Stratum logging curve environment correction method and device based on decision tree and medium

Abstract

The invention relates to the technical field of oil exploration and development, in particular to a stratum logging curve environment correction method and device based on a decision tree and a medium. Selecting a verification well marker interval; respectively carrying out curve fitting calculation on the selected verification well marker interval curve by using various correction calculation methods; determining a method with the highest correlation as a correction method of the correction section curve corresponding to the verification well marker layer section by utilizing curve cross plots calculated by different verification well marker layer section curves and various methods; and on the basis of the selected correction section curve correction method, sound wave time difference curves of different correction well sections are calculated and combined. According to the method, through the decision tree method, the existing correction method is fully utilized, the optimal correction method is adopted for different curve abnormal sections, and finally, the interval transit time curves of different corrected well sections are calculated by using different correction methods and then are combined, so that the more accurate interval transit time curve is obtained.

Description

Technical Field

[0001] The invention relates to the technical field of petroleum exploration and development, and in particular to a method, equipment and medium for correcting the environment of a clastic rock formation logging curve based on a decision tree. Background Art

[0002] Clastic rock is a new rock formed by the remnants of mechanically broken rocks after transportation, deposition, compaction, and cementation. Clastic materials can be divided into two categories: rock debris and mineral debris. Rock debris has a complex composition and can be found in all types of rocks. Mineral debris is mainly quartz, feldspar, mica and a small amount of heavy minerals. Cementing materials are mainly minerals formed by chemical deposition. They fill between the debris to act as a cementation. They mainly include siliceous minerals, sulfate minerals, carbonate minerals, phosphate minerals and silicate minerals. The pores of clastic rocks are the objects for storing groundwater, oil and gas. The study of clastic rocks is of practical significance for finding groundwater and oil and gas deposits.

[0003] With the rapid development of society, the demand for energy is also increasing day by day, among which the demand for oil and natural gas is even stronger. In order to effectively detect oil layers, geological parameters of the target formation are usually collected during formation logging. However, the structure of the formation is complex, and the clastic rock acoustic time difference curve environment needs to be corrected.

[0004] Current environmental correction methods for acoustic time difference curves of clastic rocks include multi-curve fitting linear fitting method, which searches for the relationship between other curves and acoustic time difference from a mathematical point of view, Faust empirical formula, which considers the relationship between resistivity, depth and acoustic time difference, and rock model forward modeling, which considers the relationship between lithology, pores and acoustic time difference. However, using a single method often results in the correction value being inconsistent with the actual verification value.

[0005] Therefore, there is an urgent need for formation logging curve environmental correction methods, equipment and media based on decision trees, and the optimal method is used for correction of different curve abnormal sections. Summary of the invention

[0006] In order to solve the above problems existing in the prior art, the purpose of the present invention is to provide a formation logging curve environment correction method, equipment and medium based on a decision tree.

[0007] To achieve the above object, the present invention provides the following technical solution: a formation logging curve environment correction method based on a decision tree, comprising the following steps:

[0008] S1: Obtain basic data of calibration wells and verification wells;

[0009] S2: Select the marker layer of the verification well;

[0010] S3: Use a variety of correction calculation methods to perform curve fitting calculations on the selected validation well marker layer curves;

[0011] S4: for different verification well marker layers, using the intersection diagram of different verification well marker layer curves and the curves calculated by various methods in step S3, determine the method with the highest correlation as the correction method of the correction segment curve corresponding to the verification well marker layer segment;

[0012] S5: Based on the selected correction section curve correction method, the acoustic wave time difference curves of different correction well sections are calculated and combined to obtain accurate acoustic wave time difference curves.

[0013] The present invention is further configured such that the basic data in step S1 includes the depth, resistivity, natural gamma, natural potential, acoustic time difference, and caliper logging curve of the verification well and the calibration well.

