Intelligent segmentation estimation method for volume of tailing heap in karst depression tailing reservoir

Abstract

The invention discloses an intelligent segmentation estimation method for the volume of a tailing pile in a karst depression tailing reservoir, and belongs to the technical field of environmental geology measurement. Comprising the steps of data collection; carrying out digital modeling; carrying out distribution analysis on tailings; the whole area is divided into a plurality of sub-areas with similar characteristics according to distribution characteristics and topographic changes of tailings. Each sub-region can be further subdivided into smaller parts according to the internal attributes of the sub-region so as to improve the estimation precision; and establishing an appropriate mathematical model for each segment to estimate the volume of tailings in the region. The models comprise a geometry approximation model, a polynomial fitting model and a regression analysis model; and by utilizing the established mathematical model and combining the specific parameters of each section, obtaining the volume of the tailings in the sections, and summarizing to obtain the total quantity of the tailings. According to the method, multiple mathematical models are applied to capture the complex mode of tailing distribution, and the accuracy of an estimation result is improved.

Description

Technical Field

[0001] The invention relates to the technical field of environmental geological measurement, and more particularly to an intelligent segmented estimation method for the volume of a tailings pile in a tailings reservoir in a karst depression. Background Art

[0002] Karst depression is a relatively common landform type in karst areas. Due to its special topographic and geomorphological characteristics, it is often used as a natural tailings reservoir to store tailings and other wastes generated during mineral mining and smelting.

[0003] However, traditional tailings volume estimation mainly relies on simple geometric models or manual measurements, which are difficult to accurately capture the true shape of complex terrain and irregular deposits. Some commonly used single mathematical models, such as linear regression, assume that there is a linear relationship between input and output, but in actual applications, tailings distribution often exhibits complex nonlinear characteristics. When multiple influencing factors need to be considered (such as topography, climate, geological structure, etc.), a single model cannot effectively integrate this information, which may lead to a decrease in prediction performance.

[0004] Therefore, how to provide an accurate intelligent segmented estimation method for the volume of tailings piles in karst depression tailings reservoirs is a problem that technical personnel in this field urgently need to solve. Summary of the invention

[0005] In view of this, the present invention provides an intelligent segmented estimation method for the volume of tailings piles in a karst depression tailings reservoir to ensure that the estimation result is closer to the actual situation.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] An intelligent segmented estimation method for the volume of tailings pile in a karst depression tailings reservoir comprises:

[0008] Collect information on karst depressions to be estimated;

[0009] Based on the information of the karst depression to be estimated, a three-dimensional digital model of the karst depression is created;

[0010] Conduct tailings distribution analysis to obtain the distribution characteristics of tailings and terrain changes;

[0011] According to the distribution characteristics of tailings and terrain changes, the three-dimensional digital model is preliminarily segmented;

[0012] Establish a corresponding mathematical model for each segment and estimate the volume of tailings in each segment;

[0013] The total tailings volume of the karst depression to be estimated is obtained based on the volume of tailings in each section.

[0014] Furthermore, the collecting of the karst depression information to be estimated includes:

[0015] Obtain high-resolution images of the karst depression and its surroundings through satellite images, drone aerial photography or LiDAR scanning;

[0016] The morphological features, soil types, and vegetation coverage information of the karst depression were obtained by means of web crawlers.

[0017] Furthermore, the three-dimensional digital model of the karst depression is created based on the karst depression information to be estimated, including:

[0018] Use GIS software to create a three-dimensional digital model of the karst depression information to be estimated;

[0019] The three-dimensional digital model includes the shapes of the bottom and the side walls.

[0020] Furthermore, tailings distribution analysis is conducted to obtain the distribution characteristics of tailings and terrain changes, including: spatial statistical analysis and morphological analysis.

[0021] Furthermore, the spatial statistical analysis includes applying the Kriging interpolation method to calculate the tailings thickness, and the formula is:

[0022]

[0023] In the formula, λ i is the weight coefficient, t(x i ) is the known tailings thickness and n is a known quantity.

[0024] Further, the morphological analysis includes:

[0025] Use opening and closing operations to clean up noise in three-dimensional digital models;

[0026] Enhance terrain boundaries using gradient operations.

[0027] Furthermore, according to the distribution characteristics of tailings and terrain changes, the K-means clustering method is used to preliminarily segment the 3D digital model, including:

[0028]

[0029] Where k is the preset number of clusters; S i is the set of all sample points in the nth cluster; μ n is the centroid position of the nth cluster; x m is a sample point in the data set.

[0030] Furthermore, a corresponding mathematical model is established for each segment to estimate the volume of tailings in each segment. The mathematical model includes:

[0031] Geometric approximation models, polynomial fitting models, and regression analysis models.

[0032] Furthermore, the total tailings volume of the karst depression to be estimated is obtained based on the volume of tailings in each segment, and the expression is:

[0033]

[0034] Where V h is the volume of the hth segment, and H is the total number of segments.

