Anchor drilling vehicle system and method capable of quickly detecting rock mass hardness

Abstract

The invention belongs to the technical field of rock mass hardness detection, and specifically discloses an anchor drilling vehicle system and method for quickly detecting rock mass hardness. The system comprises: an anchor drilling vehicle, comprising an anchor drilling vehicle body, a drilling unit provided on the anchor drilling vehicle body, and a drilling parameter monitoring unit arranged on the drilling unit; a data processing module, configured to obtain drilling parameters and perform data processing, and finally obtain rock mass hardness and blasthole spacing, so as to optimize the on-site rock mass blasting effect; the invention can realize drilling-based rapid detection of rock mass hardness, thereby improving detection efficiency; determine the number and spacing of blastholes in sub-areas of different blasting grades according to rock mass hardness, optimize the blasthole spacing in different sub-areas, guide on-site blasting design, avoid the problem of too many or too few blastholes, and thus optimize the blasting effect.

Description

Technical Field

[0001] The invention relates to the technical field of rock mass hardness detection, and in particular to an anchor drilling vehicle system and method capable of quickly detecting rock mass hardness. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] In the current underground engineering construction, the rock mass Proctor hardness test is an important method to evaluate the hardness and strength of rock. Obtaining the hardness of the rock mass can help determine the compressive capacity of the rock formation and guide the optimization of the rock formation support design.

[0004] At present, the commonly used rock mass Proctor hardness test method is mainly obtained through indoor compression experiments, which requires on-site rock mass processing and testing, which is time-consuming and labor-intensive. Anchor drilling vehicles are widely used in underground engineering sites. Therefore, how to use the drilling parameter data obtained by anchor drilling vehicles to directly predict the rock mass Proctor hardness has become one of the problems that need to be solved.

[0005] In addition, the excavation of underground engineering rock mass mostly adopts the traditional drilling and blasting method, that is, according to the blasting design, a blasthole of a certain diameter and depth is drilled on the rock mass, and then charged, connected and detonated to achieve the purpose of excavation. The number of blastholes is an important indicator of the drilling and blasting design. If there are too many blastholes, the drilling workload will increase, the blasting cost and time will increase, and too many blastholes may increase the consumption of explosives and cause resource waste; if there are too few blastholes, the blasting effect will be poor, the number of large pieces will increase, the wall surface will be uneven, and it may even be impossible to blast open, which may lead to uneven rock crushing, and too few blastholes may increase the safety risks during the blasting process.

[0006] In the prior art, the selection of the number of blastholes often needs to be determined based on engineering experience. For example, it is necessary to obtain in advance parameters such as the consumption of explosives per unit volume, the cross-sectional area of ​​the tunnel excavation, the utilization rate of the blasthole, the charging coefficient, and the mass of explosives per meter of the cartridge. Among them, the decisive factor is the consumption of explosives per unit volume, which is directly related to the rock type and hardness, and requires a lot of geological exploration and data collection in the early stage, which is time-consuming and labor-intensive. Summary of the invention

[0007] In order to solve the above problems, the present invention proposes an anchor drilling vehicle system and method that can quickly detect the hardness of rock masses. The anchor drilling vehicle is used to carry out drilling tests to obtain drilling parameters. Based on the drilling parameters, a rock hardness prediction model is used to obtain the hardness information of the rock mass under in-situ conditions. Then, the number of blastholes in each sub-area is determined based on the hardness information, thereby optimizing the blasthole spacing.

[0008] In some embodiments, the following technical solutions are adopted:

[0009] An anchor drilling vehicle system capable of quickly detecting rock mass hardness comprises:

[0010] An anchor drilling vehicle comprises an anchor drilling vehicle body, the anchor drilling vehicle body is provided with a drilling unit, and a drilling parameter monitoring unit arranged on the drilling unit; the drilling parameter monitoring unit is used to monitor drilling parameters;

[0011] The data processing module is configured to obtain the drilling parameters and perform data processing, and finally obtain the rock hardness and the blasthole spacing to optimize the on-site rock blasting effect; the data processing module includes:

[0012] A rock mass hardness prediction unit is configured to input the acquired while-drilling parameter data into a trained rock mass hardness prediction model to predict the rock mass hardness data corresponding to each borehole;

[0013] The blasthole spacing optimization unit is configured to perform blasting classification on different areas of the rock mass according to the obtained rock mass hardness data corresponding to each borehole, calculate the number of blastholes in each blasting grade sub-area, and thereby optimize the blasthole spacing.

