencing factors among the multiple influencing factors.

[0066] In this embodiment, the prediction device creates a first production curve of the sample well based on the historical production data and creates a second production curve of the sample well based on the theoretical production data. Among them, the first production curve is the data curve corresponding to the historical production data, and the second production curve is the data curve corresponding to the theoretical production data. The second production curve includes multiple influencing factors, where the influencing factors are the influencing factors of the sample well.

[0067] Exemplarily, the influencing factors may include static parameters and dynamic parameters of the sample well.

[0068] The prediction device performs curve fitting on the first production curve and the second production curve to determine multiple production influencing factors among the multiple influencing factors.

[0069] Exemplarily, during the fitting process of the first production curve and the second production curve, multiple production influencing factors among the multiple influencing factors are determined.

[0070] The method for predicting medium- and long-term shale oil production in this embodiment performs curve fitting on the first production curve and the second production curve to determine multiple production influencing factors among the multiple influencing factors, ensuring the accuracy of the production influencing factors and thus ensuring the data accuracy of the first production prediction data.

[0071] See Figure 3 , an embodiment of the present invention provides a method for predicting medium- and long-term shale oil production, which performs curve fitting on the first production curve and the second production curve to determine multiple production influencing factors among the multiple influencing factors, including:

[0072] S301. Obtain the curve coincidence degree between the first production curve and the second production curve;

[0073] S302. Perform inversion operation on the curve coincidence degree to obtain multiple production influencing factors among the multiple influencing factors.

[0074] In this embodiment, the prediction device obtains the curve coincidence degree between the first production curve and the second production curve, and performs an inversion operation on the curve coincidence degree to obtain multiple production influencing factors among multiple influencing factors, where the curve coincidence degree is used to represent the coincidence degree between the first production curve and the second production curve.

[0075] Exemplarily, the curve coincidence degree can be the fitting degree between the first production curve and the second production curve.

[0076] The prediction device performs an inversion operation on the curve coincidence degree to obtain multiple production influencing factors among multiple influencing factors.

[0077] Exemplarily, the prediction device adjusts and fits the second production curve based on the first production curve to make the first production curve and the second production curve coincide, and determines multiple production influencing factors among multiple influencing factors during the fitting process.

[0078] The prediction method for the medium- and long-term production of shale oil in this embodiment performs an inversion operation on the curve coincidence degree to obtain multiple production influencing factors among multiple influencing factors, ensuring the accuracy of the production influencing factors, and further ensuring the data accuracy of the first production prediction data.

[0079] See Figure 4 , the embodiment of the present invention provides a prediction method for the medium- and long-term production of shale oil. Based on multiple production influence curves, the main control factors among multiple production influencing factors are determined, including:

[0080] S401. Compare the change ranges of multiple production influence curves, and determine the production main control factor curve among multiple production influence curves;

[0081] S402. Based on the production main control factor curve, determine the main control factor among multiple production influencing factors.

[0082] In this embodiment, the prediction device compares the change ranges of multiple production influence curves, and determines the production main control factor curve among multiple production influence curves, where the production main control factor curve is the curve among multiple production influence curves.

[0083] Exemplarily, the production main control factor curve can be the curve with the largest slope among multiple production influence curves.

[0084] The prediction device determines the main control factor among multiple production influencing factors based on the production main control factor curve.

[0085] Exemplarily, in the case of determining the production main control factor curve, the main control factor corresponding to the production main control factor curve is determined among multiple production influencing factors.

[0086] In the prediction method for the medium- and long-term shale oil production in this embodiment, the change amplitudes of multiple production influence curves are compared to determine the production main control factor curve among the multiple production influence curves. Based on the production main control factor curve, the main control factor among the multiple production influence factors is determined, ensuring the accuracy of the main control factor and further ensuring the data accuracy of the first production prediction data.

[0087] See Figure 5 , an embodiment of the present invention provides a prediction method for the medium- and long-term shale oil production. Based on the medium- and long-term production prediction chart, the second production prediction data of the well to be detected is determined, including:

[0088] S501, obtain the prediction duration of the well to be detected;

[0089] S502, based on the prediction duration, query the medium- and long-term production prediction chart for data to obtain the second production prediction data.

[0090] In this embodiment, the prediction device obtains the prediction duration of the well to be detected, where the prediction duration is the duration of the predicted production of the well to be detected.

[0091] Exemplarily, the prediction duration can be 2 years or 3 years.

