Mine blasting process control optimization method and system based on big data

Abstract

The invention discloses a big data-based mine blasting process control optimization method and system, and relates to the technical field of mine blasting. Constructing a three-dimensional twinborn model of the mine, obtaining a plurality of blasting points and effective blasting areas thereof, obtaining drilling lithology information and effective blasting areas of the blasting points, constructing a charge evaluation model in combination with historical blasting parameters, and obtaining expected charge by utilizing the charge evaluation model in combination with first blasting parameters; the broken stone throwing duration of each effective blasting area is obtained, a detonation evaluation model is constructed in combination with the drilling lithology information and the historical blasting parameters, the detonation evaluation model is used for obtaining the expected detonation time difference in combination with the second blasting parameters, and recommended blasting parameters are generated according to the expected explosive loading amount and the expected detonation time difference and fed back; the corresponding expected explosive loading amount can be output according to the expected blasting area, and the explosive loading efficiency of mine blasting operation and the overall blasting effect are improved.

Description

Technical Field

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

[0002] Control and optimization of the mine blasting process is a comprehensive solution that integrates advanced technologies and intelligent algorithms. It aims to improve the efficiency and effect of mine blasting. By using technologies such as big data and machine learning, it can control and optimize each link in the mine blasting process and generate the optimal blasting plan to guide on-site operations and maximize the blasting effect. The prior art lacks an effective control method for the detonation time difference between adjacent boreholes, and cannot provide a corresponding control method according to the possible stone throwing situation caused by each borehole. If the detonation time difference is too short, the blasting effect of the next borehole will inevitably be weakened. If the detonation time difference is too long, the overall blasting efficiency will be significantly reduced. For mining blasting operations, the charge amount will directly affect the blasting effect. The existing technology lacks an effective control method for the charge amount and is unable to provide the corresponding charge amount according to the desired blasting area. In view of the shortcomings of the existing technology, the present invention provides a mining blasting process control optimization method and system based on big data. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for optimizing mine blasting process control based on big data.

[0004] The purpose of the present invention can be achieved through the following technical solutions: A mine blasting process control optimization system based on big data, comprising the following modules: The data acquisition module is used to obtain the historical blasting data of the mine, and build a corresponding three-dimensional twin model in combination with geological lithology information, and obtain several blasting points and their corresponding effective blasting areas in the three-dimensional twin model; The first evaluation module is used to obtain the drilling lithology information and effective blasting area of ​​each blasting point, and to build a corresponding charge evaluation model in combination with its historical blasting parameters to obtain the expected blasting area of ​​the mine blasting operation, and to obtain the corresponding expected charge amount by using the charge evaluation model in combination with the first blasting parameters; The second evaluation module is used to obtain the duration of the gravel throwing in each effective blasting area, and to build a corresponding detonation evaluation model in combination with the drilling lithology information and the historical blasting parameters, and to obtain the corresponding expected detonation time difference by using the detonation evaluation model in combination with the second blasting parameters; The scheme generation module is used to generate corresponding recommended blasting parameters and provide feedback based on the expected charge amount and the expected detonation time difference.

[0005] Furthermore, the process of obtaining the historical blasting data of the mine and building the corresponding 3D twin model in combination with the geological lithology information 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; The three-dimensional geological modeling technology is used to construct a corresponding three-dimensional geological model according to the geological lithology information of a single historical blasting data. The simulation software is used to simulate the mining blasting process in the three-dimensional geological model. The simulation parameters are continuously adjusted in the three-dimensional geological model until the simulation results are consistent with the corresponding historical blasting data to obtain a three-dimensional twin model.

[0006] Furthermore, the process of obtaining several blasting points and their corresponding effective blasting areas in the three-dimensional twin model includes: A drilling layout diagram under a single historical blasting data is obtained in the 3D twin model, and the distribution positions of several drilling holes are randomly selected as blasting points in the drilling layout diagram; Obtain the rock fragmentation distribution under the single historical blasting data in the three-dimensional twin model, including the large-piece rate and the small-piece rate, and draw circles outward with the single blasting point as the center and the preset fixed distances R, 2R, 3R, ..., nR as the radius in sequence; The local large block rate of the local area corresponding to each preset fixed distance is obtained, and the local large block rates between adjacent local areas of the single blasting point 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 with the single blasting point as the center and (n-1)R as the radius will be used as the effective blasting area of ​​the single blasting point.

