Buried hill reservoir permeability evaluation method and system based on Stoneley wave time difference intelligent prediction, processing equipment and storage medium

Abstract

The invention relates to a buried hill reservoir permeability evaluation method and system based on Stoneley wave time difference intelligent prediction, processing equipment and a storage medium. The method comprises the following steps: preprocessing core physical property, conventional logging and electric imaging logging data in a target area; array acoustic logging data are processed, and longitudinal wave, transverse wave and stoneley wave time difference of each well in the target area is extracted; establishing an intelligent stoneley wave time difference prediction model, and predicting the stoneley wave time difference of the interval with poor stoneley wave data quality of each well; determining the effective fracture development position and the fracture width of each well; carrying out a crack plate model experiment, and calculating the total permeability of the stratum at the effective crack development position according to the effective crack development position and the crack width of each well; inverting the total permeability of the buried hill reservoir; on the basis of the plunger sample core permeability and the total stratum permeability calculated at the effective fracture development position, permeability inversion results of the effective fracture non-development position and the effective fracture development position of each well are calibrated, and the method can be widely applied to the field of oil and gas exploration and development.

Description

Technical Field

[0001] The present invention relates to the field of oil and gas exploration and development, and particularly to a method, system, processing device and storage medium for evaluating the permeability of buried hill reservoirs based on intelligent prediction of Stoneley wave travel time difference. Background Art

[0002] Buried hills have become an important area for oil and gas exploration and development in the offshore of China. The buried hill reservoir is a typical dual-porosity reservoir with obvious fractures developed, which is the key channel for formation oil and gas seepage and directly affects the productivity of oil and gas layers. Therefore, how to accurately evaluate the permeability of buried hill reservoirs is a key problem to be solved urgently for the efficient exploration and development of buried hill reservoirs. Generally, the porosity-permeability relationship is usually established based on core physical property experiments to evaluate reservoir permeability. However, for strongly heterogeneous buried hill reservoirs, due to the different degrees of fracture development in the reservoir, within the same porosity range, the core permeabilities vary significantly, even by several orders of magnitude, and the evaluation accuracy of the conventional porosity-permeability relationship is poor.

[0003] Nuclear magnetic resonance logging quantitatively characterizes the pore structure of reservoirs based on the T2 spectrum distribution characteristics. By using the improved Timur-Coates formula and SDR model, high-precision evaluation of permeability has been achieved in pore-type reservoirs. However, for dual-porosity buried hill reservoirs, the existing nuclear magnetic resonance permeability evaluation methods are difficult to accurately reflect the seepage contribution of fractures to the reservoir, and the permeability evaluation accuracy is poor.

[0004] Researchers studied the relationship between dynamic permeability and Stoneley wave based on the simplified Biot-Rosenbaum theory, inversed reservoir permeability by using the frequency shift and travel time difference of Stoneley wave, and achieved good application results in the high-precision evaluation of dual-porosity buried hill reservoir permeability through full-diameter core experiment permeability calibration. However, this method has high requirements for the quality of Stoneley wave data. In the case of irregular borehole enlargement, the permeability inversion result is poor; at the same time, in buried hill reservoirs with obvious fractures developed, it is difficult to obtain full-diameter cores, and how to accurately calibrate the permeability inversion result still needs to be tackled, and the accurate evaluation of buried hill reservoir permeability cannot be achieved. Summary of the Invention

[0005] Aiming at the above problems, the purpose of the present invention is to provide a method, system, processing device and storage medium for evaluating the permeability of buried hill reservoirs based on intelligent prediction of Stoneley wave travel time difference applicable to buried hill reservoirs, so as to improve the logging permeability evaluation accuracy of dual-porosity buried hill reservoirs.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: In the first aspect, a method for evaluating the permeability of buried hill reservoirs based on intelligent prediction of Stoneley wave travel time difference is provided, including: Preprocess the core physical properties (surface core porosity, permeability), conventional logging, and electrical image logging data in the target area to obtain the preprocessed core physical properties, conventional logging data, and dynamic and static images of electrical image logging; Process the array acoustic logging data and extract the longitudinal, transverse, and Stoneley wave slownesses of each well in the target area; Based on the longitudinal, transverse, and Stoneley wave slownesses extracted from the intervals with good Stoneley wave data quality in each well, use an intelligent algorithm to establish an intelligent prediction model for Stoneley wave slowness and predict the Stoneley wave slowness of the intervals with poor Stoneley wave data quality in each well; Based on the dynamic and static images of electrical image logging, combined with conventional logging and acoustic image logging for comprehensive judgment, determine the effective fracture development positions and fracture widths of each well in the target area; Conduct a fracture flat plate model experiment, and calculate the total formation permeability at the effective fracture development locations according to the effective fracture development positions and fracture widths of each well; Using the intelligently predicted Stoneley wave slowness, invert the total permeability of the buried hill reservoir based on the Stoneley wave frequency shift and travel time difference; Use the plug sample core permeability to calibrate the inversion results of Stoneley wave permeability at the locations where effective fractures do not develop; According to the calculated total formation permeability at the effective fracture development locations, calibrate the inversion results of Stoneley wave permeability at the effective fracture development locations.

