Method and device for determining well logging interpretation conclusion

Abstract

The invention provides a well logging interpretation conclusion determination method and device, and the method comprises the steps: obtaining full well logging curve data of a target well, and determining at least one interpretation method corresponding to the target well; all the interpretation methods are used for processing the full-logging curve data, and an interpretation conclusion of each candidate interpretation layer section determined by each interpretation method is obtained; according to all the interpretation conclusions of each candidate interpretation layer section, screening out at least one target interpretation layer section from all the candidate interpretation layer sections; for each target interpretation layer section, determining the accuracy of each interpretation conclusion of the target interpretation layer section according to the weight coefficient of each interpretation method and the correlation coefficient of each corresponding interpretation method under the condition of the target interpretation layer section; and determining the explanation conclusion with the maximum accuracy as the final explanation conclusion of the target explanation layer section. Therefore, through the technical scheme provided by the invention, the accuracy of the explanation conclusion determination result can be effectively improved.

Description

Technical Field

[0001] This application relates to the field of logging technology, and in particular, to a method and device for determining logging interpretation conclusions. Background Art

[0002] With the vigorous development of modern oilfield exploration technology and intelligent information technology, while a large amount of logging data is rapidly collected, the demand for the accuracy of logging interpretation and evaluation is also increasing. During the process of logging interpretation, to further improve the coincidence rate of logging interpretation, different interpretation methods need to be selected for the same area or the same formation, and the interpretation conclusions generated by multiple interpretation methods are compared and analyzed and verified with each other to ensure the most reliable interpretation conclusion is finally obtained. In a sense, whether the interpretation method is properly selected is related to whether the evaluation result is correct. However, due to the concealed and heterogeneous characteristics of underground reservoirs, the ability to study and restore geological characteristics through logging interpretation not only depends on the effectiveness of interpretation methods and logging interpretation software, but also largely depends on the experience and ability accumulated by researchers. In traditional logging processing interpretation and evaluation, after calculating reservoir parameters, logging interpreters will combine the calculation results with professional knowledge to give the final logging interpretation and evaluation conclusion. This process highly depends on the regional experience of interpreters. Due to different decision-making criteria and large differences in experience among different researchers, the selection of interpretation conclusions generated by multiple interpretation and evaluation methods has great instability, ultimately resulting in the problem of low coincidence rate of interpretation conclusions. For logging interpreters, it is not an easy task to master a large number of interpretation methods, application requirements, and parameter selections well, so as to select the optimal interpretation conclusion. Therefore, in the process of logging interpretation, how to automatically select the optimal interpretation conclusion from multiple interpretation conclusions generated by multiple interpretation methods according to the different characteristics of the target interval, and improve the efficiency and accuracy of manual interpretation has become an urgent problem to be solved. Summary of the Invention

[0003] In view of this, the purpose of this application is to provide a method and device for determining logging interpretation conclusions. By introducing weight coefficients and correlation coefficients, the accuracy of each interpretation conclusion is determined, and the final interpretation conclusion is determined according to the maximum selection principle of accuracy, thereby improving the accuracy of the determination result of the interpretation conclusion and the efficiency of determining the interpretation conclusion.

[0004] An embodiment of this application provides a method for determining logging interpretation conclusions, and the determination method includes:

[0005] Obtain the full logging curve data of the target well, and determine at least one interpretation method corresponding to the target well according to the geological information of the target well; the target well includes at least one candidate interpretation interval;

[0006] Process the full log curve data using all interpretation methods respectively to predict the reservoir type of each candidate interpretation interval, and obtain the interpretation conclusion of each candidate interpretation interval determined by each interpretation method;

[0007] According to all the interpretation conclusions of each candidate interpretation interval, screen out at least one target interpretation interval from all candidate interpretation intervals;

[0008] For each target interpretation interval, determine the accuracy of each interpretation conclusion of this target interpretation interval according to the weight coefficient of each interpretation method and the correlation coefficient of each interpretation method corresponding to the conditions of this target interpretation interval;

[0009] Determine the interpretation conclusion with the maximum accuracy as the final interpretation conclusion of this target interpretation interval.

[0010] Optionally, the process of using all interpretation methods to process the full log curve data respectively to predict the reservoir type of each candidate interpretation interval and obtain the interpretation conclusion of each candidate interpretation interval determined by each interpretation method includes:

[0011] For each candidate interpretation interval, extract the interval log curve data corresponding to this candidate interpretation interval from the full log curve data;

[0012] Use the interpretation methods to process the interval log curve data respectively, and determine the interpretation conclusion of this candidate interpretation interval determined by each interpretation method.

[0013] Optionally, the initial accuracy of each interpretation method is the same.

[0014] Optionally, the process of screening out at least one target interpretation interval from all candidate interpretation intervals according to all the interpretation conclusions of each candidate interpretation interval includes:

[0015] For each candidate interpretation interval, determine whether the number of the same interpretation conclusions in this candidate interpretation interval exceeds a preset threshold; wherein, the preset threshold is determined according to the total number of interpretation methods corresponding to the target well and the rule requirements of the voting method;

[0016] If it exceeds, determine this candidate interpretation interval as the target interpretation interval.

