One-time well completion broaching blasting data analysis processing method and system

Abstract

The invention discloses a data analysis processing method and system for one-time well completion groove broaching blasting, and belongs to the technical field of computers, and through the technical scheme provided by the embodiment of the invention, structured blasting data, unstructured blasting data and expected blasting effect parameters of a to-be-blasted target area are obtained. And based on the structured blasting data, the unstructured blasting data and the expected effect parameters, a blasting scheme of the target area is generated, and automatic generation of the blasting scheme is achieved. In response to a blasting instruction for the target area, blast hole data, stress wave propagation data and laser scanning data of the multiple blast holes are obtained in real time, the blast hole data, the geological data, the stress wave propagation data, the laser scanning data and the expected blasting effect parameters are used for adjusting the initial blasting time of the target blast hole which is not blasted, and the blasting effect of the target blast hole is obtained. Therefore, the blasting process is optimized, and the blasting effect is improved.

Description

Technical Field

[0001] The present application relates to the field of blasting technology, and particularly to a data analysis and processing method and system for primary shaft sinking cut blasting. Background Art

[0002] In the fields of mine exploitation and underground engineering, the primary shaft sinking cut blasting technology plays a key role in the roadway forming quality, blasting efficiency and safety.

[0003] Traditional methods usually design blasting schemes based on static geological survey data (such as borehole cores, geological profiles), and control the energy release through fixed initiation sequences. However, the fixed initiation sequence may not be able to meet the complex blasting environment, resulting in poor blasting effects.

[0004] Therefore, there is an urgent need for a blasting data analysis method that can integrate multi-source data, real-time sense the blasting state and dynamically optimize the blasting time to improve the shaft sinking quality and blasting effect. Summary of the Invention

[0005] The embodiments of the present application provide a data analysis and processing method and system for primary shaft sinking cut blasting, which can improve the shaft sinking quality and blasting effect. The technical solutions are as follows: On the one hand, a data analysis and processing method for primary shaft sinking cut blasting is provided. The method includes: Obtain structured blasting data, unstructured blasting data and expected blasting effect parameters of a target area to be blasted. The structured blasting data includes geological data, hole attributes of blast holes and explosive parameters. The unstructured blasting data includes core images and ground penetrating radar scan point clouds; Generate a blasting scheme for the target area based on the structured blasting data, the unstructured blasting data and the expected blasting effect parameters. The blasting scheme includes the explosive filling amount and the initial initiation time of multiple blast holes in the target area; In response to a blasting instruction for the target area, real-time obtain hole data of multiple blast holes in the target area, stress wave propagation data of the target area and laser scan data of the target area. The blasting instruction is used to indicate blasting according to the initial initiation time of the multiple blast holes. The hole data includes hole position, hole temperature, hole pressure and explosive filling amount; Adjust the initial initiation time of target blast holes that have not been initiated among the multiple blast holes based on the hole data of the multiple blast holes, the geological data, the stress wave propagation data of the target area, the laser scan data of the target area and the expected blasting effect parameters.

[0006] On the one hand, a data analysis and processing system for one - time well - forming trenching blasting is provided. The system includes: A first acquisition module for acquiring structured blasting data, unstructured blasting data, and expected blasting effect parameters of a target area to be blasted. The structured blasting data includes geological data, blast hole attributes of blast holes, and explosive parameters. The unstructured blasting data includes core images and ground - penetrating radar scan point clouds; A blasting scheme generation module for generating a blasting scheme for the target area based on the structured blasting data, the unstructured blasting data, and the expected blasting effect parameters. The blasting scheme includes the explosive filling amounts of multiple blast holes in the target area and the initial detonation time; A second acquisition module for, in response to a blasting instruction for the target area, acquiring in real - time the blast hole data of multiple blast holes in the target area, the stress wave propagation data of the target area, and the laser scan data of the target area. The blasting instruction is used to indicate blasting according to the initial detonation time of the multiple blast holes. The blast hole data includes blast hole positions, blast hole temperatures, blast hole pressures, and explosive filling amounts; A time adjustment module for adjusting the initial detonation time of target blast holes that have not detonated among the multiple blast holes based on the blast hole data of the multiple blast holes, the geological data, the stress wave propagation data of the target area, the laser scan data of the target area, and the expected blasting effect parameters.

[0007] On the one hand, a computer device is provided. The computer device includes one or more processors and one or more memories. At least one computer program is stored in the one or more memories. The computer program is loaded and executed by the one or more processors to implement the method for data analysis and processing of one - time well - forming trenching blasting.

[0008] On the one hand, a computer - readable storage medium is provided. At least one computer program is stored in the computer - readable storage medium. The computer program is loaded and executed by a processor to implement the method for data analysis and processing of one - time well - forming trenching blasting.

[0009] On the one hand, a computer program product or computer program is provided. The computer program product or computer program includes program code. The program code is stored in a computer - readable storage medium. A processor of a computer device reads the program code from the computer - readable storage medium, and the processor executes the program code, causing the computer device to execute the above - mentioned method for data analysis and processing of one - time well - forming trenching blasting.

[0010] Through the technical solutions provided by the embodiments of the present application, structured blasting data, unstructured blasting data, and expected blasting effect parameters of the target area to be blasted are obtained. Based on the structured blasting data, unstructured blasting data, and expected effect parameters, a blasting plan for the target area is generated to achieve the automatic generation of the blasting plan. In response to the blasting instruction for the target area, the blast hole data, stress wave propagation data, and laser scanning data of multiple blast holes are obtained in real time, and the initial detonation time of the target blast holes that have not yet detonated is adjusted by using the blast hole data, geological data, stress wave propagation data, laser scanning data, and expected blasting effect parameters, so as to optimize the blasting process and improve the blasting effect. Description of the Drawings

[0011] To more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. Figure 1 It is a schematic diagram of the implementation environment of a method for analyzing and processing data of one-time shaft sinking cut blasting provided by the embodiments of the present application. Figure 2 It is a flowchart of a method for analyzing and processing data of one-time shaft sinking cut blasting provided by the embodiments of the present application. Figure 3 It is another flowchart of a method for analyzing and processing data of one-time shaft sinking cut blasting provided by the embodiments of the present application. Figure 4 It is a schematic diagram of the structure of a system for analyzing and processing data of one-time shaft sinking cut blasting provided by the embodiments of the present application. Figure 5 It is a schematic diagram of the structure of a computer device provided by the embodiments of the present application. Detailed Embodiments

[0012] To make the purpose, technical solutions, and advantages of the present application clearer, the following will further describe the embodiments of the present application in detail in conjunction with the drawings.

[0013] In the present application, terms such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions. It should be understood that there is no logical or temporal dependence between "first", "second", and "nth", nor are the quantity and execution order limited.

[0014] Artificial Intelligence (AI) is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain better results.

[0015] Machine Learning (ML) is an interdisciplinary field that involves multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how computers can simulate or implement human learning behaviors to acquire new knowledge or skills and reorganize existing knowledge sub-models to continuously improve their own performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent, and its applications cover all fields of artificial intelligence.

[0016] One-time shaft sinking: One-time shaft sinking refers to a construction method in underground engineering such as mines, where a complete shaft or roadway is formed through a single blasting operation. One-time shaft sinking technology is usually used to improve construction efficiency and safety, reduce the construction period and cost. It requires precise blasting design and construction techniques to ensure the stability and quality of the shaft or roadway.

[0017] Cutting blasting: Cutting blasting is a commonly used blasting technology in mining. It forms a trough-shaped space in the ore body to facilitate subsequent mining operations. Cutting blasting is usually used in the mining of open-pit mines and underground mines. Through precise blasting design and construction, a trough-shaped space is formed to facilitate subsequent mining operations.

[0018] Stress wave: A stress wave is a mechanical wave that propagates in a solid medium and is caused by stress changes. When a stress wave propagates in a solid medium, it causes deformation and vibration of the medium. The propagation speed and attenuation characteristics of stress waves depend on the properties of the medium and the frequency of the stress waves.

[0019] Borehole: A borehole refers to a drilled hole used to place explosives in blasting engineering. The layout and design of boreholes are crucial for blasting effects and safety. Parameters such as the diameter, depth, and spacing of boreholes need to be precisely designed according to the properties and requirements of the blasting object.

[0020] Ground Penetrating Radar (GPR): Ground Penetrating Radar is a geophysical exploration device used to detect underground geological structures and objects. Ground Penetrating Radar detects underground geological structures and objects by emitting high-frequency electromagnetic waves and receiving reflected waves. It can be used to detect geological information such as underground cavities, rock interfaces, and groundwater.

[0021] Core image: A core image refers to an image of a rock sample obtained through core drilling. Core images can be used to analyze geological information such as the structure, composition, and porosity of rocks. Core images are usually obtained through optical microscopes or electron microscopes.