[0007] Further, the preprocessing of the core physical properties (surface core porosity, permeability), conventional logging, and electrical image logging data in the target area to obtain the preprocessed core physical properties, conventional logging data, and dynamic and static images of electrical image logging includes: Based on the overburden experiment, establish a surface - formation porosity and permeability correction chart, and correct the surface core porosity and permeability data to formation conditions; Take the well with relatively complete logging and core experiment data in the target area as the marker well, select the intervals that are stably developed in the target area as the marker layers, and based on the marker well and marker layers, conduct depth correction and standardization processing on the conventional logging data of all wells in the target area to obtain the preprocessed conventional logging data; Process the electrical image logging data, scale the resistivity in the electrical image logging data into different color - graded images to obtain the dynamic and static images of electrical image logging of each well in the target area.

[0008] Further, the processing of the array acoustic logging data and the extraction of the longitudinal, transverse, and Stoneley wave slownesses of each well in the target area adopt the time - slowness correlation method.

[0009] Furthermore, for the extracted P-wave, S-wave, and Stoneley wave time differences in the intervals with good Stoneley wave data quality in each well, an intelligent algorithm is used to establish an intelligent prediction model for Stoneley wave time difference to predict the Stoneley wave time difference in the intervals with poor Stoneley wave data quality in each well, including: Preferably, the P-wave and S-wave time differences are used as sensitive curves for predicting the Stoneley wave time difference; The Stoneley wave waveforms in each well within the target area and the intervals where the arrival time of the Stoneley wave shows no abnormality are used as the training set; Using the MRGC algorithm, with the P-wave and S-wave time differences as the input curves and the Stoneley wave time difference as the output curve, based on the established training set, an intelligent prediction model for Stoneley wave time difference is established; For the intervals with poor Stoneley wave data quality in each well within the target area, based on the established intelligent prediction model for Stoneley wave time difference and the extracted P-wave and S-wave time differences, the Stoneley wave time difference is predicted.

[0010] Furthermore, the step of using the MRGC algorithm, with the P-wave and S-wave time differences as the input curves and the Stoneley wave time difference as the output curve, and establishing an intelligent prediction model for Stoneley wave time difference based on the established training set includes: Based on the vector space model, the selected logging curves and the predicted output curve are transformed into a vector space composed of several features; The features of each sample data in the training set are filled into the vector space; Through the geometric relationship between two feature vectors in the vector space, the Euclidean distance between the feature vector for predicting the Stoneley wave time difference and all feature vectors in the dataset is determined; Based on the Euclidean distance between the feature vector for predicting the Stoneley wave time difference and all feature vectors in the dataset, the nearest data items are found, and the Gaussian function is used to convert the Euclidean distance into weights, and the weighted arithmetic mean of the nearest neighbor data items is calculated to obtain the final predicted result of the Stoneley wave time difference.

[0011] Furthermore, a fractured flat plate model experiment is carried out. According to the effective fracture development positions and fracture widths of each well, the total formation permeability at the locations where effective fractures develop is calculated, including: A fractured flat plate model experiment is carried out. According to the fracture development positions and fracture widths of each well, the fracture permeability at the locations where effective fractures develop is calculated; Meanwhile, based on the relationship between matrix overburden porosity and permeability, the matrix permeability of each well within the target area is calculated; The fracture permeability and matrix permeability at the locations where effective fractures develop in each well within the target area are added together to obtain the total formation permeability at the locations where effective fractures develop in each well within the target area.

[0012] Further, the Stoneley wave time difference using intelligent prediction is used to invert the total permeability of the buried hill reservoir based on the Stoneley wave frequency shift and travel time difference, including: Forward model the Stoneley wave time difference of the tight formation. By adjusting parameters such as the tool modulus and mud sound velocity, make the theoretically calculated Stoneley wave time difference coincide with the intelligently predicted Stoneley wave time difference in the tight formation to obtain the calibration results of parameters such as the tool modulus and mud sound velocity; According to the parameters such as the tool modulus and mud sound velocity calibrated from the tight formation, calculate the Stoneley wave time difference of the interval to be analyzed. If there is a difference between the calculated Stoneley wave time difference and the intelligently predicted Stoneley wave time difference, it is considered to be a permeable layer, and based on the Stoneley wave frequency shift and travel time difference, invert the total permeability of the buried hill reservoir.

[0013] In a second aspect, a buried hill reservoir permeability evaluation system based on intelligent prediction of Stoneley wave time difference is provided, including: A first processing module, used to preprocess the core physical properties (surface core porosity, permeability), conventional logging, and electrical imaging logging data in the target area to obtain the preprocessed core physical properties, conventional logging data, and dynamic and static images of electrical imaging logging; A second processing module, used to process the array acoustic logging data and extract the longitudinal, transverse, and Stoneley wave time differences of each well in the target area; The Stoneley wave time difference prediction module, used to establish an intelligent prediction model of the Stoneley wave time difference by using an intelligent algorithm based on the longitudinal, transverse, and Stoneley wave time differences extracted from the intervals with good Stoneley wave data quality of each well, and predict the Stoneley wave time difference of the intervals with poor Stoneley wave data quality of each well; A comprehensive judgment module, used to make a comprehensive judgment based on the dynamic and static images of electrical imaging logging, combined with conventional logging and acoustic imaging logging, to determine the effective fracture development positions and fracture widths of each well in the target area; The formation total permeability determination module, used to carry out fracture flat plate model experiments, and calculate the formation total permeability at the effective fracture development positions according to the effective fracture development positions and fracture widths of each well; An inversion module, used to invert the total permeability of the buried hill reservoir by using the intelligently predicted Stoneley wave time difference based on the Stoneley wave frequency shift and travel time difference; A first calibration module, used to calibrate the inversion results of the Stoneley wave permeability at the positions where effective fractures do not develop by using the core permeability of the plug sample; A second calibration module, used to calibrate the inversion results of the Stoneley wave permeability at the positions where effective fractures develop according to the calculated formation total permeability at the effective fracture development positions.