[0035] It can be known from the above technical solutions that, compared with the prior art, the present invention discloses an intelligent segmented estimation method for the volume of tailings piles in karst depression tailings ponds, including: data collection; digital modeling; tailings distribution analysis; according to the distribution characteristics of tailings and terrain changes, the entire area is divided into several sub-areas with similar characteristics. Each sub-area can be further subdivided into smaller parts according to its internal properties to improve the estimation accuracy; a suitable mathematical model is established for each segment to estimate the volume of tailings in the area. These models include geometric approximation models, polynomial fitting models, and regression analysis models; using the above-established mathematical models, combined with the specific parameters of each segment, the volume of tailings in the segment is obtained, and the total amount of tailings is summarized. The present invention applies a variety of mathematical models to capture the complex patterns of tailings distribution, thereby improving the accuracy of the estimation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0037] Figure 1 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0038] 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 only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] See also Figure 1 The embodiment of the present invention discloses an intelligent segmented estimation method for the volume of tailings pile in a tailings reservoir in a karst depression, comprising:

[0040] Collect information on karst depressions to be estimated;

[0041] Based on the information of the karst depression to be estimated, a three-dimensional digital model of the karst depression is created;

[0042] Conduct tailings distribution analysis to obtain the distribution characteristics of tailings and terrain changes;

[0043] According to the distribution characteristics of tailings and terrain changes, the three-dimensional digital model is preliminarily segmented;

[0044] Establish a corresponding mathematical model for each segment and estimate the volume of tailings in each segment;

[0045] The total tailings volume of the karst depression to be estimated is obtained based on the volume of tailings in each section.

[0046] In a specific embodiment, the collecting of karst depression information to be estimated includes:

[0047] Obtain high-resolution images of the karst depression and its surroundings through satellite images, drone aerial photography or LiDAR scanning;

[0048] The morphological features, soil types, and vegetation coverage information of the karst depression were obtained by means of web crawlers.

[0049] In a specific embodiment, the step of creating a three-dimensional digital model of a karst depression based on the karst depression information to be estimated includes:

[0050] Use GIS software to create a three-dimensional digital model of the karst depression information to be estimated;

[0051] The three-dimensional digital model includes the shapes of the bottom and the side walls.

[0052] In a specific embodiment, tailings distribution analysis is performed to obtain the distribution characteristics of tailings and terrain changes, including: spatial statistical analysis and morphological analysis.

[0053] In a specific embodiment, the spatial statistical analysis includes applying the Kriging interpolation method to calculate the tailing thickness, and the formula is:

[0054]

[0055] In the formula, λ i is the weight coefficient, t(x i ) is the known tailings thickness and n is a known quantity.

[0056] In a specific embodiment, the morphological analysis comprises:

[0057] Use opening and closing operations to clean up noise in three-dimensional digital models;

[0058] Enhance terrain boundaries using gradient operations.

[0059] Specifically, the definition of opening is that the operation of first corroding and then dilating is called opening operation. Its function is to remove small protrusions and burrs, smooth the contour but not significantly change its area.

[0060] Specifically, the definition of closing operation is the operation of dilation followed by erosion. Its function is to fill small holes and smooth depressions, keeping the overall shape unchanged.

[0061] Specifically, calculating the gradient of an image can help highlight boundary information.

[0062] In this embodiment, opening and closing operations are used to clean up the noise in the three-dimensional digital model to make the terrain features clearer; gradient operations are used to emphasize terrain boundaries, which can effectively extract useful information from complex geospatial data and assist in subsequent tailings volume estimation and other geological analysis tasks.

[0063] Specifically, image processing algorithms (such as SLIC, Simple Linear Iterative Clustering) are used to extract multi-dimensional features from super-pixel regions to obtain the morphological features, soil types, and vegetation coverage information of the karst depression, including;

[0064] For each superpixel, not only color features (such as RGB values) should be considered, but also terrain features (such as height, slope), texture features, and other geographical factors that may affect the distribution of tailings (such as distance from water sources). The morphological features, soil type, and vegetation coverage information of the karst depression are obtained. This step helps to more accurately distinguish different types of tailings deposition areas;

[0065] Specifically, one or more representative sample points are selected from each superpixel to ensure that all types of tailings accumulation situations are covered.

[0066] In a specific embodiment, according to the distribution characteristics of tailings and terrain changes, the three-dimensional digital model is initially segmented using the K-means clustering method, including:

[0067]

[0068] Where k is the preset number of clusters; S i is the set of all sample points in the nth cluster; μ n is the centroid position of the nth cluster; x m is a sample point in the data set.

[0069] In a specific embodiment, a corresponding mathematical model is established for each segment to estimate the volume of tailings in each segment. The mathematical model includes:

[0070] The geometric approximation model is expressed as:

[0071] For situations like cone stacking:

[0072]

[0073] Where r is the radius of the base and h is the height.

