Information processing device and information processing method
The information processing device and method improve blasting accuracy in tunnels by analyzing hydraulic and drilling data with 3D scanners and machine learning to optimize blasting patterns, reducing over-excavation and under-excavation.
Patent Information
- Application Number
- JP2023073642
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-04-27
- Publication Date
- 2024-11-08
AI Technical Summary
Conventional blasting technologies struggle to design accurate blasting patterns that minimize over-excavation and under-excavation in tunnels, despite efforts to reduce variations among workers.
An information processing device and method that includes hydraulic data acquisition, drilling data acquisition, excavation surface data acquisition, and analysis of these data to calculate optimal blasting patterns using hydraulic rock drills, 3D scanners, and machine learning for improved accuracy.
Enhances blasting accuracy by analyzing excavation surfaces, drilling positions, and charge amounts, reducing over-excavation and under-excavation, and optimizing explosive use, thereby improving efficiency and reducing material and time costs.
Smart Images

Figure 2024158438000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an information processing device and an information processing method for drilling holes in tunnels and the like. [Background technology]
[0002] At blasting sites such as tunnels, a technology has been developed to design blasting patterns that are performed based on the experience and intuition of workers with less variation among workers. For example, Patent Document 1 discloses a tunnel construction management system that inputs the drilling pattern and explosive amount adopted in the blasting process, three-dimensional tunnel shape data, noise and vibration data, and spring water volume data, and predicts the drilling pattern and explosive amount to be adopted in the next blasting process based on the tunnel shape change acquired from the three-dimensional tunnel shape data, the geological situation acquired from the noise and vibration data, the water volume change acquired from the spring water volume data, and the first drilling pattern and explosive amount. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2023-3192 A Summary of the Invention [Problem to be solved by the invention]
[0004] However, with conventional technology, even if variation between workers was reduced, it was difficult to design a more accurate blasting pattern that minimized overexcavation and insufficient excavation due to blasting.
[0005] Therefore, the present invention has been made in consideration of the above-mentioned problems, and one example of the object of the present invention is to provide an information processing device and an information processing method for further improving blasting accuracy. [Means for solving the problem]
[0006] In order to solve the above problem, the invention described in claim 1 is characterized by comprising a hydraulic data acquisition means for acquiring hydraulic data when drilling a natural ground with a hydraulic rock drill, a drilling data acquisition means for acquiring drilling data including the drilling position of a blast hole by the hydraulic rock drill, a charge amount acquisition means for acquiring the charge amount of explosives loaded into the blast hole, an excavation surface data acquisition means for acquiring excavation surface data of the excavation surface after blasting, and an analysis means for analyzing the blasting results based on the hydraulic data, the drilling data, and the excavation surface data for the charge amount.
[0007] The invention described in claim 2 is characterized in that the hydraulic pressure data is data on rotation pressure, feed pressure, and impact pressure, and the drilling data is data on drilling position and drilling angle.
[0008] The invention described in claim 3 is further characterized in that it includes a hardness / softness distribution analysis means for analyzing the hardness / softness distribution of the ground from the hydraulic data and the drilling data, and the analysis means analyzes the blasting results according to the hardness / softness distribution and the excavation surface data for the charge amount.
[0009] The invention described in claim 4 is characterized in that it further includes a blasting pattern calculation means for calculating a blasting pattern of the drilling position and charge amount for the next blasting based on the analysis results of the blasting results.