[0092] The prediction device queries the medium- and long-term production prediction chart for data based on the prediction duration to obtain the second production prediction data.

[0093] In the prediction method for the medium- and long-term shale oil production in this embodiment, the medium- and long-term production prediction chart is queried for data based on the prediction duration to obtain the second production prediction data, ensuring the data accuracy of the second production prediction data and further ensuring the production data accuracy of the sample well.

[0094] See Figure 6 , an embodiment of the present invention provides a prediction method for the medium- and long-term shale oil production. The historical production data is recursively processed to create a medium- and long-term production prediction chart, including:

[0095] S601, obtain the preset recursive method;

[0096] S602, through the recursive method, perform data prediction on the production data of multiple periods to obtain the medium- and long-term production prediction chart.

[0097] In this embodiment, the theoretical production data includes the production data of multiple periods. The prediction device obtains the preset recursive method, where the recursive method is a method for performing data recursive processing, and the production data of a period is the production data of the sample well within the period.

[0098] Exemplarily, the production data of a period can specifically be the production data within one year.

[0099] The prediction device uses the recursive method to predict the production data for multiple periods and obtains a medium- and long-term production prediction chart.

[0100] Exemplarily, the prediction device obtains a preset confidence interval and processes the oil production data based on the confidence interval to obtain a medium- and long-term production prediction chart, where the confidence interval is a preset confidence level.

[0101] Exemplarily, the confidence interval can be 90%.

[0102] In this embodiment, the prediction method for the medium- and long-term production of shale oil uses the recursive method to predict the production data for multiple periods and obtains a medium- and long-term production prediction chart, ensuring the accuracy of the oil production chart and thus the accuracy of the production data of the sample wells.

[0103] Based on the same inventive concept, as Figure 7 shown, an embodiment of the present invention also provides a prediction device 700 for the medium- and long-term production of shale oil, including:

[0104] A processing module 702, configured to obtain the historical production data and theoretical production data of the sample wells;

[0105] The processing module 702 is further configured to process the historical production data and theoretical production data to obtain multiple production influencing factors of the sample wells, where the production influencing factors are the factors affecting the production of the sample wells;

[0106] The processing module 702 is further configured to create multiple production influence curves according to the multiple production influencing factors, where the multiple production influence curves correspond to the multiple production influencing factors one by one, and the production influence curves are used to represent the influence degree of the production influencing factors on the production of the sample wells;

[0107] The processing module 702 is further configured to determine the main control factors among the multiple production influencing factors based on the multiple production influence curves;

[0108] The processing module 702 is further configured to create an initial production prediction model based on the main control factors;

[0109] The processing module 702 is further configured to obtain the production data and geological information of the well to be detected;

[0110] The processing module 702 is further configured to input the production data and geological information into the initial production prediction model to obtain the first production prediction data of the well to be detected;

[0111] The processing module 702 is further configured to perform recursive processing on the historical production data to create a medium- and long-term production prediction chart;

[0112] The processing module 702 is further configured to determine the second production prediction data of the well to be detected based on the medium- and long-term production prediction chart

[0113] The processing module 702 is further configured that the production time corresponding to the second production prediction data is greater than the production time corresponding to the first production prediction data.

[0114] In this embodiment, a prediction device 700 for shale oil medium- and long-term production is proposed. The prediction device obtains the historical production data and theoretical production data of the sample well. Among them, the sample well is an oil well whose production needs to be estimated, the historical production data is the production data of the sample well in history, and the theoretical production data is the theoretical data corresponding to the historical production data.

[0115] Exemplarily, the sample well may specifically be a shale oil well.

[0116] Exemplarily, the historical production data may be the five-year historical production data of the sample well.

[0117] Exemplarily, the theoretical production data may be the five-year theoretical production data of the sample well, and the theoretical production data can be inferred and determined from the historical production data.

[0118] The processing module 702 processes the historical production data and the theoretical production data to obtain multiple production influencing factors of the sample well. Among them, the production influencing factor is a factor that affects the production of the sample well.

[0119] Exemplarily, the multiple production influencing factors may include parameters such as inner zone permeability, porosity, ratio of outer zone to inner zone permeability, ratio of outer zone to inner zone diffusion coefficient, boundary distance, fracture network volume ratio, and crossflow coefficient.

[0120] The processing module 702 creates multiple production influence curves according to the multiple production influencing factors. Among them, the multiple production influence curves correspond one-to-one with the multiple production influencing factors, and the production influence curve is used to represent the influence degree of the production influencing factor on the production of the sample well.