[0014] In a third aspect, a processing device is provided, including computer program instructions, where when the computer program instructions are executed by the processing device, they are used to implement the steps corresponding to the above-mentioned method for evaluating the permeability of buried hill reservoirs based on intelligent prediction of Stoneley wave travel time.

[0015] In a fourth aspect, a computer-readable storage medium is provided, on which computer program instructions are stored, where when the computer program instructions are executed by a processor, they are used to implement the steps corresponding to the above-mentioned method for evaluating the permeability of buried hill reservoirs based on intelligent prediction of Stoneley wave travel time.

[0016] Due to the above technical solutions adopted by the present invention, it has the following advantages: 1. The present invention can reduce the influence of poor Stoneley wave data quality on the permeability inversion result, and the intelligent predicted Stoneley wave travel time can effectively improve the evaluation accuracy of the permeability of buried hill reservoirs in cases such as irregular borehole enlargement.

[0017] 2. The present invention comprehensively identifies the positions of effectively developed fractures based on the dynamic and static images of electrical imaging logging, conventional logging, and acoustic imaging logging. On this basis, combined with the fracture flat plate model, it quantitatively evaluates the total permeability of the formation at the location of effectively developed fractures, providing an important basis for the fine calibration of the permeability inversion result of buried hill reservoirs under the condition of few cores, and is of great significance for the fine interpretation of logging in buried hill reservoirs.

[0018] In summary, the present invention can be widely applied in the field of oil and gas exploration and development. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Throughout the drawings, the same reference numerals are used to represent the same components. In the drawings: Figure 1 is a schematic flowchart of the method provided by an embodiment of the present invention; Figure 2 is a schematic diagram of the Stoneley wave travel time extracted by the time-slowness correlation method (STC method) for Well B in Oilfield A provided by an embodiment of the present invention; Figure 3 is a schematic diagram of the Stoneley wave travel time extracted by the time-slowness correlation method (STC method) for Well X in Oilfield A provided by an embodiment of the present invention; Figure 4 is a schematic diagram of the cross distribution of various types of data in the intelligent prediction model of Stoneley wave travel time in Oilfield A provided by an embodiment of the present invention; Figure 5It is a schematic diagram of the histogram distribution of the weight sizes of various types of data in the Stoneley wave time difference intelligent prediction model of Oilfield A provided by an embodiment of the present invention; Figure 6 It is a schematic diagram for comparing the intelligent prediction results of the Stoneley wave time difference of Well B in Oilfield A provided by an embodiment of the present invention; Figure 7 It is a schematic diagram of the relationship between fracture permeability and fracture width based on a fracture flat plate model provided by an embodiment of the present invention; Figure 8 It is a schematic diagram of the relationship between matrix overburden pore permeability in Oilfield A provided by an embodiment of the present invention; Figure 9 It is a schematic diagram of the calculation results of the total formation permeability at the fracture development location based on resistivity imaging logging of Well B in Oilfield A provided by an embodiment of the present invention; Figure 10(a) is a schematic diagram of the full-wave train waveform of Well B in Oilfield A, and Figure 10(b) is a schematic diagram of the full-wave train frequency spectrum distribution of Well B in Oilfield A; Figure 11 It is a schematic diagram of the evaluation results of permeability based on the intelligent prediction of Stoneley wave time difference of Well B in Oilfield A provided by an embodiment of the present invention. Detailed implementation manners

[0020] Hereinafter, the exemplary embodiments of the present invention will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present invention can be more thoroughly understood and the scope of the present invention can be fully conveyed to those skilled in the art.

[0021] It should be understood that the terms used herein are only for the purpose of describing specific exemplary embodiments and are not intended to be limiting. Unless otherwise clearly specified in the context, the singular forms "a", "an" and "the" as used herein may also include the plural forms. The terms "comprising", "including", "containing" and "having" are inclusive and thus specify the presence of the stated features, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not to be construed as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is explicitly stated. It should also be understood that additional or alternative steps can be used.

[0022] At present, researchers study the relationship between dynamic permeability and Stoneley wave based on the simplified Biot-Rosenbaum theory, use the frequency shift and travel time difference of Stoneley wave to invert reservoir permeability, and calibrate the permeability through full-diameter core experiment. Good application results have been achieved in the high-precision evaluation of permeability in dual-medium buried hill reservoirs. However, this method has high requirements for the quality of Stoneley wave data. In the case of irregular borehole enlargement, the permeability inversion result is poor. At the same time, in the buried hill reservoir with obvious fractures, it is difficult to obtain full-diameter core samples. How to accurately calibrate the permeability inversion result remains to be tackled, and the accurate evaluation of permeability in buried hill reservoirs cannot be achieved. The embodiment of the present invention provides a method for evaluating the permeability of a buried hill reservoir based on the intelligent prediction of Stoneley wave time difference, including: preprocessing the core physical properties (ground core porosity, permeability), conventional logging, and electrical imaging logging data in the target area to obtain the preprocessed core physical properties, conventional logging data, and dynamic and static images of electrical imaging logging; processing the array acoustic logging data to extract the longitudinal, transverse, and Stoneley wave time differences of each well in the target area; based on the longitudinal, transverse, and Stoneley wave time differences extracted from the well sections with good Stoneley wave data quality in each well, using an intelligent algorithm to establish an intelligent prediction model of Stoneley wave time difference to predict the Stoneley wave time difference of the well sections with poor Stoneley wave data quality in each well; based on the dynamic and static images of electrical imaging logging, combined with conventional logging and acoustic imaging logging for comprehensive judgment to determine the effective fracture development position and fracture width of each well in the target area; conducting a fracture flat plate model experiment, and calculating the total formation permeability at the effective fracture development location according to the effective fracture development position and fracture width of each well; using the intelligently predicted Stoneley wave time difference, based on the frequency shift and travel time difference of Stoneley wave, to invert the total permeability of the buried hill reservoir; using the plug sample core permeability to calibrate the Stoneley wave permeability inversion result at the location where effective fractures do not develop; and calibrating the Stoneley wave permeability inversion result at the location where effective fractures develop according to the calculated total formation permeability at the effective fracture development location. The present invention can reduce the influence of poor Stoneley wave data quality on the permeability inversion result, and the intelligently predicted Stoneley wave time difference can effectively improve the evaluation accuracy of the permeability of buried hill reservoirs in the case of irregular borehole enlargement and other situations.

