A fracture contour extraction method for well logging images

Abstract

The present invention relates to the field of image processing technology, and in particular to a method for extracting fracture contours from a well logging map, the method comprising obtaining a well logging map, and obtaining spatial parameters of the pixel points according to the grayscale value and position characteristics of the pixel points in the well logging map, obtaining environmental performance values ​​of the pixel points according to the spatial parameters of the pixel points and the surrounding pixel points, obtaining fracture characteristic values ​​of the pixel points according to the environmental performance values ​​of the pixel points and the coordinate spacing of the pixel points, and classifying according to the size of the fracture characteristic values ​​to distinguish the fracture positions of the well logging map. According to the solution of the present invention, the fracture positions are located, the edges of the fractures are more clearly defined, the fracture contours are accurately monitored, and the exploration technology is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and more particularly to a method for extracting fracture contours from a well logging image. Background Art

[0002] Fracture contour extraction is a key technology in well logging analysis. Its main purpose is to provide accurate geological information support for oil and gas exploration, groundwater resource management, and geological disaster prediction by analyzing underground fracture information reflected in well logging data. Fractures are common structural features in underground geological bodies. Their morphology and distribution directly affect the storage and flow of underground fluids. Therefore, extracting fracture contours is of great significance for further geological research and resource assessment.

[0003] First, fracture contour extraction can help geological engineers identify the distribution, morphological characteristics and ductility of underground fractures. By analyzing different layers in the well logging map, the geometric morphology of the fractures can be clearly revealed, and then the impact range of the fractures and the possible impact on the oil and gas reservoir or groundwater system can be predicted. It has important reference value for the exploration and development of oil and gas fields and the development of groundwater resources.

[0004] Secondly, fracture contour extraction can also provide data support for subsequent numerical simulations. By accurately extracting fracture characteristics and converting them into data suitable for geological modeling and numerical simulation, the behavior of fractures under different conditions, such as fluid flow, pressure distribution, etc., can be effectively simulated. This plays an important role in improving the efficiency of oil and gas field development, reducing development costs, and improving resource utilization.

[0005] In addition, crack contour extraction also plays an important role in geological disaster prediction. For example, in earthquake research, the distribution and activity of cracks are often closely related to the formation of the earthquake source and the vibration propagation path. By extracting crack contours and combining them with other geological data, it is possible to effectively predict potential geological disaster risks, take countermeasures in advance, and reduce the losses caused by disasters.

[0006] In general, the fracture contour extraction method has important practical application value in the fields of geological exploration, resource assessment and disaster warning. With the continuous advancement of logging technology and data processing methods, the accuracy and efficiency of fracture contour extraction are also constantly improving, providing strong support for the development of geological disciplines and engineering practice.

[0007] However, for example, in the Chinese invention patent document with the authorization announcement number CN110599595B, a three-dimensional characterization method of geological structure is disclosed, which realizes contour extraction by digitally processing geological data and extracting contour lines. At present, in the field of well logging exploration, the KNN algorithm is often used to determine the location of cracks when identifying well logging maps. However, in the well logging map, there are different geological layers. Because the geological connection is close to the crack and the boundary of the crack edge is not obvious, it will affect the judgment of the crack contour, making the traditional KNN algorithm perform poorly, resulting in inaccurate detection of the crack contour.

[0008] Therefore, how to solve the problem of inaccurate fracture contour detection in well logging images is one of the key directions of current research. Summary of the invention

[0009] In order to solve the technical problem of inaccurate fracture profile detection in the above-mentioned well logging diagram, the present invention provides solutions in the following aspects.