[0010] The invention described in claim 5 is characterized in that it includes a hydraulic data acquisition step in which a hydraulic data acquisition means acquires hydraulic data when a drilling is performed on a ground by a hydraulic rock drill; a drilling data acquisition step in which a drilling data acquisition means acquires drilling data including the drilling position of a blasting hole by the hydraulic rock drill; a charge amount acquisition step in which a charge amount acquisition means acquires the charge amount of explosives loaded in the blasting hole; an excavation surface data acquisition step in which an excavation surface data acquisition means acquires excavation surface data of the excavation surface after blasting; and an analysis step in which an analysis means analyzes the blasting results according to the hydraulic data, the drilling data, and the excavation surface data for the charge amount. Effect of the Invention
[0011] According to the present invention, the blasting results are analyzed according to hydraulic data when the ground is drilled by a hydraulic rock drill, drilling data including the drilling positions of the blast holes created by the hydraulic rock drill, and excavation surface data relative to the amount of powder charge, thereby improving the analytical accuracy, and by generating a blasting pattern using the analysis results, the blasting accuracy can be further improved. [Brief description of the drawings]
[0012] [Figure 1] 1 is a schematic diagram showing an example of a general configuration of a tunnel drilling system according to an embodiment of the present invention. FIG. [Diagram 2] FIG. 2 is a schematic diagram showing an example of an excavation surface after blasting. [Diagram 3] 2 is a block diagram showing an example of a schematic configuration of the information processing device in FIG. 1. [Figure 4] FIG. 4 is a flow chart showing an example of an operation according to the present embodiment. [Diagram 5] FIG. 2 is a schematic diagram showing an example of a blast hole block. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Note that the embodiment described below is an embodiment in which the present invention is applied to a tunnel boring system.
[0014] [1. Overview of the tunnel drilling system configuration and functions] (1.1 Structure and Functional Overview)
[0015] First, the configuration and general function of a structure according to one embodiment of the present invention will be described with reference to FIGS. 1 to 3. FIG.
[0016] Fig. 1 is a schematic diagram showing an example of a schematic configuration of a tunnel boring system according to the present embodiment. Fig. 2 is a schematic diagram showing an example of an excavation surface after blasting.
[0017] 1 and 2, the tunnel boring system S according to this embodiment includes a hydraulic rock drill 10 that drills blast holes 3a for loading explosives in the excavation surface 3 of a tunnel 1, a 3D scanner 20 that measures the excavation surface 3 after blasting, and an information processing device 30 that analyzes the blasting results from data from the hydraulic rock drill 10 and the 3D scanner 20. Here, the tunnel 1 is a tunnel in a mountainous area where blasting is required against the bedrock.
[0018] As shown in Figure 2, the excavation surface 3 has a blast hole 3a loaded with explosives, an over-excavated area 3b where the wall surface 5 of the tunnel 1 has been excavated excessively by blasting, and an insufficient excavation area 3c, called an atari, where the wall surface 5 has not been excavated enough by blasting.
[0019] The hydraulic rock drill 10 has a drilling rod bit 11 that drills holes in the excavation surface 3 for loading explosives, multiple booms 12 to which the drilling rod bits 11 are attached, a crawler 13 for moving inside the tunnel 1, a hydraulic drifter that drives the drilling rod bits 11, a position sensor that detects the position of the drilling rod bits 11, a hydraulic sensor that detects the impact pressure of the drilling rod bits 11, an information processing device 30 and communication functions, etc.
[0020] The drilling rod bit 11 uses the impact force, rotational force, and propulsion force from the hydraulic drifter to open a blast hole 3a in the excavation surface 3. The hydraulic sensor measures hydraulic data such as rotational pressure, feed pressure, impact pressure, etc., and the feed length during the blast hole drilling operation. The position sensor detects the coordinates of the position and direction of the drill of the drilling rod bit 11.
[0021] The hydraulic rock drill 10 may be operated by a human or automatically based on AI.
[0022] The 3D scanner 20 irradiates a measurement target such as the excavation surface 3 with a laser beam, and generates 3D scan data, which is point cloud data having information on three-dimensional coordinates, based on the distance and irradiation angle obtained by measuring the reflection time of the laser. The 3D scanner 20 outputs the 3D scan data to the information processing device 30. The 3D scanner 20 may be mounted on the hydraulic rock drill 10, or may be installed near the excavation surface 3 after blasting. From the design information of the tunnel 1 and the 3D scan data, the blasting results such as overexcavation points 3b, insufficient excavation points 3c, and excess / insufficient portions of the depth of the excavation surface 3 can be obtained.
[0023] The information processing device 30 performs wireless or wired communication with the hydraulic rock drill 10, the 3D scanner 20, etc. Based on the data from the hydraulic rock drill 10, the 3D scanner 20, etc., the blasting results are analyzed.
[0024] The tunnel drilling system S may include a camera for observing the tunnel face. The camera photographs the tunnel face, and the information processing device 30 extracts cracks and joints and determines the strike and inclination from the image data photographed by the camera.
