Development effect determination method and device for unconventional oil and gas reservoir, equipment and medium

Abstract

The embodiment of the invention discloses a method and device for determining the development effect of an unconventional oil and gas reservoir, equipment and a medium. The method comprises the following steps: acquiring basic data, associated with unconventional oil and gas reservoir development, of a target development block and a preset development index corresponding to the unconventional oil and gas reservoir development; according to the basic data, carrying out actual fractured well production dynamic analysis of the target development block so as to quantify a development index and obtain a development index value; aiming at the at least one influence factor corresponding to the basic data and the development effect of the unconventional oil and gas reservoir, determining a main control factor influencing the development effect from the at least one influence factor according to the basic data and the development index value; and establishing a machine learning prediction model according to the main control factors and the development indexes, and predicting the development indexes by using the machine learning prediction model to obtain a development effect. According to the technical scheme provided by the embodiment of the invention, the effective determination of the development effect of the unconventional oil and gas reservoir is realized.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of oil and gas field development, and in particular to a method, device, equipment and medium for determining the development effect of unconventional oil and gas reservoirs. Background Art

[0002] In the field of oil and gas field development, production prediction is crucial for the development of unconventional oil and gas reservoirs, especially in fracturing design, economic evaluation and decision-making.

[0003] It should be noted that the on-site fracturing completion design and production optimization of unconventional oil and gas reservoirs require a lot of geological modeling, fracture simulation and production simulation, which involves complex mechanism research. This makes it impossible to effectively determine the development effect of unconventional oil and gas reservoirs at present, and needs to be improved. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, equipment and medium for determining the development effect of an unconventional oil and gas reservoir, so as to effectively determine the development effect of the unconventional oil and gas reservoir.

[0005] According to one aspect of the present invention, a method for determining the development effect of an unconventional oil and gas reservoir is provided, which may include:

[0006] Obtaining basic data related to the development of unconventional oil and gas reservoirs in the target development block, as well as preset development indicators corresponding to the development of unconventional oil and gas reservoirs;

[0007] Based on the basic data, conduct actual fracturing well production dynamic analysis in the target development block to quantify the development indicators and obtain the development indicator values;

[0008] For at least one influencing factor corresponding to the basic data and the development effect of the unconventional oil and gas reservoir, determine a main controlling factor affecting the development effect from the at least one influencing factor according to the basic data and the development index value;

[0009] According to the main controlling factors and development indicators, a machine learning prediction model is established to predict the development indicators and obtain the development effect by utilizing the machine learning prediction model.

[0010] According to another aspect of the present invention, a device for determining the development effect of an unconventional oil and gas reservoir is provided, which may include:

[0011] A development index acquisition module is used to acquire basic data associated with the development of unconventional oil and gas reservoirs in the target development block, as well as preset development indicators corresponding to the development of unconventional oil and gas reservoirs;

[0012] The module for obtaining development index values ​​is used to conduct actual fracturing well production dynamic analysis of the target development block based on basic data, so as to quantify the development index and obtain the development index value;

[0013] A main controlling factor determination module is used to determine the main controlling factor affecting the development effect from at least one influencing factor corresponding to the basic data and the development effect of the unconventional oil and gas reservoir according to the basic data and the development index value;

[0014] The development effect determination module is used to establish a machine learning prediction model based on the main control factors and development indicators, so as to predict the development indicators by using the machine learning prediction model to obtain the development effect.

[0015] According to another aspect of the present invention, there is provided an electronic device, which may include:

[0016] at least one processor; and

[0017] a memory communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor implements the method for determining the development effect of unconventional oil and gas reservoirs provided by any embodiment of the present invention when executing the computer program.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer instructions are stored, and the computer instructions are used to enable a processor to implement the method for determining the development effect of unconventional oil and gas reservoirs provided by any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention is to obtain the basic data related to the development of unconventional oil and gas reservoirs in the target development block, and the preset development indicators corresponding to the development of unconventional oil and gas reservoirs; based on the basic data, conduct a dynamic analysis of the actual fracturing well production in the target development block to quantify the development indicators and obtain the development indicator value; for at least one influencing factor corresponding to the basic data and the development effect of the unconventional oil and gas reservoir, determine the main controlling factor affecting the development effect from at least one influencing factor based on the basic data and the development indicator value; establish a machine learning prediction model based on the main controlling factor and the development indicator, so as to predict the development indicator and obtain the development effect by using the machine learning prediction model. The above technical solution can effectively avoid the complex mechanism research of unconventional reservoir fracturing by utilizing big data analysis and mining and machine learning, and directly mine useful information from a large amount of real data, thereby realizing the effective determination of the development effect of unconventional oil and gas reservoirs.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 is a flow chart of a method for determining the development effect of an unconventional oil and gas reservoir provided according to an embodiment of the present invention;