[0014] The present invention is further configured that step S2 specifically includes selecting a normal curve segment of the verification well that has similar sedimentary characteristics to the abnormal curve segment of the calibration well, that is, a normal curve segment of the verification well that corresponds to the consistent natural gamma curve morphology as the marker layer.

[0015] The present invention is further configured to use a natural gamma curve greater than 90 as a verification well marker layer segment 1, and a natural gamma curve less than 90 as a verification well marker layer segment 2.

[0016] The present invention is further configured such that, in step S3, the correction calculation method includes curve calculation of a multi-curve fitting linear fitting method, a Faust empirical formula, and a rock model forward modeling method.

[0017] The present invention is further configured that, in step S3, the multi-curve fitting linear fitting method is specifically to calculate the curve according to the following formula:

[0018] DTc=f(GR,Rt,SP)

[0019] Wherein, DTc is the acoustic time difference; Rt is the formation resistivity; GR is the natural gamma; SP is the natural potential. The present invention is further configured that, in step S3, the Faust empirical formula is:

[0020] DTc=KHC dRt

[0021] Where K, C, d are regional empirical coefficients; H is depth (vertical depth); DTc is acoustic time difference; Rt is formation resistivity.

[0022] The present invention is further configured that the rock model forward modeling in step S3 performs curve calculation according to the following formula:

[0023]

[0024] Where DTc is the acoustic time difference; V maFormation skeleton velocity; V f The velocity of the fluid in the pores; Porosity.

[0025] The present invention is further configured that step S4 specifically comprises preparing multi-curve fitting linear fitting method, Faust empirical formula, rock model forward calculation and measured acoustic wave time difference intersection diagrams for verification well marker layer segment 1 and verification well marker layer segment 2, respectively, to obtain correlation coefficients, and taking the calculation method with the highest correlation coefficient as the calculation method for the acoustic wave time difference curve of the verification well marker layer segment.

[0026] The present invention is further configured such that step S5 specifically comprises calculating the acoustic wave time difference curve for the correction well section corresponding to the marker layer section of the corresponding verification well respectively using the selected calculation method, and splicing and merging the curves up and down according to the depth to obtain an accurate acoustic wave time difference curve.

[0027] The present invention also includes an electronic device, comprising:

[0028] A memory storing executable instructions;

[0029] A processor runs the executable instructions in the memory to implement the above-mentioned formation logging curve environment correction method based on the decision tree.

[0030] A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned decision tree-based formation logging curve environment correction method is implemented.

[0031] In summary, the beneficial effects of the above technical solution of the present invention are as follows:

[0032] 1. The present invention makes full use of the existing correction methods through the decision tree method, adopts the optimal correction method for different curve abnormal sections, and finally uses different correction methods to calculate the acoustic wave time difference curves of different correction well sections and then merges them to obtain a more accurate acoustic wave time difference curve. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0034] Figure 1 This is a flow chart of the decision tree-based formation logging curve environment correction method of the present invention.

[0035] Figure 2 This is a specific flow chart of Example 1 of the present invention.

[0036] Figure 3 Schematic diagram of logging curves of the verification well and the calibration well in Example 1 of the present invention.

[0037] Figure 4 This is a graph of acoustic time difference of a marker layer calculated by forward modeling using a multi-curve fitting linear fitting method, Faust's empirical formula, and a rock model in Example 1 of the present invention.

[0038] Figure 5 In order to verify the well marker layer 1 and the well marker layer 2, the multi-curve fitting linear fitting method, Faust empirical formula and rock model forward modeling method were used to calculate the intersection diagram of the acoustic wave time difference and the measured acoustic wave time difference.

[0039] Figure 6 This is a schematic diagram of the acoustic time difference curve obtained by merging the correction wells obtained in Example 1 of the present invention. DETAILED DESCRIPTION

[0040] In order to enable those skilled in the art to better understand the technical solution of the present invention, the technical solution of the present invention is clearly and completely described below in conjunction with the accompanying drawings of the present invention. Based on the embodiments of the present invention, other similar embodiments obtained by ordinary technicians in the field without making any creative work should all fall within the scope of protection of the present invention.

