A single well geological reserve prediction method and system

Abstract

The embodiment of the present invention provides a single well geological reserve prediction method and system, which solves the problem of errors and uncertainties in the current method for predicting single well geological reserves. The single well geological reserve prediction method includes: determining the reservoir type and driving energy type of the single well to be predicted; obtaining recoverable reserves based on the reservoir type and the driving energy type; obtaining producing reserves based on the water-oil ratio of the single well to be predicted; inputting the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into a neural network prediction model, and obtaining the geological reserves of the single well to be predicted based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves.

Description

Technical Field

[0001] The invention relates to the field of petroleum technology, and in particular to a single well geological reserve prediction method and system. Background Art

[0002] Geological reserve prediction is one of the most important parameters in the process of oil reservoir exploration and development. In particular, fracture-cavity carbonate reservoirs have complex and diverse types, complex oil-water distribution, diverse fluid flow types, and complex flow patterns. The reliability of fracture-cavity carbonate reservoir reserve evaluation is of great significance to oil field development and subsequent adjustment and potential tapping.

[0003] At present, the identification of fracture-cavity carbonate reservoirs mainly includes static and dynamic identification. my country has carried out a lot of work on the identification of fracture-cavity reservoir types and formed a preliminary quantitative standard. In terms of the calculation of recoverable reserves, Arps proposed the use of the production decline method to obtain reserves in 1945; scholar Nazarov proposed a linear relationship between the cumulative liquid-oil ratio and the cumulative water production in the form of an empirical formula in 1972 (Type D water drive curve); his compatriot Maksimov proposed a semi-logarithmic linear relationship between cumulative water production and cumulative oil production in 1959 with an empirical formula, which was later named Type A water drive curve by Tong Xianzhang in 1978, and a semi-logarithmic relationship between cumulative liquid production and cumulative oil production was proposed in the form of an empirical formula (Type B water drive curve); F In 1980, Etkovich proposed the connection between the radial flow diffusion equation and well production dynamics, and developed the declining trend analysis; scholars Shebachev and Nazarov proposed the linear relationship between the cumulative liquid-to-oil ratio and the cumulative liquid production (Type C water drive curve) in 1981 and 1982 respectively; in 1995, Yu Qitai used the three growth curves of Weible, Gomperts and Logistic to describe and predict oil field development indicators, and derived the corresponding calculation formulas for cumulative oil production, production, reserve-production ratio, maximum production and time of maximum production.

[0004] In the study of producing reserves, Schilthuis first proposed the material balance method in 1936. Based on his research results, Havlena and Odeh proposed the pressure drop method to calculate reserves in 1963. In 1956, Park Jones proposed the use of pressure recovery curve to determine the controlled reserves of a single well. In 1956, Pollard proposed a method to calculate the reserves of fractured oil reservoirs and evaluate the acidizing effect of oil wells using pressure recovery data under the assumption of constant temperature. In 1986, Owusu LA provided a reserve evaluation method for highly heterogeneous natural fractured oil reservoirs with water invasion or water injection development, established a fully implicit general calculation model for predicting recovery rate, and derived the relationship between recovery rate and production water-oil ratio based on this model. R. Aguilera studied the skin factor and reserve evaluation of natural fractured reservoirs in 1999, and proposed a general method for calculating the reserves and recovery rate of this type of reservoir. In 2006, he proposed a material balance equation that takes into account the effective compressibility of the matrix and fractures and stress sensitivity characteristic data (such as the porosity and permeability of the fractures and the gas fraction stored in the bedrock and fractures). Later scholars proposed a large number of improved methods for calculating recoverable reserves and producing reserves based on the above methods.

[0005] In terms of single-well geological reserve prediction, the scale and quality of oilfield geological reserves are important bases for oilfield development deployment and decision-making. The main methods for calculating geological reserves include empirical method, volumetric method, material balance method, dynamic method (water drive curve method, decline curve method, etc.), core analysis method, statistical simulation method, numerical simulation method, mathematical formula method, etc. Since the calculation parameters themselves are uncertain, the calculation results are uncertain. For example, the calculation parameters of the volumetric method come from seismic, drilling, geological, logging and other data. These data have multiple solutions, some of which are extrapolated and have measurement errors, which will lead to calculation uncertainty, especially for carbonate fracture-cavity reservoirs. The reservoir is highly heterogeneous and the reservoir description is difficult. In the calculation of geological reserves, there are more uncertain factors in the value of reserve parameters. At present, numerical simulation is mainly used to calculate geological reserves based on the identification of single-well fracture-cavity reservoirs and inter-well reservoir fluid measurement. For fracture-cavity carbonate reservoirs, this aspect of research is still blank. Summary of the invention

[0006] In view of this, an embodiment of the present invention provides a method and system for predicting geological reserves of a single well, which solves the problem of errors and uncertainties in the current method for predicting geological reserves of a single well.

[0007] A single well geological reserve prediction method and system provided by one embodiment of the present invention includes: determining the reservoir type and driving energy type of the single well to be predicted;

[0008] Obtaining recoverable reserves based on the reservoir type and the driving energy type;

[0009] Obtaining producing reserves based on the water-oil ratio of the single well to be predicted;

[0010] The reservoir type, the driving energy type, the recoverable reserves and the producing reserves are input into a neural network prediction model, and the geological reserves of the single well to be predicted are obtained based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves.

[0011] In one embodiment, before the reservoir type, the driving energy type, the recoverable reserves and the producing reserves are input into the neural network prediction model and geological reserves are obtained based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves, the method further includes: establishing a neural network prediction model, including:

[0012] Performing standardized preprocessing on the reservoir type, the driving energy type, the recoverable reserves, the producing reserves and the geological reserves of the single well of the sample unit;

[0013] Based on the result of the standardized preprocessing, the neural network prediction model is established.

[0014] In one embodiment, the reservoir type, the driving energy type, the recoverable reserves and the producing reserves are input into a neural network prediction model, and the geological reserves are obtained based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves, including:

[0015] inputting the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into the neural network prediction model,

[0016] The neural network prediction model performs hyperbolic tangent function processing on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves;

[0017] The neural network prediction model outputs the geological reserves.

