Intelligent reservoir classification method, device and equipment based on capillary pressure curve

Abstract

The invention relates to the technical field of exploration and development, in particular to an intelligent reservoir classification method, device and equipment based on a capillary pressure curve. Comprising the following steps: acquiring experimental data of a plurality of capillary pressure curves, and carrying out hemp skin effect correction and formation condition capillary pressure curve conversion; a non-reservoir capillary pressure curve is removed from the pore throat distribution curve, reservoir classification features of the reservoir capillary pressure curve are obtained, classification preparation of the reservoir capillary pressure curve is achieved, and distance function construction of data standardization and reservoir classification feature parameters is completed; constructing a distance function of capillary pressure curve classification according to the parameters of the reservoir classification features, and performing clustering; and generating a classification result of each capillary pressure curve based on a clustering result of the distance function. According to the method, the most basic capillary pressure curve data is input, and multi-level reservoir classification is realized by integrating all the data of the capillary pressure curve.

Description

TECHNICAL FIELD

[0001] The present specification relates to the technical field of exploration and development, and particularly relates to a reservoir intelligent classification method and device based on capillary pressure curve and equipment. BACKGROUND

[0002] At present, reservoir classification is one of the core tasks in oil and gas reservoir evaluation. Reservoir classification not only helps to understand the physical properties of the reservoir, but also provides an important basis for subsequent oil and gas exploration, development and production. Capillary curve, as an effective tool, can reflect the pore structure and fluid properties of the reservoir, and is an important means to realize reservoir classification.

[0003] Different types of reservoirs have different physical properties and fluid properties, which directly affect the exploration and development methods of oil and gas. Through capillary curve classification to realize reservoir classification, targeted suggestions and strategies can be provided for subsequent oil and gas exploration and development, including different types of reservoirs needing to adopt different exploitation schemes in the exploitation process. For example, for reservoirs with good permeability, a relatively simple exploitation method can be used; while for reservoirs with poor permeability, more complex exploitation techniques need to be adopted. Through reservoir classification, the exploitation scheme can be optimized to improve the exploitation efficiency. The physical properties and fluid properties of the reservoir have an important influence on oil and gas production. Through reservoir classification, a permeability model can be established to predict the oil and gas production of different reservoirs, providing an important reference for subsequent oil and gas production.

[0004] The existing reservoir classification technology relies more on manual work, especially the need for manual extraction of capillary pressure curve characteristic parameters such as displacement pressure, median pressure, average pore throat radius, etc., and then through cross plot analysis for classification, or giving a target function for automatic classification, on the one hand, it is heavily dependent on these capillary pressure curve characteristic parameters, so the accurate acquisition of parameters is crucial, on the other hand, the limited characteristic parameters exist the risk of information loss, the determination of the target function also faces challenges, the classification efficiency and quality still have a lot of room for improvement. The existing capillary pressure curve classification method is difficult to realize full automation, and the classification efficiency is relatively low; the work mode of extracting features for classification is difficult to comprehensively apply capillary pressure curve information, resulting in the accuracy of the result being more dependent on the experience level of the person, and the quality is at risk.

[0005] Therefore, a reservoir intelligent classification method based on capillary pressure curve is established to realize digital and intelligent reservoir classification technology. SUMMARY

[0006] To solve the problem that the feature parameters of capillary pressure curve need to be extracted manually in the prior art, full automation is difficult to achieve, and capillary pressure curve information is difficult to be comprehensively applied, the embodiments of the present specification provide a reservoir intelligent classification method, device and equipment based on capillary pressure curve, which realizes input of capillary pressure curve data, reduces manual intervention or even eliminates intervention, comprehensively uses all data information of capillary pressure curve, realizes multi-level reservoir classification, and has ideal classification effect. In the reservoir classification application in well logging old well reevaluation, the effect is remarkable, full automation classification, and quality and efficiency are greatly improved.

[0007] The specific technical solutions of the embodiments of the present specification are as follows:

[0008] In one aspect, the embodiments of the present specification provide a reservoir intelligent classification method based on capillary pressure curve, which comprises:

[0009] Obtaining experimental data of a plurality of capillary pressure curves, and performing skin effect correction on the plurality of capillary pressure curves;

[0010] Converting the corrected capillary curve under the formation condition into a pore throat distribution curve through a capillary pressure curve conversion method under the formation condition;

[0011] Eliminating non-reservoir capillary pressure curves from the pore throat distribution curve to obtain reservoir classification features of reservoir capillary pressure curves;

[0012] Constructing a distance function of capillary pressure curve classification according to the parameters of the reservoir classification features, and performing clustering;

[0013] Generating a classification result of each capillary pressure curve based on the clustering result of the distance function.

[0014] Further, the reservoir classification features include porosity, permeability, maximum mercury saturation of capillary pressure curve, morphology of pore throat distribution curve, and maximum water saturation increment and capillary radius position.