[0007] Furthermore, the process of obtaining the borehole lithology information and effective blasting area of ​​each blasting point and building a corresponding charge evaluation model in combination with its historical blasting parameters includes: Obtaining drilling lithology information of a single blasting point based on the rock core excavated during drilling at the single blasting point, including density, porosity, joint fissure ratio, compressive strength, and tensile strength of the rock core; The area of ​​the effective blasting region corresponding to the single blasting point is taken as the effective blasting area, and the hole depth, hole diameter, charge amount, charge structure, charge density and length, and detonation method of the single blasting point in the historical blasting data are taken as the historical blasting parameters; Generate a first evaluation set according to the drilling lithology information and historical blasting parameters of different blasting points and their corresponding effective blasting areas, and divide the first evaluation set into a first training set and a first test set; Constructing a first convolutional neural network, taking different borehole lithology information and historical blasting parameters in the first training set as input data of the first convolutional neural network, and taking the corresponding effective blasting area in the first training set as output data of the first convolutional neural network; The first convolutional neural network is trained to obtain an initial first convolutional neural network, the initial first convolutional neural network is model verified using a first test set, and the initial first convolutional neural network that is less than or equal to a preset first test error threshold is output as a charge evaluation model.

[0008] Furthermore, the process of obtaining the expected blasting area of ​​the mine blasting operation and obtaining the corresponding expected charge amount by using the charge evaluation model in combination with the first blasting parameter includes: In subsequent mine blasting operations, the effective blasting area that can be achieved by a single borehole is taken as the expected blasting area, and the drilling lithology information of the single borehole is obtained to set the first blasting parameters, including the preset hole depth, hole diameter, charge structure, charge density and length, and adjustable charge amount; The drilling lithology information of the single borehole and the first blasting parameter are input into the charge evaluation model, and the corresponding effective blasting area is outputted by the charge evaluation model. The charge amount in the first blasting parameter is continuously adjusted. When the effective blasting area outputted by the charge evaluation model is equal to the expected blasting area, the charge amount at this time is used as the expected charge amount corresponding to the expected blasting area.

[0009] Furthermore, the process of obtaining the duration of rock throwing in each effective blasting area and building a corresponding detonation assessment model in combination with its drilling lithology information and historical blasting parameters includes: In the three-dimensional twin model, the time when a single blasting point starts blasting is taken as the blasting start time, and the simulated large block rate of the effective blasting area of ​​the single blasting point during the blasting process is monitored in real time, and the historical large block rate of the effective blasting area in the historical blasting data is obtained; The ratio between the simulated large block rate and the historical large block rate is taken as the gravel throwing rate in the effective blasting area, and the gravel throwing rate threshold is set. The moment when the gravel throwing rate is equal to the gravel throwing rate threshold is taken as the throwing completion moment, and the time interval between the blasting start moment and the throwing completion moment is taken as the gravel throwing duration. Generate a second evaluation set according to the drilling lithology information and historical blasting parameters of different effective blasting areas and their corresponding gravel throwing durations, and divide the second evaluation set into a second training set and a second test set; Constructing a second convolutional neural network, taking different borehole lithology information and historical blasting parameters in the second training set as input data of the second convolutional neural network, and taking the corresponding gravel throwing time in the second training set as output data of the second convolutional neural network; The second convolutional neural network is trained to obtain an initial second convolutional neural network, the initial second convolutional neural network is model verified using a second test set, and an initial second convolutional neural network that is less than or equal to a preset second test error threshold is output as a detonation assessment model.

[0010] Furthermore, the process of using the detonation assessment model in combination with the second blasting parameter to obtain the corresponding expected detonation time difference includes: In subsequent mine blasting operations, the drilling lithology information of a single borehole and the expected charge amount under the expected blasting area are obtained, and the second blasting parameters are set, including the preset hole depth, hole diameter, charge structure, charge density and length and the corresponding expected charge amount; The drilling lithology information and the second blasting parameter of the single borehole are input into the detonation assessment model, and the detonation assessment model is used to output the corresponding gravel throwing duration, and the obtained gravel throwing duration is used as the expected detonation time difference between the single borehole and the next adjacent borehole in the detonation sequence.