[0018] In one embodiment, determining the reservoir type of the single well to be predicted includes: determining that the reservoir type of the single well to be predicted is one of a karst-type reservoir, a fracture-cavity reservoir, and a fracture-type reservoir.

[0019] In one embodiment, determining the driving energy type of the single well to be predicted includes: determining that the driving energy type of the single well to be predicted is one of steady-state water invasion, unsteady-state water invasion and natural energy drive.

[0020] In one embodiment, obtaining recoverable reserves based on the reservoir type and the driving energy type includes:

[0021] The first recoverable reserves are obtained by using the water drive curve method;

[0022] The second recoverable reserves are obtained by using the production decline method;

[0023] The third recoverable reserves are obtained by using the growth curve method;

[0024] The recoverable reserves of the single well to be predicted are obtained by taking an average value of the first recoverable reserves, the second recoverable reserves and the third recoverable reserves.

[0025] In one embodiment, obtaining the producing reserves based on the water-oil ratio of the single well to be predicted includes:

[0026] By means of production dynamic analysis, the total water and oil volume of the single well to be predicted is evaluated;

[0027] Obtaining the water-oil ratio of the single well to be predicted based on iterative calculation of the water-oil ratio and the total volume of water and oil;

[0028] The producing reserves of the single well to be predicted are obtained based on the water-oil ratio of the single well to be predicted.

[0029] In one embodiment, before the reservoir type, the driving energy type, the recoverable reserves, the producing reserves and the geological reserves of the single well of the sample unit are subjected to standardized preprocessing, the process includes: splitting the well-controlled area of ​​the single well of the sample unit to obtain the geological reserves of the single well of the sample unit.

[0030] A single well geological reserve prediction system, comprising:

[0031] A judgment module is used to judge the reservoir type and driving energy type of the single well to be predicted;

[0032] A calculation module, used to obtain recoverable reserves based on the reservoir type and the driving energy type; and to obtain producing reserves based on the water-oil ratio of the single well to be predicted;

[0033] A processing module is used to input the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into a neural network prediction model, and obtain the geological reserves of the single well to be tested based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves.

[0034] In one embodiment, it includes a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein when the one or more computer instructions are executed by the processor, the single well geological reserve prediction method as described in any one of the above items is implemented.

[0035] A computer-readable storage medium stores a computer program, and when the computer program is executed by one or more processors, it is used to implement the single well geological reserve prediction method as described in any one of the above items.

[0036] The embodiment of the present invention provides a single well geological reserve prediction method and system, the single well geological reserve prediction method includes: judging the reservoir type and driving energy type of the single well to be predicted; obtaining recoverable reserves based on the reservoir type and the driving energy type; obtaining producing reserves based on the water-oil ratio of the single well to be predicted; inputting the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into the prediction model, and obtaining the geological reserves of the single well to be predicted based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves. The present invention obtains the geological reserves of the single well to be predicted by combining the recoverable reserves, producing reserves, reservoir type, driving energy type of the single well to be predicted with the neural network prediction model. Compared with the traditional calculation method, it is more reliable and accurate, making the reserve estimation of unknown oil reservoirs more convenient, which can promote cost reduction and improve work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The figure shows a schematic flow chart of a method for predicting geological reserves of a single well provided in one embodiment of the present invention.

[0038] Figure 2 The figure shows a schematic diagram of the process of establishing a neural network prediction model provided by an embodiment of the present invention.

[0039] Figure 3 The figure shows a schematic flow chart of a method for predicting geological reserves of a single well provided by another embodiment of the present invention.

[0040] Figure 4 The figure shows a result diagram of a single well geological reserve system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0042] In view of the problem that the geological parameters in the existing technology are difficult to obtain, the geological reserve prediction of a single well is insufficient. The related existing technology mainly considers the classification of reservoirs, and mainly uses the type D water drive characteristic curve to calculate the well control reserves. However, due to the lack of pertinence in the calculation process, this method still has the problems of low prediction efficiency and low prediction accuracy. In view of the above problems, in addition to judging the reservoir type, the present invention adds the division and discrimination of the development stage and the driving energy type, increases the input parameters, and improves the pertinence and accuracy of the calculation; in terms of the calculation method, the calculation results of the decline curve, the water drive curve and the increase production curve are comprehensively adopted, and the single well reserves prediction of the unknown area is carried out by using the artificial neural network method, which can effectively improve the efficiency and accuracy of the geological reserve prediction of a single well in the reservoir, especially the fracture-cavity carbonate reservoir. The specific method is described in the following embodiment.

[0043] Embodiment 1

[0044] Figure 1 The figure shows a schematic flow chart of a method for predicting geological reserves of a single well provided in one embodiment of the present invention.

[0045] Figure 2 The figure shows a schematic diagram of the process of establishing a neural network prediction model provided by an embodiment of the present invention.

[0046] See also Figure 1 In this embodiment, a single well geological reserve prediction method is provided, comprising:

[0047] Step S101: Determine the reservoir type and driving energy type of the single well to be predicted.

[0048] Among them, the spatial distribution of fracture-cavity oil reservoirs is extremely heterogeneous. By sorting out the dynamic characteristics of single wells in a preset number of sample units and inheriting and absorbing the knowledge of predecessors, qualitatively comparing the differences and differences in the dynamic characteristics of single wells, calculating the pressure characteristics of the reservoirs, dividing their development stages, etc., it is determined that the reservoir types of the single wells to be predicted are roughly divided into: cave-type reservoirs, fracture-cavity reservoirs and fracture-type reservoirs.

[0049] Characteristics of cave reservoirs: Generally, the initial production of a single well is high, with a long water-free oil production period; the production is stable and declines slowly; the water content rises quickly, with step-by-step growth or violent flooding; it is mainly driven by bottom water and has little impact on elastic properties.

[0050] Characteristics of fracture-cavity reservoirs: generally higher initial production; short water-free oil production period; short stable production time, rapid decline; rapid and stable water content increase; mainly driven by bottom water, and elastic performance release cannot be ignored.

