A tunnel blasting construction method, a fully computerized rock drilling rig, electronic equipment and storage medium

Abstract

This invention proposes a tunnel blasting construction method, a fully computerized rock drilling rig, electronic equipment, and storage medium. The method includes: acquiring construction photos during actual construction, the photos containing the rock area; analyzing the construction photos based on a pre-built prediction model to output a borehole distribution map and charge information; and performing tunnel blasting construction according to the borehole distribution map and the charge information, ensuring that the over-excavation and under-excavation profiles after blasting are kept within a preset range. This invention obtains a prediction model based on extensive data training, and performs intelligent borehole layout and intelligent charge calculation based on rock information acquired before drilling. This enables blasting to achieve optimal blasting advance and over-excavation / under-excavation control effects with lower explosive costs and shorter drilling times, reducing reliance on operator experience, improving the control level of over-excavation and under-excavation, and reducing construction time and waste of subsequent wet spraying materials.

Description

Technical Field

[0001] This invention relates to the field of tunnel construction technology, and in particular to a tunnel blasting construction method, a fully computerized rock drilling rig, electronic equipment, and storage medium. Background Technology

[0002] In tunnel blasting construction, controlling over- and under-excavation is crucial. Under-excavation necessitates secondary excavation, impacting subsequent arch-building processes and extending the construction period while increasing costs. Over-excavation increases the time required for wet shotcreting and wastes concrete, also significantly extending the construction period and raising costs. Therefore, controlling over- and under-excavation has become a critical aspect, attracting considerable attention. However, controlling over- and under-excavation in blasting is closely related to the geological distribution of the rock, the distribution of drill holes (location and angle), and the distribution of explosives (type and quantity) in different holes. During construction, these multiple processes and factors cause continuous changes in the rock, making traditional methods relying on personnel experience for over- and under-excavation control generally inaccurate and unable to meet the needs of on-site construction. Summary of the Invention

[0003] This invention provides a tunnel blasting construction method, a fully computerized rock drilling rig, electronic equipment, and storage medium to solve the problems existing in related technologies. The technical solution is as follows:

[0004] In a first aspect, embodiments of the present invention provide a tunnel blasting construction method, comprising:

[0005] Obtain rock images before drilling, and use deep learning technology to extract rock features from the rock images, including rock type and rock distribution;

[0006] The drilling data collected during the drilling process is acquired, and the drilling characteristics are determined based on the drilling data. The drilling characteristics include the drilling location, drilling depth, diameter, direction, and angle.

[0007] Matching rock features with borehole data to determine the relationship between rock features and borehole features;

[0008] Acquire the charge data for each borehole and the over-excavation and under-excavation data after charge blasting. Use statistical algorithms to analyze the correlation between charge data, over-excavation and under-excavation data and borehole data. Build a prediction model based on the correlation analysis results and train the prediction model to determine the quantitative relationship between charge data, over-excavation and under-excavation data, rock characteristics and borehole characteristics.

[0009] During the actual construction process, construction photos are obtained, which include the rock area. The construction photos are analyzed based on the prediction model to output the borehole distribution map and charge information. Tunnel blasting is carried out according to the borehole distribution map and charge information to keep the over-excavation and under-excavation profiles after blasting within the preset range.

[0010] In one implementation, training the prediction model includes:

[0011] During the training process, the evaluation objectives are to optimize the prediction model by controlling the over- and under-drilling profile, the cost of drilling time and explosives, and maximizing the ratio of blasting advance to drilling depth.

[0012] In one implementation, the preset range is that the maximum over-excavation should be less than or equal to 15cm, the average over-excavation should be less than or equal to 10cm, and the maximum under-excavation should be less than or equal to 5cm.

[0013] In one implementation, the rock images are obtained by taking pictures of the tunnel rocks by hovering a drone over them.

[0014] In one implementation, the drilling data is obtained by analyzing the joint activity data of the rock drilling rig based on the kinematic model of the drill arm. The joint activity data includes the rotation angle and movement distance of each joint.

[0015] In one implementation, the charge data includes the type and amount of charge for each borehole.

[0016] In one implementation, the over- or under-excavation data is obtained by scanning the area after blasting using a laser 3D scanning device.

