Rock cutting depth automatic measuring method

Abstract

The invention provides an automatic rock cutting depth measurement method, and relates to the technical field of depth measurement, and the method comprises the steps: obtaining a plurality of groups of fracture surface CT scanning images of a rock cut by abrasive water jet, constructing a three-dimensional digital rock core model and a three-dimensional kerf model, and obtaining a rock cutting depth according to a kerf side image; the method comprises the following steps: acquiring a pixel matrix of a kerf side image and a coordinate pixel set of a kerf area, scanning each column of the kerf side image, acquiring a vertical coordinate set of zero pixel points of each column and maximum and minimum vertical coordinate values of each column, constructing a corresponding proportion of the column with the most zero pixel points and the actual depth of the column, and calculating the actual depth of the kerf area; according to the method, the rock cutting depth can be automatically measured, and meanwhile, higher measurement precision can be obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of depth measurement, and specifically to an automatic measurement method for rock cutting depth. Background Art

[0002] In abrasive water jet cutting, cutting depth measurement is a core link for optimizing process parameters and evaluating cutting effects. Traditional methods mainly rely on manual use of tools such as vernier calipers and feeler gauges to estimate the cutting depth through the average value of limited measurement points (such as 3 - 5 points). However, such methods have significant defects: First, the selection of measurement points highly depends on the operator's experience, and errors are easily caused by subjective judgment. Especially on rough or complex contour cutting surfaces, local extreme points are often ignored, resulting in deviations in the calculation of average cutting depth. Second, manual measurement is inefficient, difficult to capture microscopic details (such as tiny cracks or morphological changes of heterogeneous materials), and unable to comprehensively reflect the true depth distribution of the cross-section. With the increasing demand for measurement accuracy and efficiency in industrial scenarios, the limitations of traditional methods have become a bottleneck restricting process optimization and quality control.

[0003] In recent years, although three-dimensional imaging technologies (such as CT scans) have been gradually applied in materials science, their combination with automated data processing is still in the exploratory stage. In the existing technology, CT scans are mostly used for static structure analysis, and for depth measurement of dynamic cutting cross-sections, a systematic automated solution has not been formed. Most research still remains at the stage of manual selection of slices or limited data extraction, unable to fully utilize the global information of three-dimensional data and lacking efficient algorithm support.

[0004] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, so it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide an automatic measurement method for rock cutting depth to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] An automatic measurement method for rock cutting depth, the specific steps include:

[0008] Step 1: Obtain CT scan images of the cross-sections of rocks cut by abrasive water jets, input them into Avizo for parameter adjustment, mark the cutting seam area, and construct a three-dimensional digital core model;

[0009] Step 2: Obtain a three-dimensional cutting seam model, obtain the side image of the cutting seam, perform binary processing on the side image of the cutting seam, obtain the pixel matrix of the side image of the cutting seam, and obtain the coordinate pixel set of the cutting seam area;

[0010] Step 3: Perform a closing operation on the side image of the cut seam, scan each column of the side image of the cut seam, obtain the set of vertical coordinates of zero-pixel points for each column, and separately obtain the maximum and minimum vertical coordinate values for each column;

[0011] Step 4: Based on the number of zero-pixel points for each column, obtain the column with the most zero-pixel points and measure the actual depth of this column, and obtain the corresponding ratio between the number of pixel points and the actual depth;

[0012] Step 5: Obtain the actual depth and cut-seam length for each column, draw the actual depth table and the cut-depth curve and output them, and obtain the average depth of the cut depth.

[0013] Furthermore, clean the surface of the rock cut by abrasive water jet and perform a CT scan to obtain multiple sets of cutting cross-sections. Import the cutting cross-section data into Avizo, crop all the cutting cross-sections to remove the blank areas, process the cutting cross-sections through the BoxFilter filtering algorithm in Avizo. The filtering intensity of the BoxFilter filtering algorithm is between 2 and 5. Perform threshold segmentation on the cutting cross-sections through Avizo. During the threshold segmentation process, manually adjust the intensity range parameter to generate a binary cutting cross-section, label the cut-seam area, separately manually adjust the opacity mapping parameter and the lighting parameter, and construct a three-dimensional digital core model from the cutting cross-section data through Avizo.