[0014] As a further solution, the drilling unit includes a drilling platform and a direction adjustment device. The drilling platform includes a drill rod, a rotary thruster and a fixed column. The drill rod is connected to the rotary thruster. A drill bit is provided at the front end of the drill rod. The rotary thruster is arranged on the fixed column and can move forward and backward along the fixed column. The direction adjustment device is arranged between the drilling platform and the anchor drilling vehicle body, and is used to adjust the drilling direction of the drilling platform.

[0015] As a further solution, the drilling parameter monitoring unit includes:

[0016] A pressure sensor used to obtain the changes in drilling pressure during drilling in real time; a torque sensor used to obtain the changes in drill bit torque during drilling in real time; a speed sensor used to collect the rotation period of the rotary propeller in real time and obtain the changes in speed during drilling; a drilling speed sensor used to obtain the changes in drilling speed during drilling in real time; a vibration sensor used to obtain drill bit vibration data in real time.

[0017] As a further solution, the rock mass hardness prediction model includes an input layer, a hidden layer and an output layer;

[0018] Among them, the number of hidden layers K and the number of hidden layer neurons L are determined by the fitting coefficient R, specifically:

[0019] The number of neurons in the hidden layer is fixed to L 1 , the initial number of hidden layers K 1 Substitute it into the rock hardness prediction model for training and get the fitting coefficient Ri1 , update the number of hidden layers to K 2 , substituted into the rock hardness prediction model for training, and the fitting coefficient R i2 ; Repeat this process until the fitting coefficient R ii Satisfy the set requirements, R ii The corresponding K i is the optimal number of hidden layers;

[0020] Fixed number of hidden layers K i , the initial number of hidden layer neurons L 1 Substitute it into the rock hardness prediction model for training and get the fitting coefficient R j1 ; Update the number of hidden layer neurons to L 2 , substituted into the rock hardness prediction model for training, and the fitting coefficient R j2 ; Repeat this process until the fitting coefficient R ji Satisfy the set requirements, R ji The corresponding L i is the optimal number of hidden layer neurons.

[0021] As a further solution, the number of blastholes in each blasting level sub-area is calculated as follows:

[0022] Based on the rock hardness data corresponding to each borehole, calculate the average rock hardness value;

[0023] Calculate the total amount of explosives required based on the average hardness of the rock mass; determine the total number of blastholes based on the set amount of explosives for each blasthole y ;

[0024] Calculate the average rock hardness of each blasting grade sub-area and the sum of the average rock hardness of all blasting grade sub-areas; based on the proportional relationship between the two, use the total number of blastholes to obtain the number of blastholes in each blasting grade sub-area y i .

[0025] As a further solution, the total amount of explosives required is calculated based on the average hardness of the rock mass, specifically:

[0026] T = α × h+β ;

[0027] in, T is the total amount of explosives; α and β are the fitting coefficients of the evaluation relationship between Pugh hardness and explosive quantity, which are determined through in-situ rock mass tests.

[0028] As a further solution, the number of blastholes in each blasting level sub-area is obtained, specifically:

[0029] ;

[0030] in, y i For the i The number of blastholes in each blasting level sub-area, h i For the i The average value of Pugh hardness in each blasting grade sub-area, y is the total number of blastholes in all blasting grade sub-areas, and m is the total number of sub-areas.

[0031] In other embodiments, the following technical solutions are adopted:

[0032] A working method of an anchor drilling vehicle system capable of quickly detecting rock mass hardness, comprising:

[0033] Use the anchor drilling vehicle to drill holes in the area to be tested and obtain the drilling parameters corresponding to each hole;

[0034] The acquired while-drilling parameter data is input into the trained rock hardness prediction model to predict the rock hardness data corresponding to each borehole;

[0035] According to the rock hardness data corresponding to each borehole, blasting classification is performed on different areas of the rock mass, and the number of blasting holes in each blasting grade sub-area is calculated;

[0036] Based on the number of blastholes in each blasting grade sub-area, blastholes are evenly arranged in the corresponding blasting grade sub-area, thereby optimizing the blasthole spacing in the entire area to be tested.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] (1) The present invention conducts in-situ drilling tests on the engineering site, substitutes the drilling parameters into the rock hardness prediction neural network, and inverts the rock hardness to obtain the rock hardness; thus, rapid detection of rock hardness while drilling can be achieved, thereby improving detection efficiency.