[0017] Secondly, embodiments of the present invention provide a fully computerized rock drilling rig, comprising:

[0018] The controller executes the tunnel blasting construction method described above.

[0019] Thirdly, embodiments of the present invention provide an electronic device comprising a memory and a processor. The memory and the processor communicate with each other via an internal connection path. The memory stores instructions, and the processor executes the instructions stored in the memory. When the processor executes the instructions stored in the memory, it causes the processor to perform the method described in any of the above embodiments.

[0020] Fourthly, embodiments of the present invention provide a computer-readable storage medium that stores a computer program, wherein when the computer program is run on a computer, the methods in any of the embodiments described above are executed.

[0021] The advantages or beneficial effects of the above technical solutions include at least the following:

[0022] This invention uses a prediction model trained on a large amount of data to perform intelligent hole layout and intelligent charge calculation based on rock information obtained before drilling. This enables blasting to achieve optimal blasting advance and over- and under-excavation control effects with lower explosive costs and shorter drilling times. It reduces reliance on operator experience, improves the control level of over- and under-excavation, and reduces the waste of construction time and subsequent wet spraying materials.

[0023] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the invention will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0024] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in the invention and should not be construed as limiting the scope of the invention.

[0025] Figure 1 This is a schematic diagram of the tunnel blasting construction process of the present invention;

[0026] Figure 2 The image shows a rock obtained by means of this invention.

[0027] Figure 3 This is a schematic diagram of the over-excavation and under-excavation control of the present invention;

[0028] Figure 4 This is a schematic diagram of the prediction model training of the present invention;

[0029] Figure 5 This is a structural block diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0030] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0031] In tunnel blasting construction, controlling over- and under-excavation is crucial. Under-excavation necessitates secondary excavation, impacting subsequent arch-building processes and extending the construction period while increasing costs. Over-excavation increases the time required for wet shotcreting and wastes concrete, also significantly extending the construction period and raising costs. Therefore, controlling over- and under-excavation has become a critical point, attracting considerable attention. However, controlling over- and under-excavation in blasting is closely related to the geological distribution of the rock, the distribution of drill holes (location and angle), and the distribution of explosives (type and quantity) in different holes. During construction, these multiple processes and factors cause continuous changes in the rock. Effective over- and under-excavation control demands a high level of experience and adaptability from personnel, which is often insufficient for on-site construction needs. Existing over- and under-excavation control methods mostly consider only the rock, drill holes, or explosives, without taking a comprehensive approach.

[0032] To address the aforementioned problems, this invention provides a tunnel blasting construction method that enables intelligent hole layout and intelligent charge calculation, thereby achieving optimal blasting advance and over- and under-excavation control effects with lower explosive costs and shorter drilling times.

[0033] The tunnel blasting construction method can be executed on a designated server or on a fully computerized rock drilling vehicle used for drill-and-blast construction in tunnels and underground engineering, such as... Figure 1 As shown in the example, this embodiment uses a designated server as the execution object to illustrate the tunnel blasting construction method as follows:

[0034] Step S1: Obtain rock images before drilling, and use deep learning technology to extract rock features from the rock images, including rock type and rock distribution.

[0035] like Figure 2 As shown, in this embodiment, the rock image can be obtained by taking pictures with a drone. The drone, equipped with a supplementary light source, hovers at a certain height in front of the tunnel rock and takes high-definition pictures of the rock surface in front of the borehole, thereby obtaining the rock image.

[0036] The rock images are denoised to reduce noise interference and enhanced to improve the visibility and contrast of rock features.

[0037] A large dataset of rock images was collected and labeled, including different types of rocks and various distribution patterns. The dataset was divided into training, validation, and test sets to ensure the model's generalization ability. The deep learning model was trained using the training set to learn feature representations from the rock images. During training, the validation set was used to monitor the model's performance and make necessary adjustments and optimizations. Using the trained deep learning model, feature vectors were extracted from the rock images. These feature vectors reflect rock characteristics such as type, distribution, texture, and color.

[0038] Step S2: Obtain drilling data collected during the drilling process, and determine drilling characteristics based on the drilling data. Drilling characteristics include drilling location, drilling depth, diameter, direction, and angle.

