Tunnel blasting construction method, full-computer drill jumbo, electronic equipment and storage medium

Abstract

The invention provides a tunnel blasting construction method, a full-computer drill jumbo, electronic equipment and a storage medium, and the method comprises the following steps: obtaining a construction photo in an actual construction process, analyzing the construction photo based on a pre-constructed prediction model, outputting a drilling distribution diagram and charging information, and tunnel blasting construction is conducted according to the drilling distribution diagram and the charging information, and the back break profile after blasting construction is kept within a preset range. The prediction model is obtained based on a large amount of data training, intelligent hole arrangement and intelligent explosive loading amount calculation are carried out according to rock information obtained before drilling, the optimal blasting footage and back break control effect is obtained under the conditions of low explosive cost and short drilling time in blasting, dependence on experience of operators is reduced, and the blasting efficiency is improved. The control level of back break is improved, the construction period is shortened, and waste of follow-up wet spraying materials is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel construction, and in particular to a tunnel blasting construction method, a fully computerized rock drilling trolley, an electronic device and a storage medium. Background Art

[0002] In tunnel blasting construction, over-break and under-break control is very important. Under-break and secondary excavation will also affect subsequent arching processes, resulting in extended construction periods and increased construction costs. Over-break will increase the working time of subsequent wet spraying and waste of wet spraying concrete, which will also cause a huge extension of the construction period and increased construction costs. Over-break and under-break control has become a key control point and has attracted great attention. However, the control of blasting over-break and under-break is closely related to the geological distribution of rocks, the distribution of drilling holes (position and angle), and the distribution of explosives in different holes (type and amount of explosives). During the construction process, the influence of these multiple processes and multiple factors will cause the rocks to change continuously. Therefore, the traditional method of controlling over-break and under-break through personnel experience generally has the problem of low accuracy and cannot meet the needs of on-site construction. Summary of the invention

[0003] The embodiment of the present invention provides a tunnel blasting construction method, a fully computerized rock drilling trolley, an electronic device and a storage medium to solve the problems existing in the related technologies. The technical solution is as follows:

[0004] In a first aspect, an embodiment of the present invention provides 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. Rock features include rock type and rock distribution;

[0006] Acquire drilling data collected during the drilling process, and determine drilling characteristics based on the drilling data, the drilling characteristics including drilling position, drilling depth, diameter, direction, and angle;

[0007] Match rock features and drilling data to determine the relationship between rock features and drilling features;

[0008] Obtain the charge data of each borehole and the overbreak and underbreak data after charge blasting, use statistical algorithms to analyze the correlation between charge data, overbreak 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, overbreak data, rock characteristics and borehole characteristics;

[0009] During the actual construction process, construction photos are obtained. The construction photos include the area where the rocks are located. The construction photos are analyzed based on the prediction model, and the drilling distribution map and charging information are output. Tunnel blasting construction is carried out according to the drilling distribution map and charging information to keep the over-excavation and under-excavation contours after blasting construction within the preset range.

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

[0011] During the training process, the over-break and under-break contour control, drilling time and explosive usage cost, and maximization of the ratio of blasting footage to drilling depth are used as evaluation objectives to achieve the optimization of the prediction model.

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

[0013] In one embodiment, the rock image is obtained by hovering a drone in front of the tunnel rock and taking photos.

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

[0015] In one embodiment, the charge data includes charge type and charge quantity information for each borehole.

[0016] In one embodiment, the over-break and under-break data are obtained by scanning the blasting area using a laser 3D scanning device.

[0017] In a second aspect, an embodiment of the present invention provides a fully computerized rock drilling rig, comprising:

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

[0019] In a third aspect, an embodiment of the present invention provides an electronic device, the device comprising: a memory and a processor. The memory and the processor communicate with each other through an internal connection path, the memory is used to store instructions, the processor is used to execute the instructions stored in the memory, and when the processor executes the instructions stored in the memory, the processor executes the method in any one of the above-mentioned embodiments.

[0020] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a computer, the method in any one of the above-mentioned embodiments is executed.

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

[0022] The present invention obtains a prediction model based on a large amount of data training, and performs intelligent hole arrangement and intelligent charge calculation according to the rock information obtained before drilling, so that the blasting can achieve the optimal blasting footage and over-break and under-break control effects with low explosive cost and short drilling time, reduce dependence on operator experience, improve the control level of over-break and under-break, and reduce construction period and waste of subsequent wet spraying materials.