[0011] Furthermore, the process of generating corresponding recommended blasting parameters and providing feedback according to the expected charge amount and the expected detonation time difference includes: In the subsequent mine blasting operation, the hole spacing and row spacing of adjacent boreholes are inferred based on the expected blasting area of ​​each borehole, the expected charge amount of each borehole is obtained using the charge evaluation model, and the expected detonation time difference between two adjacent boreholes in the detonation sequence is obtained using the detonation evaluation model, and the recommended blasting parameters for the mine blasting operation are generated and fed back to relevant personnel; The recommended blasting parameters include preset hole depth, hole diameter, charge structure, charge density and length, detonation method, detonation sequence, and expected charge amount of each borehole and hole spacing, row spacing, and expected detonation time difference between adjacent boreholes.

[0012] A mine blasting process control optimization method based on big data includes the following steps: Step S1: Obtain historical blasting data of the mine, and build a corresponding three-dimensional twin model in combination with geological lithology information, and obtain several blasting points and their corresponding effective blasting areas in the three-dimensional twin model; Step S2: Obtain the drilling lithology information and effective blasting area of ​​each blasting point, and build a corresponding charge evaluation model in combination with its historical blasting parameters to obtain the expected blasting area of ​​the mine blasting operation, and use the charge evaluation model in combination with the first blasting parameter to obtain the corresponding expected charge amount; Step S3: Obtain the duration of the gravel throwing in each effective blasting area, and build a corresponding detonation evaluation model in combination with the borehole lithology information and the historical blasting parameters, and use the detonation evaluation model in combination with the second blasting parameter to obtain the corresponding expected detonation time difference; Step S4: Generate corresponding recommended blasting parameters according to the expected charge amount and the expected detonation time difference and provide feedback.

[0013] Compared with the prior art, the present invention has the following beneficial effects: The present invention constructs a corresponding three-dimensional twin model based on historical blasting data, in which different blasting points and effective blasting areas can be obtained, and a charge evaluation model is constructed based on the corresponding relationship between the drilling lithology information of different blasting points, historical blasting parameters and effective blasting areas, so that the corresponding expected charge amount can be directly output according to the expected effective blasting area; By obtaining the gravel throwing time of each effective blasting area in the three-dimensional twin model, a detonation evaluation model is constructed according to the correspondence between the borehole lithology information, historical blasting parameters and gravel throwing time of different effective blasting areas. The corresponding gravel throwing time can be obtained in combination with the expected charging amount, and it is used as the expected detonation time difference between adjacent boreholes. The above two models are used to obtain the expected charging amount of each borehole and the expected detonation time difference of different boreholes, which is conducive to greatly improving the charging efficiency and overall blasting effect of mine blasting operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0015] like Figure 1 As shown in the figure, a mine blasting process control optimization system based on big data includes the following modules: The data acquisition module is used to obtain the historical blasting data of the mine, and build a corresponding three-dimensional twin model in combination with geological lithology information, and obtain several blasting points and their corresponding effective blasting areas in the three-dimensional twin model; The first evaluation module is used to obtain the drilling lithology information and effective blasting area of ​​each blasting point, and to build a corresponding charge evaluation model in combination with its historical blasting parameters to obtain the expected blasting area of ​​the mine blasting operation, and to obtain the corresponding expected charge amount by using the charge evaluation model in combination with the first blasting parameters; The second evaluation module is used to obtain the duration of the gravel throwing in each effective blasting area, and to build a corresponding detonation evaluation model in combination with the drilling lithology information and the historical blasting parameters, and to obtain the corresponding expected detonation time difference by using the detonation evaluation model in combination with the second blasting parameters; The scheme generation module is used to generate corresponding recommended blasting parameters and provide feedback based on the expected charge amount and the expected detonation time difference.

