CN114718556A - Method, Apparatus and Equipment for Obtaining Artificial Fracture Parameters - Google Patents

Abstract

The present application discloses a method, device and equipment for obtaining parameters of artificial fractures. The method includes obtaining a shale gas well model; obtaining an initial probability distribution of parameters of artificial fractures in the shale gas well model; and obtaining a plurality of first samples based on the initial probability distribution parameters; obtaining multiple second sample parameters based on the shale gas well model, multiple first sample parameters and reference fitting errors; obtaining target artificial fracture parameters based on multiple second sample parameters and the shale gas well model. The method can reduce the manual workload in the process of obtaining artificial fracture parameters, and improve the accuracy of the results obtained by artificial fracture parameters.

Description

Method, Apparatus and Equipment for Obtaining Artificial Fracture Parameters

technical field

The embodiments of the present application relate to the technical field of shale gas well exploitation, and in particular, to a method, device, and equipment for obtaining parameters of artificial fractures.

Background technique

Shale gas is a man-made gas reservoir, and large-scale hydraulic fracturing is required to form artificial fractures during exploitation. The productivity of shale gas wells is closely related to artificial fractures. The core step in evaluating the productivity of shale gas wells is to obtain artificial fracture parameters.

In the related art, the shale gas well model is established, and the artificial fracture parameters are continuously modified artificially, and the calculation results of the model are used to fit the actual production indicators of the gas well, such as gas production and liquid production. If it is very close, it is considered that the artificial fracture parameters in the model are in line with the real situation of shale gas wells, so as to obtain the artificial fracture parameters.

However, since there are too many factors affecting the productivity of shale gas wells, the relative technology relies heavily on manual parameter adjustment, which will cause great uncertainty in the fitting results, resulting in low accuracy of the acquired artificial fracture parameters; in addition, due to the large number of samples , the workload of manual parameter adjustment is huge, so the related technology is not suitable for the actual situation, and the efficiency is low.

SUMMARY OF THE INVENTION

The embodiments of the present application provide a method, device, and equipment for acquiring parameters of artificial fractures, which are used to reduce the manual workload in the process of acquiring parameters of artificial fractures, and improve the accuracy of the results of acquiring parameters of artificial fractures.

In a first aspect, an embodiment of the present application provides a method for obtaining parameters of artificial fractures, the method includes: obtaining a shale gas well model; obtaining an initial probability distribution of parameters of artificial fractures in the shale gas well model; multiple first sample parameters; multiple second sample parameters are obtained based on the shale gas well model, multiple first sample parameters and reference fitting errors; target artificial fracture parameters are obtained based on multiple second sample parameters and the shale gas well model .

In a possible implementation manner, acquiring the first sample parameters based on the initial probability distribution includes: performing random sampling in the initial probability distribution by using a Markov Chain Monte Carlo method to obtain multiple first sample parameters.

In a possible implementation manner, acquiring a plurality of second sample parameters based on a shale gas well model, a plurality of first sample parameters, and a reference fitting error includes: based on a plurality of first sample parameters and a shale gas well model Obtain a plurality of first sample models; obtain a plurality of first fitting errors through a historical fitting error function based on the plurality of first sample models; establish a first fitting error based on the plurality of first sample parameters and the plurality of first fitting errors; a surrogate model; a plurality of second sample parameters are obtained based on the first surrogate model and the reference fitting error.

In a possible implementation manner, establishing the first surrogate model based on the multiple first sample models and the multiple first fitting errors includes: passing the multiple first sample parameters and the multiple first fitting errors through K-nearest neighbor classification KNN algorithm establishes a second surrogate model; based on the second surrogate model, multiple third sample parameters are obtained through the Markov chain Monte Carlo method; based on multiple third sample parameters and the history fitting error function, the second surrogate model is The surrogate model is iterated to obtain a first surrogate model.

In a possible implementation manner, iterating the second surrogate model based on the plurality of third sample parameters and the historical fitting error function to obtain the first surrogate model includes: based on the plurality of third sample parameters and the historical fitting error The function iterates the second surrogate model, and takes the iterated second surrogate model that meets the first condition as the first surrogate model, and the first condition is the fitting error obtained by the reference number of third sample parameters through the historical fitting error function The difference from the fitting error obtained by the iterated second surrogate model is less than the reference threshold.

In a possible implementation manner, acquiring a plurality of second sample parameters based on the first surrogate model and the reference fitting error includes: acquiring, based on the first surrogate model, a plurality of sample parameters that satisfy the reference fitting error, which will satisfy the reference fitting error. The multiple sample parameters of the combined error are used as multiple second sample parameters.

In a possible implementation manner, obtaining target artificial fracture parameters based on multiple second sample parameters and a shale gas well model includes: obtaining a target probability distribution of artificial fracture parameters based on multiple second sample parameters; The shale gas well model inverts the target artificial fracture parameters to obtain the target artificial fracture parameters.