[0051] Characteristics of fractured reservoirs: generally low initial production; no water-free production period or a very short one, with rapid production decline; mainly elastic drive, no bottom water drive or weak drive.

[0052] Determining the reservoir type of the single well to be predicted includes determining whether the reservoir type of the single well to be predicted is a karst-type reservoir, a fracture-cavity reservoir, or a fracture-type reservoir.

[0053] Among them, due to the complexity of reservoir combination, extension and distribution and strong heterogeneity of fracture-cavity carbonate reservoirs, the driving energy of different production wells varies greatly. Different driving energy types have different changing rules of the correlation between oil and water. According to the correlation of oil and water changes, it can be roughly judged that the driving energy types during oil and water production include: steady-state water invasion, non-steady-state water invasion and natural energy drive.

[0054] Steady-state water invasion: For fracture-cavity carbonate reservoirs, when energy replenishment is timely and sufficient, and the water source is relatively single, its driving energy type is often steady-state or quasi-steady-state water invasion, and its production well output characteristics are mainly manifested as: relatively stable production changes, linear increase in water content, stable oil and water output, and a good correlation between changes. When the driving energy type of the production well is steady-state water invasion, its stable production time is long, the cumulative production during the stable production period is large, and the production and pressure decrease slowly during the water invasion stage.

[0055] Non-steady-state water invasion: This type of water invasion is often caused by complex reservoir combinations, the presence of many fractures connecting multiple water bodies, different bottom water sources, different supply speeds, and large differences in fracture properties, which leads to untimely energy replenishment during the water supply process and extremely unstable driving of the water body. The output characteristics of its production wells are mainly manifested in: strong production fluctuations, no obvious regularity in water content changes, a large fluctuation-type increase, unstable oil and water output, and no stable change correlation. When the driving energy type of the production well is non-steady-state water invasion, the stable production time is short, the stable production period is short, and the production and pressure decrease rapidly during the water invasion stage.

[0056] Natural energy drive: Since there is no external water body for energy supplement, the closed reservoir is a single reservoir. Its initial production mainly relies on the release of elastic energy of reservoir rocks and reservoirs. The water invasion energy of the reservoir itself is weak. The output characteristics of its production wells are mainly manifested as: no stable production stage, a certain waterless oil production period, irregular changes in water content, large fluctuations, and a certain correlation between oil and water. When the production well driving energy type is natural energy drive, there is no stable production time, and its production and pressure decrease rapidly.

[0057] Determining the driving energy type of the single well to be predicted includes determining whether the driving energy type of the single well to be predicted is steady-state water invasion, unsteady-state water invasion, and natural energy drive.

[0058] Step S102: Obtain recoverable reserves based on the reservoir type and the driving energy type. Using the production data of the single well to be predicted, select the most suitable water drive curve according to the reservoir type and driving energy type discrimination results of the single well to be predicted, automatically sort the production data, and perform fitting calculation on the recoverable reserves by integrating the three methods of water drive curve method, production decline method and growth curve to obtain the final recoverable reserves of the single well to be predicted. Optionally:

[0059] Water drive curve method:

[0060] According to different reservoir types and energy type combinations, a reasonable pre-screening principle is determined in the existing water drive curves, and the water drive curve suitable for each combination is preferably selected:

[0061] Among them, the selection principles of water drive curves include:

[0062] Principle 1: The selected water drive curves must include the water content increase laws of different types of reservoirs.

[0063] Principle 2: The calculation of water drive straight line segment parameters is convenient and quick.

[0064] Principle 3: Since different water drive curves are applicable to different water content stages, water drive curve calculations should be performed in stages.

[0065] According to the above principles, a number of water drive characteristic curves are pre-screened and predicted, and the water drive curve with the largest proportion is selected by calculation as the most suitable water drive curve for this type of combination, and the recoverable reserves of the single well to be predicted are calculated with the most suitable water drive curve.

[0066] The method of diminishing returns:

[0067] As far as the whole process of oil field development is concerned, no matter what type of reservoir or what type of driving energy, the oil and gas field can be divided into three stages: production increase stage, production stability stage and production decline stage. With the deepening and development of development, once any oil field enters the production decline stage, the production decline analysis method can be used to study and analyze the decline type of the oil and gas field, predict the future production changes of the oil and gas field, and determine the recoverable reserves of the oil and gas field. By expanding the existing Aprs decline development model, summarizing a number of decline curves, forming a generalized decline curve formula, and calculating the recoverable reserves with the generalized decline curve formula.

[0068] Growth Curve Method:

[0069] The growth curve is summarized in practical applications. After continuous research and arrangement, it has now formed a relatively complete and systematic reservoir engineering method. It is defined as any function expression that can meet the conditions when t=0, Np=0 and t→∞, Np=NRmax is generally called the growth curve for oilfield development index prediction, where Npmax is the limit cumulative production and t=0 represents the start time of production.

[0070] Corresponding to the identified reservoir type and driving energy type combination, the single well recoverable reserves are calculated by the optimized water drive curve method, production decline method and growth curve method: the first recoverable reserves are obtained by the water drive curve method; the second recoverable reserves are obtained by the production decline method; the third recoverable reserves are obtained by the growth curve method. The first recoverable reserves, the second recoverable reserves and the third recoverable reserves are averaged to obtain the recoverable reserves of the single well to be predicted. After actual calculation, the relative errors of the three algorithms are mostly within 10%, which proves that the algorithm based on type combination has good reliability and high accuracy in recoverable reserves calculation.

[0071] Step S103: Obtaining the producing reserves based on the water-oil ratio of the single well to be predicted. The total water-oil volume of the single well to be predicted is evaluated through production data analysis (PDA), and the water-oil ratio of the single well to be predicted under the conditions of the reservoir type and driving energy type is further determined through iterative calculation of the water-oil ratio, and the water-oil volume is split to calculate the producing reserves of the single well.