[0121] Exemplarily, the production influence curve may be a production influence degree chart.

[0122] The processing module 702 determines the main control factors among the multiple production influencing factors based on the multiple production influence curves. Among them, the main control factor is a factor among the multiple production influencing factors.

[0123] Exemplarily, the main control factor is the factor that has the greatest influence on production among the multiple production influencing factors.

[0124] The processing module 702 creates an initial production prediction model based on the main control factor. Among them, the initial production prediction model is used to predict the production of the oil well.

[0125] Exemplarily, the initial production prediction model can be a mathematical model.

[0126] Exemplarily, the initial production prediction model can be a deep learning model.

[0127] The processing module 702 obtains the production data and geological information of the well to be detected, where the well to be detected is an oil well that needs to be predicted, the production data is the production data of the well to be detected, and the geological information is the information of the geology near the well to be detected.

[0128] The processing module 702 inputs the production data and geological information into the initial production prediction model to obtain the first production prediction data of the well to be detected, where the first production prediction data is the initial production prediction data of the well to be detected.

[0129] The processing module 702 performs recursive processing on the historical production data to create a medium- and long-term production prediction chart, where the medium- and long-term production prediction chart is used to query the chart of the medium- and long-term predicted production data of the well to be detected.

[0130] The processing module 702 determines the second production prediction data of the well to be detected based on the medium- and long-term production prediction chart, where the second production prediction data is the medium- and long-term production prediction data of the well to be detected, and the production duration corresponding to the second production prediction data is greater than the production duration corresponding to the first production prediction data.

[0131] Exemplarily, the second production prediction data can be the production prediction data of the well to be detected for 2 years or 3 years, and the first production prediction data can be the production prediction data of the well to be detected for half a year.

[0132] Exemplarily, the prediction device 700 for the medium- and long-term production of shale oil can implement the following steps:

[0133] (1) Data preparation: Collect the well history, fracturing construction data, pressure and production data during production of shale oil wells.

[0134] (2) Inversion of reservoir parameters by the PDA method: According to the actual geological and production data of a single well, generate the actual production and pressure curves. Set the initial values of the fitting parameters, generate the theoretical curve, and continuously adjust the fitting parameter values by comparing the coincidence degree of the actual curve and the theoretical curve to ensure the coincidence of the two curves (as Figure 8 shown), and obtain the reservoir parameters such as the inner zone permeability, porosity, ratio of outer zone to inner zone permeability, ratio of outer zone to inner zone diffusion coefficient, boundary distance, fracture network volume ratio, and crossflow coefficient.

[0135] (3) Key factors determining the production of shale oil wells: Inverse reservoir parameters for all wells in the block to obtain the distribution range of reservoir parameters in the block. The inner area permeability distribution is between [0.05 - 0.15], the porosity distribution is between [0.01 - 0.1], and the ratio of the diffusion coefficients between the outer and inner areas is between [0.05 - 0.15], etc. Uniformly sample each parameter within the specified interval, conduct single - well production simulation, and generate productivity simulation curves with different parameters. According to the variation amplitude of the curves, determine the main factors that significantly affect production. It is found that the inner area permeability, porosity, outer - to - inner area permeability, ratio of outer - to - inner area diffusion coefficients, and boundary distance all have a relatively significant impact on production (as Figure 9 shown), while the fracture network volume ratio, cross - flow coefficient, and ratio of fracture diffusion coefficients have a relatively small impact on the curve variation (as Figure 10 shown).

[0136] (4) Establishment of the initial production model: By determining the key factors affecting production, establish a productivity proxy model for the initial stage (within half a year) after fracturing of shale oil wells, and compare it with the oil production index of actual wells to verify the accuracy of the model. For the true and predicted production values of the training set and validation set, it is found that the model has a high fitting accuracy (as Figure 11 shown).

[0137] (5) Establishment of the medium - and long - term production chart: According to the production simulation results, intercept the cumulative production for production time periods of half a year, 1 year, 2 years, and 3 years. Use the recursive method to predict the production with different years, and obtain the production prediction interval according to the 90% confidence interval. Successively establish the production chart for predicting 1 - year production from half - year production, the production chart for predicting 2 - year production from 1 - year production, the production chart for predicting 3 - year production from 2 - year production, etc. (as Figure 12 , Figure 13 and Figure 14 shown) to avoid inaccurate results due to too long a prediction period. By comparing the single - well production with the actual production, when the production time is 1 year, the predicted production is 3600.05 t, the actual cumulative production is 3467.66 t, and the relative error is 3.67%; when the production time is 2 years, the predicted production is 6195.03 t, the actual cumulative production is 6603.21 t, and the relative error is 6.58%; when the production time is 3 years, the predicted production is 8057.69 t, the actual cumulative production is 8593.93 t, and the relative error is 6.65%.