In a possible implementation manner, the artificial fracture parameters include at least one of the length of the artificial fracture, the fracture height of the artificial fracture, the water saturation of the artificial fracture, the width of the artificial fracture, and the conductivity of the artificial fracture .

In the method for obtaining artificial fracture parameters provided by the embodiments of the present application, the initial probability distribution of artificial fracture parameters is obtained, and a plurality of first sample parameters are obtained based on the probability distribution, and the first sample parameters are further iterated and optimized to obtain The more representative second sample parameters, and then the artificial fracture parameters are obtained based on the second sample parameters, so that the final obtained artificial fracture parameters are more accurate, effectively solving the current shale gas well artificial fracture parameters cannot be accurately obtained and manual work. volume problem.

In a second aspect, an embodiment of the present application provides a device for obtaining parameters of artificial fractures, the device comprising: a first obtaining module for obtaining a shale gas well model; a second obtaining module for obtaining artificial fractures in the shale gas well model The initial probability distribution of fracture parameters; the third acquisition module is used to acquire multiple first sample parameters based on the initial probability distribution; the fourth acquisition module is used to acquire multiple first sample parameters based on the shale gas well model, multiple first sample parameters and reference The fitting error obtains a plurality of second sample parameters; the fifth obtaining module is used for obtaining target artificial fracture parameters based on the plurality of second sample parameters and the shale gas well model.

In a possible implementation manner, the third obtaining module is configured to perform random sampling through the Markov Chain Monte Carlo method in the initial probability distribution to obtain a plurality of first sample parameters.

In a possible implementation manner, a fourth acquisition module is configured to acquire a plurality of first sample models based on a plurality of first sample parameters and a shale gas well model; and perform history matching based on the plurality of first sample models The error function obtains a plurality of first fitting errors; establishes a first surrogate model based on the plurality of first sample parameters and the plurality of first fitting errors; obtains a plurality of second sample parameters based on the first surrogate model and the reference fitting errors .

In a possible implementation manner, the fourth acquisition module is configured to establish a second surrogate model through the K-nearest neighbor classification KNN algorithm based on a plurality of first sample parameters and a plurality of first fitting errors; based on the second surrogate model A plurality of third sample parameters are obtained through the Markov chain Monte Carlo method; the second surrogate model is iterated based on the plurality of third sample parameters and the historical fitting error function to obtain a first surrogate model.

In a possible implementation manner, the fourth acquisition module is configured to iterate the second surrogate model based on the plurality of third sample parameters and the historical fitting error function, and obtain the iterated second surrogate model that meets the first condition As the first surrogate model, the first condition is that the difference between the fitting errors obtained by the reference number of third sample parameters through the historical fitting error function and the fitting errors obtained through the iterated second surrogate model is smaller than the reference threshold.

In a possible implementation manner, a fourth obtaining module is configured to obtain a plurality of sample parameters satisfying the reference fitting error based on the first surrogate model, and use the plurality of sample parameters satisfying the reference fitting error as a plurality of first surrogate models. Two sample parameters.

In a possible implementation manner, the fifth acquisition module is configured to acquire the target probability distribution of artificial fracture parameters based on the plurality of second sample parameters; perform inversion of the target artificial fracture parameters based on the target probability distribution and the shale gas well model, Obtain the target artificial fracture parameters.

In a possible implementation manner, the target artificial fracture parameters include at least one of the length of the artificial fracture, the fracture height of the artificial fracture, the water saturation of the artificial fracture, the width of the artificial fracture, and the conductivity of the artificial fracture.

In a third aspect, an embodiment of the present application provides a computer device, the computer device includes a processor and a memory, the memory stores at least one instruction, and when the at least one instruction is executed by the processor, implements any one of the first aspect above. Methods of obtaining artificial fracture parameters.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, where at least one instruction is stored in the computer-readable storage medium, and the at least one instruction implements the artificial crack parameter described in any one of the first aspect above when executed. method of obtaining.

In a fifth aspect, an embodiment of the present application provides a computer program (product), the computer program (product) comprising: computer program code, when the computer program code is run by a computer, the computer is made to perform the above aspects. The method of obtaining artificial fracture parameters in .

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the drawings that are used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative effort.

1 is a flowchart of a method for obtaining artificial fracture parameters provided by an embodiment of the present application;

Fig. 2 is a kind of shale gas well model provided by the embodiment of the present application;

Fig. 3 is a kind of shale gas well model provided by the embodiment of the present application;

Fig. 4 is a screening result of a second sample model provided by the embodiment of the present application;

FIG. 5 is a screening result of a second sample model provided by an embodiment of the present application;

FIG. 6 is a screening result of a second sample model provided by an embodiment of the present application;

7 is a screening result of a second sample model provided by an embodiment of the present application;

8 is a screening result of a second sample model provided by an embodiment of the present application;

FIG. 9 is a screening result of a second sample model provided by an embodiment of the present application;

FIG. 10 is a visual inversion result provided by an embodiment of the present application;

FIG. 11 is a visual inversion result provided by an embodiment of the present application;

