Fine construction method for large-area open-pit bench deep-hole blasting and related components

Abstract

The present invention discloses a refined construction method for large-area open-pit bench deep-hole blasting and related components, which relates to the field of engineering blasting. The method includes obtaining multiple sets of blasting site data; training a pre-built blasting effect prediction model using all the blasting site data, and outputting a target blasting effect prediction model after the training is completed; inputting the target site data into the target blasting effect prediction model to output target blasting parameters; after drilling operations are carried out based on the target blasting parameters, obtaining the wear state data and drilling speed data of the drill bit, and obtaining the Proctor hardness coefficient of the rock at the drilling hole to obtain the hardness data of the rock mass around the hole; based on the hardness data, calculating the charge amount of the target row of holes; through the output of more accurate target blasting parameters by the target blasting effect prediction model in this application, the intelligent drill can drill holes precisely, so as to obtain the hardness data of the rock mass around the hole, and dynamically adjust the charge amount to make the obtained charge amount more accurate.

Description

Technical Field

[0001] The present invention relates to the field of engineering blasting, and particularly to a refined construction method for large-area open-pit bench deep-hole blasting and related components. Background Art

[0002] Currently, when designing blasting parameters, the design is carried out according to the empirical formula for calculating open-pit bench blasting parameters. However, due to the limited accuracy of the preliminary exploration, only a general stratum condition can be given in the preliminary exploration. The lithology of the underground rock formation often varies due to fractures, weak interlayers, and changes in moisture content. Therefore, the actual situation of the stratum lithology (hard rock, relatively hard rock, relatively soft rock, soft rock, and extremely soft rock) is uncertain, making the blasting parameters calculated by the empirical formula for calculating open-pit bench blasting parameters inaccurate. Moreover, the empirical formula for calculating open-pit bench blasting parameters often only gives a value range, and it is difficult to determine a more accurate value.

[0003] Meanwhile, in the previous blasting operation environment, on-site personnel could not accurately obtain rock formation information and only calculated the charge amount based on the hole depth and blasting volume according to the preliminary exploration report. Due to the complex underground lithology conditions, such as the existence of joints, fractures, weak interlayers, etc., if the charge situation cannot be dynamically adjusted according to the lithology conditions at this time, the blasting energy of the explosive cannot be fully utilized, resulting in large blocks and bottom roots, and the blasting effect is far lower than expected. Summary of the Invention

[0004] The purpose of the present invention is to provide a refined construction method for large-area open-pit bench deep-hole blasting and related components, aiming to solve the problem that the existing on-site explosive mixing is prone to errors in calculating blasting parameters due to the uncertainty of the stratum lithology, resulting in inaccurate calculation of the charge amount.

[0005] To solve the above technical problems, the purpose of the present invention is achieved through the following technical solutions: providing a refined construction method for large-area open-pit bench deep-hole blasting, which includes:

[0006] Obtaining multiple groups of blasting site data, wherein each group of the blasting site data includes on-site parameters and corresponding blasting parameters;

[0007] Using all the blasting site data to train a pre-built blasting effect prediction model, wherein the mean square error of the blasting effect prediction model is calculated according to the following formula:

[0008]

[0009] Wherein, f Z represents the mean square error; q s represents the number of output units; e k represents the output value of the kth unit; j kRepresents the target value of the k-th unit;

[0010] After the mean square error meets the preset error performance index, output the target blasting effect prediction model after the training ends;

[0011] Input the target field data into the target blasting effect prediction model and output the target blasting parameters;

[0012] After drilling operations are carried out based on the target blasting parameters, obtain the wear state data and drilling speed data of the drill bit;

[0013] Based on the wear state data and drilling speed data, obtain the Proctor hardness coefficient of the rock at the drilling hole, and calculate the hardness data σ of the rock mass around the hole according to the following formula c :

[0014] σ c = 10×f

[0015] where f represents the Proctor hardness coefficient of the rock;

[0016] Based on the hardness data of the rock mass around the hole, calculate the charge amount of the target blast holes according to the following formula:

[0017] E1 = eaW d H

[0018] E2 = KeabH

[0019] where E1 represents the charge amount per hole of the first row of blast holes, E2 represents the charge amount per hole of the other rows of blast holes, e represents the specific consumption, K represents the correlation coefficient, H represents the bench height, W d represents the burden, a represents the hole spacing, and b represents the row spacing.