[0023] The above summary 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 present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

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

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

[0026] Figure 2 Rock images taken for the present invention;

[0027] Figure 3 This is a schematic diagram of over-break and under-break 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 The structure block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0031] In tunnel blasting construction, over-break and under-break control is very important. Under-break and secondary excavation will also affect subsequent arching and other processes, resulting in an extension of the construction period and an increase in construction costs. Over-break will increase the working time of subsequent wet spraying and the waste of wet spraying concrete, which will also cause a huge extension of the construction period and an increase in construction costs. Over-break and under-break control has become a key control point and has attracted great attention. However, the control of blasting over-break and under-break is closely related to the geological distribution of rocks, the distribution of drilling holes (position and angle), and the distribution of explosives in different holes (type and amount of explosives). During the construction process, the influence of these multiple processes and multiple factors will cause the rocks to change continuously. Good over-break and under-break control requires extremely high experience and adaptability of personnel, which cannot meet the needs of on-site construction. Most of the existing over-break and under-break controls either consider rocks, drilling holes, or explosives, but do not take them into comprehensive consideration.

[0032] In order to solve the above problems, an embodiment of the present invention provides a tunnel blasting construction method, which can realize intelligent hole layout and intelligent charge calculation, so that the blasting can achieve the optimal blasting footage and over-excavation and under-excavation control effect with low explosive cost and short drilling time.

[0033] The execution object of the tunnel blasting construction method can be a designated server or a fully computerized rock drilling vehicle used for tunnel and underground engineering drilling and blasting construction, such as Figure 1 As shown, in this embodiment, taking the execution object as a designated server as an example, the tunnel blasting construction method includes the following:

[0034] Step S1: Obtain a rock image before drilling, and use deep learning technology to extract rock features from the rock image. The rock features include 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. After the drone equipped with a fill light source hovers at a certain height in front of the tunnel rock, high-definition photos of the rock on the rock surface before drilling are taken to obtain the rock image.

[0036] The rock images were denoised to reduce noise interference in the images, and image enhancement was performed to improve the visibility and contrast of rock features.

[0037] Collect and annotate a large number of rock image datasets, including different types of rocks and different distribution patterns; divide the dataset into training set, validation set, and test set to ensure the generalization ability of the model. Use the training set to train the deep learning model to learn the feature representation in the rock image. During the training process, use the validation set to monitor the performance of the model and make necessary adjustments and optimizations. Use the trained deep learning model to extract feature vectors from the rock image. These feature vectors can reflect rock characteristics such as rock type, rock distribution, texture, color, etc.

[0038] Step S2: Acquire drilling data collected during the drilling process, and determine drilling features based on the drilling data. The drilling features include drilling position, drilling depth, diameter, direction, and angle.

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

[0040] At the same time, the drilling operation data of each borehole during the drilling construction process is recorded in real time. The drilling operation data includes data records such as the rotation pressure, impact pressure, and thrust pressure of each hole during the drilling process. This embodiment incorporates drilling operation data to assist in rock feature identification, that is, during the drilling process, the interaction between the drill and the rock will generate various signals, such as vibration, sound, temperature, etc. These signals can be captured by sensors and converted into drilling operation data. By analyzing these data, certain characteristics of the rock can be indirectly inferred, such as the development of rock fractures and water content. These inferred features are combined with features extracted directly from rock images to further improve the accuracy of rock feature identification.

[0041] In addition, incorporating drilling operation data can also enhance the reliability of subsequent feature relationship matching. For example, when abnormal conditions such as drill sticking and block falling appear in the drilling operation data, it can be inferred that the rock there may have high strength or brittleness. These inferences combined with direct observations of rock characteristics can form a more comprehensive and accurate feature relationship matching.

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

[0043] Standardize or normalize rock characteristics and drill hole data to ensure they are compared on the same scale; remove incomplete or anomalous data records and correct errors and inconsistencies in the data.

[0044] The matching of rock characteristics and drilling data includes:

[0045] Matching based on rock type:

[0046] Directly compare the rock image classification results with the rock types of the drill core samples, and use classification algorithms (such as decision trees, support vector machines, etc.) to establish an association model between rock types and drill hole characteristics.