[0015] Further, obtaining experimental data of a plurality of capillary pressure curves, and performing skin effect correction on the plurality of capillary pressure curves further comprises,

[0016] Obtaining P pieces of capillary pressure curve experimental data, mainly including porosity, permeability of experimental core, and mercury saturation curve corresponding to different capillary pressures;

[0017] Performing skin effect correction on the plurality of capillary pressure curves:

[0018]

[0019] wherein, is the capillary pressure of the i-th point of the l-th capillary pressure curve after correction; Pc,i l MPa is the i-th capillary pressure of the l-th capillary pressure curve; is the corrected water saturation of the i-th point of the l-th capillary pressure curve; and the conversion relationship S w,i l %= 100 - S hg,i l The water saturation correction point is taken

[0020] Further, the method for converting the corrected capillary curve under the formation condition into a pore throat distribution curve further comprises,

[0021] The method for converting the capillary curve under the formation condition comprises:

[0022]

[0023] wherein, MPa is the i-th capillary pressure of the l-th capillary pressure curve under the formation condition; and res MPa is the interfacial tension under the formation condition; and res MPa is the contact angle under the formation condition; lab MPa is the interfacial tension between mercury and air; and lab MPa is the contact angle between mercury and air.

[0024] Further, the method for converting the corrected capillary curve under the formation condition into a pore throat distribution curve further comprises, calculating a capillary radius and water saturation curve wherein r i l um is the capillary radius of the l-th capillary pressure curve;

[0025] The linear interpolation method is used to calculate r interpolate,j l corresponding to the value of S w,j l

[0026]

[0027] wherein the minimum capillary radius r min l um and the maximum capillary radius r max l um of each capillary pressure curve; and the maximum mercury saturation, i.e. the minimum water saturation, of each capillary pressure curve is taken as The minimum capillary radius r​min um = min(r min l ), l = 1, 2,..., P and the maximum capillary radius r max um = min(r max l ), l = 1, 2,..., P; the minimum water saturation

[0028] Between the minimum capillary radius and the maximum capillary radius, M equal interpolation is performed,

[0029] r interpolate,j l = exp([ln(r max )-ln(r min )] / M x j), j = 0, 1, 2,..., M,

[0030] Wherein, M is the number of capillary radius equal division; r interpolate,j l is the interpolation capillary radius of the aligned capillary pressure curve;

[0031] The pore throat distribution curve {r alignment,k l , ΔS w,k l}, k = 0, 1, 2,..., M-1, r alignment,k l = exp([ln(r interpolate,k l )+ln(r interpolate,k+1 l )] / 2)

[0032] ΔS w,k l = S w,k+1 l -S w,k l

[0033] Wherein, r alignment,k l is the average capillary radius of the aligned pore throat distribution curve; ΔS w,k l is the water saturation increment of the aligned pore throat distribution curve.

[0034] Further, the pore throat distribution curve is subjected to data standardization processing to eliminate non-reservoir capillary pressure curves, which further comprises,

[0035] The maximum mercury saturation S hgmax lK-means is used for binary classification, and two class center values S of binary classification are obtained w I and S w II , the difference ΔS between the two is calculated hg,分类 =S hg I -S hg II ;

[0036] If ΔS hg,分类 ≥ 30, the corresponding capillary pressure curve is rejected as a non-reservoir capillary pressure curve;

[0037] Otherwise, all capillary pressure curves participate in the classification calculation.

[0038] Further, constructing a distance function of capillary pressure curve classification according to the parameters of the reservoir classification characteristics further comprises

[0039] Extracting 4 types of features from the capillary pressure curve to construct 5 distances, and finally fusing the 5 distances as the distance function of classification.

[0040] Further, the reservoir classification based on clustering and data output further comprises

[0041] Combining the distance function for reservoir classification, and setting the number of classifications as CN;

[0042] Initialize the capillary pressure curve with the maximum mercury saturation, and initialize the other class centers by selecting the farthest distance from all class centers that have been determined, and the distance calculation formula is

[0043] Dis class =0.5×Dis I +0.5×Dis II +Dis III,1 +2×Dis III,2 +Dis IV ,

[0044] Carry out clustering until the class center no longer changes, and output the final three-class reservoir clustering result.

[0045] On the other hand, the present specification also provides a reservoir intelligent classification device based on capillary pressure curve, which comprises:

[0046] An experimental data acquisition module for acquiring experimental data of a plurality of capillary pressure curves and carrying out skin effect correction on the plurality of capillary pressure curves;

[0047] The capillary curve conversion module is configured to convert the corrected capillary curve under the formation condition into a pore throat distribution curve by using a capillary curve conversion method under the formation condition.

[0048] The classification feature acquisition module is configured to remove a non-reservoir capillary pressure curve from the pore throat distribution curve and acquire a reservoir classification feature of the reservoir capillary pressure curve.

[0049] The clustering module is configured to construct a distance function of capillary pressure curve classification according to parameters of the reservoir classification feature and perform clustering.

[0050] The classification result generation module is configured to generate a classification result of each capillary pressure curve based on a clustering result of the distance function.

[0051] In another aspect, the embodiments of the present specification also provide a computer device, including a memory, a processor, and a computer program stored in the memory, and the processor implements the above method when executing the computer program.

[0052] In another aspect, the embodiments of the present specification also provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the above method.

[0053] Finally, the embodiments of the present specification also provide a computer program product, which includes a computer program, and the computer program is executed by a processor to implement the above method.

