Invasion state correction method and device for formation resistivity logging data interpretation

Abstract

This invention relates to the field of open-hole logging technology in oil and gas exploration and development, and particularly to a method and apparatus for correcting invasion states in the interpretation of formation resistivity logging data. The method includes setting formation parameters corresponding to different layer thickness intervals and different invasion states, performing forward modeling, and calculating theoretical K values ​​and R values ​​based on the measured parameters. d 4 -R s 18 The value is used to train the established neural network model to obtain a set of interpretation models. These interpretation models can be used to interpret three formation parameters for each layer: the variable K value, the ratio of formation resistivity to intrusion zone resistivity, and the radius of intrusion zone. This solves the problem that the original fixed K value interpretation method cannot quantitatively interpret the true resistivity value of formations because the obtained apparent resistivity values ​​for ultrathin layers are not only too low but also have too small a range of variation. This makes it impossible to develop an intrusion state correction chart for the corresponding layer thickness, and thus impossible to correct for the intrusion and state effects of formations.

Description

Technical Field

[0001] This invention relates to the field of open-hole logging technology in oil and gas exploration and development, and particularly to a method and apparatus for correcting the invasion state in the interpretation of formation resistivity logging data. Background Technology

[0002] The intrusion state of strata is generally classified into three types: non-intrusion, low-intrusion, and high-intrusion. The apparent resistivity of the strata is affected by different intrusion states. As the resistivity of the strata increases compared to the intrusion zone, R... t / R xo As the radius of the intrusion zone (ri) gradually increases, the apparent resistivity value gradually decreases in low-intrusion strata, showing a good inverse relationship between the two. However, in high-intrusion strata, the apparent resistivity gradually increases, showing a good direct relationship between the two. Therefore, to ensure the accuracy of the correction for the influence of intrusion status, it is necessary to first determine whether the intrusion status of the strata is non-intrusive, low-intrusive, or high-intrusive before performing intrusion correction.

[0003] Traditional methods for classifying intrusion states include qualitative and quantitative approaches. The qualitative approach uses the apparent resistivity difference R between shallow and deep intrusion sites. d -R s Qualitative classification uses a positive amplitude difference to indicate low intrusion, a negative amplitude difference to indicate high intrusion, and overlap to indicate no intrusion. However, this method yields low amplitude difference values ​​with a small range of variation, resulting in low accuracy for thick layers and making it unusable for thin and ultrathin layers. A quantitative classification method involves developing a set of resistivity intrusion correction charts for different layer thicknesses with varying resistivity, and distinguishing layers by observing which chart the intersection point of the interpretation layers falls on. Examples of correction charts for low intrusion at 5.0m and 0.8m thicknesses, and for high intrusion at 6.0m and 0.8m thicknesses, are shown below. Figure 1-4 As shown, from Figure 1-4 It is evident that for thick layers, the interpretation error gradually increases as the layer thickness decreases. For thin and ultrathin layers, the measured apparent resistivity values ​​are too low and the range of variation is too small, making it impossible to develop high-intrusion and low-intrusion correction charts for the corresponding layer thicknesses, and thus impossible to quantitatively interpret the true resistivity of the formation. Summary of the Invention

[0004] This invention proposes a method and apparatus for correcting the invasion state in the interpretation of formation resistivity logging data. This addresses the shortcomings of the original method, which suffers from excessively low apparent resistivity and a small range of variation, making it impossible to develop high-invasion and low-invasion correction charts for corresponding formation thicknesses. Consequently, it cannot correct for the influence of formation thickness and invasion state, and therefore cannot perform true formation resistivity R0 analysis. t The problem of quantitative explanation.

[0005] According to one aspect of the present invention, an invasion state correction method for interpreting formation resistivity logging data is provided, comprising:

[0006] Formation parameters corresponding to different layer thickness intervals and different intrusion states are set, and forward modeling is performed to obtain measurement parameter values ​​related to the formation intrusion state. Based on the set formation parameters and measurement parameter values, the deep theoretical K value and the apparent resistivity difference R between the deep and shallow sides after resistivity correction are determined. d 4 -R s 18 ;

[0007] The optimal layer thickness interval is obtained by optimizing the different set layer thickness intervals.

[0008] Using the optimal layer thickness interval set by the forward modeling and the formation parameters corresponding to different intrusion states, as well as the obtained measured parameter values, deep theoretical K values, and R values... d 4 -R s 18 The established neural network model is trained to obtain the explanatory model corresponding to different invasion states for each optimal layer thickness interval;

[0009] Obtain the measurement parameter values ​​related to the intrusion state of the target formation, the formation thickness, and the R value determined based on the measurement parameter values. d 4 -R s 18 ;

[0010] Determine the apparent resistivity difference R in the deep and shallow three lateral directions of the unintruded strata after correction for stratum thickness and resistivity. d 13 -R s 13 According to the R d 13 -R s 13 Determine the intrusion state of the target stratum;

[0011] Find the optimal layer thickness interval that best matches the formation thickness of the target formation and the interpretation model corresponding to the intrusion state. Then, combine the measured parameter values ​​related to the formation intrusion state corresponding to the target formation with R... d 4 -R s 18 The data is input into the interpretation model and run to obtain the deep variation K value and the radius r of the intrusion zone corresponding to the target strata. i Formation resistivity R of intrusive zone t / R xo The value is interpreted as a result.

[0012] Preferably, the method for setting formation parameters corresponding to different layer thickness intervals and different intrusion states, and performing forward modeling to obtain measurement parameter values ​​related to the formation intrusion state includes:

[0013] Set the true resistivity R of the formation for different layer thickness intervals and different intrusion states. t , Intrusion resistivity R xo Radius of the intrusion zone r i A set of strata is input into a forward model for forward modeling simulation to obtain the measurement parameter values ​​related to the intrusion state of each stratum.

[0014] Preferably, the measured parameter values ​​related to the formation intrusion state include at least: the ratio of the supply current of the first shielding electrode to the main electrode in the deep three-sided direction, i.e., depth I1 / I0; the ratio of the sum of the supply currents of the first and second shielding electrodes in the deep three-sided direction to the supply current of the main electrode, i.e., depth I1+I2 / I0; and the potential U of the main electrode in the deep three-sided direction. d The ratio of the supply current to the shallow three-sided shielded electrode to the main electrode, i.e., shallow I1 / I0, and the potential U of the shallow three-sided main electrode. s .

[0015] Preferably, the method for determining the deep theoretical K value based on the set formation parameters and measurement parameter values ​​includes:

[0016] The formula for calculating the K-value in the deep theory is: Deep Theory K-value = R t / U d ;

[0017] In the formula: R t U is the true resistivity of the formation set during forward modeling. d The potential of the deep three-lateral main electrode is obtained through forward modeling.

[0018] Preferably, the method for optimizing different layer thickness intervals to obtain the optimal layer thickness interval includes:

[0019] Determine whether the average relative error of all theoretical K values ​​of strata depth between two adjacent thickness intervals is less than a predetermined percentage. If not, insert several thickness intervals between the two adjacent thickness intervals until the average relative error of all theoretical K values ​​of strata depth between each pair of adjacent thickness intervals after insertion is less than the predetermined percentage, thereby obtaining the optimal thickness interval.

[0020] Preferably, the step of determining the resistivity difference R between the shallow and deep sides after resistivity correction based on the measured parameter values ​​is... d 4 -R s 18 The methods include:

[0021] Among them, R after resistivity correction is determined. d 4 The methods include:

[0022] Determine the relationship between depth I1 / I0 and the depth theory K value in the forward modeling results;

[0023] Substitute the depth I1 / I0 obtained from the target formation measurement into the relationship between the depth I1 / I0 and the theoretical depth K value to calculate the corresponding value. Multiply the corresponding value by the U measured for the target formation. d , to obtain R d 4 ;

[0024] Among them, R after resistivity correction is determined. s 18 The methods include:

[0025] The method for determining the shallow theoretical K value based on the set formation parameters and measurement parameter values ​​includes:

[0026] The formula for calculating the shallow theoretical K value is: Shallow theoretical K value = R t / U s ;

[0027] In the formula: R t U is the true resistivity of the formation set during forward modeling. s The potential of the shallow three-sided main electrode is obtained through forward modeling.

[0028] Determine the relationship between shallow I1 / I0 and shallow theoretical K values ​​in the forward simulation results;

[0029] Substitute the shallow I1 / I0 obtained from the target formation measurement into the relationship between the shallow I1 / I0 and the shallow theoretical K value to calculate the corresponding value. Multiply the corresponding value by the U measured for the target formation. s , to obtain R s 18 .

[0030] Preferably, the step of determining the apparent resistivity difference R in the deep and shallow three lateral directions of the non-intrusive stratum after correction for stratum thickness and resistivity is... d 13 -R s 13 According to the R d 13 -R s 13 A method for determining the intrusion state of the target formation includes:

[0031] Based on the forward modeling results, the relationship between the depth of the non-intrusive strata I1+I2 / I0 and the theoretical K value is established, as well as the relationship between the shallow I1 / I0 and the theoretical K value.

[0032] Substitute the depth I1+I2 / I0 measured from the target stratum into the relationship between depth I1+I2 / I0 and the theoretical depth K value to calculate the corresponding value. Multiply the corresponding value by the U measured from the target stratum. d 0 , to obtain R d 13 ;

[0033] Substitute the shallow I1 / I0 value measured in the target formation into the relationship between shallow I1 / I0 and the shallow theoretical K value to calculate the corresponding value. Multiply the corresponding value by the U value measured in the target formation. s 0 , to obtain R s 13 ;

[0034] If R d 13 With R s 13 If the difference is negative, the intrusion state of the target stratum is high intrusion. If R d 13 With R s 13 If the subtraction result is positive, then the intrusion state of the target stratum is low-intrusion or non-intrusion.

