Mine blasting optimization method and system based on artificial intelligence

Abstract

The invention discloses a mine blasting optimization method and system based on artificial intelligence, and relates to the technical field of mine blasting. Acquiring historical blasting data, constructing a three-dimensional twinborn model by combining the geological lithology information, acquiring a first effect set of each blasting point under different geological lithology information under the condition that the blasting parameter set is not changed in the three-dimensional twinborn model, and acquiring a second effect set of each blasting point under the condition that the geological lithology information is not changed in the three-dimensional twinborn model; according to a first effect set of each blasting point under different blasting parameter sets and a second effect set of each blasting point under different blasting parameter sets, constructing a mine blasting scheme generation model by combining the first effect set and the second effect set, obtaining an expected blasting effect and inputting the expected blasting effect into the scheme generation model to obtain a recommended blasting scheme; according to the technical scheme, the targeted blasting scheme can be provided for mine blasting by combining the geological conditions of the mine, the cost of manually planning the blasting scheme can be effectively reduced, and the efficiency of generating the blasting scheme is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mine blasting, and in particular to a mine blasting optimization method and system based on artificial intelligence. Background Art

[0002] Artificial intelligence-based mine blasting optimization is a comprehensive solution that integrates advanced technologies and intelligent algorithms. It aims to improve the efficiency, safety, and economy of mine blasting. By leveraging big data, machine learning, and other technologies, it can optimize each link in the mine blasting process, automatically generate the optimal blasting plan, and guide on-site operations to maximize blasting results.

[0003] In the existing technology, the optimization of mine blasting is mostly based on its historical blasting data. There are two problems. First, the influence of different geological conditions on explosive explosion is ignored. Second, the sample size of historical blasting data is insufficient to provide a reference for various blasting conditions. In addition, in the existing technology, the blasting effect is mostly difficult to predict, and it is impossible to provide targeted blasting solutions according to user needs. For this reason, the present invention provides a mine blasting optimization method and system based on artificial intelligence. Summary of the Invention

[0004] The purpose of the present invention is to provide a mine blasting optimization method and system based on artificial intelligence.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A mine blasting optimization system based on artificial intelligence includes the following modules:

[0006] The data acquisition module is used to obtain the mine's historical blasting data and build a corresponding 3D twin model based on geological and lithological information;

[0007] The first analysis module is used to obtain a number of blasting points and their corresponding blasting areas in the three-dimensional twin model, and obtain a first effect set of each blasting point under different geological and lithological information under the condition that the blasting parameter set remains unchanged;

[0008] The second analysis module is used to obtain a second effect set of each blasting point under different blasting parameter sets under the condition that the geological lithology information remains unchanged;

[0009] The solution generation module is used to construct a mine blasting solution generation model by combining the obtained first effect set and second effect set, obtain the user's expected blasting effect, and input it into the solution generation model to obtain the corresponding recommended blasting solution.

[0010] Furthermore, the process of obtaining historical blasting data from the mine and combining it with geological and lithological information to construct a corresponding 3D twin model includes:

[0011] The historical blasting data includes drilling parameters, charging parameters, detonation parameters, blasting range, and blasting degree; the geological lithology information includes rock type, geological age, rock composition, rock structure, weathering degree, and hardness;

[0012] 3D geological modeling technology is used to construct a 3D geological model of the mine based on geological and lithological information. Based on historical blasting data and the 3D geological model, simulation software is used to simulate the mine blasting process. By adjusting the simulation parameters to make the simulation results consistent with the historical blasting data, a 3D twin model of the mine is generated based on the 3D geological model and simulation.

[0013] Furthermore, the process of obtaining several blasting points and their corresponding blasting areas in the 3D twin model includes:

[0014] Obtain a drill hole layout diagram in the 3D twin model. The drill hole layout diagram refers to the distribution of the drill holes preset before the mine blasting operation. Obtain each edge drill hole in the drill hole layout diagram and randomly select several edge drill holes as blasting points.