[0054] By using the embodiments of the present specification, experimental data of multiple capillary pressure curves are acquired, the skin effect correction and the capillary pressure curve conversion under the formation condition are carried out, the corrected capillary curve under the formation condition is converted into a pore throat distribution curve by using a capillary curve conversion method under the formation condition, a non-reservoir capillary pressure curve is removed from the pore throat distribution curve, a reservoir classification feature of the reservoir capillary pressure curve is acquired, the non-reservoir capillary pressure curve is removed, the classification preparation of the reservoir capillary pressure curve is implemented, the data standardization and the distance function construction of the reservoir classification feature parameters are completed, the distance function of capillary pressure curve classification is constructed according to parameters of the reservoir classification feature, and clustering is performed. Based on the clustering result of the distance function, the classification result of each capillary pressure curve is generated. By using the full-automatic and intelligent reservoir classification scheme, the most basic capillary pressure curve data is input, the least human intervention or even no intervention is needed, all data information of the capillary pressure curve is comprehensively used, the multi-level reservoir classification is realized, the classification effect is ideal, the algorithm is stable, the generalization is good, and the automation is realized. In the reservoir classification application of the logging old well re-evaluation, the effect is remarkable, the full-automatic classification greatly improves the quality and efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0055] To more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 The figure shown is a schematic diagram of an implementation system for a reservoir intelligent classification method based on capillary pressure curves in an embodiment of this specification.

[0057] Figure 2 The diagram shown is a schematic flowchart of an embodiment of the intelligent reservoir classification method based on capillary pressure curves in this specification.

[0058] Figure 3 The diagram shown is a flowchart of the process for correcting the skin effect on the multiple capillary pressure curves in an embodiment of this specification.

[0059] Figure 4 The figure shown is a schematic diagram of the original capillary pressure curve in an embodiment of this specification.

[0060] Figure 5 The figure shown is a schematic diagram of the non-reservoir capillary pressure curve in an embodiment of this specification.

[0061] Figure 6 The figure shown is a schematic diagram of the standardized pore throat distribution curve in the first classification embodiment of this specification;

[0062] Figure 7 The figure shown is a schematic diagram of the class center of the first classification standardized pore throat distribution curve in the embodiments of this specification;

[0063] Figure 8 The figure shown is a schematic diagram of the class center of the second classification pore throat distribution curve in the embodiment of this specification;

[0064] Figure 9 The figure shown is a schematic diagram of the capillary pressure curves for three types in the embodiments of this specification;

[0065] Figure 10 The diagram shown is a schematic representation of the cluster-based reservoir classification and data output process in an embodiment of this specification.

[0066] Figure 11 The diagram shown is a structural schematic of a reservoir intelligent classification device based on capillary pressure curves in an embodiment of this specification.

[0067] Figure 12 The diagram shown is a structural schematic of the computer device in an embodiment of this specification.

[0068] [Explanation of Figure Markers]:

[0069] 101. Terminal;

[0070] 102. Server;

[0071] 1101. Experimental Data Acquisition Module;

[0072] 1102. Capillary Curve Conversion Module;

[0073] 1103. Classification Feature Acquisition Module;

[0074] 1104. Clustering module;

[0075] 1105. Classification result generation module;

[0076] 1202. Computer equipment;

[0077] 1204. Processing equipment;

[0078] 1206. Storage resources;

[0079] 1208. Drive system;

[0080] 1210. Input / output module;

[0081] 1212. Input devices;

[0082] 1214. Output devices;

[0083] 1216. Presentation equipment;

[0084] 1218. Graphical User Interface;

[0085] 1220. Network interface;

[0086] 1222. Communication link;

[0087] 1224. Communication bus. Detailed Implementation

[0088] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the embodiments of this specification.

[0089] It should be noted that the terms "first," "second," etc., in the description, claims, and accompanying drawings of the embodiments herein are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, apparatus, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0090] It should be noted that the acquisition, storage, use, and processing of data in the technical solutions of the embodiments of this specification all comply with the relevant provisions of national laws and regulations.

[0091] It should be noted that in the embodiments of this specification, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0092] like Figure 1 The diagram illustrates an implementation system for a reservoir intelligent classification method based on capillary pressure curves, as described in this specification. The system includes a terminal 101 and a server 102. The terminal 101 and server 102 can communicate via a network, which may include a local area network (LAN), a wide area network (WAN), the Internet, or a combination thereof, and is connected to a website, user equipment (e.g., computing devices), and a backend system.

[0093] Data collectors can input experimental data from multiple capillary pressure curves into server 102 via terminal 101. Server 102 performs basalt effect correction and obtains reservoir classification characteristics of the capillary pressure curves using a conversion method based on formation conditions. It then obtains the distance function for capillary pressure curve classification, performs clustering, and displays the clustering results via terminal 101. Optionally, server 102 can be a node in a cloud computing system (not shown in the figure), or each server can be a separate cloud computing system comprising multiple computers interconnected by a network and operating as a distributed processing system.

[0094] In addition, it should be noted that, Figure 1The examples shown are merely one application environment provided by the embodiments in this specification. In practical applications, other application environments may also be included, and this specification does not impose any limitations.

[0095] To address the problems existing in the prior art, this specification provides an intelligent reservoir classification method based on capillary pressure curves. It realizes the input of the most basic capillary pressure curve data, thereby integrating all the data information of the capillary pressure curve, using data to speak, and realizing multi-level reservoir classification. The classification effect is ideal, the algorithm is stable, has good generalization, and is automated. Figure 2 The diagram shown is a flowchart illustrating the intelligent reservoir classification method based on capillary pressure curves in an embodiment of this specification. The process of intelligent reservoir classification based on capillary pressure curves is described in this diagram. The order of steps listed in the embodiment is merely one possible execution order among many steps and does not represent the only possible execution order. In actual system or device products, the methods shown in the embodiments or accompanying drawings can be executed sequentially or in parallel.