[0014] Furthermore, adjust the orientation of the three-dimensional digital core model so that the cut-seam direction is upward. Automatically extract the three-dimensional cut-seam model from the three-dimensional digital core model through the extraction function of Avizo, and hide the three-dimensional digital core model to obtain the side image of the cut seam. The side image of the cut seam is a side view perpendicular to the cut-seam path direction. Perform binary processing on the side image of the cut seam, convert the background pixel values of the non-cut-seam area to 255, and convert the pixel values of the cut-seam area to 0 to obtain the pixel matrix of the side image of the cut seam. Taking the upper left corner of the side image of the cut seam as the origin, with the positive x-axis direction horizontally to the right and the positive y-axis direction vertically downward, one pixel point corresponds to one cell, and obtain the set of pixel coordinates of the cut-seam area. The formula is as follows:

[0015] S = {(x, y) | I(x, y) ≠ 255}

[0016] where S is the set of pixel positions of the cut-seam area, and I(x, y) represents the pixel value of the pixel with abscissa x and ordinate y.

[0017] Furthermore, perform a closing operation on the side of the cut seam to obtain a complete side image of the cut seam, scan each column of the complete side image of the cut seam, and obtain the set of vertical coordinates of zero-pixel points for each column on the x-axis. The formula is as follows:

[0018] y(x) = {y | I(x, y) = 0}

[0019] Where S(x) represents the set of vertical coordinates of zero pixels in the x-th column, y represents the vertical coordinate of the zero pixel in the y-th row, and I(x, y) represents the pixel value of the pixel at the x-th column and y-th row;

[0020] Screen the sets of vertical coordinates of all zero pixels on the x-axis, and remove the columns for which the set of vertical coordinates of zero pixels is an empty set;

[0021] Obtain the maximum and minimum y-axis coordinate values for each column respectively, based on the following formula:

[0022] y max (x) = MAX[S(x)]

[0023] y min (x) = MIN[S(x)]

[0024] Where y max (x) represents the maximum vertical coordinate value in the set S(x), and y min (x) represents the minimum vertical coordinate value in the set S(x), MAX represents the function for selecting the maximum value, MIN represents the function for selecting the minimum value, and S(x) represents the set of vertical coordinates of zero pixels in the x-th column.

[0025] Furthermore, based on the scanning result of each column, obtain the number of zero pixels in each column, based on the following formula:

[0026] Δy(x) = y max (x) - y min (x)

[0027] Where Δy(x) represents the number of zero pixels in the s-th column, y max (s) represents the maximum vertical coordinate value in the set S(x), and y min (x) represents the minimum vertical coordinate value in the set S(x);

[0028] Obtain the column with the largest number of zero pixels, and measure the actual depth of this column through the ruler function of Avizo to obtain the corresponding ratio of the number of pixels to the actual depth, based on the following formula:

[0029]

[0030] Where γ is the corresponding ratio, Δy represents the number of zero pixels in the column with the largest number of zero pixels, and Y represents the actual depth of the column with the largest number of zero pixels.

[0031] Furthermore, obtain the actual depth of each column respectively, based on the following formula:

[0032] γ·Δy(x) = Y(x)

[0033] Among them, Y(x) represents the actual depth of the x-th column, Δy(x) represents the number of zero-pixel points in the x-th column, and γ is the corresponding ratio;

[0034] Output the actual depths of all columns in the form of a table;

[0035] Obtain the number of the set of zero-pixel point ordinates, and construct the crack length according to the following formula:

[0036] L = γ·|S(x)|

[0037] Among them, L is the crack length, γ is the corresponding ratio, and |S(x)| is the number of the set of zero-pixel point ordinates;

[0038] Draw and output the cutting depth curve based on the actual depths of all columns. The abscissa is the crack length, the ordinate is the actual depth of the crack, and obtain the average depth of the cutting seam.

[0039] Compared with the prior art, the beneficial effects of the present invention are:

[0040] The present invention obtains the rock cross-section image through CT scanning, constructs a three-dimensional digital core model and a three-dimensional cutting seam model in Avizo, analyzes the side image of the cutting seam by scanning, obtains the number of zero-pixel points in each column of the side image of the cutting seam, measures the actual depth of the column with the most zero-pixel points, obtains the actual depth table and the cutting depth curve, automatically completes the measurement of the rock cutting depth, and at the same time obtains higher measurement accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0042] Figure 2 It is a schematic diagram of the side image scanning of the cutting seam of the present invention;

[0043] Figure 3 It is a schematic diagram of the cutting depth curve of the present invention;

[0044] Figure 4 It is a schematic diagram of the comparison effect of the measurement method of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0045] In order to make the purpose, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to specific embodiments.