[0020] In addition, the technical problem to be solved by the present invention is also to provide a refined construction device for large-area open-pit bench deep-hole blasting in tunnels, which includes:

[0021] An acquisition unit for acquiring multiple groups of blasting site data, where each group of the blasting site data includes site parameters and corresponding blasting parameters;

[0022] A training unit for training a pre-built blasting effect prediction model using all the blasting site data, where the mean square error of the blasting effect prediction model is calculated according to the following formula:

[0023]

[0024] where f Z represents the mean square error; q s represents the number of output units; e k represents the output value of the k-th unit; jk represents the target value of the k-th unit;

[0025] An output unit, configured to output a target blasting effect prediction model after the mean square error meets a preset error performance index;

[0026] A target blasting parameter output unit, configured to input target site data into the target blasting effect prediction model and output target blasting parameters;

[0027] A drilling data acquisition unit, configured to acquire the wear state data and drilling speed data of the drill bit after drilling operations are performed based on the target blasting parameters;

[0028] A hardness data acquisition unit, configured to obtain the Proctor hardness coefficient of the rock at the drilling location based on the wear state data and drilling speed data, and calculate the hardness data σ of the rock mass around the hole according to the following formula c :

[0029] σ c = 10×f

[0030] where f represents the Proctor hardness coefficient of the rock;

[0031] A calculation unit, configured to calculate the charge amount of the target blast holes according to the following formula based on the hardness data of the rock mass around the hole:

[0032] E1 = eaW d H

[0033] E2 = KeabH

[0034] where E1 represents the charge amount per hole of the first row of blast holes, E2 represents the charge amount per hole of the other rows of blast holes, e represents the specific consumption, K represents the correlation coefficient, H represents the bench height, and W d represents the burden, a represents the hole spacing, and b represents the row spacing.

[0035] In addition, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the large-area open-pit bench deep-hole blasting refined construction method described in the first aspect above.

[0036] In addition, an embodiment of the present invention also provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor is caused to execute the large-area open-pit bench deep-hole blasting refined construction method described in the first aspect above.

[0037] An embodiment of the present invention discloses a refined construction method and related components for large-area open-pit bench deep-hole blasting. The method includes: obtaining multiple groups of blasting site data; training a pre-built blasting effect prediction model using all the blasting site data; after the mean square error meets the preset error performance index, outputting the target blasting effect prediction model after training; inputting the target site data into the target blasting effect prediction model to output the target blasting parameters; after drilling operations are carried out based on the target blasting parameters, obtaining the wear state data and drilling speed data of the drill bit; based on the wear state data and drilling speed data, obtaining the Proctor hardness coefficient of the rock at the drilling hole to obtain the hardness data of the rock mass around the hole; calculating the charge amount of the target row of holes based on the hardness data of the rock mass around the hole. This method outputs more accurate target blasting parameters through the target blasting effect prediction model, enabling the intelligent drill rig to accurately drill holes, thereby obtaining the hardness data around the holes to dynamically adjust the charge amount and make the obtained charge amount more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1 It is a flowchart of the refined construction method for large-area open-pit bench deep-hole blasting provided by the embodiment of the present invention;

[0040] Figure 2 It is a structural diagram of the blasting effect prediction model in the refined construction method for large-area open-pit bench deep-hole blasting provided by the embodiment of the present invention;

[0041] Figure 3 It is a structural diagram of the first row of holes and other rows of holes in the refined construction method for large-area open-pit bench deep-hole blasting provided by the embodiment of the present invention;

[0042] Figure 4 It is a schematic block diagram of the refined construction device for large-area open-pit bench deep-hole blasting in the tunnel provided by the embodiment of the present invention;

[0043] Figure 5 It is a schematic block diagram of the computer device provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0045] It should be understood that when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0046] It should also be understood that the terms used in this specification of the present invention are merely for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in this specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0047] It should be further understood that the term " / and / " used in this specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0048] Please refer to Figure 1 , Figure 1 which is a schematic flow chart of the refined construction method for large-area open-pit bench deep-hole blasting provided by the embodiment of the present invention;

[0049] As Figure 1 shown, the method includes steps S101 to S107.

[0050] S101. Obtain multiple groups of blasting site data, where each group of the blasting site data includes site parameters and corresponding blasting parameters;

[0051] In this embodiment, the site parameters include drilling diameter, rock hardness, drilling proximity density coefficient, burden value, bench height, and the blasting parameters include hole depth and hole pattern parameters.