[0022] In related technologies, during the process of primary shaft sinking and trenching blasting, once the positions of the blast holes are determined, usually engineers will analyze relevant data based on experience to determine the explosive filling amount and initiation time of the blast holes. After the initiation time of the blast holes is determined, it is usually impossible to adjust, and there may be problems with poor blasting effects.

[0023] By adopting the technical solution provided by the embodiment of the present application, after the positions of the blast holes are determined, relevant data can be automatically analyzed to determine the explosive filling amount and the initial initiation time of the blast holes. At the same time, it can also analyze and process the real-time collected data during the blasting process, so as to adjust the initial initiation time of the blast holes that have not been initiated yet, and improve the final blasting effect.

[0024] Figure 1 It is a schematic diagram of the implementation environment of a data analysis and processing method for primary shaft sinking and trenching blasting provided by the embodiment of the present application. Refer to Figure 1 In this implementation environment, it includes a data processing device 101 and a blasting controller 102.

[0025] The data processing device 101 is electrically connected to multiple sensors and can obtain the blasting data collected by the multiple sensors. The data processing device has strong data processing capabilities and can process multi-modal data relatively quickly.

[0026] The blasting controller 102 is used to control the initiation time of the blast holes, that is, to control the explosion time of the explosives in the blast holes. The blasting controller 102 is electrically connected to the data processing device 101, and data interaction can be carried out between the blasting controller 102 and the data processing device 101. The data processing device 101 can send instructions to the blasting controller to control the initiation time of the blast holes by controlling the blasting controller 102.

[0027] Next, the application scenario of the embodiment of the present application will be introduced. The technical solution provided by the embodiment of the present application can be applied in the scenario of primary shaft sinking and trenching blasting. Since the blasting environment is relatively complex, using a fixed initiation time may not meet the requirements of primary shaft sinking. By adopting the technical solution provided by the embodiment of the present application, not only can the blasting plan be automatically determined before the blasting starts, but also the initiation time of the blast holes can be adjusted in real time during the blasting process, so that the blasting effect can be as close as possible to the requirements of primary shaft sinking.

[0028] Next, the data analysis and processing method for primary shaft sinking and trenching blasting provided by the embodiment of the present application will be described. Figure 2It is a flowchart of a method for data analysis and processing of one-time well-sinking cut blasting provided by an embodiment of the present application. Refer to Figure 2 , taking the data processing device as the execution subject as an example, the method includes the following steps.

[0029] 201. The data processing device acquires structured blasting data, unstructured blasting data, and expected blasting effect parameters of the target area to be blasted. The structured blasting data includes geological data, hole attributes of blast holes, and explosive parameters. The unstructured blasting data includes core images and ground penetrating radar scan point clouds.

[0030] Among them, the target area is the area where one-time well-sinking cut blasting needs to be carried out. The target area includes multiple blast holes, and all the multiple blast holes are pre-drilled blast holes. The geological data is used to represent the geological conditions of the target area. The hole attribute is the characteristic after the blast hole is drilled. For example, the hole attribute includes the hole position and the hole size. The explosive parameters include the explosive energy. The explosive energy refers to the energy generated after the explosion of a unit amount of explosive, and the explosive energy is related to the type of explosive. The core image is an image of the rock sample obtained by core drilling and can be used to analyze information such as the structure, composition, and porosity of the rock. The ground penetrating radar scan point cloud is the point cloud obtained by detecting the target area with the ground penetrating radar. The expected blasting effect parameter is used to represent the expected blasting effect of the target area, that is, the quantitative representation of the expected blasting effect. In some embodiments, the expected blasting effect parameter includes the expected blasting area shape and the expected blasted rock size.

[0031] 202. The data processing device generates a blasting plan for the target area based on the structured blasting data, the unstructured blasting data, and the expected blasting effect parameters. The blasting plan includes the explosive filling amount and the initial detonation time of multiple blast holes in the target area.

[0032] Among them, the blasting plan is determined based on the structured blasting data, the unstructured blasting data, and the expected blasting effect parameters. The structured blasting data and the unstructured blasting data can reflect the situation of the target area, and the expected blasting effect parameters can reflect the expected blasting effect. The combined blasting plan is more matched with the actual situation of the target area and the expected blasting effect. The explosive filling amount of multiple blast holes refers to the explosive filling amount of each blast hole among multiple blast holes. For any two blast holes among multiple blast holes, the explosive filling amounts of these two blast holes may be different. Correspondingly, the initial detonation time of multiple blast holes refers to the initial detonation time of each blast hole among multiple blast holes. For any two blast holes among multiple blast holes, the initial detonation times of these two blast holes may be different.

[0033] 203. In response to a blasting instruction for the target area, the data processing device obtains in real time the blast hole data of multiple blast holes in the target area, the stress wave propagation data of the target area, and the laser scanning data of the target area. The blasting instruction is used to indicate blasting according to the initial detonation time of the multiple blast holes. The blast hole data includes blast hole temperature, blast hole pressure, and explosive filling amount.

[0034] Among them, the blasting instruction is used to indicate the start of blasting the target area according to the initial detonation time in the blasting plan. Without adjusting the blasting plan generated in step 202, it is considered that the blast holes have been filled with explosives according to the explosive filling amount in the blasting plan. The stress wave propagation data is collected by a stress wave data sensor. For example, the stress wave propagation data includes the time history curve of the stress wave. The laser scanning data is the data obtained after scanning the target area with a laser detector, and the laser scanning data is also a kind of point cloud.

[0035] 204. The data processing device adjusts the initial detonation time of the target blast holes that have not yet detonated among the multiple blast holes based on the blast hole data of the multiple blast holes, the geological data, the stress wave propagation data of the target area, the laser scanning data of the target area, and the expected blasting effect parameters.

[0036] Through the technical solution provided by the embodiments of the present application, structured blasting data, unstructured blasting data, and expected blasting effect parameters of the target area to be blasted are obtained. Based on the structured blasting data, unstructured blasting data, and expected effect parameters, a blasting plan for the target area is generated, realizing the automatic generation of the blasting plan. In response to a blasting instruction for the target area, the blast hole data, stress wave propagation data, and laser scanning data of multiple blast holes are obtained in real time, and the initial detonation time of the target blast holes that have not yet detonated is adjusted by using the blast hole data, geological data, stress wave propagation data, laser scanning data, and expected blasting effect parameters, thereby optimizing the blasting process and improving the blasting effect.

[0037] The above steps 201-204 are a brief introduction to the data analysis and processing method for one-time shaft sinking cut blasting provided by the embodiments of the present application. Below, some examples will be combined to more clearly illustrate the data analysis and processing method for one-time shaft sinking cut blasting provided by the embodiments of the present application. See Figure 3 , taking the data processing device as the execution subject as an example, the method includes the following steps.

[0038] 301. The data processing device obtains structured blasting data, unstructured blasting data, and expected blasting effect parameters of the target area to be blasted. The structured blasting data includes geological data, blast hole attributes of the blast holes, and explosive parameters. The unstructured blasting data includes core images and ground penetrating radar scanning point clouds.

[0039] Among them, the target area is the area where one-time well-sinking and trenching blasting needs to be carried out. The target area includes multiple blast holes, and all the multiple blast holes are pre-drilled blast holes. Geological data is used to represent the geological conditions of the target area. Generally speaking, the geological data is obtained by relevant technicians through geological exploration before blasting in the target area. The geological data is stored in the storage medium of the data processing device, and the geological data of the target area can be queried by using the area identifier of the target area. The blast hole attributes are the characteristics after the blast holes are drilled. For example, the blast hole attributes include the blast hole position and the blast hole size. The explosive parameters include the explosive energy. The explosive energy refers to the energy generated after the explosion of a unit amount of explosive, and the explosive energy is related to the type of explosive. The explosive parameters are pre-stored by technicians in the storage medium of the data processing device. The core image is an image of the rock sample obtained through core drilling, and can be used to analyze information such as the structure, composition, and porosity of the rock. The ground penetrating radar scanning point cloud is the point cloud obtained by detecting the target area with the ground penetrating radar. The expected blasting effect parameters are used to represent the expected blasting effect of the target area, that is, the quantitative representation of the expected blasting effect. In some embodiments, the expected blasting effect parameters include the expected blasting area shape and the expected blasting stone size. The expected blasting area shape refers to the shape that the target area is expected to form after blasting is completed, and the expected blasting stone size refers to the size of the stones expected after blasting is completed.

[0040] In a possible implementation manner, the data processing device queries by using the area identifier of the target area to obtain the geological data of the target area, the blast hole attributes of multiple blast holes in the target area, the explosive parameters, the core image, the ground penetrating radar scanning point cloud, and the expected blasting effect parameters.

