Blasting information processing device, blasting information processing method, and trained model

Abstract

To easily collect teacher data for generating a learned model used for setting a blasting pattern.SOLUTION: A blasting information processing device 5 comprises a first input data acquisition unit 502 that acquires drilling energy consumed when a first hole H1 arranged at an outer peripheral edge of a face R among the plurality of holes arranged in the face R is drilled and the amount of explosive loaded in the first drilling hole H1 as first input data for each drilling hole, a first output data acquisition unit 503 that acquires the cross-sectional size of each perforation perpendicular to the axial direction of a first area A1 set from the cross-section after blasting and formed by the explosion of the explosive loaded in the first hole H1, as first output data, and a model generator 504 that performs machine learning based on first input data and first output data and generates a trained model that correlates the drilling energy and amount of explosive loaded with the size of the area formed by the detonation.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present invention relates to a blasting information processing device, a blasting information processing method executed in the blasting information processing device, and a trained model generated by the blasting information processing device. [Background technology]

[0002] Conventionally, when excavating a medium-hard rock in the construction of a mountain tunnel, the excavation of the ground is generally carried out by blasting. In blasting, the position of the drill hole in which the explosives are to be loaded and the amount of the explosives to be loaded in the drill hole are determined based on the experience of a skilled engineer.

[0003] However, even for experienced engineers, it is difficult to make the shape of the ground after blasting exactly as designed. Attempts have been made to machine-learn the judgment of the quality of blasting by experienced blasters using the blasting conditions based on the scattering and accumulation of debris after blasting and the excavation conditions of the face as index values, without relying on the skills, experience, and judgment of experienced blasters. By using this trained model, it may be possible to set the optimal blasting pattern (Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2019-190189 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, conventional technology is complicated by the need to measure and input the scattering and accumulation state of debris. In addition, the learning process requires the judgment of a skilled worker. Furthermore, since the indicators of the blasting condition and the data indicating the quality of the blasting in one blasting are used as training data for machine learning, only one set of training data can be obtained in one blasting, and collecting training data takes a lot of time and costs.

[0006] The present invention aims to provide a blasting information processing device that can easily collect training data for generating a learning model used to set blasting patterns and perform machine learning using the collected training data, a blasting information processing method executed in the blasting information processing device, and a trained model generated by the blasting information processing device. [Means for solving the problem]

[0007] The invention of claim 1 of the present application is a blasting information processing device used in a blasting method in which explosives loaded in each of a plurality of drill holes arranged at a rock face are detonated to perform a single blast, the blasting information processing device comprising: a first input data acquisition unit that acquires, for each drill hole, as first input data, the drilling energy consumed when a first drill hole arranged on the outer peripheral edge of the rock face is drilled, and the amount of explosives loaded in the first drill hole; a first output data acquisition unit that acquires, for each drill hole, as first output data, the size of a cross section perpendicular to the axial direction of a first area formed by the explosion of the explosives loaded in the first drill hole, which is set from the cross section after the blasting; and a model generation unit that performs machine learning based on the first input data and the first output data to generate a trained model showing a correlation between the drilling energy consumed when the first drill hole is drilled, the amount of explosives loaded in the first drill hole, and the size of the area formed by the explosion of the explosives loaded in the first drill hole.

[0008] The invention according to claim 2 of the present application is characterized in that the first output data acquisition unit further acquires, as first output data for each drilling hole, an axial length of a first region set from the cross section after the blasting and formed by the explosion of the explosive loaded in the first drilling hole, and a second input data acquisition unit acquires, as second input data for each drilling hole, the drilling energy consumed when a second drilling hole different from the first drilling hole is drilled and the amount of explosive loaded in the second drilling hole; The blasting information processing device of claim 1 further comprises a second output data acquisition unit that acquires as second output data for each borehole the size of a cross section perpendicular to the axial direction of the second region calculated based on the ratio of the size of a cross section perpendicular to the axial direction of the region and the length of the axial direction, and the model generation unit further performs machine learning based on the second input data and the second output data to generate a trained model showing a correlation between the drilling energy consumed when drilling the second borehole, the amount of explosives loaded in the second borehole, and the size of the region formed by the explosion of the explosives loaded in the second borehole.

[0009] The invention according to claim 3 of the present application is a blasting information processing method used in a blasting method in which explosives loaded in each of a plurality of drill holes arranged at a rock face are detonated to perform a single blast, the blasting information processing method including: acquiring, as first input data for each drill hole, the drilling energy consumed when a first drill hole arranged at the outer peripheral edge of the rock face among the drill holes is drilled, and the amount of explosives loaded in the first drill hole; acquiring, as first output data for each drill hole, the size of a cross section perpendicular to the axial direction of a first area formed by the explosion of the explosives loaded in the first drill hole, which is set from the cross section after the blasting; and performing machine learning based on the first input data and the first output data to generate a trained model showing a correlation between the drilling energy consumed when the first drill hole is drilled, the amount of explosives loaded in the first drill hole, and the size of the area formed by the explosion of the explosives loaded in the first drill hole.

[0010] The invention according to claim 4 of the present application further includes, as the first output data, acquiring for each borehole an axial length of a first region that is set from the cross section after the blasting and that is formed by the explosion of the explosives loaded in the first borehole, acquiring as second input data for each borehole an amount of explosives loaded in the second borehole, and acquiring as second input data for each borehole an axial length of a second region that is set from the cross section after the blasting and that is formed by the explosion of the explosives loaded in the second borehole, and acquiring as second input data for each borehole an axial length of a first region that is set from the cross section after the blasting and that is formed by the explosion of the explosives loaded in the second borehole. and acquiring as second output data for each borehole a size of a cross section perpendicular to the axial direction of the second region calculated based on a ratio of a size of a cross section perpendicular to the axial direction of the second region to a length in the axial direction of the second region, and further performing machine learning based on the second input data and the second output data to generate a trained model showing a correlation between the drilling energy consumed when drilling the second borehole, the amount of explosives loaded in the second borehole, and the size of the region formed by the explosion of the explosives loaded in the second borehole.