[0023] Example 1 As Figure 1 shown, this embodiment provides a method for evaluating the permeability of a buried hill reservoir based on the intelligent prediction of Stoneley wave time difference, including the following steps: As Figure 1 shown, this embodiment provides a method for evaluating the permeability of a buried hill reservoir, including the following steps: 1) Preprocess the core physical properties (surface core porosity and permeability), conventional logging (de-uranium gamma logging, caliper logging, resistivity logging, acoustic logging, density logging, neutron logging), and electrical imaging logging data in the target area, correct the environmental impacts, and obtain the preprocessed core physical properties, conventional logging data, and dynamic and static images of electrical imaging logging. Specifically: 1.1) Based on the overburden experiment, establish the correction charts for surface - formation porosity and permeability, and correct the surface core porosity and permeability data to formation conditions.

[0024] 1.2) Select the well with relatively complete logging and core experiment data in the target area as the marker well, select the stable - developed intervals in the target area as the marker beds, and based on the marker well and marker beds, perform depth correction and standardization processing on the conventional logging data of all wells in the target area to eliminate environmental impacts and obtain the preprocessed conventional logging data.

[0025] 1.3) Perform processing such as bad electrode removal, voltage correction, acceleration correction, and equalization processing on the electrical imaging logging data to improve the accuracy of the electrical imaging logging data, and through image processing, scale the resistivity in the electrical imaging logging data into different color - graded images to obtain the preprocessed electrical imaging logging data, that is, the dynamic and static images of electrical imaging logging for each well in the target area.

[0026] 2) Process the array acoustic logging data and extract the longitudinal, transverse, and Stoneley wave slownesses of all wells in the target area.

[0027] Specifically, use the time - slowness correlation (STC) method to process the array acoustic logging data and extract the longitudinal, transverse, and Stoneley wave slownesses corresponding to different depth points.

[0028] 3) Based on the longitudinal, transverse, and Stoneley wave slownesses extracted from the intervals with good Stoneley wave data quality in each well, use the MRGC algorithm (multi - resolution clustering algorithm based on graphic groups) to establish an intelligent prediction model for Stoneley wave slowness, and predict the Stoneley wave slownesses of the intervals with poor Stoneley wave data quality in each well. Specifically: 3.1) Optimally select the longitudinal and transverse wave slownesses as the sensitive curves for Stoneley wave slowness prediction.

[0029] 3.2) Use the intervals with good Stoneley wave data quality (normal Stoneley wave waveform and Stoneley wave arrival time) in each well in the target area as the training set.

[0030] 3.3) Use the MRGC algorithm, with the longitudinal and transverse wave slownesses as the input curves and the Stoneley wave slowness as the output curve, and based on the established training set, establish an intelligent prediction model for Stoneley wave slowness: 3.3.1) Based on the vector space model, transform the optimally selected logging curves and the predicted output curve into a vector space composed of several features 。

[0031] 3.3.2) Fill the features of each sample data in the training set into the vector space, then each sample data can be represented as , where represents the sample data on the feature value, represents the dimension of the feature vector.

[0032] 3.3.3) Determine the similarity between the feature vector for predicting the Stoneley wave travel time and all feature vectors in the dataset through the geometric relationship between two feature vectors in the vector space, that is, the Euclidean distance.

[0033] Specifically, assume that the two feature vectors are , , respectively, then the similarity between them can be represented by the Euclidean distance: (1) where represents the -th eigenvalue of the feature vector ; represents the -th eigenvalue of the feature vector .

[0034] 3.3.4) Based on the Euclidean distance between the feature vector for predicting the Stoneley wave travel time and all feature vectors in the dataset, find the nearest data items, and use the Gaussian function to convert the Euclidean distance into weights, and calculate the weighted arithmetic mean of the nearest neighbor data items, and the final predicted result of the Stoneley wave travel time is: (2) where is the final predicted result of the Stoneley wave travel time; is the -th nearest neighbor data item; is the corresponding weight value.

[0035] 3.4) For the intervals in each well in the target area where the quality of the Stoneley wave data is poor (the Stoneley wave waveform is abnormal, the arrival time of the Stoneley wave is delayed, and there are obvious differences from the upper and lower intervals), based on the established intelligent prediction model of the Stoneley wave travel time and the extracted longitudinal and transverse wave travel times, predict the Stoneley wave travel time.

[0036] 4) Based on the dynamic and static images of the electrical imaging logging, combined with the conventional logging and acoustic imaging logging for comprehensive judgment, determine the effective fracture development positions and fracture widths of each well in the target area.