FIG. 12 is a visual inversion result provided by an embodiment of the present application;

FIG. 13 is a visual inversion result provided by an embodiment of the present application;

FIG. 14 is a visual inversion result provided by an embodiment of the present application;

FIG. 15 is a visual inversion result provided by an embodiment of the present application;

FIG. 16 is a visual inversion result provided by an embodiment of the present application;

FIG. 17 is a visual inversion result provided by an embodiment of the present application;

FIG. 18 is a visual inversion result provided by an embodiment of the present application;

FIG. 19 is a visual inversion result provided by an embodiment of the present application;

FIG. 20 is a visual inversion result provided by an embodiment of the present application;

FIG. 21 is a visual inversion result provided by an embodiment of the present application;

FIG. 22 is a visual inversion result provided by an embodiment of the present application;

FIG. 23 is a visual inversion result provided by an embodiment of the present application;

FIG. 24 is a visual inversion result provided by an embodiment of the present application;

FIG. 25 is a visual inversion result provided by an embodiment of the present application;

FIG. 26 is a visual inversion result provided by an embodiment of the present application;

FIG. 27 is a visual inversion result provided by an embodiment of the present application;

FIG. 28 is a visual inversion result provided by an embodiment of the present application;

FIG. 29 is a visual inversion result provided by an embodiment of the present application;

FIG. 30 is a schematic diagram of a device for acquiring parameters of an artificial fracture provided by an embodiment of the present application.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

Please refer to FIG. 1 , which shows a flowchart of a method for acquiring parameters of artificial fractures provided by an embodiment of the present application. The method provided by the embodiment of the present application may include the following steps:

Step 101, obtaining a shale gas well model.

The shale gas well model refers to a gas-liquid two-phase model of a shale gas multi-stage fracturing horizontal well. The model includes fluid flows in two phases. Optionally, the fluids in the two phases can be natural gas and formation water.

In a possible implementation manner, a shale gas well model is established according to the existing information of the shale gas well, and the shale gas well model is obtained. Among them, the existing information of shale gas wells includes information of existing geology, gas reservoirs, fluids, fractures, and wells.

Exemplarily, the shale gas well model is established according to the existing information of the shale gas well, including but not limited to the following sub-steps 1011-1012:

1011. Establish artificial fractures of shale gas wells.

In a possible implementation, artificial fractures of shale gas wells are established by using embedded discrete fracture model (EDFM).

1012. Based on the artificial fracture, establish a shale gas well model according to the existing information of the shale gas well, and obtain a shale gas well model.

In a possible implementation manner, based on artificial fractures, a gas-liquid two-phase numerical model of shale gas wells is established according to the existing information of shale gas wells, and the gas-liquid two-phase numerical model of rock gas wells is used as a shale gas well model.

In another possible implementation manner, based on artificial fractures, a gas-liquid two-phase simulation model of shale gas wells is established according to the existing information of shale gas wells, and the gas-liquid two-phase simulation model of rock gas wells is used as a shale gas well model.

In order to make the shale gas well model closer to the real situation of the shale gas well, in any of the above implementation manners, natural fractures can also be added to the shale gas well model, and the natural fractures can be established by the embedded discrete fracture technology.

Please refer to FIG. 2 , which is a shale gas well model provided by an embodiment of the present application. As shown in FIG. 2 , in this embodiment, based on artificial fractures, a gas-liquid two-phase simulation model of a shale gas well is established as a shale gas well model according to the existing information of the shale gas well. The simulation model includes information such as wellbore length, perforation position, and basic fracture shape, but does not include the distribution information of natural fractures.

Optionally, the shale gas well model may also include natural fractures. Please refer to FIG. 3 , which is a shale gas well model provided by an embodiment of the present application. As shown in FIG. 3 , in this embodiment, based on artificial fractures, a shale gas well gas-liquid two-phase simulation model is established as a shale gas well model according to the existing information of the shale gas well, wherein the shale gas well gas-liquid two-phase The simulation model also includes information on the distribution of natural fractures. Optionally, the distribution information of natural fractures is obtained by stochastic simulation.

Step 102: Obtain the initial probability distribution of artificial fracture parameters in the shale gas well model.

The shale gas well model includes deterministic parameters and uncertain parameters. The deterministic parameters include horizontal well length, number of perforation clusters, reservoir length, reservoir width, reservoir thickness, and matrix permeability. Uncertain parameters include artificial The length of the fracture, the fracture height value of the artificial fracture, the water saturation of the artificial fracture, the width of the artificial fracture, and the conductivity coefficient of the artificial fracture, etc., the uncertain parameters are the artificial fracture parameters in the embodiment of the present application.

In a possible implementation manner, obtaining the initial probability distribution of the artificial fracture parameters in the shale gas well model includes: initially setting the deterministic parameters and artificial fracture parameters of the shale gas well model, and obtaining the numerical value of the deterministic parameters and the artificial fracture parameters. The initial probability distribution of the parameters.