[0039] (2) The present invention determines the total amount of explosives required according to the hardness of the rock mass, and calculates the total number of blastholes; based on the range of the rock mass hardness of each borehole, the test area is divided into sub-areas of five blasting levels, namely, difficult-to-blast rock mass, relatively difficult-to-blast rock mass, medium-to-blast rock mass, relatively easy-to-blast rock mass and easy-to-blast rock mass; the average rock mass hardness of each sub-area is calculated, and then the number of blastholes in each sub-area is calculated; the blastholes in each sub-area are evenly arranged, and the sub-area with a higher blasting level has a larger number of blastholes; compared with the prior art method of combining a variety of on-site parameters and determining the number of blastholes based on engineering experience, the present invention can determine the number and spacing of blastholes in sub-areas of different blasting levels based on the rock mass hardness, optimize the spacing of blastholes in different sub-areas, guide on-site blasting design, avoid the problem of too many or too few blastholes, and thus optimize the blasting effect.

[0040] (3) The anchor drilling vehicle of the present invention can perform in-situ drilling tests on site. By obtaining the drilling parameters during the rock drilling process and using the rock hardness prediction model, the Proctor hardness of the rock mass can be directly obtained, thereby realizing rapid and accurate determination of the rock hardness.

[0041] Other features and advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic diagram of the structure of the anchor drilling vehicle in an embodiment of the present invention;

[0043] Figure 2 Schematic diagram of the rock hardness prediction model training process in an embodiment of the present invention;

[0044] Figure 3 A schematic diagram of a working method of an anchor drilling vehicle system capable of quickly detecting rock mass hardness according to an embodiment of the present invention;

[0045] Among them, 1. drill bit, 2. drill rod, 3. fixed column, 4. rotary propeller, 5. horizontal adjuster, 6. vertical adjuster, 7. drill arm support column, 8. crawler chassis. DETAILED DESCRIPTION

[0046] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0047] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0048] Embodiment 1

[0049] In one or more embodiments, a bolt drilling vehicle system capable of quickly detecting rock hardness is disclosed, specifically comprising:

[0050] (1) An anchor drilling vehicle, comprising an anchor drilling vehicle body, a drilling unit provided on the anchor drilling vehicle body, and a drilling parameter monitoring unit provided on the drilling unit; the drilling parameter monitoring unit is used to monitor drilling parameters.

[0051] (2) A data processing module is configured to obtain the drilling parameters and perform data processing, and finally obtain the rock hardness and the blasthole spacing to optimize the on-site rock blasting effect; the data processing module includes:

[0052] (2-1) a rock hardness prediction unit, configured to input the acquired while-drilling parameter data into a trained rock hardness prediction model to predict the rock hardness data corresponding to each borehole;

[0053] (2-2) The blasthole spacing optimization unit is configured to perform blasting classification on different areas of the rock mass according to the obtained rock mass hardness data corresponding to each drill hole, calculate the number of blastholes in each blasting grade sub-area, and thereby optimize the blasthole spacing.

[0054] Specifically, combined Figure 1 The specific structure of the anchor drilling vehicle in this embodiment includes: an anchor drilling vehicle body, and the anchor drilling vehicle body includes a crawler chassis 8, which can meet the needs of drilling vehicle walking under complex underground engineering conditions.

[0055] A drilling unit is provided on the anchor drilling vehicle body, and the drilling unit includes a drilling platform and a direction regulator, wherein the drilling platform includes a drill bit 1, a drill rod 2, a fixed column 3 and a rotary propeller 4, etc. The drill rod 2 is connected to the rotary propeller 4, and the rotary propeller 4 can control drilling parameters such as the propulsion speed and rotation speed of the drill rod, so as to realize real-time regulation of the drilling parameters; a drill bit 1 is provided at the front end of the drill rod 2, and the drill rod drives the drill bit to rotate and propel, so as to realize rotary cutting of the rock mass in front; the rotary propeller is provided on the fixed column and can move forward and backward along the fixed column; the fixed column can ensure the overall stability of the drilling platform during the drilling and propulsion process of the drill rod.

[0056] The direction adjustment device is arranged between the drilling platform and the anchor drilling vehicle body, and is used to adjust the drilling direction of the drilling platform; the direction adjustment device is composed of a horizontal adjuster 5, a vertical adjuster 6 and a drill arm support column 7. The horizontal adjuster 5 realizes the angle adjustment of the drilling platform in the horizontal direction, and the vertical adjuster 6 realizes the angle adjustment of the drilling platform in the vertical direction. The horizontal adjuster and the vertical adjuster work together to realize multi-horizontal direction drilling of the drilling platform; the drill arm support column 7 is used to support the drilling platform to ensure the overall stability of the drilling device.