[0025] Next, the configuration and functions of the information processing device 30 will be described with reference to Fig. 3. Fig. 3 is a block diagram showing an example of a schematic configuration of the information processing device 30.
[0026] 3, the information processing device 30 functioning as a computer is, for example, a personal computer. The information processing device 30 includes a communication unit 31, a display unit 32, a storage unit 33, an operation unit 34, an input / output interface unit 35, and a control unit 36. The control unit 36 and the input / output interface unit 35 are connected via a system bus 37. The information processing device 30 may be a computer such as a smartphone or a tablet.
[0027] The communication unit 31 controls communication with the hydraulic rock drill 10, the 3D scanner 20, etc., wirelessly or via wired connection.
[0028] The display unit 32 is configured by, for example, a liquid crystal display element or an organic EL (Electro Luminescence) element.
[0029] The storage unit 33 is, for example, a hard disk drive, and stores programs such as an operating system and applications. The storage unit 32 stores design information for the tunnel 1, a blasting plan for a blasting pattern such as drilling positions and charges for blasting, and the like. The storage unit 33 also stores a database of past blasting work results. Here, the blasting pattern includes the number of blast holes 3a, the drilling positions and intervals of the blast holes 3a, the drilling length, the drilling direction (angle), the charges, and the like. The storage unit 33 records the results of face observation.
[0030] In addition, a machine learning database for artificial intelligence (AI) is constructed in the memory unit 33. An example of machine learning is deep learning having a multi-layer neural network structure. For example, the memory unit 33 stores hydraulic data when drilling the blast hole 3a, the position of the blast hole 3a, blasting patterns, learned models for blasting results, etc.
[0031] The operation unit 34 is composed of, for example, a keyboard and a mouse.
[0032] The input / output interface unit 35 is an interface between the communication unit 31 and the storage unit 33 and the control unit 36 .
[0033] The control unit 36 is composed of a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), etc. The control unit 36 may have a calculation chip such as a GPU (Graphics Processing Unit) that performs AI calculations exclusively. The control unit 36 calculates the distribution of hardness and softness of the ground, analyzes blasting results, and generates blasting patterns by the CPU reading and executing various programs stored in the ROM and the memory unit 33.
[0034] [2. Example of operation of Tunnel Drilling System S] Next, an example of the operation of the tunnel drilling system S will be described with reference to the drawings.
[0035] FIG. 4 is a flow diagram showing an example of the operation according to the present embodiment.
[0036] Before starting drilling, the hydraulic rock drill 10 obtains information on the drilling position and the blasting pattern of the charge amount for blasting from the information processing device 30. The drilling rod and bit 11 of the hydraulic rock drill 10 drills each blast hole 3a at a predetermined drilling position according to the blasting pattern of the blasting plan. The hydraulic sensor of the hydraulic rock drill 10 detects hydraulic data such as rotation pressure, feed pressure, and impact pressure during the drilling operation of the blast hole 3a. The position sensor of the hydraulic rock drill 10 detects the position coordinate of the drill of the drilling rod and bit 11. The hydraulic rock drill 10 transmits the detected hydraulic data and the position coordinate data of the drill for each blast hole 3a to the information processing device 30. The hydraulic rock drill 10 also transmits information on the machine coordinates of the hydraulic rock drill 10 to the information processing device 30. The hydraulic data and the position coordinate data of the drill may be time-series data during the drilling operation of the blast hole 3a.
[0037] Next, as shown in Fig. 4, the tunnel boring system S acquires hydraulic data when drilling the natural ground (step S1). Specifically, the information processing device 30 acquires hydraulic data for each blast hole 3a from the hydraulic rock drill 10. In this way, the information processing device 30 functions as an example of a hydraulic data acquisition means that acquires hydraulic data when the natural ground is drilled by the hydraulic rock drill.
[0038] Next, the tunnel boring system S acquires the position coordinates of the drill (step S2). Specifically, the information processing device 30 acquires the position coordinates of the drill corresponding to each blast hole 3a from the hydraulic rock drill 10. In this way, the information processing device 30 functions as an example of a drilling position data acquisition means that acquires drilling position data of the blast holes by the hydraulic rock drill.