Among them, the deterministic parameter values are fixed model parameter values, which can be set as empirical values. For the initial setting of artificial fracture parameters, a prior distribution can be assigned to the artificial fracture parameters to obtain the initial probability distribution of the artificial fracture parameters.

Prior distribution refers to predicting a probability distribution for the target sample based on other relevant parameters before testing or sampling. Optionally, in this embodiment, a random and uniform estimated probability distribution is assigned to the artificial fracture parameters as the distribution of initial sampling.

Optionally, if the shale gas well model also includes natural fractures, the natural fracture parameters are deterministic parameters in the shale gas well model, and in this embodiment of the present application, a set of fixed parameter combinations may also be used to initially set the natural fracture parameters. .

Step 103: Acquire a plurality of first sample parameters based on the initial probability distribution.

In a possible implementation manner, the initial probability distribution of artificial fractures is sampled, and multiple artificial fracture parameters obtained by sampling are used as the first sample parameters.

Optionally, random sampling may be performed in the initial probability distribution through the Markov Chain Monte Carlo method to obtain a plurality of first sample parameters. The Markov Chain Monte Carlo method is a method of computer simulation and sampling under the framework of Bayesian theory.

Optionally, a plurality of first sample parameters can also be obtained by sampling from the initial probability distribution by using the Latin hypercube sampling method in the orthogonal experiment. The Latin hypercube sampling method can make the first sample parameters evenly distributed in the high-dimensional space, so as to ensure the unbiased sampling. Optionally, the number of the first sample parameters may be appropriately adjusted according to the number of artificial fracture parameters, which is not limited in this embodiment of the present invention.

Step 104 , obtain a plurality of second sample parameters based on the shale gas well model, the plurality of first sample parameters, and the reference fitting error.

Due to the inaccuracy of the first sample parameters, directly using the first sample parameters to obtain the artificial fracture parameters will result in a large error in the results. The rock and gas well model and the reference fitting error are used to obtain more representative and accurate second sample parameters.

In a possible implementation manner, acquiring a plurality of second sample parameters based on a shale gas well model, a plurality of first sample parameters, and a reference fitting error includes the following steps.

1041. Acquire a plurality of first sample models based on the plurality of first sample parameters and the shale gas well model.

In a possible implementation manner, acquiring multiple first sample models based on multiple first sample parameters and the shale gas well model includes: inputting multiple first sample parameters into the shale gas well model to obtain multiple first sample parameters For the multiple shale gas well models corresponding to the first sample parameters, the multiple shale gas well models corresponding to the multiple first sample parameters are used as the first sample models. Wherein, the first sample parameters are in one-to-one correspondence with the first sample models.

For example, the first sample parameter is used as the input parameter of the reservoir simulator, and the first sample model is obtained according to the shale gas well model combined with the embedded discrete fracture preprocessor.

1042. Obtain a plurality of first fitting errors by using a history fitting error function based on the plurality of first sample models.

The history fit error function is used to evaluate the accuracy of the sample model. Optionally, define the history fitting error function according to the following formula:

Among them, i is the sequence of actual data points, j is the sequence of historical fitting objective functions, n is the number of actual points, m is the number of historical fitting objective functions, x _{ij, model} represents the simulation result of the model, that is, the first sample Model, x _{ij, history} is the actual production data, NF _j is the normalized value, defined as the maximum difference between the simulation result and the actual production data, w _ij represents the weight of the historical fitting data.

The first fitting error corresponding to each first sample model is obtained by calculating the historical fitting error function based on the plurality of first sample models. It can be seen from the foregoing that the first sample parameters correspond to the first sample models one-to-one, and therefore, the first sample parameters also correspond to the first fitting errors one-to-one.

1043. Establish a first surrogate model based on the plurality of first sample parameters and the plurality of first fitting errors.

In a possible implementation manner, establishing a first surrogate model based on multiple first sample parameters and the multiple first fitting errors includes the following steps.

10431. Establish a second surrogate model by using the K-nearest neighbor classification KNN algorithm based on the plurality of first sample parameters and the plurality of first fitting errors.

Optionally, based on a plurality of first sample parameters and a plurality of first fitting errors, the K nearest neighbor classification algorithm (k-Nearest Neighbor, KNN) is used to train the data, and the first fitting errors and the first sample parameters that characterize the first fitting error are established. the second agent model. Wherein, the first sample parameter is input as an independent variable based on the second surrogate model, and the first fitting error is output as a dependent variable of the second surrogate model, so as to train the data to generate the second surrogate model.

Further optionally, the basic concept of the K-nearest neighbor classification algorithm is shown in the following formula:

θ _i is the uncertainty parameter combination of the k nearest observation points, namely k first sample parameters, i represents each first sample parameter, y(θ _i ) is the target variable value of the k nearest observation points, That is, the first fitting error corresponding to the first sample parameter of the k nearest observation points, θ ₀ is the uncertainty parameter combination, that is, the sample parameter as the independent variable, and y(θ ₀ ) is the target variable that needs to be predicted value, which is the fitting error as the dependent variable.