[0039] Drilling data can be obtained by analyzing the joint movement data recorded by the drilling rig during the drilling process and the drilling operation data. The analysis of the joint movement data of the drilling rig based on the drill arm kinematic model includes the rotation angle and travel distance of each joint. Using the drill arm kinematic model and joint movement data, the position and orientation of the drill bit in three-dimensional space can be calculated. Based on the position and orientation of the drill bit, as well as the performance of the drilling rig and engineering requirements, the drilling data can be determined.

[0040] Simultaneously, drilling operation data for each borehole is recorded in real time during the drilling process. This data includes records of rotational pressure, impact pressure, and propulsion pressure during drilling. This embodiment incorporates borehole operation data to aid in rock feature identification. During drilling, the interaction between the drill bit and the rock generates various signals, such as vibration, sound, and temperature. These signals can be captured by sensors and converted into drilling operation data. By analyzing this data, certain rock characteristics can be indirectly inferred, such as the development of rock fractures and water content. Combining these inferred features with features extracted directly from rock images can further improve the accuracy of rock feature identification.

[0041] Furthermore, incorporating borehole operation data can enhance the reliability of subsequent feature relationship matching. For example, when abnormalities such as stuck drill bits or falling rocks appear in the borehole operation data, it can be inferred that the rock at that location may have high strength or be brittle. Combining these inferences with direct observations of rock characteristics can lead to more comprehensive and accurate feature relationship matching.

[0042] Step S3: Match the rock features with the borehole data to determine the relationship between the rock features and the borehole features.

[0043] Rock characteristics and borehole data are standardized or normalized to ensure they are compared on the same scale; incomplete or anomalous data records are removed, and errors and inconsistencies in the data are corrected.

[0044] The matching of rock characteristics with borehole data specifically includes:

[0045] Rock type-based matching:

[0046] By directly comparing the rock image classification results with the rock types of borehole core samples, classification algorithms (such as decision trees, support vector machines, etc.) are used to establish a correlation model between rock types and borehole features.

[0047] Feature vector-based matching:

[0048] The similarity between the feature vectors of the rock image and the feature vectors of the borehole core sample is calculated (e.g., cosine similarity, Euclidean distance, etc.); based on the similarity score, the correspondence between the rock features and the borehole features is determined.

[0049] Multi-feature fusion:

[0050] A comprehensive analysis is conducted by combining multiple features of the rock (such as texture, color, physical properties, etc.) with multiple features of the borehole (such as depth, strength, water content, etc.); machine learning algorithms (such as random forest, neural network, etc.) are used to establish a multi-feature fusion association model.

[0051] Association rule mining algorithms (such as Apriori, FP-Growth, etc.) are used to discover association rules between rock features and borehole features. These rules can describe which rock features usually appear together with which borehole features.

[0052] At the same time, visualization tools (such as scatter plots, heat maps, decision tree diagrams, etc.) can be used to show the relationship between rock features and borehole features, which helps to intuitively understand the interaction and correlation patterns between different features.

[0053] Furthermore, data collected during geological exploration and mining can be used to establish correlation models to more accurately determine the relationship between rock characteristics and borehole characteristics.

[0054] Step S4: Obtain the charge data for each borehole and the over-excavation and under-excavation data after charge blasting. Use statistical algorithms to analyze the correlation between charge data, over-excavation and under-excavation data and borehole data. Establish a prediction model based on the correlation analysis results and train the prediction model to determine the quantitative relationship between charge data, over-excavation and under-excavation data, rock characteristics and borehole characteristics.

[0055] In this embodiment, the charge data includes the type of explosive, the amount of explosive, the charging method (continuous charging or segmented charging), and the charging depth for each borehole.

[0056] Over-excavation and under-excavation data refers to the difference between the actual and expected diameter of the borehole after blasting (over-excavation is a positive difference, under-excavation is a negative difference), and the distribution of these differences across the borehole depth. Over-excavation and under-excavation data can be obtained by scanning with laser 3D scanning or similar methods to acquire 3D data. This 3D data is then analyzed to determine the over-excavation and under-excavation results. Specifically, a 3D laser scanner or similar equipment is used to scan the blasted tunnel to acquire high-precision 3D point cloud data. The acquired 3D point cloud data undergoes preprocessing operations such as denoising and filtering to improve data quality. The point cloud data is then converted into a format suitable for subsequent analysis, such as a mesh model or triangular mesh model. The actual 3D model obtained from the scan is overlaid and compared with the target model. Through comparative analysis, the difference between the actual tunnel shape and the target model is determined, i.e., the over-excavation and under-excavation data. The target model contains key information such as the expected shape, size, and location of the tunnel.