[0015] Obtaining rock fragmentation distribution after mine blasting corresponding to the drilling layout diagram, wherein the rock fragmentation distribution includes a large-piece ratio and a small-piece ratio;

[0016] With the blasting point as the center and the preset fixed distances R, 2R, 3R, ..., nR as the radius, circles are drawn outward in sequence to obtain the local areas corresponding to the preset fixed distances, and the local large block rate in each local area is obtained, where n is a natural number greater than 1;

[0017] The local large block rates of adjacent local areas are compared. When the local large block rate of the local area corresponding to nR is greater than the local large block rate of the local area corresponding to (n-1)R, the circular area constructed with the blasting point as the center and (n-1)R as the radius will be used as the blasting area of ​​the blasting point.

[0018] Furthermore, the process of obtaining the first effect set of each blasting point under different geological and lithological information under the condition that the blasting parameter set remains unchanged includes:

[0019] The blasting parameter set includes drilling parameters, charging parameters, and detonation parameters. The blasting parameter set is kept fixed in the three-dimensional twin model, and the geological lithology information is continuously changed using an exhaustive method. The mine blasting process under different geological lithology information is simulated using simulation software to obtain different first effect sets for each blasting point;

[0020] The first effect set includes the blasting area of ​​the blasting region of each blasting point, and the large block rate and small block rate in the blasting region of each blasting point. The obtained first effect set is bound to its corresponding geological lithology information and blasting parameter set.

[0021] Furthermore, the process of obtaining the second effect set of each blasting point under different blasting parameter sets under the condition that the geological lithology information remains unchanged includes:

[0022] In the 3D twin model, the geological and lithological information is kept fixed, and the blasting parameter set is continuously changed using the exhaustive method. The mine blasting process under different blasting parameter sets is simulated using simulation software to obtain different second effect sets for each blasting point.

[0023] The second effect set includes the blasting area of ​​the blasting region of each blasting point, and the large block rate and small block rate in the blasting region of each blasting point. The obtained second effect set is bound to its corresponding geological lithology information and blasting parameter set.

[0024] Furthermore, the process of constructing a mine blasting solution generation model by combining the obtained first effect set and the second effect set includes:

[0025] generating a model building set according to the first effect set and the second effect set, wherein the model building set includes different geological and lithological information and effect sets and their corresponding blasting parameter sets, wherein the effect set includes the first effect set and the second effect set, and dividing the model building set into a training set and a test set;

[0026] Constructing a convolutional neural network, using different geological and lithological information and effect sets in the training set as input data of the convolutional neural network, and using the corresponding blasting parameter sets in the training set as output data of the convolutional neural network, and training the convolutional neural network to obtain an initial convolutional neural network;

[0027] The initial convolutional neural network is model verified using the test set, and the initial convolutional neural network with a test error threshold less than or equal to the preset value is output as the solution generation model.

[0028] Furthermore, the process of obtaining the user's expected blasting effect and inputting it into the solution generation model to obtain the corresponding recommended blasting solution includes:

[0029] The expected blasting effect refers to the blasting effect that the user expects to achieve in the mine blasting operation, including the expected blasting area, expected large block rate, and expected small block rate of a single drill hole. The expected effect set is generated by combining the geological and lithological information of the mine;

[0030] The expected effect set is input into the scheme generation model, and the scheme generation model is used to output the corresponding recommended blasting scheme according to the expected effect set. The recommended blasting scheme includes drilling parameters, charging parameters, and detonation parameters, and the recommended blasting scheme is fed back to the user.

[0031] The mine blasting optimization method based on artificial intelligence includes the following steps:

[0032] Step S1: Obtain historical blasting data of the mine and build a corresponding 3D twin model based on geological and lithological information;

[0033] Step S2: obtaining a number of blasting points and their corresponding blasting areas in the 3D twin model, and obtaining a first effect set of each blasting point under different geological and lithological information under the condition that the blasting parameter set remains unchanged;

[0034] Step S3: obtaining a second effect set of each blasting point under different blasting parameter sets under the condition that the geological lithology information remains unchanged;

[0035] Step S4: constructing a mine blasting solution generation model by combining the first effect set and the second effect set, obtaining the user's expected blasting effect, and inputting it into the solution generation model to obtain a corresponding recommended blasting solution.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention collects historical blasting data of mines and combines it with geological and lithological information. It uses 3D geological modeling technology and simulation software to construct a 3D twin model of mine blasting, which can simulate mine blasting operations in a virtual space.

