WO2022240049A1 - Blasting management system for analysis of vibration and fragmentation caused by blasting - Google Patents

Abstract

A blasting management system for the analysis of vibration and fragmentation caused by blasting according to an embodiment of the present invention is characterized by comprising: a data learning unit for generating a result estimation formula by using machine learning to learn on the basis of vibration data and fragmentation data according to blasting conditions; a blasting design unit for generating a blasting design including at least one of perforation information, charging information, or initiation information; a result prediction unit for generating estimated data by inputting the blasting design into the result estimation formula; a data collection unit for collecting result data of blasting carried out according to the blasting design; and an analysis unit for comparing the result data and the estimated data and analyzing differences therebetween.

Description

Blasting management system for vibration and crushing analysis by blasting

An embodiment of the present invention is a blasting management system (BLASTING MANAGEMENT SYSTEM FOR ANALYSIS OF VIBRATION AND FRAGMENTATION CAUSED BY BLASTING) for analyzing vibration and fracture caused by blasting, in particular, open pit mining, or open pit D & B Service (Open Pit Drilling & Blasting Service) automatically collects and stores drilling and blasting design, work, and blasting results, and guides drilling and blasting design reflecting the characteristics of blasting sites (e.g., vibration and blasting) using machine learning. It relates to a blasting management system capable of providing a crushing degree estimation formula).

BACKGROUND OF THE INVENTION [0002] BACKGROUND OF THE INVENTION [0002] BACKGROUND OF THE INVENTION [0002] In general, a blasting system for exploding and collapsing using explosives is used in construction fields such as blasting of rocks, blasting of abandoned buildings, and blasting in open air.

Specifically, a region or object to be blasted is divided into a plurality of sections, and a plurality of blast holes into which explosives are inserted are drilled for each section. After charging explosives into each of the drilled blast holes, it is connected to the blasting device. By detonating the detonator located in the blast holes, the explosive is detonated and the blasting object is detonated and collapsed.

In a conventional blasting management system, when a blasting result is predicted according to a result of a drilling operation or charging operation, vibration or crushing due to blasting can be estimated using an estimation formula widely known in the art. However, since these existing estimation formulas contain fixed coefficients, they do not reflect the specifics of the site, and thus there is a problem in that the estimation results are not accurate and cause inefficiency of blasting.

In addition, in the case of blasting design, since the initial design could be maintained as it is or modified only by relying on the experience and intuition of field users, it was difficult to perform blasting efficiently because accurate modification based on data was impossible. In particular, in the case of blasting, once it is performed, it is difficult to reproduce and easily disappears unless data is saved, so there is a problem of relying on user experience.

[Blast vibration estimation formula]

Devine (1966) proposed Equation (1) based on the experimental observation results of the quarry.

Here, V is the maximum vibration speed (in / s), D is the distance (ft), and W represents the amount of action per delay (lbs). And, K and n are location constants determined by the ground conditions of each quarry.

According to Devine's observation, K was estimated to be 0.675 to 4.04, with an average of 1.85, and n to be 1.083 to 2.346, with an average of 1.536.

Equation (1) to which the average constant is applied is converted to cm/s as Equation (2) below.

Here, V is the maximum vibration speed (cm/s), D is the distance (m), and W is the amount of energy per delay (kg).

du Pont presented the following equation (3) in the blasting handbook. (converted to SI units)

Here, V is the maximum vibration speed (cm/s), D is the distance (m), and W is the amount of energy per delay (kg).

Dowding (1985) showed the degree of dispersion of blasting vibration according to the conversion distance using data from 40 boreholes, quarries, and construction blasting in the United States. Table 1. is the vibration estimation formula for each industry obtained by the square root conversion distance formula of the 95% confidence interval.

Blasting vibration estimation formula for each industry (95% confidence level)

industry	Estimation formula (cm/s)
all
surface mining
quarrying
erection

As shown in the theoretical background above, the existing blasting vibration estimation equation is organized as an empirical relational expression according to the influencing variables (D, W), and the estimation coefficients (K, n) at this time are very dependent on the nature of the site. Therefore, applying the existing formula to individual sites as it is has a problem in that its utilization is low and incorrect vibration values are predicted, which often causes vibration standards to be exceeded or inefficient blasting results. ]

The empirical formula has been steadily improved since it was presented by Kuznetsov (1973), and developed to Equation (4) presented by Cunningham (2005). The most popular crush estimation formula so far is as follows.