[0138] (6) Prediction of new well productivity: Collect single - well geological and production data, conduct parameter inversion by the PDA method, input it into the initial production model to obtain the production for half a year, and then refer to the medium - and long - term production chart to obtain the production under different development years.

[0139] The prediction device 700 for the medium- and long-term shale oil production in this embodiment ensures the data accuracy of the first production prediction data and the second production prediction data. At the same time, it improves the confirmation efficiency of the first production prediction data and the second production prediction data, and improves the production prediction efficiency of the well to be detected.

[0140] Based on the same inventive concept, an embodiment of the present invention further provides a prediction device 700 for the medium- and long-term shale oil production, further including:

[0141] The processing module 702 is further configured to create a first production curve of the sample well based on the historical production data;

[0142] The processing module 702 is further configured to create a second production curve of the sample well based on the theoretical production data, and the second production curve includes multiple influencing factors;

[0143] The processing module 702 is further configured to perform curve fitting processing on the first production curve and the second production curve to determine multiple production influencing factors among the multiple influencing factors.

[0144] The prediction device 700 for the medium- and long-term shale oil production in this embodiment performs curve fitting processing on the first production curve and the second production curve to determine multiple production influencing factors among the multiple influencing factors, which ensures the accuracy of the production influencing factors, and further ensures the data accuracy of the first production prediction data.

[0145] Based on the same inventive concept, an embodiment of the present invention further provides a prediction device 700 for the medium- and long-term shale oil production, further including:

[0146] The processing module 702 is further configured to obtain the curve coincidence degree between the first production curve and the second production curve;

[0147] The processing module 702 is further configured to perform an inversion operation on the curve coincidence degree to obtain multiple production influencing factors among the multiple influencing factors.

[0148] The prediction device 700 for the medium- and long-term shale oil production in this embodiment performs an inversion operation on the curve coincidence degree to obtain multiple production influencing factors among the multiple influencing factors, which ensures the accuracy of the production influencing factors, and further ensures the data accuracy of the first production prediction data.

[0149] Based on the same inventive concept, an embodiment of the present invention further provides a prediction device 700 for the medium- and long-term shale oil production, further including:

[0150] The processing module 702 is further configured to compare the change amplitudes of multiple production influence curves to determine the production main control factor curve among the multiple production influence curves;

[0151] The processing module 702 is further configured to determine the main control factor among multiple production influencing factors based on the production main control factor curve.

[0152] In the prediction device 700 for medium- and long-term shale oil production of this embodiment, by comparing the change amplitudes of multiple production influencing curves, the production main control factor curve among the multiple production influencing curves is determined, and based on the production main control factor curve, the main control factor among the multiple production influencing factors is determined, ensuring the accuracy of the main control factor, and further ensuring the data accuracy of the first production prediction data.

[0153] Based on the same inventive concept, an embodiment of the present invention further provides a prediction device 700 for medium- and long-term shale oil production, further including:

[0154] The processing module 702 is further configured to obtain the prediction duration of the well to be detected.

[0155] The processing module 702 is further configured to query data from the medium- and long-term production prediction chart based on the prediction duration to obtain the second production prediction data.

[0156] In the prediction device 700 for medium- and long-term shale oil production of this embodiment, by querying data from the medium- and long-term production prediction chart based on the prediction duration to obtain the second production prediction data, the data accuracy of the second production prediction data is ensured, and further the production data accuracy of the sample well is ensured.

[0157] Based on the same inventive concept, an embodiment of the present invention further provides a prediction device 700 for medium- and long-term shale oil production, further including:

[0158] The processing module 702 is further configured to obtain a preset recursive method.

[0159] The processing module 702 is further configured to perform data prediction on the production data of multiple time periods through the recursive method to obtain the medium- and long-term production prediction chart.

[0160] In the prediction device 700 for medium- and long-term shale oil production of this embodiment, by performing data prediction on the production data of multiple time periods through the recursive method to obtain the medium- and long-term production prediction chart, the accuracy of the oil production chart is ensured, and further the production data accuracy of the sample well is ensured.