[0024] Figure 2 is a flow chart of an example of outlier identification in a method for determining development effect of unconventional oil and gas reservoirs provided according to an embodiment of the present invention;

[0025] Figure 3 is a schematic diagram of an example of selecting influencing factors in a method for determining development effects of unconventional oil and gas reservoirs provided in an embodiment of the present invention;

[0026] Figure 4 is a flow chart of another method for determining development effect of unconventional oil and gas reservoirs provided according to an embodiment of the present invention;

[0027] Figure 5 is a flow chart of another method for determining the development effect of unconventional oil and gas reservoirs provided according to an embodiment of the present invention;

[0028] Figure 6 It is a schematic diagram of an example of quantitatively determining development effects based on main controlling factors of SHAP analysis in another method for determining development effects of unconventional oil and gas reservoirs provided in an embodiment of the present invention;

[0029] Figure 7 This is a structural block diagram of a device for determining the development effect of unconventional oil and gas reservoirs provided according to an embodiment of the present invention;

[0030] Figure 8 It is a structural schematic diagram of an electronic device for implementing the method for determining the development effect of unconventional oil and gas reservoirs according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. The situations of "target", "original", etc. are similar and will not be repeated here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] Before introducing the embodiment of the present invention, an application scenario of the embodiment of the present invention is first exemplified to better understand the method for determining the development effect of an unconventional oil and gas reservoir described in the embodiment of the present invention.

[0034] Production prediction is crucial for the economic exploration and development of unconventional resources, especially in fracturing design, economic evaluation and decision-making. With the rapid development of computer science and the explosive accumulation of oilfield data, machine learning has been widely used in the oil industry with its powerful nonlinear approximation capabilities. On-site fracturing completion design and production optimization of unconventional oil and gas reservoirs require a lot of geological modeling, fracture simulation and production simulation. On this basis, big data and artificial intelligence algorithms can help to mine large amounts of useful information from massive data, thereby greatly improving the level of completion design.

[0035] In view of the current problems of difficulty in evaluating the fracturing effect, ambiguity of the main controlling factors affecting the fracturing effect, and time-consuming calculation of fracturing engineering design optimization, it is necessary to carry out big data mining and analysis research based on actual reservoir geology, completion and oil and gas data for unconventional oil and gas reservoirs to clarify the key geological and engineering factors (i.e., main controlling factors) that affect the fracturing effect, and establish a prediction model for oil and gas reservoir development indicators under different reservoir and fracturing parameters. It should be noted that the application of big data analysis and mining methods can effectively avoid the complex mechanism research of unconventional reservoir fracturing, such as avoiding large-scale fracturing-seepage numerical simulation, and mining potential value from a large amount of real data, that is, mining useful information, which can provide theoretical guidance and technical support for optimizing the design of shale fracturing schemes and making reasonable decisions on on-site construction adjustments, and finally form a theoretical and technical system for evaluating the development effect of different reservoir types in the target area.

[0036] In view of this, the embodiment of the present invention integrates the characteristics of unconventional oil reservoir development and proposes a new prediction framework based on geological-engineering-production dynamic big data and machine learning. This framework is based on development indicators such as reserve utilization, energy utilization, and geological-engineering applicability, and takes into account economic benefit evaluation, and considers all the main control factors that affect the development effect of unconventional oil and gas reservoirs, thereby solving the problem that the current reservoir development effect evaluation scheme is not applicable in the unconventional field, and filling the gap in the unconventional oil reservoir development effect evaluation technology.

[0037] According to the above description, compared with the intersection chart method, multivariate linear regression, predetermined interval method, experimental and numerical simulation methods, etc., machine learning can effectively avoid the complex mechanism research of unconventional reservoir fracturing with its powerful nonlinear mapping ability and tap the potential value from a large amount of real data. On this basis, it should be noted that there are obvious differences between the quantitative evaluation modeling of development effects based on oil and gas data and the traditional machine learning modeling. Next, the targeted big data analysis process will be explained in detail.