[0047] Matching based on feature vectors:

[0048] The similarity between the feature vector of the rock image and the feature vector of the drill core sample is calculated (such as cosine similarity, Euclidean distance, etc.); based on the similarity score, the correspondence between the rock characteristics and the drill hole characteristics is determined.

[0049] Multi-feature fusion:

[0050] Combine multiple characteristics of rock (such as texture, color, physical properties, etc.) with multiple characteristics of borehole (such as depth, strength, water content, etc.) for comprehensive analysis; use machine learning algorithms (such as random forests, neural networks, etc.) 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 drill hole features. These rules can describe which rock features usually appear with which drill hole features.

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

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

[0054] Step S4: Obtain the charging data of each borehole and the over-break and under-break data after charging and blasting, use statistical algorithms to analyze the correlation between the charging data, over-break data and drilling data, establish a prediction model based on the correlation analysis results, and train the prediction model to determine the quantitative relationship between the charging data, over-break data, rock characteristics and drilling characteristics.

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

[0056] The over-break and under-break data are the difference between the actual diameter of the borehole after blasting and the expected diameter (over-break is a positive difference, under-break is a negative difference), as well as the distribution of these differences in the depth of the borehole. The over-break and under-break data can be obtained by scanning three-dimensional data through laser three-dimensional scanning and other methods, and the three-dimensional data is analyzed to obtain the over-break and under-break results. Specifically, a three-dimensional laser scanner or similar equipment is used to scan the tunnel after blasting to obtain high-precision three-dimensional point cloud data, and the obtained three-dimensional point cloud data is pre-processed by denoising and filtering to improve data quality; the point cloud data is converted into a format suitable for subsequent analysis, such as a mesh model or a triangulated network model, and the three-dimensional model obtained by the actual scan is superimposed and compared with the target model. Through comparison and analysis, the difference between the actual tunnel shape and the target model, that is, the over-break and under-break data, is determined. The target model contains key information such as the expected shape, size and position of the tunnel.

[0057] like Figure 3 As shown, during the overlay comparison process, the actual contour line of the tunnel can be extracted and compared with the target contour line, the values ​​and positions of overbreak and underbreak can be calculated, and different colors or marks can be used to indicate the overbreak and underbreak areas, so as to intuitively understand the overbreak and underbreak conditions of the tunnel.

[0058] In this embodiment, a statistical algorithm is used to analyze the correlation between charging data, overbreak data and drilling data. Statistical methods such as the Pearson correlation coefficient and the Spearman rank correlation coefficient can be used to calculate the correlation between charging data, overbreak data and drilling data.

[0059] For the nonlinear relationship between the above variables, the interactive features such as the product of charge and borehole depth, the product of rock hardness and borehole diameter can be considered to reveal how the variables jointly affect the over-break phenomenon, thereby improving the accuracy of the prediction model. For example, the product of charge and borehole depth may indicate that in a deeper borehole, more charge is required to achieve the expected blasting effect.

[0060] Among them, interactive features can be created manually, that is, the values ​​of these interactive features are manually calculated and added to the dataset as new features. For example, the product of the charge and the borehole depth can be calculated and used as a new feature.

[0061] Alternatively, use polynomial feature expansion to automatically generate interactive features by combining the original features into polynomial combinations. For example, using quadratic polynomial feature expansion, you can automatically generate features for charge, borehole depth, and their product.

[0062] Alternatively, deep learning models (such as neural networks) can be used to automatically learn the interactions between features without manually creating interactive features. By building a deep neural network, the model can discover which feature combinations are most helpful for predicting results, thereby determining the correlation between various variables.

[0063] It should be noted that correlation analysis can usually only provide information on whether there is a relationship between variables and the direction of the relationship (positive or negative correlation), but cannot provide a specific quantitative relationship. The learning model can establish mathematical expressions between variables, thereby more accurately quantifying the relationship between various variables.

[0064] Therefore, this embodiment selects a suitable prediction model type, such as linear regression, nonlinear regression, decision tree, random forest, neural network, etc., according to the results of correlation analysis and the characteristics of the data, and collects a large amount of data sets to train the prediction model. Figure 4 As shown, the data set includes rock images, drilling data, charging data, and over-excavation and under-excavation data, and the correlations between various data are marked in the data set to facilitate model training.

[0065] During the training process, a reward function is designed with the over-break and under-break contour control, drilling time and explosive usage cost, and maximization of the ratio of blasting footage to drilling depth as evaluation objectives.