[0096] Specific examples Figure 2 As shown, the method may include:

[0097] Step 201: Obtain experimental data from multiple capillary pressure curves and perform dermal irritation correction on the multiple capillary pressure curves;

[0098] Step 202: Convert the corrected capillary pressure curve under formation conditions into a pore throat distribution curve using the capillary pressure curve conversion method under formation conditions;

[0099] Step 203: Remove non-reservoir capillary pressure curves from the pore throat distribution curves to obtain the reservoir classification characteristics of the reservoir capillary pressure curves;

[0100] Step 204: Construct a distance function for capillary pressure curve classification based on the parameters of the reservoir classification characteristics, and perform clustering;

[0101] Step 205: Generate the classification results of each capillary pressure curve based on the clustering results of the distance function.

[0102] Using the embodiments of this specification, experimental data of multiple capillary pressure curves are obtained, and corrections for the skin effect and conversion of formation-condition capillary pressure curves are performed. The corrected formation-condition capillary pressure curves are converted into pore-throat distribution curves using the formation-condition capillary pressure curve conversion method. Non-reservoir capillary pressure curves are removed from the pore-throat distribution curves to obtain reservoir classification characteristics of the reservoir capillary pressure curves. The removal of non-reservoir capillary pressure curves prepares for reservoir capillary pressure curve classification. Data standardization and the construction of distance functions for reservoir classification characteristic parameters are completed. A distance function for capillary pressure curve classification is constructed based on the parameters of the reservoir classification characteristics, and clustering is performed. Classification results for each capillary pressure curve are generated based on the clustering results of the distance function. Through a fully automated and intelligent reservoir classification scheme, the input capillary pressure curve data can be processed with minimal or no human intervention. By integrating all the data information from the capillary pressure curve, the system uses data to speak for itself, achieving multi-level reservoir classification with ideal classification results. The algorithm is stable, has good generalization ability, and is automated. It has shown significant results in reservoir classification applications for the re-evaluation of old logging wells, and the fully automated classification greatly improves quality and efficiency.

[0103] In the embodiments of this specification, the reservoir classification characteristics include: porosity, permeability, maximum mercury saturation of the capillary pressure curve, morphology of the pore throat distribution curve, and the position of the maximum water saturation increment and capillary radius.

[0104] To conduct correction for the skin effect and conversion of formation condition capillary pressure curves, such as Figure 3 As shown, it is necessary to obtain experimental data from multiple capillary pressure curves, and further perform dermal correction on these multiple capillary pressure curves, including...

[0105] Step 301: Obtain experimental data of capillary pressure curves for P strips, mainly including the porosity, permeability, and mercury saturation curves corresponding to different capillary pressures of the experimental core.

[0106] Step 302: Perform dermal patch correction on the multiple capillary pressure curves:

[0107]

[0108] in, P represents the capillary pressure at point i on the corrected l-th capillary pressure curve; c,i l MPa represents the i-th capillary pressure of the l-th capillary pressure curve; The water saturation at point i on the corrected l-th capillary pressure curve; the conversion relationship between water saturation and mercury saturation S. w,i l %,% = 100 - S hg,i l Take the water saturation correction point

[0109] Step 303: Convert the corrected capillary pressure curve under formation conditions into a pore throat distribution curve using the formation condition capillary pressure curve conversion method.

[0110] Specifically, the method for converting the formation condition capillary curve is as follows:

[0111]

[0112] in, σ represents the capillary pressure at point i on the l-th capillary pressure curve under formation conditions. res For interfacial tension under formation conditions; θ res σ is the contact angle; lab The interfacial tension between mercury and air; θ lab This represents the contact angle between mercury and air.

[0113] For example, inputting P capillary pressure curve experimental data, mainly including the porosity Poro of the experimental core. l %, Perm penetration l ,m D and different capillary pressures P c,i l Mercury saturation S corresponding to MPa hg,i 1 The % curve was used to perform correction for the skin effect and conversion of the capillary pressure curve under formation conditions, such as... Figure 4 As shown. Among them, Poro l Perm represents the porosity of the l-th capillary pressure curve. l P represents the permeability of the l-th capillary pressure curve; c,i l MPa represents the i-th capillary pressure on the l-th capillary pressure curve; S hg,i l This represents the i-th mercury saturation on the l-th capillary pressure curve.

[0114] The method for correcting the skin irritation effect:

[0115] Conversion relationship between water saturation and mercury saturation (S) w,i l %,% = 100 - S hg,i l Take the water saturation correction point.

[0116]

[0117] in, This refers to the capillary pressure at point i on the corrected l-th capillary pressure curve. The water saturation at point i on the corrected l-th capillary pressure curve.

[0118] Method for converting formation condition capillary curves:

[0119]

[0120] in, σ represents the capillary pressure at point i on the l-th capillary pressure curve under formation conditions. res The interfacial tension under formation conditions is typically 72 mN / m for gas-water interface and 32 mN / m for oil-water interface; θ res The contact angle is 0° for air and water, and 30° for oil and water; σ lab The interfacial tension between mercury and air is 480 mN / m; θ lab The contact angle between mercury and air is 140°.