[0017] Optionally, the process of determining the accuracy of each interpretation conclusion of each target interpretation interval according to the weight coefficient of each interpretation method and the correlation coefficient of each interpretation method determined under the conditions of this target interpretation interval includes:

[0018] For each interpretation conclusion of each target interpretation interval, multiply the initial accuracy, weight coefficient of the interpretation method corresponding to the interpretation conclusion, and the correlation coefficient of the interpretation method under the conditions of the target interpretation interval to determine the accuracy of the interpretation conclusion;

[0019] Add up the accuracies of the interpretation conclusions of the same type under the same target interpretation interval to determine the accuracy of each interpretation conclusion in each target interpretation interval.

[0020] Optionally, the weight coefficient of each interpretation method is determined through the following steps:

[0021] Obtain the importance scores determined by experts for all interpretation methods corresponding to the target well;

[0022] Construct an importance score matrix according to all the importance scores in a preset sorting manner;

[0023] According to the importance score matrix, perform consistency test processing to determine whether the consistency requirement is met;

[0024] If it is met, use the sum and integral or square root method to process the importance score matrix to determine the weight coefficient of each interpretation method.

[0025] Optionally, the correlation coefficient of each interpretation method under the conditions of the target interpretation interval is determined through the following steps:

[0026] Align the top and bottom depths of the interval logging curve data of the target interpretation interval, and determine the input data of each input parameter in each interpretation method corresponding to the target interpretation interval according to the processed interval logging curve data;

[0027] For each interpretation method, determine the correlation coefficient between two input parameters in the interpretation method through the correlation coefficient calculation formula and the data of all input parameter items in the interpretation method;

[0028] Add up and average the correlation coefficients between two input parameters determined in the same interpretation method to determine the correlation coefficient of each interpretation method corresponding to the target interpretation interval.

[0029] The embodiment of the present application also provides a device for determining logging interpretation conclusions, and the determining device includes:

[0030] An acquisition module, configured to acquire the full logging curve data of the target well, and determine at least one interpretation method corresponding to the target well according to the geological information of the target well; the target well includes at least one candidate interpretation interval;

[0031] A prediction module, configured to process the full log curve data respectively using all the interpretation methods to predict the reservoir type of each candidate interpretation interval, and obtain the interpretation conclusion of each candidate interpretation interval determined by each interpretation method;

[0032] A screening module, configured to screen out at least one target interpretation interval from all candidate interpretation intervals according to all the interpretation conclusions of each candidate interpretation interval;

[0033] A first determination module, configured to, for each target interpretation interval, determine the accuracy of each interpretation conclusion of this target interpretation interval according to the weight coefficient of each interpretation method and the correlation coefficient of each interpretation method corresponding to the condition of this target interpretation interval;

[0034] A second determination module, configured to determine the interpretation conclusion with the maximum accuracy as the final interpretation conclusion of this target interpretation interval.

[0035] Optionally, when the prediction module is configured to process the full log curve data respectively using all the interpretation methods to predict the reservoir type of each candidate interpretation interval and obtain the interpretation conclusion of each candidate interpretation interval determined by each interpretation method, the prediction module is configured to:

[0036] For each candidate interpretation interval, extract the interval log curve data corresponding to this candidate interpretation interval from the full log curve data;

[0037] Process the interval log curve data respectively using the interpretation methods to determine the interpretation conclusion of this candidate interpretation interval determined by each interpretation method.

[0038] Optionally, the initial accuracy of each interpretation method is the same.

[0039] Optionally, when the screening module is configured to screen out at least one target interpretation interval from all candidate interpretation intervals according to all the interpretation conclusions of each candidate interpretation interval, the screening module is configured to:

[0040] For each candidate interpretation interval, determine whether the number of the same interpretation conclusions in this candidate interpretation interval exceeds a preset threshold; wherein, the preset threshold is determined according to the total number of the interpretation methods corresponding to the target well and the rule requirements of the voting method;

[0041] If it exceeds, determine this candidate interpretation interval as a target interpretation interval.

[0042] Optionally, when the first determination module is used to determine the accuracy of each interpretation conclusion of the target interpretation segment according to the weight coefficient of each interpretation method and the correlation coefficient of each interpretation method determined under the conditions of the target interpretation segment, the first determination module is used to:

[0043] For each interpretation conclusion of each target interpretation segment, multiply the initial accuracy, weight coefficient of the interpretation method corresponding to the interpretation conclusion, and the correlation coefficient of the interpretation method corresponding to the target interpretation segment to determine the accuracy of the interpretation conclusion;

[0044] Add up the accuracies of the interpretation conclusions of the same type under the same target interpretation segment to determine the accuracy of each interpretation conclusion in each target interpretation segment.

[0045] Optionally, the determination device further includes a third determination module, and the third determination module is used to:

[0046] Obtain the importance scores of all interpretation methods corresponding to the target well determined by experts;

[0047] According to all the importance scores, construct an importance score matrix in a preset sorting manner;

[0048] According to the importance score matrix, perform consistency test processing to determine whether the consistency requirement is met;

[0049] If it is satisfied, use the sum or root method to process the importance score matrix to determine the weight coefficient of each interpretation method.