[0041] Among them, the geological data, the core image, and the ground penetrating radar scanning point cloud are all obtained by technicians through geological exploration of the target area before blasting. The multiple blast holes are drilled by technicians in the target area according to the actual situation. After the multiple blast holes are formed, the blast hole attributes of each blast hole are determined. The explosive parameters are associated with the type of explosive selected by the technician. After the explosive used for blasting is determined, the explosive parameters can be determined. The expected blasting effect parameters are configured by technicians according to requirements, and the embodiments of the present application do not limit this. In the embodiments of the present application, the one-time well-sinking and trenching blasting is reflected by the expected blasting effect parameters. The technical solution provided by the embodiments of the present application is committed to making the actual blasting effect of the target area close to the expected blasting effect parameters, so as to improve the blasting effect. In the embodiments of the present application, the data related to blasting all belong to blasting data. For example, the above-mentioned structured blasting data, unstructured blasting data, and expected blasting effect parameters all belong to blasting data.

[0042] In this implementation manner, by querying using the area identifier of the target area, the structured blasting data, unstructured blasting data, and expected blasting effect parameters of the target area can be obtained, and the acquisition efficiency of the structured blasting data, unstructured blasting data, and expected blasting effect parameters is relatively high.

[0043] In some embodiments, the geological data includes the longitudinal wave propagation velocity. During blasting, the longitudinal wave propagation velocity is affected by various factors. For example, the longitudinal wave propagation velocity is related to the type of medium, the density of the medium, the elastic modulus of the medium, and the Poisson's ratio of the medium. Generally speaking, the greater the density of the medium, the faster the longitudinal wave propagation velocity; the greater the elastic modulus of the medium, the faster the longitudinal wave propagation velocity; the smaller the Poisson's ratio of the medium, the faster the longitudinal wave propagation velocity.

[0044] 302. The data processing device generates a three-dimensional geological model of the target area based on the core image and the ground penetrating radar scan point cloud.

[0045] Among them, the three-dimensional geological model is a three-dimensional model that can be visualized. Through the three-dimensional geological model, the digital representation of the target area can be realized. The data processing device can use the three-dimensional geological model to simulate the target area and facilitate the processing of data related to the target area.

[0046] In a possible implementation manner, the data processing device determines the fracture information of the target area based on the core image. The fracture information is used to represent the fracture rate, fracture size, and fracture density of the target area. The data processing device processes the ground penetrating radar scan point cloud to generate an initial three-dimensional geological model of the target area. The data processing device processes the initial three-dimensional geological model based on the fracture information to generate a three-dimensional geological model of the target area.

[0047] Among them, a fissure refers to a crack existing in the target area, which can be regarded as a crack in the rock mass within the target area. The fissure rate refers to the ratio of the volume or area of fissures in the rock mass to the total volume or total area of the rock mass, usually expressed as a percentage. The fissure size is used to describe the size of the fissure. The fissure density refers to the number of fissures per unit area, usually expressed as number of fissures per square meter. It is an important index to describe the density of fissure distribution in the rock mass. The larger the fissure surface density, the denser the fissures in the rock mass, and vice versa, the sparser the fissures. It should be noted that the number of core images of the target area is multiple, and the fissure information of the target area is determined based on multiple core images. The ground penetrating radar scan point cloud refers to the scan data obtained by the ground penetrating radar scanning the target area. Processing the ground penetrating radar scan point cloud means performing three-dimensional reconstruction on the ground penetrating radar scan point cloud to obtain an initial three-dimensional geological model. Processing the initial three-dimensional geological model based on the fissure information is to add relevant information about the fissures to the initial three-dimensional geological model, thereby improving the accuracy of the generated three-dimensional geological model. In addition, in the embodiments of the present application, since there is a way to dynamically adjust the detonation time of the blast holes, therefore, when determining the blasting plan, it does not rely on a three-dimensional geological model with very high precision. During the actual engineering experiment process, the three-dimensional geological model generated by using the core images and the ground penetrating radar scan point cloud can improve the blasting effect. Of course, with the development of science and technology and the improvement of the data processing ability of data processing devices, using a three-dimensional geological model with higher precision to generate the blasting plan will also have higher accuracy, but it does not affect the implementation of the technical solution provided by the embodiments of the present application. In other words, step 302 above provides a way to generate a low-cost three-dimensional geological model for blasting.

[0048] In this implementation manner, the core images and the ground penetrating radar scan point cloud are used to generate a three-dimensional geological model of the target area, and the generation cost of the three-dimensional geological model is low and the efficiency is high.

[0049] In order to more clearly illustrate the above implementation manner, the above implementation manner will be described in several parts below.

[0050] The first part: The data processing device determines the fissure information of the target area based on the core images.

[0051] In a possible implementation manner, the number of the core images is multiple, and different core images correspond to different positions of the target area. The data processing device inputs the multiple core images into the fissure information recognition model respectively, extracts features of each core image through the fissure information recognition model, and obtains the core image features of each core image. The data processing device determines the fissure information of multiple positions in the target area through the fissure information recognition model based on the core image features of each core image.

[0052] Among them, in the embodiments of the present application, the positions all refer to the positions in the coordinate system corresponding to the target area. For example, the above-mentioned blast hole positions and the positions corresponding to the core images are all the positions in this coordinate system. The base model of the fracture information recognition model is an image recognition model. By using this fracture information recognition model, fractures can be recognized from the core images, and then the fracture information can be determined by combining the fractures in the core images. The embodiments of the present application do not limit the structure and training method of this fracture information recognition model.

[0053] In this implementation manner, by using the fracture information recognition model to recognize multiple core images, the fracture information at multiple positions in the target area can be obtained, and the acquisition efficiency of the fracture information is relatively high.

[0054] For example, the data processing device inputs multiple core images into the fracture information recognition model respectively, and through multiple rounds of convolution of each core image by the fracture information recognition model, the core image features of each core image are obtained. The data processing device performs fracture recognition based on the core image recognition of each core image through this fracture information recognition model, and obtains the fractures in each core image. The data processing device determines the fracture rate, fracture size, and fracture density corresponding to each core image based on the fractures in each core image.

[0055] It should be noted that since one core image corresponds to one position in the target area, the fracture rate, fracture size, and fracture density corresponding to the obtained core image are actually the fracture rate, fracture size, and fracture density at the position corresponding to the core image.

[0056] Second part: The data processing device processes the ground penetrating radar scan point cloud to generate an initial three-dimensional geological model of the target area.

[0057] In a possible implementation manner, the data processing device interpolates the ground penetrating radar scan point cloud to obtain three-dimensional voxel grid data of the target area. The data processing device generates an initial three-dimensional geological model of the target area based on the three-dimensional voxel grid data of the target area.

[0058] Among them, the ground penetrating radar (GPR) scan point cloud is usually discrete data. Interpolating the GPR scan point cloud is to convert the discrete data into continuous data for facilitating the generation of a three-dimensional geological model. In some embodiments, the interpolation methods include Kriging interpolation method, inverse distance weighted interpolation method, etc., and the embodiments of the present application do not limit this. Three-dimensional voxel grid data (3D Voxel Grid Data) is a data structure used to represent objects or scenes in three-dimensional space. Similar to pixels in a two-dimensional image, a voxel is the smallest unit in three-dimensional space, representing a small cube region. These voxels are arranged in a regular three-dimensional grid to form a voxel grid, which is used to describe the shape, structure, and properties of an object.

[0059] In this implementation, by interpolating the GPR scan point cloud, the three-dimensional voxel grid data of the target area can be obtained, and the initial three-dimensional geological model of the target area can be generated using the three-dimensional voxel grid data, with a relatively high generation efficiency of the initial three-dimensional geological model.

[0060] For example, the data processing device denoises and filters the GPR scan point cloud to obtain a reference GPR scan point cloud. The data processing device converts the coordinates of the target GPR scan point cloud from the coordinate system of the GPR to the coordinate system of the target area to obtain the target GPR scan point cloud. The data processing device interpolates the target GPR scan point cloud to obtain the three-dimensional voxel grid data of the target area. The data processing device performs three-dimensional reconstruction on the three-dimensional voxel grid data of the target area to obtain the initial three-dimensional geological model of the target area.

[0061] Among them, denoising and filtering are to eliminate the abnormal points in the GPR scan point cloud. For example, filtering includes longitudinal filtering (such as band-pass filtering, stacking) and transverse filtering (such as background removal, gain compensation). Longitudinal filtering is used to remove high-frequency noise and direct wave interference, and transverse filtering is used to correct signal attenuation. The methods of three-dimensional reconstruction include Marching Cubes algorithm and Dual Contouring algorithm.

[0062] The third part: The data processing device processes the initial three-dimensional geological model based on the fracture information to generate the three-dimensional geological model of the target area.

[0063] In a possible implementation, the data processing corrects the fractures at the corresponding positions in the initial three-dimensional geological model based on the fracture information at multiple positions in the target area to obtain the three-dimensional geological model of the target area.