[0121] In one embodiment of this specification, after obtaining the corrected capillary curve under formation conditions, it is also necessary to calculate and align the pore throat distribution curve. Converting the corrected capillary curve under formation conditions into a pore throat distribution curve further includes...

[0122] Based on the capillary curve under the aforementioned formation conditions Calculate the capillary radius versus water saturation curve Where r i l The capillary radius of the l-th capillary pressure curve is given in μm.

[0123] Based on the capillary pressure curve of the lth line and the capillary radius and water saturation curve, r is calculated using linear interpolation. interpolate,j l The corresponding S w,j l value:

[0124]

[0125] Among them, the minimum capillary radius r of each capillary pressure curve min l ,um and maximum capillary radius r max l ,um; the maximum mercury saturation of each capillary pressure curve, i.e., the minimum water saturation, is taken as The minimum capillary radius r of all capillary pressure curves min ,um=min(r min l ), l=1,2,...,P and the maximum capillary radius r max ,um=min(r max l), l=1,2,...,P;Minimum water saturation Interpolate by dividing the minimum capillary radius and the maximum capillary radius into M equal parts.

[0126] r interpolate,j l =exp([ln(r max )-ln(r min )] / M×j), j=0,1,2,...,M,

[0127] Where M is the number of equal divisions of capillary radius; r interpolate,j l The interpolated capillary radius is used to align the capillary pressure curve; the orifice-throat distribution curve of the aligned capillary pressure curve is calculated. alignment,k l ,ΔS w,k l}, k=0,1,2,...,M-1,r alignment,k l =exp([ln(r interpolate,k l )+ln(r interpolate,k+1 l )] / 2),

[0128] ΔS w,k l =S w,k+1 l -S w,k l ,

[0129] Where, r alignment,k l The average capillary radius of the aligned pore throat distribution curve; ΔS w,k l The water saturation increment of the aligned pore throat distribution curve.

[0130] For example, based on the capillary curve under corrected formation conditions Calculate the capillary radius versus water saturation curve

[0131]

[0132] r i l Let the capillary radius be (µm) of the l-th capillary pressure curve; calculate the minimum capillary radius r for each capillary pressure curve. min l ,um and maximum capillary radius r max l ,um. Calculate the maximum mercury saturation, which is also the minimum water saturation, for each capillary pressure curve, taking . Calculate the minimum capillary radius r for all capillary pressure curves. min ,um=min(r min l ), l=1,2,...,P and the maximum capillary radius r max ,um=min(r max l ), l=1,2,...,P. and minimum water saturation.

[0133] Interpolate M equal parts between the minimum capillary radius and the maximum capillary radius. Linear interpolation is used here, and M can be set to 50.

[0134] r interpolate,j l =exp([ln(r max )-ln(r min )] / M×j), j=0,1,2,...,M,

[0135] M is the number of equal divisions of capillary radius; r interpolate,j l The interpolated capillary radius is aligned with the capillary pressure curve; r is calculated using linear interpolation based on the capillary radius of the l-th capillary pressure curve and the water saturation curve. interpolate,j l The corresponding S w,j l value:

[0136]

[0137] Calculate the pore throat distribution curve of the aligned capillary pressure curve {r alignment,k l ,ΔS w,k l}, k=0,1,2,...,M-1,

[0138] r alignment,k l =exp([ln(r interpolate,k l )+ln(r interpolate,k+1 l )] / 2),

[0139] ΔS w,k l =S w,k+1 l -S w,k l ,

[0140] r alignment,k lThe average capillary radius of the aligned pore throat distribution curve; ΔS w,k l The water saturation increment of the aligned pore throat distribution curve is expressed as %.

[0141] In one embodiment of this specification, it is also necessary to remove non-reservoir capillary pressure curves to prepare for the classification of reservoir capillary pressure curves. Further, the removal of non-reservoir capillary pressure curves by standardizing the pore-throat distribution curves includes...

[0142] Maximum mercury saturation for each capillary curve K-means is used for binary classification to obtain the two class center values ​​S of the binary classification. w I and S w II Calculate the difference ΔS between the two. hg,分类 =S hg I -S hg II ;

[0143] If ΔS hg,分类 If the value is ≥30, the corresponding capillary pressure curve will be discarded as a non-reservoir capillary pressure curve.

[0144] Otherwise, all capillary pressure curves are included in the classification calculation.

[0145] For example, primarily the maximum mercury saturation of each capillary curve. K-means was used for binary classification. During initialization, class 1 was selected based on the minimum value of the capillary pressure curve. Choose the largest of the two categories Then, the classification results are calculated, yielding the two class center values ​​S for binary classification. w I and S w II Calculate the difference ΔS between the two. hg,分类 =S hg I -S hg II If ΔS hg,分类 If the value is ≥30, the capillary pressure curve corresponding to Category 1 will be discarded as a non-reservoir capillary pressure curve. Subsequent classification will primarily target the capillary pressure curves corresponding to Category 2. Otherwise, all capillary pressure curves will be included in the classification calculation. Figure 5 As shown, S w I S represents the center value of the maximum mercury saturation in Class 1 (the average value of the maximum mercury saturation in Class 1); w IIThe value represents the center value of the maximum mercury saturation in Category 2 (the average value of the maximum mercury saturation in Category 2), where the horizontal axis represents SHG mercury saturation in %, and the vertical axis represents PC capillary pressure in MPa. Figure 5 This is for identifying non-reservoir capillary pressure curves using a two-class classification method.