[0038] Figure 1 It is a flow chart of a method for determining the development effect of an unconventional oil and gas reservoir provided in an embodiment of the present invention. This embodiment can be applied to the case of determining the development effect of an unconventional oil and gas reservoir, and is particularly applicable to the case of effectively determining the development effect in combination with machine learning. The method can be executed by a device for determining the development effect of an unconventional oil and gas reservoir provided in an embodiment of the present invention, and the device can be implemented by software and / or hardware, and the device can be integrated on an electronic device, and the electronic device can be various user terminals or servers.

[0039] See also Figure 1 The method of the embodiment of the present invention specifically includes the following steps:

[0040] S110, acquiring basic data associated with the development of unconventional oil and gas reservoirs in the target development block, and preset development indicators corresponding to the development of unconventional oil and gas reservoirs.

[0041] Among them, the target development block can be understood as a block where unconventional oil and gas reservoir development is to be carried out. Basic data can be understood as data related to the development of unconventional oil and gas reservoirs in the target development block, for example, it can be at least one of geological data, drilling and completion data, development data, fracturing construction data, rock mechanics data, logging data, oil and gas production dynamic data, and post-pressure drainage production dynamic data. In practical applications, optionally, the basic data exemplified above can be collectively referred to as original geological-engineering-production data; optionally, the basic data described above can also be referred to as oil and gas data.

[0042] The development index can be understood as a pre-set index used to characterize the development of unconventional oil and gas reservoirs. In combination with the application scenarios that may be involved in the embodiments of the present invention, it can be, for example, well-controlled reserves, pressure decline rate, recovery rate or internal rate of return, etc., which are not specifically limited here. The number of development indicators can be one, two or more, which is related to the actual situation and is not specifically limited here.

[0043] Obtain basic data and develop indicators.

[0044] S120. Based on the basic data, conduct a dynamic analysis of the actual fracturing well production in the target development block to quantify the development indicators and obtain the development indicator values.

[0045] Among them, based on basic data, starting from the development effects such as the control and utilization of geological reserves, the retention and utilization of quasi-elastic energy, and economic benefits, the actual fracturing well production dynamics analysis of the target development block is carried out, so as to realize the quantification of development indicators and obtain development indicator values.

[0046] S130. For at least one influencing factor corresponding to the basic data and the development effect of the unconventional oil and gas reservoir, determine a main controlling factor affecting the development effect from the at least one influencing factor according to the basic data and the development index value.

[0047] Among them, the influencing factors can be understood as factors that are associated with the basic data and may affect the development effect of unconventional oil and gas reservoirs. The number of the influencing factors can be one, two or more, which is related to the actual situation and is not specifically limited here. In combination with the application scenarios that may be involved in the embodiments of the present invention, the above-mentioned influencing factors can also be optionally referred to as influencing factor features.

[0048] According to the basic data and the development index value, the main controlling factor that mainly affects the development effect is determined from at least one influencing factor, that is, the main controlling factor can be understood as the influencing factor with a greater degree of influence on the development effect among at least one influencing factor. In practical applications, the number of main controlling factors can be one, two or more, which is related to the actual situation and is not specifically limited here.

[0049] S140. Establish a machine learning prediction model based on the main controlling factors and development indicators, so as to predict the development indicators and obtain the development effect by utilizing the machine learning prediction model.

[0050] Among them, according to the main controlling factors and development indicators, a machine learning prediction model is established for predicting development indicators based on the main controlling factors. For example, machine learning and data mining algorithms such as random forests, gradient enhancement and linear regression are used to establish a machine learning prediction model of the main controlling factors and development indicators. The machine learning prediction model can be an interpretable machine learning model of nonlinear multi-model fusion.

[0051] On this basis, further, since development indicators can be used to characterize the development status of unconventional oil and gas reservoirs, after establishing a machine learning prediction model, the development indicators can be predicted by using the machine learning prediction model to obtain the development effect of unconventional oil and gas reservoirs.