[0064] Among them, the fracture information includes fracture rate, fracture size, and fracture density. Using the fracture information can supplement the fracture-related information in the initial three-dimensional geological model, thereby improving the accuracy of the three-dimensional geological model. The reason for using the fracture information to correct the initial three-dimensional geological model is that during the blasting process, the existence of fractures has a greater impact on the blasting effect. After adding the fracture-related information to the initial three-dimensional geological model, it helps to improve the accuracy of the subsequent determined blasting plan.

[0065] 303. The data processing device determines multiple blasting energy transfer paths of the target area based on the blast hole attributes, the geological data, and the three-dimensional geological model.

[0066] Among them, the blast hole attributes include blast hole position and blast hole size. The blasting energy transfer path refers to the transfer path of blasting energy during blasting. It should be noted that the multiple blasting energy transfer paths determined in step 303 above are estimated blasting energy transfer paths. During the actual blasting process, the energy may not strictly follow the determined multiple blasting energy transfer paths for transfer. Therefore, the initiation time of the blast holes will be corrected later.

[0067] In a possible implementation manner, the data processing device adds explosion sources in the three-dimensional geological model based on the blast hole position and the blast hole size to obtain a three-dimensional explosion source distribution model of the target area. The explosion sources are the blast holes in the target area. The data processing device identifies the three-dimensional explosion source distribution model to obtain the connectivity parameters between multiple blast holes in the target area. The connectivity parameters are used to represent the degree of connectivity. The data processing device determines the multiple blasting energy transfer paths based on the geological data and the connectivity parameters.

[0068] Among them, since the blast holes are filled with explosives, the blast holes can be regarded as explosion sources. The connectivity parameters are used to represent the connectivity between blast holes. For example, during the process of drilling blast holes in the target area, two blast holes may be directly connected, or although two blast holes are not directly connected, due to the existence of fractures in the target area, these fractures may cause the two blast holes to be actually connected or nearly connected. In some embodiments, the connectivity parameter between two blast holes is determined based on the connected area. The larger the connected area, for the convenience of processing, the connectivity parameter can be expressed as a percentage. 100% represents complete connectivity and the largest connected area, and 0% represents complete non-connectivity. During the blasting process, the transfer direction of blasting energy is associated with the connectivity degree between blast holes and the geological data. That is, the blasting energy will preferentially transfer to the connected blast holes. In addition, the transfer direction of blasting energy is also affected by the geological properties and will preferentially transfer to the weak positions. The geological properties are represented by the geological data.

[0069] In this embodiment, based on the blast hole positions and blast hole sizes, explosive sources are added to the three-dimensional geological model to obtain a three-dimensional explosive source distribution model. The three-dimensional explosive source distribution model is identified to obtain the connectivity parameters between multiple blast holes within the target area. Using the geological data and the connectivity parameters, multiple blasting energy transfer paths are determined to achieve the estimation of the blasting energy transfer paths.

[0070] To more clearly illustrate the above embodiment, the above embodiment will be described in several parts below.

[0071] First part: The data processing device adds explosive sources to the three-dimensional geological model based on the blast hole positions and the blast hole sizes to obtain the three-dimensional explosive source distribution model of the target area.

[0072] In a possible implementation manner, the data processing device determines the voxels corresponding to each blast hole in the three-dimensional geological model based on the blast hole positions of each blast hole. The data processing unit adjusts the voxels corresponding to each blast hole in the three-dimensional geological model based on the blast hole sizes of each blast hole to obtain the three-dimensional explosive source distribution model.

[0073] Among them, compared with the three-dimensional geological model, the three-dimensional explosive source distribution model only marks the positions and sizes of the blast holes in the model. Adjusting the voxels corresponding to the blast holes is to establish an association relationship between the multiple voxels corresponding to the blast holes and the blast holes. Since the voxels corresponding to the blast holes are determined using the blast hole positions in the previous step, the voxels determined using the blast hole positions are single voxels. However, due to the certain size of the blast holes, the blast holes actually correspond to multiple voxels. Adjusting the voxels corresponding to the blast holes is to mark all the voxels corresponding to the blast holes.

[0074] Second part: The data processing device identifies the three-dimensional explosive source distribution model to obtain the connectivity parameters between multiple blast holes within the target area.

[0075] In a possible implementation manner, the data processing device converts the three-dimensional explosive source distribution model into a graph network. The graph network includes multiple nodes, and one node corresponds to one blast hole. The data processing device divides the three-dimensional explosive source distribution model into multiple sub-models, and one sub-model corresponds to one blast hole. The data processing device uses the model data corresponding to each sub-model and the blast hole positions of each blast hole as the node features of the corresponding nodes to obtain the target graph network. The data processing device performs graph convolution on the target network to obtain the weights between every two nodes among the multiple nodes, and this weight is the connectivity parameter between two blast holes.

[0076] Among them, the method of dividing the three-dimensional explosive source distribution model is set by those skilled in the art according to the actual situation, and this application embodiment does not limit it. The method adopted for graph convolution can be the graph convolution method in the related art, and this application embodiment does not limit it.

[0077] Part III: The data processing device determines the multiple blasting energy transfer paths based on the geological data and the connectivity parameters.

[0078] Among them, one blasting energy transfer path corresponds to one blast hole. A blasting energy transfer path refers to the transfer path of the blasting energy of a blast hole when only one blast hole explodes.

[0079] In a possible implementation manner, the geological data includes the rock mass density, the rock mass elastic modulus, and the rock mass Poisson's ratio. For any blast hole among the multiple blast holes, the data processing device determines the blasting energy transfer path of the blast hole based on the connectivity parameter of the blast hole and the rock mass density, the rock mass elastic modulus, and the rock mass Poisson's ratio of the rock mass where the target blast hole is located.

[0080] Among them, the energy transfer path is calculated by the simulation software after the data processing device inputs the connectivity parameter of the blast hole and the rock mass density, the rock mass elastic modulus, and the rock mass Poisson's ratio of the rock mass where the target blast hole is located into the simulation software. For example, the simulation software can be a general finite element analysis software, such as LS-DYNA or ANSYS Autodyn, etc. The embodiments of the present application do not limit this.

[0081] 304. The data processing device generates a blasting plan for the target area based on the blast hole attributes, the three-dimensional geological model, the geological data, the multiple blasting energy transfer paths, the explosive parameters, and the expected blasting effect parameters. The blasting plan includes the explosive filling amounts and the initial detonation times of multiple blast holes in the target area.

[0082] Among them, the blasting plan is determined based on the structured blasting data, the unstructured blasting data, and the expected blasting effect parameters. The structured blasting data and the unstructured blasting data can reflect the situation of the target area, and the expected blasting effect parameters can reflect the expected blasting effect. The combined blasting plan is relatively matched with the actual situation of the target area and the expected blasting effect. The explosive filling amounts of multiple blast holes refer to the explosive filling amounts of each blast hole among the multiple blast holes. For any two blast holes among the multiple blast holes, the explosive filling amounts of these two blast holes may be different. Correspondingly, the initial detonation times of multiple blast holes refer to the initial detonation times of each blast hole among the multiple blast holes. For any two blast holes among the multiple blast holes, the initial detonation times of these two blast holes may be different.

[0083] In a possible implementation, the explosive parameters include the explosive energy, the expected blasting effect parameters include the shape of the expected blasting area and the size of the expected blasted stones, the blast hole attributes include the blast hole position and the blast hole size, and the data processing device determines the explosive demand of the target area based on the three-dimensional geological model, the geological data, the explosive parameters, the shape of the expected blasting area, and the size of the expected blasted stones. The data processing device adds the blast hole position, the blast hole size, and the multiple blasting energy transfer paths to the three-dimensional geological model to obtain the three-dimensional energy transfer model of the target area. The data processing device determines the explosive filling amount of multiple blast holes in the target area based on the explosive demand, the three-dimensional energy transfer model, and the size of the expected blasted stones. The data processing device determines the initial detonation time of multiple blast holes in the target area based on the explosive filling amount of the multiple blast holes, the shape of the expected blasting area, and the three-dimensional energy transfer model.

[0084] Among them, the explosive demand of the target area refers to the sum of the explosive filling amounts of multiple blast holes in the target area. The three-dimensional energy transfer model is obtained by adding multiple blasting energy transfer paths to the three-dimensional geological model, and the starting points of the multiple blasting energy transfer paths are all blast holes.

[0085] To illustrate the above implementation more clearly, the above implementation will be described in several parts below.

[0086] First part: The data processing device determines the explosive demand of the target area based on the three-dimensional geological model, the geological data, the explosive parameters, the shape of the expected blasting area, and the size of the expected blasted stones.

