CN113947230A

CN113947230A - Oil gas yield prediction method and device

Info

Publication number: CN113947230A
Application number: CN202010698284.1A
Authority: CN
Inventors: 靳军; 寇根; 魏云; 王子强; 周伟; 周波; 杨龙; 唐红娇; 龙威; 昝成; 程浩然; 陶兴
Original assignee: Petrochina Co Ltd
Current assignee: Petrochina Co Ltd
Priority date: 2020-07-17
Filing date: 2020-07-17
Publication date: 2022-01-18

Abstract

The invention discloses a method and a device for predicting oil and gas yield. Wherein, the method comprises the following steps: acquiring characteristic data of a core collected from a target reservoir, obtaining seepage data in the target reservoir according to measurement of the core, obtaining oil-containing data in the target reservoir according to measurement of the core, and carrying out oil and gas exploitation planned engineering data on the target reservoir; predicting the oil and gas yield in the target reservoir through a spectral clustering model according to the characteristic data, the seepage data, the oil-containing data and the engineering data, wherein the spectral clustering model is obtained by performing model training according to sample data corresponding to a sample rock core, and the sample data at least comprises: sample characteristic data, sample seepage data, sample oil-containing data, sample engineering data and sample oil and gas yield data corresponding to the sample core. The method solves the technical problems of time consumption and high cost of oil gas yield prediction in the related technology.

Description

Oil gas yield prediction method and device

Technical Field

The invention relates to the technical field of oil and gas exploitation, in particular to a method and a device for predicting oil and gas yield.

Background

In the field of oil and gas exploitation, when development decisions are made for a plurality of reservoirs, basic information of the reservoirs is required to be combined to decide how to carry out oil and gas exploitation and determine a preferential development area. And the oil and gas yield directly reflects the oil storage condition in the reservoir, so the oil and gas yield has an important role in making oil and gas exploitation decisions.

However, before oil and gas development is not carried out, the amount of oil and gas stored in a reservoir, particularly the oil and gas productivity, is generally unknown, and a complete core detection project consumes a long time, so that the rapid evaluation of oil and gas developers is not facilitated; well testing, namely researching various physical parameters, production capacity and communication relation between oil, gas and water layers of oil, gas and water layers and the test well through testing the production dynamics of the oil and gas well, is a traditional method for evaluating productivity, but the cost is high, and the current reservoir can be comprehensively evaluated only by being combined with other methods such as core analysis and the like.

In order to solve the problems that the prediction of oil and gas yield is time-consuming and high in cost in the related art, an effective solution is not provided at present.

Disclosure of Invention

The embodiment of the invention provides a method and a device for predicting oil and gas yield, which at least solve the technical problems of time consumption and high cost of oil and gas yield prediction in the related art.

According to an aspect of an embodiment of the present invention, there is provided a method for predicting hydrocarbon production, including: acquiring characteristic data of a core collected from a target reservoir, obtaining seepage data in the target reservoir according to measurement of the core, obtaining oil-containing data in the target reservoir according to measurement of the core, and carrying out oil and gas exploitation planning on the target reservoir; predicting the oil and gas yield in the target reservoir according to the characteristic data, the seepage data, the oil-containing data and the engineering data through a spectral clustering model, wherein the spectral clustering model is obtained by performing model training according to sample data corresponding to a sample rock core, and the sample data at least comprises: sample characteristic data, sample seepage data, sample oil-containing data, sample engineering data and sample oil-gas yield data corresponding to the sample core.

Optionally, before obtaining characteristic data of a core collected from a target reservoir, obtaining seepage data in the target reservoir according to measurement of the core, obtaining oil-containing data in the target reservoir according to measurement of the core, and performing oil and gas production planned engineering data on the target reservoir, the method further includes: acquiring training data corresponding to a sample rock core; predicting the predicted oil gas yield of the reservoir from which the sample core comes according to sample seepage data, sample oil-containing data and sample engineering data in the training data through a pre-constructed spectral clustering model; adjusting parameters of the pre-constructed spectral clustering model according to the predicted oil gas yield and the actual oil gas yield obtained by calculation according to sample oil gas yield data in the training data so that the distance between the predicted oil gas yield and the actual oil gas yield meets a preset condition; and when the training end condition is reached, taking the pre-constructed spectral clustering model after the parameters are adjusted as the spectral clustering model.

Optionally, before obtaining training data corresponding to the sample core, the method further includes: acquiring initial training data corresponding to each acquired sample rock core; and preprocessing the initial training data corresponding to each sample core to obtain the training data corresponding to each sample core.

Optionally, the preprocessing the initial training data corresponding to each sample core to obtain the training data corresponding to each sample core includes: carrying out noise reduction processing on the initial training data corresponding to each sample rock core; normalizing each parameter in the initial training data after the noise reduction treatment to obtain normalized data; calculating the correlation coefficient of every two parameters in the normalized data corresponding to each sample rock core; and filtering the normalized data according to the correlation coefficient to obtain training data corresponding to the sample rock core.

Optionally, the filtering the normalized data according to the correlation coefficient to obtain training data corresponding to the sample core includes: according to the correlation coefficient, determining a parameter of which the correlation coefficient with the parameter in the target data is lower than a first set threshold value in the reference operation data, and determining a parameter of which the correlation coefficient between the two parameters in the reference operation data is higher than a second set threshold value; and filtering one parameter of the parameters of which the correlation coefficient with the parameters in the target data is lower than a first set threshold value in the determined reference data and the parameters of which the correlation coefficient between the two parameters in the reference operation data is higher than a second set threshold value, and taking the filtered data as training data corresponding to the sample core.