[0161] Based on the same inventive concept, as Figure 15As shown in the figure, an embodiment of the present invention further provides a prediction device 1500 for medium- and long-term shale oil production, including a processor 1502 and a memory 1504. A program or instruction is stored in the memory 1504, and when the program or instruction is executed by the processor 1502, the steps of the prediction method for medium- and long-term shale oil production in any of the above technical solutions are implemented. Therefore, the prediction device 1500 for medium- and long-term shale oil production has all the beneficial effects of the prediction method for medium- and long-term shale oil production in any of the above technical solutions, which will not be elaborated here.

[0162] Based on the same inventive concept, an embodiment of the present invention further provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the prediction method for medium- and long-term shale oil production in any possible implementation manner above are implemented.

[0163] Optionally, the storage medium may be a non-transitory computer-readable storage medium. For example, the non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0164] Based on the same inventive concept, an embodiment of the present invention further provides a computer program product, including a computer program, and when the program is executed by a processor, the steps of the prediction method for medium- and long-term shale oil production in any possible implementation manner above are implemented.

[0165] The embodiments of the subject matter and functional operations described in this specification can be implemented in the following: digital electronic circuits, tangible embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. The embodiments of the subject matter described in this specification can be implemented as one or more computer programs, that is, one or more modules in computer program instructions encoded on a tangible non-transitory program carrier to be executed by a data processing device or to control the operation of the data processing device. Alternatively or additionally, the program instructions can be encoded on a manually generated propagated signal, such as a machine-generated electrical, optical, or electromagnetic signal, which is generated to encode information and transmit it to a suitable receiver device for execution by the data processing device. The computer storage medium can be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.

[0166] The processes and logical flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform the corresponding functions by operating on input data and generating output. The processes and logical flows can also be performed by, for example, special purpose logic circuitry such as an FPGA (Field Programmable Gate Array) or ASIC (Application Specific Integrated Circuit), and the apparatus can also be implemented as special purpose logic circuitry.

[0167] Computers suitable for executing computer programs include, by way of example, general and / or special purpose microprocessors, or any other type of central processing unit. In general, a central processing unit will receive instructions and data from a read only memory and / or a random access memory. Basic components of a computer include a central processing unit for executing or implementing instructions and one or more memory devices for storing instructions and data. In general, a computer will also include one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, etc., or the computer will be operatively coupled to such mass storage devices to receive data therefrom or to transfer data thereto, or both. However, a computer need not have such devices. In addition, a computer may be embedded in another device, such as a mobile phone, a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a portable storage device such as a Universal Serial Bus (USB) flash drive, to name just a few.

[0168] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, including by way of example semiconductor memory devices (such as EPROM, EEPROM, and flash memory devices), magnetic disks (such as internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. The processor and the memory may be supplemented by, or incorporated in, special purpose logic circuitry.

[0169] Although this specification contains many specific implementation details, these should not be construed as limiting the scope of any invention or the scope of what is claimed, but rather as primarily describing features of particular embodiments of a particular invention. Certain features that are described in this specification in the context of multiple embodiments can also be implemented in a single embodiment in combination. On the other hand, the various features described in a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination. In addition, although features may operate in certain combinations as described above and even be initially claimed as such, one or more features from a claimed combination can in some cases be removed from the combination, and the claimed combination can be directed to a sub-combination or a variation of a sub-combination.

[0170] Similarly, although the operations are depicted in the drawings in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or sequentially, or that all illustrated operations be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above embodiments should not be construed as required in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0171] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the acts recited in the claims can be performed in a different order and still achieve the desired result. In addition, the processes depicted in the figures are not necessarily in the particular order or sequential order shown to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0172] It should be noted that, in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0173] The above are only specific embodiments of the present invention, which enable those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for predicting medium - and long - term shale oil production, characterized in that, the method for predicting medium - and long - term shale oil production includes: Obtain the historical production data and theoretical production data of the sample wells; Perform data processing on the historical production data and the theoretical production data to obtain multiple production influencing factors of the sample wells, where the production influencing factors are the factors affecting the production of the sample wells; According to the multiple production influencing factors, create multiple production influence curves, and the multiple production influence curves correspond one - to - one with the multiple production influencing factors. The production influence curves are used to represent the influence degree of the production influencing factors on the production of the sample wells; Based on the multiple production influence curves, determine the main control factors among the multiple production influencing factors; Based on the main control factors, create an initial production prediction model; Obtain the production data and geological information of the wells to be detected; Input the production data and the geological information into the initial production prediction model to obtain the first production prediction data of the wells to be detected; Perform recursive processing on the historical production data to create a medium - and long - term production prediction chart; Based on the medium - and long - term production prediction chart, determine the second production prediction data of the wells to be detected; The production duration corresponding to the second production prediction data is greater than the production duration corresponding to the first production prediction data.