The KNN algorithm can effectively ensure that the obtained target variable value is more representative in the high-dimensional spatial distribution. At the same time, unlike the polynomial algorithm, the KNN algorithm does not have the problem of overfitting. In addition, the KNN algorithm can ensure the efficiency of calculation, and its calculation time can be increased by 5-20 times compared with other algorithms.

10432: Obtain a plurality of third sample parameters through the Markov chain Monte Carlo method based on the second surrogate model.

Based on the second surrogate model, a Markov chain Monte Carlo method can be used to regenerate a large number of sample parameters, and the sample parameters can be used as the third sample parameters.

10433. Iterate the second surrogate model based on the plurality of third sample parameters and the history fitting error function to obtain the first surrogate model.

In a possible implementation manner, iterating the second surrogate model based on the plurality of third sample parameters and the historical fitting error function to obtain the first surrogate model includes: based on the plurality of third sample parameters and the historical fitting error The function iterates the second surrogate model, and takes the iterated second surrogate model that meets the first condition as the first surrogate model. The first condition is that the difference between the fitting error obtained by the historical fitting error function for the reference number of third sample parameters and the fitting error obtained by the iterated second surrogate model is smaller than the reference threshold.

Wherein, iterating the second surrogate model based on the plurality of third sample parameters and the historical fitting error function includes: inputting the plurality of third sample parameters into the second surrogate model, and obtaining the third sample parameter obtained by the second surrogate model Fitting error, taking the fitting error obtained by the third sample parameter through the second proxy model as the second fitting error; selecting the third sample parameter with the smallest second fitting error, and obtaining the third sample model based on the shale gas well model; Repeat the above steps 1042 and 10431 based on the third sample model to obtain the iterated second surrogate model. If the iterative second model does not meet the first condition, continue to follow the steps 10432 above to obtain a new surrogate model based on the iterated second model. until the iterated second surrogate model satisfies the first condition, no new third sample parameters are acquired, and the iterated second surrogate model at this time is used as the first surrogate model. The first surrogate model thus obtained is sufficiently accurate to describe the relationship between the fitting error and the sample parameters.

It should be noted that the fitting error of the third sample parameter obtained by the historical fitting error function and the fitting error of the third sample parameter obtained by the iterative second surrogate model in the first condition are obtained according to the following methods.

Inputting multiple third sample parameters into the shale gas well model to obtain multiple shale gas well models corresponding to multiple third sample parameters, and entering multiple shale gas well models corresponding to multiple third sample parameters into the history matching error function , to obtain the fitting error of the third sample parameter obtained through the historical fitting error function; inputting multiple third sample parameters into the second surrogate model can obtain the fitting error of the third sample parameter obtained through the second surrogate model.

1044. Obtain a plurality of second sample parameters based on the first surrogate model and the reference fitting error.

In a possible implementation manner, acquiring a plurality of second sample parameters based on the first surrogate model and the reference fitting error includes: acquiring, based on the first surrogate model, a plurality of sample parameters that satisfy the reference fitting error, which will satisfy the reference fitting error. The multiple sample parameters of the combined error are used as multiple second sample parameters.

Optionally, a plurality of second sample models that satisfy the reference fitting error are obtained based on the first proxy model, and sample parameters corresponding to the plurality of second sample models that satisfy the reference fitting error are used as the plurality of second sample parameters.

Wherein, the second sample model is selected from the shale gas well model corresponding to the third sample parameter generated last time in step 1043 . The second fitting error is the fitting error calculated by the second surrogate model for the third sample parameter generated last time in step 1043 . The reference fitting error is a specific fitting error threshold. Optionally, the reference fitting error can be set according to engineering experience. For example, the reference fitting error can be based on a representative simulation curve (bottom hole flow pressure curve, water production curve) The fitting effect is obtained.

After the second sample model is selected, the artificial fracture parameters corresponding to the second sample model are counted, and the artificial fracture parameters corresponding to the second sample model are used as the second sample parameters.

Optionally, the second sample model obtained by screening may contain the distribution of natural fractures, or may not contain the distribution of natural fractures.

Please refer to FIG. 4-9. FIG. 4-9 shows a screening result of a second sample model provided by an embodiment of the present application. Among them, Figure 4, Figure 6, Figure 8 are the results without considering natural fractures, Figure 5, Figure 7, Figure 9 are the results considering a fixed set of natural fracture parameters.

Step 105 , acquiring target artificial fracture parameters based on the plurality of second sample parameters and the shale gas well model.

In a possible implementation manner, acquiring target artificial fracture parameters based on multiple second sample parameters and a shale gas well model includes the following steps.

1051. Obtain a target probability distribution of artificial fracture parameters based on the plurality of second sample parameters.

Statistics are performed on a plurality of second sample parameters to obtain a target probability distribution of artificial fracture parameters.

1052. Perform inversion of the target artificial fracture parameters based on the target probability distribution and the shale gas well model, to obtain the target artificial fracture parameters.