[0037] Specifically, the method for determining the effective fracture development positions in each well within the target area is as follows: Based on the dynamic and static images of the electrical imaging logging in each well within the target area, determine whether there is a possibility of fracture development. It is considered that there is a possibility of fracture development in the sinusoidal display section of the dynamic and static images of the electrical imaging logging. On this basis, combined with conventional logging and acoustic imaging logging, it is considered that there is a display in the acoustic imaging logging travel time image, and the layers with a small uranium removal gamma value, an increased neutron logging value, a decreased density logging value, and an increased acoustic logging value develop effective fractures and need to be picked up.

[0038] 5) Conduct fracture flat plate model experiments. According to the effective fracture development positions and fracture widths of each well, calculate the total formation permeability at the locations where effective fractures develop, specifically as follows: 5.1) Conduct fracture flat plate model experiments. According to the effective fracture development positions and fracture widths of each well, calculate the fracture permeability at the locations where effective fractures develop in each well within the target area.

[0039] Specifically, the fracture flat plate model is a flat plate core model containing a horizontal single fracture. Experimentally measure the fracture permeability at different fracture widths. Combining with the experimental results of the French Petroleum Company, establish the relationship between the fracture permeability and the fracture width: (3) Among them, represents the fracture permeability, with the unit of mD; represents the fracture width, with the unit of μm.

[0040] 5.2) At the same time, based on the relationship between matrix overburden porosity and permeability, calculate the matrix permeability of each well within the target area.

[0041] 5.3) Add the fracture permeability and the matrix permeability at the locations where effective fractures develop in each well within the target area to obtain the total formation permeability at the locations where effective fractures develop in each well within the target area.

[0042] 6) Use the intelligent predicted Stoneley wave slowness to invert the total permeability of the buried hill reservoir based on the Stoneley wave frequency shift and travel time difference, specifically as follows: 6.1) Forward simulate the Stoneley wave slowness of the tight formation. By adjusting parameters such as the tool modulus and mud sound velocity, make the theoretically calculated Stoneley wave slowness coincide with the intelligent predicted Stoneley wave slowness in the tight formation to obtain the calibration results of parameters such as the tool modulus and mud sound velocity.

[0043] 6.2) According to the parameters such as the tool modulus and mud sound velocity calibrated from the tight formation, calculate the Stoneley wave slowness of the layer to be analyzed. If there is a difference between the calculated Stoneley wave slowness and the intelligent predicted Stoneley wave slowness, it is considered to be a permeable layer, and based on the Stoneley wave frequency shift and travel time difference, invert the total permeability of the buried hill reservoir.

[0044] Specifically, the key to the Stoneley wave permeability inversion of buried hill reservoirs is to determine the frequency band distribution range of the permeability inversion model based on the main frequency position and spectral width distribution range of the Stoneley wave spectrum.

[0045] 7) Use the plunger core permeability to calibrate the Stoneley wave permeability inversion results at locations where effective fractures are not developed.

[0046] 8) Calibrate the Stoneley wave permeability inversion results at locations where effective fractures are developed according to the calculated total formation permeability at these locations.

[0047] The following details the method for evaluating the permeability of buried hill reservoirs based on intelligent prediction of Stoneley wave travel time according to the present invention through specific embodiments: 1) Preprocess the core physical properties (surface core porosity and permeability), conventional logging, and electrical image logging data in the target area to obtain the preprocessed core physical properties, conventional logging data, and dynamic and static images of electrical image logging.

[0048] 2) Use the time-slowness correlation method to process the array acoustic logging data of all wells in the target area to obtain the longitudinal, transverse, and Stoneley wave travel times of all wells in the target area.

[0049] 3) Based on the longitudinal, transverse, and Stoneley wave travel times extracted from the intervals with good Stoneley wave data quality in each well, use the MRGC algorithm to establish an intelligent prediction model for Stoneley wave travel time to predict the Stoneley wave travel time of the intervals with poor Stoneley wave data quality in each well: Taking Well B in Oilfield A in the target area as an example, compared with the interval below X334.00m, the interval from X140.5 to X334.00m is affected by irregular borehole enlargement, with poor Stoneley wave data quality and a later arrival time. The Stoneley wave travel time extracted by the time-slowness correlation method (STC method) shows an obviously abnormally high value, as Figure 2 shown, and it is difficult to directly apply it to the Stoneley wave permeability inversion.

[0050] Taking Well X in Oilfield A in the target area as an example, the Stoneley wave data quality of this well is good and the arrival time is not abnormal. There is a good correlation between the Stoneley wave travel time extracted by the time-slowness correlation method (STC method) and the longitudinal and transverse wave travel times, as Figure 3 shown. Therefore, Well X is selected as the training set. Using the MRGC algorithm, with the longitudinal and transverse wave travel times of Well X as the input curves and the Stoneley wave travel time as the output curve, considering the prediction accuracy and resolution, the data of Well X in the training set are clustered into 20 categories to establish an intelligent prediction model for Stoneley wave travel time. The cross-distribution of various data in the model is as Figure 4 described, and the weight size and histogram distribution are as Figure 5 shown.