[0011] The invention of claim 5 of the present application is a trained model generated based on first input data and first output data in a blasting information processing device used in a blasting method in which explosives loaded in each of a plurality of drill holes arranged at a rock face are detonated to perform a single blast, the trained model being generated based on first input data and first output data, the first input data being obtained for each drill hole the drilling energy consumed when a first drill hole arranged at the outer peripheral edge of the rock face is drilled, and the amount of explosives loaded in the first drill hole, the first output data being set from a cross section after the blasting, and the size of a cross section perpendicular to the axial direction of a first area formed by the explosion of the explosives loaded in the first drill hole being obtained for each drill hole, the trained model being generated by performing machine learning based on the first input data and the first output data, and showing a correlation between the drilling energy consumed when drilling the first drill hole and the amount of explosives loaded in the first drill hole, and the size of the area formed by the explosion of the explosives loaded in the first drill hole.

[0012] The invention according to claim 6 of the present application is further generated based on second input data and second output data, the first output data being further set from the cross section after the blasting, and being obtained for each bore hole an axial length of a first region formed by the explosion of the explosives loaded in the first bore hole, the second input data being obtained for each bore hole an axial length of a first region formed by the explosion of the explosives loaded in the first bore hole, the second output data being obtained for each bore hole an axial length of a first region formed by the explosion of the explosives loaded in the first bore hole, the second input data being obtained for each bore hole an axial length of a first region formed by the explosion of the explosives loaded in the first bore hole, the second output data being obtained for each bore hole an axial length of a first region formed by the explosion of the explosives loaded in the second bore hole, the second output data being obtained for each bore hole an axial length of a first region formed by the explosion of the explosives loaded in the second bore hole, the second input data being obtained for each bore hole an axial length of a first region formed by the explosion of the explosives loaded in the second bore hole, the second output ... input data being obtained for each bore hole an axial length of a first and a cross-sectional size perpendicular to the axial direction of the second region calculated based on a ratio of the cross-sectional size perpendicular to the axial direction of the first region to the axial length of the first region, which are obtained for each perforation, and further showing a correlation between the drilling energy consumed when drilling the second perforation, and the amount of explosives loaded in the second perforation, which are generated by performing machine learning based on the second input data and the second output data, and the size of the region formed by the explosion of the explosives loaded in the second perforation. Effect of the Invention

[0013] The present disclosure makes it possible to easily collect training data for generating learning models used to set blasting patterns. In addition, with conventional technology, it was necessary to perform learning or other adjustments for each different tunnel shape and cross-sectional area, but with the present disclosure, learning is performed for each drilling, making it easy to accommodate tunnels of various shapes and cross-sectional areas, thereby increasing versatility. [Brief description of the drawings]

[0014] [Figure 1] FIG. 1 is a diagram illustrating an example of work in a blasting method. [Diagram 2] FIG. 1 shows an example of an apparatus used to excavate a tunnel. [Diagram 3] FIG. 13 is a diagram illustrating an example of a drilling position indicated by a blasting pattern. [Figure 4] FIG. 2 is a diagram illustrating an example of a hardware configuration of a blasting information processing device. [Diagram 5] FIG. 2 is a diagram illustrating an example of a function of a blasting information processing device. [Figure 6] 11 is a diagram illustrating a method for acquiring the size of a cross section perpendicular to the axial direction of a first region. FIG. [Figure 7] FIG. 1 is a diagram illustrating an example of machine learning using a neural network. [Figure 8] 13 is a diagram illustrating an example of a processing flow executed by a blasting information processing device. FIG. [Figure 9] 2 is a block diagram illustrating an example of the function of a blasting information processing device. FIG. [Figure 10] FIG. 4 is a diagram illustrating the axial length of a first region. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Note that not all combinations of features described in the following embodiments are necessarily required to solve the problem. In addition, unnecessary detailed description may be omitted. In addition, the following description of the embodiment and the drawings are provided to enable those skilled in the art to fully understand the present invention, and are not intended to limit the scope of the claims.

[0016] <First embodiment> When constructing mountain tunnels, the blasting method is generally used to excavate rock masses such as medium-hard rocks. The blasting method involves drilling holes in the rock mass and detonating explosives inside to break up the rock mass.

[0017] Fig. 1 is a diagram for explaining an example of work in the blasting method. A drilling machine 1 drills a plurality of holes (not shown) required for excavating one excavation length S at a tunnel face R. The drilling machine 1 drills holes at positions determined based on a predetermined blasting pattern.

[0018] The boreholes are loaded with explosives, the amount of explosives to be loaded into each of the boreholes also being determined based on a predetermined blasting pattern.

[0019] When the holes drilled at the positions specified by the blasting pattern are filled with explosives, the blasting takes place. After the blasting, the rubble is removed using a wheel loader (not shown). If necessary, checks and marks are taken before or after the rubble is removed.

[0020] After the rubble is removed, concrete is sprayed onto the wall surface using a sprayer (not shown) to reinforce the natural ground. Once the concrete sprayed onto the wall surface has hardened, rock bolts are driven into the wall.

[0021] After the rock bolts have been driven, holes are drilled in the face R to excavate another tunnel length S, each hole is charged with explosives, and then detonated. This process is repeated until the tunnel is excavated.

[0022] The equipment used to excavate the tunnel will now be described.

[0023] 2 is a diagram showing an example of an apparatus used to excavate a tunnel. The apparatus used to excavate a tunnel includes, for example, the above-mentioned drilling machine 1, a blasting pattern management device 2, a communication line 3, and a shape measuring device 4.