[0035] Preferably, it further includes: measuring parameters obtained during forward simulation, and determining R based on the measuring parameters. d 4 -R s 18 The formation thickness is input into the interpretation model that best matches the formation thickness and the corresponding intrusion state, and the model is run to obtain the corresponding depth-varying K value and r. i R t / R xo Interpretation of the value;

[0036] Compare this with the deep theoretical K value of forward modeling and the set r i R t / R xo By comparing the values, the relative error between the two is determined. The relative error between the deep variable K value and the deep theoretical K value is the relative error of the final interpretation of the true resistivity of the formation.

[0037] According to one aspect of the present invention, an invasion state correction device for interpreting formation resistivity logging data is provided, comprising:

[0038] The forward modeling unit is used to set formation parameters corresponding to different layer thickness intervals and different intrusion states, and to perform forward modeling to obtain measurement parameter values ​​related to the formation intrusion state. Based on the set formation parameters and measurement parameter values, the deep theoretical K value and the apparent resistivity difference R between the deep and shallow sides after resistivity correction are determined. d 4 -R s 18 ;

[0039] The layer thickness interval optimization unit is used to optimize different set layer thickness intervals to obtain the optimal layer thickness interval.

[0040] The interpretation model building unit is used to utilize the optimal layer thickness interval set by the forward modeling and the formation parameters corresponding to different intrusion states, as well as the obtained measured parameter values, deep theoretical K values, and R values. d 4 -R s 18 The established neural network model is trained to obtain the explanatory model corresponding to different invasion states for each optimal layer thickness interval;

[0041] The acquisition unit is used to acquire the measurement parameter values ​​related to the intrusion state of the target formation, the formation thickness, and the R value determined based on the measurement parameter values. d 4 -R s 18 ;

[0042] The intrusion state determination unit is used to determine the apparent resistivity difference R in the deep and shallow three lateral directions of the undentrous strata after correction for stratum thickness and resistivity. d 13 -R s 13 According to the R d 13 -R s 13 Determine the intrusion state of the target stratum;

[0043] The interpretation result output unit is used to find the optimal layer thickness interval that best matches the formation thickness of the target formation and the interpretation model corresponding to the intrusion state. It then outputs the measurement parameters related to the formation intrusion state corresponding to the target formation and R... d 4 -R s 18 The data is input into the interpretation model and run to obtain the deep variation K value and the radius r of the intrusion zone corresponding to the target strata. i Formation resistivity R of intrusive zone t / R xo The value is interpreted as a result.

[0044] The present invention has at least the following beneficial effects:

[0045] This invention proposes a method and apparatus for correcting the invasion state in the interpretation of formation resistivity logging data. By performing forward modeling, parameters related to the formation invasion state are obtained. Then, the neural network models for different invasion states are trained using these parameters to obtain the interpretation model. The formation invasion state is accurately determined. Finally, the interpretation result is obtained by running the interpretation model corresponding to the formation invasion state. This achieves the correction of the influence of the invasion state on the true resistivity of the formation, thereby effectively improving the interpretation accuracy of the true resistivity value and solving the problem of the inability to quantitatively interpret the true resistivity value. Attached Figure Description

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present invention and, together with the specification, serve to explain the technical solutions of the present invention.

[0047] Figure 1 This illustration shows a three-sided low-intrusion correction diagram with a layer thickness of 5 meters according to an embodiment of the present invention;

[0048] Figure 2 A diagram showing a 0.8-meter layer thickness with three-sided low-intrusion correction according to an embodiment of the present invention is provided.

[0049] Figure 3 This illustration shows a 6-meter thick layer with three-sided high-intrusion correction diagram according to an embodiment of the present invention;

[0050] Figure 4 A diagram showing the three-sided high-intrusion correction of a layer with a thickness of 0.8 meters according to an embodiment of the present invention is provided.

[0051] Figure 5 This diagram illustrates the distribution of main current lines in a homogeneous layer according to an embodiment of the present invention.

[0052] Figure 6 A diagram showing the distribution of main current lines with a layer thickness of 4.8 meters according to an embodiment of the present invention is provided.

[0053] Figure 7 A diagram showing the distribution of main current lines with a layer thickness of 0.2 meters according to an embodiment of the present invention is provided.

[0054] Figure 8 The non-invasive stratum R shown is an embodiment of the present invention. t / R m Relationship diagram with K-value in deep theory;

[0055] Figure 9 This illustrates the non-invasive formation depths I1 / I0 and R according to an embodiment of the present invention. t / R m Relationship diagram;

[0056] Figure 10 This diagram illustrates the relationship between depth I1 / I0 and the theoretical depth K value for a fourth invasive state according to an embodiment of the present invention.

[0057] Figure 11 This diagram illustrates the relationship between shallow I1 / I0 and the shallow theoretical K value for the eighteenth invasive state according to an embodiment of the present invention.

[0058] Figure 12 A graph showing the relationship between the depth variation K value and the formation thickness according to an embodiment of the present invention is shown.

[0059] Figure 13 This diagram illustrates the relationship between the theoretical K value of the non-intrusive stratum depth and the depth I1+I2 / I0 according to an embodiment of the present invention.

[0060] Figure 14 This diagram illustrates the relationship between the theoretical K value for shallow, non-invasive formations and the shallow I1 / I0 ratio according to an embodiment of the present invention.

[0061] Figure 15 A flowchart illustrating an invasion state correction method for interpreting formation resistivity logging data according to an embodiment of the present invention is shown. Detailed Implementation

[0062] Various exemplary embodiments, features, and aspects of the present invention will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0063] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0064] In this document, 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 three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0065] Furthermore, to better illustrate the present invention, numerous specific details are set forth in the following detailed embodiments. Those skilled in the art will understand that the present invention can be practiced without certain specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order to highlight the spirit of the invention.

[0066] Figure 1 This illustration shows a three-sided low-intrusion correction diagram with a layer thickness of 5 meters according to an embodiment of the present invention; Figure 2 A diagram showing a 0.8-meter layer thickness with three-sided low-intrusion correction according to an embodiment of the present invention is provided. Figure 3 This illustration shows a 6-meter thick layer with three-sided high-intrusion correction diagram according to an embodiment of the present invention; Figure 4 A diagram showing the three-sided high-intrusion correction of a layer with a thickness of 0.8 meters according to an embodiment of the present invention is provided. Figure 5 This diagram illustrates the distribution of main current lines in a homogeneous layer according to an embodiment of the present invention.

[0067] Figure 6 A diagram showing the distribution of main current lines with a layer thickness of 4.8 meters according to an embodiment of the present invention is provided. Figure 7 A diagram showing the distribution of main current lines with a layer thickness of 0.2 meters according to an embodiment of the present invention is provided. Figure 8 The non-invasive stratum R shown is an embodiment of the present invention. t / R m Relationship diagram with K-value in deep theory; Figure 9 This illustrates the non-invasive formation depths I1 / I0 and R according to an embodiment of the present invention. t / R m Relationship diagram; Figure 10 This diagram illustrates the relationship between depth I1 / I0 and the theoretical depth K value for a fourth invasive state according to an embodiment of the present invention. Figure 11 This diagram illustrates the relationship between shallow I1 / I0 and the shallow theoretical K value for the eighteenth invasive state according to an embodiment of the present invention. Figure 12 A graph showing the relationship between the depth variation K value and the formation thickness according to an embodiment of the present invention is shown. Figure 13 This diagram illustrates the relationship between the theoretical K value of the non-intrusive stratum depth and the depth I1+I2 / I0 according to an embodiment of the present invention.

[0068] Figure 14 This diagram illustrates the relationship between the theoretical K value for shallow, non-invasive formations and the shallow I1 / I0 ratio according to an embodiment of the present invention. Figure 15 A flowchart illustrating an invasion state correction method for interpreting formation resistivity logging data according to an embodiment of the present invention is shown. Figure 1-15 As shown, a method for correcting the invasion state in the interpretation of formation resistivity logging data includes: Step S01: Setting formation parameters corresponding to different layer thickness intervals and different invasion states, and performing forward modeling to obtain measurement parameter values ​​related to the formation invasion state; determining the deep theoretical K value and the deep and shallow three-lateral apparent resistivity difference R after resistivity correction based on the set formation parameters and measurement parameter values. d 4 -R s 18Step S02: Optimize the set layer thickness intervals to obtain the optimal layer thickness interval; Step S03: Utilize the optimal layer thickness interval set in the forward modeling, the formation parameters corresponding to different intrusion states, and the obtained measurement parameter values, deep theoretical K value, and R... d 4 -R s 18 The established neural network model is trained to obtain the interpretation model corresponding to different intrusion states for each optimal layer thickness interval; Step S04: Obtain the measurement parameter values ​​related to the intrusion state of the target stratum, the stratum thickness, and the R value determined based on the measurement parameter values. d 4 -R s 18 Step S05: Determine the apparent resistivity difference R in the deep and shallow lateral directions of the non-intrusive strata after correction for stratum thickness and resistivity. d 13 -R s 13 According to the R d 13 -R s 13 Determine the intrusion state of the target formation; Step S06: Find the optimal layer thickness interval closest to the formation thickness of the target formation and the interpretation model corresponding to the intrusion state, and combine the measurement parameters related to the formation intrusion state of the target formation with R... d 4 -R s 18 The data is input into the interpretation model and run to obtain the deep variation K value and the radius r of the intrusion zone corresponding to the target strata. i Formation resistivity R of intrusive zone t / R xo The value is interpreted as a result.