[0046] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those with ordinary skills in the field to which the present invention pertains. The "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. Words such as "comprising" or "including" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. Words such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Upper", "lower", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0047] Embodiment:

[0048] Please refer to Figure 1 , the present invention provides a technical solution:

[0049] A method for automatically measuring the cutting depth of a rock, the specific steps including:

[0050] Step 1: Obtain CT scan images of the cross-sections of rocks cut by abrasive water jets, input them into Avizo for parameter adjustment, mark the cut seam area, and construct a three-dimensional digital core model;

[0051] The said Step 1 includes the following contents:

[0052] Clean the surface of the rock cut by abrasive water jets and perform CT scanning to obtain multiple groups of cutting cross-sections. Import the cutting cross-section data into Avizo, crop all the cutting cross-sections to remove the blank areas, process the cutting cross-sections through the BoxFilter filtering algorithm in Avizo, where the filtering intensity of the BoxFilter filtering algorithm is between 2 and 5. Perform threshold segmentation on the cutting cross-sections through Avizo. During the threshold segmentation process, manually adjust the intensity range parameter to generate a binary cutting cross-section, mark the cut seam area, and manually adjust the opacity mapping parameter and the lighting parameter respectively. Construct a three-dimensional digital core model from the cutting cross-section data through Avizo.

[0053] As a preferred embodiment, the original data obtained from CT scans is imported into Avizo software. After starting Avizo software, select Open under the File menu and select the corresponding CT scan data file from the file directory. After the data is imported, the system will automatically display two-dimensional slice images, and the images usually represent rock density information in grayscale. Since the original CT scan images often contain a large number of irrelevant regions, to improve the efficiency of subsequent processing and save memory space, the rock region is cropped. The sample region is selected by dragging the cropping box with the mouse to ensure that only the valid data containing the target rock structure is retained. This step reduces the data volume by eliminating irrelevant regions, which helps to optimize memory usage and speed up the subsequent processing process.

[0054] As a preferred embodiment, a filtering algorithm in Avizo is used to denoise the image data. Right-click on the cropped data set, select AddModule→ImageProcessing→Filter to add a filtering module, and perform filtering through the BoxFilter algorithm to well detect the object boundary. The edge-preserving property of this algorithm enables it to effectively detect blurred edges. In the Filter panel, adjust the FilterStrength parameter according to the image noise level. It is usually recommended to set the filtering intensity between 2 and 5 to achieve a balanced effect of noise reduction and edge preservation. After clicking Apply, the system will generate the filtered image. Subsequently, by comparing the visualization results of the images before and after filtering in Avizo, it is ensured that the noise in the image is significantly reduced. This step can effectively improve the noise problem in CT scan data and lay a data foundation for subsequent crack extraction and 3D reconstruction.

[0055] As a preferred embodiment, right-click on the filtered image data set and select AddModule→Segmentation→InteractiveThresholding to add a threshold segmentation module. In the InteractiveThresholding panel, adjust the IntensityRange parameter and control the display of different grayscale regions in the image by dragging the slider. To ensure that the crack structure is clearly visible, the slider needs to be gradually fine-tuned until the crack region is clearly shown and the blue-labeled crack part is complete. If over-segmentation or incomplete cracks occur, the parameters can be further fine-tuned until the most suitable threshold is reached. After completing the threshold segmentation, click Apply to generate binary image data, with the crack region labeled in blue and the rock body represented in gray or white. This step uses the threshold segmentation algorithm to effectively extract the boundary information of cracks and rocks, providing an accurate morphological basis for 3D reconstruction.

[0056] As a preferred embodiment, after completing the binary segmentation of the fissures and the rock matrix, 3D reconstruction is achieved using the 3D rendering tool provided by Avizo. Right-click on the dataset after threshold segmentation is completed and select Add Module → Visualization → Volume Rendering Settings to add the 3D reconstruction module. After entering the Volume Rendering Settings panel, set the Opacity Mapping parameter and highlight the outline of the rock structure by adjusting the transparency curve. To enhance the visual effect of the 3D model, the Lighting Controls module can be further adjusted to optimize the lighting angle, brightness, and shadow intensity. After the parameter adjustment is completed, click Render to generate the 3D model. Subsequently, the 360° rotation, zoom, and translation of the model can be achieved using the Camera Controls module of Avizo to further enhance the stereoscopic display effect of the model. This step uses the 3D reconstruction algorithm to intuitively restore the spatial morphology of the rock fissures, providing a more realistic data model for structural analysis and experimental research.