[0010] In a first aspect, the present invention provides a fracture contour extraction method for a well logging map, comprising: obtaining a well logging map, and obtaining a spatial parameter of the pixel point according to the gray value and position characteristics of the pixel point in the well logging map, wherein the spatial parameter is positively correlated with the gray value and position characteristics of the pixel point; obtaining an environmental performance value of the pixel point according to the spatial parameter of the pixel point and the surrounding pixels, wherein the calculation formula of the environmental performance value is: ;in, represents the environmental performance value of pixel i, Represents the spatial parameter of pixel i, Represents the spatial parameter of data j within the range corresponding to pixel i, Indicates the distance between the data i corresponding to the pixel point i in the three-dimensional coordinate system data space and the data j within its range, represents the slope of the line connecting two data points, Indicates the number of data within the range of data i in the three-dimensional coordinate system data space corresponding to pixel point i, represents a normalization function, n represents the number of data in the corresponding range of pixel point i; the fracture characteristic value of the pixel point is obtained according to the environmental performance value of the pixel point and the coordinate spacing of the pixel point, wherein the fracture characteristic value is negatively correlated with the mean deviation of the environmental performance value and positively correlated with the maximum value of the coordinate spacing; classification is performed according to the size of the fracture characteristic value to distinguish the fracture position of the logging map.

[0011] The present invention obtains the crack characteristic values ​​of the pixel points by analyzing the grayscale characteristics and position characteristics of the pixel points in the logging image and calculating the environmental performance values ​​of the pixel points. The crack characteristic values ​​are used for classification to determine the boundaries of the cracks and locate the crack positions, making the edges of the cracks clearer, achieving accurate monitoring of the crack contours and effectively improving the exploration technology.

[0012] Preferably, the calculation formula of the spatial parameter of the pixel is:

[0013] ;

[0014] in, Represents the spatial parameter of pixel i, Represents the gray value of a pixel. Represents the horizontal coordinate value of pixel i, Represents the vertical coordinate value of pixel i.

[0015] The present invention reflects the spatial position of pixel points through the spatial parameters of pixel points, which can fully demonstrate the uniqueness of each pixel point, thereby achieving more accurate detection of crack contours.

[0016] Preferably, the environmental performance value of the pixel point is obtained based on the spatial parameters of the pixel point and the pixels around it, including: constructing a three-dimensional coordinate system data space corresponding to the pixel point; in the three-dimensional coordinate system data space, selecting the distance between the farthest data points corresponding to the pixel point in the custom window of the image as the radius, and obtaining the data points within its spherical range; according to the distance between the pixel point and the data points within the corresponding spherical range, calculating the environmental performance value of the corresponding pixel point.

[0017] The present invention uses pixel points and their surrounding pixel points to perform environmental analysis and determine the different performances of pixel points and surrounding pixel points, which can achieve the distinction between different geology, geological gaps or cracks in the logging image, detect the coordination of the environment around the pixel points, and distinguish the different environmental performances of different pixel points, thereby achieving the purpose of accurately distinguishing geological performances and effectively improving the accuracy of fracture contour extraction.

[0018] Preferably, the method of constructing the three-dimensional coordinate system data space corresponding to the pixel point includes: constructing a three-dimensional coordinate system data space, whose horizontal axis is the horizontal axis coordinate of the pixel point, the vertical axis is the vertical axis coordinate of the pixel point, and the vertical axis is the spatial parameter of the pixel point, and corresponding the spatial parameter, horizontal coordinate and vertical coordinate of the pixel point to the three-dimensional coordinate system data space.

[0019] Preferably, the crack characteristic value of the pixel point is obtained according to the environmental performance value of the pixel point and the coordinate spacing of the pixel point, including: recording the connected pixel points whose environmental performance value difference is less than the set value as the connected approximate pixel points corresponding to the pixel point; determining the horizontal coordinate spacing and the vertical coordinate spacing between the pixel point and its connected approximate pixel points, and determining the maximum value of the horizontal coordinate spacing and the vertical coordinate spacing; determining the mean deviation between the environmental performance value and the mean of the environmental performance value, and calculating the crack characteristic value according to the ratio of the maximum value to the mean deviation.

[0020] The present invention distinguishes the different environmental performances of pixel points and distinguishes the pixel points with crack characteristics, so as to achieve the purpose of accurate distinction.