[0052] Specifically, during the actual engineering blasting process, the data of the blasting site are collected so that the following on-site parameters can be utilized: drilling diameter, rock hardness, drilling adjacent density coefficient, toe burden value, bench height, for calculating the following blasting parameters: hole depth, hole pattern parameters; and after comprehensively evaluating the fragment size distribution, loose coefficient, bottom residue rate, post-cracking distance, muck pile size, blasting vibration, flying rock distance, shock wave, and noise, the blasting effect is obtained, and the rationality of the blasting parameter design is verified through the real-time blasting effect.

[0053] It should be noted that the drilling diameter is determined by the drill rig model, the lithology of the rock at the site (on-site) is determined by the preliminary exploration, and the toe burden value is determined by the empirical formula; various parameters in the blasting parameters are calculated from different classical blasting theory formulas. It should be added that the lithology of the rock obtained from the preliminary exploration is rough and is the lithology of the entire site, while the hardness data obtained in step S106 of this application refers to the precise hardness data around the hole.

[0054] S102. Use all the above-mentioned blasting site data to train the pre-built blasting effect prediction model. Among them, the mean square error of the blasting effect prediction model is calculated according to the following formula:

[0055]

[0056] where, f Z represents the mean square error; q s represents the number of output units; e k represents the output value of the kth unit; j k represents the target value of the kth unit;

[0057] In this embodiment, the pre-built blasting effect prediction model is trained by using the blasting site data obtained in the above step S101. Among them, the blasting effect prediction model is established based on the BP neural network depth. Specifically, the blasting effect prediction model includes an input layer, a first hidden layer, a second hidden layer, and an output layer connected in sequence. Among them, the number of nodes in the input layer is determined by the number of sample attributes; the number of nodes in the output layer is the number of predicted nodes; the number of hidden layers is determined according to the recognition accuracy. Since the training samples are large, the required accuracy is high, and the number of hidden layers generally does not exceed 2 layers, so 2 hidden layers are selected.

[0058] During the deep learning training process of the neural network, there are x groups of on-site parameters and real blasting parameters respectively. Each real blasting parameter is combined with the corresponding on-site parameter. At the same time, the on-site parameter is used as the input vector to input the blasting effect prediction model, and the output vector is the training blasting parameter, forming a training sample set. That is, the following functional relationship is established between the five on-site parameters of drilling diameter, rock hardness, drilling adjacent density coefficient, toe burden value, and bench height and the blasting parameters:

[0059] Q f = f(M1, M2, M3, M4, M5)

[0060] where M1, M2, M3, M4, and M5 respectively represent the drilling diameter, rock hardness, adjacent hole density coefficient, burden value, and bench height; Q f represents the output value, i.e., the training blasting parameter, and f(M) represents an unknown function model.

[0061] It should be emphasized that the training blasting parameter is obtained by training the blasting effect prediction model, and the real blasting parameter is calculated in advance by the classical blasting theory formula. Moreover, the real blasting parameter is a range value, while the training blasting parameter is a value within the range of the real blasting parameter.

[0062] Input a set of acquired on-site parameter samples (hole diameter, rock lithology, adjacent hole density coefficient, burden value, bench height) into the corresponding input layer, and after passing through the first hidden layer, the second hidden layer, and the output layer in sequence, output the vector corresponding to the training blasting parameter of this set.

[0063] Calculate the mean square error between the output vector of the output layer (the vector corresponding to the training blasting parameter) and the target vector (the vector corresponding to the real blasting parameter) through the formula in step S102. When the mean square error meets the preset error performance index, the learning / training of the blasting effect prediction model is completed; when the mean square error does not meet the error performance index, modify the neural network weights of the blasting effect prediction model until the error converges to the standard.

[0064] S103. After the mean square error meets the preset error performance index, output the target blasting effect prediction model after training;

[0065] S104. Input the target on-site data into the target blasting effect prediction model and output the target blasting parameter;

[0066] During the actual engineering blasting process, acquire the on-site data of the blasting construction site, and then input it into the optimized target blasting effect prediction model to output the target blasting parameter. It should be noted that the predicted target blasting parameter is a further narrowed range within the range of the blasting parameter calculated by the empirical formula, which will be more accurate.