Optionally, the characteristic data at least includes characteristic parameters describing characteristics of a core corresponding to the core, the seepage data at least includes seepage parameters describing pore seepage performance of the target reservoir, and the oil-containing data at least includes oil-containing parameters describing oil-gas conditions in the target reservoir.

Optionally, after predicting hydrocarbon production in the target reservoir from the characteristic data, the seepage data, the oil-bearing data, and the engineering data by a spectral clustering model, the method further comprises: and determining the reservoir classification corresponding to the target reservoir according to the predicted oil and gas yield.

According to another aspect of the embodiments of the present invention, there is also provided a hydrocarbon production prediction apparatus, including: the first acquisition module is used for acquiring characteristic data of a core collected from a target reservoir, obtaining seepage data in the target reservoir according to measurement of the core, obtaining oil-containing data in the target reservoir according to measurement of the core, and carrying out oil and gas exploitation planned engineering data on the target reservoir; the first prediction module is used for predicting the oil and gas yield in the target reservoir according to the characteristic data, the seepage data, the oil-containing data and the engineering data through a spectral clustering model, wherein the spectral clustering model is obtained by performing model training according to sample data corresponding to a sample rock core, and the sample data at least comprises: sample characteristic data, sample seepage data, sample oil-containing data, sample engineering data and sample oil-gas yield data corresponding to the sample core.

According to another aspect of the embodiment of the present invention, there is also provided a computer-readable storage medium, which includes a stored program, wherein when the program runs, the apparatus on which the computer-readable storage medium is located is controlled to execute the method for predicting hydrocarbon production.

According to another aspect of the embodiments of the present invention, there is also provided a processor for executing a program, wherein the program is executed to perform the method for predicting hydrocarbon production.

In the embodiment of the invention, the characteristic data of the core collected from a target reservoir is obtained, the seepage data in the target reservoir is obtained according to the measurement of the core, the oil-containing data in the target reservoir is obtained according to the measurement of the core, and the engineering data for oil and gas exploitation of the target reservoir is adopted; predicting the oil and gas yield in the target reservoir according to the characteristic data, the seepage data, the oil-containing data and the engineering data through a spectral clustering model, wherein the spectral clustering model is obtained by performing model training according to sample data corresponding to a sample rock core, and the sample data at least comprises: the method comprises the steps of obtaining the oil gas yield in a target reservoir through a spectral clustering model according to characteristic data, seepage data, oil-containing data and engineering data of a core in the target reservoir in a mode of sample characteristic data, sample seepage data, sample oil-containing data, sample engineering data and sample oil gas yield data corresponding to a sample core, and achieving the purpose of rapidly and accurately predicting the oil gas yield, so that the technical effects of improving the speed of predicting the oil gas yield and reducing the operation cost of predicting the oil gas yield are achieved, and the technical problems that the prediction of the oil gas yield is time-consuming and high in cost in the related technology are solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:

FIG. 1 is a flow chart of a method of predicting hydrocarbon production according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a hydrocarbon production prediction device according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

In accordance with an embodiment of the present invention, there is provided an embodiment of a method for hydrocarbon production prediction, it is noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions and that, although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than that presented herein.

Fig. 1 is a flowchart of a method for predicting hydrocarbon production according to an embodiment of the present invention, as shown in fig. 1, the method for predicting hydrocarbon production includes the steps of:

step S102, acquiring characteristic data of a core collected from a target reservoir, obtaining seepage data in the target reservoir according to core measurement, obtaining oil-containing data in the target reservoir according to core measurement, and carrying out oil and gas exploitation planning on the target reservoir;

in order to know the geological condition or the mineral condition in the reservoir, the core needs to be collected from the reservoir for analysis, and the analysis data of the core is used as the field address data for analyzing the reservoir condition. In other words, the core is a sample rock taken from a reservoir of interest.

As an alternative embodiment, in order to estimate the hydrocarbon production in the target reservoir, a core is collected from the target reservoir, and the estimation of the hydrocarbon production in the target reservoir is performed by using the analysis data of the core. The target reservoir is not specific to a certain reservoir, but generally refers to a reservoir to be subjected to oil and gas yield estimation.

The characteristic data of the core can be basic information of the core, such as the depth of a target reservoir from which the core is derived, the pressure gradient at the target reservoir, and information describing the pore structure in the core.

It should be noted that the core includes pores and a skeleton, and if a target reservoir from which the core is derived has a hydrocarbon resource, the hydrocarbon resource actually exists in the pores in the target reservoir, so that the pore condition in the target reservoir can be known by means of analysis of the core.

In particular embodiments, the characteristic parameters include, but are not limited to, depth, pressure gradient, core type, core density, cementation type, clay content, primary particle size, sorting coefficient, kurtosis, skewness, median pore throat radius, maximum pore throat radius, average capillary radius, pore throat volume ratio, capillary median pressure, displacement pressure, mercury removal efficiency.

Wherein, the depth refers to the depth of a target reservoir from which the core is derived in geology. The pressure gradient corresponding to the core refers to a pressure gradient corresponding to the depth of a target reservoir from which the core is derived. The pressure gradient is characterized by the change in pressure per unit length of the path in the direction of fluid flow.

The core type refers to the classification of the core classified according to the set type, and the core type comprises cemented clastic rock, carbonate, loose sandstone, karst cave carbonate rock, clay-containing rock, low-permeability rock, shale, oil shale and the like. Of course, the above list of core types is merely an illustrative example and should not be taken as limiting the scope of use of the present disclosure.

Alternatively, the classification standard corresponding to the core type may be a classification standard set according to the composition of the core. Alternatively, the classification criterion corresponding to the core type may also be a grain size.