[0021] Preferably, the set value is less than or equal to 0.1.

[0022] Preferably, the calculation formula of the crack characteristic value is:

[0023] ;

[0024] in, Represents the crack feature value of the pixel point, Represents the horizontal coordinate distance between pixel i and the lth connected approximate pixel, Represents the vertical coordinate distance between pixel i and the lth connected approximate pixel, Indicates the maximum value, represents the mean value of the environmental performance value, and m represents the number of connected approximate pixels corresponding to pixel i.

[0025] Preferably, classification is performed according to the size of the fracture characteristic value to distinguish the fracture position of the logging map, including: arranging the fracture characteristic values ​​from large to small, and using the first maximum interval position as the positioning classification line, wherein the pixel points on the side with larger fracture characteristic values ​​are fracture pixel points, and the pixel points on the side with smaller fracture characteristic values ​​are non-fracture pixel points; determining the pixel points of all fracture areas to obtain the fracture contour.

[0026] The present invention locates the classification line at the first maximum interval position of the crack characteristic value from large to small, and the pixel point on the side with the larger crack characteristic value is the crack pixel point, so as to accurately obtain the pixel points of the crack area and accurately judge the crack contour.

[0027] Preferably, after acquiring the well logging map, the method further includes: graying the well logging map to obtain a grayscale well logging map.

[0028] The beneficial effects of the present invention are as follows: the present invention obtains fracture characteristic values ​​according to the characteristics of the well logging map, and then classifies the fractures according to the fracture characteristic values, accurately distinguishing the fracture positions of the well logging map, avoiding the influence of the geological connection points being close to the fractures and the unclear boundaries of the fracture edges on the fracture contour judgment, and improving the accuracy of fracture detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0030] Figure 1 FIG. 4 is a flow chart schematically illustrating a method for extracting fracture contours from a well logging image according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0032] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0033] Figure 1 FIG. 1 is a flow chart schematically illustrating a fracture profile extraction method 100 for a well logging image according to an embodiment of the present invention.

[0034] like Figure 1 As shown, in step S101, a well logging map is obtained, and the spatial parameter of the pixel point is obtained according to the gray value and position feature of the pixel point in the well logging map. The spatial parameter is positively correlated with the gray value and position feature of the pixel point.

[0035] Specifically, a well logging map is collected and generated, and then the well logging map is grayed to obtain a grayscale well logging map, and then the grayscale well logging map is used to perform subsequent processing steps.

[0036] In the grayscale logging map, different geology and well locations have different image performances, and for the pixels in the image, each pixel is unique, so it is necessary to consider the characteristics of each pixel and make each pixel unique, so as to analyze each pixel.

[0037] Furthermore, in order to facilitate calculation and analysis, the present invention uses spatial parameters to construct a corresponding three-dimensional coordinate system data space, and performs subsequent calculations of environmental performance values ​​based on the three-dimensional coordinate system.

[0038] At step S102, the environmental performance value of the pixel is obtained according to the spatial parameters of the pixel and the surrounding pixels. In some embodiments, a three-dimensional coordinate system data space corresponding to the pixel is constructed. In the three-dimensional coordinate system data space, the distance between the farthest data points corresponding to the pixel in the custom window of the image is selected as the radius to obtain the data points within its spherical range. According to the distance between the pixel and the data points within the corresponding spherical range, the environmental performance value of the corresponding pixel is calculated.

[0039] The three-dimensional coordinate system data space corresponding to the pixel point can be constructed in the following way: construct a three-dimensional coordinate system data space, whose horizontal axis is the horizontal axis coordinate of the pixel point, the vertical axis is the vertical axis coordinate of the pixel point, and the vertical axis is the spatial parameter of the pixel point, and correspond the spatial parameters, horizontal coordinate and vertical coordinate of the pixel point to the three-dimensional coordinate system data space.