[0069] In this embodiment of the invention, the original resistivity logging data is interpreted using the fixed K-value method. The basic formulas for resistivity logging and interpretation are as follows:

[0070] R a =K*U d / I0 (1);

[0071] In the formula: U d I0 is the main electrode potential, in millivolts (mV); I0 is the main electrode supply current, in milliamperes (mA); K is the electrode system constant; R0... a This is the apparent resistivity value, expressed in ohm-meters (Ω·m). d / I0 can be obtained through measurement, R aK and are two variables. Since the advent of resistivity logging and interpretation technology, the traditional approach has been to proceed from the right side of the above formula to the left side, that is, to measure U... d The apparent resistivity R is obtained by multiplying the I0 value by the fixed electrode system constant K obtained from the homogeneous layer. a Value, R a Treating it as a variable, the true resistivity R of the formation is ultimately explained by correcting for various influencing factors. t value.

[0072] This fixed K-value interpretation method has been used for decades and has effectively solved the problem of true resistivity R in thicker formations. t The quantitative interpretation of this method addresses the challenge of accurately determining formation oil saturation values, providing crucial information for reservoir evaluation and yielding significant geological results. However, this fixed K-value interpretation method suffers from the following two problems:

[0073] Question 1: Please provide two lateral low resistivity and intrusion correction charts with layer thicknesses of 5 meters and 0.8 meters, as shown in the attached charts. Figure 1 , Figure 2 As shown, in Figure 1 and 2 In this context, d is the wellbore diameter, di is the diameter of the intrusion zone, dn is the outer diameter of the instrument, and R is the diameter of the well. LL3 d For the deep three-lateral apparent resistivity, R LL3 s For shallow three-sided apparent resistivity, R s R is the resistivity of the surrounding rock, h is the layer thickness, and R is the resistivity of the surrounding rock. m For the resistivity of the mud, from Figure 1 and Figure 2 As can be seen from the comparison, as the layer thickness gradually decreases from 5 meters to 0.8 meters, the opening of the calibration chart gradually narrows, resulting in a decrease in the true resistivity R of the formation. t The interpretation error gradually increases. Especially when the layer thickness reaches 0.6 meters, due to the narrow plot and low values, some errors in the original data may cause the intersection point to fall outside the plot, making R-squared impossible. t Quantitative interpretation of the value.

[0074] Question 2: For ultrathin layers less than 0.6 meters, taking a 0.2-meter ultrathin layer as an example, the apparent resistivity R is significantly affected by the layer thickness. a The values ​​are not only too low but also have a small range of variation, making it impossible to develop resistivity and intrusion effect correction charts for ultrathin layers, to perform intrusion effect correction on ultrathin layers, and to perform formation true resistivity R. t / R m (R m =1) value is interpreted quantitatively.

[0075] Ultrathin layers generally refer to strata with a thickness of 0.2m-0.5m. To solve the problem of the true resistivity R of ultrathin layers... tThe challenge of quantitative interpretation lies in accurately identifying the main problems with the original fixed K-value interpretation method.

[0076] (1) For the first time, the distribution diagram of the main current line vividly and intuitively reveals the contradiction between the stratification capability and the detection depth of the lateral logging method and the root cause of its existence.

[0077] The distribution of main current in a homogeneous stratum with a K-value is shown in the attached figure. Figure 5 As shown, from the appendix Figure 5 It is evident that the main current not only enters the formation entirely in a flat, planar manner, but also has a divergence width of only 0.8 meters at a depth of 10 meters, perfectly conforming to the basic principles of three-sided logging. This demonstrates that the shielding effect is optimal when the shielding electrode and the main electrode are equipotential (U1 = U0), resulting in the deepest detection depth and a maximum measured main electrode potential of 688.1 mV.

[0078] The ratio R of the true resistivity of the formation to the resistivity of the mud. t / R m =30(R) m =1), intrusion radius r i In a 0.1-meter non-intrusive stratum with a thickness of 4.8 meters, the main current distribution is shown in the attached figure. Figure 6 As shown. From the appendix Figure 6 It can be seen that the main current initially enters the stratum in a flat manner, but begins to diverge at a depth of 4 meters, and starts to flow into the surrounding rock at a depth of 7 meters. At a depth of 10 meters, 1 / 4 of the main current still flows. This indicates that the shielding electrode and the main electrode are equipotential (U1=U0), which has a good shielding effect, allows for a deeper detection depth, and the measured main electrode potential of 516.1mV is relatively large.

[0079] The main current distribution of the 0.2-meter-thick ultrathin layer is shown in the attached figure. Figure 7 As shown, from the appendix Figure 7 It is evident that most of the main current flows along the wellbore towards the surrounding rock, with only a small portion entering the formation and immediately flowing towards the surrounding rock. At a depth of 0.3 meters, no main current flows. This indicates that the shielding effect is worst when the shielding electrode and the main electrode are at the same equipotential (U1=U0), resulting in the shallowest detection depth and the lowest measured main electrode potential of 114.3.

[0080] Therefore, it can be concluded that for lateral logging, the fundamental reason why the contradiction between stratification capability and detection depth cannot be resolved by using the same method for each heterogeneous stratum and measuring it under the condition of shielded electrode and main electrode being in equipotential (U1=U0), is that the true resistivity of ultrathin strata cannot be explained.

[0081] (2) It profoundly reveals the fundamental problems of the fixed K value interpretation method.

[0082] In R t / R m =30(R) mIn the non-intrusive strata of (=1), the effects of different interpretation methods are shown in Table 1:

[0083] Table 1: Results of Different Interpretive Methods

[0084]

[0085] As shown in Table 1, the measured main electrode potential U varies from a homogeneous layer to a 0.2-meter ultrathin layer. d The apparent resistivity R decreased from 688.1 mV to 114.3 mV, a reduction of 6.02 times. Multiplying this by the fixed K value of 0.0436 measured in a homogeneous layer, the calculated apparent resistivity R... a The value dropped rapidly from 30 to 4.98, a reduction of 6.02 times, thus transferring all the drawbacks of the lateral logging method to the apparent resistivity R by multiplying by a fixed K value. a The value is being determined, ultimately resulting in the apparent resistivity R of the 0.2-meter ultrathin layer. a The values ​​are not only too low but also too small in range, making it impossible to develop low- and high-intrusion resistivity and intrusion effect correction charts for corresponding layer thicknesses, and thus impossible to perform formation true resistivity R. t Quantitative interpretation of the value.

[0086] This profoundly reveals that the original fixed K-value interpretation method for resistivity logging data applied a one-size-fits-all approach to each heterogeneous layer, using a fixed K-value measured in a homogeneous layer for the apparent resistivity R. a Value calculation directly transfers the inherent contradiction between the layering capability and the depth of exploration in well logging methods to the interpretation of apparent resistivity. This is also why the current method cannot distinguish the ultrathin layer invasion state, leading to an inaccurate true resistivity R. t The fundamental reason why the value cannot be quantitatively explained.

[0087] The method for correcting the invasion state in the interpretation of formation resistivity logging data provided in this embodiment of the invention specifically includes the following steps:

[0088] Step S01: Set a set of formation parameters corresponding to different layer thickness intervals and different intrusion states, and perform forward modeling to obtain measurement parameter values ​​related to the formation intrusion state. Based on the set formation parameters and measurement parameter values, determine the deep theoretical K value and the deep and shallow three-lateral apparent resistivity difference R after resistivity correction. d 4 -R s 18 .

[0089] In this invention, the method for setting formation parameters corresponding to different layer thickness intervals and different intrusion states, and performing forward modeling to obtain measurement parameter values ​​related to the formation intrusion state, includes: setting the true resistivity R of the formation corresponding to different layer thickness intervals and different intrusion states. t, Intrusion resistivity R xo Radius of the intrusion zone r i A set of strata is input into a forward model for forward modeling simulation to obtain the measurement parameter values ​​related to the intrusion state of each stratum.

[0090] In this invention, the measured parameter values ​​related to the formation intrusion state include at least: the ratio of the supply current of the first shielding electrode to the main electrode in the deep three-sided direction, i.e., depth I1 / I0; the ratio of the sum of the supply currents of the first and second shielding electrodes in the deep three-sided direction to the supply current of the main electrode, i.e., depth I1+I2 / I0; and the potential U of the main electrode in the deep three-sided direction. d The ratio of the supply current to the shallow three-sided shielded electrode to the main electrode, i.e., shallow I1 / I0, and the potential U of the shallow three-sided main electrode. s .

[0091] In this embodiment of the invention, among the measurement parameters obtained from forward simulation, its U d and U s These are the two parameters that have been measured in the original fixed K value interpretation method, while the three parameters I1 / I0, I1+I2 / I0, and I1 / I0 have never been measured or used.

[0092] In this invention, the method for determining the deep theoretical K value based on the set formation parameters and measurement parameter values ​​includes: the calculation formula for the deep theoretical K value is:

[0093] Deep Theory K Value = R t / U d ;

[0094] In the formula: R t U is the true resistivity of the formation set during forward modeling. d The potential of the deep three-sided main electrode is obtained through forward modeling.