[0038] By conducting quantitative analysis in a three-dimensional twin model, the impact of geology on mine blasting can be determined by continuously changing geological conditions while keeping blasting parameters constant. Secondly, the impact of blasting parameters on mine blasting can be determined by continuously changing blasting parameters while keeping geological conditions constant. The specific impact is reflected in the blasting area, large block rate, and small block rate of a single borehole. This allows the complex mine blasting effects to be represented through quantitative data.

[0039] Based on this, a mine blasting scheme generation model is constructed. The scheme generation model can directly generate corresponding recommended blasting schemes according to the user's expected blasting area, large block rate, and small block rate. This is conducive to providing targeted blasting schemes for mine blasting based on the geological conditions of the mine, which can effectively reduce the cost of manual planning of blasting schemes and improve the efficiency of blasting scheme generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0041] like Figure 1 As shown in the figure, the mine blasting optimization system based on artificial intelligence includes the following modules:

[0042] The data acquisition module is used to obtain the mine's historical blasting data and build a corresponding 3D twin model based on geological and lithological information;

[0043] The first analysis module is used to obtain a number of blasting points and their corresponding blasting areas in the three-dimensional twin model, and obtain a first effect set of each blasting point under different geological and lithological information under the condition that the blasting parameter set remains unchanged;

[0044] The second analysis module is used to obtain a second effect set of each blasting point under different blasting parameter sets under the condition that the geological lithology information remains unchanged;

[0045] The solution generation module is used to construct a mine blasting solution generation model by combining the obtained first effect set and second effect set, obtain the user's expected blasting effect, and input it into the solution generation model to obtain the corresponding recommended blasting solution.

[0046] It should be further explained that, in the specific implementation process, the process of obtaining the historical blasting data of the mine and combining it with geological and lithological information to build the corresponding 3D twin model includes:

[0047] The historical blasting data is a comprehensive concept that covers various parameters and indicators in mine blasting operations, such as drilling parameters, charging parameters, detonation parameters, blasting range, and blasting degree;

[0048] The drilling parameters include hole depth, hole diameter, hole spacing and row spacing; the charging parameters include charging amount, charging structure, charging density and length; the detonation parameters include detonation method, detonation sequence and time difference; the blasting range refers to the range and area of ​​rock fragmentation after blasting; the blasting degree refers to the rock fragmentation distribution after blasting, including large block rate and small block rate;

[0049] The geological lithology information refers to the characteristics and properties of the rocks blasted by various historical blasting data, including rock type, geological age, rock composition, rock structure, weathering degree, and hardness;

[0050] Using 3D geological modeling technology, a 3D geological model of the mine is constructed based on geological and lithological information. This model includes descriptions of the morphology, structure, and properties of the geological body. Based on historical blasting data and the 3D geological model, simulation software is used to simulate the mine blasting process, including the explosive explosion process, rock crushing process, and the throwing and accumulation process after blasting.

[0051] By adjusting the simulation parameters to make the simulation results consistent with the historical blasting data, a three-dimensional twin model of the mine is obtained based on the three-dimensional geological model and simulation.

[0052] It should be further explained that, in the specific implementation process, the process of obtaining several blasting points and their corresponding blasting areas in the 3D twin model includes:

[0053] In the 3D twin model, a drill hole layout diagram for the mine blasting operation is obtained. The drill hole layout diagram refers to the distribution of the drill holes planned before the mine blasting operation. In the drill hole layout diagram, each drill hole at the edge is obtained and recorded as an edge drill hole. There are no other drill holes in the outward direction of the edge drill hole. The outward direction is the direction away from the center of the drill hole layout diagram.