[0052] The technical solution of the embodiment of the present invention is to obtain the basic data related to the development of unconventional oil and gas reservoirs in the target development block, and the preset development indicators corresponding to the development of unconventional oil and gas reservoirs; based on the basic data, conduct a dynamic analysis of the actual fracturing well production in the target development block to quantify the development indicators and obtain the development indicator value; for at least one influencing factor corresponding to the basic data and the development effect of the unconventional oil and gas reservoir, determine the main controlling factor affecting the development effect from at least one influencing factor based on the basic data and the development indicator value; establish a machine learning prediction model based on the main controlling factor and the development indicator, so as to predict the development indicator and obtain the development effect by using the machine learning prediction model. The above technical solution can effectively avoid the complex mechanism research of unconventional reservoir fracturing by utilizing big data analysis and mining and machine learning, and directly mine useful information from a large amount of real data, thereby realizing the effective determination of the development effect of unconventional oil and gas reservoirs.

[0053] An optional technical solution, after obtaining basic data associated with the development of unconventional oil and gas reservoirs in the target development block, the method for determining the development effect of the unconventional oil and gas reservoirs further includes:

[0054] By using at least one of box plot, isolation forest and dimensionality reduction clustering, outliers are identified for basic data and the types of the identified outliers are determined; the outliers are processed according to the types, and the basic data are updated based on the processed outliers.

[0055] The above technical solution can effectively identify outliers in basic data and improve model performance.

[0056] In order to understand the above technical solution more vividly, the following is an exemplary description of it with reference to specific examples. Figure 2 As shown in the figure, this example combines three methods: box plot, isolation forest and dimensionality reduction clustering, to identify outliers from the perspective of statistical characteristics and feature correlation, and then combines professional experience to deal with outliers. Next, the box plot and isolation forest methods are illustrated.

[0057] The box plot is a graphical description of the quartiles of the basic data, which can describe the dispersion of the data. It is a very simple and effective statistical method for visualizing outliers. Moreover, this method does not make assumptions about the data distribution and is widely used. Figure 2As shown in the figure, the distance between the lower quartile (Q1) and the upper quartile (Q3) is recorded as IQR, and the upper and lower whiskers are the boundaries of the data distribution. Any data point higher than the upper whisker (Q3+1.5IQR) or lower than the lower whisker (Q1-1.5IQR) can be considered an outlier.

[0058] In Isolation Forest, outliers are defined as "outliers that are easily isolated", which can be understood as points that are sparsely distributed and far away from dense groups. The Isolation Forest algorithm recursively and randomly splits the basic data until all sample points are isolated. Under this random splitting strategy, outliers usually have shorter paths. Intuitively speaking, those high-density clusters need to be cut many times to be isolated, but those low-density points can be easily isolated.

[0059] Another optional technical solution, before determining the main controlling factor affecting the development effect from at least one influencing factor, the above-mentioned method for determining the development effect of unconventional oil and gas reservoirs further includes:

[0060] At least one influencing factor is selected through at least one of correlation analysis, elimination of multicollinearity, feature importance calculation, and feature quantity optimization; and then, based on the selected influencing factor, at least one influencing factor is updated.

[0061] Among them, there may be "irrelevant features" and "redundant features" in at least one candidate factor (i.e., candidate factor features). Therefore, before determining the main controlling factor, at least one of correlation analysis, elimination of multicollinearity, feature importance calculation, and feature quantity optimization can be used for feature selection, thereby reducing data complexity and noise, eliminating linear relationships between data, and thereby increasing model readability.

[0062] In order to understand the above technical solution more vividly, the following is an exemplary description of it with reference to specific examples. Figure 3 , the correlation analysis method is used to calculate the correlation between the candidate factor characteristics (hereinafter referred to as characteristics) and the target yield, and a wide range of feature filtering is performed based on the correlation, and the irrelevant or weakly correlated features are first eliminated from a large number of features. Optionally, the Spearman correlation coefficient and mutual information method are used here to comprehensively calculate the correlation. Among them,

[0063] The Spearman correlation coefficient is a rank correlation coefficient, which is calculated based on the correlation of the ranking positions of the data in the two features. The specific calculation method is shown in the following formula. As long as the ranking order of the corresponding values ​​of the two features in each group is similar, there is a significant correlation. Therefore, the Spearman correlation coefficient can not only measure linear correlation, but also evaluate nonlinear correlation.