[0146] In one embodiment of this specification, constructing the distance function for capillary pressure curve classification based on the parameters of the reservoir classification characteristics further includes,

[0147] Four types of features are extracted from the capillary pressure curve to construct five distances, and finally the five distances are fused as a distance function for classification.

[0148] Specifically, the key factors influencing reservoir classification are multifaceted. Therefore, to construct a unified classification distance, it is necessary to standardize data of various dimensions, which is also a crucial element of classification. Here, we extract four types of features from the input capillary pressure curve data to construct five distances, and finally fuse these five distances as the classification distance function.

[0149] Feature 1: The porosity and permeability input from each capillary pressure curve are taken. l Perm l The standardization method is to standardize porosity according to the maximum and minimum values:

[0150]

[0151] Among them, Poro min l The minimum porosity in the capillary pressure curve; Poro max l The porosity is the maximum porosity in the capillary pressure curve; permeability is normalized according to the logarithmic maximum and minimum.

[0152]

[0153] Characteristic 1 of the two capillary pressure curves: distance

[0154] Feature 2: The maximum mercury saturation of each capillary pressure curve is standardized using the following formula:

[0155]

[0156] Characteristic 2 of the two capillary pressure curves: Distance II =|ΔS hg,std l1,l2 |

[0157] Feature 3: The morphology of the pore throat distribution curve is a very important detail in classification. Each capillary pressure curve has its own unique morphology, reflecting the unique pore structure of the core. According to {r alignment,k l ,ΔS w,k l Construct two distances, first standardizing the maximum and minimum values ​​of the capillary radius and water saturation increment.

[0158]

[0159] The maximum mercury saturation increment for all pore-throat distribution curves; the characteristic 3-1 distance between the two capillary pressure curves; The Euclidean distance describes the pore-throat distribution curves; the second distance is constructed as the correlation distance, and the cosine similarity between the two pore-throat distribution curves is set as:

[0160]

[0161] Select a capillary radius on the pore-throat distribution curve as a reference position, move the pore-throat distribution curve, and calculate the cosine similarity between two related pore-throat distribution curves. When the cosine similarity is maximized, take the current moving distance Δr = |r current -r origion |As a distance from Dis III,2 ;r origion The original position of the capillary radius, a parameter of the pore throat distribution curve; r current The current position of the reference capillary radius for the pore throat distribution curve.

[0162] The characteristic of the two capillary pressure curves is the distance between them (3-2).

[0163] Dis III,2 =Δr|max(Dis cos l1,l2 ),

[0164] Feature 4: The location of the maximum water saturation increment and capillary radius; calculate the maximum water saturation increment ΔS on each pore throat distribution curve. w-std-max l =max(ΔS) w-std,k l k = 0, 1, 2, ..., M-1, and the corresponding capillary radius r std-max l The distance of feature 4 is defined as:

[0165]

[0166] After constructing the capillary pressure curve classification distance function described above, this distance function is combined for reservoir classification using the K-means++ algorithm. Let the number of classifications be CN. The initialization of the class center for the first class is based on the capillary pressure curve with the highest mercury saturation. The initialization of other class centers is sequentially based on the furthest distance from all currently determined class centers. The formula for calculating the distance is as follows:

[0167] Dis class =0.5×Dis I +0.5×Dis II +Dis III,1 +2×Dis III,2 +Dis IV ,

[0168] Then clustering is performed until the cluster centers no longer change, thus classifying the capillary pressure curves. The method for determining the CN (cell density) for hyperparameter classification is as follows: The Calinski-Harabasz coefficient criterion is used for trial calculations. Reservoirs are typically divided into three categories: Class I, Class II, and Class III, corresponding to good, medium, and poor, respectively. The pore structure in a given region and stratum is controlled by factors such as tectonics, sedimentation, and diagenesis. Constrained by this, the maximum number of classifications is empirically given in the range of (6–10), usually 8 is sufficient. Within the range of (3–8), the Calinski-Harabasz coefficient criterion is used for trial calculations. That is, the larger the ratio of intra-cluster density to inter-cluster separation, the better the classification effect, and the optimal number of classifications CN can be obtained. Figure 6 and Figure 7 The figure shows the relationship between the pore throat radius and the mercury saturation increment of the reservoir core after capillary curve processing, which describes the distribution characteristics of the pore throat. The horizontal axis rstd is the standardized pore throat radius, which is dimensionless, and the vertical axis is the mercury saturation increment corresponding to the pore throat radius, which describes the volume percentage of the corresponding pore throat.

[0169] If CN > 3, then we use nested clustering. We input the results of the first clustering (i.e., the cluster centers of each class) to classify reservoirs into three categories: Class I, Class II, and Class III, and then perform a second clustering. This completes the classification of the three reservoir types. We still use the K-means++ algorithm, with CN... 2 =3. After clustering is completed, the final clustering results for the three reservoir types are output. The results of the first clustering correspond to the three reservoir types as the second-level reservoir subdivision results, such as I, II-1, II-2, II-3, III-1, III-2, etc. Figure 8 , Figure 9 As shown. CN 2 This represents the number of categories in the second clustering.

[0170] In one embodiment of this specification, such asFigure 10 As shown, cluster-based reservoir classification and data output further include

[0171] Step 1001: Combine the distance functions to perform reservoir classification, and let the number of classifications be CN;

[0172] Step 1002: Initialize the capillary pressure curve with the maximum mercury saturation. For other class centers, initialize them sequentially by selecting the furthest distance from all currently determined class centers. The formula for calculating the distance is...