[0074] For upright columnar deposits:

[0075] V prism =A base ×h;

[0076] Among them, A base is the base area and h is the height.

[0077] The polynomial fitting model is expressed as:

[0078] P(x)=a0+a1x+a2x 2 +...+a n x n ;

[0079] Where a0, a1, ..., a n are the coefficients of the polynomial, determined by the least squares method.

[0080] The regression analysis model is expressed as:

[0081] y=β0+β1x+∈;

[0082] Where β0 is the intercept, β1 is the slope, and ∈ is the error term.

[0083] Specifically, choosing a suitable mathematical model is crucial for estimating the tailing volume in karst depressions, which not only affects the accuracy of the estimation, but also the interpretability and computational efficiency of the model. The following are the factors and steps that can be considered when choosing a suitable mathematical model:

[0084] If the tailings accumulation forms a regular geometric shape (such as a cone or prism), a simple geometric approximation model can be directly applied for rapid estimation.

[0085] For those cases where there is a continuous but nonlinear trend with position, a polynomial fit can be tried to capture this variation.

[0086] When multiple factors need to be considered comprehensively (such as topography, climate, geological structure, etc.), a multivariate regression model can be constructed to deal with the influence of multiple independent variables at the same time.

[0087] In a specific embodiment, the total tailings volume of the karst depression to be estimated is obtained based on the volume of the tailings in each segment, and the expression is:

[0088]

[0089] Where V h is the volume of the hth segment, and H is the total number of segments.

[0090] Through the above steps, the estimation of the volume of karst depression tailings was completed, which not only improved the accuracy of the results, but also provided a scientific basis for subsequent environmental protection measures.

[0091] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0092] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent segmented estimation method for the volume of tailings pile in a karst depression tailings reservoir, characterized in that: include: Collect information on karst depressions to be estimated; Based on the information of the karst depression to be estimated, a three-dimensional digital model of the karst depression is created; Conduct tailings distribution analysis to obtain the distribution characteristics of tailings and terrain changes; According to the distribution characteristics of tailings and terrain changes, the three-dimensional digital model is preliminarily segmented; Establish a corresponding mathematical model for each segment and estimate the volume of tailings in each segment; The total tailings volume of the karst depression to be estimated is obtained based on the volume of tailings in each section.

2. The intelligent segmented estimation method for the volume of tailings pile in a karst depression tailings reservoir according to claim 1 is characterized in that: The collecting of the karst depression information to be estimated includes: Obtain high-resolution images of the karst depression and its surroundings through satellite images, drone aerial photography or LiDAR scanning; The morphological features, soil types, and vegetation coverage information of the karst depression were obtained by means of web crawlers.

3. The intelligent segmented estimation method for the volume of tailings pile in a karst depression tailings reservoir according to claim 1 is characterized in that: The method of creating a three-dimensional digital model of a karst depression based on the karst depression information to be estimated includes: Use GIS software to create a three-dimensional digital model of the karst depression information to be estimated; The three-dimensional digital model includes the shapes of the bottom and the side walls.

4. The intelligent segmented estimation method for the volume of tailings pile in a karst depression tailings reservoir according to claim 1 is characterized in that: Conduct tailings distribution analysis to obtain the distribution characteristics of tailings and terrain changes, including: spatial statistical analysis and morphological analysis.

5. The intelligent segmented estimation method for the volume of tailings pile in a karst depression tailings reservoir according to claim 4 is characterized in that: The spatial statistical analysis includes applying the Kriging interpolation method to calculate the tailings thickness, using the formula: In the formula, λ i is the weight coefficient, t(x i ) is the known tailings thickness and n is a known quantity.

6. The intelligent segmented estimation method for the volume of tailings pile in a karst depression tailings reservoir according to claim 4 is characterized in that: The morphological analysis includes: Use opening and closing operations to clean up noise in three-dimensional digital models; Enhance terrain boundaries using gradient operations.

7. The intelligent segmented estimation method for the volume of tailings pile in a karst depression tailings reservoir according to claim 1 is characterized in that: According to the distribution characteristics of tailings and terrain changes, the K-means clustering method is used to preliminarily segment the 3D digital model, including: Where k is the preset number of clusters; S i is the set of all sample points in the nth cluster; μ n is the centroid position of the nth cluster; x m is a sample point in the data set.

8. The intelligent segmented estimation method for the volume of tailings pile in a karst depression tailings reservoir according to claim 1 is characterized in that: A corresponding mathematical model is established for each segment to estimate the volume of tailings in each segment. The mathematical model includes: Geometric approximation models, polynomial fitting models, and regression analysis models.

9. The intelligent segmented estimation method for the volume of tailings pile in a karst depression tailings reservoir according to claim 1 is characterized in that: Based on the volume of tailings in each segment, the total tailings volume of the karst depression to be estimated is obtained, and the expression is: Where V h is the volume of the hth segment, and H is the total number of segments.

Images