2. The method for predicting medium - and long - term shale oil production according to claim 1, characterized in that, the performing data processing on the historical production data and the theoretical production data to obtain multiple production influencing factors of the sample wells includes: Based on the historical production data, create the first production curve of the sample wells; Based on the theoretical production data, create the second production curve of the sample wells, and the second production curve includes multiple influencing factors; Perform curve fitting processing on the first production curve and the second production curve to determine multiple production influencing factors among the multiple influencing factors.

3. The method for predicting medium - and long - term shale oil production according to claim 2, characterized in that, the performing curve fitting processing on the first production curve and the second production curve to determine multiple production influencing factors among the multiple influencing factors includes: Obtain the curve coincidence degree between the first production curve and the second production curve; Perform inversion operation on the curve coincidence degree to obtain multiple production influencing factors among the multiple influencing factors.

4. The method for predicting medium - and long - term shale oil production according to claim 1, characterized in that, the determining the main control factors among the multiple production influencing factors based on the multiple production influence curves includes: Compare the change amplitudes of the multiple production influence curves to determine the production main control factor curve among the multiple production influence curves; Based on the production main control factor curve, determine the main control factors among the multiple production influencing factors.

5. The method for predicting medium - and long - term shale oil production according to any one of claims 1 to 4, characterized in that, the determining the second production prediction data of the wells to be detected based on the medium - and long - term production prediction chart includes: Obtain the predicted duration of the well to be detected; Based on the predicted duration, query data from the medium- and long-term production prediction chart to obtain the second production prediction data.

6. The method for predicting the medium- and long-term production of shale oil according to any one of claims 1 to 4, characterized in that, The historical production data includes production data for multiple periods. The recursive processing of the historical production data to create a medium- and long-term production prediction chart includes: Obtain a preset recursive method; Through the recursive method, perform data prediction on the production data for multiple periods to obtain the medium- and long-term production prediction chart.

7. A device for predicting the medium- and long-term production of shale oil, characterized in that, The device for predicting the medium- and long-term production of shale oil includes: A processing module, configured to obtain the historical production data and theoretical production data of the sample well; The processing module is further configured to perform data processing on the historical production data and the theoretical production data to obtain multiple production influencing factors of the sample well, and the production influencing factors are factors affecting the production of the sample well; The processing module is further configured to create multiple production influence curves according to multiple production influencing factors, and the multiple production influence curves correspond to the multiple production influencing factors one by one. The production influence curve is used to represent the influence degree of the production influencing factor on the production of the sample well; The processing module is further configured to determine the main control factors among the multiple production influencing factors based on the multiple production influence curves; The processing module is further configured to create an initial production prediction model based on the main control factors; The processing module is further configured to obtain the production data and geological information of the well to be detected; The processing module is further configured to input the production data and the geological information into the initial production prediction model to obtain the first production prediction data of the well to be detected; The processing module is further configured to perform recursive processing on the historical production data to create a medium- and long-term production prediction chart; The processing module is further configured to determine the second production prediction data of the well to be detected based on the medium- and long-term production prediction chart; The processing module is further configured to ensure that the production duration corresponding to the second production prediction data is greater than the production duration corresponding to the first production prediction data.

8. A device for predicting the medium- and long-term production of shale oil, characterized in that, including: A processor; A memory, in which a program or instruction is stored. When the processor executes the program or instruction in the memory, the steps of the method for predicting the medium- and long-term production of shale oil according to any one of claims 1 to 6 are implemented.

9. A storage medium, characterized in that, A computer program is stored thereon. When the computer program is executed by a processor, the steps of the method for predicting the medium- and long-term production of shale oil according to any one of claims 1 to 6 are implemented.

10. A program product, characterized in that, including a computer program. When the computer program is executed by a processor, the steps of the method for predicting the medium- and long-term production of shale oil according to any one of claims 1 to 6 are implemented.

Images