[0072] Step S104: Input the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into the neural network prediction model, and obtain the geological reserves of the single well to be predicted based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves. Before inputting the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into the neural network prediction model, the step of establishing the neural network prediction model includes:

[0073] Step 1: Standardize and pre-process the reservoir type, driving energy type, recoverable reserves, producing reserves and geological reserves of the single well of the sample unit. First, determine the reservoir type and driving energy type of each single well of the sample unit respectively; then calculate the recoverable reserves, producing reserves and geological reserves of each single well of the sample unit; the calculation method of the recoverable reserves and producing reserves of the single well has been explained in this embodiment and will not be repeated here.

[0074] The geological reserves of the sample unit can be calculated using the volumetric method. Based on parameters such as oil-bearing area, effective thickness, effective porosity, and original oil saturation, the geological reserves of the sample unit are calculated using the volumetric method. Optionally, an oil reservoir with relatively certain single-well geological data such as effective thickness and effective porosity is used as a single well in the sample unit, and the single well in the sample unit is split by the well control area to obtain the geological reserves of the single well in the sample unit. The principles for splitting the well control area of ​​the single well include: determining the control range of the single well based on half of the well spacing and in combination with the unit boundary; and determining the single well control area based on the percentage of the area of ​​each well in the total area of ​​the unit.

[0075] Step 2: Perform neural network processing with the geological reserves as supervision to establish the prediction model. Geological reserves are essentially related to geological parameters, and intuitively manifested as being related to types. Different reservoir types and different driving energy types correspond to different geological reserves. At the same time, there is a certain correlation between recoverable reserves, producing reserves and geological reserves in terms of values. Therefore, under the premise that the recoverable reserves, producing reserves and geological reserves of a single well in the sample unit have been determined, combined with the reservoir type and driving energy type of the single well, the corresponding relationship of these parameters is analyzed using multi-layer neural network technology to establish a geological reserve prediction model.

[0076] refer to Figure 2 On the basis that the geological reserves of the reservoir or reservoir unit have been determined and the recoverable reserves and producing reserves of a single well have been calculated, combined with the reservoir type and driving energy type of the single well, the multi-layer neural network technology is used to analyze the correspondence of all the above parameters, and a single well geological reserve prediction model for the area where geological data are difficult to obtain (hereinafter referred to as the prediction unit) is established.

[0077] After the neural network prediction model is established, the reservoir type, driving energy type, recoverable reserves and producing reserves of the single well to be predicted are input into the neural network prediction model, and the neural network prediction model performs hyperbolic tangent function processing on the reservoir type, driving energy type, recoverable reserves and producing reserves; finally, the geological reserves of the unit to be predicted are output.

[0078] The embodiment of the present invention provides a single well geological reserve prediction method and system, the single well geological reserve prediction method includes: judging the reservoir type and driving energy type of the single well to be predicted; obtaining recoverable reserves based on the reservoir type and the driving energy type; obtaining producing reserves based on the water-oil ratio of the single well to be predicted; inputting the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into the prediction model, and obtaining the geological reserves of the single well to be predicted based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves. The present invention obtains the geological reserves of the single well to be predicted by combining the recoverable reserves, producing reserves, reservoir type, driving energy type of the single well to be predicted with the neural network prediction model. Compared with the traditional calculation method, it is more reliable and accurate, making the reserve estimation of unknown oil reservoirs more convenient, which can promote cost reduction and improve work efficiency.

[0079] Embodiment 2

[0080] Figure 3 The figure shows a schematic flow chart of a method for predicting geological reserves of a single well provided by another embodiment of the present invention.

[0081] refer to Figure 3 The artificial neural network prediction model described in this embodiment is established based on the actual working data of 203 wells, and is now described using Well S48 as an example. The basic situation of Well S48 is: there are a lot of leakage and emptying phenomena; the well is directly completed by lowering the oil pipe into the open hole; the initial oil pressure is relatively high, and the daily oil production is 400t / d; the water-free period is 1024 days, and the cumulative oil production is 473,000 tons; the water content rises slowly after water is seen, and the average monthly water content rises at a rate of 3.8%. By March 9, 2013, the cumulative oil production reached 730,400 tons, and the water content has reached more than 95%, which has entered the late stage of development. On the basis of Example 1, this embodiment provides another method for predicting the geological reserves of a single well, including:

[0082] Step S201: Identify the reservoir type and energy type of the single well to be predicted.

[0083] In the elastic stage of Well S48, oil was produced without water, and the reservoir pressure gradually expanded to the boundary of the oil body. The oil pressure remained basically unchanged, the production was stable, and the production differential pressure increased rapidly due to the release of elastic energy (0.00164MPa / day); in the mixed drive stage, oil was produced without water, the oil pressure decreased steadily (at a rate of 0.00824MPa / day), the production increased (at a rate of 0.41727 tons / day), and the production differential pressure slowed down due to the exhaustion of elastic energy and the energy replenishment of some edge and bottom water (0.00156MPa / day); in the water invasion drive stage, the water cut began to increase (at a rate of 0.10618% / day), pure edge and bottom water drive, sufficient energy replenishment, stable oil pressure, due to the increase in pressure changes near the wellbore, the bottom water invasion speed increased, the oil pressure fluctuated after breaking through the bottom of the well, and the production decreased due to the increase in water cut (at a rate of 0.77737 tons / day). As the edge and bottom water energy began to be replenished, the production differential pressure began to decrease from a steady change (0.00375MPa / day). The initial production is high, the elastic energy release time is long, the cumulative production in the elastic stage is large, and the elastic release stage decreases slowly. The reservoir type is judged to be cave type. The pressure change is relatively stable, there is a pressure stability section, the pressure decreases slowly, the bottom water drive is the main, the elastic energy has little impact, and the driving energy type is judged to be stable water invasion.

[0084] S202: Obtaining the recoverable reserves of the single well to be predicted based on the reservoir type and energy type of the single well to be predicted:

[0085] ① Calculation by water drive curve method: Well S48 was put into production on October 27, 1997, and the cumulative oil production reached 730,400 tons by March 9, 2013. The water content has reached more than 95%, and it has entered the late stage of development. Six water drive curves were used to calculate recoverable reserves. The result of the first curve was 1.11 million tons, the result of the second curve was 1.91 million tons, the result of the third curve was 1 million tons, the result of the fourth curve was 810,000 tons, the result of the fifth curve was 890,000 tons, and the result of the sixth curve was 992,000 tons. According to the high water content status and cumulative oil production of Well S48, it is judged that the recoverable reserves calculated by the fourth curve are most consistent with the actual situation of the well, that is, 810,000 tons, and the relative error with the cumulative oil production is 4.75%.