[0040] In an application scenario, the calculation formula of the environmental performance value is:

[0041] ;

[0042] in, represents the environmental performance value of pixel i, Represents the spatial parameter of pixel i, Represents the spatial parameter of data j within the range corresponding to pixel i, Indicates the distance between the data i corresponding to the pixel point i in the three-dimensional coordinate system data space and the data j within its range, represents the slope of the line connecting two data points, Indicates the number of data within the range of data i in the three-dimensional coordinate system data space corresponding to pixel point i, represents the normalization function, and n represents the number of data in the range corresponding to pixel i.

[0043] In step S103, the crack characteristic value of the pixel point is obtained according to the environmental performance value of the pixel point and the coordinate spacing of the pixel point, wherein the crack characteristic value is negatively correlated with the mean deviation of the environmental performance value and positively correlated with the maximum value of the coordinate spacing.

[0044] In some embodiments, when calculating the crack characteristic value, the pixel value and position characteristics of the pixel point and the pixel points around it can be used for analysis. Specifically, the pixel points whose environmental performance value gap is less than the set value and are connected are recorded as the connected approximate pixel points corresponding to the pixel point. Determine the horizontal coordinate spacing and the vertical coordinate spacing between the pixel point and the connected approximate pixel points, and determine the maximum value of the horizontal coordinate spacing and the vertical coordinate spacing. Determine the mean deviation between the environmental performance value and the mean of the environmental performance value, and calculate the crack characteristic value based on the ratio of the maximum value to the mean deviation. The set value can be a value less than or equal to 0.1.

[0045] In one embodiment, the calculation formula of the crack characteristic value is:

[0046] ;

[0047] in, Represents the crack feature value of the pixel point, Represents the horizontal coordinate distance between pixel i and the lth connected approximate pixel, Represents the vertical coordinate distance between pixel i and the lth connected approximate pixel, Indicates the maximum value, represents the mean value of the environmental performance value, and m represents the number of connected approximate pixels corresponding to pixel i.

[0048] At step S104, the fracture characteristic values ​​are classified according to their magnitude to distinguish the fracture positions of the well logging map. In some embodiments, the fracture characteristic values ​​may be arranged from large to small, and the first maximum interval position is used as the positioning classification line, where the pixel points on the side with larger fracture characteristic values ​​are fracture pixel points, and the pixel points on the side with smaller fracture characteristic values ​​are non-fracture pixel points. The pixel points of all fracture areas are determined to obtain the fracture contour.

[0049] Next, the solution of the present invention will be described in detail in combination with the specific principles of the above steps.

[0050] Step 1: Collect and pre-process the well logging map. In the present invention, professional equipment is used to collect and generate the well logging map, and then the well logging map is grayed using a graying algorithm to obtain a gray logging map, and then the gray logging map is used to perform subsequent steps.

[0051] In the grayscale logging map, different geology and well locations have different image performances, and for the pixels in the image, each pixel is unique, so it is necessary to consider the characteristics of each pixel and make each pixel unique, so as to analyze each pixel.

[0052] Step 2: Obtain the spatial parameters of the pixel points based on the grayscale value and position characteristics of the pixel points, and establish a three-dimensional coordinate system data space based on the spatial parameters.

[0053] In the present invention, taking pixel i as an example, the spatial parameter of the pixel is obtained according to the gray value and position characteristics of the pixel.

[0054] ;

[0055] in, The spatial parameter representing pixel i can be used to reflect the spatial position characteristics of the pixel. Represents the gray value of a pixel. Represents the horizontal coordinate value of pixel i, Reflects the vertical coordinate value of pixel i. To reflect the position characteristics of the corresponding pixels, and at the same time make each pixel have a unique mark.

[0056] Afterwards, the abscissa value, ordinate value and calculated spatial parameters of the above pixel points are used to establish a three-dimensional coordinate system data space, wherein the abscissa is the abscissa coordinate of the pixel point, the ordinate is the ordinate coordinate of the pixel point, and the vertical axis is the spatial parameter of the pixel point, and then the spatial parameter, abscissa and ordinate of the pixel point are mapped to the three-dimensional coordinate system data space.