[0057] like Figure 3 As shown, during the overlay comparison process, the actual outline of the tunnel can be extracted and compared with the target outline to calculate the values ​​and locations of over-excavation and under-excavation. Different colors or markers are used to represent the over-excavation and under-excavation areas so as to intuitively understand the over-excavation and under-excavation situation of the tunnel.

[0058] In this embodiment, statistical algorithms are used to analyze the correlation between charge data, over-excavation and under-excavation data, and borehole data. Statistical methods such as Pearson correlation coefficient and Spearman rank correlation coefficient can be used to calculate the correlation between charge data, over-excavation and under-excavation data, and borehole data.

[0059] To address the nonlinear relationships among the aforementioned variables, interactive features such as the product of charge quantity and borehole depth, and the product of rock hardness and borehole diameter, can be considered. These interactive features reveal how the variables collectively influence over- and under-explosion phenomena, thereby improving the accuracy of the prediction model. For example, the product of charge quantity and borehole depth may indicate that a larger charge quantity is required in deeper boreholes to achieve the desired blasting effect.

[0060] Interactive features can be created manually, meaning their values ​​can be calculated manually and added to the dataset as new features. For example, the product of the explosive charge and the borehole depth can be calculated and used as a new feature.

[0061] Alternatively, polynomial feature extension can be used to automatically generate interactive features by combining the original features in a polynomial fashion. For example, quadratic polynomial feature extension can automatically generate features such as charge amount, borehole depth, and their product.

[0062] Alternatively, deep learning models (such as neural networks) can automatically learn the interactions between features without manually creating them. By building deep neural networks, the model can discover which feature combinations are most helpful for predictions, thereby determining the correlations between various variables.

[0063] It's important to note that correlation analysis typically only indicates whether a relationship exists between variables and the direction of that relationship (positive or negative), but it cannot provide a specific quantitative measure of the relationship. Learning models, on the other hand, can establish mathematical expressions between variables, thus enabling a more precise quantification of the relationships between various variables.

[0064] Therefore, based on the results of correlation analysis and the characteristics of the data, this embodiment selects an appropriate prediction model type, such as linear regression, nonlinear regression, decision tree, random forest, neural network, etc., and collects a large dataset to train the prediction model. Figure 4 As shown, the dataset includes rock images, borehole data, explosive charge data, and over- and under-drilling data, and the correlations between various data are marked in the dataset to facilitate model training.

[0065] During the training process, a reward function is designed with the following evaluation objectives: over-drilling and under-drilling profile control, drilling time and explosive cost, and maximizing the ratio of blasting advance to drilling depth.

[0066] Over-excavation and under-excavation profile control evaluates the predictive model's ability to control the rock excavation profile during drilling and blasting operations. The predictive model needs to learn how to minimize over-excavation (excavation exceeding the design profile) and under-excavation (excavation failing to reach the design profile) by adjusting borehole data and charge quantity. During training, the predictive model will attempt to predict the profile after blasting (e.g.,...). Figure 5 (as shown), and optimizes its decision by comparing the actual profile with the design profile.

[0067] The evaluation objective, focusing on the efficiency and cost of drilling operations, considers drilling time and explosive usage. The predictive model needs to learn to reduce drilling time and explosive usage while maintaining blasting effectiveness, thereby lowering costs. During training, the predictive model will consider both time and material costs, optimizing borehole distribution and charging strategies to reduce overall costs.

[0068] The evaluation objective is to maximize the ratio of blasting advance to borehole depth. This ratio aims to maximize the ratio of the advance (distance the rock moves after blasting) to the borehole depth for each blast. The predictive model needs to learn how to improve blasting efficiency by optimizing borehole and charge parameters. During training, the predictive model will attempt to maximize this ratio to improve the efficiency of blasting operations.