[0095] In this embodiment of the invention, the variable K-value (deeply variable K-value) interpretation method is a reverse approach based on the original fixed K-value interpretation method, using the apparent resistivity R of the original formation. a In the calculation formula, the K value is treated as a variable. A larger measured main electrode potential indicates a thicker layer, so a smaller K value is used; conversely, a smaller measured main electrode potential indicates a thinner layer, so a larger K value is used. The depth-varying K value is used to offset the influence of layer thickness on the measurement. The expected results of the depth-varying K value interpretation method for 0.2-meter ultrathin layer electrical logging data are shown in Table 1. As can be seen from Table 1, from a homogeneous layer to a 0.2-meter ultrathin layer, although the deep lateral main electrode potential U... dThe value rapidly decreased from 688.1 mv to 114.3 mv, a reduction of 6.02 times. However, the calculated theoretical K value for depth rapidly increased from 0.0436 to 0.2625, a reverse increase of 6.02 times. This overcomes the shortcomings of the lateral logging method, achieving a perfect unity between the opposing forces of layering capability and detection depth in the depth-variable K value interpretation method. Ultimately, regardless of whether it is a 4.8-meter thick layer or a 0.2-meter ultrathin layer, R can be made... a / R m =R t / R m =30, which is the true resistivity value of the formation, achieving the same effect as a homogeneous formation. Therefore, it can be seen that as long as a method is found to make the depth-varying K value K of each layer... d 0 The value is calculated, and various influencing factors are corrected to make it approximate the theoretical K value. This value is then multiplied by the measured deep three-sided main electrode potential U. d That is, to obtain the true resistivity R of the formation. t The value, thus determining the true resistivity R of the formation. t The quantitative interpretation of the value is transformed into a deep-variable K-value. d 0 The exact solution.

[0096] In this embodiment of the invention, resistivity is one of the most important influencing factors among various factors in interpreting electrical logging data. The ratio R of the true resistivity of the 0.2-meter ultrathin non-invasive formation layer to the mud resistivity is... t / R m With deep theoretical K value K d 0 The relationship is as follows: Figure 8 As shown, from the appendix Figure 8 It can be seen that when R t / R m As K gradually increases from 2 to 40, the corresponding K... d 0 The value increased from 0.063 to 0.351, a 5.57-fold increase, demonstrating a strong positive correlation between the two values. This indicates the deep theoretical K value K d 0 It is greatly affected by resistivity and must be corrected.

[0097] Because it is impossible to develop a corresponding chart to correct for the influence of formation true resistivity on the 0.2-meter ultrathin layer, and the formation true resistivity R t The value is unknown before interpretation, therefore, to understand the deep variable K-value K... d 0 Innovative ideas and methods must be explored to correct for the effects of resistivity.

[0098] 0.2-meter ultrathin non-intrusive stratum depth I1 / I0 and R t / R mThe relationship is as follows: Figure 9 As shown, in Figure 9 In the middle, when R t / R m As the value increases from 2 to 40, the depth I1 / I0 ratio also increases from 15.13 to 40.55, a 2.64-fold increase, showing a good positive correlation between the two. In traditional lateral logging, the depth I1 / I0 parameter has not been measured or studied, but it is easily obtained through additional measurements. Therefore, this paper proposes for the first time to use the ratio of the supply current of the first shielding electrode to the supply current of the main electrode in deep three-sided lateral logging, depth I1 / I0, to replace the true formation resistivity R. t / R m For deep variation K value K d 0 A resistivity influence correction method was developed to solve the problem that deep variable K-value resistivity influence correction cannot be performed on 0.2-meter ultrathin layers.

[0099] In this invention, the measured resistivity-corrected apparent resistivity difference R between the shallow and deep sides is determined based on the measured parameter values. d 4 -R s 18 The method includes: wherein, determining the resistivity-corrected R d 4 The method includes: determining the relationship between depth I1 / I0 and the theoretical depth K value in the forward modeling results; substituting the depth I1 / I0 obtained from the target formation measurement into the relationship between depth I1 / I0 and the theoretical depth K value to calculate the corresponding value; and multiplying the corresponding value by the U value measured in the target formation. d , to obtain R d 4 ;

[0100] Among them, R after resistivity correction is determined. s 18 The method includes: determining the shallow theoretical K value based on the set formation parameters and measurement parameter values, wherein the method includes: the calculation formula for the shallow theoretical K value is: Shallow theoretical K value = R t / U s ;

[0101] In the formula: R t U is the true resistivity of the formation set during forward modeling. s The potential of the shallow three-sided main electrode is obtained through forward modeling.

[0102] Determine the relationship between shallow I1 / I0 and shallow theoretical K values ​​in the forward modeling results; substitute the shallow I1 / I0 obtained from the target formation measurement into the relationship between shallow I1 / I0 and shallow theoretical K values ​​to calculate the corresponding value, and multiply the corresponding value by the U measured in the target formation. s , to obtain R s 18 .

[0103] In this embodiment of the invention, an ultrathin layer with a set formation thickness of 0.2 meters and a deep three-dimensional lateral depth of R is used. t / R xo =2, r i Using a 0.3-meter intrusion condition as a benchmark, the measured depth I1 / I0 and the theoretical depth K value were obtained through forward modeling. The depth I1 / I0 and the theoretical depth K value are... d 0 The relational data table is shown in Table 2 below.

[0104] Table 2: Depth I1 / I0 and Theoretical Depth K Value d 0 Relational Data Table

[0105] <![CDATA[R t / R m ]]> 40 30 20 10 5 3 <![CDATA[R xo / R m ]]> 20 15 10 5 2.5 1.5 <![CDATA[r i (meters) 0.30 0.30 0.30 0.30 0.30 0.30 <![CDATA[Deep I1 / I0]]> 34.49 31.60 27.47 21.09 16.35 14.03 <![CDATA[Deep theory K value K d 0 > 0.421 0.349 0.275 0.191 0.138 0.107

[0106] Plot the depth I1 / I0 and the depth theory K value K d 0 The intersection diagram, the result is as follows Figure 10 As shown, a clear proportional relationship exists between the two, thus establishing the relationship between depth I1 / I0 and the theoretical depth K value K. d 0 The relationship between them is shown in equation (2) below.

[0107] Deep Theory K Value K d 0 =0.0465e 0.0643x (2);

[0108] Where x is the depth I1 / I0.

[0109] Substituting the actual measured depth I1 / I0 value of the target stratum into the relation (2) to calculate the corresponding value K d 0 Because this type of intrusion state is uniformly defined as the fourth type of intrusion state, it is called K. d 4 , will K d 4 Multiply by U obtained from the target formation measurement d The value, i.e., obtaining R d 4 .

[0110] In this embodiment of the invention, an ultrathin layer with a set formation thickness of 0.2 meters and a shallow three-dimensional lateral R-shape are used. t / R xo =0.33, r i Based on an intrusion condition of 0.175 meters, the measured shallow I1 / I0 and the calculated shallow theoretical K value were obtained through forward modeling. s 0 Among them, shallow I1 / I0 and shallow theoretical K value K s 0 The relational data table is shown in Table 3 below.

[0111] Table 3: Shallow I1 / I0 and Shallow Theoretical K Values ​​K s 0 Relational Data Table

[0112]

[0113]

[0114] Plotting shallow I1 / I0 and shallow theoretical K values ​​K s 0 The intersection diagram, the result is as follows Figure 11 As shown, this establishes the shallow I1 / I0 and the shallow theoretical K value K. s 0 The relationship between them is shown in equation (3) below.

[0115] Theoretical K value K s 0 =0.0219e 0.057x (3);

[0116] Where x is shallow I1 / I0.

[0117] Substituting the shallow I1 / I0 values ​​obtained from actual measurements of the target stratum into equation (3) yields the corresponding K. s 0 The value, because this type of intrusion state is uniformly defined as the eighteenth intrusion state, is called K. s 18 , will K s 18 Multiply by U obtained from the target formation measurement s The value, i.e., obtaining R s 18 .

[0118] In the input parameters, R d 4 -R s 18 This parameter was calculated by processing data from both deep and shallow lateral logging. d 4 -Rs 18 The maximum difference is 57.99, which is very large, while the original deep and shallow three-sided apparent resistivity difference R d -R s The maximum value is only 0.76, which is very small. Compared with the two, the absolute value of the maximum difference is 57.23 higher, and the relative value is 76.3 times larger. R d 4 -R s 18 The maximum range of the value is between 57.99 and 1.94, with the absolute value of the difference changing by nearly 30 times, which is a very large range; while the original R... d -R s The difference ranged from 0.76 to 0.04. Although the relative change in the difference reached 19 times, the absolute value of the difference only changed by 0.72, which is too small.

[0119] Therefore, it can be seen that the processed R d 4 -R s 18 Using the difference as an input parameter, the neural network model effectively corrects for layer thickness, resistivity, intrusion, and state effects on the K-value of deep variations compared to the original method using R. d -R s The difference will definitely lead to a qualitative improvement.

[0120] Step S02: Optimize the different layer thickness intervals to obtain the optimal layer thickness interval.

[0121] In this invention embodiment, layer thickness is one of the most important influencing factors in the interpretation of resistivity logging data. This invention scientifically reveals for the first time the objective law governing the influence of thin and ultra-thin layer thickness. In unintruded formations where the ratio of true resistivity to mud resistivity is equal to 30, the depth-varying K value K... d 0 The relationship between the formation thickness h and the stratigraphic thickness is shown in the attached figure. Figure 12 As shown, from the appendix Figure 12 It is evident that the variable K-value gradually increases as the layer thickness gradually decreases, exhibiting a strong inverse relationship. However, for thinner layers less than 0.5 meters thick, the effect of layer thickness on the variable K-value increases abruptly. For example, compared to a layer thickness of 4.8 meters, a difference of 4.3 meters (0.5 meters), the variable K-value only increases by 36%. But compared to a layer thickness of 0.3 meters (0.2 meters), a difference of only 0.1 meters, the variable K-value increases by an average of 53%, with a maximum increase of nearly 100% (92.3%). Therefore, the variable K-value is significantly affected by layer thickness and must be corrected for.