[0024] The blasting pattern management device 2 is a device that manages the blasting pattern for one excavation length S. The blasting pattern includes information on the combination of the drilling position of the face R and the amount of explosives to be loaded into the drilled hole. Blasting patterns include, for example, those that are predetermined based on the experience of skilled workers, known ones, and also those arranged according to the characteristics of the site.

[0025] FIG. 3 is a diagram for explaining an example of the drilling position indicated by the blasting pattern. The blasting pattern includes information indicating the position of the drilling hole to be drilled in the tunnel face R. The information indicating the drilling position is expressed, for example, by coordinate values ​​with a predetermined position as the origin. When the cross-sectional shape of the tunnel is a horseshoe shape, part of which coincides with the shape of a part of an ellipse, the origin is, for example, the intersection of the major axis and the minor axis of the ellipse.

[0026] Each drill hole can be classified into a first drill hole H1 arranged on the outer peripheral edge of the face and a second drill hole H2 different from the first drill hole H1.

[0027] The first drilling H1 is shown surrounded by a dashed line in FIG. 3 and is a drilling formed on the outer peripheral edge of the tunnel cross-sectional shape at the tunnel face R. When the cross-sectional shape of the tunnel is a horseshoe shape with a part of the shape coinciding with an ellipse, the first drilling H1 is a drilling formed on the outer peripheral edge of the ellipse. In other words, the first drilling H1 is a drilling formed on the outermost part of the tunnel face R, and no other drillings are formed outside the first drilling H1. Therefore, the explosives loaded in the first drilling H1 blast the outermost region of the tunnel face R. In this embodiment, the first drilling H1 does not include any drilling that blasts a region close to the invert, but may be included as a drilling formed on the outer peripheral edge of the tunnel cross-sectional shape.

[0028] The second drilling hole H2 is different from the first drilling hole H1. That is, the second drilling hole H2 is a drilling hole formed inside the outer peripheral edge of the ellipse. Therefore, the first drilling hole H1 or another second drilling hole H2 is formed around the second drilling hole in the face S. The explosives loaded in the second drilling hole H2 blast an area inside the face R more than the explosives loaded in the first drilling hole H1. In addition, if the first drilling hole H1 includes an explosive that blasts an area close to the invert, the one inside the area becomes the second drilling hole H2.

[0029] The blasting pattern may include data such as the angle of each of the drill holes relative to the face R, the diameter of the drill holes, and the depth of the drill holes.

[0030] The blasting pattern management device 2 may manage a plurality of blasting patterns. That is, the blasting pattern management device 2 may manage a plurality of blasting patterns according to the size of the tunnel to be excavated, the hardness of the rock, and the like.

[0031] The blasting pattern management device 2 is configured by, for example, a PC (Personal Computer). The blasting pattern management device 2 transmits data indicating the blasting pattern to the drilling machine 1 via the communication line 3.

[0032] The communication line 3 connects the blasting pattern management device 2, the drilling machine 1, and the shape measuring device 4 to each other. The communication line 3 may be a wired line or a wireless line. The communication line 3 is, for example, an Internet line.

[0033] The drilling machine 1 is a device that drills holes in a rock face R. The drilling machine 1, for example, uses a drill to drill holes. The drilling machine 1 receives a blasting pattern from a blasting pattern management device 2. The drilling machine 1 drills holes based on the drilling positions indicated by the blasting pattern. The drilling machine 1 is, for example, a fully automatic computer jumbo or a semi-automatic computer jumbo.

[0034] The drilling machine 1 includes, for example, a projector, which displays an image showing the drilling positions and the amount of explosives loaded at each drilling position on the face R based on the blasting pattern. The drilling machine 1 uses a drill to drill holes at the drilling positions displayed on the face R. Furthermore, a worker loads explosives into a predetermined drilling hole using the amount of explosives displayed on the face R as a guide. The amount of explosives loaded into each drilling hole is actually measured, and the measured amount of explosives is associated with the drilling position and input to, for example, the blasting pattern management device 2.

[0035] The drilling machine 1 is equipped with multiple guide shells, each of which has a hydraulic drifter that slides in the drilling direction. Each hydraulic drifter slides in the drilling direction to drill a hole in the face R. The drilling machine 1 is equipped with multiple sensors that detect predetermined physical quantities when drilling.

[0036] Each sensor detects, for example, the hydraulic pressure applied to the hydraulic drifter, the sliding speed of the hydraulic drifter, and the sliding distance of the hydraulic drifter. The drilling machine 1 obtains the drilling energy consumed when drilling each hole using the physical quantities detected by each sensor.

[0037] The shape measuring device 4 measures the shape of a portion corresponding to one excavation length S after the piled up rubble by blasting is carried out. The shape measuring device 4 is, for example, a three-dimensional shape measuring device. The three-dimensional shape measuring device is, for example, a three-dimensional laser scanner. The shape measuring device 4 identifies the area crushed by blasting based on the shape before and after blasting. The shape measuring device 4 sets a predetermined coordinate system at the face, for example, and identifies the shape of the natural ground before and after blasting using the coordinate values ​​in the predetermined coordinate system. The shape measuring device 4 may measure the shape before the rubble is carried out, or may measure the shape after deducting the work of crushing and marking. In other words, the shape excavated by blasting is measured.

[0038] Next, the blasting information processing device 5 will be described. The blasting information processing device 5 learns the correlation between the drilling energy consumed when drilling at least a drilling hole in the face R, the amount of explosives loaded in the drilling hole, and the size of the area formed by the explosion of the explosives loaded in the drilling hole. The blasting information processing device 5 is connected to the communication line 3 shown in FIG. 2, and acquires various data from the blasting pattern management device 2, the drilling machine 1, and the shape measuring device 4. The blasting information processing device 5 is composed of, for example, a PC. The blasting information processing device 5 is implemented in the PC that implements the blasting pattern management device 2, but may be provided separately.