[0057] In this embodiment, the drilling parameter monitoring unit includes: a pressure sensor for real-time acquisition of drilling pressure changes during drilling; a torque sensor for real-time acquisition of drill bit torque changes during drilling; a speed sensor for real-time acquisition of the rotation cycle of the rotary propeller and acquisition of drill bit speed changes during drilling; a drilling speed sensor for real-time acquisition of drilling speed changes during drilling; and a vibration sensor for real-time acquisition of drill bit vibration data. Among them, the speed sensor, drilling speed sensor and vibration sensor can be set on the rotary propeller, and the pressure sensor and torque sensor can be set on the drilling platform.

[0058] The drilling parameters during each drilling process can be obtained through the drilling parameters monitoring unit. The drilling parameters specifically include drill bit torque, drill bit speed, drill bit vibration, drilling speed and drilling pressure.

[0059] In this embodiment, the rock hardness prediction unit obtains the while-drilling parameter data of each borehole and inputs the data into the trained rock hardness prediction model to predict the rock hardness data corresponding to each borehole.

[0060] The rock hardness prediction model of this embodiment is a neural network model, including an input layer, a hidden layer and an output layer. As a specific example, there are 5 input units, namely drill bit torque, drill bit speed, drill bit vibration, drilling speed and drilling pressure; there is 1 output unit, which is the rock mass hardness.

[0061] The number of hidden layers is K, and the number of neurons in the hidden layer is L; the number of hidden layers K and the number of neurons in the hidden layer L are determined by the fitting coefficient R. First, K 1 =5 and substitute it into the neural network for training. At this time, fix L 1 =1, and the fitting coefficient R is obtained. 1 , then take K 2 =6 is substituted into the neural network for training and the fitting coefficient R is obtained. 2 Until R is obtained i >95%, R i The corresponding K i is the optimal number of hidden layers. i , L increases by 1 each time and is substituted into the neural network for training until R is obtainedj >95%, R j The corresponding L j is the optimal number of hidden layer neurons, and the number of neurons in each hidden layer is the same.

[0062] The neurons in the i-th layer of the neural network model are fully connected to the neurons in the i+1-th layer. The nonlinear activation function of the hidden layer is the ReLU function, and the learning rate is determined by trial and error.

[0063]

[0064] In the formula, x is the output of the previous neuron.

[0065] In this embodiment, the training process of the rock mass hardness prediction neural network model is as follows: Figure 2 As shown, firstly, the anchor drilling vehicle is tested while drilling to obtain the drill torque, drill speed, drill vibration, drilling speed and drilling pressure while drilling parameters as input units; at the same time, the rock hardness at the drilling position is tested and obtained as the real output unit.

[0066] According to the above process, corresponding arrays of multiple groups of input units and corresponding real output units are obtained to form a training data set.

[0067] When training the neural network model, the input unit is multiplied by the first weight coefficient w 1 Add the first bias variable b 1 , substitute into the hidden layer for nonlinear operation, after determining K i After linear and nonlinear operations on hidden layers, multiply by the weight coefficient w i+1 Add the bias variable b i+1 Get the output unit, calculate the error between the output unit and the real output unit using the least squares method, and continuously update the weight w i and the bias variable b i , and when the error reaches the expected value, a trained rock hardness prediction model is obtained.

[0068] In this embodiment, the blasthole spacing optimization unit performs blasting classification on different areas of the rock mass according to the obtained rock mass hardness data corresponding to each borehole, calculates the number of blastholes in each blasting grade sub-area, and thereby optimizes the blasthole spacing.

[0069] Specifically, an evaluation relationship between the Proctor hardness of the rock mass to be blasted and the amount of explosives required is established:

[0070] T = α × h+β

[0071] in,h is the average hardness of the rock mass, T is the total amount of explosives, α and β The fitting coefficient of the evaluation relationship between the Pullman hardness and the amount of explosives is determined through in-situ rock mass tests. The Pullman hardness of the rock mass is substituted into the evaluation relationship to determine the total amount of explosives required for the rock mass in the area to be blasted.