[0122] Since existing electrical logging data interpretation methods cannot correct for the influence of ultrathin layer thickness, it is necessary to explore new methods. After repeated research, it was finally determined that a set of neural network algorithm interpretation models with different layer thickness intervals should be established to correct the layer thickness.

[0123] In this invention, the method for optimizing different layer thickness intervals to obtain the optimal layer thickness interval includes: determining whether the average relative error of all theoretical K values ​​of strata depth between two adjacent layer thickness intervals is less than a predetermined percentage; if not, inserting several layer thickness intervals between the two adjacent layer thickness intervals until the average relative error of all theoretical K values ​​of strata depth between each pair of inserted layer thickness intervals is less than the predetermined percentage, thereby obtaining the optimal layer thickness interval.

[0124] In this embodiment of the invention, the predetermined percentage is 10%. The optimal layer thickness interval is selected based on the principle that the average relative error of all theoretical K values ​​of the strata between two adjacent layer thickness intervals must be less than 10%, thereby ensuring that the error of the final layer thickness correction is controlled within 5%. If the average relative error of the theoretical K values ​​is greater than 10%, several layer thickness intervals are inserted between the two adjacent layer thickness intervals until the average relative error of all theoretical K values ​​of the strata between each pair of inserted layer thickness intervals is less than 10%. If the sum of the average relative errors of the theoretical K values ​​between two adjacent layer thickness intervals in three adjacent layer thickness intervals is still less than 10%, one of the layer thickness intervals is deleted. The layer thickness interval is selected based on the principle that the layer thickness gradually decreases and the layer thickness interval gradually increases in density as the layer thickness gradually decreases.

[0125] Ten different layer thickness intervals were initially set, ranging from 4.8 meters to 0.2 meters: 4.8, 3.6, 2.4, 1.2, 0.8, 0.6, 0.5, 0.4, 0.3, and 0.2. The depth variation K value between each pair of layer thickness intervals was calculated. d 0 The average relative error and the initial selection of layer thickness intervals are shown in Table 11.

[0126] Table 11: Preliminary Statistical Table of Layer Thickness Intervals from 4.8m to 0.2m

[0127]

[0128]

[0129] As can be seen from Table 11, the average relative error of the theoretical K value between the two layer thickness intervals of 4.8 meters and 3.6 meters is 6.7%, so there is no need for sparse or dense layering in between.

[0130] Although the average relative error of the theoretical K value between the six layer thickness intervals of 3.6 and 2.4, 2.4 and 1.2, 1.2 and 0.8, 0.8 and 0.6, and 0.6 and 0.5 is between 7.4% and 9.8%, which is less than 10%, most layers exceed 10% when the stratum resistivity is relatively high and the intrusion is relatively deep. Therefore, it is necessary to densify the layers with five layer thickness intervals of 3.0, 1.8, 1.0, 0.7, and 0.55.

[0131] The theoretical K value has an average relative error of 14.1% between the two layer thickness intervals of 0.5 and 0.4 meters, so a 0.45-meter layer thickness interval must be added in the middle.

[0132] The average relative error of the theoretical K value between the two layer thickness intervals of 0.4 meters and 0.3 meters is as high as 26.4%, so it is necessary to densify the layer thickness interval by 2-3 layers in between.

[0133] The average relative error of the theoretical K value between the two layer thickness intervals of 0.3 meters and 0.2 meters is as high as 53.7%, so it is necessary to densify the layer thickness interval by 3-4 layers in between.

[0134] If the error between two layer thickness intervals is too large, exceeding 10%, multiple layer thickness intervals must be inserted in between. This means inserting several layer thickness intervals between intervals with an average relative error greater than 10%, ensuring that the relative error between the depth variation K values ​​corresponding to any two adjacent intervals after the insertion is less than or equal to 10%. Furthermore, for two layer thickness intervals with errors less than 10% but greater than 7%, an intermediate layer thickness interval can be inserted to further improve the correction accuracy.

[0135] To gain a deeper understanding of the optimal use of layer thickness intervals between 0.6 meters and 0.2 meters, measurements were taken at 14 layer thickness intervals. The average relative error of the theoretical K value of all strata depths between each pair of layer thickness intervals and the optimal use of layer thickness intervals are shown in Table 7.

[0136] Table 7: Statistical Table of Optimal Layer Thickness Intervals from 0.2m to 0.6m

[0137]

[0138]

[0139] As shown in Table 7, the average relative error of the depth variation K value among the 12 thickness intervals from 0.5 m to 0.2 m is less than 10%, so densification and sparsification are unnecessary. Among the three thickness intervals from 0.5 m to 0.6 m, the sum of the average relative errors of the theoretical depth K values ​​between adjacent thickness intervals is also less than 10%, so the middle thickness interval of 0.55 m can be deleted. The final determined optimal thickness intervals are 4.8 m, 3.6 m, 3.0 m, 2.4 m, 1.8 m, 1.2 m, 1.0 m, 0.8 m, 0.7 m, 0.6 m, 0.5 m, 0.45 m, 0.4 m, 0.375 m, 0.35 m, 0.325 m, 0.3 m, 0.28 m, 0.26 m, 0.24 m, 0.22 m, and 0.2 m, for a total of 22 thickness intervals.

[0140] Step S03: Using the optimal layer thickness interval set in the forward modeling and the formation parameters corresponding to different intrusion states, as well as the obtained measurement parameter values, deep theoretical K value, and R... d 4 -R s 18 The established neural network model is trained to obtain the explanatory model corresponding to different invasion states for each optimal layer thickness interval.

[0141] In this embodiment of the invention, the optimal layer thickness interval set during forward modeling and the different R values ​​corresponding to different intrusion states are used. t R xo r i The values ​​and forward simulations yield the corresponding measurement parameters, namely depth I1 / I0, depth I1+I2 / I0, and U. d 、Shallow I1 / I0、U s And the theoretical depth K value calculated based on measurement parameters. d 0 and R d 4 -R s 18 The data is fed into the corresponding neural network model to train the model, thereby obtaining each optimal layer thickness interval. Specifically, 22 layer thickness intervals correspond to 44 explanatory models for both high-invasion and low-invasion states. The neural network model is modeled using a Bayesian regularized backpropagation neural network algorithm.

[0142] In this embodiment of the invention, the formation depth variation K value K is solved by modeling using a neural network algorithm with six measured input parameters. d 0 R t / R xo r iThe optimal selection criteria for the input parameters of the three parameters are not only closely related to the layer thickness, resistivity, intrusion and state, but also require large values, with the maximum variation range being more than twice, in order to ensure the accuracy of the correction.

[0143] Table 4 shows the maximum values ​​and maximum variation factors of eight parameters measured at layer thicknesses of 0.2 meters and 1.0 meters. The maximum and minimum values ​​are respectively at R... t / R m =40 non-intrusive strata and R t / R m =3, r i = Value measured in an intrusive stratum of 0.3m.

[0144] Table 4: Maximum values ​​and maximum variation factors of measurement parameters for different layer thicknesses

[0145]

[0146] As can be seen from Table 4: 1. The depth I1 / I0 value is related to the layer thickness, true resistivity, and intrusion state parameter R. t / R xo r i Closely correlated, the maximum value is 25.8 with a layer thickness of 0.2m and a maximum variation range of 2.4 times; the maximum value is 11 with a layer thickness of 1.0m and a maximum variation range of 1 time. This meets the input parameter optimization criteria. It is used to correct for the influence of layer thickness, resistivity, and invasive state on the K-value, and R... d 4 Calculation of values.

[0147] 2. The relationship between the depth I1+I2 / I0 value and layer thickness, true resistivity, and intrusion state parameter R t / R xo r i Closely correlated, its value gradually increases with increasing layer thickness. The maximum value is 1098.3 for a layer thickness of 0.2m, with a maximum variation range of 4.7 times; the maximum value is 4737.6 for a layer thickness of 1m, with a maximum variation range of 15.4 times. This meets the input parameter optimization criteria. It is used for correction of the influence of layer thickness, resistivity, and invasive state on the K-value of deep variations, and for R... d 4 The calculations show that as the layer thickness gradually increases from 0.2 meters, its effect becomes better and better than that of depth I1 / I0.

[0148] 3. U d Values ​​related to layer thickness, true resistivity, and invasive state parameter R t / R xo r i Closely related, with a layer thickness of 0.2m, the maximum value is 173.7, and the maximum variation range is 4.7 times; with a layer thickness of 1m, the maximum value is 877.5, and the maximum variation range is 17.1 times. The effect is better than using the original calculated apparent resistivity R. aThe value is much better, meeting the input parameter optimization criteria. It is used for correction of the influence of layer thickness, resistivity, and intrusion state on the K-value of deep variation, and for the theoretical K-value of each layer depth. d 0 With K d 4 The calculation.

[0149] 4. Shallow I1 / I0 value and layer thickness, true resistivity and invasive state parameter R t / R xo r i There is a good relationship; the maximum value is 34.2 with a layer thickness of 0.2m and the maximum variation is 2.3 times; the maximum value is 39.1 with a layer thickness of 1m and the maximum variation is 2.6 times. This meets the input parameter optimization criteria. It is used to correct for the influence of layer thickness, resistivity, and intrusion state on the deep variation K value, and to determine the shallow theoretical K value for each layer. s 0 With R s 18 Calculation of values.