[0069] During training, the model learns how to select the optimal action based on the current state to maximize long-term rewards. After training, the model's performance is evaluated using an independent test set. Evaluation metrics may include reductions in over- and under-drilling profile errors, decreases in drilling time and explosive costs, and improvements in blasting efficiency. Based on the evaluation results, the reward function, reinforcement learning algorithm, and model architecture are adjusted iteratively, and the training steps are repeated until the model's performance meets the requirements.

[0070] After training, a predictive model can be obtained that can output borehole distribution maps and explosive charge information from an input rock image.

[0071] Step S5: During the actual construction process, construction photos are obtained, which include the rock area. The construction photos are analyzed based on the prediction model to output the borehole distribution map and charge information. Tunnel blasting is carried out according to the borehole distribution map and charge information to keep the over-excavation and under-excavation profiles after blasting within the preset range.

[0072] This embodiment uses a high-definition camera to take photos of rocky areas at the construction site, marking the target outline of the tunnel construction in the photos to determine the tunnel's size and location. The construction photos must be clear, evenly lit, and cover the entire construction area. These real-time photos are input into a trained prediction model. The model analyzes the input photos, identifies rocky areas, and predicts borehole locations and explosive charge information. Based on the analysis results, it generates a borehole distribution map and an explosive charge information report, which may include the borehole location, depth, diameter, explosive type, and quantity.

[0073] Tunnel blasting is carried out based on borehole distribution maps and charge information. After blasting, the tunnel is scanned and measured using surveying tools or drones to evaluate the blasting effect. Based on the evaluation results, necessary adjustments are made to the borehole distribution maps and charge information. If over- or under-excavation exceeds the preset range, the photos need to be re-analyzed and the strategy adjusted. Ultimately, it is ensured that the over- or under-excavation profile of the tunnel after blasting remains within the preset range. In this embodiment, the preset range is that the maximum over-excavation should be less than or equal to 15cm, the average over- or under-excavation should be less than or equal to 10cm, and the maximum under-excavation should be less than or equal to 5cm, in order to improve the control level of over- or under-excavation and reduce the waste of construction time and subsequent wet spraying materials.

[0074] Another embodiment of the present invention provides a fully computerized rock drilling rig, comprising:

[0075] The measurement system includes drones and cameras integrated on a fully computerized rock drilling rig, used to capture rock images and scan for over- and under-excavation data. The drones and cameras can be integrated on the fully computerized rock drilling rig used for tunnel and underground engineering drilling and blasting construction, and the rock images and over- and under-excavation data collected by the drones and cameras can be transmitted to the controller of the fully computerized rock drilling rig for analysis through a designated data interface.

[0076] The rock drilling system, integrated on a fully computerized rock drilling rig, is used to record drilling data during the drilling process and transmit the drilling data to the controller of the fully computerized rock drilling rig.

[0077] The charging system, integrated on the fully computerized rock drilling rig, is used to load explosives into the boreholes for blasting and to record the type and quantity of explosives for each borehole. This information is then transmitted to the controller of the fully computerized rock drilling rig, thereby linking the charging data with the distribution map and drilling operation parameters of each borehole.

[0078] The controller is integrated into the fully computerized rock drilling rig. In this embodiment, the trained prediction model can be embedded into the controller of the fully computerized rock drilling rig, so that the tunnel blasting construction method described above can be executed on the fully computerized rock drilling rig.

[0079] This embodiment integrates the predictive model into the host computer of a fully computerized rock drilling rig. Through extensive data training, the rig is transformed into a system capable of intelligently planning hole layout and calculating explosive charges based on rock information obtained before drilling. This enables blasting to achieve optimal blasting progress and over- and under-drilling control with lower explosive costs and shorter drilling times. Furthermore, a charging robot can be directly integrated into the fully computerized rock drilling rig, utilizing its fully computerized positioning system to achieve automatic hole finding and charging functions after drilling.

[0080] The functions of each module in the fully computerized rock drilling rig of this invention can be found in the corresponding descriptions in the above methods, and will not be repeated here.

[0081] Another embodiment of the present invention provides an electronic device, Figure 5 A structural block diagram of an electronic device according to an embodiment of the present invention is shown. Figure 5 As shown, the electronic device includes a memory 100 and a processor 200. The memory 100 stores a computer program that can run on the processor 200. When the processor 200 executes the computer program, it implements the tunnel blasting construction method described in the above embodiments. The number of memories 100 and processors 200 can be one or more.