[0050] Optionally, the determination device further includes a fourth determination module, and the fourth determination module is used to:

[0051] Align the top and bottom depths of the well logging curve data of the segment of the target interpretation segment, and determine the input data of each input parameter in each interpretation method corresponding to the target interpretation segment according to the processed well logging curve data of the segment;

[0052] For each interpretation method, determine the correlation coefficient between two input parameters in the interpretation method through the correlation coefficient calculation formula and the data of all input parameter items in the interpretation method;

[0053] Add up and average the correlation coefficients between two input parameters determined in the same interpretation method to determine the correlation coefficient of each interpretation method corresponding to the target interpretation segment.

[0054] An embodiment of the present application further provides an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the memory through the bus. When the machine-readable instructions are executed by the processor, the steps of the determination method as described above are executed.

[0055] An embodiment of the present application further provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is run by a processor, the steps of the determination method as described above are executed.

[0056] A method and device for determining a logging interpretation conclusion provided by an embodiment of the present application. The determination method includes: obtaining full logging curve data of a target well, and determining at least one interpretation method corresponding to the target well according to the geological information of the target well; the target well includes at least one candidate interpretation interval; using all interpretation methods to process the full logging curve data respectively to predict the reservoir type of each candidate interpretation interval, and obtaining the interpretation conclusion of each candidate interpretation interval determined by each interpretation method; screening at least one target interpretation interval from all candidate interpretation intervals according to all interpretation conclusions of each candidate interpretation interval; for each target interpretation interval, determining the accuracy of each interpretation conclusion of the target interpretation interval according to the weight coefficient of each interpretation method and the correlation coefficient of each interpretation method corresponding to the target interpretation interval; and determining the interpretation conclusion with the maximum accuracy as the final interpretation conclusion of the target interpretation interval.

[0057] In this way, in this solution, by calculating the index weights of each interpretation method based on expert scoring, compared with directly assigning weights in the past, it avoids the bias of weight coefficients caused by subjective assignment, and improves the rationality and reliability of weight coefficients; on the basis of the weight voting method, adding the correlation analysis of interpretation methods to determine the correlation coefficients of different interpretation methods makes the selected interpretation conclusions more reliable. In addition, the results of this solution can be integrated into a software system, and all calculations and processes are implemented by a computer. Compared with the manual comparison and analysis in the past, it saves labor and improves work efficiency.

[0058] To make the above objects, features, and advantages of the present application more obvious and understandable, the following specifically enumerates preferred embodiments and cooperates with the accompanying drawings for detailed description as follows. Brief Description of the Drawings

[0059] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the accompanying drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0060] Figure 1 It is a flowchart of a method for determining a logging interpretation conclusion provided by an embodiment of the present application;

[0061] Figure 2 It is a schematic diagram of an interpretation conclusion display interface provided by the present application;

[0062] Figure 3 It is one of the structural schematic diagrams of a device for determining a logging interpretation conclusion provided by an embodiment of the present application;

[0063] Figure 4 It is the second structural schematic diagram of a device for determining a logging interpretation conclusion provided by an embodiment of the present application;

[0064] Figure 5 It is a structural schematic diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0065] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some, rather than all, of the embodiments of the present application. Usually, the components of the embodiments of the present application described and shown in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application claimed, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, every other embodiment obtained by those of ordinary skill in the art without creative efforts belongs to the scope of protection of the present application.

[0066] With the booming development of modern oilfield exploration technologies and intelligent information technologies, while a large amount of logging data is rapidly collected, the demand for the accuracy of logging interpretation and evaluation is also increasing. During the process of logging interpretation, to further improve the coincidence rate of logging interpretation, for the same area or the same formation, different interpretation methods need to be selected. Through the comparative analysis and mutual verification of the interpretation conclusions generated by multiple interpretation methods, the most reliable interpretation conclusion can be obtained. In a sense, whether the interpretation method is appropriately selected is related to whether the evaluation result is correct. However, due to the concealed and heterogeneous characteristics of underground reservoirs, the ability to study and restore geological characteristics through logging interpretation not only depends on the effectiveness of the interpretation method and logging interpretation software, but also largely relies on the experience and ability accumulated by researchers. In traditional logging data processing, interpretation, and evaluation, after calculating reservoir parameters, logging interpreters will combine the calculation results with professional knowledge to give the final logging interpretation and evaluation conclusion. This process highly depends on the regional experience of interpreters. Due to different decision-making criteria and large differences in experience among different researchers, the selection of interpretation conclusions generated by multiple interpretation and evaluation methods has great instability, ultimately resulting in a low coincidence rate of interpretation conclusions. For logging interpreters, it is not an easy task to master a large number of interpretation methods, application requirements, and parameter selections to select the optimal interpretation conclusion. Therefore, during the logging interpretation process, how to automatically select the optimal interpretation conclusion from multiple interpretation conclusions generated by multiple interpretation methods according to the different characteristics of the target interval, and improve the efficiency and accuracy of manual interpretation has become an urgent problem to be solved.