[0087] In a possible implementation, the data processing device determines the target blasted rock volume of the target area based on the three-dimensional geological model and the shape of the expected blasting area. The data processing device determines the initial explosive demand and the initial size of the blasted stones based on the target blasted rock volume, the geological parameters, and the explosive parameters. The data processing device determines the demand correction coefficient based on the size of the expected blasted stones and the initial size of the blasted stones. The data processing device corrects the initial explosive demand using the demand correction coefficient to obtain the explosive demand of the target area.

[0088] Among them, the target blasted rock volume is the amount of rock that needs to be blasted to make the target area form the shape of the expected blasting area. The initial size of the blasted stones refers to the estimated size of the stones after blasting the target area according to the initial explosive demand. The demand correction coefficient is used to correct the initial explosive demand to obtain a more accurate explosive demand.

[0089] To illustrate the above implementation more clearly, the above implementation will be further described in several parts below.

[0090] A. The data processing device determines the target blasting rock volume of the target area based on the three-dimensional geological model and the shape of the expected blasting area.

[0091] In a possible implementation, the data processing device adds virtual boundary lines in the three-dimensional geological model based on the shape dimensions carried by the expected blasting area shape. The shape enclosed by the virtual boundary lines is the shape of the area blasting area, and the dimensions of the area enclosed by the virtual boundary lines are the shape dimensions. The data processing device superimposes the rock volume enclosed by the virtual boundary lines to obtain the target blasting rock volume.

[0092] B. The data processing device determines the initial explosive demand and the initial blasting stone size based on the target blasting rock volume, the geological parameters, and the explosive parameters.

[0093] In a possible implementation, the geological parameters include the rock mass density, the rock mass elastic modulus, and the rock mass Poisson's ratio. The data processing device splices the target blasting rock volume, the geological parameters, and the explosive parameters to obtain the blasting rock volume prediction parameters. The data processing device inputs the blasting rock volume prediction parameters into the explosive demand determination model, extracts the features of the blasting rock volume prediction parameters through the explosive demand determination model, and obtains the blasting rock volume prediction features corresponding to the blasting rock volume prediction parameters. The data processing device maps the blasting rock volume prediction features through the explosive demand determination model to obtain the initial explosive demand. The data processing device splices the initial explosive demand, the target blasting rock volume, the geological parameters, and the explosive parameters to obtain the blasting stone size prediction parameters. The data processing device inputs the blasting stone size prediction parameters into the stone size determination model, extracts the features of the blasting stone size prediction parameters through the stone size determination model, and obtains the blasting stone size prediction features corresponding to the blasting stone size prediction parameters. The data processing device maps the blasting stone size prediction features through the stone size determination model to obtain the initial blasting stone size.

[0094] Among them, both the explosive demand determination model and the stone size determination model are regression models, which can respectively map the input data to the initial explosive demand and the initial blasting stone size. The embodiments of the present application do not limit the structures and training methods of the explosive demand determination model and the stone size determination model.

[0095] For example, the data processing device splices the target blasted rock quantity, the geological parameters, and the explosive parameters to obtain the predicted rock quantity blasting parameters. The data processing device inputs the predicted rock quantity blasting parameters into the explosive demand determination model, and performs multiple fully connected operations on the predicted rock quantity blasting parameters through the explosive demand determination model to obtain the predicted rock quantity blasting characteristics corresponding to the predicted rock quantity blasting parameters. The data processing device performs a fully connected operation and normalization on the predicted rock quantity blasting characteristics through the explosive demand determination model to obtain the initial explosive demand. The data processing device splices the initial explosive demand, the target blasted rock quantity, the geological parameters, and the explosive parameters to obtain the predicted blasted stone size parameters. The data processing device inputs the predicted blasted stone size parameters into the stone size determination model, and performs multiple fully connected operations on the predicted blasted stone size parameters through the stone size determination model to obtain the predicted blasted stone size characteristics corresponding to the predicted blasted stone size parameters. The data processing device performs a fully connected operation and normalization on the predicted blasted stone size characteristics through the stone size determination model to obtain the initial blasted stone size.

[0096] C. The data processing device determines a demand correction coefficient based on the expected blasted stone size and the initial blasted stone size.

[0097] In a possible implementation manner, the data processing device subtracts the expected blasted stone size from the initial blasted stone size to obtain a stone size difference. The data processing device determines the demand correction coefficient based on the stone size difference.

[0098] To more clearly illustrate the above implementation manner, the following describes the manner of determining the demand correction coefficient based on the stone size difference in the above implementation manner.

[0099] In some embodiments, the data processing device substitutes the stone size difference into the first relationship data to obtain the demand correction coefficient. Alternatively, the data processing device queries the first relationship table using the stone size difference to obtain the demand correction coefficient.

[0100] Wherein, the first relationship data is a relationship function for representing the corresponding relationship between the stone size difference and the demand correction coefficient. The first relationship table stores multiple size difference ranges and the demand correction coefficients corresponding to each size difference range. Both the first relationship data and the first relationship table are set by technicians according to actual situations, and the embodiments of the present application do not limit this.

[0101] D. The data processing device corrects the initial explosive demand using the demand correction coefficient to obtain the explosive demand for the target area.

[0102] In a possible implementation, the data processing device adds the demand correction coefficient to the target value and then corrects the initial explosive demand to obtain the explosive demand for the target area.

[0103] Wherein, the target value is 1.

[0104] Second part: The data processing device adds the blast hole position, the blast hole size, and the multiple blasting energy transfer paths to the three-dimensional geological model to obtain the three-dimensional energy transfer model of the target area.

[0105] In a possible implementation, the data processing device adds an explosion source to the three-dimensional geological model based on the blast hole position and the blast hole size to obtain the three-dimensional explosion source distribution model of the target area. The data processing device adds the multiple blasting energy transfer paths to the three-dimensional explosion source distribution model to obtain the three-dimensional energy transfer model of the target area.

[0106] Wherein, the generation method of the three-dimensional explosion source distribution model belongs to the same inventive concept as the method in step 303 above, and the implementation process will not be elaborated. In the case where the three-dimensional explosion source distribution model has been generated in step 303, the multiple blasting energy transfer paths can be directly added to the three-dimensional explosion source distribution model to obtain the three-dimensional energy transfer model of the target area, without repeated generation.

[0107] Third part: The data processing device determines the explosive filling amount of multiple blast holes in the target area based on the explosive demand, the three-dimensional energy transfer model, and the expected blasted rock size.

[0108] In a possible implementation, the data processing device performs multiple rounds of iteration on the explosive filling amount of multiple blast holes with the explosive demand and the three-dimensional energy transfer model as constraints. In each round of iteration, a predicted blasted rock size is determined based on the determined explosive filling amount. Before the next round of iteration, the difference between the predicted blasted rock size of the previous round and the expected blasted rock size is used to adjust the explosive demand in the blast hole, thereby completing this round of iteration.

[0109] Among them, being constrained by the explosive demand and the three-dimensional energy transfer model means that the sum of the explosive filling amounts of multiple blast holes does not exceed the explosive demand, and at the same time, the positions of the multiple blast holes and the blasting energy transfer paths are constrained by the three-dimensional energy transfer model. After one round of iteration is completed, multiple explosive filling amounts will be obtained. One explosive filling amount corresponds to one blast hole, indicating the explosive filling amount of this blast hole determined in this round. The data processing device uses the explosive filling amounts of the multiple blast holes determined in this round to perform blasting simulation, and obtains the predicted blasting stone sizes of this round. The data processing device adjusts the explosive filling amounts of the multiple blast holes based on the difference between the predicted blasting stone sizes of this round and the expected blasting stone sizes, thereby completing this round of iteration. The above process is the same as the supervised learning process of the model. The explosive filling amount of the blast hole can be regarded as the weight during model training. Through multiple rounds of iteration, the explosive filling amounts of multiple blast holes in the target area can be obtained.

[0110] Part 4: The data processing device determines the initial detonation times of multiple blast holes in the target area based on the explosive filling amounts of the multiple blast holes, the shape of the expected blasting area, and the three-dimensional energy transfer model.

[0111] In a possible implementation manner, the data processing device performs multiple rounds of iteration on the detonation times of multiple blast holes with the explosive filling amount and the three-dimensional energy transfer model as constraints. In each round of iteration, a predicted blasting area shape is determined according to the determined detonation time. Before the next round of iteration, the deviation between the predicted blasting area shape of the previous round and the expected blasting area shape is used to adjust the detonation times of the blast holes, thereby completing this round of iteration.

[0112] Among them, being constrained by the explosive demand and the three-dimensional energy transfer model means that the explosive filling amounts of multiple blast holes remain unchanged, and at the same time, the positions of the multiple blast holes and the blasting energy transfer paths are constrained by the three-dimensional energy transfer model. After one round of iteration is completed, multiple detonation times will be obtained. One detonation time corresponds to one blast hole, indicating the detonation time of this blast hole determined in this round. The data processing device uses the detonation times of the multiple blast holes determined in this round to perform blasting simulation, and obtains the predicted blasting area shape of this round. The data processing device adjusts the detonation times of the multiple blast holes based on the deviation between the predicted blasting area shape of this round and the expected blasting area shape, thereby completing this round of iteration. The above process is the same as the supervised learning process of the model. The detonation time of the blast hole can be regarded as the weight during model training. Through multiple rounds of iteration, the detonation times of multiple blast holes in the target area can be obtained.