[0039] 4 is a diagram showing an example of a hardware configuration of the blasting information processing device 5. The blasting information processing device 5 includes a CPU (Central Processing Unit) 51, a bus 52, a ROM (Read Only Memory) 53, a RAM (Random Access Memory) 54, a non-volatile memory 55, and an input / output interface 56.

[0040] The CPU 51 is a processor that controls the entire blasting information processing device 5 in accordance with a system program. The CPU 51 reads the system program and the like stored in the ROM 53 via the bus 52, and performs various processes based on the system program.

[0041] The bus 52 is a communication path that connects each piece of hardware in the blasting information processing device 5. Each piece of hardware in the blasting information processing device 5 exchanges data via the bus 52.

[0042] The ROM 53 is a storage device that stores a system program for controlling the entire blasting information processing device 5. The ROM 53 is a computer-readable storage medium.

[0043] The RAM 54 is a storage device that temporarily stores various data and functions as a working area for the CPU 51 to process various data.

[0044] The non-volatile memory 55 is a storage device that retains data even when the power to the blasting information processing device 5 is turned off. The non-volatile memory 55 stores various information such as a machine learning program and a trained model. The non-volatile memory 55 is a computer-readable storage medium. The non-volatile memory 55 is, for example, configured with an SSD (Solid State Drive).

[0045] The input / output interface 56 is a communication path that connects an external device (not shown) to the bus 52. The blasting information processing device 5 is connected to the communication line 3 via the input / output interface 56.

[0046] Next, the function of the blasting information processing device 5 will be described.

[0047] 5 is a diagram for explaining an example of the function of the blasting information processing device 5. The blasting information processing device 5 learns the correlation between the drilling energy consumed when drilling a drill hole at least in the face R, the amount of explosives loaded in the drill hole, and the size of the area formed by the explosion of the explosives loaded in the drill hole.

[0048] The blasting information processing device 5 includes a receiving unit 501 , a first input data acquisition unit 502 , a first output data acquisition unit 503 , a model generation unit 504 , a model storage unit 505 , and an output unit 506 .

[0049] The reception unit 501 and the output unit 506 are realized by the input / output interface 56 exchanging various data via the communication line 3. The first input data acquisition unit 502, the first output data acquisition unit 503, and the model generation unit 504 are realized by the CPU 51 executing arithmetic processing using the system program stored in the ROM 53, the machine learning program stored in the non-volatile memory 55, and various data. The model storage unit 505 is realized by storing the calculation results of the arithmetic processing by the CPU 51 in the RAM 54 or the non-volatile memory 55.

[0050] The reception unit 501 receives input of various data. For example, the reception unit 501 receives data indicating a blasting pattern and information indicating an actual measurement value of the amount of explosives loaded in each drill hole from the blasting pattern management device 2 via the communication line 3. The reception unit 501 also receives data indicating the drilling energy consumed when drilling each drill hole from the drilling machine 1. The reception unit 501 also receives data indicating the shape after blasting from the shape measuring device 4.

[0051] The first input data acquisition unit 502 acquires, from the data received by the reception unit 501, the drilling energy consumed when the first drilling hole H1 formed on the outer peripheral edge of the face R is drilled, and the amount of explosives loaded in the first drilling hole H1 as the first input data for each drilling hole. The amount of explosives loaded in the first drilling hole H1 is the amount of explosives actually loaded in the first drilling hole H1. In other words, the amount of explosives loaded in the first drilling hole H1 is an actually measured value. However, the amount of explosives loaded in the first drilling hole H1 may not be an actually measured value, but may be an amount specified by the blasting pattern.

[0052] The first input data is a data set of data indicating drilling energy consumed when drilling one first bore hole H1 and data indicating an amount of explosives loaded into one first bore hole H1. The first input data includes a plurality of data sets corresponding to each of the plurality of first bore holes H1.

[0053] The first output data acquisition unit 503 acquires, as first output data for each drilling hole, the size of a cross section perpendicular to the axial direction of the first region formed by the explosion of the explosives loaded in the first drilling hole H1. Here, the axial direction is the direction in which the tunnel extends and is perpendicular to the face R.

[0054] 6 is a diagram for explaining a method for acquiring the size of a cross section perpendicular to the axial direction of the first region. If only one drill hole is formed in the face R and an explosive loaded in this one drill hole explodes, the size of the cross section perpendicular to the axial direction of the region formed by the explosion can be actually measured.

[0055] On the other hand, multiple drill holes are drilled at the face R, and the explosives loaded in each drill hole are exploded with a single blast, so it is necessary to set the area that will be crushed by the explosives loaded in one drill hole based on the fracture shape after blasting at the face R.

[0056] Therefore, the first output data acquisition unit 503 acquires the size of each circle having a radius r, which is the distance from the center of each first drilling hole H1 to the excavation line Y1 of the natural ground after blasting, as the size of the cross section perpendicular to the axial direction of the first region A1. For example, the radius r is set to the distance from the center of each first drilling hole H1 to the point where the extension in the normal direction of the tunnel outline (the excavation line L determined in advance in the design) intersects with the excavation line Y1 of the natural ground after blasting. It may also be set to the point on the excavation line Y1 of the natural ground after blasting that is the shortest distance from the center of each first drilling hole H1. Note that the size of the cross section perpendicular to the axial direction of each first region A1 may be expressed by a diameter instead of the set radius r, and may further be expressed by the area of ​​a circle having the radius r. In addition, when calculating the radius r of the circle, the average value of the intersection point between the normal line of the excavation line L and the excavation line Y1 and the shortest distance between the intersection point and the excavation line Y1 may be set to the radius r. Furthermore, the first area A1 may be set to a rectangle, polygon, or the like instead of a circle.