Here, A is the Blastability Index (Equation (5)),

is the correction coefficient for the parallax, K is the charge amount (PF), Q is the charge amount (kg), RWS is the relative power coefficient of the explosive, and C(A) is the correction coefficient for the Rock Factor (0.5 to 2.0) indicates

A = 0.06* (RMD+JF+RDI+HF) (5)

where RMD is the Rock Mass Description, JF is the sum of the Joint Plane Angle and Vertical Joint Spacing, RDI　 is the Rock Density Influence, and HF represents a hardness factor.

As described above, since the crushing degree estimation formula is a value that varies depending on site conditions rather than complex elements and individual coefficients are not fixed values, it is difficult to find an estimation formula tailored to the site without multiple test blasts accompanied by precise measurements. there was.

An object of the present invention is to automatically collect and store the design, operation, and blasting results of drilling and blasting, and use machine learning to guide drilling and blasting design reflecting the characteristics of the blasting site (eg, vibration and crushing degree estimation formula) It is to provide a blasting management system that can provide.

Another object of the present invention is a blasting management system that can database information on blasting operations such as drilling and charging, and information on vibration, noise and crushing corresponding to blasting results, and provide optimal blasting conditions suitable for the site. is to provide

Another object of the present invention is to provide a blasting management system capable of providing an optimal estimation equation considering the characteristics of a site by applying different weights according to characteristics of rocks to be blasted.

Another object of the present invention is to provide a blasting management system capable of providing an optimal estimation formula by adding a variable when an additional variable is required.

According to an embodiment of the present invention, a blasting management system for analyzing blasting vibration and crushing degree, using machine learning, learning based on vibration data and crushing data according to blasting conditions to generate a result estimation formula data learning unit; a blasting design unit for generating a blasting design including at least one of drilling information, charge information, and initial time information; a result prediction unit for generating estimation data by inputting the blasting design into the result estimation equation; a data collection unit for collecting result data according to blasting performed according to the blasting design; and an analyzer configured to analyze a difference by comparing the resulting data and the estimation data.

In the present invention, the result estimation formula includes a vibration estimation formula and a crushability estimation formula, the estimation data includes vibration estimation data and crushability estimation data, and the resultant data includes vibration result data and a crushability result. Characterized in that it contains data.

In the present invention, the data learning unit, a database for storing the vibration data and the crushing degree data; a first learning unit for learning a first correlation between a first blasting condition and the vibration data; a second learning unit for learning a second correlation between a second blasting condition and the crushing degree data; and an estimation equation generator for setting coefficients of the vibration estimation equation and the crushability estimation equation based on the first correlation and the second correlation.

In the present invention, the database stores the first blasting condition, the second blasting condition, the vibration result data and the crushing result data of the result data, the first learning unit and the second learning unit, Learning is performed based on the vibration result data and the crush degree result data, and the estimation formula generation unit resets the coefficients of the vibration estimation formula and the crush degree estimation formula.

In the present invention, the first blasting condition includes at least one of a maximum charge per charge, a distance to a vibration measuring device, a vibration value, an average blast transmission speed, and a rock coefficient, and the second blasting condition includes a charge amount and a charge amount. and a rock coefficient.

In the present invention, the estimation formula generating unit adds variables affecting vibration and crushability to the vibration estimation formula and the crushability estimation formula using a multiple linear regression model, and sets coefficients for the added variables. It is characterized by doing.

In the present invention, the first learning unit sets the maximum charge per charge, the distance to the vibration meter, the vibration value, the average blast transmission speed, and the rock coefficient as variables for the vibration estimation equation, and the estimation equation generation unit, respectively It is characterized in that the vibration estimation equation is generated by deriving coefficients for variables of .

In the present invention, the second learning unit sets the charge amount, the charge amount, and the rock coefficient as variables for the crushing degree estimation equation, and the estimation equation generation unit derives coefficients for each variable, thereby estimating the crushing degree It is characterized by generating an expression.