[0067] Based on this, the embodiments of the present application provide a method and device for determining a logging interpretation conclusion. By introducing a weight coefficient and a correlation coefficient, the accuracy of each interpretation conclusion is determined, and the final interpretation conclusion is determined according to the principle of selecting the maximum accuracy, thereby improving the accuracy of the determination result of the interpretation conclusion and the efficiency of determining the interpretation conclusion.

[0068] Please refer to Figure 1 , Figure 1 which is a flowchart of a method for determining a logging interpretation conclusion provided by an embodiment of the present application. As shown in Figure 1 , the determination method provided by the embodiments of the present application includes:

[0069] S101. Obtain the full logging curve data of the target well, and determine at least one interpretation method corresponding to the target well according to the geological information of the target well.

[0070] Here, the target well includes at least one candidate interpretation interval; the number and type of interpretation methods corresponding to different target wells may be different or the same.

[0071] Exemplarily, the interpretation methods may include the apparent resistivity increase rate method, the sensitive parameter crossplot method, the dual Rwa method, the array induction gradient factor method, the dual porosity ratio method, the dual water superposition method, etc.

[0072] S102. Use all the interpretation methods to process the full well logging curve data respectively to predict the reservoir type of each candidate interpretation interval, and obtain the interpretation conclusions of each candidate interpretation interval determined by each interpretation method.

[0073] Here, each interpretation method can determine an interpretation conclusion for each candidate interpretation interval. The interpretation conclusions determined by different interpretation methods for the same candidate interpretation interval may be the same or different, and the interpretation conclusions of different candidate interpretation intervals can be the same or different.

[0074] Exemplarily, an interpretation conclusion can be displayed in the following form: The candidate interpretation interval is an oil layer.

[0075] In addition, after determining at least one interpretation conclusion for each candidate interpretation interval, all the interpretation conclusions of the candidate interpretation interval can be visually displayed on the same screen so that the differences in the conclusions formed by different interpretation methods can be intuitively shown in the graph for researchers.

[0076] Exemplarily, please refer to Figure 2 , Figure 2 which is a schematic diagram of an interpretation conclusion display interface provided by this application. As shown in Figure 2 , the interpretation methods used for analyzing the target well include the apparent resistivity increase rate method, the sensitive parameter crossplot method, and the dual Rwa method. According to the display interface, the interpretation conclusion determined for the 41st interpretation interval by the apparent resistivity increase rate method is an oil-water layer, the interpretation conclusion determined by the sensitive parameter crossplot method is a water layer, and the interpretation conclusion determined by the dual Rwa method is an oil-water layer.

[0077] In an implementation manner provided by this application, the step of using all the interpretation methods to process the full well logging curve data respectively to predict the reservoir type of each candidate interpretation interval and obtain the interpretation conclusions of each candidate interpretation interval determined by each interpretation method includes:

[0078] S1021. For each candidate interpretation interval, extract the interval well logging curve data corresponding to the candidate interpretation interval from the full well logging curve data.

[0079] S1022. Use the interpretation methods to process the interval well logging curve data respectively, and determine the interpretation conclusions of the candidate interpretation interval determined by each interpretation method.

[0080] For step S1021, for each candidate interpreted interval, according to the geographical location information of the candidate interpreted interval, the interval well logging curve data corresponding to the candidate interpreted interval can be extracted from the full well logging curve data. The interval well logging curve data is a part of the full well logging curve data.

[0081] S103. Screen at least one target interpreted interval from all candidate interpreted intervals according to all the interpretation conclusions of each candidate interpreted interval.

[0082] Here, according to the voting method, at least one target interpreted interval can be screened from all candidate interpreted intervals according to all the interpretation conclusions of each candidate interpreted interval.

[0083] It should be noted that the final interpretation conclusions of the candidate interpreted intervals not determined as target interpreted intervals can be manually determined by relevant staff.

[0084] In an implementation manner provided by the present application, the screening of at least one target interpreted interval from all candidate interpreted intervals according to all the interpretation conclusions of each candidate interpreted interval includes:

[0085] S1031. For each candidate interpreted interval, determine whether the number of the same interpretation conclusions in the candidate interpreted interval exceeds a preset threshold.

[0086] S1032. If it exceeds, determine the candidate interpreted interval as a target interpreted interval.

[0087] For step S1031, the preset threshold is determined according to the total number of interpretation methods corresponding to the target well and the rule requirements of the voting method. The rule requirement of the voting method is that the minority obeys the majority.

[0088] Exemplarily, assuming that T interpretation methods are determined for the target well, the preset threshold can be T / 2.

[0089] S104. For each target interpreted interval, determine the accuracy of each interpretation conclusion of the target interpreted interval according to the weight coefficient of each interpretation method and the correlation coefficient of each interpretation method corresponding to the target interpreted interval.

[0090] Here, the weight coefficients of different interpretation methods may be the same or different. The correlation coefficients of the same interpretation method under the conditions of different target interpreted intervals may be the same or different.