[0057] If the excavation line Y1 of the ground after blasting is located outside the excavation line L that was pre-designed, then an excessively excavated portion, i.e., over-excavation, has occurred. On the other hand, if the excavation line Y1 of the ground after blasting is located inside the excavation line L that was pre-designed, then an insufficiently excavated portion, i.e., a hit portion, has occurred. Returning to the explanation of Figure 5.

[0058] The model generation unit 504 performs machine learning based on the first input data and the first output data, and generates a trained model that indicates a correlation between at least the drilling energy consumed when drilling a drilling hole in the face R, and the amount of explosives loaded in the drilling hole, and the size of an area formed by the explosion of the explosives loaded in the drilling hole. The model generation unit 504 performs supervised learning using, for example, a neural network.

[0059] Fig. 7 is a diagram for explaining an example of machine learning using a neural network. The neural network NN includes an input layer, an intermediate layer, and an output layer. The input layer, the intermediate layer, and the output layer each include a plurality of neurons N. In the example shown in Fig. 7, the intermediate layer has a single-layer structure, but the intermediate layer may have a multi-layer structure.

[0060] First input data is input to a neuron N in the input layer. In addition, the output value output from the neuron N in the input layer is multiplied by a weight and input to a neuron N in the middle layer. A transfer function is set in the neuron N in the middle layer, and an output value that has passed through the transfer function is output from the middle layer. The output value output from the middle layer is further multiplied by a weight and input to a neuron N in the output layer. An output result is output from each neuron N in the output layer.

[0061] The weights of the intermediate layer are adjusted, for example, by the backpropagation method so that the output results output from each neuron N of the output layer approach the first output data. In other words, machine learning is performed so that each weight multiplied by the data input to each neuron N approaches the optimal solution.

[0062] The model storage unit 505 stores the trained model generated by the model generation unit 504.

[0063] The output unit 506 outputs the trained model stored in the model storage unit 505. The output unit 506 transmits the trained model to the blasting pattern management device 2 via the communication line 3, for example.

[0064] Next, the flow of the process executed by the blasting information processing device 5 will be described.

[0065] 8 is a diagram for explaining an example of the flow of processing executed by the blasting information processing device 5. First, the reception unit 501 receives various data (step S1). As described above, the various data includes data indicating the blasting pattern, data indicating the drilling energy, and data indicating the shape of the natural ground after blasting.

[0066] Next, the first input data acquisition unit 502 acquires the first input data (step S2). The first input data is data indicating at least the drilling energy consumed when drilling the first drilling hole H1 formed at the outer peripheral edge of the face R, and the amount of explosives loaded in the first drilling hole H1.

[0067] Next, the first output data acquisition unit 503 acquires the first output data (step S3). The first output data is data indicating the size of a cross section perpendicular to the axial direction of the first region A1 formed by the explosion of the explosive loaded in the first borehole H1.

[0068] Next, the model generation unit 504 generates a trained model by executing machine learning (step S4). The trained model indicates a correlation between at least the drilling energy consumed when drilling the first drilling hole in the face R, and the amount of explosives loaded in the first drilling hole and the size of the area formed by the explosion of the explosives loaded in the first drilling hole.

[0069] Next, the model storage unit 505 stores the trained model (step S5).

[0070] Finally, the output unit 506 outputs the trained model stored in the model storage unit 505 (step S6), and the process ends.

[0071] As described above, the blasting information processing device 5 includes a first input data acquisition unit 502 that acquires, as first input data for each drilling, the drilling energy consumed when drilling at least the first drilling hole H1 formed on the outer peripheral edge portion of the face R, and the amount of explosives loaded in the first drilling hole H1; a first output data acquisition unit 503 that acquires, as first output data for each drilling, the size of a cross section perpendicular to the axial direction of the first area A1 formed by the explosion of the explosives loaded in the first drilling hole H1; and a model generation unit 504 that performs machine learning based on the first input data and the first output data to generate a trained model showing a correlation between the drilling energy consumed when drilling the first drilling hole, the amount of explosives loaded in the first drilling hole, and the size of the area formed by the explosion of the explosives loaded in the first drilling hole.

[0072] Therefore, since the blasting information processing device 5 obtains input data and output data for each drilling hole, not for the entire face, it is possible to easily collect a large amount of training data for generating a learning model used to set a blasting pattern, and machine learning can be performed using the collected training data. As a result, the blasting information processing device 5 can easily generate a trained model that shows a correlation between the drilling energy consumed when drilling at least the first drilling hole in the face R, the amount of explosives loaded in the first drilling hole, and the size of the area formed by the explosion of the explosives loaded in the first drilling hole.

[0073] The trained model output by the output unit 506 is used, for example, in the blasting pattern management device 2 for optimal design of the blasting pattern. For example, the drilling position and the amount of explosives loaded can be optimized based on the correlation between the drilling energy consumed when drilling a hole in the face R, the amount of explosives loaded in the hole, and the size of the area formed by the explosion of the explosives loaded in the hole. As a result, the cost related to excavation can be reduced. Furthermore, the face shape after blasting can be made closer to the design shape.

[0074] In the above-described embodiment, the first input data acquisition unit acquires the drilling energy consumed when the first drilling hole is drilled and the amount of explosives loaded in the first drilling hole as the first input data, but is not limited thereto. The first input data acquisition unit may further acquire information indicating the depth (drilling length) of the first drilling hole as the first input data. In this case, it is possible to deal with a case where one drilling length is changed, and the model generation unit generates a trained model indicating a correlation between the drilling energy consumed when drilling a drilling hole in the face, the depth of the drilling hole, and the amount of explosives loaded in the drilling hole, and the size of the area formed by the explosion of the explosives loaded in the drilling hole.