[0113] 305. In response to the blasting instruction for the target area, the data processing device acquires in real time the blast hole data of multiple blast holes in the target area, the stress wave propagation data of the target area, and the laser scanning data of the target area. The blasting instruction is used to indicate blasting according to the initial detonation time of the multiple blast holes. The blast hole data includes blast hole position, blast hole temperature, blast hole pressure, and explosive filling amount.

[0114] Among them, the blasting instruction is used to indicate the start of blasting the target area according to the initial detonation time in the blasting plan. In the case where the blasting plan generated in step 302 is not adjusted, it is considered that the blast holes have been filled with explosives according to the explosive filling amount in the blasting plan. The stress wave propagation data is collected by a stress wave data sensor. For example, the stress wave propagation data includes the time history curve of the stress wave. The laser scanning data is the data obtained after scanning the target area using a laser detector. The laser scanning data is also a kind of point cloud.

[0115] In a possible implementation, a temperature sensor and a pressure sensor are configured in the blast hole, so that the blast hole temperature and blast hole pressure can be determined in real time. The explosive filling amount of the blast hole has been determined in the above step 304 and can be directly used. The laser detector continuously scans the target area to obtain laser scanning data. In addition, a stress wave data sensor is also arranged in the blast hole, and the stress wave data sensor can directly collect the stress wave propagation data.

[0116] 306. The data processing device determines the remaining energy transferred from the blasted area in the target area to the target blast hole based on the stress wave propagation data and the geological data.

[0117] Among them, the target blast hole is a blast hole that has not been detonated among the multiple blast holes.

[0118] In a possible implementation, the stress wave propagation data includes a stress wave time history curve. The data processing device integrates the stress wave time history curve to obtain the initial energy of the blasted area. The data processing device determines the energy attenuation coefficient corresponding to the target blast hole based on the distance between the target blast hole and the blasted area and the geological data. The data processing device determines the remaining energy transferred from the blasted area in the target area to the target blast hole based on the initial energy and the energy attenuation coefficient.

[0119] Among them, the stress wave is a form of propagation of stress and strain disturbances. For example, under dynamic loads such as explosion, impact, or earthquake, a wave phenomenon is generated in the medium. The time history curve records the variation of dynamic parameters (such as velocity, acceleration) of the stress wave during propagation with time through sensors (such as accelerometers or velocimeters) to form a continuous waveform diagram.

[0120] For example, geological data includes rock mass density, rock mass elastic modulus, and rock mass Poisson's ratio. The data processing device integrates the stress wave time history curve through the following formula (1) to obtain the initial energy of the blasted area. The data processing device substitutes the distance between the target blast hole and the blasted area and the geological data into the second relationship data to obtain the energy attenuation coefficient corresponding to the target blast hole. The data processing device multiplies the difference between the initial energy and the target value and the energy attenuation coefficient to obtain the remaining energy transferred from the blasted area in the target area to the target blast hole.

[0121] Among them, the target value is 1, and the formula for determining the remaining energy can be simplified to initial energy - (1 - energy attenuation coefficient). The second relationship data is a relationship function used to represent the corresponding relationship between distance, geological data, and energy attenuation coefficient. The second relationship data is set by technicians according to actual situations, and the embodiments of the present application do not limit this.

[0122] Among them, represents the initial energy, represents the variation function between stress and time in the stress wave time history curve, represents the variation function between the stress wave propagation speed and time in the stress wave time history curve, represents the current time.

[0123] 307. The data processing device determines the rock formation displacement field of the target area based on the laser scanning data.

[0124] In a possible implementation manner, the data processing device extracts key points from the laser scanning data to obtain multiple key points in the laser scanning data. The data processing device determines the rock formation displacement field corresponding to the target blast hole based on the initial positions and current positions of the multiple key points.

[0125] Among them, the initial position of the key point is the position of the key point when blasting has not started, and the current position is the position of the key point at the current time after blasting has started. The rock formation displacement field is a set of displacement vectors of each point in the rock mass at different time points, characterizing the deformation state of the rock mass after being affected by external forces or internal stress changes. For example, when underground mining causes rock formation bending, fracture, or caving, the displacement vectors at different depths and regions will form a dynamically changing displacement field.

[0126] 308. The data processing device adjusts the initial detonation time of the target blast hole that has not been detonated among the multiple blast holes based on the blast hole data of the target blast hole, the geological data, the remaining energy, the rock formation displacement field, and the expected blasting effect parameters.

[0127] In a possible implementation, the geological data includes the longitudinal wave propagation velocity, and the data processing device determines the strain tensor of the target blast hole based on the rock formation displacement field. The data processing device determines the change in detonation time based on the strain tensor, the longitudinal wave propagation velocity, the blast hole data, the remaining energy, and the expected blasting effect parameters. The data processing device adds the initial detonation time of the target blast hole and the change in detonation time to obtain the target detonation time of the target blast hole.

[0128] To illustrate the above implementation more clearly, the above implementation will be described in several parts below.

[0129] First part: The data processing device determines the strain tensor of the target blast hole based on the rock formation displacement field.

[0130] Among them, the strain tensor is a second-order symmetric tensor, and its components are composed of the symmetric part of the displacement gradient tensor. For any point in the rock formation, if the displacement vector is , then the components of the strain tensor are defined as . This expression reflects the normal strain (diagonal components) and shear strain (non-diagonal components) of the material microelement in different directions during the deformation process.

[0131] In addition, the rock formation displacement is directly related to the strain tensor through the displacement gradient tensor. The displacement gradient can be decomposed into a symmetric part (strain tensor and an anti-symmetric part (rigid body rotation tensor ). Among them, the strain tensor only reflects the pure deformation of the material, and the rigid body rotation does not affect the strain. The spatial distribution of the rock formation displacement (displacement field) directly determines the distribution of the strain tensor. For example, during the blasting process, the non-uniformity of the displacement field will cause tensile, compressive or shear strains inside the rock formation, thereby forming delamination cracks or fracture zones.

[0132] Second part: The data processing device determines the change in detonation time based on the strain tensor, the longitudinal wave propagation velocity, the blast hole data, the remaining energy, and the expected blasting effect parameters.

[0133] In a possible implementation, the data processing device determines the expected strain tensor and the expected remaining energy of the target blast hole based on the expected blasting effect parameters and the blast hole position in the blast hole data. The data processing device determines the initial change in detonation time based on the tensor deviation between the strain tensor and the expected strain tensor, and the energy deviation between the remaining energy and the expected remaining energy. The data processing device corrects the initial change in detonation time using the longitudinal wave propagation velocity, the blast hole temperature, the blast hole pressure, and the explosive filling amount to obtain the change in detonation time.

[0134] To illustrate the above - mentioned embodiments more clearly, the above - mentioned embodiments will be further described in several parts below.

[0135] A. Based on the expected blasting effect parameters and the hole positions in the blast hole data, the data processing device determines the expected strain tensor and the expected remaining energy of the target blast hole.

[0136] In a possible implementation, the data processing device queries using the expected blasting effect parameters and the hole position to obtain the expected strain tensor and the expected remaining energy of the target blast hole.

[0137] Among them, the expected strain tensor and the expected remaining energy when multiple blast holes are blasted with the expected blasting effect parameters are stored in advance by technicians in a storage medium. By querying using the expected blasting effect parameters and the hole position, the expected strain tensor and the expected remaining energy of the target blast hole can be obtained.

[0138] B. Based on the tensor deviation between the strain tensor and the expected strain tensor, and the energy deviation between the remaining energy and the expected remaining energy, the data processing device determines the change amount of the initial detonation time.

[0139] In a possible implementation, the data processing device substitutes the tensor deviation and the energy deviation into the third relationship data to obtain the change amount of the initial detonation time.

[0140] Among them, the third relationship data is a relationship function used to represent the corresponding relationship between the tensor deviation, the energy deviation, and the change amount of the initial detonation time. The third relationship data is set by technicians according to the actual situation, and the embodiments of this application do not limit this.

[0141] C. The data processing device corrects the change amount of the initial detonation time using the longitudinal wave propagation speed, the hole temperature, the hole pressure, and the explosive filling amount to obtain the change amount of the detonation time.

[0142] In a possible implementation, the data processing device splices the longitudinal wave propagation speed, the hole temperature, the hole pressure, and the explosive filling amount into a time correction coefficient determination parameter. The data processing device substitutes the time correction coefficient determination parameter into a time correction coefficient determination model, extracts features of the time correction coefficient determination parameter through the time correction coefficient determination model to obtain the time correction coefficient determination features of the time correction coefficient determination parameter. The data processing device maps the time correction coefficient determination features through the time correction coefficient determination model to obtain the detonation time correction coefficient. The data processing device corrects the change amount of the initial detonation time using the detonation time correction coefficient to obtain the change amount of the detonation time.