[0057] Step 2: Obtain a 3D cut slot model, obtain the side image of the cut slot, perform binary processing on the side image of the cut slot, obtain the pixel matrix of the side image of the cut slot, and obtain the coordinate pixel set of the cut slot area;

[0058] The said Step 2 includes the following content:

[0059] Adjust the direction of the 3D digital core model so that the cut slot direction is upward. Automatically extract the 3D cut slot model from the 3D digital core model through the extraction function of Avizo, and hide the 3D digital core model. Obtain the side image of the cut slot. The side image of the cut slot is a side view perpendicular to the cut slot path direction. Perform binary processing on the side image of the cut slot, convert the background pixel value of the non-cut slot area to 255, and convert the pixel value of the cut slot area to 0. Obtain the pixel matrix of the side image of the cut slot. Taking the upper left corner of the side image of the cut slot as the origin, the positive x-axis direction is horizontally to the right, and the positive y-axis direction is vertically downward. One pixel point corresponds to one cell, and obtain the pixel coordinate set of the cut slot area. The formula is as follows:

[0060] S = {(x, y) | I(x, y) ≠ 255}

[0061] where S is the pixel position set of the cut slot area, and I(x, y) represents the pixel value of the pixel with the abscissa x and the ordinate y.

[0062] As a preferred embodiment, the side image of the slit is extracted in Avizo, and the cv2.threshold() method is used to binarize the side image of the slit, converting the background area to pure white (pixel value 255) to quickly distinguish the target area. Subsequently, the np.where() function is used to detect the pixel value coordinates of all pixels with pixel values not equal to 255 in the non-background area. By this method, the problem of background interference in complex images is effectively solved, ensuring the accuracy of depth measurement.

[0063] Step 3: Perform closing operation on the side image of the slit, scan each column of the side image of the slit, obtain the set of vertical coordinates of zero-pixel points in each column, and respectively obtain the maximum and minimum vertical coordinate values of each column;

[0064] The said Step 3 includes the following content;

[0065] Perform closing operation on the side of the slit to obtain a complete side image of the slit, scan each column of the complete side image of the slit, and obtain the set of vertical coordinates of zero-pixel points in each column on the x-axis. The formula is as follows:

[0066] S(x) = {y | I(x, y) = 0}

[0067] Among them, S(x) represents the set of vertical coordinates of zero-pixel points in the x-th column, y represents the vertical coordinate of the zero-pixel point in the y-th row, and I(x, y) represents the pixel value of the pixel point in the x-th column and y-th row;

[0068] Screen the set of vertical coordinates of all zero-pixel points on the x-axis and remove the columns with an empty set of vertical coordinates of zero-pixel points;

[0069] Respectively obtain the maximum and minimum y-axis coordinate values of each column. The formula is as follows:

[0070] y max (x) = MAX[S(x)]

[0071] y min (x) = MIN[S(x)]

[0072] Among them, y max (x) represents the maximum vertical coordinate value in the S(x) set, and y min (x) represents the minimum vertical coordinate value in the S(x) set. MAX represents the function of selecting the maximum value, MIN represents the function of selecting the minimum value, and S(x) represents the set of vertical coordinates of zero-pixel points in the x-th column.

[0073] As a preferred embodiment, such as Figure 2As shown in the figure, the cv2.threshold() method is used to binarize the grayscale image again, filtering out the non-target areas and only retaining the contours of the target objects. Subsequently, the closing operation method in cv2.morphologyEx() is used to eliminate the isolated noise points in the image and fill the small holes that may exist in the contours, thereby improving the contour integrity. After the above processing, the program scans the image column by column, uses np.where() to detect all the pixel points with pixel value 0 in each column, and records their X and Y coordinates, and summarizes them to form the set of the vertical coordinates of the zero pixel points in each column. The curve extraction algorithm in this step can ensure the continuity and integrity of the curve data during the measurement process, providing data support for subsequent depth calculation.