[0150] 5. U s Values ​​related to layer thickness, true resistivity, and invasive state parameter R t / R xo r i There is a good relationship; the maximum value is 42.3 with a layer thickness of 0.2m, and the maximum variation is 3.3 times; the maximum value is 67.4 with a layer thickness of 1m, and the maximum variation is 5.0 times. The effect is better than using the original shallow three-sided apparent resistivity R. s It is much better, meets the input parameter optimization criteria, and is used for correction of the effects of layer thickness, resistivity, and intrusion state on deep variable K-values ​​and shallow theoretical K-values. s 0 With R s 18 The calculation.

[0151] 6. R d 4 -R s 18 Values ​​related to layer thickness, true resistivity, and invasive state parameter R t / R xo r i Closely related, with a maximum value of 57.99 at a layer thickness of 0.2m and a maximum variation of 30 times, it meets the input parameter optimization criteria and is used to correct for the influence of layer thickness, resistivity and invasive state on the deep variation K value.

[0152] Step S04: Obtain the measurement parameter values ​​related to the intrusion state of the target formation, the formation thickness, and the R value determined based on the measurement parameter values. d 4 -R s 18 .

[0153] In this embodiment of the invention, the formation thickness of the target stratum needs to be interpreted using a stratification method based on well logging data. Strata thicker than 0.6 meters are delineated using conventional well logging data, while ultra-thin layers of 0.2-0.5 meters are delineated using electrical imaging well logging data. For the first time, detailed requirements for the accuracy of formation thickness delineation are explicitly stated: for layers between 4.8 meters and 1.2 meters, the accuracy must be within 0.6 meters; for layers between 1.2 meters and 0.8 meters, the accuracy must be within 0.2 meters; for layers between 0.8 meters and 0.5 meters, the accuracy must be within 0.1 meters; for layers between 0.5 meters and 0.4 meters, the accuracy must be within 0.05 meters; for layers between 0.4 meters and 0.3 meters, the accuracy must be within 0.025 meters; and for layers between 0.3 meters and 0.2 meters, the accuracy must be within 0.02 meters.

[0154] The measurement parameters corresponding to the target strata are depth I1 / I0, depth I1+I2 / I0, and U. d 、Shallow I1 / I0、U s Then determine the corresponding R based on the measurement parameters. d 4 -R s 18 .

[0155] Step S05: Determine the apparent resistivity difference R in the deep and shallow three lateral directions of the uninvaded strata after correction for stratum thickness and resistivity. d 13 -R s 13 According to the R d 13 -R s 13 Determine the intrusion state of the target formation.

[0156] In this invention, the apparent resistivity difference R in the deep and shallow three lateral directions of the non-invasive stratum, after correction for stratum thickness and resistivity, is determined. d 13 -R s 13 According to the R d 13 -R s 13 The method for determining the intrusion state of the target stratum includes: establishing, based on the forward modeling results, a relationship between the depth I1+I2 / I0 of the unintruded stratum and the theoretical K value, and a relationship between the shallow I1 / I0 and the theoretical K value; substituting the measured depth I1+I2 / I0 value of the target stratum into the relationship between the depth I1+I2 / I0 and the theoretical K value to calculate the corresponding value; and multiplying the corresponding value by the U value measured in the target stratum. d 0 , to obtain R d13 Substitute the shallow I1 / I0 value measured in the target formation into the relationship between shallow I1 / I0 and the shallow theoretical K value to calculate the corresponding value, and then multiply the corresponding value by the U value measured in the target formation. s 0 , to obtain R s 13 If R s 13 With R d 13 If the difference is negative, the intrusion state of the target stratum is high intrusion. If R s 13 With R d 13 If the subtraction result is positive, then the intrusion state of the target stratum is low intrusion or non-intrusion.

[0157] In this embodiment of the invention, to ensure the deep variation K value K d 0 Intrusion affects the accuracy of correction. Before intrusion correction, the intrusion status of the target stratum must be determined, i.e., whether it is low-intrusion (non-intrusion) or high-intrusion.

[0158] R d 13 The apparent resistivity of the formation is obtained by using the variable K-value method after correcting for the effects of layer thickness and resistivity on the three-dimensional lateral logging data in the non-invasive formation.

[0159] The forward modeling data of 20 non-intrusive strata in the deep three-dimensional lateral direction of electrode system No. 9 are shown in Table 8.

[0160] Table 8: Three-lateral measurement data of non-intrusive strata depth for electrode system No. 9

[0161]

[0162]

[0163] As can be seen from Table 8, with R... t / R m Gradually decrease, depth I1+I2 / I0 and K d 0 The value also gradually decreases, showing a strong positive proportional relationship between the two. Based on the data in Table 8, a deep theoretical K-value K is established. d 0 The relationship with depth I1+I2 / I0 is as follows Figure 13 As shown, from Figure 13 The polynomial relationship between the two can be obtained as shown in equation (4) below:

[0164] Deep Theory K Value K d 0=6.8455755E-13(depth I1+2 / I0) 4 -1.4408700E-09 (Deep I1+2 / I0) 3

[0165] +1.1645956E-06 (Deep I1+2 / I0) 2 -2.9322345E-04(Deep I1+2 / I0)

[0166] +5.9341769E-02 (4);

[0167] Its correlation coefficient R 2 =0.9999. K calculated using formula (4) d 0 It was obtained from 20 non-intrusive strata, so it is collectively referred to as K. d 13 K is calculated according to equation (4). d 13 With deep theoretical K value K d 0 The average relative error is only 0.42%, which is very high precision.

[0168] Substituting the actual measured depth I1+I2 / I0 value of the target stratum into equation (4), the corresponding K is obtained. d 13 Multiply it by the U obtained from the actual measurement of the target stratum. d The value can ultimately yield the corresponding R. d 13 value.

[0169] R s 13 The apparent resistivity of the formation is determined by using the variable K-value method after correcting for the effects of layer thickness and resistivity on shallow three-dimensional lateral logging data in non-invasive formations.

[0170] Taking the forward modeling data of 20 unintruded strata in the shallow three-lateral direction of electrode system No. 9 as an example, as shown in Table 9:

[0171] Table 9: Shallow Three-Lateral Measurement Data of Electrode System No. 9 (Non-Intrusive Strata)

[0172]

[0173]

[0174] As can be seen from Table 9, with R t / R m Gradually decrease, shallow I1 / I0 and K s 0The value also gradually decreases, showing a strong positive proportional relationship between the two. Based on the data in Table 9, a preliminary theoretical K value K is established. s 0 The relationship with shallow I1 / I0 is as follows Figure 14 As shown, from Figure 14 The polynomial relationship between the two can be obtained as shown in equation (5) below:

[0175] Theoretical K value K s 0 =2.0531988E-06(Shallow I1 / I0) 5 -2.4165718E-04 (Light I1 / I0) 4

[0176] +1.1367868E-02(Light I1 / I0) 3 -2.6584193E-01 (Light I1 / I0) 2

[0177] +3.0994132(Shallow I1 / I0)-14.321412(5);

[0178] Its correlation coefficient R 2 =0.9999. K calculated using formula (5) s 0 It was obtained from 20 non-intrusive strata, so it is collectively referred to as K. s 13 K is calculated according to equation (5). s 13 With shallow theory K value K s 0 The average relative error is only 0.35%, which is very high precision.

[0179] Substituting the actual measured shallow I1 / I0 values ​​of the target stratum into equation (5), the corresponding K is obtained. s 13 Multiply it by the U obtained from the actual measurement of the target stratum. s The value can ultimately yield the corresponding R. s 13 value.

[0180] Based on this, R d 13 Subtract R s 13 The difference can be obtained. In order to better classify the intrusion state of the strata, it is best to have a difference close to zero in the non-intrusive strata. The difference values ​​of 20 layers were found to be between +0.08 and 0.09, with an average difference of 0.033, which meets the expected requirements.

[0181] To understand the R calculated using a combination of deep and shallow lateral logging data for electrode system No. 9 d 13 -R s 13 The effectiveness of the value in classifying stratigraphic intrusion states was investigated by measuring 351 stratigraphic layers with a 0.2-meter ultrathin layer. These included 12 intrusive layers, 259 low-intrusive layers, and 80 high-intrusive layers. Statistical analysis was performed based on the criteria: positive differences indicated low intrusion or intrusion, while negative differences indicated high intrusion. Of the 12 intrusive layers, 11 had positive differences (91% accuracy rate); all 259 low-intrusive layers had positive differences (100% accuracy rate); and of the 80 high-intrusive layers, 79 had negative differences (98.8% accuracy rate). In total, 249 out of 351 layers were accurate, resulting in an overall accuracy rate of 99.4%.

[0182] This innovative method effectively solves the global challenge of accurately classifying the intrusion states of strata of all thicknesses, including ultrathin layers of 0.2 meters, providing an important guarantee for accurate correction of intrusion and state effects of variable K values.

[0183] Step S06: Find the optimal layer thickness interval that best matches the formation thickness of the target formation and the interpretation model corresponding to the intrusion state. Then, combine the measurement parameters related to the formation intrusion state corresponding to the target formation with R... d 4 -R s 18 The data is input into the interpretation model and run to obtain the deep variation K value and the radius r of the intrusion zone corresponding to the target strata. i Formation resistivity R of intrusive zone t / R xo The value is interpreted as a result.