The target artificial fracture parameters include at least one of the length of the artificial fracture, the fracture height of the artificial fracture, the water saturation of the artificial fracture, the conductivity coefficient of the artificial fracture, and the width of the artificial fracture.

The inversion of artificial fracture parameters refers to the use of the established shale gas well model, and the use of computer programs to obtain the geometric shape of artificial fractures and the distribution of parameters such as conductivity coefficients through numerical simulation calculation and historical matching of production data.

Among them, production history matching refers to using the recorded static parameters of shale gas reservoirs to calculate the main dynamic indicators in the process of shale gas development, and comparing the calculated results with the observed main dynamic indicators of gas wells, such as wellhead pressure, production If there is a difference between the two, modify the static parameters of the gas reservoir, and use the modified static parameters to calculate and compare again until the calculated results are equivalent to the measured dynamic parameters. In the embodiment of the present application, the artificial fracture parameters of the shale gas well to be inverted are equivalent to the static parameters to be modified in the above method.

Optionally, based on the target probability distribution and the shale gas well model, a statistical method is used to gradually invert the target artificial fracture parameters, which may include any one or more of the following methods, which are not limited in the embodiments of the present application.

Method 1: Invert the length of artificial fractures based on the target probability distribution and the shale gas well model. This parameter depends on geological factors and construction effects. The empirical value of the length of artificial fractures is generally in the range of 80-120 meters.

The second method is to invert the fracture height of artificial fractures based on the target probability distribution and the shale gas well model. This parameter depends on the thickness of the specific shale gas reservoir. The fracture height of artificial fractures fluctuates widely.

The third method is to invert the water saturation of artificial fractures in shale gas wells based on the target probability distribution and the shale gas well model. Due to the phenomenon of fracturing water backflow often encountered in the early stage of shale gas development, the water saturation of artificial fractures generally fluctuates in the interval of 0.6%-0.7%. However, different reservoir conditions also result in different artificial fracture water saturation (sometimes down to below 0.5%).

Method 4: Invert the width of artificial fractures in shale gas wells based on the target probability distribution and the shale gas well model. The equivalent value of the width of artificial fractures is generally 0.2-0.8 meters, and this parameter is closely related to the production of water.

Method 5. Based on the target probability distribution and the shale gas well model, the conductivity coefficient of the artificial fracture of the shale gas well is inverted. The value of this parameter depends on the effect of the fracturing operation and fluctuates widely (10-8 millidarcy meters).

Optionally, after inverting the target artificial fracture parameters based on the target probability distribution and the shale gas well model, the method further includes: generating a visualized inversion result based on the inverted artificial fracture parameters. Optionally, the artificial fracture parameters after the inversion may include the length of the artificial fracture after the inversion, the fracture height value of the artificial fracture in the shale gas well after the inversion, the water saturation of the artificial fracture in the shale gas well after the inversion, One or more of the width of the inversion artificial fracture and the conductivity coefficient of the inversion artificial fracture of the shale gas well.

In a possible implementation, based on the length of the artificial fracture after inversion, the fracture height value of the artificial fracture after inversion, the water saturation of the artificial fracture after inversion, the width of the artificial fracture after inversion, and After inversion of the conductivity coefficient of artificial fractures, a combined histogram and probability distribution diagram are drawn. Optionally, the visualization results may or may not contain natural fracture parameters.

Please refer to FIGS. 10-19 , which illustrate a visual inversion result provided by an embodiment of the present application. In Fig. 10-19, a combined histogram and probability distribution graph are used to represent the inversion results, where the bar graph represents the frequency of occurrence of artificial fracture parameters corresponding to this range, and the curve represents the fitting based on the frequency bar graph. probability distribution curve. Figure 10, Figure 12, Figure 14, Figure 16, Figure 18 represent the inversion results without considering natural fractures, Figure 11, Figure 13, Figure 15, Figure 17, Figure 19 represent the inversion results considering a fixed set of natural fracture parameters .

In another possible implementation, based on the length of artificial fractures in shale gas wells after inversion, the fracture height value of artificial fractures in shale gas wells after inversion, and the water saturation of artificial fractures in shale gas wells after inversion , the width of artificial fractures in shale gas wells after inversion, and the conductivity coefficient of artificial fractures in shale gas wells after inversion, to generate a cumulative probability distribution map. Optionally, the visualization results may or may not contain natural fracture parameters.

Among them, the cumulative probability distribution map refers to the visual distribution map with the probabilities of P10, P50 and P90. The values of P10 and P90 help to understand the representative actual range of a certain artificial fracture parameter, and the value of P50 can determine the average representative value of a certain artificial fracture parameter. Cumulative probability distribution maps help to better range the inversion results.

Please refer to FIGS. 20-29 , which illustrate a visual inversion result provided by an embodiment of the present application. In Fig. 20-29, the cumulative probability distribution diagram is used to represent the inversion results, in which Fig. 20, Fig. 22, Fig. 24, Fig. 26, Fig. 28 represent the cumulative probability distribution without considering natural fracture parameters, Fig. 21, Fig. 23, Fig. Figures 25, 27, and 29 represent cumulative probability distributions considering a fixed set of natural fracture parameters.