[0091] In an implementation manner provided by the present application, the determining of the accuracy of each interpretation conclusion of the target interpreted interval according to the weight coefficient of each interpretation method and the correlation coefficient of each interpretation method determined under the conditions of the target interpreted interval includes:

[0092] S1041. For each interpretation conclusion of each target interpretation segment, multiply the initial accuracy, weight coefficient of the interpretation method corresponding to this interpretation conclusion, and the correlation coefficient of this interpretation method under the conditions of this target interpretation segment to determine the accuracy of this interpretation conclusion.

[0093] S1042. Add up the accuracies of the interpretation conclusions of the same type under the same target interpretation segment to determine the accuracy of each interpretation conclusion in each target interpretation segment.

[0094] For step S1041, the initial accuracies of each interpretation method are the same.

[0095] For step S1042, for each target interpretation segment, add up the accuracies of the interpretation conclusions of the same type in this target interpretation segment to determine the accuracy of each interpretation conclusion of this target interpretation segment.

[0096] In another implementation manner provided by this application, the weight coefficient of each interpretation method is determined through the following steps:

[0097] S201. Obtain the importance scores of all the interpretation methods corresponding to the target well determined by experts for each other.

[0098] S202. According to all the importance scores, construct an importance score matrix in a preset sorting manner.

[0099] S203. According to the importance score matrix, perform consistency test processing to determine whether the consistency requirement is met.

[0100] S204. If it is met, process the importance score matrix using the sum and integral or square root method to determine the weight coefficient of each interpretation method.

[0101] For step S201, the importance score is the importance score of one interpretation method relative to another interpretation method.

[0102] For example, assume there are 3 interpretation methods, namely h1, h2, and h3, and the determined importance scores are a ij (i = 1, 2, 3; j = 1, 2, 3), representing the importance score of interpretation method hi relative to interpretation method hj. For example, a 12 is the importance score of interpretation method h1 relative to interpretation method h2, and a ii is the importance score of the i-th interpretation method relative to itself, so it can be set to 1.

[0103] For step S202, for example, the preset sorting method can be determined according to the expert scoring table, and the preset sorting method is that the i-th row and the i-th column represent the same interpretation method.

[0104] For example, assume that the interpretation methods determined for the target well include the apparent resistivity increase rate method, the sensitive parameter crossplot method, and the double Rwa method. Please refer to Table 1, which is the expert scoring table.

[0105] Table 1:

[0106] Importance Score Resistance Increase Rate Method Sensitive Parameter Cross Method Dual Rwa Method Resistance Increase Rate Method 1 0.2 0.33 Sensitive Parameter Cross Method 5 1 0.14 Dual Rwa Method 3 7 1

[0107] In this way, the importance scoring matrix constructed according to the expert scoring table is:

[0108]

[0109] Therefore, the general form of the importance scoring matrix can be shown as follows:

[0110]

[0111] For step S203, in order to avoid logical errors in expert scoring, consistency test processing is required.

[0112] Here, the consistency test processing steps are as follows:

[0113] First, calculate the maximum eigenvalue according to the obtained importance scoring matrix, and its calculation formula is:

[0114]

[0115] Among them, n is the order of the importance scoring matrix, AW is the weight after standardizing the importance scoring matrix, and then the cumulative value by row. W i is the weight coefficient of the i-th interpretation method, W i The calculation formula of is shown as follows:

[0116]

[0117] n is the matrix order, a ij represents the importance scoring value of the i-th row and the j-th column in the matrix.

[0118] Then, solve the CI, RI, and CR values to determine whether the consistency passes.

[0119] Solve the consistency index CI value, and its solution formula is:

[0120]

[0121] Obtain the average random consistency index RI value, which is obtained by querying the consistency test index table.

[0122] Calculate the consistency ratio CR: CR = CI / RI.

[0123] Finally, make a judgment on whether the consistency requirement is met: when CR < 0.1, it indicates that the consistency degree of the importance scoring matrix is considered within the allowable range. At this time, the eigenvector of the importance scoring matrix can be used to calculate the weight vector; if CR ≥ 0.1, it means that there is a logical error in constructing the importance scoring matrix, and the importance scoring matrix needs to be reconstructed.

[0124] For step S204, the process of using sum and integral to process the importance scoring matrix and determine the weight coefficients of each interpretation method includes the following:

[0125] Sum-product method calculation formula:

[0126]

[0127] Normalize the importance scoring matrix by column, add the normalized columns, and divide each element after addition by n to obtain the corresponding weight vector, that is, determine the weight coefficients of each interpretation method.

[0128] The process of using the root method to process the importance scoring matrix and determine the weight coefficients of each interpretation method includes the following:

[0129] Root method calculation formula:

[0130]

[0131]

[0132] Calculate the nth power of the product of each row to obtain an n-dimensional vector, and normalize the vector to be the weight vector, that is, obtain the weight coefficients of each interpretation method.