[0086] ② Calculation by production decline method: Taking months as time units, the cumulative oil production data of Well S48 was sorted out, and the cumulative oil production data of each month was calculated. The last decreasing section was used as the calculation fitting section. The initial value required by the decreasing method calculation formula was given, and the data was repeatedly fitted. The actual cumulative oil production before the decrease was added to obtain the recoverable reserves of Well S48 of 729,700 tons, with a relative error of -5.63% with the cumulative oil production.

[0087] ③ Growth curve calculation: According to the mathematical rationality, theoretical significance, practical application effect and calculation convenience, the 3Y1 curve is selected for growth curve calculation. After multiple full-segment fitting of the production data of well S48, the highest correlation coefficient is 0.947. At this time, the recoverable reserves are 780,000 tons, and the relative error with the cumulative oil production is 0.88%.

[0088] The recoverable reserves calculated by the three methods were combined, and the average value of 773,230 tons was taken as the recoverable reserves of Well S48.

[0089] Step S203: Calculation of the producing reserves of the single well to be predicted:

[0090] The elastic drive time of Well S48 was from October 27, 1997 to October 30, 1998. During this period, the cumulative oil production was 129,374 tons, and the pressure drop was 0.509 MPa; the mixed drive time was from October 30, 1998 to November 5, 2001. During this period, the cumulative oil production was 452,393 tons, the pressure drop was 1.73 MPa, and the water invasion volume was 15,402 tons; the water invasion drive time was from November 5, 2001 to June 29, 2005. During this period, the cumulative oil production was 58,264 tons, the pressure drop was 0.223 MPa, and the water invasion volume was 67,732 tons. According to the elastic stage, the oil production index J of the elastic stage was calculated to be 253972.8383, and the reserves used were 960,200 tons.

[0091] Calculation of geological reserves of a single well to be predicted:

[0092] Step S204: Predicting the geological reserves of a single well to be predicted based on an artificial neural network:

[0093] By calculating the reservoir type, driving energy type, recoverable reserves, producing reserves and geological reserves of 203 wells, an artificial neural network was established. The reservoir type, driving energy type, recoverable reserves and producing reserves of a single well were standardized and pre-processed, and then imported as the input layer (70% of the wells were sample wells and 30% of the wells were test wells). After being processed by artificial neural network methods such as the hyperbolic tangent function of the hidden layer, the geological reserves were finally used as the output result of the output layer. The error of the prediction result of the artificial neural network model obtained did not exceed ±10%. According to the reservoir type (cavern type), driving energy type (steady-state water invasion), recoverable reserves (773,230 tons) and producing reserves (960,200 tons) of Well S48, the geological reserves predicted by its artificial neural network are 2.5873 million tons.

[0094] In addition, the geological reserves of each unit can be calculated by the volumetric method. Under the condition that the geological reserves of the unit are known, the geological reserves of a single well can be determined by proportion. The area of ​​the S48 unit where the S48 well is located is 15.11 km2, and the geological reserves are 35.53889 million tons. The control range of a single well is determined based on half of the well spacing and combined with the unit boundary, and then the control area of ​​a single well is determined based on the percentage of the area of ​​each well in the total area of ​​the unit. The control radius of the S48 well is 374 m, and the control area is 0.4396 km2. According to the control area, thickness, and porosity of each well, the geological reserves of the S48 well account for 7.09% of the unit, which is 2.483 million tons.

[0095] It can be seen that the geological reserves obtained by the neural network prediction model in step S204 are compared with the geological reserves calculated by the volumetric method, and the error is 4.2%, which reflects the reliability of the neural network prediction model. In the later stage, for the wells of unknown oil reservoirs or units, the reservoir type and driving energy type, recoverable reserves calculation, and producing reserves calculation can be performed through the workflow provided by the present invention to obtain the reservoir type and driving energy type, recoverable reserves, and producing reserves of each well as input data, and the artificial neural network model proposed by the present invention is used to predict the geological reserves of each well. The present invention obtains the geological reserves of the single well to be predicted by combining the recoverable reserves, producing reserves, reservoir type, and driving energy type of the single well to be predicted with the neural network prediction model. Compared with the traditional calculation method, it is more reliable and accurate, making the reserve estimation of unknown oil reservoirs more convenient, which can promote cost reduction and improve work efficiency.

[0096] Embodiment 3

[0097] Figure 4 The figure shows a result diagram of a single well geological reserve system provided by an embodiment of the present invention.

[0098] See also Figure 4 This embodiment provides a single well geological reserve prediction system 100, including a judgment module 10, a calculation module 20 and a processing module 30.

[0099] The judgment module 10 is used to judge the reservoir type and driving energy type of the single well to be predicted;

[0100] The calculation module 20 is used to obtain recoverable reserves based on the reservoir type and the driving energy type; and obtain producing reserves based on the water-oil ratio of the single well to be predicted;

[0101] The processing module 30 is used to input the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into a neural network prediction model, and obtain the geological reserves of the single well to be tested based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves.

[0102] The judgment module 10 judges the reservoir type and driving energy type of the single well to be predicted, and judges that the reservoir type of the single well to be predicted is one of a karst-type reservoir, a fracture-type reservoir and a fracture-type reservoir, and the driving energy type of the single well to be predicted is one of steady-state water invasion, unsteady-state water invasion and natural energy drive. The calculation module 20 calculates the recoverable reserves of the single well to be predicted based on the reservoir type and driving energy type of the single well to be predicted judged by the judgment module 10, and obtains the producing reserves based on the water-oil ratio of the single well to be predicted. The processing module 30 inputs the reservoir type, driving energy type, recoverable reserves and producing reserves of the single well to be predicted into the neural network prediction model, and obtains the geological reserves of the single well to be tested based on the reservoir type, driving energy type, recoverable reserves and producing reserves.