[0066] Among them, overbreak and underbreak contour control is to evaluate the ability of the prediction model to control the rock excavation contour during drilling and blasting operations. The prediction model needs to learn how to minimize overbreak (excavation exceeding the designed contour) and underbreak (excavation that does not reach the designed contour) by adjusting the drilling data and charge amount. During training, the prediction model will try to predict the contour after blasting (such as Figure 5 ), and optimizes its decision by comparing the actual profile with the designed profile.

[0067] Drilling time and explosive usage cost, this evaluation objective focuses on the efficiency and cost of drilling operations. The prediction model needs to learn to reduce drilling time and explosive usage while ensuring blasting results to reduce costs. During training, the prediction model will consider time cost and material cost, and reduce overall costs by optimizing drilling distribution and charging strategies.

[0068] The ratio of blasting footage to drilling depth is maximized. This evaluation goal aims to maximize the ratio of each blasting footage (the distance the rock moves after blasting) to drilling depth. The prediction model needs to learn how to improve blasting efficiency by optimizing drilling and charging parameters. During training, the prediction model will try to maximize this ratio to improve the efficiency of blasting operations.

[0069] During the training process, the model will learn how to choose the best action based on the current state to maximize the long-term reward. After the training is completed, the performance of the model is evaluated using an independent test set. Evaluation indicators can include the reduction of over-break and under-break contour errors, the reduction of drilling time and explosives costs, and the improvement of blasting efficiency. According to the evaluation results, the reward function, reinforcement learning algorithm, model architecture, etc. are adjusted, iterative optimization is performed, and the training steps are repeated until the model performance meets the requirements.

[0070] After learning and training, a prediction model is obtained that can output a drilling distribution map and charging information by inputting a rock image.

[0071] Step S5: Acquire construction photos during the actual construction process. The construction photos include the area where the rocks are located. Analyze the construction photos based on the prediction model, output the drilling distribution map and charging information, and perform tunnel blasting construction according to the drilling distribution map and charging information, so that the over-break and under-break contours after the blasting construction are kept within a preset range.

[0072] In this embodiment, a high-definition camera is used to take photos of rock areas at the construction site, and the target outline of the tunnel construction is marked in the photos, so as to determine the size and location of the tunnel; wherein, the construction photos must ensure that the photos are clear, the light is even, and cover the entire construction area. Photos taken in real time at the construction site are input into the trained prediction model, which analyzes the input photos, identifies the rock areas, and predicts the drilling location and charging information. Based on the analysis results of the prediction model, a drilling distribution map and charging information report are generated, which may include the location, depth, diameter, type and amount of explosives, etc. of the drilling holes.

[0073] Tunnel blasting construction is carried out according to the drilling distribution map and charging information. After the blasting construction, use measuring tools or equipment such as drones to scan and measure the tunnel, evaluate the blasting effect, and make necessary adjustments to the drilling distribution map and charging information based on the evaluation results of the blasting effect. If the over-break and under-break situation exceeds the preset range, it is necessary to re-analyze the photos and adjust the strategy. Ultimately, ensure that the over-break and under-break contour of the tunnel after blasting remains within the preset range. In this embodiment, the preset range is that the maximum over-break must be less than or equal to 15cm, the average over-break must be less than or equal to 10cm, and the maximum under-break must be less than or equal to 5cm, so as to improve the control level of over-break and under-break and reduce the construction period and subsequent waste of 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 the fully computerized rock drilling rig, which are used to capture rock images and scan to obtain overbreak and underbreak data. The drones and cameras can be integrated on the fully computerized rock drilling rig used for drilling and blasting construction of tunnels and underground projects, and the rock images and overbreak and underbreak data collected by the drones and cameras can be transmitted to the controller of the fully computerized rock drilling rig for analysis through designated data interfaces.

[0076] The rock drilling system, integrated on the fully computerized rock drilling rig, is used to record the 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 in the fully computerized rock drilling rig, is used to load explosives into the boreholes for blasting, record the type and amount of charge for each borehole, and transmit the information to the controller of the fully computerized rock drilling rig, thereby associating the charging data with the distribution map of each borehole and the drilling operation parameters.