[0064]

[0065] The mutual information method is used to measure the correlation between features and target yield. Mutual information is a measure used in information theory to evaluate the degree of dependence between two random variables. The specific calculation method is shown in the following formula. The larger the mutual information value between a feature and the target yield, the more the uncertainty of the target variable is reduced after knowing the feature, that is, the stronger the correlation between the two.

[0066]

[0067] Figure 4 It is a flow chart of another method for determining the development effect of unconventional oil and gas reservoirs provided in an embodiment of the present invention. This embodiment is optimized based on the above-mentioned technical solutions. In this embodiment, optionally, according to the basic data and the development index value, the main controlling factor affecting the development effect is determined from at least one influencing factor, which may include: according to the basic data and the development index value, respectively determining the first degree of influence of each influencing factor of at least one influencing factor on the development index; according to the first degree of influence corresponding to the obtained at least one influencing factor, determining the main controlling factor affecting the development effect from at least one influencing factor. Among them, the explanations of the terms that are the same or corresponding to the above-mentioned embodiments are not repeated here.

[0068] See also Figure 4 The method of this embodiment may specifically include the following steps:

[0069] S210, acquiring basic data associated with the development of unconventional oil and gas reservoirs in the target development block, and preset development indicators corresponding to the development of unconventional oil and gas reservoirs.

[0070] S220. Based on the basic data, conduct a dynamic analysis of the actual fracturing well production in the target development block to quantify the development indicators and obtain the development indicator values.

[0071] S230. For at least one influencing factor corresponding to the basic data, determine a first degree of influence of each influencing factor in the at least one influencing factor on the development indicator according to the basic data and the development indicator value.

[0072] S240. For the development effect of unconventional oil and gas reservoirs, according to the first influence degree corresponding to the at least one influence factor, determine the main controlling factor affecting the development effect from the at least one influence factor.

[0073] S250. Establish a machine learning prediction model based on the main controlling factors and development indicators, so as to predict the development indicators and obtain the development effect by utilizing the machine learning prediction model.

[0074] The technical solution of the embodiment of the present invention can accurately determine the main controlling factor from the at least one influencing factor by determining the first influence degree of at least one influencing factor on the development indicator.

[0075] An optional technical solution, the above-mentioned method for determining the development effect of unconventional oil and gas reservoirs, further includes:

[0076] Constructing a machine learning determination model, and cross-validating the basic data by using the machine learning determination model to train and update the machine learning determination model;

[0077] Accordingly, determining a first influence degree of each influencing factor of at least one influencing factor on the development indicator according to the basic data and the development indicator value respectively includes:

[0078] By utilizing machine learning to determine the model, a first degree of influence of each influencing factor of at least one influencing factor on the development indicator is determined based on voting according to basic data and the development indicator value.

[0079] Among them, a machine learning determination model is constructed, and combined with the application scenarios that may be involved in the embodiments of the present invention, for example, random forest and recursive feature elimination can be used for modeling. Then, by using the constructed machine learning determination model, the basic data is cross-validated, and the Bayesian optimization method is used to obtain the optimal hyperparameters, which can be, for example, the number of hidden layers, the number of neurons, and the activation function, so as to determine the optimal model architecture and complete the training process of the machine learning determination model.

[0080] Furthermore, based on the trained machine learning determination model, the second degree of influence of each influencing factor on the development indicator is comprehensively judged through voting, and the main controlling factor is determined based on this.

[0081] The above technical solution, based on machine learning methods, achieves accurate determination of the main controlling factors.

[0082] Figure 5 It is a flow chart of another method for determining the development effect of unconventional oil and gas reservoirs provided in an embodiment of the present invention. This embodiment is optimized based on the above-mentioned technical solutions. In this embodiment, optionally, the machine learning prediction model is an interpretable machine learning prediction model, and the development effect is obtained by predicting the development indicators using the machine learning prediction model, including: determining the second degree of influence of the main controlling factor on the development indicator by using the machine learning prediction model and combining the SHAP explanation corresponding to the machine learning prediction model; and predicting the development indicator according to the second degree of influence to obtain the development effect. Among them, the explanations of the terms that are the same or corresponding to the above-mentioned embodiments are not repeated here.