[0133] It should be noted that when the proportion weights of each interpretation method are determined by researchers, due to the different professional levels of different researchers and their different understandings of geological conditions such as reservoirs, it often results in multiple weights for the same evaluation method, and the assignment of weight coefficients is relatively arbitrary, leading to unsatisfactory final prediction conclusions. By introducing the calculation of weight coefficients using the analytic hierarchy process, the analytic hierarchy process is a multi-index comprehensive evaluation algorithm, which is often used in comprehensive evaluation models. The analytic hierarchy process decomposes the elements related to decision-making into multiple levels such as goals, criteria, and solutions, and qualitative and quantitative analyses can be carried out on this basis.

[0134] Therefore, the weight coefficients calculated by this method avoid the problem of large instability caused by direct weight assignment due to large differences in researchers' experience, etc., and ultimately lead to a low coincidence rate of interpretation conclusions.

[0135] In another implementation provided by this application, the correlation coefficients of each interpretation method corresponding to the target interpretation interval condition are determined through the following steps:

[0136] S301. Align the top and bottom depths of the interval logging curve data of the target interpretation interval, and determine the input data of each input parameter in each interpretation method corresponding to the target interpretation interval condition according to the processed interval logging curve data.

[0137] S302. For each interpretation method, determine the correlation coefficients between pairwise input parameters in this interpretation method through the correlation coefficient calculation formula and the data of all input parameter items in this interpretation method.

[0138] S303. Add and average the correlation coefficients between pairwise input parameters determined in the same interpretation method to determine the correlation coefficient of each interpretation method corresponding to the target interpretation interval condition.

[0139] Regarding step S301, aligning the top and bottom depths of the interval logging curve data of the target interpretation interval specifically includes: The alignment process is to align the depth to the depth point closest to an integer multiple of the logging depth sampling interval, and the two correlation analysis sample points should have the same sampling interval (generally, the sampling interval is 0.125 m).

[0140] The input parameters of different interpretation methods may be the same or different, and the input data of the input parameters of the same interpretation method under different target interpretation interval conditions are generally different.

[0141] For example, the input parameters of the apparent resistivity increase rate method may be: porosity, resistivity. The sensitive parameter crossplot method is a method for identifying sensitive parameters based on the interpretation chart, and the type of interpretation chart required is the acoustic travel time - resistivity crossplot, and the input parameters may be: resistivity, acoustic travel time. The double Rwa method is a method for identifying fluid properties based on the formation water resistivity, and the input parameters may be: resistivity, porosity, spontaneous potential.

[0142] Regarding step S302, the correlation coefficient calculation formula may be the Pearson correlation coefficient calculation formula. For example, the Pearson correlation coefficient calculation formula is:

[0143]

[0144] where r is the Pearson correlation coefficient; xi, yi are the logging curve values corresponding to the i-th target interpretation interval; are the average values of the logging curves respectively. The value range of the correlation coefficient r is -1 ≤ r ≤ 1.

[0145] For step S303, assume that an interpretation method includes three input parameters. By calculating the correlation coefficients between every two of them, three correlation coefficients can be determined. The value obtained by adding the three correlation coefficients and taking the average is determined as the correlation coefficient of this interpretation method.

[0146] Among them, when an interpretation method includes only one input parameter, the correlation coefficient of this interpretation method is determined as 1. When an interpretation method includes two input parameters, the correlation coefficient between the two parameters is determined as the correlation coefficient of this interpretation method.

[0147] In this way, by integrating the correlation coefficient into the weighted voting method, the logging interpretation conclusion selected by the weighted voting method based on correlation analysis is more persuasive, improving the accuracy of the interpretation conclusion and the coincidence rate of the interpretation.

[0148] S105. Determine the interpretation conclusion with the maximum accuracy as the final interpretation conclusion of the target interpreted interval.

[0149] Here, after determining the final interpretation conclusion of each target interpreted interval, it can also be presented to the user in a visual way. For example, it can be presented on the Figure 2 interface shown.

[0150] Among them, the final interpretation conclusion is also the optimal interpretation conclusion.

[0151] In this way, in this solution, by calculating the index weights of each interpretation method based on expert scoring, compared with directly assigning weights in the past, it avoids the bias of the weight coefficient caused by subjective assignment, improving the rationality and reliability of the weight coefficient. Based on the weighted voting method, adding the correlation analysis of the interpretation method to determine the correlation coefficients of different interpretation methods makes the selected interpretation conclusion more reliable. In addition, the results of this solution can be integrated into a software system, and all calculations and processing are implemented by a computer. Compared with the previous manual comparison and analysis, it saves labor and improves work efficiency.