In the present invention, the blasting design unit is characterized in that the blasting design is performed for a new blasting site based on the analysis result of the analysis unit.

The blasting management system for analyzing vibration and crushing according to blasting of the present invention automatically collects and stores drilling and blasting design, operation, and blasting results, and uses machine learning to design drilling and blasting that reflects the characteristics of the blasting site. There is an effect of providing a guide (eg, vibration and crushability estimation formula).

In addition, the blasting management system for analyzing vibration and crushing according to blasting of the present invention databases information on blasting operations such as drilling and charging and information on vibration, noise and crushing corresponding to blasting results, and It has the effect of providing the optimal blasting conditions.

In addition, the blasting management system for analyzing vibration and crushability according to blasting according to the present invention has the effect of providing an optimal estimation formula considering the characteristics of the site by applying different weights according to the characteristics of the rock to be blasted. .

In addition, the blasting management system for analyzing vibration and crushing according to blasting according to the present invention has an effect of providing an optimal estimation equation by adding additional variables when additional variables are required.

1 is a diagram showing a blasting management system according to an embodiment of the present invention.

2 is a diagram showing a blasting management system according to an embodiment of the present invention.

3 is a diagram showing a data learning unit according to an embodiment of the present invention.

4 is a diagram illustrating the operation of a data learning unit according to an embodiment of the present invention.

The present invention is described in more detail.

Hereinafter, with reference to the accompanying drawings, embodiments of the present invention and other matters necessary for those skilled in the art to easily understand the contents of the present invention will be described in detail. However, since the present invention can be implemented in many different forms within the scope described in the claims, the embodiments described below are merely illustrative regardless of whether they are expressed or not.

Like reference numerals designate like components. Also, in the drawings, the thickness, ratio, and dimensions of components are exaggerated for effective description of technical content. “And/or” may include any combination of one or more that the associated elements may define.

Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. These terms are only used for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the present invention. Singular expressions may include plural expressions unless the context clearly dictates otherwise.

In addition, terms such as "below", "lower side", "above", and "upper side" are used to describe the relationship between components shown in the drawings. The above terms are relative concepts and will be described based on the directions shown in the drawings.

Terms such as "include" or "have" are intended to indicate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but that one or more other features, numbers, or steps are present. However, it should be understood that it does not preclude the possibility of existence or addition of operations, components, parts, or combinations thereof.

That is, the present invention is not limited to the embodiments disclosed below, but can be implemented in various different forms, and in the following description, when a part is connected to another part, it is directly connected. In addition, it may also include a case where the other element is electrically connected with another element interposed therebetween. In addition, it should be noted that the same reference numerals and symbols refer to the same components in the drawings, even if they are displayed on different drawings.

1 is a diagram showing a blasting management system 10 according to an embodiment of the present invention.

Referring to FIG. 1, the blasting management system 10 of the present invention is designed for a field where D & B Service (Open Pit Drilling & Blasting Service) is regularly performed in open-air mines, quarries, etc., 1) drilling and blasting design , work, and result information are automatically collected and stored, and 2) drilling and blasting design guides suitable for the user's purpose can be provided. In particular, the blasting management system 10 proposes a method for deriving an estimation formula based on regression model machine learning.

To this end, the blasting management system 10 may include a data learning unit 100, a blasting design unit 200, a result prediction unit 300, a data collection unit 400, and an analysis unit 500.

The data learning unit 100 may generate a result estimation equation by learning based on vibration data and crushing degree data according to blasting conditions using machine learning. Since vibration and noise have substantially the same or similar origins and estimation methods, they are described based on vibration data in this specification. However, the present invention is not limited thereto, and the data learning unit 100 may perform learning using noise data. In this case, the result estimation equation may include a vibration estimation equation for estimating vibration due to blasting and a crushing degree estimation equation for estimating the degree of crushing.

The blasting design unit 200 may generate a blasting design including at least one of drilling information, charge information, and initial time information. In addition, the blasting design unit 200 may proceed with blasting design for a new blasting site based on the analysis result of the analysis unit 500 .

The result prediction unit 300 may generate estimated data by inputting the blasting design into the result estimation equation. In this case, the estimated data may include vibration estimation data calculated according to the vibration estimation equation and crushability estimation data calculated according to the crushability estimation equation.