[0075] <Second embodiment> Hereinafter, the second embodiment of the present invention will be described with reference to Figures 9 and 10. Note that a description of the same parts as in the first embodiment will be omitted, and differences will be mainly described.

[0076] In the second embodiment, the blasting information processing device 5 further performs machine learning using other input data and other output data.

[0077] Fig. 9 is a block diagram for explaining an example of the functions of the blasting information processing device 5. The blasting information processing device 5 shown in Fig. 9 further includes a second input data acquisition unit 511, a calculation unit 512, and a second output data acquisition unit 513 in addition to the functions of the blasting information processing device 5 shown in Fig. 5. The second input data acquisition unit 511, the calculation unit 512, and the second output data acquisition unit 513 are realized by the CPU 51 executing arithmetic processing using the system program stored in the ROM 53, the machine learning program stored in the non-volatile memory 55, and various data.

[0078] The receiving unit 501 receives, for example, data indicating the blasting pattern and information indicating the actual amount of explosives loaded in each drill hole from the blasting pattern management device 2 via the communication line 3. The receiving unit 501 also receives data indicating the drilling energy consumed when drilling each drill hole from the drilling machine 1. The receiving unit 501 also receives data indicating the shape after blasting from the shape measuring device 4.

[0079] The first input data acquisition unit 502 acquires, from the data accepted by the acceptance unit 501, the drilling energy consumed when drilling at least the first drilling hole H1 formed on the outer peripheral edge portion of the drilling face R, and the amount of explosives loaded in the first drilling hole H1, as first input data for each drilling hole. The amount of explosives loaded in the first drilling hole H1 is an actual measurement value of the amount of explosives loaded in the first drilling hole H1.

[0080] The first input data is a data set of data indicative of drilling energy consumed when drilling at least one first bore hole H1 and data indicative of an amount of explosives loaded into the one first bore hole H1. The first input data includes a plurality of data sets corresponding to each of the plurality of first bore holes H1.

[0081] The second input data acquisition unit 511 acquires, as second input data for each drilling, the drilling energy consumed when drilling a second drilling hole H2 different from the first drilling hole H1 formed in the face R, and the amount of explosives loaded in the second drilling hole H2. The amount of explosives loaded in the second drilling hole H2 is an actual measurement value of the amount of explosives loaded in the second drilling hole H2.

[0082] The second input data is a data set of data indicative of drilling energy consumed when at least one second bore hole H2 is drilled and data indicative of an amount of explosives loaded into the one second bore hole H2. The second input data includes a plurality of data sets corresponding to each of the plurality of second bore holes H2.

[0083] As in the first embodiment, the first output data acquisition unit 503 acquires, for each first bore hole H1, the size of a cross section perpendicular to the axial direction of the first region A1 formed by the explosion of the explosive loaded in the first bore hole H1 as first output data.

[0084] The calculation unit 512 calculates the ratio between the size of the cross section perpendicular to the axial direction of the first region A1 and the length in the axial direction of the first region A1 based on the data indicating the shape of the natural ground after blasting received by the reception unit 501. Here, the size of the cross section perpendicular to the axial direction of the first region A1 is the size of a circle having a radius r that is the distance from the center of the first drill hole H1 to the excavation line Y1 of the natural ground after blasting, as in the first embodiment. The length in the axial direction of the first region A1 will be described in detail below.

[0085] FIG. 10 is a diagram for explaining the axial length of the first region A1. The upper diagram of FIG. 10 is a plan view of the natural ground after blasting, and the lower diagram of FIG. 10 is a front view of the natural ground after blasting. The dashed line indicates the excavation line L that is predetermined in the design for one excavation length. The hatched area indicates the area excavated by blasting. In the area excavated by blasting, the excavation line that forms the side is indicated by Y1, and the excavation line that forms the new face R is indicated by Y2. The hatched area where the diagonal lines intersect indicates one of the first regions A1.

[0086] The axial length of the first region A1 can be expressed as the distance between the position P1 of the opening of the first drilling H1 at the face R before blasting and the position P2 where the central axis of the first drilling H1 intersects with the excavation line Y2 (face R) of the natural ground after blasting. Since explosives are charged up to the tip P0 in the first drilling H1 in the axial length of this first region A1, the region from the opening position P1 to the tip P0 can be said to be the part excavated by blasting related to the size of the cross section perpendicular to the axial direction of the first region A1, so that the excavation by blasting of the axial length of the first region A1 can be said to have been performed from the tip P0 of the first drilling H1 to the excavation line Y2 of the natural ground after blasting, excluding the region from the opening position P1 to the tip P0. The distance from the tip P0 of the first drilling hole H1 to the excavation line Y2 of the natural ground after blasting is used to calculate the ratio to the size of the cross section perpendicular to the axial direction of the first area A1 as the axial length of the first area A1. The position of the tip P0 can be determined, for example, from the position and length of the drilling hole.

[0087] Specifically, the distance from the tip P0 of the first drilling hole H1 to the excavation line Y2 of the natural ground after blasting is the distance from the tip P0 of the first drilling hole H1 to the position P2 where the central axis of the first drilling hole H1 and the excavation line Y2 (face R) of the natural ground after blasting intersect. However, this is not limited to this, and for example, the shortest distance from the tip 0 of the first drilling hole H1 to the point on the excavation line Y2 (face R) of the natural ground after blasting may be used as the axial length of the first region A1 for calculation.

[0088] When there are multiple first perforations H1, the calculation unit 512 calculates the ratio between the size of the cross section perpendicular to the axial direction of the first region A1 and the length in the axial direction of the first region A1 for each perforation. The calculation unit 512 may calculate the average value of the ratios calculated for each first perforation H1.

[0089] The calculation unit 512 calculates the size of a cross section perpendicular to the axial direction of the second region based on the calculated ratio and the axial length of the second region formed by the explosion of the explosive loaded in the second borehole H2.