[0016] It should be further explained that, in the specific implementation process, the process of obtaining the historical blasting data of the mine and building the corresponding three-dimensional twin model in combination with geological lithology information includes: The historical blasting data includes drilling parameters, charging parameters, detonation parameters, blasting range, and blasting degree. The geological lithology information refers to the rock characteristics and properties corresponding to each historical blasting data, including rock type, geological age, rock composition, rock structure, weathering degree, and hardness; 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 detonation time difference; the blasting range refers to the crushing range and area of ​​the rock after blasting; the blasting degree refers to the rock fragmentation distribution after blasting, including large block rate and small block rate; Using 3D geological modeling technology, a 3D geological model of the corresponding mine is constructed based on the geological lithology information of a single historical blasting data, including descriptions of the morphology, structure and properties of the geological body. Simulation software is used to simulate the mine blasting process in the 3D geological model, including the blasting process of explosives, the crushing process of rocks, and the throwing and stacking process after blasting. The simulation parameters are continuously adjusted in the three-dimensional geological model until the simulation results are consistent with the corresponding historical blasting data. The three-dimensional geological model at this time is used as the three-dimensional twin model under the historical blasting data, and the three-dimensional twin models of different historical blasting data are obtained respectively.

[0017] It should be further explained that, in the specific implementation process, the process of obtaining several blasting points and their corresponding effective blasting areas in the three-dimensional twin model includes: A drilling layout map under a single historical blasting data is obtained in the three-dimensional twin model. The drilling layout map refers to the distribution positions of each drill hole deployed during the mine blasting operation. The distribution positions of several drill holes are randomly selected as blasting points in the drilling layout map, and the corresponding effective blasting area is obtained with each blasting point as the center. Obtain the rock fragmentation distribution under the historical blasting data in the 3D twin model. The rock fragmentation distribution refers to the distribution of rock blocks of different sizes formed in the process of rock crushing and accumulation, including the large block rate and the small block rate. In the mine blasting operation, the crushed rocks formed by a single borehole after blasting will be thrown and accumulated in all directions. Among them, the larger crushed stones mostly fall nearby, while the smaller crushed stones mostly fall far away. Therefore, the effective blasting area can be determined by analyzing the change of the large-piece rate around a single borehole. Take any blasting point as an example, take the blasting point as the center of the circle, and use the preset fixed distances R, 2R, 3R, ..., nR as the radius to draw circles outward in sequence, where n is a natural number greater than 1; Obtain the local large block rate of the local area corresponding to each preset fixed distance, where the local area corresponding to R is a circle, and the local area corresponding to nR is a ring. The local large block rate of different local areas decreases with the increase of the preset fixed distance. When the local large block rate increases instead of decreasing, it means that the local area contains large pieces of gravel formed by other boreholes; The local large block rates between adjacent local areas of the blasting point 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 with the blasting point as the center and (n-1)R as the radius is taken as the effective blasting area of ​​the blasting point, and the effective blasting areas of each blasting point under different historical blasting data are obtained respectively.

[0018] It should be further explained that, in the specific implementation process, the process of obtaining the drilling lithology information and effective blasting area of ​​each blasting point and building the corresponding charge evaluation model in combination with its historical blasting parameters includes: Taking any blasting point as an example, the drilling lithology information of the blasting point is obtained according to the rock core excavated during drilling at the blasting point, and the drilling lithology information includes density, porosity, joint fissure ratio, compressive strength and tensile strength of the rock core; The area of ​​the effective blasting region corresponding to the blasting point is taken as its effective blasting area, and the hole depth, hole diameter, charge amount, charge structure, charge density and length, and detonation method of the blasting point in the historical blasting data are taken as its historical blasting parameters; Generate a first evaluation set according to the drilling lithology information and historical blasting parameters of different blasting points and their corresponding effective blasting areas, and divide the first evaluation set into a first training set and a first test set; Constructing a first convolutional neural network, taking different borehole lithology information and historical blasting parameters in the first training set as input data of the first convolutional neural network, and taking the corresponding effective blasting area in the first training set as output data of the first convolutional neural network; The first convolutional neural network is trained to obtain an initial first convolutional neural network, the initial first convolutional neural network is model verified using a first test set, and the initial first convolutional neural network that is less than or equal to a preset first test error threshold is output as a charge evaluation model.

[0019] It should be further explained that, in the specific implementation process, the process of obtaining the expected blasting area of ​​the mine blasting operation and obtaining the corresponding expected charge amount by using the charge evaluation model combined with the first blasting parameter includes: In the subsequent mine blasting operation, the effective blasting area that the relevant personnel expect a single borehole to achieve is taken as the expected blasting area, and the borehole lithology information is obtained according to the core of the single borehole to set the first blasting parameters, which include the preset hole depth, hole diameter, charge structure, charge density and length, and adjustable charge amount; The acquired borehole lithology information and the first blasting parameter are input into the charge evaluation model, and the corresponding effective blasting area is outputted by the charge evaluation model. The charge amount in the first blasting parameter is continuously increased. When the effective blasting area outputted by the charge evaluation model is equal to the expected blasting area, the charge amount at this time is used as the expected charge amount corresponding to the expected blasting area.