[0051] Taking Well B in Oilfield A of the target area as an example, based on the established intelligent prediction model of Stoneley wave time difference, features are extracted from the logging data to be predicted in Well B and transformed into the vector space. The data of Well B are projected onto the intelligent prediction model of Stoneley wave time difference, and the nearest neighbor data items are obtained. Based on the weights of the nearest neighbor data items and the distances of the remaining data to be predicted, the mean value is solved to predict the Stoneley wave time difference. The prediction result of the Stoneley wave time difference in Well B is as shown in Figure 6 . In the interval below X334.00m with good data quality, the Stoneley wave time difference extracted by the time-slowness correlation method (STC method) basically coincides with the predicted Stoneley wave time difference. In the interval of X140.5 - X334.00m with poor data quality, the predicted Stoneley wave time difference has better correlation with the longitudinal and transverse wave time differences, without abnormal high values, and the variation range of the Stoneley wave time difference in the whole well section is more stable, which proves the accuracy and applicability of the method of the present invention.

[0052] 4) Based on the dynamic and static images of the electrical imaging logging, combined with the conventional logging and acoustic imaging logging for comprehensive judgment, determine the effective fracture development positions and fracture widths of each well in the target area.

[0053] 5) Conduct fracture flat plate model experiments. According to the effective fracture development positions and fracture widths of each well, calculate the total formation permeability at the locations where effective fractures develop: As shown in Figure 7 , it is the relationship between fracture permeability and fracture width established by combining the experimental results of the French Petroleum Company. As shown in Figure 8 , it is the matrix overburden pore permeability relationship of Oilfield A in the target area with Well B in Oilfield A of the target area as an example. As shown in Figure 9 , it is the total formation permeability at the locations where fractures develop.

[0054] 6) Using the intelligently predicted Stoneley wave time difference, based on the Stoneley wave frequency shift and travel time difference, invert the total permeability of the buried hill reservoir: Taking Well B in Oilfield A of the target area as an example, according to the full-wave train waveform and spectrum, as shown in Figure 10, the frequency band distribution range of the Stoneley wave is 500 - 3000Hz. Based on this frequency band distribution range, combined with the Stoneley wave waveform and the intelligently predicted Stoneley wave time difference, invert the total formation permeability.

[0055] 7) Use the core permeability of the piston sample to calibrate the inversion result of the Stoneley wave permeability at the locations where effective fractures do not develop.

[0056] 8) According to the calculated total formation permeability at the locations where effective fractures develop, calibrate the inversion result of the Stoneley wave permeability at the locations where effective fractures develop.

[0057] Taking Well B in Oilfield A in the target area as an example, Well B conducted open-hole testing in the range of X144.00 - X275.00m (a total of 131.00m), with an average daily oil production of 1105.81m 3 , and an average daily gas production of 27384m 3 , being a typical high-yield well. Based on the total formation permeability at the fracture development site, under the condition that Well B lacks full-diameter core experiments, in the intervals where effective fractures do not develop, the plug sample core permeability is used to calibrate the Stoneley wave permeability inversion results; in the intervals where effective fractures develop, based on the total formation permeability at the fracture development site, the Stoneley wave permeability inversion results are calibrated. By combining the two, accurate calibration of the buried hill reservoir permeability inversion results is achieved, as Figure 11 shown.

[0058] Comparing the total formation permeability inverted based on the original Stoneley wave travel time, in the interval of X140.5 - X334.00m where the Stoneley wave data quality is poor, the total formation permeability inverted based on the intelligent predicted Stoneley wave travel time reflects the changes in reservoir permeability more accurately, reducing the impact of abnormal Stoneley wave travel time on the permeability inversion results and improving the accuracy of permeability evaluation. At the same time, the total formation permeability at the fracture development site calculated based on the fracture flat plate model and the relationship between matrix overburden porosity and permeability has a good matching trend with the Stoneley wave permeability inversion results, and can be used as a method for calibrating the permeability inversion results under the condition of few cores, improving the accuracy of the permeability inversion results. The above permeability inversion results based on the intelligent prediction of Stoneley wave travel time are also verified by the high-yield test results.

[0059] Example 2 This example provides a buried hill reservoir permeability evaluation system based on the intelligent prediction of Stoneley wave travel time, including: The first processing module is used to preprocess the core physical properties (surface core porosity, permeability), conventional logging, and electrical imaging logging data in the target area to obtain the preprocessed core physical properties, conventional logging data, and dynamic and static images of electrical imaging logging.

[0060] The second processing module is used to process the array acoustic logging data and extract the longitudinal, transverse, and Stoneley wave travel times of each well in the target area.

[0061] The Stoneley wave travel time prediction module is used to establish an intelligent prediction model of Stoneley wave travel time based on the longitudinal, transverse, and Stoneley wave travel times extracted from the intervals with good Stoneley wave data quality of each well, and predict the Stoneley wave travel times of the intervals with poor Stoneley wave data quality of each well.

[0062] The comprehensive judgment module is used to make a comprehensive judgment based on the dynamic and static images of electrical imaging logging, combined with conventional logging and acoustic imaging logging, to determine the effective fracture development positions and fracture widths of each well in the target area.

[0063] The total formation permeability determination module is used to conduct fracture flat plate model experiments and calculate the total formation permeability at the locations where effective fractures develop according to the effective fracture development positions and fracture widths of each well.

[0064] The inversion module is used to invert the total permeability of the buried hill reservoir based on the intelligent predicted Stoneley wave travel time difference, the Stoneley wave frequency shift, and the travel time difference.

[0065] The first calibration module is used to calibrate the inversion results of the Stoneley wave permeability at locations where effective fractures do not develop by using the core permeability of the piston sample.

[0066] The second calibration module is used to calibrate the inversion results of the Stoneley wave permeability at locations where effective fractures develop according to the calculated total formation permeability at the locations where effective fractures develop.