[0057] When a pixel point exists in different geological locations or geological gaps or cracks in a logging image, the pixel point and the pixels around it have different performances. For example, the grayscale value of the pixel point in the crack is lower, and the morphology of the crack is different from that of the geological layer or geological gap. Therefore, the present invention combines the environment around the pixel point for analysis.

[0058] Step 3: Obtain the environmental performance value of the pixel based on the spatial parameters of the pixel and its surrounding pixels.

[0059] Taking the data of the three-dimensional coordinate system data space corresponding to pixel point i as an example, the distance between the farthest data points corresponding to the pixel point in the custom window of the image is selected as the radius, and the data points within its spherical range are obtained. Specifically, the environmental performance value of the pixel point is obtained according to the spatial parameters of the pixel point and its surrounding pixels.

[0060] ;

[0061] in, Represents the environmental performance value of pixel i. The larger the value, the more inconsistent the pixel i is with the surrounding environment. Represents the spatial parameter of pixel i, It indicates the distance between the data i in the three-dimensional coordinate system data space corresponding to the pixel point i and the data j within its range. The farther the distance, the greater the difference in the pixel point features. represents the slope of the line connecting two data points, Indicates the number of data points corresponding to pixel i in the three-dimensional coordinate system data space. It can reflect the degree of coordination of data within the scope.

[0062] Through the above steps, the environmental performance value of the pixel point is obtained, and then the different environmental performances of the pixel point are distinguished. In the present invention, the environmental performance value is used to distinguish the pixel points with crack characteristics, so as to achieve the purpose of accurate distinction, because the crack is narrow, and the geological performance vertically connected to the crack direction is relatively similar. Next, the situation of each pixel point is analyzed in combination with the overall image.

[0063] Step 4: Obtain the crack characteristic value of the pixel point based on the environmental performance value and position morphology of the pixel point.

[0064] Taking the data of the three-dimensional coordinate system data space corresponding to pixel point i as an example, the connected pixels whose environmental performance value difference is less than 0.1 are recorded as the connected approximate pixels of pixel point i.

[0065] Specifically, the crack characteristic value of the pixel point is obtained according to the environmental performance value and position shape of the pixel point:

[0066] ;

[0067] in, Represents the crack characteristic value of the pixel point. The larger the value, the more crack characteristics the pixel point has. , It represents the horizontal and vertical distances between pixel i and the lth connected approximate pixel. Because the crack is narrow, the maximum value of the horizontal and vertical distances is small. Reflects the shape of the pixel. Because the crack is wider than the gap, the characteristics of the internal pixels are similar, but compared with the pixels in the geology, there are certain differences. Therefore, the environmental performance value is compared with the mean environmental performance value. The closer it is to the mean, the more it conforms to the characteristics of the crack pixels.

[0068] Step 5: Classify according to the fracture characteristic values ​​and accurately distinguish the fracture locations in the well logging map.

[0069] The crack characteristic values ​​of the pixel points are obtained through the above steps. The classification line is located at the first maximum interval position after the crack characteristic values ​​are arranged from large to small. The pixel points on the side with larger crack characteristic values ​​are the crack pixels. In this way, the pixel points in the crack area are accurately obtained and the crack contour is accurately determined.

[0070] The present invention determines the fracture characteristics through the pixel features in the logging image, thereby achieving accurate acquisition of the fracture location, effectively improving the accuracy of fracture detection, and can effectively predict the potential geological disaster risks, take countermeasures in advance, and reduce the losses caused by disasters, providing strong support for the development of geological disciplines and engineering practice.

[0071] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly defined.