[0041] In addition, the directional words mentioned in the following embodiments, such as "up", "down", "left", "right", etc., are only reference directions of the drawings. Therefore, the directional words used are used to illustrate rather than limit the invention.

[0042] The present invention will be further described below in conjunction with the accompanying drawings and preferred embodiments.

[0043] Embodiment 1:

[0044] like Figure 1-Figure 2 As shown in the figure, a preferred embodiment of the present invention is a formation logging curve environment correction method based on a decision tree, comprising the following steps:

[0045] S1: Obtain various basic data of the calibration well and the verification well; the basic data include the depth, resistivity, natural gamma, natural potential, acoustic time difference, and caliper logging curve of the verification well and the calibration well.

[0046] S2: Select the marker layer segment of the verification well; select the normal curve segment of the verification well that has similar sedimentary characteristics to the abnormal curve segment of the correction well, that is, the normal curve segment of the verification well that corresponds to the consistent natural gamma curve morphology as the marker layer.

[0047] The natural gamma curve greater than 90 is used as the verification well marker layer segment 1, and the natural gamma curve less than 90 is used as the verification well marker layer segment 2. Figure 3shown.

[0048] S3: Use a variety of correction calculation methods to carry out curve fitting calculations for the selected validation well marker layer curves; the results are as follows Figure 4 shown.

[0049] The correction calculation method includes curve calculation of multi-curve fitting linear fitting method, Faust empirical formula, and rock model forward modeling method.

[0050] The multi-curve fitting linear fitting method specifically calculates the curve according to the following formula:

[0051] DTc=f(GR,Rt,SP)

[0052] In the formula, DTc is the acoustic time difference; Rt is the formation resistivity; GR is the natural gamma; SP is the natural potential.

[0053] The Faust empirical formula is:

[0054] DTc=KHC dRt

[0055] Where K, C, d are regional empirical coefficients; H is depth (vertical depth); DTc is acoustic time difference; Rt is formation resistivity.

[0056] The rock model forward modeling in step S3 performs curve calculation according to the following formula:

[0057]

[0058] Where, DTc is the acoustic time difference; V ma Formation skeleton velocity; V f The velocity of the fluid in the pores; Porosity.

[0059] S4: for different verification well marker layers, using the intersection diagram of different verification well marker layer curves and the curves calculated by various methods in step S3, determine the method with the highest correlation as the correction method of the correction segment curve corresponding to the verification well marker layer segment;

[0060] The multi-curve fitting linear fitting method, Faust empirical formula, and rock model forward calculation were respectively produced with the measured acoustic wave time difference intersection diagrams of the verification well marker layer segment 1 and the verification well marker layer segment 2 to obtain the correlation coefficient, such as Figure 5 As shown in the figure, in the marker layer 1, the correlation between the acoustic wave time difference calculated by the Faust empirical formula and the measured acoustic wave time difference is as high as 0.93; in the marker layer 2, the correlation between the acoustic wave time difference calculated by the multi-curve fitting linear fitting method and the measured acoustic wave time difference is as high as 0.96.

[0061] S5: Based on the selected correction section curve correction method, the acoustic wave time difference curves of different correction well sections are calculated and combined to obtain accurate acoustic wave time difference curves.

[0062] The Faust empirical formula and the multi-curve fitting linear fitting method are used to calculate the acoustic time difference curves for the calibration well marker segment 1 and marker segment 2, and the curves are combined up and down according to the depth to obtain accurate acoustic time difference curves. The calibration well marker segment 1 and calibration well marker segment 2 are the curve anomaly segments of the calibration well corresponding to the verification well marker segment 1 and verification well marker segment 2. The results are shown in Figure 6 shown.

[0063] Embodiment 2:

[0064] An electronic device, comprising:

[0065] A memory storing executable instructions;

[0066] A processor runs the executable instructions in the memory to implement the above-mentioned formation logging curve environment correction method based on the decision tree.