[0152] Please refer to Figure 3 、 Figure 4 , Figure 3 which is one of the structural schematic diagrams of a device for determining a logging interpretation conclusion provided by an embodiment of the present application, Figure 4 and which is the second structural schematic diagram of a device for determining a logging interpretation conclusion provided by an embodiment of the present application. As shown in Figure 3 , the determining device 300 includes:

[0153] An acquisition module 310, configured to acquire the full logging curve data of a target well, and determine at least one interpretation method corresponding to the target well according to the geological information of the target well; the target well includes at least one candidate interpreted interval;

[0154] A prediction module 320, configured to process the full well logging curve data respectively using all the interpretation methods to predict the reservoir type of each candidate interpreted interval, and obtain the interpretation conclusion of each candidate interpreted interval determined by each interpretation method;

[0155] A screening module 330, configured to screen out at least one target interpreted interval from all candidate interpreted intervals according to all the interpretation conclusions of each candidate interpreted interval;

[0156] A first determination module 340, configured to, for each target interpreted interval, determine the accuracy of each interpretation conclusion of the target interpreted interval according to the weight coefficient of each interpretation method and the correlation coefficient of each interpretation method corresponding to the target interpreted interval;

[0157] A second determination module 350, configured to determine the interpretation conclusion with the maximum accuracy as the final interpretation conclusion of the target interpreted interval.

[0158] Optionally, when the prediction module 320 is configured to process the full well logging curve data respectively using all the interpretation methods to predict the reservoir type of each candidate interpreted interval and obtain the interpretation conclusion of each candidate interpreted interval determined by each interpretation method, the prediction module 320 is configured to:

[0159] For each candidate interpreted interval, extract the interval well logging curve data corresponding to the candidate interpreted interval from the full well logging curve data;

[0160] Use the interpretation methods to process the interval well logging curve data respectively, and determine the interpretation conclusion of the candidate interpreted interval determined by each interpretation method.

[0161] Optionally, the initial accuracy of each interpretation method is the same.

[0162] Optionally, when the screening module 330 is configured to screen out at least one target interpreted interval from all candidate interpreted intervals according to all the interpretation conclusions of each candidate interpreted interval, the screening module 330 is configured to:

[0163] For each candidate interpreted interval, determine whether the number of the same interpretation conclusions in the candidate interpreted interval exceeds a preset threshold; wherein, the preset threshold is determined according to the total number of the interpretation methods corresponding to the target well and the rule requirements of the voting method;

[0164] If it exceeds, determine the candidate interpreted interval as the target interpreted interval.

[0165] Optionally, when the first determination module 340 is used to determine the accuracy of each interpretation conclusion of the target interpretation segment according to the weight coefficient of each interpretation method and the correlation coefficient of each interpretation method determined under the conditions of the target interpretation segment, the first determination module 340 is used for:

[0166] For each interpretation conclusion of each target interpretation segment, multiply the initial accuracy, weight coefficient of the interpretation method corresponding to this interpretation conclusion, and the correlation coefficient of this interpretation method corresponding to the conditions of the target interpretation segment to determine the accuracy of this interpretation conclusion;

[0167] Add up the accuracies of the interpretation conclusions of the same type under the same target interpretation segment to determine the accuracy of each interpretation conclusion in each target interpretation segment.

[0168] Optionally, the determination device further includes a third determination module 360, and the third determination module 360 is used for:

[0169] Obtain the importance scores of all interpretation methods corresponding to the target well determined by experts;

[0170] According to all the importance scores, construct an importance score matrix in a preset sorting manner;

[0171] According to the importance score matrix, perform consistency test processing to determine whether the consistency requirement is met;

[0172] If it is satisfied, use the sum and integral or root method to process the importance score matrix to determine the weight coefficient of each interpretation method.

[0173] Optionally, the determination device further includes a fourth determination module 370, and the fourth determination module 370 is used for:

[0174] Perform top-bottom depth alignment processing on the well log curve data of the segment of the target interpretation segment, and determine the input data of each input parameter in each interpretation method corresponding to the conditions of the target interpretation segment according to the processed well log curve data of the segment;

[0175] For each interpretation method, determine the correlation coefficient between two input parameters in this interpretation method through the correlation coefficient calculation formula and the data of all input parameter items in this interpretation method;

[0176] Add up and average the correlation coefficients between two input parameters determined in the same interpretation method to determine the correlation coefficient of each interpretation method corresponding to the conditions of the target interpretation segment.

[0177] Please refer to Figure 5 ,Figure 5 The following is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 5 shown in the figure, the electronic device 500 includes a processor 510, a memory 520, and a bus 530.

[0178] The memory 520 stores machine-readable instructions executable by the processor 510. When the electronic device 500 runs, the processor 510 communicates with the memory 520 through the bus 530. When the machine-readable instructions are executed by the processor 510, the steps in the method embodiments as described above Figure 1 and Figure 2 shown can be executed. For the specific implementation manners, reference can be made to the method embodiments, which will not be elaborated herein.

[0179] An embodiment of the present application further provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is run by a processor, the steps in the method embodiments as described above Figure 1 and Figure 2 shown can be executed. For the specific implementation manners, reference can be made to the method embodiments, which will not be elaborated herein.

[0180] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be elaborated herein.