The core type can be determined by performing component analysis or further performing microstructure observation on the collected core.

The type of cementation refers to the contact relationship between the cement or interstitial material and the particles of detritus in the core. In particular, the types of bonds include substrate bonds, pore bonds, contact bonds, and damascene bonds. For basal cementing, it appears that the crushed rock particles do not touch; for pore-type cementation, it is characterized by point contact between particles, the cement being distributed in the pores; the contact cementation is characterized in that the particles are in point-line contact, and the cementate is distributed at the contact position; the mosaic cementation expression is as follows: the particles are in line contact or concave contact.

The cement refers to the mineral in the rock core which is formed in the intergranular space in a chemical precipitation mode, and the cement comprises siliceous materials, carbonate and partial iron. Thus, the types of cement may also include argillaceous cements, calcareous cements, siliceous cements, ferro-manganese cements, classified according to the type of cement.

For the cores, the cementing types are different, and the mechanical properties of the cores are correspondingly different, so that the oil and gas storage conditions in target reservoirs from which the cores with different cementing types are sourced may also be different.

In particular embodiments, the type of cement to which the core corresponds may be determined by microscopic observation or compositional testing of the core.

For cores derived from the reservoir of interest, the core is rock from which rock debris and mineral debris formed from mechanical weathering of the rock has been transported, deposited, compacted and cemented, and thus the rock is actually clastic. Therefore, the skeleton in the core is formed by combining a plurality of debris particles.

In order to determine parameters such as main particle size, kurtosis, skewness and sorting coefficient corresponding to the rock core, particle size statistics is carried out on the clastic particles in the rock core. The particle size refers to the size of particles, and is generally expressed as a diameter.

In particular embodiments, the particle size of the debris particles may be characterized by an equivalent particle size, due to the variety of shapes of the actual particles, such as the presence of debris particles that are not spherical. Wherein, the equivalent particle size means that when a particle has a physical property identical or similar to that of a homogeneous spherical particle, the diameter of the spherical particle is used to represent the diameter of the actual particle.

After the particle size of each crumb particle in the core is measured, a cumulative particle size curve for the core is further constructed based on the particle size of each crumb particle. The determination of the main particle diameter, kurtosis, skewness, and sorting coefficient is performed based on the particle size accumulation curve.

Wherein, the main particle size refers to the particle size corresponding to the cumulative particle size distribution number reaching the set proportion on the particle size cumulative curve corresponding to the rock core. The set ratio may be selected according to actual needs, for example, the set ratio is selected to be 50%, 60%, 75%, etc., and is not particularly limited herein.

The sorting coefficient is a ratio of diameters of debris particles corresponding to 75% and 25% on a particle size cumulative curve, and serves as a reference of core sorting performance, when the sorting performance of the core is good, the two values of P25 (namely, the particle size corresponding to 25% of cumulative particle size distribution) and P75 (namely, the particle size corresponding to 75% of cumulative particle size distribution) are very close to each other, the closer to 1, and on the contrary, the larger the value is, the more the value is, the core sorting performance is, and the more the value is, the more the value is, the more the value is, the value is more the value, the value is, the value is, the value is, the value is, the value.

Kurtosis, also known as the index coefficient. The kurtosis corresponding to the core is a characteristic number of the average particle size with the peak height on a particle size accumulation curve, and the kurtosis reflects the sharpness of a peak. The kurtosis corresponding to the core can be calculated according to the following formula:

wherein X represents the particle size of the chip particles in the core, mu is the average particle size, and sigma is the standard deviation.

The skewness corresponding to the core is a characteristic number used for representing the asymmetry degree of a particle size accumulation curve relative to the average particle size. The skewness corresponding to the core can be calculated by the following formula:

in addition to solid phases such as debris particles and cement, the core also includes a plurality of pores, and oil and gas in a target reservoir where the core is located actually exist in the pores. The distribution of the pores in the core can approximately reflect the pore distribution in the target reservoir, and further approximately reflect the oil-gas distribution in the target reservoir. The median pore throat radius, the maximum pore throat eight-piece, the pore throat volume ratio, the average capillary radius and the like can be used as characteristic parameters for reflecting the pore distribution in the rock core.

The pore throat radius, also known as the pore throat radius, is measured as the maximum spherical radius that can pass through the pore throat. It will be appreciated that several pore throats are included in the core. To understand the overall distribution of pores in the core, the pore distribution in the core is generally reflected by the median pore throat radius and the maximum pore throat radius.

The pore-throat volume ratio refers to the ratio of the pore volume in the core to the throat volume.

The capillary pressure median value refers to the capillary pressure value corresponding to the mercury saturation of 50%. The capillary pressure median is obtained by measuring the capillary pressure curve of the core for which capillary pressure is determined by the curvature of the non-wetting phase surface, which in turn is related to the size of the pore throat, and for which capillary pressure increases as the saturation of the wet phase decreases. The capillary pressure median value corresponding to the core can be measured by a mercury intrusion method, a centrifugal method and the like.

Drainage pressure refers to the lowest pressure required for the non-wetting phase (mercury) to begin to enter the core, and is the start pressure required for the mercury to begin to enter the core at the maximum communication pore throat to form a continuous flow. The radius of a pore throat which mercury can enter under the drainage pressure is the maximum pore throat radius in the rock core.

If a mercury pressing method is selected to measure the capillary pressure median value and the displacement pressure, wherein the processes of pressing mercury and removing mercury into the pore throat of the core are involved, an important characteristic parameter of the mercury removing process is the mercury removing efficiency. Mercury removal efficiency is the ratio of the volume of mercury removed from the core of the rock to the volume of mercury injected during the pressing process when the maximum injection pressure is reduced to the minimum pressure after the pressing process is completed.