[0082] The electronic device also includes:

[0083] The communication interface 300 is used to communicate with external devices and perform data exchange and transmission.

[0084] If the memory 100, processor 200, and communication interface 300 are implemented independently, they can be interconnected via a bus to communicate with each other. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc.

[0085] Optionally, in a specific implementation, if the memory 100, processor 200, and communication interface 300 are integrated on a single chip, then the memory 100, processor 200, and communication interface 300 can communicate with each other through an internal interface.

[0086] This invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method provided in this invention.

[0087] This invention also provides a chip, which includes a processor for calling and executing instructions stored in a memory, causing a communication device on which the chip is installed to perform the method provided in this invention.

[0088] This invention also provides a chip, including: an input interface, an output interface, a processor, and a memory. The input interface, output interface, processor, and memory are connected through an internal connection path. The processor is used to execute code in the memory. When the code is executed, the processor is used to execute the method provided in this invention.

[0089] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting the Advanced Reduced Instruction Set Computing (RISC) machine (ARM) architecture.

[0090] Further, optionally, the aforementioned memory may include read-only memory and random access memory, and may also include non-volatile random access memory. The memory may be volatile or non-volatile, or may include both. Non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which serves as an external cache. Many forms of RAM are available by way of example, but not limitation. Examples include static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0091] In the above embodiments, implementation can be achieved, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.

[0092] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0093] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0094] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in the present invention, and these should all be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method of tunnel blasting construction, characterized in that, The method comprises the following steps: acquiring a rock image before drilling, and extracting rock features from the rock image by using deep learning technology, wherein the rock features include rock types and rock distribution, and the rock image is obtained by taking a picture when a drone hovers in front of the tunnel rock; acquiring drilling data collected during drilling, and determining drilling features according to the drilling data, wherein the drilling features include drilling positions, drilling depths, diameters, directions and angles; matching the rock features and the drilling data to determine the relationship between the rock features and the drilling features; acquiring charging data of each drilling hole and overbreak and underbreak data after blasting, wherein the charging data includes the explosive type, explosive amount, charging method and charging depth of each drilling hole, and the charging method is continuous charging or segmented charging; analyzing the correlation among the charging data, the overbreak and underbreak data and the drilling data by using a statistical algorithm, establishing a prediction model according to the correlation analysis result, and training the prediction model to determine the quantitative relationship among the charging data, the overbreak and underbreak data, the rock features and the drilling features, wherein, in the training process, the overbreak and underbreak profile control, the cost of drilling time and explosive amount, and the maximum ratio of blasting footage to drilling depth are taken as evaluation targets to optimize the prediction model; acquiring construction photos in the actual construction process, wherein the construction photos contain the area where the rock is located, analyzing the construction photos based on the prediction model, outputting a drilling distribution map and a charging information report, and performing tunnel blasting construction according to the drilling distribution map and the charging information report, so that the overbreak and underbreak profile after blasting construction is kept within a preset range.

2. The method of tunnel blasting according to claim 1, wherein, The preset range is that the maximum overbreak is less than or equal to 15 cm, the average overbreak is less than or equal to 10 cm, and the maximum underbreak is less than or equal to 5 cm.

3. The method of tunnel blasting according to claim 1, wherein The drilling data is obtained by analyzing joint activity data of a rock drilling jumbo based on a drilling arm kinematics model, wherein the joint activity data includes the rotation angle and movement distance of each joint.

4. The tunneling method according to claim 1, wherein The overbreak and underbreak data is obtained by scanning the blasting site by using a laser three-dimensional scanning device.

5. A fully computerized drill jumbo, characterized in that The method comprises the following steps: A controller is used to execute the tunnel blasting construction method according to any one of claims 1 to 4.

6. An electronic device, comprising: A processor and a memory are used to execute the tunnel blasting construction method according to any one of claims 1 to 4. A computer program is stored in a computer readable storage medium, and the computer program is executed by a processor to implement the tunnel blasting construction method according to any one of claims 1 to 4.

7. A computer readable storage medium characterized in that, ​

Images