[0173] Dis class =0.5×Dis I +0.5×Dis II +Dis III,1 +2×Dis III,2 +Dis IV ,

[0174] Step 1003: Perform clustering until the cluster centers no longer change, and output the final three-class reservoir clustering results.

[0175] Compared to previous reservoir classification methods based on capillary pressure curves, the method used in this specification is a fully automated and intelligent reservoir classification scheme. It achieves multi-level reservoir classification by integrating all the data information from the capillary pressure curves, with minimal or no manual intervention, based on the input of the most basic capillary pressure curve data. The classification effect is ideal, the algorithm is stable, has good generalization, and is automated. It has shown significant results in reservoir classification applications for the re-evaluation of old logging wells, and the fully automated classification greatly improves quality and efficiency.

[0176] Based on the same inventive concept, embodiments of this specification also provide a reservoir intelligent classification device based on capillary pressure curves, such as... Figure 11 As shown, the device includes:

[0177] The experimental data acquisition module 1101 is used to acquire experimental data of multiple capillary pressure curves and to perform dermal irritation correction on the multiple capillary pressure curves.

[0178] The capillary curve conversion module 1102 is used to convert the corrected capillary curve under formation conditions into a pore throat distribution curve by using the capillary pressure curve conversion method under formation conditions.

[0179] The classification feature acquisition module 1103 is used to remove non-reservoir capillary pressure curves from the pore throat distribution curves and obtain the reservoir classification features of the reservoir capillary pressure curves.

[0180] Clustering module 1104 is used to construct a distance function for capillary pressure curve classification based on the parameters of the reservoir classification characteristics, and to perform clustering.

[0181] The classification result generation module 1105 is used to generate classification results for each capillary pressure curve based on the clustering results of the distance function.

[0182] like Figure 12 The diagram shown is a structural schematic of a computer device according to an embodiment of this specification. The methods described in this specification can be applied to the computer device of this embodiment.

[0183] Specifically, such as Figure 12 As shown, computer device 1202 may include one or more processing devices 1204, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. Computer device 1202 may also include any storage resource 1206 for storing information of any kind, such as code, settings, data, etc. Non-limitingly, for example, storage resource 1206 may include any one or more combinations of: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any storage resource can use any technology to store information.

[0184] Furthermore, any storage resource can provide volatile or non-volatile retention of information.

[0185] Furthermore, any storage resource can represent a fixed or removable component of the computer device 1202. In one case, when the processing device 1204 executes associated instructions stored in any storage resource or combination of storage resources, the computer device 1202 can perform any operation of the associated instructions. The computer device 1202 also includes one or more drive systems 1208 for interacting with any storage resource, such as a hard disk drive system, an optical disk drive system, etc.

[0186] Computer device 1202 may also include an input / output module 1210 (I / O) for receiving various inputs (via input device 1212) and providing various outputs (via output device 1214). A specific output mechanism may include a presentation device 1216 and an associated graphical user interface (GUI) 1218. In other embodiments, the input / output module 1210 (I / O), input device 1212, and output device 1214 may be omitted, and the device may function solely as a computer device within a network. Computer device 1202 may also include one or more network interfaces 1220 for exchanging data with other devices via one or more communication links 1222. One or more communication buses 1224 couple the components described above together.

[0187] Communication link 1222 can be implemented in any way, such as via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, or any combination thereof. Communication link 1222 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0188] This specification also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0189] This specification also provides computer-readable instructions, wherein when a processor executes the instructions, the program therein causes the processor to perform the above-described method.

[0190] It should be understood that in the various embodiments of this specification, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this specification.

[0191] It should also be understood that, in the embodiments of this specification, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the embodiments of this specification, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0192] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the embodiments in this specification.

[0193] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0194] In the embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0195] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described in this specification, depending on actual needs.

[0196] Furthermore, the functional units in the various embodiments of this specification can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0197] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this specification, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this specification. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0198] This specification describes the principles and implementation methods of the embodiments using specific examples. The above descriptions of the embodiments are only for the purpose of helping to understand the methods and core ideas of the embodiments in this specification. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the embodiments in this specification. Therefore, the content of this specification should not be construed as a limitation on the embodiments in this specification.

Claims

1. A reservoir intelligent classification method based on capillary pressure curves, characterized in that, The method includes: Experimental data from multiple capillary pressure curves were obtained, and the capillary pressure curves were corrected for the tingling effect. The corrected capillary pressure curve under formation conditions is converted into a pore throat distribution curve by the capillary pressure curve conversion method under formation conditions. Remove non-reservoir capillary pressure curves from the pore throat distribution curves to obtain reservoir classification characteristics of the reservoir capillary pressure curves. Based on the parameters of the reservoir classification characteristics, a distance function for capillary pressure curve classification is constructed, and clustering is performed. The classification results of each capillary pressure curve are generated based on the clustering results of the distance function.

2. The intelligent reservoir classification method based on capillary pressure curves according to claim 1, characterized in that, The reservoir classification characteristics include: porosity, permeability, maximum mercury saturation of the capillary pressure curve, morphology of the pore throat distribution curve, and the position of the maximum water saturation increment and capillary radius.