The above lists only the reflection of the porosity in the core by the characteristic parameters of median pore throat radius, maximum pore throat radius, capillary pressure median, pore throat volume ratio, displacement pressure and mercury removal efficiency. In other embodiments, parameters characterizing pore throat sorting characteristics (e.g., pore throat sorting coefficient, pore throat kurtosis, mean coefficient), pore throat connectivity, and fluid flow control characteristics (e.g., pore throat coordination number, pore tortuosity, etc.) may be further selected as characteristic parameters.

The characteristic parameters for characterizing the pore condition in the core may be measured by a mercury intrusion method, a dynamic displacement method, a centrifuge method, or the like, or may be measured by constructing a digital core as a pore structure model in the core, analyzing the digital core, and performing a simulation experiment, which is not specifically limited herein.

For paint stored in the target reservoir, it is constantly flowing in the pores. While the seepage parameters may reflect the seepage performance of pores in the target reservoir. In particular embodiments, the percolation parameter may be at least one of porosity, permeability.

Porosity is the ratio of the pore volume to the solid volume in the core, and porosity is a parameter for measuring the storage capacity of the core.

Permeability is the ability of the core to allow fluid to pass through. Permeability characterizes the core's ability to conduct fluids. In practice, the permeability may be at least one of an absolute permeability, an effective permeability, or a relative permeability, and is not particularly limited herein.

The oil content parameter is used to describe the oil content in the target reservoir. In particular implementations, the oil parameters include, but are not limited to, oil saturation, free fluid saturation, irreducible water saturation, crude oil viscosity, parameters indicating wax content.

Wherein, the oil saturation refers to the ratio of the volume of pores occupied by crude oil in an oil layer to the total pore volume. The free fluid saturation refers to the ratio of the volume of the pores in which the free fluid is located to the total pore volume in the oil layer, wherein the free fluid can be water, oil or gas. If water, oil and gas exist in a reservoir simultaneously, the ratio of the volume of the pores occupied by the water, oil and gas in the reservoir to the total pore volume is the free fluid saturation in the reservoir.

A large amount of field coring analysis shows that even a pure oil-gas reservoir contains a certain amount of stagnant water with oil inside, and the stagnant water in the reservoir is called bound water. The existence of the bound water is related to the formation process of oil reservoirs, and different oil reservoirs have different oil and gas migration conditions due to different rock and fluid properties, so that the saturation of the bound water is greatly different. Irreducible water saturation refers to the ratio of the volume of the pores occupied by irreducible water in the target reservoir to the total pore volume.

The oil saturation, the free fluid saturation, the irreducible water saturation and other oil-containing parameters can be measured by an atmospheric dry distillation method, a distillation drawer method, a chromatography method and a well logging method, the oil saturation and the water saturation in the rock core can be determined by a relative permeability curve or a capillary pressure curve, and the oil saturation and the water saturation in the rock core are used as the oil saturation and the water saturation in a target reservoir from which the rock core is derived.

Crude oil viscosity is a measure of the frictional resistance of one part of the crude oil interior to flow relative to another. Crude oil viscosity may be measured by taking a sample of crude oil in a reservoir of interest (e.g., crude oil in a core) and performing a physical experiment on the crude oil sample.

The engineering data may include one or more engineering parameters such as total amount of fracturing fluid, type of proppant, amount of proppant, etc., and is not specifically limited herein.

The fracturing fluid is a heterogeneous unstable chemical system formed by a plurality of additives according to a certain proportion, and is a working fluid used for fracturing modification of an oil-gas layer. Its main function is to transmit the high pressure created by surface equipment into the formation, fracture the formation to form fractures and transport proppant along the fractures.

The total amount of the fracturing fluid refers to the total amount of the fracturing fluid which is supposed to be used for oil and gas exploitation of a target reservoir.

When the oil and gas deep well is exploited, the high closure pressure and low permeability deposit is fractured to crack the oil and gas containing rock stratum, the oil and gas are collected from the channel formed by the fracture, at the moment, the fluid is injected into the rock base layer to exceed the pressure of the fracture strength of the stratum, so that the rock stratum around the shaft is fractured to form a channel with high laminar flow capacity, and the oil and gas product can smoothly pass through the channel to keep the fracture formed after fracturing open. Wherein the fluid injected into the demonstration substrate is the proppant. Among the proppant types are hard brittle ceramic proppants and ductile proppants. Proppant volume refers to the volume of proppant proposed for oil and gas production from a target reservoir.

Step S104, predicting the oil and gas yield in the target reservoir according to the characteristic data, the seepage data, the oil-containing data and the engineering data through a spectral clustering model, wherein the spectral clustering model is obtained by performing model training according to sample data corresponding to a sample rock core, and the sample data at least comprises: sample characteristic data, sample seepage data, sample oil-containing data, sample engineering data and sample oil and gas yield data corresponding to the sample core.

The sample characteristic data refers to characteristic data corresponding to the sample rock core and comprises at least one characteristic parameter for describing the characteristic of the rock core corresponding to the sample rock core. The characteristic parameters are referred to in the above list.

The sample seepage data refers to seepage data in a reservoir from which the core sample is obtained according to the measurement of the core sample, and comprises at least one seepage parameter for describing pore seepage performance in the reservoir from which the core sample is obtained, and the seepage parameter is described in the above list.

The sample oil content data refers to the oil content data of a reservoir from which the sample core is obtained according to measurement of the sample core, and comprises at least one oil content parameter for describing the oil-gas condition of the reservoir from which the sample core is obtained. Oil content parameters are detailed in the above examples.