[0083] See also Figure 5 The method of this embodiment may specifically include the following steps:

[0084] S310, obtaining basic data related to the development of unconventional oil and gas reservoirs in the target development block, and preset development indicators corresponding to the development of unconventional oil and gas reservoirs.

[0085] S320. Based on the basic data, conduct a dynamic analysis of the actual fracturing well production in the target development block to quantify the development indicators and obtain the development indicator values.

[0086] S330. For at least one influencing factor corresponding to the basic data and the development effect of the unconventional oil and gas reservoir, determine a main controlling factor affecting the development effect from the at least one influencing factor according to the basic data and the development index value.

[0087] S340. Establish an explainable machine learning prediction model based on the main control factors and development indicators, so as to execute S350 and S360 by utilizing the machine learning prediction model.

[0088] S350. Determine the second degree of influence of the main controlling factor on the development indicator in combination with the SHAP explanation corresponding to the machine learning prediction model.

[0089] For example, Figure 6 As shown in the figure, after the machine learning prediction model is established, the SHAP interpretation can be combined to quantitatively determine the secondary influence of the main controlling factors on the development indicators.

[0090] S360. According to the second impact degree, a prediction is made for the development indicator to obtain a development effect.

[0091] The technical solution of the embodiment of the present invention, by combining SHAP interpretation, determines the second influence degree of the main controlling factor on the development index, and then predicts the development index according to the second influence degree to obtain the development effect.

[0092] In order to better understand the above-mentioned technical solutions as a whole, the following is an illustrative description of them in combination with specific examples. For example, here we take the multiphase flow production prediction of tight oil fractured horizontal wells based on multi-task deep learning as an example, and the specific steps are as follows:

[0093] Step 1: For the target development blocks, collect, analyze and organize the relevant information of the fracturing well big data, and perform pre-processing such as dimensionality reduction, normalization and outlier removal on the basic data so as to unify and standardize the dimensions of the original data and improve the quality of the data in the entire cycle of geology, engineering and production.

[0094] Step 2: Based on the development effects such as the control and utilization of geological reserves, the retention and utilization of quasi-elastic energy, and economic benefits, conduct a dynamic analysis of the actual fracturing well production to quantify multiple development indicators such as well-controlled reserves, pressure decline rate, recovery factor, and internal rate of return.

[0095] Step 3: Based on the pre-processed data, random forest and recursive feature elimination are used to build a model, and well-controlled reserves, pressure decline rate, recovery rate, internal rate of return, etc. are used as development indicators. Through voting, the first degree of influence of each influencing factor on the development indicator is comprehensively evaluated, and based on this, the main controlling factors affecting the development effect of unconventional oil and gas reservoirs are determined.

[0096] Step 4: Use machine learning and data mining algorithms such as random forest, gradient enhancement and linear regression to establish an interpretable machine learning model of nonlinear multi-model fusion between the main controlling factors and development indicators. Further combine the SHAP interpretation method to quantitatively determine the second degree of influence of the main controlling factors on the development indicators, and based on this, predict the development indicators to obtain the development effect of unconventional oil and gas reservoirs.

[0097] The above example combines the characteristics of oil and gas big data and modeling requirements to establish a system framework from oil and gas data (i.e., basic data) collection, data preprocessing, feature selection, to model optimization and prediction, thereby achieving effective determination of the development effect of unconventional oil and gas reservoirs.

[0098] Figure 7 This is a structural block diagram of a device for determining the development effect of unconventional oil and gas reservoirs provided in an embodiment of the present invention. The device is used to execute the method for determining the development effect of unconventional oil and gas reservoirs provided in any of the above embodiments. The device and the method for determining the development effect of unconventional oil and gas reservoirs in the above embodiments belong to the same inventive concept. For details not fully described in the embodiment of the device for determining the development effect of unconventional oil and gas reservoirs, reference can be made to the embodiment of the method for determining the development effect of unconventional oil and gas reservoirs. Figure 7 The device may specifically include: a development index acquisition module 410, a development index value acquisition module 420, a main control factor determination module 430 and a development effect determination module 440.