[0054] In the drilling layout diagram, the distribution locations of several edge drill holes are randomly selected as blasting points, and the corresponding blasting areas are obtained with each blasting point as the center;

[0055] Taking any blasting point as an example, in the 3D twin model, the rock fragmentation distribution of the mine blasting operation corresponding to the drill hole layout diagram is obtained. The rock fragmentation distribution refers to the distribution of rock blocks of different sizes formed during the rock crushing or accumulation process, including the large block ratio and small block ratio.

[0056] In mining blasting operations, the crushed rocks formed after the blasting of a single borehole will be thrown and accumulated in all directions. Large crushed rocks tend to fall nearby, while small crushed rocks tend to fall far away. Based on this law, the effective blasting area can be determined by analyzing the changes in the large-piece rate around the borehole and used as the corresponding blasting area.

[0057] With the blasting point as the center and the preset fixed distances R, 2R, 3R, ..., nR as the radius, circles are drawn outward in sequence, where n is a natural number greater than 1. The local large block rate in the local area corresponding to each preset fixed distance is obtained. The local area corresponding to the preset fixed distance R is a circle, and the local areas corresponding to other preset fixed distances are rings.

[0058] Under normal circumstances, the local large-block rate will decrease as the preset fixed distance increases. When the local large-block rate increases instead of decreasing, it means that the corresponding area contains large pieces of gravel formed by other drilling and blasting, and the effective blasting area of ​​the current drilling hole is within this range.

[0059] The local large block rates of adjacent local areas are continuously compared. When the local large block rate of the local area corresponding to nR is greater than the local large block rate of the local area corresponding to (n-1)R, the circular area constructed with the blasting point as the center and (n-1)R as the radius will be used as the blasting area of ​​the blasting point.

[0060] It should be further explained that, in a specific implementation process, the process of obtaining the first effect set of each blasting point under different geological and lithological information under the condition that the blasting parameter set remains unchanged includes:

[0061] The blasting parameter set includes drilling parameters, charging parameters, and detonation parameters. In the three-dimensional twin model, the blasting parameter set is kept fixed, and the geological and lithological information in the three-dimensional twin model is continuously changed using an exhaustive method. The mine blasting process under different geological and lithological information is simulated using simulation software to obtain different first effect sets for each blasting point;

[0062] The first effect set includes two items, one is the area of ​​the blasting area corresponding to each blasting point, recorded as the blasting area, and the other is the large block rate and small block rate in the blasting area corresponding to each blasting point. The obtained first effect set is bound to its corresponding geological lithology information and blasting parameter set.

[0063] It should be further explained that, in a specific implementation process, the process of obtaining the second effect set of each blasting point under different blasting parameter sets under the condition that the geological lithology information remains unchanged includes:

[0064] In the 3D twin model, the geological and lithological information is kept fixed, and the blasting parameter set in the 3D twin model is continuously changed using an exhaustive method. The mine blasting process under different blasting parameter sets is simulated using simulation software to obtain different second effect sets for each blasting point.

[0065] Since the blasting parameter set includes drilling parameters, charging parameters, and detonation parameters, changes to the blasting parameter set include changing the drilling parameters alone, changing the charging parameters alone, changing the detonation parameters alone, and changing two or more parameters simultaneously;

[0066] The second effect set includes the blasting area of ​​the blasting region corresponding to each blasting point, and the large block rate and small block rate in the blasting region corresponding to each blasting point, and the obtained second effect set is bound to its corresponding geological lithology information and blasting parameter set.

[0067] It should be further explained that, in a specific implementation process, the process of constructing a mine blasting scheme generation model by combining the obtained first effect set and the second effect set includes:

[0068] generating a model building set according to the obtained first effect set and second effect set, wherein the model building set includes different geological and lithological information and effect sets and their corresponding blasting parameter sets, wherein the effect set includes the first effect set and the second effect set, and dividing the generated model building set into a training set and a test set;

[0069] Constructing a convolutional neural network, using different geological and lithological information and effect sets in the training set as input data of the convolutional neural network, and using the corresponding blasting parameter sets in the training set as output data of the convolutional neural network, and training the convolutional neural network to obtain an initial convolutional neural network;

[0070] The initial convolutional neural network is model verified using the test set, and the initial convolutional neural network with a test error threshold less than or equal to the preset value is output as the corresponding solution generation model.