[0074] Step 4: Obtain the zeros of each column. According to the number of zero pixel points, obtain the column with the most zero pixel points and measure the actual depth of this column, and obtain the corresponding ratio between the number of pixel points and the actual depth;

[0075] The said step 4 includes the following contents:

[0076] According to the scanning results of each column, obtain the number of zero pixel points in each column. The formula is as follows:

[0077] Δy(x) = y max (x) - y min (x)

[0078] Where, Δy(x) represents the number of zero pixel points in the x-th column, y max (x) represents the maximum vertical coordinate value in the set S(x), and y min (x) represents the minimum vertical coordinate value in the set S(x);

[0079] Obtain the column with the most zero pixel points, and measure the actual depth of this column through the ruler function of Avizo, and obtain the corresponding ratio between the number of pixel points and the actual depth. The formula is as follows:

[0080]

[0081] Where, γ is the corresponding ratio, Δy represents the number of zero pixel points in the column with the most zero pixel points, and Y represents the actual depth of the column with the most zero pixel points.

[0082] As a preferred embodiment, use the ruler function of Avizo to measure the cutting depth at the maximum. As the reference cutting depth for subsequent processing.

[0083] Step 5: Obtain the actual depth and cutting seam length of each column, draw the actual depth table and cutting depth curve and output them, and obtain the average depth of the cutting depth.

[0084] The said step 5 includes the following contents:

[0085] Obtain the actual depth of each column respectively, based on the following formula:

[0086] γ·Δy(x) = Y(x)

[0087] Wherein, Y(x) represents the actual depth of the x-th column, Δy(x) represents the number of zero-pixel points in the x-th column, and γ is the corresponding ratio;

[0088] Output the actual depths of all columns in the form of a table;

[0089] Obtain the number of the set of zero-pixel point ordinates, and construct the crack length, based on the following formula:

[0090] L = γ·|S(x)|

[0091] Wherein, L is the crack length, γ is the corresponding ratio, and |S(x)| is the number of the set of zero-pixel point ordinates;

[0092] Draw and output the cutting depth curve according to the actual depths of all columns, with the crack length as the abscissa and the actual depth of the crack as the ordinate, and obtain the average depth of the cutting seam.

[0093] As a preferred embodiment, as Figure 3 shown, the X and Y coordinates of the cutting depth of each column and their millimeter depth values are organized into a pandas.DataFrame data table through a program and exported in.csv format, which is convenient for users to further analyze and archive. The program uses cv2.circle() to mark the position of each cutting depth point with a red dot on the original image, and uses matplotlib to visually display the result image. Users can quickly identify the cutting depth change situation in the key area through this image, realizing visual analysis. This step greatly improves the intuitiveness and practicality of the data and provides a convenient analysis means for users.

[0094] As a preferred embodiment, as Figure 4 shown, taking the example of randomly selecting 3 - 5 points by a traditional method of using a feeler gauge to calculate the average value, in this paper, five points of cutting depth are randomly selected from the test data to simulate the five data measured by an actual feeler gauge, which are 45.73mm, 39.57mm, 33.01mm, 36.78mm, and 34.99mm respectively, and their average value is 38.02mm. The average value of the actual cutting depth obtained by the method proposed in this paper is 32.24mm, and the reduced error amount is 17.92%.

[0095] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0096] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0097] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units. They may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0098] As described above, the above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all of them should be covered by the protection scope of this application.

Claims

1. An automated measurement method for rock cutting depth, characterized in that, The specific steps include: Step 1: Obtain CT scan images of the cross-sections of rocks cut by abrasive water jets, input them into Avizo for parameter adjustment, mark the cut seam area, and construct a three-dimensional digital core model; Step 2: Obtain a three-dimensional cut seam model, obtain the side image of the cut seam, perform binary processing on the side image of the cut seam, obtain the pixel matrix of the side image of the cut seam, and obtain the coordinate pixel set of the cut seam area; Step 3: Perform closing operation on the side image of the cut seam, scan each column of the side image of the cut seam, obtain the set of vertical coordinates of zero-pixel points in each column, and respectively obtain the maximum and minimum vertical coordinate values of each column; Step 4: Obtain the zero-pixel point number in each column, obtain the column with the most zero-pixel points and measure the actual depth of this column, and obtain the corresponding ratio between the pixel point number and the actual depth; Step 5: Obtain the actual depth and cut seam length of each column, draw the actual depth table and cut depth curve and output them, and obtain the average depth of the cut depth.