[0067] S105. After drilling operations are carried out based on the target blasting parameter, acquire the wear state data and drilling speed data of the drill bit;

[0068] In this embodiment, the intelligent drill rig (i.e., the machine required for the target row of holes, which can be an intelligent drill rig with an intelligent drill rig built-in system developed by the team of Academician Yan Taining) drills holes according to the obtained target blasting parameters. Specifically, the intelligent drill rig drills holes according to the predicted hole pattern parameters and hole depth. According to the rock fragmentation theory, the built-in system carried by the intelligent drill rig itself can collect the drilling speed data of the drill bit and obtain the wear state data of the drill bit. When the rock formation changes or there are fissures, the drilling speed data of the drill bit and the wear state data of the drill bit will also change accordingly, so as to understand the existence of rock formation changes or fissures.

[0069] It should be added that in the existing related technologies, the calculation formula for the wear state data of the drill bit is as follows:

[0070]

[0071] Among them, D represents the wear state of the drill bit, P represents the actual penetration rate, P' represents the theoretical penetration rate, s represents the corrected axial pressure, with the unit of kN, b represents the rotational speed of the drill bit of the drill rig, with the unit of r / min, and k represents the correlation coefficient.

[0072] However, according to the actual measurement at the blasting site, it is found that for every 10 m of penetration of the drill bit / drill pipe, the axial pressure will increase by Δs. That is to say, the axial pressure s is not constant. Therefore, the present application corrects the calculation formula for the wear state data of the drill bit as follows:

[0073]

[0074] Among them, D represents the wear state of the drill bit, P represents the actual penetration rate, P' represents the theoretical penetration rate, s represents the corrected axial pressure, with the unit of kN, b represents the rotational speed of the drill bit of the drill rig, with the unit of r / min, and k represents the correlation coefficient.

[0075] The calculated hardness data is closer to the actual hardness data through the corrected wear state data.

[0076] S106. Based on the wear state data and the drilling speed data, obtain the Proctor hardness coefficient of the rock at the drilling hole, and calculate the hardness data σ of the rock mass around the hole according to the following formula c :

[0077] σ c = 10 × f

[0078] Among them, f represents the Proctor hardness coefficient of the rock;

[0079] It should be noted that the Proctor hardness coefficient of the rock at the drilling hole is directly calculated by the built-in system of the intelligent drill rig, and the present application does not make specific descriptions. Among them, σ cIt represents the uniaxial compressive strength and is used to characterize the hardness of the rock.

[0080] In this embodiment, based on the drilling speed data and the wear state data of the drill bit, calculations are performed to obtain the hardness data of the rock mass around the hole. It should be noted that the rock hardness data includes: hard rock, relatively hard rock, relatively soft rock, soft rock, and extremely soft rock.

[0081] S107. Based on the hardness data of the rock mass around the hole, calculate the charge amount of the target blast holes according to the following formula:

[0082] E1 = eaW d H

[0083] E2 = KeabH

[0084] Among them, E1 represents the charge amount per single hole of the first row of blast holes, E2 represents the charge amount per single hole of the other rows of blast holes, e represents the specific consumption (the unit consumption of explosive when reaching loose blasting), K represents the correlation coefficient (the coefficient of the empirical formula, generally taking a value of 1.1 - 1.2), H represents the bench height, and W d represents the burden, a represents the hole spacing, and b represents the row spacing. Among them, as Figure 3 shown, the first row of blast holes is a row of holes close to the bench face, and the other rows of blast holes are holes far from the bench face.

[0085] In step S107 of this application, it should be noted that since the rock hardness data affects the specific consumption (the unit consumption of explosive when reaching loose blasting), specifically, the harder and more intact the rock mass is, the higher the specific consumption. Therefore, for the blast holes at different positions, the charge amounts of the blast holes are dynamically adjusted.

[0086] During the actual process of bench blasting, since the first row of blast holes is close to the bench face, the distance from the first row of blast holes to the bench face changes. Therefore, the first row of blast holes cannot be directly set in a fixed-spacing manner with the other rows of blast holes, so the charge amount needs to be calculated separately.

[0087] This application outputs more accurate target blasting parameters through the target blasting effect prediction model, enabling the intelligent drill rig to drill holes precisely, thereby obtaining the hardness data of the rock mass around the hole to dynamically adjust the charge amount and make the obtained charge amount more accurate.

[0088] The embodiment of the present invention also provides a tunnel large-area open-pit bench deep-hole blasting refinement construction device, and this tunnel large-area open-pit bench deep-hole blasting refinement construction device is used to execute any embodiment of the foregoing large-area open-pit bench deep-hole blasting refinement construction method. Specifically, please refer to Figure 4 , Figure 4 is a schematic block diagram of the tunnel large-area open-pit bench deep-hole blasting refinement construction device provided by the embodiment of the present invention.