The method for obtaining artificial fracture parameters provided by the above embodiments effectively solves the problems that the current shale gas well artificial fracture parameters cannot be accurately obtained and the manual workload is large. By establishing a shale gas well model, a priori for artificial fracture parameters is set In the probability distribution interval, the "Markov chain-Monte Carlo" algorithm is used to iteratively optimize the artificial fracture parameters of shale gas horizontal wells, and the most representative artificial fracture values and numerical models that are as close to the real situation as possible are obtained. The production performance prediction of shale gas horizontal wells is closer to the actual production, reducing the uncertainty and artificial workload caused by a large number of unrepresentative samples. Through the statistics of all optimized artificial fracture parameters, the posterior probability distribution of the parameters, that is, the target probability distribution, is obtained. The geometric shape of the artificial fracture (length, width, fracture height, etc.) The distribution trend is an infinite approximation to the real situation in the ground, which enables researchers and decision makers to have a new quantitative understanding of the underground fracture network, and to evaluate the fracturing effect of deep shale gas wells, predict the final recoverable reserves and make reasonable Well spacing optimization is of great significance.

Based on the same technical concept, please refer to FIG. 30 , which shows a schematic diagram of a device for acquiring artificial fracture parameters provided by an embodiment of the present application. The device includes but is not limited to the following modules 701-705:

The first acquisition module 701 is used to acquire a shale gas well model.

The second obtaining module 702 is configured to obtain the initial probability distribution of artificial fracture parameters in the shale gas well model.

The third obtaining module 703 is configured to obtain a plurality of first sample parameters based on the initial probability distribution.

In a possible implementation manner, the third obtaining module 703 is configured to perform random sampling through the Markov Chain Monte Carlo method in the initial probability distribution to obtain multiple first sample parameters.

The fourth obtaining module 704 is configured to obtain a plurality of second sample parameters based on the shale gas well model, a plurality of first sample parameters and a reference fitting error.

In a possible implementation manner, the fourth obtaining module 704 is configured to obtain multiple first sample models based on multiple first sample parameters and the shale gas well model; The history fitting error function obtains a plurality of first fitting errors; establishes a first surrogate model based on the plurality of first sample parameters and the plurality of first fitting errors; obtains a plurality of first surrogate models based on the first surrogate model and the reference fitting errors Two sample parameters.

Optionally, the fourth acquisition module 704 establishes a second surrogate model through the K-nearest neighbor classification KNN algorithm based on multiple first sample parameters and multiple first fitting errors; based on the second surrogate model, through Markov Chain Monte The Carlo method obtains a plurality of third sample parameters; the second surrogate model is iterated based on the plurality of third sample parameters and the historical fitting error function to obtain the first surrogate model.

Optionally, the fourth obtaining module 704 is configured to iterate the second surrogate model based on a plurality of third sample parameters and the historical fitting error function, and use the iterated second surrogate model that meets the first condition as the first surrogate. model, wherein the first condition is that the difference between the fitting error obtained by the reference number of third sample parameters through the historical fitting error function and the fitting error obtained through the iterated second surrogate model is less than the reference threshold.

Optionally, the fourth obtaining module 704 is configured to obtain a plurality of sample parameters satisfying the reference fitting error based on the first surrogate model, and use the plurality of sample parameters satisfying the reference fitting error as a plurality of second sample parameters.

The fifth obtaining module 705 is configured to obtain target artificial fracture parameters based on the plurality of second sample parameters and the shale gas well model.

In a possible implementation manner, the fifth obtaining module 705 is configured to obtain a target probability distribution of artificial fracture parameters based on a plurality of second sample parameters; invert the target artificial fracture parameters based on the target probability distribution and a shale gas well model , to obtain the target artificial fracture parameters.

The target artificial fracture parameters include at least one of the length of the artificial fracture, the fracture height of the artificial fracture, the water saturation of the artificial fracture, the width of the artificial fracture, and the conductivity of the artificial fracture.

It should be noted that, when the device provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example for illustration. The internal structure is divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process thereof is detailed in the method embodiments, which will not be repeated here.

In an exemplary embodiment, there is also provided a computer device including a processor and a memory having at least one instruction stored in the memory. The at least one instruction is configured to be executed by one or more processors to implement any of the methods for obtaining artificial fracture parameters described above.

In an exemplary embodiment, a storage medium is also provided, and the storage medium stores at least one piece of program code, the at least one piece of program code is loaded and executed by the processor, so that the computer can realize any one of the above artificial crack parameters. get method.

Optionally, the above-mentioned storage medium may be read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), compact disc read-only memory (compact disc read-only memory, CD-ROM), magnetic tape , floppy disks and optical data storage devices.