[0090] Here, a method for calculating the size of the cross section perpendicular to the axial direction of the second region A2 will be described. Since the size of the second region A2 is not the outer peripheral edge of the tunnel, the axial length (the distance from the tip P0 of the second drilling hole H2 to the position P2 where the central axis of the second drilling hole H2 intersects with the excavation line Y2 (face R) of the natural ground after blasting, as with the first drilling hole H1) can be grasped from the measurement, but the size of the cross section perpendicular to the axial direction is difficult to grasp, unlike the size of the first region A1. On the other hand, if it is assumed that the explosive force of the explosive loaded in the drilling hole is almost uniform in all directions at each point in the axial direction of the drilling hole, it is assumed that there is a correlation between the axial length of the region formed by the explosive explosion (the distance from the tip P0 of the drilling hole to the position P2 where the central axis of the drilling hole intersects with the excavation line Y2 of the natural ground after blasting) and the length perpendicular to the axis. In other words, if the face R in the axial direction is largely excavated by the explosion, it is considered that the natural ground in the direction perpendicular to the axis is also largely excavated.

[0091] Therefore, the size of the cross section perpendicular to the axial direction of the second region A2 can be calculated based on the ratio of the axial length of the second region A2 (the distance from the tip P0 of the second drilling hole H2 to the excavation line Y2 of the natural ground after blasting) to the size of the cross section perpendicular to the axial direction of the first region A1 described above (the distance from the center of the first drilling hole H1 to the excavation line Y1 of the natural ground after blasting) to the axial length (the distance from the tip P0 of the first drilling hole H1 to the excavation line Y2 of the natural ground after blasting). In other words, the size of the cross section perpendicular to the axial direction of the second region A2 acquired by the calculation unit 512 is not an actual measurement value, but an estimated value calculated based on the axial length of the second region A2 and the ratio of the size of the cross section perpendicular to the axial direction of the first region A1 to the axial length. In addition, when calculating the size of the cross section perpendicular to the axial direction of the second region A2, the ratio of the size of the cross section perpendicular to the axial direction of the first region A1 to the axial length may be, for example, that of the first region A1 closest to the second region A2, or the average of those of multiple first regions A1 included within a predetermined range from the second region A2, or the average of those of all multiple first regions A1.

[0092] The second output data acquisition unit 513 acquires as second output data the axial length of the second region formed by the explosion of the explosive loaded in the second borehole H2, and the size of a cross-section perpendicular to the axial direction of the second region A2 calculated based on the ratio between the size of the cross-section perpendicular to the axial direction of the first region A1 and the axial length of the first region A1.

[0093] The model generation unit 504 performs machine learning based on the first input data and the first output data, and further based on the second input data and the second output data, to generate a trained model that shows a correlation between the drilling energy consumed when drilling a drill hole into the face R, and the amount of explosives loaded in the drill hole, and the size of the area formed by the explosion of the explosives loaded in the drill hole, i.e., in addition to the correlation between the drilling energy consumed when drilling a first drill hole, and the amount of explosives loaded in the first drill hole, and the size of the area formed by the explosion of the explosives loaded in the first drill hole, the model generates a trained model that shows a correlation between the drilling energy consumed when drilling a second drill hole, and the amount of explosives loaded in the second drill hole, and the size of the area formed by the explosion of the explosives loaded in the second drill hole.

[0094] As described above, the blasting information processing device 5 further includes a second input data acquisition unit 511 that acquires as second input data the drilling energy consumed when a second drilling hole H2 different from the first drilling hole H1 is drilled in the face R, and the amount of explosives loaded in the second drilling hole H2, and a second output data acquisition unit 513 that acquires as second output data the axial length of a second region formed by the explosion of the explosives loaded in the second drilling hole H2, and the size of a cross section perpendicular to the axial direction of the second region A2 calculated based on the ratio between the size of a cross section perpendicular to the axial direction of the first region A1 and the axial length of the first region A1. The model generation unit 504 further performs machine learning based on the second input data and the second output data to generate a trained model showing a correlation between the drilling energy consumed when a drilling hole is drilled in the face R, the amount of explosives loaded in the drilling hole, and the size of the region formed by the explosion of the explosives loaded in the drilling hole.

[0095] Therefore, the blasting information processing device 5 can more easily collect training data for generating a learning model used to set blasting patterns, and can optimize the drilling position and the amount of explosives loaded based on the correlation with the size of the area formed by the explosion of the explosives loaded in the drilling hole.

[0096] [Other Modifications] The present invention is not limited to the above-mentioned embodiment, and may also include the following, for example.

[0097] In this embodiment, the input data acquisition unit acquires the drilling energy consumed when drilling the drilling hole and the amount of explosives loaded in the drilling hole as input data. However, the input data acquisition unit is not limited to this, and may further acquire information indicating the depth of the drilling hole (drilling length) as input data. In addition, information such as the type of explosives and the diameter of the drilling hole may be acquired as other data as input data. In this case, the model generation unit generates a trained model showing a correlation between information including these and the size of the area formed by the explosion of the explosives loaded in the drilling hole. In addition, information such as rock type, crack density, and spring water pressure at the drilling position may be acquired as other input data, and a trained model showing a correlation between information including these and the size of the area formed by the explosion may be generated.

[0098] In this embodiment, a full-section blasting method is used, but the present invention is not limited to this and may also be applied to a full-section method with an auxiliary bench or an upper semi-circular method.