3. The intelligent reservoir classification method based on capillary pressure curves according to claim 2, characterized in that, The experimental data of multiple capillary pressure curves are obtained, and the correction for the tingling effect on the multiple capillary pressure curves is further included. The experimental data of capillary pressure curves of P strips were obtained, mainly including the porosity, permeability and mercury saturation curves corresponding to different capillary pressures of the experimental core. The dermal effect correction was performed on the multiple capillary pressure curves: in, P represents the capillary pressure at point i on the corrected l-th capillary pressure curve; c,i l MPa represents the i-th capillary pressure of the l-th capillary pressure curve; The water saturation at point i on the corrected l-th capillary pressure curve; the conversion relationship between water saturation and mercury saturation S. w,i l %,% = 100 - S hg,i l , This is the water saturation correction point.

4. The intelligent reservoir classification method based on capillary pressure curves according to claim 3, characterized in that, The corrected capillary pressure curve under formation conditions is converted into a pore throat distribution curve using a formation condition capillary pressure curve conversion method, which further includes... The method for converting capillary curves under the aforementioned formation conditions is as follows: in, σ represents the capillary pressure at point i on the l-th capillary pressure curve under formation conditions. res For interfacial tension under formation conditions; θ res σ is the contact angle; lab The interfacial tension between mercury and air; θ lab This represents the contact angle between mercury and air.

5. The intelligent reservoir classification method based on capillary pressure curves according to claim 4, characterized in that, The corrected capillary curves under the aforementioned formation conditions are further converted into pore throat distribution curves, including... Based on the capillary curve under the aforementioned formation conditions Calculate the capillary radius versus water saturation curve Where r i l The capillary radius of the l-th capillary pressure curve is given in μm. Based on the capillary pressure curve of the lth line and the capillary radius and water saturation curve, r is calculated using linear interpolation. interpolate,j l The corresponding S w,j l value: Among them, the minimum capillary radius r of each capillary pressure curve min l ,um and maximum capillary radius r max l ,um; the maximum mercury saturation of each capillary pressure curve, i.e., the minimum water saturation, is taken as The minimum capillary radius r of all capillary pressure curves min ,um=min(r min l ), l=1,2,...,P and the maximum capillary radius r max ,um=min(r max l ), l=1,2,...,P;Minimum water saturation Interpolate by dividing the minimum capillary radius and the maximum capillary radius into M equal parts. r interpolate,j l =exp([ln(r max )-ln(r min )] / M×j),j=0,1,2,...,M, Where M is the number of equal divisions of capillary radius; r interpolate,j l The interpolated capillary radius is used to align with the capillary pressure curve. Calculate the pore throat distribution curve of the aligned capillary pressure curve {r alignment,k l ,ΔS w,k l }, k=0,1,2,...,M-1,r alignment,k l =exp([ln(r interpolate,k l )+ln(r interpolate,k+1 l )] / 2) ΔS w,k l =S w,k+1 l -S w,k l Where, r alignment,k l The average capillary radius of the aligned pore throat distribution curve; ΔS w,k l The water saturation increment of the aligned pore throat distribution curve.

6. The intelligent reservoir classification method based on capillary pressure curves according to claim 5, characterized in that, The pore throat distribution curves are further included by performing data standardization processing to remove non-reservoir capillary pressure curves. Maximum mercury saturation for each capillary curve K-means is used for binary classification to obtain the two class center values ​​S of the binary classification. w I and S w II Calculate the difference ΔS between the two. hg,分类 =S hg I -S hg II ; If ΔS hg,分类 If the value exceeds the preset threshold, the corresponding capillary pressure curve will be discarded as a non-reservoir capillary pressure curve. Otherwise, all capillary pressure curves are included in the classification calculation.

7. The intelligent reservoir classification method based on capillary pressure curves according to claim 6, characterized in that, The distance function for classifying capillary pressure curves based on the parameters of the reservoir classification characteristics further includes, Four types of features are extracted from the capillary pressure curve to construct five distances, and finally the five distances are fused as a distance function for classification.

8. The intelligent reservoir classification method based on capillary pressure curves according to claim 7, characterized in that, Cluster-based reservoir classification and data output further include The reservoir is classified by combining the distance functions, and the number of classifications is CN; Initialize the capillary pressure curve with the highest mercury saturation. For other class centers, initialize them sequentially by selecting the furthest distance from all currently determined class centers. The formula for calculating this distance is... Dis class =0.5×Dis I +0.5×Dis II +Dis III,1 +2×Dis III,2 +Dis IV , Perform clustering until the cluster centers no longer change, and output the final three-class reservoir clustering results.

9. A reservoir intelligent classification device based on capillary pressure curves, characterized in that, The device includes: The experimental data acquisition module is used to acquire experimental data from multiple capillary pressure curves and to perform dermal irritation correction on the multiple capillary pressure curves. The capillary curve conversion module is used to convert the corrected capillary curve under formation conditions into a pore throat distribution curve by using the capillary pressure curve conversion method under formation conditions. The classification feature acquisition module is used to remove non-reservoir capillary pressure curves from the pore throat distribution curves and obtain the reservoir classification features of the reservoir capillary pressure curves. The clustering module is used to construct a distance function for classifying capillary pressure curves based on the parameters of the reservoir classification characteristics, and to perform clustering. The classification result generation module is used to generate classification results for each capillary pressure curve based on the clustering results of the distance function.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 8.

12. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images