[0184] In this embodiment of the invention, if the target stratum thickness is 0.36 meters and the intrusion state is low-intrusion, then the corresponding low-intrusion state neural network interpretation model with the optimal thickness interval of 0.35 meters closest to the target stratum thickness is selected. This interpretation model is input with five parameters actually measured for the target stratum and R calculated based on the measured parameters. d 4 -R s 18 The values ​​are then used to obtain the interpreted results, namely the deep-variable K-value and r. i R t / R xo This invention is the first to use a Bayesian regularized backpropagation neural network algorithm for modeling, replacing the correction chart in the original fixed K-value interpretation method with a neural network model, thereby achieving accurate correction of the impact of invasion state on resistivity logging interpretation.

[0185] In this invention, the method further includes: measuring parameters obtained during forward simulation, and determining R based on the measuring parameters.d 4 -R s 18 The formation thickness is input into the interpretation model that best matches the formation thickness and the corresponding intrusion state, and the model is run to obtain the corresponding depth-varying K value and r. i R t / R xo The value is interpreted; it is compared with the deep theoretical K value and the set r value in the forward modeling. i R t / R xo By comparing the values, the relative error between the two is determined. The relative error between the deep variable K value and the deep theoretical K value is the relative error of the final interpretation of the true resistivity of the formation.

[0186] In this embodiment of the invention, after obtaining the interpretation model through training, to determine the error of the interpretation result of the interpretation model, it is necessary to find the formation with the set thickness during the forward simulation corresponding to the optimal layer thickness interval of the interpretation model, and obtain the measurement parameters obtained from the forward simulation of the formation corresponding to that formation, i.e., the deep theory K value K. d 0 、deep I1 / I0, deep I1+I2 / I0, U d 、Shallow I1 / I0、U s and the calculated R d 4 -R s 18 Input the corresponding interpretation model, run it, and obtain the interpretation result, i.e., r. i R t / R xo Deep variable K value K d 0 The interpretation results were compared with the r set during the corresponding forward model. i R t / R xo The relative error between the calculated deep theoretical K value and the calculated K value is determined by comparing them. This relative error is the relative error of the final explanation result obtained from running the final explanation model. Here, K... d 0 The relative error in the interpretation of the value is the true resistivity R of the formation. t Error in quantitative interpretation.

[0187] In this embodiment of the invention, electrode system No. 9 was used to measure 360 ​​strata (276 low-intrusion and 84 high-intrusion) with a thickness of 0.2 meters and a thickness of 0.8 meters, and the results were interpreted using the variable K-value method. The interpretation results are shown in Tables 5 and 6.

[0188] Table 5: Data on the interpretation of different intrusion states of the 0.2-meter ultrathin layer

[0189]

[0190] Table 6: Interpretation data of different intrusion states in 0.8-meter thick strata

[0191]

[0192] As can be seen from Tables 5 and 6, 1. The variable K value K d 0 The average relative error of the interpretation was 9.59% for a 0.2-meter ultrathin layer in low-intrusion strata, with an interpretation accuracy 70.1 percentage points higher than the original fixed K-value interpretation method; and 7.77% for a 0.8-meter thick layer, with an interpretation accuracy 45.1 percentage points higher than the original fixed K-value interpretation method. In high-intrusion strata, the average relative error was 4.72% for a 0.2-meter ultrathin layer, with an interpretation accuracy 35.7 percentage points higher than the original fixed K-value interpretation method; and 9.54% for a 0.8-meter thick layer, with an interpretation accuracy 19.6 percentage points higher than the original fixed K-value interpretation method. All these results demonstrate high accuracy. Furthermore, the number of layers with positive and negative errors and the average relative error are very close, with all relative errors less than 10%, indicating a good result. This demonstrates that the stratigraphic intrusion state classification is effective and can accurately reflect the true resistivity R of both low-intrusion and high-intrusion strata. t Quantitative explanations have yielded promising results.

[0193] 2. In the method of interpreting variable K values, R can also be provided. t / R xo and r i The average relative errors of key parameters for the two stratigraphic intrusion conditions are 2.90% and 16.8% for a 0.2-meter ultrathin layer and 2.14% and 13.9% for a 0.8-meter thick layer, respectively, in low-intrusion strata. In high-intrusion strata, the average relative errors are 0.81% and 3.33% for a 0.2-meter ultrathin layer and 2.90% and 6.48% for a 0.8-meter thick layer, respectively, all showing high accuracy. Furthermore, the number of layers with positive and negative errors and the average relative errors are very close, with the relative errors of most layers being less than 10%, demonstrating excellent results. This data is fully capable of quantitative interpretation and can be used to scientifically analyze the intrusion conditions of each layer, providing crucial foundational data for accurate impact correction.

[0194] In this embodiment of the invention, 250 0.2-meter ultrathin layers (150 low-intrusion layers and 100 high-intrusion layers) of electrode system No. 5 were interpreted using corresponding intrusion state interpretation models and opposite intrusion state interpretation models (low-intrusion strata were interpreted using high-intrusion models, and high-intrusion strata were interpreted using low-intrusion models). The final interpretation results are shown in Table 10.

[0195] Table 10: Explanation of Data for Corresponding and Interchangeable Network Models

[0196]

[0197] Table 10 shows the results interpreted using the corresponding and opposite intrusion state models, respectively. As can be seen from Table 10: 1. The interpretation using the corresponding intrusion state model yielded high accuracy and good results for all three stratigraphic parameters; 2. The interpretation using the opposite intrusion state model showed variations in the K-value between low-intrusion and high-intrusion strata. d 0 The average relative errors were 49.1% and 360%, respectively. t / R xo The average relative errors were 155.8% and 3257%, respectively. i The average relative errors were 756.9% and 243%, respectively, both too large to be used. This fully demonstrates that accurate division of the formation intrusion state is crucial for accurate intrusion correction and accurate determination of the formation's true resistivity R. t How important is the quantitative interpretation of values?

[0198] This invention is applicable not only to lateral logging but also to the interpretation of all resistivity logging data. It is applicable not only to ultra-thin layers of 0.2 to 0.5 meters but also to all other formation thicknesses. The thinner the layer, the greater the improvement in accuracy compared to the original interpretation method. It has the advantages of high interpretation accuracy, low input cost, and high output benefits.

[0199] It is understood that the various method embodiments mentioned above in this invention can be combined with each other to form combined embodiments without violating the principle and logic. Due to space limitations, this invention will not elaborate further.

[0200] The execution entity for the invasion state correction method in formation resistivity logging data interpretation can be a formation resistivity logging data interpretation invasion state correction device. For example, the method can be executed by a terminal device, server, or other processing device. The terminal device can be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, vehicle-mounted device, wearable device, etc. In some possible implementations, the invasion state correction method can be implemented by a processor calling computer-readable instructions stored in memory.

[0201] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0202] This invention also provides an invasion state correction device for interpreting formation resistivity logging data, comprising: a forward modeling unit, used to set formation parameters corresponding to different layer thickness intervals and different invasion states, and to perform forward modeling to obtain measurement parameter values ​​related to the formation invasion state; and to determine the deep theoretical K value and the deep and shallow three-lateral apparent resistivity difference R after resistivity correction based on the set formation parameters and measurement parameter values. d 4 -R s 18 The layer thickness interval optimization unit is used to optimize different set layer thickness intervals to obtain the optimal layer thickness interval; the interpretation model establishment unit is used to utilize the optimal layer thickness interval set by the forward modeling and the formation parameters corresponding to different intrusion states, as well as the obtained measurement parameter values, deep theoretical K values, and R values. d 4 -R s 18 The established neural network model is trained to obtain the interpretation model corresponding to different intrusion states for each optimal layer thickness interval; the acquisition unit is used to acquire the measurement parameter values ​​related to the intrusion state of the target stratum, the stratum thickness, and R determined based on the measurement parameter values. d 4 -R s 18 The intrusion state determination unit is used to determine the apparent resistivity difference R in the deep and shallow three lateral directions of the undentrous strata after correction for stratum thickness and resistivity. d 13 -R s 13 According to the R d 13 -R s 13 The intrusion state of the target stratum is determined; the interpretation result output unit is used to find the optimal layer thickness interval closest to the formation thickness of the target stratum and the interpretation model corresponding to the intrusion state, and to input the measurement parameters related to the formation intrusion state of the target stratum and R... d 4 -R s 18 The data is input into the interpretation model and run to obtain the deep variation K value and the radius r of the intrusion zone corresponding to the target strata. i Formation resistivity R of intrusive zone t / R xo The value is interpreted as a result.

[0203] In some embodiments, the functions or modules and units included in the apparatus provided by the present invention can be used to execute the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0204] This invention replaces the original fixed K-value interpretation method with a variable K-value interpretation method to correct for the influence of intrusion state, thus solving the problem caused by R. a The values ​​are not only too low but also too small in range, making it impossible to develop low- and high-impact resistivity intrusion effect correction patterns for corresponding layer thicknesses, thus hindering accurate correction of intrusion effects and R... t This invention addresses the challenge of quantitative interpretation of K-values. Furthermore, it is the first to employ a Bayesian regularized backpropagation neural network algorithm for modeling, replacing the correction chart used in the original fixed K-value interpretation method to correct for resistivity, intrusion, and state effects on variable K-values. By establishing interpretation models corresponding to different layer thickness intervals and intrusion states, and training a neural network model with set formation parameters, six parameters obtained through forward modeling, and deep theoretical K-value inputs corresponding to the optimal layer thickness interval and intrusion state, the interpretation model is obtained. This is then applied through R... d 13 -R s 13 The difference is used to classify the intrusion state of the formation, thus correcting for the influence of intrusion state on the variable K-value. The actual target formation is interpreted using the optimal layer thickness interval closest to the actual formation thickness and an interpretation model corresponding to the actual intrusion state. This solves the previously insurmountable problem of correcting for the influence of intrusion state, improves the accuracy of intrusion and state influence correction, and makes the formation variable K-value interpretation method a complete success. It also effectively addresses the true resistivity R of the formation. t The value cannot be quantitatively explained, which is a global problem.