[0089] As shown Figure 4 in the figure, the refined construction device 500 for large-area open-pit bench deep-hole blasting in tunnels includes:

[0090] An acquisition unit 501, configured to acquire multiple groups of blasting site data, where each group of the blasting site data includes site parameters and corresponding blasting parameters;

[0091] A training unit 502, configured to train a pre-built blasting effect prediction model by using all the blasting site data, where the mean square error of the blasting effect prediction model is calculated according to the following formula:

[0092]

[0093] where f Z represents the mean square error; q s represents the number of output units; e k represents the output value of the k-th unit; j k represents the target value of the k-th unit;

[0094] An output unit 503, configured to output the target blasting effect prediction model after the training ends when the mean square error meets a preset error performance index;

[0095] A target blasting parameter output unit 504, configured to input target site data into the target blasting effect prediction model and output target blasting parameters;

[0096] A drilling data acquisition unit 505, configured to acquire the wear state data and drilling speed data of the drill bit after drilling operations are performed based on the target blasting parameters;

[0097] A hardness data acquisition unit 506, configured to acquire the Proctor hardness coefficient of the rock at the drilling hole based on the wear state data and drilling speed data, and calculate the hardness data σ of the rock mass around the hole according to the following formula c :

[0098] σ c = 10×f

[0099] where f represents the Proctor hardness coefficient of the rock;

[0100] A calculation unit 507, configured to calculate the charge amount of the target row of holes according to the following formula based on the hardness data of the rock mass around the hole:

[0101] E1 = eaW d H

[0102] E2 = KeabH

[0103] Among them, E1 represents the charge amount per single hole of the first row of holes, E2 represents the charge amount per single hole of other rows of holes, e represents the specific charge, K represents the correlation coefficient, H represents the bench height, and W d represents the burden, a represents the hole spacing, and b represents the row spacing.

[0104] The device outputs more accurate target blasting parameters through the target blasting effect prediction model, enabling the intelligent drill rig to drill holes precisely, thereby obtaining the hardness data around the holes to dynamically adjust the charge amount and make the obtained charge amount more accurate.

[0105] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described device and unit can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0106] The above-mentioned tunnel large-area open-pit bench deep-hole blasting refined construction device can be implemented in the form of a computer program, and this computer program can run on a computer device as Figure 5 shown.

[0107] Please refer to Figure 5 , Figure 5 which is a schematic block diagram of the computer device provided by the embodiment of the present invention. The computer device 1100 is a server, and the server can be an independent server or a server cluster composed of multiple servers.

[0108] Referring to Figure 5 , the computer device 1100 includes a processor 1102, a memory, and a network interface 1105 connected through a system bus 1101. Among them, the memory can include a non-volatile storage medium 1103 and an internal memory 1104.

[0109] The non-volatile storage medium 1103 can store an operating system 11031 and a computer program 11032. When the computer program 11032 is executed, the processor 1102 can be enabled to execute the large-area open-pit bench deep-hole blasting refined construction method.

[0110] The processor 1102 is used to provide computing and control capabilities to support the operation of the entire computer device 1100.

[0111] The internal memory 1104 provides an environment for the operation of the computer program 11032 in the non-volatile storage medium 1103. When the computer program 11032 is executed by the processor 1102, the processor 1102 can be enabled to execute the large-area open-pit bench deep-hole blasting refined construction method.

[0112] The network interface 1105 is used for network communication, such as providing the transmission of data information, etc. Those skilled in the art can understand thatFigure 5 The structure shown is only a block diagram of some structures related to the solution of the present invention, and does not constitute a limitation on the computer device 1100 to which the solution of the present invention is applied. Specifically, the computer device 1100 may include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0113] Those skilled in the art can understand that Figure 5 the embodiments of the computer device shown do not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than those shown, or combine certain components, or have a different component arrangement. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structures and functions of the memory and the processor are the same as those in Figure 5 the embodiment shown and will not be described in detail herein.

[0114] It should be understood that in the embodiment of the present invention, the processor 1102 may be a central processing unit (CPU), and the processor 1102 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0115] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be a non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the refined construction method for large-area open-pit bench deep-hole blasting in the embodiment of the present invention is implemented.

[0116] The storage medium is a physical, non-transitory storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disc, etc., which are all physical storage media that can store program codes.