[0020] It should be further explained that, in the specific implementation process, the process of obtaining the duration of rock throwing in each effective blasting area and building a corresponding detonation assessment model in combination with its drilling lithology information and historical blasting parameters includes: In the three-dimensional twin model, the corresponding time when the blasting of a single blasting point starts is taken as the blasting start time, and the large block rate of the effective blasting area of ​​the single blasting point during the blasting process is monitored in real time and marked as the simulated large block rate. The final large block rate of the effective blasting area in the historical blasting data is obtained and marked as the historical large block rate. The ratio between the simulated large block rate and the historical large block rate is used as the gravel throwing rate of the effective blasting area, and a gravel throwing rate threshold is set. The corresponding moment when the gravel throwing rate is equal to the gravel throwing rate threshold is used as the throwing completion moment, and the time interval between the blasting start moment and the throwing completion moment is used as the corresponding gravel throwing duration; Generate a second evaluation set according to the drilling lithology information and historical blasting parameters of different effective blasting areas and their corresponding gravel throwing durations, and divide the second evaluation set into a second training set and a second test set; Constructing a second convolutional neural network, taking different borehole lithology information and historical blasting parameters in the second training set as input data of the second convolutional neural network, and taking the corresponding gravel throwing time in the second training set as output data of the second convolutional neural network; The second convolutional neural network is trained to obtain an initial second convolutional neural network, the initial second convolutional neural network is model verified using a second test set, and an initial second convolutional neural network that is less than or equal to a preset second test error threshold is output as a detonation assessment model.

[0021] It should be further explained that, in the specific implementation process, the process of using the detonation evaluation model in combination with the second blasting parameter to obtain the corresponding expected detonation time difference includes: In subsequent mine blasting operations, the drilling lithology information of a single borehole and the expected charge amount under the expected blasting area are obtained, and the second blasting parameters are set, wherein the second blasting parameters include a preset hole depth, hole diameter, charge structure, charge density and length, and the corresponding expected charge amount; The acquired borehole lithology information and the second blasting parameter are input into the detonation assessment model, and the detonation assessment model is used to output the corresponding gravel throwing duration, and the acquired gravel throwing duration is used as the expected detonation time difference between the single borehole and the next adjacent borehole in the detonation sequence.

[0022] It should be further explained that, in the specific implementation process, the process of generating corresponding recommended blasting parameters and providing feedback according to the expected charge amount and the expected detonation time difference includes: In the subsequent mine blasting operation, the hole spacing and row spacing of adjacent boreholes are inferred based on the expected blasting area of ​​each borehole. The hole spacing and row spacing of adjacent boreholes must meet two conditions: the expected blasting area of ​​all boreholes can cover the entire mine blasting operation area and the total number of boreholes is the minimum; The expected charge amount of each borehole is obtained by using the charge assessment model, and the expected detonation time difference between two adjacent boreholes in the detonation sequence is obtained by using the detonation assessment model. Based on this, the recommended blasting parameters for the mine blasting operation are generated and fed back to relevant personnel. The recommended blasting parameters include preset hole depth, hole diameter, charge structure, charge density and length, detonation method, detonation sequence, and expected charge amount of each borehole and hole spacing, row spacing, and expected detonation time difference between adjacent boreholes.

[0023] The embodiment of the present invention also includes a mine blasting process control optimization method based on big data, comprising the following steps: Step S1: Obtain historical blasting data of the mine, and build a corresponding three-dimensional twin model in combination with geological lithology information, and obtain several blasting points and their corresponding effective blasting areas in the three-dimensional twin model; Step S2: Obtain the drilling lithology information and effective blasting area of ​​each blasting point, and build a corresponding charge evaluation model in combination with its historical blasting parameters to obtain the expected blasting area of ​​the mine blasting operation, and use the charge evaluation model in combination with the first blasting parameter to obtain the corresponding expected charge amount; Step S3: Obtain the duration of the gravel throwing in each effective blasting area, and build a corresponding detonation evaluation model in combination with the borehole lithology information and the historical blasting parameters, and use the detonation evaluation model in combination with the second blasting parameter to obtain the corresponding expected detonation time difference; Step S4: Generate corresponding recommended blasting parameters according to the expected charge amount and the expected detonation time difference and provide feedback.