[0072] Calculate the charge of a single blast hole and the total number of blast holes, the relationship is: T = x × y ,in x The charge for a single blast hole can be set as needed; y is the total number of blastholes. This formula can be used to calculate the total number of blastholes. y .

[0073] In this embodiment, according to the Pusch hardness test results corresponding to each borehole, the difficulty of blasting the rock mass to be blasted is divided into five levels, namely: difficult to blast rock mass, relatively difficult to blast rock mass, medium blast rock mass, relatively easy to blast rock mass, and easy to blast rock mass. As shown in Table 1, according to the rock mass blasting level, the rock mass is divided into m Sub-area ( m =1, 2, 3, 4,5), for example: the corresponding areas of all boreholes with rock hardness values ​​less than 2 constitute the blasting-prone rock sub-area.

[0074] Table 1

[0075]

[0076] For each sub-area, calculate the average value of the rock mass Proctor hardness corresponding to all the boreholes in it. h i , then the number of blastholes in each area is determined according to the classification results of the rock mass to be blasted, specifically:

[0077] ;

[0078] in, y i For the i The number of blastholes in each sub-area, h i For the i The average Pugh hardness of each sub-area is y is the total number of blastholes, and m is the total number of sub-areas. i The number of blast holes in a sub-region is equal to the ratio of the average value of the universal hardness of the ith sub-region to the average value of the universal hardness of all sub-regions multiplied by the total number of blast holes.

[0079] Based on the above formula, the number of blastholes y in the i-th sub-area can be obtainedi The blastholes in each sub-area are evenly arranged to optimize the blasthole spacing of the entire rock mass, thereby guiding the on-site blasting design and optimizing the on-site rock blasting effect.

[0080] Embodiment 3

[0081] In one or more embodiments, a method for operating an anchor drilling vehicle system capable of quickly detecting rock mass hardness is disclosed, in combination with Figure 3 , specifically including the following process:

[0082] (1) Use the anchor drilling vehicle to drill holes in the area to be tested and obtain the drilling parameters corresponding to each hole;

[0083] (2) Input the acquired while-drilling parameter data into the trained rock hardness prediction model to predict the rock hardness data corresponding to each borehole;

[0084] (3) According to the rock hardness data corresponding to each borehole, blasting classification is performed on different areas of the rock mass, and the number of blast holes in each blasting grade sub-area is calculated;

[0085] (4) Based on the number of blastholes in each blasting grade sub-area, blastholes are evenly arranged in the corresponding blasting grade sub-area, thereby optimizing the blasthole spacing in the entire test area.

[0086] Among them, the number of blastholes in each blasting level sub-area is calculated as follows:

[0087] Based on the rock hardness data corresponding to each borehole, calculate the average rock hardness value;

[0088] Calculate the total amount of explosives required based on the average hardness of the rock mass; determine the total number of blastholes based on the set amount of explosives for each blasthole y ;

[0089] Calculate the average rock hardness of each blasting grade sub-area and the sum of the average rock hardness of all blasting grade sub-areas; based on the proportional relationship between the two, use the total number of blastholes to obtain the number of blastholes in each blasting grade sub-area y i .

[0090] The specific implementation method of the above steps is the same as that in Example 1, so it will not be described in detail.

[0091] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. An anchor drilling vehicle system capable of quickly detecting rock hardness, characterized in that: include: The anchor drilling vehicle comprises an anchor drilling vehicle body, the anchor drilling vehicle body is provided with a drilling unit, and a drilling parameter monitoring unit arranged on the drilling unit; The drilling-while-drilling parameter monitoring unit is used to monitor drilling-while-drilling parameters; The data processing module is configured to obtain the drilling parameters and perform data processing, and finally obtain the rock hardness and the blasthole spacing to optimize the on-site rock blasting effect; the data processing module includes: A rock mass hardness prediction unit is configured to input the acquired while-drilling parameter data into a trained rock mass hardness prediction model to predict the rock mass hardness data corresponding to each borehole; The blasthole spacing optimization unit is configured to perform blasting classification on different areas of the rock mass according to the obtained rock mass hardness data corresponding to each drill hole, calculate the number of blastholes in each blasting grade sub-area, and thus optimize the blasthole spacing; Calculate the number of blastholes in each blasting level sub-area, specifically: Based on the rock hardness data corresponding to each borehole, calculate the average rock hardness value; Calculate the total amount of explosives required based on the average hardness of the rock mass; determine the total number of blastholes based on the set amount of explosives for each blasthole y ; Calculate the average rock hardness of each blasting grade sub-area and the sum of the average rock hardness of all blasting grade sub-areas; based on the proportional relationship between the two, use the total number of blastholes to obtain the number of blastholes in each blasting grade sub-area y i .