[0205] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for correcting the invasion state in the interpretation of formation resistivity logging data, characterized in that, include: Formation parameters corresponding to different layer thickness intervals and different intrusion states are set, and forward modeling is performed to obtain measurement parameter values ​​related to the formation intrusion state. Based on the set formation parameters and measurement parameter values, the deep theoretical K value and the apparent resistivity difference R between the deep and shallow sides after resistivity correction are determined. d 4 -R s 18 ; The optimal layer thickness interval is obtained by optimizing the different set layer thickness intervals. Using the optimal layer thickness interval set by the forward modeling and the formation parameters corresponding to different intrusion states, as well as the obtained measured parameter values, deep theoretical K values, and R values... d 4 -R s 18 The established neural network model is trained to obtain the explanatory model corresponding to different invasion states for each optimal layer thickness interval; Obtain the measurement parameter values ​​related to the formation intrusion state, formation thickness, and R determined based on the measurement parameter values ​​corresponding to the target formation. d 4 -R s 18 ; Determine the apparent resistivity difference R in the deep and shallow three lateral directions of the unintruded strata after correction for stratum thickness and resistivity. d 13 -R s 13 According to the R d 13 -R s 13 Determine the intrusion state of the target stratum; Find the optimal layer thickness interval that best matches the formation thickness of the target formation and the interpretation model corresponding to the intrusion state. Then, combine the measured parameter values ​​related to the formation intrusion state corresponding to the target formation with R... d 4 -R s 18 The data is input into the interpretation model and run to obtain the deep variation K value and the radius r of the intrusion zone corresponding to the target strata. i Formation resistivity R of intrusive zone t / R xo The value is interpreted as a result.

2. The method for correcting the invasion state in the interpretation of formation resistivity logging data according to claim 1, characterized in that, The method for setting formation parameters corresponding to different layer thickness intervals and different intrusion states, and performing forward modeling to obtain measurement parameter values ​​related to the formation intrusion state includes: Set the true resistivity R of the formation for different layer thickness intervals and different intrusion states. t , Intrusion resistivity R xo Radius of the intrusion zone r i A set of strata is input into a forward model for forward modeling simulation to obtain the measurement parameter values ​​related to the intrusion state of each stratum.

3. The method for correcting the invasion state in the interpretation of formation resistivity logging data according to claim 2, characterized in that, The measured parameter values ​​related to the formation intrusion state include at least: the ratio of the supply current of the first shielding electrode to the main electrode in the deep three-sided direction, i.e., depth I1 / I0; the ratio of the sum of the supply currents of the first and second shielding electrodes in the deep three-sided direction to the supply current of the main electrode, i.e., depth I1+I2 / I0; and the potential U of the main electrode in the deep three-sided direction. d The ratio of the supply current to the shallow three-sided shielded electrode to the main electrode, i.e., shallow I1 / I0, and the potential U of the shallow three-sided main electrode. s .

4. The method for correcting the invasion state in the interpretation of formation resistivity logging data according to claim 3, characterized in that: The method for determining the deep theoretical K value based on the set formation parameters and measurement parameter values ​​includes: The formula for calculating the K-value in deep theory is: Deep theory K-value = R t / U d ; In the formula: R t U is the true resistivity of the formation set during forward modeling. d The potential of the deep three-sided main electrode is obtained through forward modeling.

5. The method for correcting the invasion state in the interpretation of formation resistivity logging data according to claim 2, characterized in that, The method for optimizing different layer thickness intervals to obtain the optimal layer thickness interval includes: Determine whether the average relative error of all theoretical K values ​​of strata depth between two adjacent thickness intervals is less than a predetermined percentage. If not, insert several thickness intervals between the two adjacent thickness intervals until the average relative error of all theoretical K values ​​of strata depth between each pair of adjacent thickness intervals after insertion is less than the predetermined percentage, thereby obtaining the optimal thickness interval.

6. The method for correcting the invasion state in the interpretation of formation resistivity logging data according to claim 2, characterized in that, The resistivity difference R between the shallow and deep three sides after resistivity correction is determined based on the measured parameter values. d 4 -R s 18 The method, include: Among them, R after resistivity correction is determined. d 4 The methods include: Determine the relationship between depth I1 / I0 and the depth theory K value in the forward modeling results; Substitute the depth I1 / I0 obtained from the target formation measurement into the relationship between the depth I1 / I0 and the theoretical depth K value to calculate the corresponding value. Multiply the corresponding value by the U measured for the target formation. d , to obtain R d 4 ; Among them, R after resistivity correction is determined. s 18 The methods include: The method for determining the shallow theoretical K value based on the set formation parameters and measurement parameter values ​​includes: The formula for calculating the shallow theoretical K value is: Shallow theoretical K value = R t / U s ; In the formula: R t U is the true resistivity of the formation set during forward modeling. s The shallow three-lateral main electrode potential is obtained through forward modeling measurement; Determine the relationship between shallow I1 / I0 and shallow theoretical K values ​​in the forward simulation results; Substitute the shallow I1 / I0 obtained from the target formation measurement into the relationship between the shallow I1 / I0 and the shallow theoretical K value to calculate the corresponding value. Multiply the corresponding value by the U measured for the target formation. s , to obtain R s 18 .

7. The method for correcting the invasion state in the interpretation of formation resistivity logging data according to claim 6, characterized in that, The apparent resistivity difference R, after correction for layer thickness and resistivity, is determined for the depth, shallowness, and three lateral dimensions of the undisturbed layer. d 13 -R s 13 According to the R d 13 -R s 13 A method for determining the intrusion state of the target formation includes: Based on the forward modeling results, the relationship between the depth of the non-intrusive strata I1+I2 / I0 and the theoretical K value is established, as well as the relationship between the shallow I1 / I0 and the theoretical K value. Substitute the depth I1+I2 / I0 measured from the target stratum into the relationship between depth I1+I2 / I0 and the theoretical depth K value to calculate the corresponding value. Multiply the corresponding value by the U measured from the target stratum. d 0 , to obtain R d 13 ; Substitute the shallow I1 / I0 value measured in the target formation into the relationship between shallow I1 / I0 and the shallow theoretical K value to calculate the corresponding value. Multiply the corresponding value by the U value measured in the target formation. s 0 , to obtain R s 13 ; If R d 13 With R s 13 If the difference is negative, the intrusion state of the target stratum is high intrusion. If R d 13 With R s 13 If the subtraction result is positive, then the intrusion state of the target stratum is low-intrusion or non-intrusion.

8. The method for correcting the invasion state in the interpretation of formation resistivity logging data according to any one of claims 2-7, characterized in that, Also includes: The measurement parameter values ​​are obtained during forward simulation, and R is determined based on these measurement parameter values. d 4 -R s 18 The formation thickness is input into the interpretation model that best matches the formation thickness and the corresponding intrusion state, and the model is run to obtain the corresponding depth-varying K value and r. i R t / R xo Interpretation of the value; Compare this with the deep theoretical K value of forward modeling and the set r i R t / R xo By comparing the values, the relative error between the two is determined. The relative error between the deep variable K value and the deep theoretical K value is the relative error of the final interpretation of the true resistivity of the formation.

9. An invasion state correction device for interpreting formation resistivity logging data, characterized in that, include: The forward modeling unit is used to set formation parameters corresponding to different layer thickness intervals and different intrusion states, and to perform forward modeling to obtain measurement parameter values ​​related to the formation intrusion state. Based on the set formation parameters and measurement parameter values, the deep theoretical K value and the apparent resistivity difference R between the deep and shallow sides after resistivity correction are determined. d 4 -R s 18 ; The layer thickness interval optimization unit is used to optimize different set layer thickness intervals to obtain the optimal layer thickness interval. The interpretation model building unit is used to utilize the optimal layer thickness interval set by the forward modeling and the formation parameters corresponding to different intrusion states, as well as the obtained measured parameter values, deep theoretical K values, and R values. d 4 -R s 18 The established neural network model is trained to obtain the explanatory model corresponding to different invasion states for each optimal layer thickness interval; The acquisition unit is used to acquire the measurement parameter values ​​related to the intrusion state of the target formation, the formation thickness, and the R value determined based on the measurement parameter values. d 4 -R s 18 ; The intrusion state determination unit is used to determine the apparent resistivity difference R in the deep and shallow three lateral directions of the undentrous strata after correction for stratum thickness and resistivity. d 13 -R s 13 According to the R d 13 -R s 13 Determine the intrusion state of the target stratum; The interpretation result output unit is used to find the optimal layer thickness interval that best matches the formation thickness of the target formation and the interpretation model corresponding to the intrusion state. It outputs the measured parameter values ​​related to the formation intrusion state corresponding to the target formation and R... d 4 -R s 18 The data is input into the interpretation model and run to obtain the deep variation K value and the radius r of the intrusion zone corresponding to the target strata. i Formation resistivity R of intrusive zone t / R xo The value is interpreted as a result.

Images