[0071] It should be further explained that, in the specific implementation process, the process of obtaining the user's expected blasting effect and inputting it into the solution generation model to obtain the corresponding recommended blasting solution includes:

[0072] The expected blasting effect refers to the blasting effect that the user expects to achieve in subsequent mine blasting operations, including the expected blasting area, expected large block rate, and expected small block rate of a single drill hole. The corresponding expected effect set is generated in combination with the geological and lithological information of the mine;

[0073] The obtained expected effect set is input into the constructed scheme generation model. The constructed scheme generation model outputs the corresponding blasting parameter set based on the input expected effect set, and marks it as a recommended blasting scheme. The recommended blasting scheme includes drilling parameters, charging parameters, and detonation parameters. The obtained recommended blasting scheme is fed back to the user, and the user is advised to perform mine blasting operations according to the recommended blasting scheme.

[0074] An embodiment of the present invention also includes a mine blasting optimization method based on artificial intelligence, comprising the following steps:

[0075] Step S1: Obtain historical blasting data of the mine and build a corresponding 3D twin model based on geological and lithological information;

[0076] Step S2: obtaining a number of blasting points and their corresponding blasting areas in the 3D twin model, and obtaining a first effect set of each blasting point under different geological and lithological information under the condition that the blasting parameter set remains unchanged;

[0077] Step S3: obtaining a second effect set of each blasting point under different blasting parameter sets under the condition that the geological lithology information remains unchanged;

[0078] Step S4: constructing a mine blasting solution generation model by combining the first effect set and the second effect set, obtaining the user's expected blasting effect, and inputting it into the solution generation model to obtain a corresponding recommended blasting solution.

[0079] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. The mine blasting optimization system based on artificial intelligence is characterized by: Includes the following modules: The data acquisition module is used to obtain the mine's historical blasting data and build a corresponding 3D twin model based on geological and lithological information; The first analysis module is used to obtain a number of blasting points and their corresponding blasting areas in the three-dimensional twin model, and obtain a first effect set of each blasting point under different geological and lithological information under the condition that the blasting parameter set remains unchanged; The second analysis module is used to obtain a second effect set of each blasting point under different blasting parameter sets under the condition that the geological lithology information remains unchanged; The solution generation module is used to construct a mine blasting solution generation model by combining the obtained first effect set and second effect set, obtain the user's expected blasting effect, and input it into the solution generation model to obtain the corresponding recommended blasting solution.

2. The artificial intelligence-based mine blasting optimization system according to claim 1 is characterized in that: The process of acquiring historical blasting data and combining it with geological and lithological information to construct a 3D twin model includes: The historical blasting data includes drilling parameters, charging parameters, detonation parameters, blasting range, and blasting degree; the geological lithology information includes rock type, geological age, rock composition, rock structure, weathering degree, and hardness; 3D geological modeling technology is used to construct a 3D geological model of the mine based on geological and lithological information. Based on historical blasting data and the 3D geological model, simulation software is used to simulate the mine blasting process. By adjusting the simulation parameters to make the simulation results consistent with the historical blasting data, a 3D twin model of the mine is generated based on the 3D geological model and simulation.

3. The artificial intelligence-based mine blasting optimization system according to claim 2, characterized in that: The process of obtaining several blasting points and their corresponding blasting areas in the 3D twin model includes: Obtain a drill hole layout diagram in the 3D twin model. The drill hole layout diagram refers to the distribution of the drill holes preset before the mine blasting operation. Obtain each edge drill hole in the drill hole layout diagram and randomly select several edge drill holes as blasting points. Obtaining rock fragmentation distribution after mine blasting corresponding to the drilling layout diagram, wherein the rock fragmentation distribution includes a large-piece ratio and a small-piece ratio; With the blasting point as the center and the preset fixed distances R, 2R, 3R, ..., nR as the radius, circles are drawn outward in sequence to obtain the local areas corresponding to the preset fixed distances, and the local large block rate in each local area is obtained, where n is a natural number greater than 1; The local large block rates of adjacent local areas are compared. When the local large block rate of the local area corresponding to nR is greater than the local large block rate of the local area corresponding to (n-1)R, the circular area constructed with the blasting point as the center and (n-1)R as the radius will be used as the blasting area of ​​the blasting point.