[0143] Among them, the time correction coefficient determination model is a regression model. Using this time correction coefficient determination model, the time correction coefficient determination parameters can be mapped to the initiation time correction coefficient. The reason for being able to use this time correction coefficient to correct the initial initiation time variation is that during the blasting process, the energy transfer is also affected by the longitudinal wave propagation speed, hole temperature, hole pressure, and explosive filling amount. The accuracy of the initiation time variation obtained by using this time correction coefficient to correct the initial initiation time variation is relatively high.

[0144] For example, the data processing device splices the longitudinal wave propagation speed, hole temperature, hole pressure, and explosive filling amount into the time correction coefficient determination parameters. The data processing device substitutes the time correction coefficient determination parameters into the time correction coefficient determination model, and performs multiple full connections on the time correction coefficient determination parameters through this time correction coefficient determination model to obtain the time correction coefficient determination features of the time correction coefficient determination parameters. The data processing device uses this time correction coefficient determination model to perform full connection and normalization on the time correction coefficient determination features to obtain the initiation time correction coefficient. The data processing device multiplies the sum of the initiation time correction coefficient and the target value by the initial initiation time variation to obtain the initiation time variation.

[0145] Among them, the target value is 1.

[0146] All the above optional technical solutions can be combined arbitrarily to form optional embodiments of the present application, which will not be elaborated one by one here.

[0147] Through the technical solution provided by the embodiment of the present application, structured blasting data, unstructured blasting data, and expected blasting effect parameters of the target area to be blasted are obtained. Based on the structured blasting data, unstructured blasting data, and expected effect parameters, a blasting plan for the target area is generated to realize the automatic generation of the blasting plan. In response to the blasting instruction for the target area, the hole data, stress wave propagation data, and laser scanning data of multiple holes are obtained in real time. Using the hole data, geological data, stress wave propagation data, laser scanning data, and expected blasting effect parameters, the initial initiation time of the target hole that has not been initiated is adjusted, thereby optimizing the blasting process and improving the blasting effect.

[0148] Figure 4 It is a schematic structural diagram of a data analysis and processing system for one - time shaft - forming cut blasting provided by an embodiment of the present application. Refer to Figure 4 , the system includes: a first acquisition module 401, a blasting plan generation module 402, a second acquisition module 403, and a time adjustment module 404.

[0149] The first acquisition module 401 is configured to acquire the structured blasting data, unstructured blasting data, and expected blasting effect parameters of the target area to be blasted. The structured blasting data includes geological data, blast hole attributes of blast holes, and explosive parameters. The unstructured blasting data includes core images and ground penetrating radar scan point clouds.

[0150] The blasting plan generation module 402 is configured to generate a blasting plan for the target area based on the structured blasting data, the unstructured blasting data, and the expected blasting effect parameters. The blasting plan includes the explosive filling amounts and initial detonation times of multiple blast holes in the target area.

[0151] The second acquisition module 403 is configured to, in response to a blasting instruction for the target area, acquire in real time the blast hole data of multiple blast holes in the target area, the stress wave propagation data of the target area, and the laser scan data of the target area. The blasting instruction is used to indicate blasting according to the initial detonation times of the multiple blast holes. The blast hole data includes blast hole positions, blast hole temperatures, blast hole pressures, and explosive filling amounts.

[0152] The time adjustment module 404 is configured to adjust the initial detonation times of target blast holes that have not yet detonated among the multiple blast holes based on the blast hole data of the multiple blast holes, the geological data, the stress wave propagation data of the target area, the laser scan data of the target area, and the expected blasting effect parameters.

[0153] In a possible implementation manner, the blasting plan generation module 402 is configured to generate a three-dimensional geological model of the target area based on the core image and the ground penetrating radar scan point cloud. Based on the blast hole attributes, the geological data, and the three-dimensional geological model, determine multiple blasting energy transfer paths of the target area. Based on the blast hole attributes, the three-dimensional geological model, the geological data, the multiple blasting energy transfer paths, the explosive parameters, and the expected blasting effect parameters, generate a blasting plan for the target area.

[0154] In a possible implementation manner, the blasting plan generation module 402 is configured to determine the fracture information of the target area based on the core image. The fracture information is used to represent the fracture rate, fracture size, and fracture density of the target area. Process the ground penetrating radar scan point cloud to generate an initial three-dimensional geological model of the target area. Process the initial three-dimensional geological model based on the fracture information to generate a three-dimensional geological model of the target area.

[0155] In a possible implementation, the blast hole attributes include the blast hole position and the blast hole size. The blasting plan generation module 402 is configured to add explosion sources in the three-dimensional geological model based on the blast hole position and the blast hole size to obtain a three-dimensional explosion source distribution model of the target area. The explosion sources are the blast holes in the target area. Identifying the three-dimensional explosion source distribution model to obtain the connectivity parameters between multiple blast holes in the target area, where the connectivity parameters are used to represent the degree of connectivity. Based on the geological data and the connectivity parameters, determine the multiple blasting energy transfer paths.

[0156] In a possible implementation, the explosive parameters include the explosive energy of the explosive, the expected blasting effect parameters include the shape of the expected blasting area and the size of the expected blasted stones, the blast hole attributes include the blast hole position and the blast hole size, and the blasting plan generation module 402 is configured to determine the explosive demand of the target area based on the three-dimensional geological model, the geological data, the explosive parameters, the shape of the expected blasting area, and the size of the expected blasted stones. Add the blast hole position, the blast hole size, and the multiple blasting energy transfer paths to the three-dimensional geological model to obtain a three-dimensional energy transfer model of the target area. Based on the explosive demand, the three-dimensional energy transfer model, and the size of the expected blasted stones, determine the explosive filling amount of multiple blast holes in the target area. Based on the explosive filling amount of the multiple blast holes, the shape of the expected blasting area, and the three-dimensional energy transfer model, determine the initial detonation time of multiple blast holes in the target area.

[0157] In a possible implementation, the time adjustment module 404 is configured to determine the remaining energy of the energy transferred from the blasted area in the target area to the target blast hole based on the stress wave propagation data and the geological data. Determine the rock formation displacement field of the target area based on the laser scan data. Adjust the initial detonation time of the target blast hole based on the blast hole data of the target blast hole, the geological data, the remaining energy, the rock formation displacement field, and the expected blasting effect parameters.

[0158] In a possible implementation, the stress wave propagation data includes a stress wave time history curve, and the time adjustment module 404 is configured to integrate the stress wave time history curve to obtain the initial energy of the blasted area. Determine the energy attenuation coefficient corresponding to the target blast hole based on the distance between the target blast hole and the blasted area and the geological data. Based on the initial energy and the energy attenuation coefficient, determine the remaining energy of the energy transferred from the blasted area in the target area to the target blast hole.

[0159] In a possible implementation, the time adjustment module 404 is configured to extract key points from the laser scan data to obtain multiple key points in the laser scan data. Determine the rock formation displacement field corresponding to the target blast hole based on the initial positions and current positions of the multiple key points.

[0160] In a possible implementation, the geological data includes the longitudinal wave propagation velocity. The time adjustment module 404 is configured to determine the strain tensor of the target blast hole based on the rock formation displacement field. Based on the strain tensor, the longitudinal wave propagation velocity, the blast hole data, the remaining energy, and the expected blasting effect parameters, determine the change amount of the initiation time. Add the initial initiation time of the target blast hole and the change amount of the initiation time to obtain the target initiation time of the target blast hole.

[0161] It should be noted that: when the data analysis and processing system for one - time well - forming cut blasting provided in the above - mentioned embodiment performs blasting data analysis, only the division of the above - mentioned functional modules is used as an example for illustration. In actual application, the above - mentioned functions can be assigned to different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the data analysis and processing system for one - time well - forming cut blasting provided in the above - mentioned embodiment and the embodiment of the data analysis and processing method for one - time well - forming cut blasting belong to the same concept. The specific implementation process can be seen in the method embodiment and will not be elaborated here.

[0162] Through the technical solution provided by the embodiment of the present application, structured blasting data, unstructured blasting data, and expected blasting effect parameters of the target area to be blasted are obtained. Based on the structured blasting data, unstructured blasting data, and expected effect parameters, a blasting plan for the target area is generated to achieve the automatic generation of the blasting plan. In response to the blasting instruction for the target area, the blast hole data, stress wave propagation data, and laser scan data of multiple blast holes are obtained in real time. Using the blast hole data, geological data, stress wave propagation data, laser scan data, and expected blasting effect parameters, the initial initiation time of the target blast hole that has not been initiated is adjusted, thereby optimizing the blasting process and improving the blasting effect.