In an exemplary embodiment, there is also provided a computer program or computer program product having stored therein at least one computer instruction that is loaded and executed by a processor to cause a computer to implement The method for obtaining any of the above artificial fracture parameters. The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed system and method may be implemented in other manners. For example, the system embodiments described above are only illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components may be combined or Integration into another system, or some features can be ignored, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or modules, and may also be electrical, mechanical or other forms of connection.

The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, may be located in one place, or may be distributed to multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solutions of the embodiments of the present application.

In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically alone, or two or more modules may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules.

It should also be understood that, in each embodiment of the present application, the size of the sequence number of each process does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not be used in the embodiment of the present application. Implementation constitutes any limitation.

The meaning of the term "at least one" in this application refers to one or more, and the meaning of the term "plurality" in this application refers to two or more, for example, a plurality of data refers to two or more data.

It is to be understood that the terminology used in describing the various described examples herein is for the purpose of describing particular examples and is not intended to be limiting. As used in the description of the various described examples and the appended claims, the singular forms "a", "an")" and "the" are intended to include the plural forms as well, unless the context dictates otherwise. clearly instructed.

The above are only exemplary embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the protection of the present application. within the range.

Claims (10)

1. an acquisition method of artificial crack parameter, is characterized in that, described method comprises: Obtain a shale gas well model; obtaining the initial probability distribution of artificial fracture parameters in the shale gas well model; obtaining a plurality of first sample parameters based on the initial probability distribution; Obtaining a plurality of second sample parameters based on the shale gas well model, the plurality of first sample parameters, and a reference fitting error; Target artificial fracture parameters are obtained based on the plurality of second sample parameters and the shale gas well model. 2. The method according to claim 1, wherein the acquiring a plurality of first sample parameters based on the initial probability distribution comprises: In the initial probability distribution, random sampling is performed by a Markov Chain Monte Carlo method to obtain the plurality of first sample parameters. 3. The method according to claim 1, wherein the acquiring a plurality of second sample parameters based on the shale gas well model, the plurality of first sample parameters and a reference fitting error comprises: obtaining a plurality of first sample models based on the plurality of first sample parameters and the shale gas well model; Obtaining a plurality of first fitting errors by using a history fitting error function based on the plurality of first sample models; establishing a first surrogate model based on the plurality of first sample parameters and the plurality of first fitting errors; The plurality of second sample parameters are obtained based on the first surrogate model and the reference fitting error. 4. The method according to claim 3, wherein the establishing a first surrogate model based on the plurality of first sample parameters and the plurality of first fitting errors comprises: A second surrogate model is established by the K-nearest neighbor classification KNN algorithm based on the plurality of first sample parameters and the plurality of first fitting errors; Obtaining a plurality of third sample parameters through a Markov chain Monte Carlo method based on the second surrogate model; The first surrogate model is obtained by iterating the second surrogate model based on the plurality of third sample parameters and the history fitting error function. 5 . The method according to claim 4 , wherein the first surrogate model is obtained by iterating the second surrogate model based on the plurality of third sample parameters and the history fitting error function. 6 . models, including: The second surrogate model is iterated based on the plurality of third sample parameters and the history fitting error function, and the iterated second surrogate model that meets the first condition is used as the first surrogate model, and the The first condition is that the difference between the fitting errors obtained by the reference number of third sample parameters through the historical fitting error function and the fitting errors obtained through the iterated second surrogate model is smaller than a reference threshold. 6. The method according to claim 3, wherein the acquiring the plurality of second sample parameters based on the first surrogate model and the reference fitting error comprises: Obtain a plurality of sample parameters satisfying the reference fitting error based on the first surrogate model, and use the plurality of sample parameters satisfying the reference fitting error as the plurality of second sample parameters. 7. The method according to claim 1, wherein the acquiring target artificial fracture parameters based on the plurality of second sample parameters and the shale gas well model comprises: obtaining a target probability distribution of artificial fracture parameters based on the plurality of second sample parameters; The target artificial fracture parameters are inverted based on the target probability distribution and the shale gas well model to obtain the target artificial fracture parameters. 8. The method according to any one of claims 1-7, wherein the target artificial fracture parameters at least include the length of the artificial fracture, the fracture height value of the artificial fracture, the water saturation of the artificial fracture, and the width of the artificial fracture And one of the conductivity coefficients of artificial fractures. 9. A device for obtaining artificial fracture parameters, wherein the device comprises: a first acquisition module, used to acquire a shale gas well model; a second acquisition module, configured to acquire the initial probability distribution of artificial fracture parameters in the shale gas well model; a third obtaining module, configured to obtain a plurality of first sample parameters based on the initial probability distribution; a fourth obtaining module, configured to obtain a plurality of second sample parameters based on the shale gas well model, the plurality of first sample parameters and the reference fitting error; A fifth acquisition module, configured to acquire target artificial fracture parameters based on the plurality of second sample parameters and the shale gas well model. 10. A computer device, characterized in that the computer device comprises a processor and a memory, wherein the memory stores at least one instruction, the at least one instruction implements the steps of claims 1 to 1 when executed by the processor 8. The method for obtaining any of the artificial fracture parameters.

Images