The sample engineering data refers to engineering parameters actually adopted for oil and gas exploitation of a reservoir from which the sample core is derived, and the engineering parameters are described in detail in the above list.

The sample oil and gas production data refers to the oil and gas volume data obtained by oil and gas exploitation of the reservoir from which the sample core is derived according to the engineering parameters in the sample engineering data. In particular embodiments, the sample hydrocarbon production data may include daily oil production, reservoir thickness, and the operating regime (i.e., the length of time each day of production).

In the training process, the initial model is used for clustering the oil gas yield according to sample characteristic data, sample seepage data, sample oil-containing data and sample engineering data in the sample data by taking the oil gas yield indicated by the sample oil gas yield data in each sample data as a target to obtain the predicted oil gas yield. And adjusting parameters of the model based on the predicted hydrocarbon production and the actual hydrocarbon production indicated by the sample hydrocarbon production data until the predicted hydrocarbon production is sufficiently close to the actual hydrocarbon production, e.g., the predicted hydrocarbon production is the same as the actual hydrocarbon production. And then, continuing to perform model training by using sample data corresponding to the next sample core until a training end condition is reached.

After the spectral clustering model is obtained through the training process, the spectral clustering model has the capability of estimating the oil and gas yield in the reservoir according to the characteristic data, the seepage data, the oil-containing data and the engineering data, so that the estimated oil and gas yield is output.

Through the above process, the estimation of the oil and gas production in the target reservoir is carried out through the trained spectral clustering model, the estimated oil and gas production is used as a decision reference for carrying out oil and gas exploitation, for example, a preferential development area is determined according to the predicted oil and gas production, and the like.

In the specific implementation process, the most key physical parameters determining the productivity performance can be selected by utilizing big data clustering and establishing a correlation model based on the existing exploration and development well core, formation test data and oil and gas production historical data; after the new well is drilled, the key physical parameters are preferentially detected through a core test, the oil and gas yield is rapidly predicted by using the correlation model established in the early stage, reference is provided for production designers of the new well, reasonable matching measures are designed, and the operation cost is reduced.

It should be noted that the big data oil and gas reserves prediction method based on reservoir experimental parameters can be applied to a glutenite area, and the reservoir type of the current well can be rapidly judged and the predicted capacity can be given out by using key 8-10 core test data in a plurality of working days after the new well drilling is finished.

Through the steps, the oil and gas yield in the target reservoir can be obtained through the spectral clustering model according to the characteristic data, the seepage data, the oil-containing data and the engineering data of the rock core in the target reservoir, the purpose of quickly and accurately predicting the oil and gas yield is achieved, the technical effects of improving the speed of predicting the oil and gas yield and reducing the operation cost of predicting the oil and gas yield are achieved, and the technical problems that the prediction of the oil and gas yield is time-consuming and high in cost in the related technology are solved.

Optionally, before obtaining characteristic data of a core collected from the target reservoir, obtaining seepage data in the target reservoir according to measurement of the core, obtaining oil-containing data in the target reservoir according to measurement of the core, and performing oil and gas exploitation planned engineering data on the target reservoir, the method further includes: acquiring training data corresponding to a sample rock core; predicting the predicted oil gas yield of the reservoir where the sample core is sourced according to sample seepage data, sample oil-containing data and sample engineering data in the training data through a pre-constructed spectral clustering model; adjusting parameters of a pre-constructed spectral clustering model according to the predicted oil gas yield and the actual oil gas yield obtained by calculation according to sample oil gas yield data in the training data so that the distance between the predicted oil gas yield and the actual oil gas yield meets a preset condition; and when the training end condition is reached, taking the pre-constructed spectral clustering model after the parameters are adjusted as a spectral clustering model.

The preset condition may be that the predicted oil gas production is equal to the actual oil gas production, or that the distance between the predicted oil gas production and the actual oil gas production satisfies a numerical range, which is not specifically limited herein. In summary, in the training process, the adjustment of the pre-constructed spectral clustering model parameters is performed according to the target that the predicted oil gas yield is close to the actual oil gas yield. After each parameter adjustment, oil gas yield prediction is carried out again through the pre-constructed spectral clustering model after the parameters are adjusted, whether the predicted oil gas yield obtained through prediction again and the actual oil gas yield meet preset conditions or not is calculated, and if yes, next sample data are used for training; if not, the process is repeated.

The pre-constructed spectral clustering model can be constructed according to sample characteristic data, sample seepage data, sample oil-containing data, sample engineering data and sample oil and gas yield data corresponding to a plurality of sample cores. It is worth mentioning that the sample core used for pre-constructing the spectral clustering model is different from the sample core used for training the pre-constructed spectral clustering model.

The training end condition may be the number of iterations or the prediction accuracy, and is not particularly limited herein. Specifically, when the training end condition is the number of iterations, if the number of iterations in the training process reaches the set number of iterations, the training is stopped, and the pre-constructed spectral clustering model with the parameters adjusted is used as the spectral clustering model. When the training end condition is prediction quasi-measure, after the pre-constructed spectral clustering model is trained for a period of time, the prediction accuracy of the model is calculated through the test sample, if the prediction accuracy meets the set prediction accuracy requirement, the training is stopped, and if the prediction accuracy does not meet the set prediction accuracy requirement, the training is continued. The test sample comprises sample characteristic data, sample seepage data, sample oil-containing data, sample engineering data and sample oil and gas yield data corresponding to a plurality of sample cores.

The spectral clustering model is obtained by training according to sample characteristic data, sample seepage data, sample oil-containing data, sample engineering data and sample oil and gas yield data obtained by actually carrying out oil and gas exploitation in the actual oil and gas exploitation, so that the accuracy of the oil and gas yield predicted by the spectral clustering model can be ensured.