[0103] The method for performing single well geological reserve prediction based on the above modules includes:

[0104] Step S101: Determine the reservoir type and driving energy type of the single well to be predicted.

[0105] Among them, the spatial distribution of fracture-cavity reservoirs is extremely heterogeneous. By combing the dynamic characteristics of single wells in a preset number of sample units, inheriting and absorbing the knowledge of previous work, qualitatively comparing the differences and differences in the dynamic characteristics of single wells, calculating the pressure characteristics of the reservoir, dividing its development stage, etc., it is determined that the reservoir type of the single well to be predicted is roughly divided into: cave reservoir, fracture-cavity reservoir and fracture reservoir. Determining the reservoir type of the single well to be predicted includes determining whether the reservoir type of the single well to be predicted is a cave reservoir, a fracture-cavity reservoir and a fracture reservoir. Determining the driving energy type of the single well to be predicted includes determining whether the driving energy type of the single well to be predicted is steady-state water invasion, unsteady-state water invasion and natural energy drive.

[0106] Step S102: Obtain recoverable reserves based on the reservoir type and the driving energy type. Using the production data of the single well to be predicted, the most suitable water drive curve is selected according to the reservoir type and driving energy type discrimination results of the single well to be predicted, and the production data is automatically sorted. The recoverable reserves are fitted and calculated by integrating the three methods of water drive curve method, production decline method and growth curve to obtain the final recoverable reserves of the single well to be predicted.

[0107] Corresponding to the identified reservoir type and driving energy type combination, the single well recoverable reserves are calculated respectively by the optimal water drive curve method, production decline method and growth curve method: the first recoverable reserves are obtained by the water drive curve method; the second recoverable reserves are obtained by the production decline method; the third recoverable reserves are obtained by the growth curve method. The recoverable reserves of the single well to be predicted are obtained by taking the average of the first recoverable reserves, the second recoverable reserves and the third recoverable reserves.

[0108] Step S103: Obtaining the produced reserves based on the water-oil ratio of the single well to be predicted. The total water-oil volume of the single well to be predicted is evaluated by the PDA method, and the water-oil ratio of the single well to be predicted under the conditions of the reservoir type and driving energy type is further determined by iterative calculation of the water-oil ratio, the water-oil volume is split, and the produced reserves of the single well are calculated.

[0109] Step S104: Input the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into the neural network prediction model, and obtain the geological reserves of the single well to be predicted based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves. Before inputting the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into the neural network prediction model, it includes establishing a neural network prediction model. After the neural network prediction model is established, the reservoir type, driving energy type, recoverable reserves and producing reserves of the single well to be predicted are input into the neural network prediction model, and the neural network prediction model performs hyperbolic tangent function processing on the reservoir type, driving energy type, recoverable reserves and producing reserves; finally, the geological reserves of the unit to be predicted are output.

[0110] Embodiment 4

[0111] This embodiment provides an electronic device, which may be a mobile phone, a computer or a tablet computer, etc., including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the method for predicting the geological reserves of a single well as described in Embodiment 1 is implemented. It is understood that the electronic device may also include an input / output (I / O) interface and a communication component.

[0112] The processor is used to execute all or part of the steps in the single well geological reserve prediction method in Example 1. The memory is used to store various types of data, which may include instructions of any application or method in the electronic device, and data related to the application.

[0113] The processor can be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components, and is used to execute the single well geological reserve prediction method in the above-mentioned embodiment 1.

[0114] The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0115] Embodiment 5

[0116] This embodiment also provides a computer-readable storage medium. Each functional unit in each embodiment of the present invention may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.

[0117] Based on such understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0118] The aforementioned storage media include: flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, server, APP application mall, etc. Various media that can store program check codes, on which a computer program is stored, and when the computer program is executed by a processor, the following method steps can be implemented:

[0119] Step S101: Determine the reservoir type and driving energy type of the single well to be predicted.

[0120] Among them, the spatial distribution of fracture-cavity oil reservoirs is extremely heterogeneous. By sorting out the dynamic characteristics of single wells in a preset number of sample units and inheriting and absorbing the knowledge of predecessors, qualitatively comparing the differences and differences in the dynamic characteristics of single wells, calculating the pressure characteristics of the reservoirs, dividing their development stages, etc., it is determined that the reservoir types of the single wells to be predicted are roughly divided into: cave-type reservoirs, fracture-cavity reservoirs and fracture-type reservoirs.

[0121] Characteristics of cave reservoirs: Generally, the initial production of a single well is high, with a long water-free oil production period; the production is stable and declines slowly; the water content rises quickly, with step-by-step growth or violent flooding; it is mainly driven by bottom water and has little impact on elastic properties.

[0122] Characteristics of fracture-cavity reservoirs: generally higher initial production; short water-free oil production period; short stable production time, rapid decline; rapid and stable water content increase; mainly driven by bottom water, and elastic performance release cannot be ignored.

[0123] Characteristics of fractured reservoirs: generally low initial production; no water-free production period or a very short one, with rapid production decline; mainly elastic drive, no bottom water drive or weak drive.

[0124] Determining the reservoir type of the single well to be predicted includes determining whether the reservoir type of the single well to be predicted is a karst-type reservoir, a fracture-cavity reservoir, or a fracture-type reservoir.

[0125] Among them, due to the complexity of reservoir combination, extension and distribution and strong heterogeneity of fracture-cavity carbonate reservoirs, the driving energy of different production wells varies greatly. Different driving energy types have different changing rules of the correlation between oil and water. According to the correlation of oil and water changes, it can be roughly judged that the driving energy types during oil and water production include: steady-state water invasion, non-steady-state water invasion and natural energy drive.

[0126] Steady-state water invasion: For fracture-cavity carbonate reservoirs, when energy replenishment is timely and sufficient, and the water source is relatively single, its driving energy type is often steady-state or quasi-steady-state water invasion, and its production well output characteristics are mainly manifested as: relatively stable production changes, linear increase in water content, stable oil and water output, and a good correlation between changes. When the driving energy type of the production well is steady-state water invasion, its stable production time is long, the cumulative production during the stable production period is large, and the production and pressure decrease slowly during the water invasion stage.