[0117] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the foregoing method embodiments and will not be described in detail herein.

[0118] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A refined construction method for large-area open-pit bench deep-hole blasting, characterized in that, Including: Obtain multiple groups of blasting site data, where each group of the blasting site data includes site parameters and corresponding blasting parameters; Use all the blasting site data to train a pre-built blasting effect prediction model, where the mean square error of the blasting effect prediction model is calculated according to the following formula: Among them, f z represents the mean square error; q s Indicates the number of output units; e k represents the output value of the kth unit; j k represents the target value of the kth unit; After the mean square error meets the preset error performance index, output the target blasting effect prediction model after training; Input the target site data into the target blasting effect prediction model and output the target blasting parameters; After drilling operations are carried out based on the target blasting parameters, obtain the wear state data and drilling speed data of the drill bit; Based on the wear state data and the drilling speed data, obtain the Proctor hardness coefficient of the rock at the borehole, and calculate the hardness data σ of the rock mass around the hole according to the following formula c : σ c = 10 × f Where f represents the rock Prandtl hardness coefficient; Based on the hardness data of the rock mass around the hole, calculate the charge amount of the target row of holes according to the following formula: E1 = eaW d H E2 = KeabH Among them, E1 represents the single-hole charge of the first row of holes, E2 represents the single-hole charge of other rows of holes, e represents the specific consumption, K represents the correlation coefficient, H represents the bench height, and W d represents the burden, a represents the hole spacing, and b represents the row spacing.

2. The refined construction method for large-area open-pit bench deep-hole blasting according to claim 1, characterized in that, The obtaining of the wear state data of the drill bit includes: Obtain the wear state data of the drill bit according to the following formula: Where D represents the wear state of the drill bit, P represents the actual penetration rate, P' represents the theoretical penetration rate, s represents the corrected axial pressure with the unit of kN, b represents the rotational speed of the drill bit of the drill rig with the unit of r / min, and k represents the relationship coefficient.

3. The refined construction method for large-area open-pit bench deep-hole blasting according to claim 1, characterized in that The blasting effect prediction model includes an input layer, a first hidden layer, a second hidden layer, and an output layer connected in sequence.

4. The refined construction method for large-area open-pit bench deep-hole blasting according to claim 1, characterized in that The hardness data of the rock mass around the hole includes: hard rock, relatively hard rock, relatively soft rock, soft rock, and extremely soft rock.

5. The refined construction method for large-area open-pit bench deep-hole blasting according to claim 4, characterized in that, The site parameters include the drilling diameter, rock hardness, drilling adjacent density coefficient, burden value, bench height, and the blasting parameters include the hole depth and hole pattern parameters.

6. A refined construction device for large-area open-pit bench deep-hole blasting in tunnels, characterized in that, Including: An acquisition unit for obtaining multiple groups of blasting site data, where each group of the blasting site data includes site parameters and corresponding blasting parameters; A training unit for using all the blasting site data to train a pre-built blasting effect prediction model, where the mean square error of the blasting effect prediction model is calculated according to the following formula: Among them, f Z represents the mean square error; q s represents the number of output units; e k represents the output value of the k-th unit; j k represents the target value of the k-th unit; An output unit for outputting the target blasting effect prediction model after training after the mean square error meets the preset error performance index; A target blasting parameter output unit for inputting the target site data into the target blasting effect prediction model and outputting the target blasting parameters; A drilling data acquisition unit for obtaining the wear state data and drilling speed data of the drill bit after drilling operations are carried out based on the target blasting parameters; The hardness data acquisition unit is used to obtain the Proctor hardness coefficient of the rock at the borehole based on the wear state data and the drilling speed data, and calculate the hardness data σ of the rock mass around the hole according to the following formula c : σ c = 10 × f Where f represents the rock Prandtl hardness coefficient; A calculation unit for calculating the charge amount of the target row of holes based on the hardness data of the rock mass around the hole according to the following formula: E1 = eaW d H E2 = KeabH Among them, E1 represents the charge per hole of the first row of holes, E2 represents the charge per hole of other rows of holes, e represents the specific consumption, K represents the correlation coefficient, H represents the bench height, and W d represents the burden, a represents the hole spacing, and b represents the row spacing.

7. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the large-area open-pit bench deep-hole blasting refined construction method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, it causes the processor to execute the large-area open-pit bench deep-hole blasting refined construction method according to any one of claims 1 to 5.

Images