The preprocessing may be noise reduction, numerical mapping, normalization, filtering, etc., and is not particularly limited herein. By preprocessing, the training data can be directly identified by the pre-constructed spectral clustering model so as to be directly trained without other data processing.

Optionally, preprocessing the initial training data corresponding to each sample core, and obtaining the training data corresponding to each sample core includes: carrying out noise reduction processing on initial training data corresponding to each sample rock core; normalizing each parameter in the initial training data after the noise reduction treatment to obtain normalized data; calculating the correlation coefficient of every two parameters in the normalized data corresponding to each sample rock core; and filtering the normalized data according to the correlation coefficient to obtain training data corresponding to the sample rock core.

Wherein, the normalization processing means calculating the average value and standard deviation of each parameter in the data after the noise reduction processing, and according to a formula

The value corresponding to each parameter is transformed, wherein,

the average value of the parameter Y is represented, and σ represents the standard deviation of the parameter Y, so that the parameter Y is converted into Y' by the above conversion, thereby realizing the normalization of the parameter Y.

Wherein, the calculation of the correlation coefficient is carried out, namely, the correlation coefficient between two different parameters in the parameters of each characteristic parameter, each oil content parameter, each seepage parameter, each engineering parameter and the oil gas yield in the normalized data is calculated.

The correlation coefficient is calculated by the formula:

where Corr (M, N) is the covariance of parameter M and parameter N, σ_mIs the variance, σ, of the parameter M_nIs the variance of the parameter N, thereby obtaining the parameter M and the parameter according to the formulaThe correlation coefficient of N. The correlation coefficient calculated is in the range of [0, 1 ]]0 means no correlation and 1 means a complete linear correlation. And determining the correlation magnitude between the two parameters according to the calculated correlation coefficient.

Optionally, the filtering the normalized data according to the correlation coefficient to obtain training data corresponding to the sample core includes: according to the correlation coefficient, determining a parameter of which the correlation coefficient with the parameter in the target data in the reference operation data is lower than a first set threshold value, and determining a parameter of which the correlation coefficient between the two parameters in the reference operation data is higher than a second set threshold value; and filtering one parameter of the parameters of which the correlation coefficient with the parameters in the target data is lower than a first set threshold value and the parameters of which the correlation coefficient between the two parameters in the reference operation data is higher than a second set threshold value in the determined reference data, and taking the filtered data as training data corresponding to the sample core.

As an alternative embodiment, the normalized data includes actual hydrocarbon production and reference operation data, and the reference operation data is data other than the actual hydrocarbon production in the normalized data.

The first set threshold and the second set threshold are set for judging the correlation between the two parameters. Specifically, if the correlation coefficient of the two parameters is lower than a first set threshold, determining that the correlation between the two parameters is low; and if the correlation coefficient of the two parameters is higher than a second set threshold value, determining that the correlation between the two parameters is high.

And if the correlation coefficient between a parameter and the actual oil and gas production in the reference operation data is lower than a first set threshold value, determining that the correlation between the parameter and the actual oil and gas production is low, indicating that the parameter does not contribute much to the oil and gas production prediction, and filtering the parameter.

If the correlation coefficient of the two parameters in the reference operation data is higher than the second set threshold, it indicates that the correlation coefficient of the two parameters is high, and one of the two parameters can be represented by the other parameter, so that one of the two parameters can be eliminated.

Optionally, the characteristic data at least includes characteristic parameters describing characteristics of the core corresponding to the core, the seepage data at least includes seepage parameters describing pore seepage performance of the target reservoir, and the oil-containing data at least includes oil-containing parameters describing oil-gas conditions in the target reservoir.

Optionally, after predicting the hydrocarbon production in the target reservoir according to the characteristic data, the seepage data, the oil-bearing data and the engineering data through the spectral clustering model, the method further comprises: and determining the reservoir classification corresponding to the target reservoir according to the predicted oil and gas yield.

Wherein the reservoir classification is divided according to oil and gas production.

As an optional embodiment, the reservoir is divided into three categories according to oil and gas production, the oil and gas production is characterized by oil and gas production per meter day, the reservoir categories comprise category I, category II and category III, wherein the range of oil and gas production per meter day corresponding to the category I reservoir is greater than or equal to 2.2 tons; the range of oil gas production per meter per day (unit: ton) corresponding to the II type reservoir is 0.6 and 2.2; the range of oil and gas production per meter per day (unit: ton) for a class III reservoir is 0, 0.6. Of course, in other embodiments, the reservoir types may be divided according to actual needs, and the above is only an exemplary example and should not be considered as limiting the scope of the disclosure.

After the reservoir classification corresponding to the target reservoir is determined, oil and gas exploitation in the reservoir can be planned in a targeted manner, for example, for the reservoir of the type I, the oil and gas production per meter per day is high, and the reservoir is an area with good economic benefit and can be used as a preferential development area. Thus, the determined reservoir classification may be used as a reference for planning hydrocarbon production.

Example 2

According to another aspect of the embodiment of the present invention, there is also provided a hydrocarbon production prediction apparatus, fig. 2 is a schematic diagram of a hydrocarbon production prediction apparatus according to an embodiment of the present invention, as shown in fig. 2, the hydrocarbon production prediction apparatus includes: a first acquisition module 22 and a first prediction module 24. The oil and gas production prediction device will be described in detail below.