[0024] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. 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. A mine blasting process control optimization system based on big data, characterized in that: Includes the following modules: The data acquisition module is used to obtain the historical blasting data of the mine, and build a corresponding three-dimensional twin model in combination with geological lithology information, and obtain several blasting points and their corresponding effective blasting areas in the three-dimensional twin model; The first evaluation module is used to obtain the drilling lithology information and effective blasting area of ​​each blasting point, and to build a corresponding charge evaluation model in combination with its historical blasting parameters to obtain the expected blasting area of ​​the mine blasting operation, and to obtain the corresponding expected charge amount by using the charge evaluation model in combination with the first blasting parameters; The second evaluation module is used to obtain the duration of the gravel throwing in each effective blasting area, and to build a corresponding detonation evaluation model in combination with the drilling lithology information and the historical blasting parameters, and to obtain the corresponding expected detonation time difference by using the detonation evaluation model in combination with the second blasting parameters; The scheme generation module is used to generate corresponding recommended blasting parameters and provide feedback based on the expected charge amount and the expected detonation time difference.

2. The mine blasting process control optimization system based on big data according to claim 1 is characterized in that: The process of building the corresponding 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; The three-dimensional geological modeling technology is used to construct a corresponding three-dimensional geological model according to the geological lithology information of a single historical blasting data. The simulation software is used to simulate the mining blasting process in the three-dimensional geological model. The simulation parameters are continuously adjusted in the three-dimensional geological model until the simulation results are consistent with the corresponding historical blasting data to obtain a three-dimensional twin model.

3. The mine blasting process control optimization system based on big data according to claim 2 is characterized in that: The process of obtaining several blasting points and their corresponding effective blasting areas includes: A drilling layout diagram under a single historical blasting data is obtained in the 3D twin model, and the distribution positions of several drilling holes are randomly selected as blasting points in the drilling layout diagram; Obtain the rock fragmentation distribution under the single historical blasting data in the three-dimensional twin model, including the large-piece rate and the small-piece rate, and draw circles outward with the single blasting point as the center and the preset fixed distances R, 2R, 3R, ..., nR as the radius in sequence; The local large block rate of the local area corresponding to each preset fixed distance is obtained, and the local large block rates between adjacent local areas of the single blasting point 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 with the single blasting point as the center and (n-1)R as the radius will be used as the effective blasting area of ​​the single blasting point.

4. The mine blasting process control optimization system based on big data according to claim 3 is characterized in that: The process of building the corresponding charge evaluation model includes: Obtaining drilling lithology information of a single blasting point based on the rock core excavated during drilling at the single blasting point, including density, porosity, joint fissure ratio, compressive strength, and tensile strength of the rock core; The area of ​​the effective blasting region corresponding to the single blasting point is taken as the effective blasting area, and the hole depth, hole diameter, charge amount, charge structure, charge density and length, and detonation method of the single blasting point in the historical blasting data are taken as the historical blasting parameters; Generate a first evaluation set according to the drilling lithology information and historical blasting parameters of different blasting points and their corresponding effective blasting areas, and divide the first evaluation set into a first training set and a first test set; Constructing a first convolutional neural network, taking different borehole lithology information and historical blasting parameters in the first training set as input data of the first convolutional neural network, and taking the corresponding effective blasting area in the first training set as output data of the first convolutional neural network; The first convolutional neural network is trained to obtain an initial first convolutional neural network, the initial first convolutional neural network is model verified using a first test set, and the initial first convolutional neural network that is less than or equal to a preset first test error threshold is output as a charge evaluation model.