2. The automated measurement method for rock cutting depth according to claim 1, wherein: Clean the surface of the rock cut by abrasive water jets and perform CT scanning to obtain multiple groups of cutting cross-sections. Import the cutting cross-section data into Avizo, crop all the cutting cross-sections to remove the blank areas, process the cutting cross-sections through the BoxFilter filtering algorithm in Avizo, where the filtering intensity of the BoxFilter filtering algorithm is between 2 and 5. Perform threshold segmentation on the cutting cross-sections through Avizo. During the threshold segmentation process, manually adjust the intensity range parameter to generate a binary cutting cross-section, mark the cut seam area, manually adjust the opacity mapping parameter and lighting parameter respectively, and construct a three-dimensional digital core model through Avizo with the cutting cross-section data.

3. The automated measurement method for rock cutting depth according to claim 2, wherein: Adjust the direction of the three-dimensional digital core model so that the cut seam direction is upward. Automatically extract the three-dimensional cut seam model from the three-dimensional digital core model through the extraction function of Avizo and hide the three-dimensional digital core model to obtain the side image of the cut seam. The side image of the cut seam is a side view perpendicular to the cutting path direction of the cut seam. Perform binary processing on the side image of the cut seam, convert the background pixel values of the non-cut seam area to 255, convert the pixel values of the cut seam area to 0, obtain the pixel matrix of the side image of the cut seam. Taking the upper left corner of the side image of the cut seam as the origin, the positive x-axis direction is horizontal to the right, and the positive y-axis direction is downward numerically. One pixel point corresponds to one cell, and obtain the pixel coordinate set of the cut seam area. The formula is as follows: S = {(x, y) | I(x, y) ≠ 255} Where, S is the set of pixel positions of the cut seam area, and I(x, y) represents the pixel value of the pixel with the abscissa x and the ordinate y.

4. The automated rock cutting depth measurement method according to claim 3, characterized in that: Perform closing operation on the side of the cut seam to obtain a complete side image of the cut seam. Scan each column of the complete side image of the cut seam to obtain the set of vertical coordinates of zero-pixel points on the x-axis. The formula is as follows: S(x) = {y | I(x, y) = 0} Where, S(x) represents the set of vertical coordinates of zero-pixel points in the x-th column, y represents the vertical coordinate of the zero-pixel point in the y-th row, and I(x, y) represents the pixel value of the pixel point in the x-th column and the y-th row; Screen the set of the vertical coordinates of all zero pixels on the x-axis, and remove the columns where the set of the vertical coordinates of zero pixels is an empty set; Obtain the maximum and minimum y-axis coordinate values of each column respectively, and the basis formula is as follows: y max (x) = MAX[S(x)] y min (x) = MIN[S(x)] Among them, y max (x) represents the maximum ordinate value in the set S(x), y min (x) represents the minimum ordinate value in the set S(x), MAX represents the function of selecting the maximum value, MIN represents the function of selecting the minimum value, and S(x) represents the set of ordinate values of zero pixels in the x-th column.

5. The automated measurement method for rock cutting depth according to claim 4, wherein: According to the scanning result of each column, obtain the number of zero pixels in each column, and the basis formula is as follows: Δy(x) = y max (x) - y min (x) where Δy(x) represents the number of zero pixels in the x-th column, and y max (x) represents the maximum ordinate value in the set S(x), and y min (x) represents the minimum ordinate value in the set S(x); Obtain the column with the largest number of zero pixels, and measure the actual depth of this column through the scale function of Avizo, and obtain the corresponding ratio of the number of pixels to the actual depth, and the basis formula is as follows: Where γ is the corresponding ratio, Δy represents the number of zero pixels in the column with the largest number of zero pixels, and Y represents the actual depth of the column with the largest number of zero pixels.

6. The automated rock cutting depth measurement method according to claim 5, characterized in that: Obtain the actual depth of each column respectively, and the basis formula is as follows: γ·Δy(x) = Y(x) Where Y(x) represents the actual depth of the x-th column, Δy(x) represents the number of zero pixels in the x-th column, and γ is the corresponding ratio; Output the actual depths of all columns in the form of a table; Obtain the number of the set of the vertical coordinates of zero pixels, and construct the crack length, and the basis formula is as follows: L = γ·|S(x)| Where L is the crack length, γ is the corresponding ratio, and |S(x)| is the number of the set of the vertical coordinates of zero pixels; Draw and output the cutting depth curve according to the actual depths of all columns, with the crack length as the abscissa and the actual depth of the crack as the ordinate, and obtain the average depth of the cutting seam.

Images