[0067] Embodiment 3:

[0068] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned decision tree-based formation logging curve environment correction method.

[0069] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. Decision tree-based environmental correction method for formation logging curves, characterized in that, it includes the following steps: S1: Obtain various basic data of the calibration well and the verification well; S2: Select the marker layer section of the verification well; S3: Use a variety of calibration calculation methods to carry out curve fitting calculations for the curves of the selected marker layer section of the verification well respectively; S4: For different marker layer sections of the verification well, use the intersection diagrams of the curves of different marker layer sections of the verification well and the curves calculated by various methods in step S3 to determine the method with the highest correlation as the calibration method for the calibration section curve corresponding to this marker layer section of the verification well; S5: Based on the selected calibration method for the calibration section curve, calculate the acoustic travel time curves of different calibration well sections and merge them to obtain an accurate acoustic travel time curve.

2. The decision tree-based environmental correction method for formation logging curves according to claim 1, characterized in that, the basic data in step S1 includes the depth, resistivity, natural gamma ray, spontaneous potential, acoustic travel time, and well diameter logging curves of the verification well and the calibration well.

3. The decision tree-based environmental correction method for formation logging curves according to claim 2, characterized in that, step S2 is specifically to select the normal curve section of the verification well whose sedimentary characteristics are similar to the curve abnormal section of the calibration well, that is, the section corresponding to the same natural gamma ray curve shape as the marker layer.

4. The decision tree-based environmental correction method for formation logging curves according to claim 3, characterized in that, take the natural gamma ray curve greater than 90 as the marker layer section 1 of the verification well, and the natural gamma ray curve less than 90 as the marker layer section 2 of the verification well.

5. The decision tree-based environmental correction method for formation logging curves according to claim 1, characterized in that, in step S3, the calibration calculation methods include curve calculations of multi-curve fitting linear fitting method, Faust empirical formula, and rock model forward modeling method.

6. The decision tree-based environmental correction method for formation logging curves according to claim 5, characterized in that, the multi-curve fitting linear fitting method specifically performs curve calculation according to the following formula: DTc = f(GR, Rt, SP) where DTc is the acoustic travel time; Rt is the formation resistivity; GR is the natural gamma ray; SP is the spontaneous potential.

7. The decision tree-based environmental correction method for formation logging curves according to claim 5, characterized in that, the Faust empirical formula is, DTc = KHC dRt where K, C, d are regional empirical coefficients; H is the depth, that is, the vertical depth; DTc is the acoustic travel time; Rt is the formation resistivity.

8. The decision tree-based environmental correction method for formation logging curves according to claim 5, characterized in that, the rock model forward modeling performs curve calculation according to the following formula: where DTc is the acoustic travel time; V ma formation matrix velocity; V f fluid velocity in the pores; porosity.

9. The decision tree-based environmental correction method for formation logging curves according to claim 5, characterized in that, step S4 is specifically to make intersection diagrams of the multi-curve fitting linear fitting method, Faust empirical formula, and rock model forward modeling calculations of the marker layer section 1 and marker layer section 2 of the verification well respectively with the measured acoustic travel time, obtain the correlation coefficients, and take the calculation method with the highest correlation coefficient as the calculation method for the acoustic travel time curve of this marker layer section of the verification well.

10. The formation logging curve environmental correction method based on decision tree according to claim 1, characterized in that, step S5 is specifically as follows: using the selected calculation method to calculate the acoustic travel time curve for the corresponding correction well section corresponding to the verified well marker layer section respectively, and splicing and merging the curves vertically according to the depth to obtain an accurate acoustic travel time curve.

11. An electronic device, characterized in that, the electronic device includes: a memory storing executable instructions; a processor, the processor running the executable instructions in the memory to implement the formation logging curve environmental correction method based on decision tree according to any one of claims 1-10.

12. A computer-readable storage medium, characterized in that, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the formation logging curve environmental correction method based on decision tree according to any one of claims 1-10.

Images