The data collection unit 400 may collect result data according to blasting conducted according to the blasting design. In this case, the result data may include vibration result data and crushing result data.

For example, the data collection unit 400 may also collect result data for newly performed blasting. For example, the data collection unit 400 may obtain result data from an external sensing device installed at a safe distance from a blasting site. However, the present invention is not limited thereto, and according to embodiments, the data collection unit 400 may directly generate result data.

The analysis unit 500 may analyze the difference by comparing result data and estimated data. For example, the analysis unit 500 compares the resultant data and the estimated data to calculate the difference, and the prediction and actual error of the blasting result according to a certain blasting condition is calculated in the vibration and crushing estimation equation considering the sensitivity of each blasting condition. can be analyzed to see if it has occurred.

The data learning unit 100 may modify the previously obtained blasting estimation equation using the newly obtained blasting results (vibration, degree of crushing). Through this, the blasting management system 10 according to the embodiment of the present invention derives the optimal blasting estimation formula suitable for the bedrock or geological characteristics of the site as the conditions and result data for the additionally performed blasting are added thereafter. can do.

2 is a diagram showing a blasting management system 10 according to an embodiment of the present invention.

Referring to FIG. 2 , the blasting management system 10 may communicate with the sensing device SD for detecting the blasting area BA. Depending on the embodiment, the blasting management system 10 may perform communication with the detection device SD through a wireless or wired network.

For example, the blasting management system 10 may include a wireless communication network module such as a mobile communication network, a Wi-Fi communication network, a long range communication network, and a Bluetooth communication network. However, the present invention is not limited thereto, and within the scope of achieving the object of the present invention, the blasting management system 10 may include various communication modules.

When blasting is performed on the first sector ST1, the sensing device SD detects the result of blasting on the first sector ST1.

The sensing device (SD) transmits result data indicating the detected blasting result to the blasting management system 10, and the blasting management system 10 can proceed with blasting design and update the learning model based on the resultant data. have.

That is, when the vibration estimation equation and the crushing degree estimation equation suitable for the second sector ST2 are derived through the blasting of the first sector ST1, the blasting management system 10 based on this is derived. Blasting design can be implemented.

The blasting management system 10 may finely adjust blasting conditions so that the result is below the target degree of crushing and below the target vibration value. At this time, the blasting management system 10 may predict the result of blasting using an estimation formula before actual blasting is performed.

3 is a diagram showing the data learning unit 100 according to an embodiment of the present invention.

* Referring to FIGS. 1 to 3 , the data learning unit 100 may include a database 110, a first learning unit 120, a second learning unit 130, and an estimation equation generating unit 140. .

The database 110 may store vibration data and crushability data. In addition, the database 110 may store the first blasting condition and the second blasting condition.

The first learning unit 120 may learn a first correlation between a first blasting condition and vibration data. In this case, the first blasting condition may include at least one of the amount of blast per minute, the distance to the vibration measuring device, the vibration measurement value, the average blasting transmission speed, and the rock coefficient.

For example, the first learning unit 120, through learning about the first correlation, sets the maximum charge per charge, the distance to the vibration meter, the vibration value, the average blast propagation speed, and the rock coefficient as variables for the vibration estimation equation. can be set

The second learning unit 130 may learn a second correlation between the second blasting condition and the crushing degree data. In this case, the second blasting condition may include at least one of a charge amount, a charge amount, and a rock coefficient.

For example, the second learning unit 130 may set the charge amount, the charge amount, and the rock coefficient as variables for the crushing degree estimation equation through learning of the second correlation.

The estimation equation generation unit 140 may set coefficients of the vibration estimation equation and the fracture degree estimation equation based on the first correlation and the second correlation. That is, the estimation equation generation unit 140 may generate the vibration estimation equation and the fracture degree estimation equation by deriving coefficients for each variable. In addition, the estimation formula generating unit 140 adds additional variables affecting vibration and crushability to the vibration estimation formula and the crushability estimation formula using a multilinear regression model, and sets coefficients for the additional variables. can Details related to this are described below.

[Multiple Linear Regression Model]

Regression analysis is a statistical analysis method that assumes a mathematical model to investigate the functional relationship between variables and estimates this model from the data of measured variables. Among several regression lines, an expression that minimizes the residual is selected. It may mean a method of doing, for example, a method of least squares.