[0099] The technical aspects of any of the embodiments may be combined to form an embodiment. [Explanation of symbols]

[0100] 1 drilling machine 2 Blasting pattern control device 3. Communication lines 4 Shape measuring device 5 Blasting information processing device 51 CPU 52 Bus 53 ROM 54 RAM 55 Non-volatile memory 56 Input / Output Interface 501 Reception 502 first input data acquisition unit 503 First output data acquisition unit 504 Model Generation Unit 505 Model Memory Unit 506 Output section 511 Second input data acquisition unit 512 Calculation Unit 513 Second output data acquisition unit

Claims

1. A blasting information processing device for use in a blasting method in which explosives loaded in each of a plurality of drilling holes arranged in a face are detonated to perform a single blast, a first input data acquisition unit that acquires, as first input data for each drilling hole, a drilling energy consumed when a first drilling hole that is located on an outer peripheral edge portion of a face of the drilling hole is drilled and an amount of explosives loaded in the first drilling hole; a first output data acquisition unit that acquires, as first output data for each borehole, a size of a cross section perpendicular to an axial direction of a first region that is set based on the shape of the natural ground after the blasting and is formed by the explosion of the explosive loaded in the first borehole; A model generation unit that executes machine learning based on the first input data and the first output data to generate a trained model that shows a correlation between the drilling energy consumed when drilling the first borehole, the amount of explosives loaded in the first borehole, and the size of an area formed by the explosion of the explosives loaded in the first borehole; A blasting information processing device comprising:

2. The first output data acquisition unit further acquires, as first output data for each borehole, an axial length of a first region that is set from the shape of the natural ground after the blasting and is formed by the explosion of the explosive loaded in the first borehole; a second input data acquisition unit that acquires, as second input data for each of the drilling holes, drilling energy consumed when a second drilling hole different from the first drilling hole is drilled and an amount of explosives loaded in the second drilling hole; and a second output data acquisition unit that acquires, as second output data for each drilling hole, the axial length of a second region that is set from the shape of the natural ground after the blasting and that is formed by the explosion of the explosives loaded in the second drilling hole, and the size of a cross section perpendicular to the axial direction of the second region that is calculated based on the ratio between the size of the cross section perpendicular to the axial direction of the first region and the length in the axial direction of the first region, The blasting information processing device of claim 1, wherein the model generation unit further performs machine learning based on the second input data and the second output data to generate a trained model showing a correlation between the drilling energy consumed when drilling the second borehole, the amount of explosives loaded in the second borehole, and the size of the area formed by the explosion of the explosives loaded in the second borehole.

3. A blasting information processing method for use in a blasting method in which explosives loaded in each of a plurality of drill holes arranged in a face are detonated to perform a single blast, comprising the steps of: Acquiring, as first input data for each drilling hole, a drilling energy consumed when a first drilling hole disposed on an outer peripheral edge portion of a face is drilled and an amount of explosives loaded in the first drilling hole; acquiring, as first output data for each borehole, a size of a cross section perpendicular to an axial direction of a first region that is set based on the shape of the natural ground after the blasting and that is formed by detonating the explosives loaded in the first borehole; Executing machine learning based on the first input data and the first output data to generate a trained model showing a correlation between the drilling energy consumed when drilling the first borehole, the amount of explosives loaded in the first borehole, and the size of an area formed by the explosion of the explosives loaded in the first borehole; A blasting information processing method comprising:

4. As the first output data, the axial length of a first region formed by the explosion of the explosives loaded in the first borehole is acquired for each borehole, the axial length being set from the shape of the natural ground after the blasting; Acquiring, as second input data for each of the drilling holes, drilling energy consumed when a second drilling hole different from the first drilling hole is drilled and an amount of explosives loaded into the second drilling hole; and acquiring, as second output data for each drilling hole, an axial length of a second region formed by the explosion of the explosives loaded in the second drilling hole, and a size of a cross section perpendicular to the axial direction of the second region, the size being calculated based on a ratio between a size of the cross section perpendicular to the axial direction of the first region and a length in the axial direction of the first region; The blasting information processing method of claim 3 further comprises performing machine learning based on the second input data and the second output data to generate a trained model showing a correlation between the drilling energy consumed when drilling the second borehole, the amount of explosives loaded in the second borehole, and the size of the area formed by the explosion of the explosives loaded in the second borehole.

5. In a blasting information processing device used in a blasting method in which explosives loaded in each of a plurality of drill holes arranged in a face are detonated to perform a single blast, a trained model is generated based on first input data and first output data, The first input data is obtained by acquiring, for each of the drilling holes, a drilling energy consumed when a first drilling hole disposed on an outer peripheral edge portion of a face of the drilling hole is drilled, and an amount of explosives loaded into the first drilling hole, The first output data is set based on the shape of the natural ground after the blasting, and is obtained for each borehole by measuring the size of a cross section perpendicular to the axial direction of a first region formed by the explosion of the explosive loaded in the first borehole, A trained model generated by performing machine learning based on the first input data and the first output data, the trained model indicating a correlation between the drilling energy consumed when drilling the first borehole, the amount of explosives loaded into the first borehole, and the size of the area formed by the explosion of the explosives loaded into the first borehole.

6. further generated based on the second input data and the second output data; The first output data is further set from the shape of the natural ground after the blasting, and is obtained for each of the first boreholes by acquiring an axial length of a first region formed by the explosion of the explosive loaded in the first borehole, The second input data is obtained by acquiring, for each of the perforations, a perforation energy consumed when a second perforation different from the first perforation is perforated, and an amount of explosives loaded into the second perforation, The second output data is set from the shape of the natural ground after the blasting, and is obtained for each borehole by calculating the axial length of a second region formed by the explosion of the explosive loaded in the second borehole, and the size of a cross section perpendicular to the axial direction of the second region calculated based on the ratio between the size of the cross section perpendicular to the axial direction of the first region and the axial length of the first region, The trained model of claim 5 further shows a correlation between the drilling energy consumed when drilling the second perforation, and the amount of explosives loaded in the second perforation, generated by performing machine learning based on the second input data and the second output data, and the size of the area formed by the explosion of the explosives loaded in the second perforation.

Images