5. The mine blasting process control optimization system based on big data according to claim 4 is characterized in that: The process of obtaining the expected blasting area and its corresponding expected charge amount includes: In subsequent mine blasting operations, the effective blasting area that can be achieved by a single borehole is taken as the expected blasting area, and the drilling lithology information of the single borehole is obtained to set the first blasting parameters, including the preset hole depth, hole diameter, charge structure, charge density and length, and adjustable charge amount; The drilling lithology information of the single borehole and the first blasting parameter are input into the charge evaluation model, and the corresponding effective blasting area is outputted by the charge evaluation model. The charge amount in the first blasting parameter is continuously adjusted. When the effective blasting area outputted by the charge evaluation model is equal to the expected blasting area, the charge amount at this time is used as the expected charge amount corresponding to the expected blasting area.

6. The mine blasting process control optimization system based on big data according to claim 5 is characterized in that: The process of building the corresponding detonation assessment model includes: In the three-dimensional twin model, the time when a single blasting point starts blasting is taken as the blasting start time, and the simulated large block rate of the effective blasting area of ​​the single blasting point during the blasting process is monitored in real time, and the historical large block rate of the effective blasting area in the historical blasting data is obtained; The ratio between the simulated large block rate and the historical large block rate is taken as the gravel throwing rate in the effective blasting area, and the gravel throwing rate threshold is set. The moment when the gravel throwing rate is equal to the gravel throwing rate threshold is taken as the throwing completion moment, and the time interval between the blasting start moment and the throwing completion moment is taken as the gravel throwing duration. Generate a second evaluation set according to the drilling lithology information and historical blasting parameters of different effective blasting areas and their corresponding gravel throwing durations, and divide the second evaluation set into a second training set and a second test set; Constructing a second convolutional neural network, taking different borehole lithology information and historical blasting parameters in the second training set as input data of the second convolutional neural network, and taking the corresponding gravel throwing time in the second training set as output data of the second convolutional neural network; The second convolutional neural network is trained to obtain an initial second convolutional neural network, the initial second convolutional neural network is model verified using a second test set, and an initial second convolutional neural network that is less than or equal to a preset second test error threshold is output as a detonation assessment model.

7. The mine blasting process control optimization system based on big data according to claim 6 is characterized in that: The process of obtaining the expected detonation time difference includes: In subsequent mine blasting operations, the drilling lithology information of a single borehole and the expected charge amount under the expected blasting area are obtained, and the second blasting parameters are set, including the preset hole depth, hole diameter, charge structure, charge density and length and the corresponding expected charge amount; The drilling lithology information and the second blasting parameter of the single borehole are input into the detonation assessment model, and the detonation assessment model is used to output the corresponding gravel throwing duration, and the obtained gravel throwing duration is used as the expected detonation time difference between the single borehole and the next adjacent borehole in the detonation sequence.

8. The mine blasting process control optimization system based on big data according to claim 7 is characterized in that: The process of generating recommended blasting parameters and providing feedback includes: In the subsequent mine blasting operation, the hole spacing and row spacing of adjacent boreholes are inferred based on the expected blasting area of ​​each borehole, the expected charge amount of each borehole is obtained using the charge evaluation model, and the expected detonation time difference between two adjacent boreholes in the detonation sequence is obtained using the detonation evaluation model, and the recommended blasting parameters for the mine blasting operation are generated and fed back to relevant personnel; The recommended blasting parameters include preset hole depth, hole diameter, charge structure, charge density and length, detonation method, detonation sequence, and expected charge amount of each borehole and hole spacing, row spacing, and expected detonation time difference between adjacent boreholes.

9. A mine blasting process control optimization method based on big data, which is implemented based on the mine blasting process control optimization system according to any one of claims 1 to 8, characterized in that: The method comprises: Step S1: Obtain historical blasting data of the mine, and build a corresponding three-dimensional twin model in combination with geological lithology information, and obtain several blasting points and their corresponding effective blasting areas in the three-dimensional twin model; Step S2: Obtain the drilling lithology information and effective blasting area of ​​each blasting point, and build a corresponding charge evaluation model in combination with its historical blasting parameters to obtain the expected blasting area of ​​the mine blasting operation, and use the charge evaluation model in combination with the first blasting parameter to obtain the corresponding expected charge amount; Step S3: Obtain the duration of the gravel throwing in each effective blasting area, and build a corresponding detonation evaluation model in combination with the borehole lithology information and the historical blasting parameters, and use the detonation evaluation model in combination with the second blasting parameter to obtain the corresponding expected detonation time difference; Step S4: Generate corresponding recommended blasting parameters according to the expected charge amount and the expected detonation time difference and provide feedback.

Images