[0127] Non-steady-state water invasion: This type of water invasion is often caused by complex reservoir combinations, the presence of many fractures connecting multiple water bodies, different bottom water sources, different supply speeds, and large differences in fracture properties, which leads to untimely energy replenishment during the water supply process and extremely unstable driving of the water body. The output characteristics of its production wells are mainly manifested in: strong production fluctuations, no obvious regularity in water content changes, a large fluctuation-type increase, unstable oil and water output, and no stable change correlation. When the driving energy type of the production well is non-steady-state water invasion, the stable production time is short, the stable production period is short, and the production and pressure decrease rapidly during the water invasion stage.

[0128] Natural energy drive: Since there is no external water body for energy supplement, the closed reservoir is a single reservoir. Its initial production mainly relies on the release of elastic energy of reservoir rocks and reservoirs. The water invasion energy of the reservoir itself is weak. The output characteristics of its production wells are mainly manifested as: no stable production stage, a certain waterless oil production period, irregular changes in water content, large fluctuations, and a certain correlation between oil and water. When the production well driving energy type is natural energy drive, there is no stable production time, and its production and pressure decrease rapidly.

[0129] Determining the driving energy type of the single well to be predicted includes determining whether the driving energy type of the single well to be predicted is steady-state water invasion, unsteady-state water invasion, and natural energy drive.

[0130] Step S102: Obtain recoverable reserves based on the reservoir type and the driving energy type. Using the production data of the single well to be predicted, select the most suitable water drive curve according to the reservoir type and driving energy type discrimination results of the single well to be predicted, automatically sort the production data, and perform fitting calculation on the recoverable reserves by integrating the three methods of water drive curve method, production decline method and growth curve to obtain the final recoverable reserves of the single well to be predicted. Optionally:

[0131] Water drive curve method:

[0132] According to different reservoir types and energy type combinations, a reasonable pre-screening principle is determined in the existing water drive curves, and the water drive curve suitable for each combination is preferably selected:

[0133] Among them, the selection principles of water drive curves include:

[0134] Principle 1: The selected water drive curves must include the water content increase laws of different types of reservoirs.

[0135] Principle 2: The calculation of water drive straight line segment parameters is convenient and quick.

[0136] Principle 3: Since different water drive curves are applicable to different water content stages, water drive curve calculations should be performed in stages.

[0137] According to the above principles, a number of water drive characteristic curves are pre-screened and predicted, and the water drive curve with the largest proportion is selected by calculation as the most suitable water drive curve for this type of combination, and the recoverable reserves of the single well to be predicted are calculated with the most suitable water drive curve.

[0138] The method of diminishing returns:

[0139] As far as the whole process of oil field development is concerned, no matter what type of reservoir or what type of driving energy, the oil and gas field can be divided into three stages: production increase stage, production stability stage and production decline stage. With the deepening and development of development, once any oil field enters the production decline stage, the production decline analysis method can be used to study and analyze the decline type of the oil and gas field, predict the future production changes of the oil and gas field, and determine the recoverable reserves of the oil and gas field. This part expands the existing Aprs decline, summarizes a number of decline curves, forms a generalized decline curve formula, and calculates recoverable reserves using the generalized decline curve formula.

[0140] Growth Curve Method:

[0141] The growth curve is summarized in practical applications. After continuous research and arrangement, it has now formed a relatively complete and systematic reservoir engineering method. It is defined as any function expression that can meet the conditions when t=0, Np=0 and when t→∞, Np=NRmax is generally called the growth curve for predicting oilfield development indicators.

[0142] Corresponding to the identified reservoir type and driving energy type combination, the single well recoverable reserves are calculated by the optimized water drive curve method, production decline method and growth curve method: the first recoverable reserves are obtained by the water drive curve method; the second recoverable reserves are obtained by the production decline method; the third recoverable reserves are obtained by the growth curve method. The first recoverable reserves, the second recoverable reserves and the third recoverable reserves are averaged to obtain the recoverable reserves of the single well to be predicted. After actual calculation, the relative errors of the three algorithms are mostly within 10%, which proves that the algorithm based on type combination has good reliability and high accuracy in recoverable reserves calculation.

[0143] Step S103: Obtaining the produced reserves based on the water-oil ratio of the single well to be predicted. The total water-oil volume of the single well to be predicted is evaluated by the PDA method, and the water-oil ratio of the single well to be predicted under the conditions of the reservoir type and driving energy type is further determined by iterative calculation of the water-oil ratio, the water-oil volume is split, and the produced reserves of the single well are calculated.

[0144] Step S104: Input the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into the neural network prediction model, and obtain the geological reserves of the single well to be predicted based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves. Before inputting the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into the neural network prediction model, the step of establishing the neural network prediction model includes:

[0145] Step 1: Standardize and pre-process the reservoir type, driving energy type, recoverable reserves, producing reserves and geological reserves of a single well in a sample unit.

[0146] First, the reservoir type and driving energy type of each single well in the sample unit are determined respectively; then the recoverable reserves, producing reserves and geological reserves of each single well in the sample unit are determined; the calculation method of the recoverable reserves and producing reserves of the single well has been explained in this embodiment and will not be repeated here.

[0147] The geological reserves of the sample unit can be calculated using the volumetric method. Based on parameters such as oil-bearing area, effective thickness, effective porosity, and original oil saturation, the geological reserves of the sample unit are calculated using the volumetric method. Optionally, an oil reservoir with relatively certain single-well geological data such as effective thickness and effective porosity is used as a single well in the sample unit, and the single well in the sample unit is split by the well control area to obtain the geological reserves of the single well in the sample unit. The principles for splitting the well control area of ​​the single well include: determining the control range of the single well based on half of the well spacing and in combination with the unit boundary; and determining the single well control area based on the percentage of the area of ​​each well in the total area of ​​the unit.

[0148] Step 2: Perform neural network processing with the geological reserves as supervision to establish the prediction model.