[0181] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings, direct couplings, or communication connections shown or discussed with each other can be through some communication interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0182] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0183] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0184] When the above-mentioned functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0185] Finally, it should be noted that the above-mentioned embodiments are only specific implementation manners of the present application, used to illustrate the technical solutions of the present application, rather than limiting them. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed by the present application can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for determining logging interpretation conclusions, characterized in that, the determination method includes: obtaining the full logging curve data of a target well, and determining at least one interpretation method corresponding to the target well according to the geological information of the target well; the target well includes at least one candidate interpretation interval; using all the interpretation methods to process the full logging curve data respectively to predict the reservoir type of each candidate interpretation interval, and obtaining the interpretation conclusions of each candidate interpretation interval determined by each interpretation method; screening out at least one target interpretation interval from all the candidate interpretation intervals according to all the interpretation conclusions of each candidate interpretation interval; for each target interpretation interval, determining the accuracy of each interpretation conclusion of the target interpretation interval according to the weight coefficient of each interpretation method and the correlation coefficient of each interpretation method corresponding to the conditions of the target interpretation interval; determining the interpretation conclusion with the maximum accuracy as the final interpretation conclusion of the target interpretation interval.

2. The determination method according to claim 1, characterized in that, the using all the interpretation methods to process the full logging curve data respectively to predict the reservoir type of each candidate interpretation interval, and obtaining the interpretation conclusions of each candidate interpretation interval determined by each interpretation method includes: for each candidate interpretation interval, extracting the interval logging curve data corresponding to the candidate interpretation interval from the full logging curve data; using the interpretation methods to process the interval logging curve data respectively, and determining the interpretation conclusions of the candidate interpretation interval determined by each interpretation method.

3. The determination method according to claim 1, characterized in that, the initial accuracy of each interpretation method is the same.

4. The determination method according to claim 1, characterized in that, the screening out at least one target interpretation interval from all the candidate interpretation intervals according to all the interpretation conclusions of each candidate interpretation interval includes: for each candidate interpretation interval, determining whether the number of the same interpretation conclusions in the candidate interpretation interval exceeds a preset threshold; wherein, the preset threshold is determined according to the total number of the interpretation methods corresponding to the target well and the rule requirements of the voting method; if it exceeds, determining the candidate interpretation interval as the target interpretation interval.

5. The determination method according to claim 3, characterized in that, the for each target interpretation interval, determining the accuracy of each interpretation conclusion of the target interpretation interval according to the weight coefficient of each interpretation method and the correlation coefficient of each interpretation method determined under the conditions of the target interpretation interval includes: for each interpretation conclusion of each target interpretation interval, multiplying the initial accuracy, the weight coefficient of the interpretation method corresponding to the interpretation conclusion, and the correlation coefficient of the interpretation method corresponding to the conditions of the target interpretation interval to determine the accuracy of the interpretation conclusion; adding the accuracies of the same type of interpretation conclusions under the same target interpretation interval to determine the accuracy of each interpretation conclusion in each target interpretation interval.

6. The determination method according to claim 1, characterized in that, Determine the weight coefficients of each interpretation method through the following steps: Obtain the importance scores of all the interpretation methods corresponding to the target well determined by experts with respect to each other; Construct an importance score matrix according to all the importance scores in a preset sorting manner; Perform a consistency test process according to the importance score matrix to determine whether the consistency requirement is met; If it is met, process the importance score matrix using the sum and integral or square root method to determine the weight coefficients of each interpretation method.

7. According to the determination method described in claim 2, characterized in that, Determine the correlation coefficients of each interpretation method corresponding to the target interpretation interval through the following steps: Perform top-bottom depth alignment processing on the interval logging curve data of the target interpretation interval, and determine the input data of each input parameter in each interpretation method corresponding to the target interpretation interval according to the processed interval logging curve data; For each interpretation method, determine the correlation coefficients between pairwise input parameters in this interpretation method through the correlation coefficient calculation formula and the data of all input parameter items in this interpretation method; Add and average the correlation coefficients between pairwise input parameters determined in the same interpretation method to determine the correlation coefficients of each interpretation method corresponding to the target interpretation interval.

8. A device for determining logging interpretation conclusions, characterized in that, the determination device includes: An acquisition module, configured to acquire the full logging curve data of the target well, and determine at least one interpretation method corresponding to the target well according to the geological information of the target well; the target well includes at least one candidate interpretation interval; A prediction module, configured to use all the interpretation methods to process the full logging curve data respectively to predict the reservoir type of each candidate interpretation interval, and obtain the interpretation conclusions of each candidate interpretation interval determined by each interpretation method; A screening module, configured to screen at least one target interpretation interval from all the candidate interpretation intervals according to all the interpretation conclusions of each candidate interpretation interval; A first determination module, configured to, for each target interpretation interval, determine the accuracy of each interpretation conclusion of this target interpretation interval according to the weight coefficient of each interpretation method and the correlation coefficient of each interpretation method corresponding to this target interpretation interval; A second determination module, configured to determine the interpretation conclusion with the maximum accuracy as the final interpretation conclusion of this target interpretation interval.

9. An electronic device, characterized in that, it includes: A processor, a memory and a bus, the memory stores machine-readable instructions executable by the processor, when the electronic device runs, communication is carried out between the processor and the memory through the bus, and when the machine-readable instructions are run by the processor, the steps of the determination method according to any one of claims 1 to 7 are executed.

10. A computer-readable storage medium, characterized in that, a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the steps of the determination method according to any one of claims 1 to 7 are executed.

Images