[0099] The development index acquisition module 410 is used to acquire basic data associated with the development of unconventional oil and gas reservoirs in the target development block, as well as preset development indicators corresponding to the development of unconventional oil and gas reservoirs;

[0100] The development index value obtaining module 420 is used to carry out actual fracturing well production dynamic analysis of the target development block based on the basic data, so as to quantify the development index and obtain the development index value;

[0101] A main controlling factor determination module 430 is used to determine a main controlling factor affecting the development effect from at least one influencing factor corresponding to the basic data and the development effect of the unconventional oil and gas reservoir according to the basic data and the development index value;

[0102] The development effect determination module 440 is used to establish a machine learning prediction model based on the main control factors and development indicators, so as to predict the development indicators by using the machine learning prediction model to obtain the development effect.

[0103] Optionally, the main control factor determination module 430 may include:

[0104] A first influence degree determination unit, configured to determine a first influence degree of each influencing factor of at least one influencing factor on the development indicator according to the basic data and the development indicator value;

[0105] The main controlling factor determination unit is used to determine the main controlling factor affecting the development effect from at least one influencing factor according to the first influence degree corresponding to each of the at least one influencing factors.

[0106] On this basis, optionally, the above-mentioned device for determining the development effect of unconventional oil and gas reservoirs further includes:

[0107] A machine learning determination model update module is used to build a machine learning determination model, and to cross-validate basic data by using the machine learning determination model to train and update the machine learning determination model;

[0108] Accordingly, the first impact degree determination unit is specifically configured to:

[0109] By utilizing machine learning to determine the model, a first degree of influence of each influencing factor of at least one influencing factor on the development indicator is determined based on voting according to basic data and the development indicator value.

[0110] Optionally, the machine learning prediction model is an explainable machine learning prediction model, and the development effect determination module 440 includes:

[0111] A second impact degree determination unit, used to determine a second impact degree of the main control factor on the development indicator by using the machine learning prediction model and combining the SHAP explanation corresponding to the machine learning prediction model;

[0112] The development effect obtaining unit is used to predict the development index according to the second impact degree to obtain the development effect.

[0113] Optionally, the above-mentioned device for determining the development effect of unconventional oil and gas reservoirs further includes:

[0114] A type determination module is used to, after acquiring basic data associated with the development of unconventional oil and gas reservoirs in the target development block, identify outliers on the basic data by using at least one of a box plot, an isolation forest, and a dimensionality reduction clustering, and determine the type of the identified outliers;

[0115] The basic data updating module is used to process the abnormal values ​​according to the type, and update the basic data based on the processed abnormal values.

[0116] Optionally, the above-mentioned device for determining the development effect of unconventional oil and gas reservoirs further includes:

[0117] An influencing factor selection module, used for selecting at least one influencing factor by at least one of correlation analysis, elimination of multicollinearity, feature importance calculation and feature quantity optimization before determining a main controlling factor affecting the development effect from at least one influencing factor;

[0118] The influencing factor updating module is used to update at least one influencing factor based on the selected influencing factors.

[0119] Optionally, based on any of the above-mentioned devices for determining development effects of unconventional oil and gas reservoirs, the basic data includes original geological-engineering-production data.

[0120] The device for determining the development effect of unconventional oil and gas reservoirs provided in the embodiment of the present invention obtains the basic data associated with the development of unconventional oil and gas reservoirs of the target development block and the preset development indicators corresponding to the development of unconventional oil and gas reservoirs through the development indicator acquisition module; through the development indicator value acquisition module, according to the basic data, the actual fracturing well production dynamic analysis of the target development block is carried out to quantify the development indicators and obtain the development indicator value; through the main control factor determination module, for at least one influencing factor corresponding to the basic data and the development effect of the unconventional oil and gas reservoir, according to the basic data and the development indicator value, the main control factor affecting the development effect is determined from at least one influencing factor; through the development effect determination module, according to the main control factor and the development indicator, a machine learning prediction model is established to predict the development indicator by using the machine learning prediction model to obtain the development effect. The above device can effectively avoid the complex mechanism research of unconventional reservoir fracturing by using big data analysis and mining and machine learning, and directly mine useful information from a large amount of real data, thereby realizing the effective determination of the development effect of unconventional oil and gas reservoirs.

[0121] The device for determining the development effect of unconventional oil and gas reservoirs provided in the embodiment of the present invention can execute the method for determining the development effect of unconventional oil and gas reservoirs provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0122] It is worth noting that in the above-mentioned embodiment of the device for determining the development effect of unconventional oil and gas reservoirs, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0123] Figure 8 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0124] like Figure 8 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0125] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0126] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for determining the development effect of unconventional oil and gas reservoirs.