[0039] Next, the tunnel boring system S acquires the explosive charge for each hole (step S3). Specifically, the information processing device 30 acquires information on the number of explosives loaded in each blast hole 3a. For example, the information processing device 30 may accept input of data read from an explosives ledger, or may acquire an electronic explosives ledger from a database. In this way, the information processing device 30 functions as an example of an explosive charge acquisition means for acquiring the explosive charge amount loaded in the blast hole.
[0040] Next, the tunnel boring system S analyzes the hardness of the ground at the drilling position (step S4). Specifically, the information processing device 30 calculates the degree of hardness of each blast hole 3a from the data of the rotation pressure, feed pressure, and impact pressure at the time of drilling the blast hole 3a. For example, the degree of hardness of the ground is calculated by multiplying the average rotation pressure, average feed pressure, and average impact pressure by a predetermined coefficient and adding them together. The degree of hardness of the ground may be calculated according to the depth to which the blast hole 3a is excavated, by adding information on the position coordinates of the drill. For example, the degree of hardness of the ground is calculated from the rotation pressure, feed pressure, and impact pressure when the drilling rod bit 11 reaches that depth. In this way, the information processing device 30 functions as an example of a hardness distribution analysis means that analyzes the distribution of hardness of the ground from the hydraulic data and the drilling position data.
[0041] Next, the tunnel boring system S calculates the drilling position (step S5). Specifically, the information processing device 30 calculates the position, direction, and length of each blast hole 3a as the drilling position from the machine coordinates of the hydraulic rock drill 10 and the position coordinates of the drill. In this way, the information processing device 30 functions as an example of a drilling position data acquisition means that acquires drilling position data of the blast holes by the hydraulic rock drill.
[0042] Next, the tunnel boring system S calculates the distribution of hardness of the ground (step S6). Specifically, the information processing device 30 calculates the distribution of hardness of the ground from the calculated drilling positions and the hardness of the ground.
[0043] Next, the tunnel boring system S executes blasting (step S7). Specifically, a predetermined number of explosives are loaded into each of the drilled blast holes 3a according to a blasting plan, and blasting is performed.
[0044] Next, the tunnel boring system S acquires point cloud data of the excavation surface 3 by the 3D scanner 20 (step S8). Specifically, the 3D scanner 20 measures the excavation surface 3 after blasting, and outputs point cloud data of the excavation surface 3 of the 3D scan data to the information processing device 30. The information processing device 30 acquires the point cloud data from the 3D scanner 20. In this way, the information processing device 30 functions as an example of an excavation surface data acquisition means that acquires data of the excavation surface after blasting.
[0045] The information processing device 30 may obtain image data of the excavation surface 3 after blasting, taken by a camera or the like, from the camera for observing the excavation face.
[0046] Next, the tunnel boring system S analyzes the blasting results (step S9). Specifically, the information processing device 30 calculates the overexcavation portion 3b, the insufficient excavation portion 3c, and the excess and deficiency portion of the depth of the excavation surface 3 from the acquired point cloud data and the design information of the tunnel 1. The information processing device 30 evaluates the blasting from the calculated overexcavation portion 3b, the insufficient excavation portion 3c, and the excess and deficiency portion of the depth of the excavation surface 3. For example, the area, volume, etc. of the overexcavation portion 3b, the insufficient excavation portion 3c, and the excess and deficiency portion of the depth of the excavation surface 3 are calculated, and the value obtained by multiplying each of them by a predetermined coefficient and adding them is the evaluation value of the blasting. In this way, the information processing device 30 functions as an example of an analysis means for analyzing the blasting results according to the hydraulic data, the drilling position data, and the excavation surface data for the amount of the powder. The information processing device 30 also functions as an example of an analysis means for analyzing the blasting results according to the hardness / softness distribution and the excavation surface data for the amount of the powder.
[0047] The information processing device 30 generates face observation data by extracting cracks and joints and determining strike and inclination from image data of the excavation surface 3 acquired by the camera as a face observation result. The information processing device 30 may also accept input of face observation data performed by a person.