[0072] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A fracture contour extraction method for well logging, characterized in that: include: Acquire a well logging map, and obtain a spatial parameter of the pixel point according to the gray value and position characteristics of the pixel point in the well logging map, wherein the spatial parameter is positively correlated with the gray value and position characteristics of the pixel point; The environmental performance value of the pixel is obtained according to the spatial parameters of the pixel and its surrounding pixels, where the calculation formula of the environmental performance value is: Among them, Q i represents the environmental performance value of pixel i, B i Represents the spatial parameter of pixel i, B ij Represents the spatial parameter of data j within the range corresponding to pixel i, E ij G represents the distance between the data i in the three-dimensional coordinate system data space and the data j within its range corresponding to the pixel i. ij Represents the slope of the line connecting two data points, F i represents the number of data i corresponding to pixel point i in the three-dimensional coordinate system data space, norm() represents the normalization function, and n represents the number of data j in the range corresponding to pixel point i; Obtaining a crack characteristic value of the pixel point according to the environmental performance value of the pixel point and the coordinate spacing of the pixel point, wherein the crack characteristic value is negatively correlated with the mean deviation of the environmental performance value and positively correlated with the maximum value of the coordinate spacing; Classify according to the size of the fracture characteristic value to distinguish the fracture location of the well logging map; The calculation formula of the spatial parameters of the pixel is: Among them, H i Represents the gray value of the pixel, X i Indicates the horizontal coordinate value of pixel i, Y i Represents the ordinate value of pixel i; The environmental performance value of the pixel is obtained based on the spatial parameters of the pixel and its surrounding pixels, including: Construct the three-dimensional coordinate system data space corresponding to the pixel points; In the three-dimensional coordinate system data space, the distance between the farthest data points corresponding to the pixel points in the custom window of the image is selected as the radius to obtain the data points within its spherical range; According to the distance between the pixel point and the data point within the corresponding spherical range, the environmental performance value of the corresponding pixel point is calculated; The crack characteristic value of the pixel point is obtained according to the environmental performance value of the pixel point and the coordinate spacing of the pixel point, including: The connected pixels whose environmental performance value difference is less than the set value are recorded as the connected approximate pixels corresponding to the pixels; Determine the horizontal coordinate spacing and the vertical coordinate spacing between the pixel point and the adjacent approximate pixel points, and determine the maximum value of the horizontal coordinate spacing and the vertical coordinate spacing; Determining a mean deviation between an environmental performance value and a mean of the environmental performance values, and calculating a crack characteristic value based on a ratio of the maximum value to the mean deviation; The calculation formula of the crack characteristic value is: Among them, A i Represents the crack feature value of the pixel point, C il represents the horizontal coordinate distance between pixel i and the lth connected approximate pixel, D il Indicates the vertical coordinate distance between pixel i and the lth connected approximate pixel, max() indicates the maximum value, represents the mean value of the environmental performance value, m represents the number of connected approximate pixels corresponding to pixel i; Classify according to the size of the fracture characteristic value to distinguish the fracture location of the well logging map, including: Arrange the crack feature values ​​from large to small, and use the first maximum interval position as the positioning classification line, where the pixel points on the side with larger crack feature values ​​are crack pixels, and the pixel points on the side with smaller crack feature values ​​are non-crack pixels; Determine the pixel points of all crack areas to obtain the crack contour.

2. The fracture contour extraction method for well logging diagram according to claim 1, characterized in that: The construction method of the three-dimensional coordinate system data space corresponding to the pixel point includes: Construct a three-dimensional coordinate system data space, whose horizontal axis is the horizontal axis coordinate of the pixel point, the vertical axis is the vertical axis coordinate of the pixel point, and the vertical axis is the spatial parameter of the pixel point. The spatial parameter, horizontal coordinate and vertical coordinate of the pixel point are mapped to the three-dimensional coordinate system data space.

3. The fracture contour extraction method for well logging diagram according to claim 1, characterized in that: The set value is less than or equal to 0.

1.

4. The fracture contour extraction method for well logging according to any one of claims 1 to 3, characterized in that: After obtaining the well logging diagram, it also includes: Grayscale the well logging image to obtain a grayscale well logging image.

Images