[0067] The system provided in this embodiment is used to execute the above-mentioned method embodiments. For the specific process and detailed content, please refer to the above-mentioned embodiments and will not be elaborated here.

[0068] Embodiment 3 This embodiment provides a processing device corresponding to the evaluation method of the buried hill reservoir permeability based on intelligent prediction of Stoneley wave travel time difference provided in Embodiment 1. The processing device can be a processing device applicable to a client, such as a mobile phone, a laptop computer, a tablet computer, a desktop computer, etc., to execute the method of Embodiment 1.

[0069] The processing device includes a processor, a memory, a communication interface, and a bus. The processor, the memory, and the communication interface are connected through the bus to complete communication with each other. The memory stores a computer program that can run on the processing device. When the processing device runs the computer program, it executes the evaluation method of the buried hill reservoir permeability based on intelligent prediction of Stoneley wave travel time difference provided in this Embodiment 1.

[0070] In some implementations, the memory can be a high-speed random access memory (RAM: Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory.

[0071] In other implementations, the processor can be a general-purpose processor of various types such as a central processing unit (CPU) and a digital signal processor (DSP), which will not be limited here.

[0072] In addition, when the logical instructions in the above-mentioned memory are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This 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 various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0073] Those skilled in the art can understand that the structure of the above-mentioned computing device is only a part of the structure related to the solution of the present invention and does not constitute a limitation on the computing device to which the solution of the present invention is applied. The specific computing device may include more or fewer components, or combine certain components, or have different component arrangements.

[0074] Embodiment 4 This embodiment provides a computer program product corresponding to the method for evaluating the permeability of buried hill reservoirs based on intelligent prediction of Stoneley wave time difference provided in Embodiment 1. The computer program product may include a computer-readable storage medium, on which computer-readable program instructions for executing the method for evaluating the permeability of buried hill reservoirs based on intelligent prediction of Stoneley wave time difference described in Embodiment 1 are uploaded.

[0075] A computer-readable storage medium may be a tangible device that holds and stores instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination of the above.

[0076] The computer-readable storage medium provided in the above-mentioned embodiment has the same implementation principle and technical effect as the above method embodiment and will not be elaborated herein.

[0077] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0078] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0080] The above embodiments are only used to illustrate the present invention, and the structures, connection manners, manufacturing processes, etc. of each component can be changed. Any equivalent transformation and improvement based on the technical solution of the present invention should not be excluded from the protection scope of the present invention.

Claims

1. A method for evaluating the permeability of buried hill reservoirs based on intelligent prediction of Stoneley wave travel time, characterized in that, Including: Preprocess the core physical properties, conventional logging, and electrical imaging logging data in the target area to obtain the preprocessed core physical properties, conventional logging data, and dynamic and static images of electrical imaging logging; Process the array acoustic logging data and extract the longitudinal, transverse, and Stoneley wave slownesses of each well in the target area; Based on the longitudinal, transverse, and Stoneley wave slownesses extracted from the intervals with good Stoneley wave data quality in each well, use an intelligent algorithm to establish an intelligent prediction model for Stoneley wave slowness, and predict the Stoneley wave slowness of the intervals with poor Stoneley wave data quality in each well; Based on the dynamic and static images of electrical imaging logging, combined with conventional logging and acoustic imaging logging, make a comprehensive judgment to determine the effective fracture development positions and fracture widths of each well in the target area; Carry out fracture slab model experiments, and calculate the total formation permeability at the locations where effective fractures develop according to the effective fracture development positions and fracture widths of each well; Using the intelligently predicted Stoneley wave slowness, based on the frequency shift and travel time difference of Stoneley waves, invert the total permeability of the buried hill reservoir; Use the plug sample core permeability to calibrate the inversion results of Stoneley wave permeability at locations where effective fractures do not develop; According to the calculated total formation permeability at the locations where effective fractures develop, calibrate the inversion results of Stoneley wave permeability at the locations where effective fractures develop.

2. The method for evaluating the permeability of buried hill reservoirs based on the intelligent prediction of Stoneley wave travel time as described in claim 1, wherein The preprocessing of the core physical properties, conventional logging data, and electrical imaging logging data in the target area to obtain the preprocessed core physical properties, conventional logging data, and dynamic and static images of electrical imaging logging includes: Based on the overburden pressure experiment, establish a ground - formation porosity and permeability correction chart, and correct the ground core porosity and permeability data to formation conditions; Take the well with relatively complete logging and core experiment data in the target area as the marker well, select the intervals that are stably developed in the target area as the marker layers, and based on the marker well and marker layers, perform depth correction and standardization processing on the conventional logging data of all wells in the target area to obtain the preprocessed conventional logging data; Process the electrical imaging logging data, scale the resistivity in the electrical imaging logging data into different color - graded images to obtain the dynamic and static images of electrical imaging logging of each well in the target area.

3. The evaluation method of buried hill reservoir permeability based on intelligent prediction of Stoneley wave travel time as claimed in claim 1, wherein The processing of the array acoustic logging data to extract the longitudinal, transverse, and Stoneley wave slownesses of each well in the target area uses the time - slowness correlation method.