[0048] Next, the tunnel boring system S generates the next blasting pattern (step S10). Specifically, the information processing device 30 generates the next blasting pattern based on the calculated distribution of hardness and softness of the natural ground, the blasting pattern in which the blasting was performed, and the point cloud data of the excavation surface 3 from the 3D scanner 20. More specifically, the information processing device 30 generates the next blasting pattern of the optimal solution in which the value of a predetermined evaluation function is minimized from the blasting pattern in which the blasting was performed, based on the calculated distribution of hardness and softness of the natural ground and the blasting results of the point cloud data of the excavation surface 3. In this way, the information processing device 30 functions as an example of a blasting pattern calculation means that calculates the blasting pattern of the drilling position and the amount of charge for the next blasting based on the analysis result of the blasting result. Note that face observation data may be added to the blasting result.
[0049] The information processing device 30 may generate the next blasting pattern of the optimal solution by AI of a predetermined machine learning model trained in advance using the calculated distribution of hardness and softness of the natural ground, the charge amount of each blast hole 3a, and the point cloud data of the excavation surface 3 as input data. The information processing device 30 may also generate the next blasting pattern of the optimal solution by AI of a predetermined machine learning model trained in advance using the hydraulic data at the time of drilling the natural ground, the position coordinates of the drill, the charge amount of each blast hole 3a, and the point cloud data of the excavation surface 3 as input data.
[0050] In addition to the charge amount of each blast hole 3a in the blasting pattern, the data for the AI of the machine learning model may be the charge amount for each block of blast holes 3a grouped together. As shown in Figure 5, the blocks of blast holes 3a include the ceiling block B1 in the central ceiling part, the upper left block B2, the upper right block B2, the central block B3 at the center of the arch of the excavation surface 3, the left central block B4 on the left side along the arch from the central block, the right central block B4 on the right side along the arch from the central block, the left bottom block B5 on the lower side of the excavation surface 3, the right bottom block B5, the left corner block B6 on the lower side of the excavation surface 3, and the right corner block B6.
[0051] The data for the AI of the machine learning model may be information such as the variation in the interval between each blast hole 3a and the variation in the amount of charge per blast hole for each block. For example, for each block, information such as whether the interval between each blast hole 3a in the block has become wider or narrower than the previous blasting, whether the interval between the blast holes 3a has been widened, whether the interval between the blast holes 3a has been narrowed, whether the amount of charge per blast hole has been increased, or whether the amount of charge per blast hole has been reduced, may be information. In particular, the central block B3, the upper left block B2, and the upper right block B2 are blocks related to over-digging and hitting, and it is meaningful to handle the blast holes 3a for each block. In this way, by summarizing the information on each blast hole 3a by block unit of the excavation surface 3, the speed and accuracy of learning are improved. In addition, even if the amount of charge cannot be grasped for each blast hole 3a, it is also possible to grasp the amount of charge for each block and estimate the amount of charge for each blast hole from the number of blast holes contained in the block.
[0052] In addition, the data of face observation may be added to the input data for the AI of the machine learning model. In addition to quantitative data such as drilling rotation pressure, drilling feed pressure, drilling impact pressure, number of drilling holes, position of drilling holes, drilling angle, charge amount, face observation data, and post-blasting excavation surface scanner data, qualitative data such as the experience value of skilled miners may be added to the input data for learning the AI. For example, a hearing survey conducted on a block of blast holes 3a conducted on skilled miners. The hearing items are the locations in each block where the interval between blast holes 3a was widened or narrowed, the reasons for this (hardness, face shape), and the evaluation points of over-excavation and hits in the central block B3, upper left block B2, and upper right block B2. Such evaluation may be performed by the information processing device 30 from the point cloud data of the excavation surface 3 and image data for face observation.
[0053] Based on the generated blasting pattern, the hydraulic rock drill 10 drills the next blast holes 3a in the excavation surface 3 after blasting, and detects hydraulic data and drill position coordinates. The tunnel drilling system S returns to step S1 and step S2, and repeats the process until the tunnel 1 is excavated to the predetermined position.
[0054] According to the tunnel drilling system S of the embodiment, the blasting results are analyzed according to the hydraulic data when the hydraulic rock drill 10 drills the ground, the drilling position data of the blast holes drilled by the hydraulic rock drill, and the excavation surface data relative to the amount of powder, thereby improving the analytical accuracy, and by generating a blasting pattern using the analysis results, the blasting accuracy can be further improved.