[0149] Geological reserves are essentially related to geological parameters, and intuitively manifested as being related to types. Different reservoir types and different driving energy types correspond to different geological reserves. At the same time, there is a certain correlation between recoverable reserves, producing reserves and geological reserves in terms of values. Therefore, under the premise that the recoverable reserves, producing reserves and geological reserves of a single well in the sample unit have been determined, combined with the reservoir type and driving energy type of a single well, the corresponding relationship of these parameters is analyzed using multi-layer neural network technology to establish a geological reserve prediction model.

[0150] On the basis that the geological reserves of the reservoir or reservoir unit have been determined and the recoverable reserves and producing reserves of a single well have been calculated, combined with the reservoir type and driving energy type of the single well, the multi-layer neural network technology is used to analyze the correspondence of all the above parameters, and a single well geological reserve prediction model for the area where geological data are difficult to obtain (hereinafter referred to as the prediction unit) is established.

[0151] After the neural network prediction model is established, the reservoir type, driving energy type, recoverable reserves and producing reserves of the single well to be predicted are input into the neural network prediction model, and the neural network prediction model performs hyperbolic tangent function processing on the reservoir type, driving energy type, recoverable reserves and producing reserves; finally, the geological reserves of the unit to be predicted are output.

[0152] The embodiment of the present invention provides a single well geological reserve prediction method and system, the single well geological reserve prediction method includes: judging the reservoir type and driving energy type of the single well to be predicted; obtaining recoverable reserves based on the reservoir type and the driving energy type; obtaining producing reserves based on the water-oil ratio of the single well to be predicted; inputting the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into the prediction model, and obtaining the geological reserves of the single well to be predicted based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves. The present invention obtains the geological reserves of the single well to be predicted by combining the recoverable reserves, producing reserves, reservoir type, driving energy type of the single well to be predicted with the neural network prediction model. Compared with the traditional calculation method, it is more reliable and accurate, making the reserve estimation of unknown oil reservoirs more convenient, which can promote cost reduction and improve work efficiency.

[0153] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0154] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0155] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0156] The block diagrams of devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems may be connected, arranged, or configured in any manner.

[0157] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0158] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0159] In the description of the application, the meaning of "multiple" is at least two, for example, two, three, etc., unless otherwise clearly and specifically limited. In the embodiment of the present application, all directional indications (such as up, down, left, right, front, back, top, bottom ...) are only used to explain the relative position relationship, motion conditions, etc. between the components under a certain specific posture (as shown in the drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their deformations are intended to cover non-exclusive inclusions. For example, the process, method, system, product or equipment comprising a series of steps or units are not limited to the steps or units listed, but optionally also include the steps or units not listed, or optionally also include other steps or units inherent to these processes, methods, products or equipment.

[0160] In addition, the reference to "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0161] The above is only a specific implementation of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims. The above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0162] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, etc. 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 geological reserves of a single well, characterized in that: include: Determine the reservoir type and driving energy type of the single well to be predicted; Obtaining recoverable reserves based on the reservoir type and the driving energy type; Obtaining producing reserves based on the water-oil ratio of the single well to be predicted; Inputting the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into a trained neural network prediction model, and obtaining the geological reserves of the single well to be predicted based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves; Wherein, obtaining recoverable reserves based on the reservoir type and the driving energy type includes: The first recoverable reserves are obtained by using the water drive curve method; The second recoverable reserves are obtained by using the production decline method; The third recoverable reserves are obtained by using the growth curve method; Taking an average value of the first recoverable reserves, the second recoverable reserves and the third recoverable reserves to obtain the recoverable reserves of the single well to be predicted; The produced reserves obtained based on the water-oil ratio of the single well to be predicted include: The total volume of water and oil in the single well to be predicted is evaluated by production dynamic analysis method; Obtaining the water-oil ratio of the single well to be predicted based on iterative calculation of the water-oil ratio and the total volume of water and oil; Obtaining the producing reserves of the single well to be predicted based on the water-oil ratio of the single well to be predicted; Inputting the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into a training neural network prediction model, and obtaining geological reserves based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves includes: inputting the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into the neural network prediction model, The neural network prediction model performs hyperbolic tangent function processing on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves; The neural network prediction model outputs the geological reserves.

2. The single well geological reserve prediction method according to claim 1, characterized in that: Before the reservoir type, the driving energy type, the recoverable reserves and the producing reserves are input into the trained neural network prediction model and geological reserves are obtained based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves, the neural network prediction model is established by the following steps: Performing standardized preprocessing on the reservoir type, the driving energy type, the recoverable reserves, the producing reserves and the geological reserves of the single well of the sample unit; Based on the result of the standardized preprocessing, the neural network prediction model is established.

3. The single well geological reserve prediction method according to claim 1, characterized in that: Determining the reservoir type of the single well to be predicted includes: determining that the reservoir type of the single well to be predicted is one of a karst-type reservoir, a fracture-cavity reservoir, and a fracture-type reservoir.

4. The single well geological reserve prediction method according to claim 1, characterized in that: Determining the driving energy type of the single well to be predicted includes: determining that the driving energy type of the single well to be predicted is one of steady-state water invasion, unsteady-state water invasion and natural energy drive.

5. The single well geological reserve prediction method according to claim 1, characterized in that: Before the reservoir type, the driving energy type, the recoverable reserves, the producing reserves and the geological reserves of the single well of the sample unit are subjected to standardized preprocessing, the method includes: splitting the well-controlled area of ​​the single well of the sample unit to obtain the geological reserves of the single well of the sample unit.

6. A single well geological reserve prediction system for implementing the single well geological reserve prediction method according to any one of claims 1 to 5, characterized in that: include: A judgment module is used to judge the reservoir type and driving energy type of the single well to be predicted; A calculation module, used for obtaining recoverable reserves based on the reservoir type and the driving energy type; Obtaining producing reserves based on the water-oil ratio of the single well to be predicted; A processing module is used to input the reservoir type, the driving energy type, the recoverable reserves and the producing reserves into a neural network prediction model, and obtain the geological reserves of the single well to be predicted based on the reservoir type, the driving energy type, the recoverable reserves and the producing reserves.

7. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein when the one or more computer instructions are executed by the processor, the single well geological reserve prediction method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by one or more processors, it is used to implement the single well geological reserve prediction method according to any one of claims 1 to 5.

Images