[0163] Figure 5 It is a schematic structural diagram of a computer device provided by the embodiment of the present application. The computer device can be implemented as the above - mentioned data processing device. The computer device 500 may vary greatly due to configuration or performance differences. It may include one or more processors (Central Processing Units, CPU) 501 and one or more memories 502. Among them, at least one computer program is stored in the one or more memories 502, and the at least one computer program is loaded and executed by the one or more processors 501 to implement the methods provided by the above - mentioned various method embodiments. Of course, the computer device 500 may also have components such as a wired or wireless network interface, a keyboard, and an input - output interface for input - output. The computer device 500 may also include other components for implementing device functions, which will not be elaborated here.

[0164] In an exemplary embodiment, a computer-readable storage medium is further provided, such as a memory including a computer program, and the computer program can be executed by a processor to complete the method for analyzing and processing data of one-time well completion and slot blasting in the above embodiment. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0165] In an exemplary embodiment, a computer program product or a computer program is further provided. The computer program product or the computer program includes program code, and the program code is stored in a computer-readable storage medium. The processor of the computer device reads the program code from the computer-readable storage medium, and the processor executes the program code, so that the computer device executes the method for analyzing and processing data of one-time well completion and slot blasting.

[0166] In some embodiments, the computer program involved in the embodiments of the present application may be deployed to be executed on a single computer device, or on multiple computer devices located at one place. Or, it may be executed on multiple computer devices distributed at multiple locations and interconnected through a communication network. The multiple computer devices distributed at multiple locations and interconnected through a communication network may form a blockchain system.

[0167] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above embodiments can be completed by hardware, or can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk, or an optical disc, etc.

[0168] The above are only optional embodiments of the present application, and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A data analysis and processing method for one-time well-sinking trenching blasting, characterized in that, The method includes: Obtaining structured blasting data, unstructured blasting data, and expected blasting effect parameters of a target area to be blasted. The structured blasting data includes geological data, hole attributes of blast holes, and explosive parameters. The unstructured blasting data includes core images and ground penetrating radar scanning point clouds; Generating a blasting plan for the target area based on the structured blasting data, the unstructured blasting data, and the expected blasting effect parameters. The blasting plan includes the explosive filling amount and the initial detonation time of multiple blast holes in the target area; In response to a blasting instruction for the target area, obtaining in real time the hole data of multiple blast holes in the target area, the stress wave propagation data of the target area, and the laser scanning data of the target area. The blasting instruction is used to indicate blasting according to the initial detonation time of the multiple blast holes. The hole data includes hole position, hole temperature, hole pressure, and explosive filling amount; Adjusting the initial detonation time of target blast holes that have not detonated among the multiple blast holes based on the hole data of the multiple blast holes, the geological data, the stress wave propagation data of the target area, the laser scanning data of the target area, and the expected blasting effect parameters.

2. The method according to claim 1, wherein The generating the blasting plan for the target area based on the structured blasting data, the unstructured blasting data, and the expected blasting effect parameters includes: Generating a three-dimensional geological model of the target area based on the core image and the ground penetrating radar scanning point cloud; Determining multiple blasting energy transfer paths of the target area based on the hole attributes, the geological data, and the three-dimensional geological model; Generating a blasting plan for the target area based on the hole attributes, the three-dimensional geological model, geological data, the multiple blasting energy transfer paths, the explosive parameters, and the expected blasting effect parameters.

3. The method according to claim 2, characterized in that, The generating the three-dimensional geological model of the target area based on the core image and the ground penetrating radar scanning point cloud includes: Determining the fracture information of the target area based on the core image. The fracture information is used to represent the fracture rate, fracture size, and fracture density of the target area; Processing the ground penetrating radar scanning point cloud to generate an initial three-dimensional geological model of the target area; Processing the initial three-dimensional geological model based on the fracture information to generate a three-dimensional geological model of the target area.

4. The method according to claim 2, wherein The hole attributes include hole position and hole size. The determining the multiple blasting energy transfer paths of the target area based on the hole attributes, the geological data, and the three-dimensional geological model includes: Adding explosion sources in the three-dimensional geological model based on the hole position and the hole size to obtain a three-dimensional explosion source distribution model of the target area. The explosion sources are the blast holes in the target area; Identifying the three-dimensional explosion source distribution model to obtain the connectivity parameters between multiple blast holes in the target area. The connectivity parameters are used to represent the degree of connectivity; Determining the multiple blasting energy transfer paths based on the geological data and the connectivity parameters.

5. The method according to claim 2, wherein The explosive parameters include the explosive energy, the expected blasting effect parameters include the shape of the expected blasting area and the size of the expected blasted stones, the blast hole attributes include the blast hole position and the blast hole size, and generating the blasting plan for the target area based on the blast hole attributes, the three-dimensional geological model, the geological data, the multiple blasting energy transfer paths, the explosive parameters, and the expected blasting effect parameters includes: Determining the explosive demand of the target area based on the three-dimensional geological model, the geological data, the explosive parameters, the shape of the expected blasting area, and the size of the expected blasted stones; Adding the blast hole position, the blast hole size, and the multiple blasting energy transfer paths to the three-dimensional geological model to obtain the three-dimensional energy transfer model of the target area; Determining the explosive filling amount of multiple blast holes in the target area based on the explosive demand, the three-dimensional energy transfer model, and the size of the expected blasted stones; Determining the initial detonation time of multiple blast holes in the target area based on the explosive filling amount of the multiple blast holes, the shape of the expected blasting area, and the three-dimensional energy transfer model.

6. The method according to claim 1, wherein Adjusting the initial detonation time of the target blast holes that have not yet detonated among the multiple blast holes based on the blast hole data of the multiple blast holes, the geological data, the stress wave propagation data of the target area, the laser scanning data of the target area, and the expected blasting effect parameters, includes: Determining the remaining energy transferred from the blasted area in the target area to the target blast holes based on the stress wave propagation data and the geological data; Determining the rock displacement field of the target area based on the laser scanning data; Adjusting the initial detonation time of the target blast holes based on the blast hole data of the target blast holes, the geological data, the remaining energy, the rock displacement field, and the expected blasting effect parameters.

7. The method according to claim 6, wherein The stress wave propagation data includes the stress wave time history curve, and determining the remaining energy transferred from the blasted area in the target area to the target blast holes based on the stress wave propagation data and the geological data includes: Integrating the stress wave time history curve to obtain the initial energy of the blasted area; Determining the energy attenuation coefficient corresponding to the target blast holes based on the distance between the target blast holes and the blasted area and the geological data; Determining the remaining energy transferred from the blasted area in the target area to the target blast holes based on the initial energy and the energy attenuation coefficient.

8. The method according to claim 6, wherein Determining the rock displacement field corresponding to the target blast holes based on the laser scanning data includes: Performing key point extraction on the laser scanning data to obtain multiple key points in the laser scanning data; Determining the rock displacement field corresponding to the target blast holes based on the initial positions and the current positions of the multiple key points.

9. The method according to claim 6, characterized in that, The geological data includes the longitudinal wave propagation speed, and adjusting the initial detonation time of the target blast holes based on the blast hole data of the target blast holes, the geological data, the remaining energy, the rock displacement field, and the expected blasting effect parameters includes: Determine the strain tensor of the target blast hole based on the rock formation displacement field; Determine the change in detonation time based on the strain tensor, the longitudinal wave propagation velocity, the blast hole data, the remaining energy, and the expected blasting effect parameters; Add the initial detonation time of the target blast hole and the change in detonation time to obtain the target detonation time of the target blast hole.

10. A data analysis and processing system for one-pass shaft sinking cut blasting, characterized in that A first acquisition module for acquiring structured blasting data, unstructured blasting data, and expected blasting effect parameters of a target area to be blasted, wherein the structured blasting data includes geological data, blast hole attributes of blast holes, and explosive parameters, and the unstructured blasting data includes core images and ground penetrating radar scan point clouds; A blasting plan generation module for generating a blasting plan for the target area based on the structured blasting data, the unstructured blasting data, and the expected blasting effect parameters, wherein the blasting plan includes the explosive filling amount and the initial detonation time of multiple blast holes in the target area; A second acquisition module for, in response to a blasting instruction for the target area, acquiring in real time the blast hole data of multiple blast holes in the target area, the stress wave propagation data of the target area, and the laser scan data of the target area, wherein the blasting instruction is used to indicate blasting according to the initial detonation time of the multiple blast holes, and the blast hole data includes blast hole position, blast hole temperature, blast hole pressure, and explosive filling amount; A time adjustment module for adjusting the initial detonation time of the target blast holes that have not yet detonated among the multiple blast holes based on the blast hole data of the multiple blast holes, the geological data, the stress wave propagation data of the target area, the laser scan data of the target area, and the expected blasting effect parameters.

Images