[0055] When the hydraulic data is data on rotation pressure, feed pressure, and impact pressure, the hardness of the ground can be measured more accurately using data on the blast hole 3a obtained directly from the drilling rod bit 11.
[0056] When the hardness / softness distribution of the ground is analyzed from hydraulic data and drilling position data, and the blasting results are analyzed according to the excavation surface data for the hardness / softness distribution and the amount of explosive charge, the hardness / softness of the ground can be determined more accurately by combining it with the drilling position data of the blast hole 3a.
[0057] When the blasting pattern for the next blasting operation, including the drilling position and the amount of charge, is calculated based on the analysis results of the blasting operation, the blasting accuracy can be improved. In addition, the difference in the work results due to the experience of the workers is eliminated, and efficient blasting work can be continuously and stably realized.
[0058] In addition, improved blasting accuracy can reduce the amount of explosives used, the amount of over-excavation that needs to be filled with concrete, and the amount of additional excavation in areas that are insufficient, thereby reducing material costs and shortening construction time.
[0059] If the operation of the hydraulic rock drill 10 is performed automatically by AI or the like according to the calculated blasting pattern, there is no need to operate the hydraulic rock drill 10, and the number of workers can be reduced. In this way, drilling can be performed automatically in response to geological conditions and other factors with greater flexibility.
[0060] Three-dimensional tunnel shape data, hydraulic data, and drilling data are analyzed and evaluated, and in addition, the qualitative drilling techniques (tacit knowledge) that skilled miners have acquired are quantitatively analyzed and evaluated. When the data is used for AI learning, it can be made into explicit knowledge and reflected in the information processing device 30. [Explanation of symbols]
[0061] 3: Excavation surface 3a: Blast hole 10: Hydraulic rock drill 20: 3D scanner 30: Information processing device S: Tunnel Drilling System
Claims
1. a hydraulic data acquisition means for acquiring hydraulic data when drilling a natural ground with a hydraulic rock drill; A drilling data acquisition means for acquiring drilling data including the drilling position of the blast hole by the hydraulic rock drill; A charge amount acquisition means for acquiring a charge amount of the explosives loaded in the blast hole; An excavation surface data acquisition means for acquiring excavation surface data of the excavation surface after blasting; an analysis means for analyzing the blasting results according to the hydraulic data, the drilling data, and the excavation surface data for the charge amount; An information processing device comprising:
2. 2. The information processing apparatus according to claim 1, wherein the hydraulic pressure data is data on rotation pressure, feed pressure, and impact pressure, and the drilling data is data on drilling position and drilling angle.
3. Further comprising a hardness distribution analysis means for analyzing a hardness distribution of the natural ground from the hydraulic data and the drilling data, 3. An information processing apparatus according to claim 1, wherein said analysis means analyzes blasting results in accordance with said excavation surface data for said hardness / softness distribution and said powder charge amount.
4. 2. An information processing device as described in claim 1, further comprising a blasting pattern calculation means for calculating a blasting pattern of drilling positions and charge amounts for the next blasting based on the analysis results of the blasting results.
5. a hydraulic data acquisition step in which hydraulic data acquisition means acquires hydraulic data when drilling a natural ground with the hydraulic rock drill; A drilling data acquisition step in which a drilling data acquisition means acquires drilling data including a drilling position of a blast hole by the hydraulic rock drill; A charge amount acquisition step in which a charge amount acquisition means acquires the charge amount of the explosive loaded in the blast hole; An excavation surface data acquisition step in which an excavation surface data acquisition means acquires excavation surface data of the excavation surface after blasting; an analysis step of analyzing the blasting result according to the hydraulic data, the drilling data, and the excavation surface data for the charge amount by an analysis means; 13. An information processing method comprising:
Citation Information
Patent Citations
Natural ground evaluation method and system in front of tunnel working face
JP2017057708A
Explosive charge management device, boring and charging system, and explosive charge management method
JP2021075844A
Charging volume calculation system
JP2022153213A
Mine vehicle boom positioning control
US20220162911A1
Tunnel construction management system
JP2023003192A