The first acquisition module 22 is used for acquiring characteristic data of a core collected from a target reservoir, obtaining seepage data in the target reservoir according to measurement of the core, obtaining oil-containing data in the target reservoir according to measurement of the core, and carrying out oil and gas exploitation planning on the target reservoir; a first prediction module 24, connected to the first obtaining module 22, configured to predict, according to the feature data, the seepage data, the oil-bearing data, and the engineering data, an oil-gas yield in the target reservoir through a spectral clustering model, where the spectral clustering model is obtained by performing model training according to sample data corresponding to a sample core, where the sample data at least includes: sample characteristic data, sample seepage data, sample oil-containing data, sample engineering data and sample oil and gas yield data corresponding to the sample core.

It should be noted that the above modules may be implemented by software or hardware, for example, for the latter, the following may be implemented: the modules can be located in the same processor; alternatively, the modules may be located in different processors in any combination.

It should be noted here that the first obtaining module 22 and the first predicting module 24 correspond to steps S102 to S104 in embodiment 1, and the modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of embodiment 1. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.

As can be seen from the above, in the above embodiments of the present application, the oil and gas yield in the target reservoir is predicted according to the characteristic data, the seepage data, the oil-containing data, and the engineering data of the core in the target reservoir by the spectral clustering model, so as to achieve the purpose of predicting the oil and gas yield quickly and accurately, thereby achieving the technical effects of increasing the speed of predicting the oil and gas yield and reducing the operation cost of predicting the oil and gas yield, and further solving the technical problems of time consumption and high cost of predicting the oil and gas yield in the related art.

Optionally, before obtaining characteristic data of a core collected from a target reservoir, obtaining seepage data in the target reservoir according to measurement of the core, obtaining oil-containing data in the target reservoir according to measurement of the core, and performing oil and gas exploitation planned engineering data on the target reservoir, the apparatus further includes: the second acquisition module is used for acquiring training data corresponding to the sample rock core; the second prediction module is used for predicting the predicted oil and gas yield of the reservoir where the sample rock core comes from according to sample seepage data, sample oil-containing data and sample engineering data in the training data through a pre-constructed spectral clustering model; the adjusting module is used for adjusting parameters of the pre-constructed spectral clustering model according to the predicted oil gas yield and the actual oil gas yield obtained by calculation according to the sample oil gas yield data in the training data so that the distance between the predicted oil gas yield and the actual oil gas yield meets the preset condition; and the processing module is used for taking the pre-constructed spectral clustering model after the parameters are adjusted as the spectral clustering model when the training ending condition is reached.

Optionally, before obtaining training data corresponding to the sample core, the apparatus further includes: the third acquisition module is used for acquiring initial training data corresponding to each acquired sample rock core; and the preprocessing module is used for preprocessing the initial training data corresponding to each sample core to obtain the training data corresponding to each sample core.

Optionally, the preprocessing module includes: the noise reduction unit is used for carrying out noise reduction processing on the initial training data corresponding to each sample rock core; the normalization unit is used for normalizing each parameter in the initial training data after the noise reduction processing to obtain normalized data; the calculation unit is used for calculating the correlation coefficient of every two parameters in the normalized data corresponding to each sample rock core; and the filtering unit is used for filtering the normalized data according to the correlation coefficient to obtain training data corresponding to the sample rock core.

Optionally, the filter unit comprises: the determining subunit is used for determining a parameter, of which the correlation coefficient with the parameter in the target data is lower than a first set threshold value, in the reference operation data and determining a parameter, of which the correlation coefficient between the two parameters in the reference operation data is higher than a second set threshold value, according to the correlation coefficient; and the filtering subunit is used for filtering one of the parameters of which the correlation coefficient with the parameters in the target data is lower than a first set threshold value and the parameters of which the correlation coefficient between the two parameters in the reference operation data is higher than a second set threshold value, and taking the filtered data as training data corresponding to the sample core.

Optionally, after the oil and gas production in the target reservoir is predicted by the spectral clustering model according to the characteristic data, the seepage data, the oil-containing data and the engineering data, the apparatus further comprises: and the determining module is used for determining the reservoir classification corresponding to the target reservoir according to the predicted oil and gas yield.

Example 3

According to another aspect of the embodiments of the present invention, there is also provided a computer readable storage medium, which includes a stored program, wherein the program when executed controls an apparatus where the computer readable storage medium is located to perform the method for predicting hydrocarbon production.

Optionally, in this embodiment, the computer-readable storage medium may be located in any one of a group of computer terminals in a computer network or in any one of a group of mobile terminals, and the computer-readable storage medium includes a stored program.

Optionally, the program when executed controls an apparatus in which the computer-readable storage medium is located to perform the following functions: acquiring characteristic data of a core collected from a target reservoir, obtaining seepage data in the target reservoir according to measurement of the core, obtaining oil-containing data in the target reservoir according to measurement of the core, and carrying out oil and gas exploitation planned engineering data on the target reservoir; predicting the oil and gas yield in the target reservoir through a spectral clustering model according to the characteristic data, the seepage data, the oil-containing data and the engineering data, wherein the spectral clustering model is obtained by performing model training according to sample data corresponding to a sample rock core, and the sample data at least comprises: sample characteristic data, sample seepage data, sample oil-containing data, sample engineering data and sample oil and gas yield data corresponding to the sample core.

Example 4

According to another aspect of the embodiments of the present invention, there is also provided a processor for executing a program, wherein the program when executed performs the method for predicting hydrocarbon production as described in any one of the above.