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

[0079] This embodiment integrates the prediction model into the host computer of the fully computerized rock drilling rig. Through a large amount of data training, the fully computerized rock drilling rig is transformed into a machine that can intelligently arrange holes and intelligently calculate the charge amount according to the rock information obtained before drilling, so that the blasting can achieve the optimal blasting footage and over-excavation and under-excavation control effect with low explosive cost and short drilling time. The charging manipulator can also be directly integrated on the fully computerized rock drilling rig, and the fully computerized positioning system of the fully computerized rock drilling rig can be used to realize the automatic hole finding and charge charging functions after rock drilling.

[0080] The functions of each module in the fully computerized rock drilling rig in the embodiment of the present invention can be found in the corresponding description in the above method, which will not be repeated here.

[0081] Another embodiment of the present invention provides an electronic device, Figure 5 FIG. 2 shows a structural block diagram of an electronic device according to an embodiment of the present invention. Figure 5 As shown, the electronic device includes: a memory 100 and a processor 200. The memory 100 stores a computer program that can be run on the processor 200. When the processor 200 executes the computer program, the tunnel blasting construction method in the above embodiment is implemented. The number of the memory 100 and the processor 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 transmission.

[0084] If the memory 100, the processor 200 and the communication interface 300 are implemented independently, the memory 100, the processor 200 and the communication interface 300 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The 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, the processor 200 and the communication interface 300 are integrated on a chip, the memory 100, the processor 200 and the communication interface 300 can communicate with each other through an internal interface.

[0086] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which implements the method provided in the embodiment of the present invention when executed by a processor.

[0087] An embodiment of the present invention further provides a chip, which includes a processor for calling and executing instructions stored in the memory from the memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present invention.

[0088] An embodiment of the present invention also provides a chip, including: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided by the embodiment of the invention.

[0089] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the advanced RISC machines (ARM) architecture.

[0090] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct rambus RAM (DR RAM).

[0091] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present invention is generated in whole or in part. 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 transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0092] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0093] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0094] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of various changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A tunnel blasting construction method, characterized in that: include: Obtaining a rock image before drilling, and extracting rock features from the rock image using deep learning technology, wherein the rock features include rock type and rock distribution; Acquire drilling data collected during the drilling process, and determine drilling characteristics according to the drilling data, wherein the drilling characteristics include drilling position, drilling depth, diameter, direction, and angle; Matching the rock features and the drilling data to determine the relationship between the rock features and the drilling features; Obtaining the charging data of each borehole and the overbreak and underbreak data after charging and blasting, using a statistical algorithm to analyze the correlation between the charging data, the overbreak and underbreak data, and the borehole data, establishing a prediction model based on the correlation analysis results, and training the prediction model to determine the quantitative relationship between the charging data, the overbreak and underbreak data, the rock characteristics, and the borehole characteristics; During the actual construction process, construction photos are obtained, the construction photos include the area where the rocks are located, the construction photos are analyzed based on the prediction model, a drilling distribution map and charging information are output, and tunnel blasting construction is performed according to the drilling distribution map and the charging information, so that the over-break and under-break contours after the blasting construction are kept within a preset range.

2. The tunnel blasting construction method according to claim 1, characterized in that: The training of the prediction model comprises: During the training process, the over-break and under-break contour control, drilling time and explosive usage cost, and maximization of the ratio of blasting footage to drilling depth are used as evaluation targets to achieve optimization of the prediction model.

3. The tunnel blasting construction method according to claim 1, characterized in that: The preset range is that the maximum over-break must be less than or equal to 15 cm, the average excess must be less than or equal to 10 cm, and the maximum under-break must be less than or equal to 5 cm.

4. The tunnel blasting construction method according to claim 1, characterized in that: The rock image is obtained by hovering a drone in front of the tunnel rock and taking photos.

5. The tunnel blasting construction method according to claim 1, characterized in that: The drilling data is obtained by analyzing the joint activity data of the drilling trolley based on the kinematic model of the drill arm, and the joint activity data includes the rotation angle and movement distance of each joint.

6. The tunnel blasting construction method according to claim 1, characterized in that: The charge data includes charge type and charge quantity information of each borehole.

7. The tunnel blasting construction method according to claim 1, characterized in that: The over-break and under-break data are obtained by scanning the blasting site using a laser three-dimensional scanning device.

8. A fully computerized rock drilling rig, characterized in that: include: A controller for executing the tunnel blasting construction method according to any one of claims 1 to 7.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement the tunnel blasting construction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the tunnel blasting construction method according to any one of claims 1 to 7 is implemented.

Images