4. The artificial intelligence-based mine blasting optimization system according to claim 3 is characterized in that: The process of obtaining the first effect set of each blasting point under different geological and lithological information includes: The blasting parameter set includes drilling parameters, charging parameters, and detonation parameters. The blasting parameter set is kept fixed in the three-dimensional twin model, and the geological lithology information is continuously changed using an exhaustive method. The mine blasting process under different geological lithology information is simulated using simulation software to obtain different first effect sets for each blasting point; The first effect set includes the blasting area of ​​the blasting region of each blasting point, and the large block rate and small block rate in the blasting region of each blasting point. The obtained first effect set is bound to its corresponding geological lithology information and blasting parameter set.

5. The artificial intelligence-based mine blasting optimization system according to claim 4 is characterized in that: The process of obtaining the second effect set of each blasting point under different blasting parameter sets includes: In the 3D twin model, the geological and lithological information is kept fixed, and the blasting parameter set is continuously changed using the exhaustive method. The mine blasting process under different blasting parameter sets is simulated using simulation software to obtain different second effect sets for each blasting point. The second effect set includes the blasting area of ​​the blasting region of each blasting point, and the large block rate and small block rate in the blasting region of each blasting point. The obtained second effect set is bound to its corresponding geological lithology information and blasting parameter set.

6. The artificial intelligence-based mine blasting optimization system according to claim 5, characterized in that: The process of building a solution generation model by combining the first effect set and the second effect set includes: generating a model building set according to the first effect set and the second effect set, wherein the model building set includes different geological and lithological information and effect sets and their corresponding blasting parameter sets, wherein the effect set includes the first effect set and the second effect set, and dividing the model building set into a training set and a test set; Constructing a convolutional neural network, using different geological and lithological information and effect sets in the training set as input data of the convolutional neural network, and using the corresponding blasting parameter sets in the training set as output data of the convolutional neural network, and training the convolutional neural network to obtain an initial convolutional neural network; The initial convolutional neural network is model verified using the test set, and the initial convolutional neural network with a test error threshold less than or equal to the preset value is output as the solution generation model.

7. The artificial intelligence-based mine blasting optimization system according to claim 6, characterized in that: The process of obtaining the expected blasting effect and its corresponding recommended blasting plan includes: The expected blasting effect refers to the blasting effect that the user expects to achieve in the mine blasting operation, including the expected blasting area, expected large block rate, and expected small block rate of a single drill hole. The expected effect set is generated by combining the geological and lithological information of the mine; The expected effect set is input into the scheme generation model, and the scheme generation model is used to output the corresponding recommended blasting scheme according to the expected effect set. The recommended blasting scheme includes drilling parameters, charging parameters, and detonation parameters, and the recommended blasting scheme is fed back to the user.

8. An artificial intelligence-based mine blasting optimization method, which is implemented based on the artificial intelligence-based mine blasting optimization system according to any one of claims 1 to 7, characterized in that: The method comprises: Step S1: Obtain historical blasting data of the mine and build a corresponding 3D twin model based on geological and lithological information; Step S2: obtaining a number of blasting points and their corresponding blasting areas in the 3D twin model, and obtaining a first effect set of each blasting point under different geological and lithological information under the condition that the blasting parameter set remains unchanged; Step S3: obtaining a second effect set of each blasting point under different blasting parameter sets under the condition that the geological lithology information remains unchanged; Step S4: constructing a mine blasting solution generation model by combining the first effect set and the second effect set, obtaining the user's expected blasting effect, and inputting it into the solution generation model to obtain a corresponding recommended blasting solution.

Images