2. The anchor drilling vehicle system capable of quickly detecting rock hardness according to claim 1, characterized in that: The drilling unit includes a drilling platform and a direction adjustment device. The drilling platform includes a drill rod, a rotary propeller and a fixed column. The drill rod is connected to the rotary propeller. A drill bit is provided at the front end of the drill rod. The rotary propeller is arranged on the fixed column and can move forward and backward along the fixed column. The direction adjustment device is arranged between the drilling platform and the anchor drilling vehicle body and is used to adjust the drilling direction of the drilling platform.

3. The anchor drilling vehicle system capable of quickly detecting rock hardness according to claim 1, characterized in that: The drilling parameter monitoring unit comprises: A pressure sensor used to obtain the changes in drilling pressure during drilling in real time; a torque sensor used to obtain the changes in drill bit torque during drilling in real time; a speed sensor used to collect the rotation period of the rotary propeller in real time and obtain the changes in speed during drilling; a drilling speed sensor used to obtain the changes in drilling speed during drilling in real time; a vibration sensor used to obtain drill bit vibration data in real time.

4. The anchor drilling vehicle system capable of quickly detecting rock hardness according to claim 1, characterized in that: The rock mass hardness prediction model includes an input layer, a hidden layer and an output layer; Among them, the number of hidden layers K and the number of hidden layer neurons L are determined by the fitting coefficient R, specifically: The number of hidden layer neurons is fixed to L1, and the initial number of hidden layer neurons K1 is substituted into the rock hardness prediction model for training to obtain the fitting coefficient R i1 , update the number of hidden layers to K2, substitute it into the rock hardness prediction model for training, and get the fitting coefficient R i2 ; Repeat this process until the fitting coefficient R ii Satisfy the set requirements, R ii The corresponding K i is the optimal number of hidden layers; Fixed number of hidden layers K i , substitute the initial hidden layer neuron number L1 into the rock hardness prediction model for training, and obtain the fitting coefficient R j1 ; Update the number of hidden layer neurons to L2, substitute it into the rock hardness prediction model for training, and get the fitting coefficient R j2 ; Repeat this process until the fitting coefficient R ji Satisfy the set requirements, R ji The corresponding L i is the optimal number of hidden layer neurons.

5. The anchor drilling vehicle system capable of quickly detecting rock hardness as claimed in claim 1, characterized in that: The total amount of explosives required is calculated based on the average hardness of the rock mass, specifically: T = α × h+β ； in, T is the total amount of explosives; α and β are the fitting coefficients of the evaluation relationship between Pugh hardness and explosive quantity, which are determined through in-situ rock mass tests.

6. The anchor drilling vehicle system capable of quickly detecting rock hardness according to claim 1, characterized in that: Get the number of blastholes in each blasting level sub-area, specifically: ； in, y i For the i The number of blastholes in each blasting level sub-area, h i For the i The average value of Pugh hardness in each blasting grade sub-area, y is the total number of blastholes in all blasting grade sub-areas, and m is the total number of sub-areas.

7. A working method of an anchor drilling vehicle system capable of quickly detecting rock hardness, characterized in that: include: Use the anchor drilling vehicle to drill holes in the area to be tested and obtain the drilling parameters corresponding to each hole; The acquired while-drilling parameter data is input into the trained rock hardness prediction model to predict the rock hardness data corresponding to each borehole; According to the rock hardness data corresponding to each borehole, blasting classification is performed on different areas of the rock mass, and the number of blasting holes in each blasting grade sub-area is calculated; Based on the number of blastholes in each blasting grade sub-area, blastholes are evenly arranged in the corresponding blasting grade sub-area, so as to optimize the blasthole spacing of the entire test area; the number of blastholes in each blasting grade sub-area is calculated, specifically: Based on the rock hardness data corresponding to each borehole, calculate the average rock hardness value; Calculate the total amount of explosives required based on the average hardness of the rock mass; determine the total number of blastholes based on the set amount of explosives for each blasthole y ; Calculate the average rock hardness of each blasting grade sub-area and the sum of the average rock hardness of all blasting grade sub-areas; based on the proportional relationship between the two, use the total number of blastholes to obtain the number of blastholes in each blasting grade sub-area y i .

Images