4. The evaluation method of buried hill reservoir permeability based on intelligent prediction of Stoneley wave time difference according to claim 1, characterized in that The method of using the longitudinal, transverse, and Stoneley wave slownesses extracted from the intervals with good Stoneley wave data quality in each well, using an intelligent algorithm to establish an intelligent prediction model for Stoneley wave slowness, and predicting the Stoneley wave slowness of the intervals with poor Stoneley wave data quality in each well includes: Select the longitudinal and transverse wave slownesses as the sensitive curves for Stoneley wave slowness prediction; Take the Stoneley wave waveforms of each well in the target area and the intervals where the Stoneley wave arrival time is normal as the training set; Use the MRGC algorithm, with the longitudinal and transverse wave slownesses as the input curves and the Stoneley wave slowness as the output curve, and based on the established training set, establish an intelligent prediction model for Stoneley wave slowness; For the intervals with poor Stoneley wave data quality in each well in the target area, based on the established intelligent prediction model for Stoneley wave slowness and the extracted longitudinal and transverse wave slownesses, predict the Stoneley wave slowness.

5. The evaluation method for permeability of buried hill reservoir based on intelligent prediction of Stoneley wave travel time according to claim 4, characterized in that The MRGC algorithm is adopted, with the longitudinal and transverse wave slownesses as the input curves and the Stoneley wave slowness as the output curve. Based on the established training set, an intelligent prediction model for the Stoneley wave slowness is established, including: Based on the vector space model, the selected logging curves and the predicted output curve are transformed into a vector space composed of several features; The features of each sample data in the training set are filled into the vector space; Through the geometric relationship between two feature vectors in the vector space, the Euclidean distance between the feature vector for predicting the Stoneley wave slowness and all feature vectors in the dataset is determined; Based on the Euclidean distance between the eigenvector for predicting the Stoneley wave travel time difference and all eigenvectors in the dataset, find the nearest data items, and use a Gaussian function to convert the Euclidean distance into weights, and calculate the weighted arithmetic mean of the nearest data items to obtain the final prediction result of the Stoneley wave travel time difference.

6. The method for evaluating the permeability of buried hill reservoirs based on intelligent prediction of Stoneley wave time difference according to claim 1, characterized in that Carry out fracture slab model experiments. According to the effective fracture development positions and fracture widths of each well, calculate the total formation permeability at the locations where effective fractures develop, including: Carry out fracture slab model experiments. According to the fracture development positions and fracture widths of each well, calculate the fracture permeability at the locations where effective fractures develop; Meanwhile, based on the relationship between matrix overburden porosity and permeability, calculate the matrix permeability of each well in the target area; Add the fracture permeability and matrix permeability at the locations where effective fractures develop in each well in the target area to obtain the total formation permeability at the locations where effective fractures develop in each well in the target area.

7. The evaluation method for permeability of buried hill reservoir based on intelligent prediction of Stoneley wave travel time as claimed in claim 1, wherein The intelligent predicted Stoneley wave slowness is adopted to invert the total permeability of the buried hill reservoir based on the Stoneley wave frequency shift and travel time difference, including: Forward simulate the Stoneley wave slowness of the tight formation. By adjusting the parameters, make the theoretically calculated Stoneley wave slowness coincide with the intelligent predicted Stoneley wave slowness in the tight formation to obtain the calibration result of the parameters; According to the parameters calibrated for the tight formation, calculate the Stoneley wave slowness of the interval to be analyzed. If there is a difference between the calculated Stoneley wave slowness and the intelligent predicted Stoneley wave slowness, it is considered as a permeable layer, and based on the Stoneley wave frequency shift and travel time difference, invert the total permeability of the buried hill reservoir.

8. An evaluation system for permeability of buried hill reservoirs based on intelligent prediction of Stoneley wave travel time difference, characterized in that, Including: The first processing module is used to preprocess the core physical properties, conventional logging, and electrical image logging data in the target area to obtain the preprocessed core physical properties, conventional logging data, and dynamic and static images of electrical image logging; The second processing module is used to process the array acoustic logging data and extract the longitudinal, transverse, and Stoneley wave slownesses of each well in the target area; The Stoneley wave slowness prediction module is used to establish an intelligent prediction model for the Stoneley wave slowness based on the longitudinal, transverse, and Stoneley wave slownesses extracted from the intervals with good Stoneley wave data quality of each well, and predict the Stoneley wave slowness of the intervals with poor Stoneley wave data quality of each well; The comprehensive judgment module is used to make a comprehensive judgment based on the dynamic and static images of electrical image logging, combined with conventional logging and acoustic image logging, to determine the effective fracture development positions and fracture widths of each well in the target area; The total formation permeability determination module is used to carry out fracture slab model experiments and calculate the total formation permeability at the locations where effective fractures develop according to the effective fracture development positions and fracture widths of each well; The inversion module is used to invert the total permeability of the buried hill reservoir by using the intelligent predicted Stoneley wave slowness based on the Stoneley wave frequency shift and travel time difference; The first calibration module is used to calibrate the inversion result of the Stoneley wave permeability at the locations where effective fractures do not develop by using the core permeability of the plug sample; The second calibration module is used to calibrate the inversion result of the Stoneley wave permeability at the location where effective fractures develop according to the calculated total formation permeability at the location where effective fractures develop.

9. A processing device, characterized in that, It includes computer program instructions, wherein when the computer program instructions are executed by a processing device, they are used to implement the steps corresponding to the evaluation method of the buried hill reservoir permeability based on intelligent prediction of Stoneley wave travel time according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, Computer program instructions are stored on the computer-readable storage medium, wherein when the computer program instructions are executed by a processor, they are used to implement the steps corresponding to the evaluation method of the buried hill reservoir permeability based on intelligent prediction of Stoneley wave travel time according to any one of claims 1-7.

Images