[0127] In some embodiments, the method for determining the development effect of unconventional oil and gas reservoirs may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining the development effect of unconventional oil and gas reservoirs described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for determining the development effect of unconventional oil and gas reservoirs in any other appropriate manner (e.g., by means of firmware).

[0128] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0129] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0130] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0131] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0132] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0133] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0134] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0135] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining the development effect of unconventional oil and gas reservoirs, characterized in that: include: Acquire basic data associated with the development of unconventional oil and gas reservoirs in the target development block, as well as preset development indicators corresponding to the development of the unconventional oil and gas reservoirs; Conducting actual fracturing well production dynamic analysis of the target development block based on the basic data to quantify the development index and obtain a development index value; For at least one influencing factor corresponding to the basic data and the development effect of the unconventional oil and gas reservoir, determining a main controlling factor affecting the development effect from the at least one influencing factor according to the basic data and the development index value; A machine learning prediction model is established based on the main controlling factors and the development indicators, so as to obtain the development effect by predicting the development indicators using the machine learning prediction model.

2. The method according to claim 1, characterized in that Determining the main controlling factor affecting the development effect from the at least one influencing factor according to the basic data and the development index value includes: Determining, according to the basic data and the development indicator value, a first influence degree of each of the at least one influencing factor on the development indicator; According to the obtained first influence degree respectively corresponding to the at least one influence factor, a main controlling factor affecting the development effect is determined from the at least one influence factor.

3. The method according to claim 2, characterized in that Also includes: Constructing a machine learning determination model, and cross-validating the basic data by using the machine learning determination model to train and update the machine learning determination model; Accordingly, determining, based on the basic data and the development indicator value, a first degree of influence of each of the at least one influencing factor on the development indicator, includes: By utilizing the machine learning determination model, according to the basic data and the development indicator value, based on a voting method, a first degree of influence of each of the at least one influencing factor on the development indicator is determined respectively.

4. The method according to claim 1, characterized in that: The machine learning prediction model is an explainable machine learning prediction model, and the development effect is obtained by predicting the development indicator using the machine learning prediction model, including: Determining a second degree of influence of the main controlling factor on the development indicator by utilizing the machine learning prediction model and combining the SHAP explanation corresponding to the machine learning prediction model; According to the second impact degree, the development indicator is predicted to obtain the development effect.

5. The method according to claim 1, characterized in that After obtaining the basic data associated with the development of unconventional oil and gas reservoirs in the target development block, the method further includes: Identify outliers on the basic data by using at least one of a box plot, an isolation forest, and a dimensionality reduction clustering method, and determine the type of the identified outliers; The abnormal value is processed according to the type, and the basic data is updated based on the processed abnormal value.

6. The method according to claim 1, characterized in that Before determining the main controlling factor affecting the development effect from the at least one influencing factor, the method further includes: Selecting the at least one influencing factor through at least one of correlation analysis, elimination of multicollinearity, feature importance calculation, and feature quantity optimization; Based on the selected influencing factor, the at least one influencing factor is updated.

7. The method according to any one of claims 1 to 6, characterized in that: The basic data include original geological-engineering-production data.

8. A device for determining the development effect of unconventional oil and gas reservoirs, characterized in that: include: A development index acquisition module, used to acquire basic data associated with the development of unconventional oil and gas reservoirs in a target development block, and preset development indicators corresponding to the development of the unconventional oil and gas reservoirs; A development index value obtaining module is used to carry out actual fracturing well production dynamic analysis of the target development block based on the basic data, so as to quantify the development index and obtain the development index value; A main controlling factor determination module, for determining a main controlling factor affecting the development effect from at least one influencing factor corresponding to the basic data and the development effect of the unconventional oil and gas reservoir according to the basic data and the development index value; The development effect determination module is used to establish a machine learning prediction model based on the main control factors and the development indicators, so as to obtain the development effect by predicting the development indicators using the machine learning prediction model.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method for determining the development effect of an unconventional oil and gas reservoir as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining the development effect of an unconventional oil and gas reservoir as described in any one of claims 1-7 when executed.

Images