The embodiment of the application provides equipment, which comprises a processor, a memory and a program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the following steps: acquiring characteristic data of a core collected from a target reservoir, obtaining seepage data in the target reservoir according to measurement of the core, obtaining oil-containing data in the target reservoir according to measurement of the core, and carrying out oil and gas exploitation planned engineering data on the target reservoir; predicting the oil and gas yield in the target reservoir through a spectral clustering model according to the characteristic data, the seepage data, the oil-containing data and the engineering data, wherein the spectral clustering model is obtained by performing model training according to sample data corresponding to a sample rock core, and the sample data at least comprises: sample characteristic data, sample seepage data, sample oil-containing data, sample engineering data and sample oil and gas yield data corresponding to the sample core.

The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: acquiring characteristic data of a core collected from a target reservoir, obtaining seepage data in the target reservoir according to measurement of the core, obtaining oil-containing data in the target reservoir according to measurement of the core, and carrying out oil and gas exploitation planned engineering data on the target reservoir; predicting the oil and gas yield in the target reservoir through a spectral clustering model according to the characteristic data, the seepage data, the oil-containing data and the engineering data, wherein the spectral clustering model is obtained by performing model training according to sample data corresponding to a sample rock core, and the sample data at least comprises: sample characteristic data, sample seepage data, sample oil-containing data, sample engineering data and sample oil and gas yield data corresponding to the sample core.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims

1. A method for predicting hydrocarbon production, comprising:

acquiring characteristic data of a core collected from a target reservoir, obtaining seepage data in the target reservoir according to measurement of the core, obtaining oil-containing data in the target reservoir according to measurement of the core, and carrying out oil and gas exploitation planning on the target reservoir;

predicting the oil and gas yield in the target reservoir according to the characteristic data, the seepage data, the oil-containing data and the engineering data through a spectral clustering model, wherein the spectral clustering model is obtained by performing model training according to sample data corresponding to a sample rock core, and the sample data at least comprises: sample characteristic data, sample seepage data, sample oil-containing data, sample engineering data and sample oil-gas yield data corresponding to the sample core.

2. The method of claim 1, wherein prior to obtaining characteristic data of a core collected from a target reservoir, obtaining seepage data in the target reservoir based on measurements of the core, obtaining oil-bearing data in the target reservoir based on measurements of the core, and engineering data intended for oil and gas production from the target reservoir, the method further comprises:

acquiring training data corresponding to a sample rock core;

predicting the predicted oil gas yield of the reservoir from which the sample core comes according to sample seepage data, sample oil-containing data and sample engineering data in the training data through a pre-constructed spectral clustering model;

adjusting parameters of the pre-constructed spectral clustering model according to the predicted oil gas yield and the actual oil gas yield obtained by calculation according to sample oil gas yield data in the training data so that the distance between the predicted oil gas yield and the actual oil gas yield meets a preset condition;

and when the training end condition is reached, taking the pre-constructed spectral clustering model after the parameters are adjusted as the spectral clustering model.

3. The method of claim 2, wherein prior to obtaining training data corresponding to the sample core, the method further comprises:

acquiring initial training data corresponding to each acquired sample rock core;

and preprocessing the initial training data corresponding to each sample core to obtain the training data corresponding to each sample core.

4. The method according to claim 3, wherein preprocessing the initial training data corresponding to each sample core to obtain the training data corresponding to each sample core comprises:

carrying out noise reduction processing on the initial training data corresponding to each sample rock core;

normalizing each parameter in the initial training data after the noise reduction treatment to obtain normalized data;

calculating the correlation coefficient of every two parameters in the normalized data corresponding to each sample rock core;

and filtering the normalized data according to the correlation coefficient to obtain training data corresponding to the sample rock core.

5. The method according to claim 4, wherein the filtering the normalized data according to the correlation coefficient to obtain training data corresponding to the sample core comprises:

according to the correlation coefficient, determining a parameter of which the correlation coefficient with the parameter in the target data is lower than a first set threshold value in the reference operation data, and determining a parameter of which the correlation coefficient between the two parameters in the reference operation data is higher than a second set threshold value;

and filtering one parameter of the parameters of which the correlation coefficient with the parameters in the target data is lower than a first set threshold value in the determined reference data and the parameters of which the correlation coefficient between the two parameters in the reference operation data is higher than a second set threshold value, and taking the filtered data as training data corresponding to the sample core.

6. The method according to any one of claims 1 to 5, wherein the characteristic data at least comprises characteristic parameters describing characteristics of a core corresponding to the core, the seepage data at least comprises seepage parameters describing pore seepage performance of the target reservoir, and the oil-containing data at least comprises oil-containing parameters describing oil-gas conditions in the target reservoir.

7. The method of any one of claims 1 to 5, further comprising, after predicting hydrocarbon production in the target reservoir from the characteristic data, the seepage data, the oil-bearing data, and the engineering data by a spectral clustering model:

and determining the reservoir classification corresponding to the target reservoir according to the predicted oil and gas yield.

8. A hydrocarbon production prediction device, comprising:

the first acquisition module is used for acquiring characteristic data of a core collected from a target reservoir, obtaining seepage data in the target reservoir according to measurement of the core, obtaining oil-containing data in the target reservoir according to measurement of the core, and carrying out oil and gas exploitation planned engineering data on the target reservoir;

the first prediction module is used for predicting the oil and gas yield in the target reservoir according to the characteristic data, the seepage data, the oil-containing data and the engineering data through a spectral clustering model, wherein the spectral clustering model is obtained by performing model training according to sample data corresponding to a sample rock core, and the sample data at least comprises: sample characteristic data, sample seepage data, sample oil-containing data, sample engineering data and sample oil-gas yield data corresponding to the sample core.

9. A computer-readable storage medium, comprising a stored program, wherein the program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the method for hydrocarbon production prediction of any one of claims 1-7.

10. A processor for running a program, wherein the program when run performs the method of hydrocarbon production prediction of any one of claims 1 to 7.