At this time, the regression line does not actually mean a linear expression, which is a linear expression, but means that variables and coefficients are formed by a linear combination, and may be a two-dimensional or more curved expression in the form of polynomial regression.

The multilinear regression model aims to create a regression model for predicting a dependent variable (y) with several independent variables (x).

At this time, it is possible to first create a regression equation with several independent variables and leave only significant variables through the variable selection method. It is possible to improve the predictive performance of the blasting management system 10 according to an embodiment of the present invention by selecting a significant variable from the predictive model through variable selection and removing an error or unnecessary variable.

Depending on the embodiment, a forward selection method, a backward elimination method, a stepwise selection method, or the like may be used as a variable selection method.

The blasting management system 10 may select the best model represented by the AIC by calculating and comparing AIC (Akaike's Information Criterion) values at the time of variable selection.

Meanwhile, the data learning unit 100 may update a learning model based on result data according to blasting results.

Specifically, the database 110 may store vibration result data and crushing result data of result data.

The first learning unit 120 and the second learning unit 130 may perform learning based on the vibration result data and the crushing result data.

And, the estimation formula generation unit 140 may reset the coefficients of the vibration estimation formula and the crushing degree estimation formula.

4 is a diagram illustrating the operation of the data learning unit 100 according to an embodiment of the present invention.

Referring to FIGS. 1 to 4 , the database 110 may store data related to blasting conditions and blasting results. According to embodiments, the database 110 may be implemented as a cloud storage device.

At this time, data such as blasting design and blasting work results, that is, blasting condition data, may be automatically stored in the database 110.

In this specification, the blasting condition data may refer to comprehensive data including drilling/charging/blasting (initial time) design data and result data of drilling/charging operations. However, the present invention is not limited thereto, and blasting condition data may be interpreted in various ways within the scope of achieving the object of the present invention.

In addition, blasting result data may also be automatically stored in the database 110 .

In this specification, the blasting result data may refer to comprehensive data including blasting vibration, noise, and degree of crushing. However, the present invention is not limited thereto, and blasting result data may be interpreted in various ways within the scope of achieving the object of the present invention.

Specifically, the degree of blasting and crushing may be stored as an analysis result through a degree of crushing analysis program, and vibration data or noise data may be stored as data sensed from a sensing device installed in the field.

Accordingly, the database 110 may be configured to store all of the blasting conditions and blasting result data for one blasting.

The first learning unit 120 and the second learning unit 130 automatically determine data characteristics using a Recurrent Neural Network (RNN) that generates a machine learning-based classification model to derive a vibration estimation equation and a crushing degree estimation equation. can be analyzed. For example, the first learning unit 120 and the second learning unit 130 analyze data characteristics using RNN and perform signal classification and pattern recognition to determine the relationship between blasting conditions and results. Correlation analysis can be performed, parameters of the estimation formula can be selected among the blasting conditions, and coefficients can be calculated. However, the present invention is not limited thereto, and according to embodiments, the data learning unit 100 of the present invention may perform learning and analysis in various ways.

The data learning unit 100 may derive a vibration estimation equation and a crushing degree estimation equation.

*The set of drilling/charge/blasting (first time) design data and result data of drilling/charge corresponding to the blasting conditions may be factors that have a complex effect on the occurrence of vibration, noise and crushing corresponding to the result of blasting. .

Therefore, it is possible to analyze changes in vibration, noise, and degree of crushing, which are results of blasting, according to changes in blasting condition data corresponding to the input data.

Several studies have suggested formulas for estimating the degree of crushing and blasting vibration/noise of blasting stones, but given the nature of the blasting target being a rock with strong individuality, the constants of the estimation formula can vary over a wide range depending on the bedrock or geological condition of each site. can

The data learning unit 100 of the blasting management system 10 of the present invention may derive a vibration estimation equation and a crushing degree estimation equation in which field characteristics are reflected based on the vibration data and the crushing degree data.

According to the embodiment, the data learning unit 100 analyzes the blasting condition data and the blasting result data built through 10 or more blasts, and the variables and coefficients for the variables of the vibration estimation equation and the crushing degree estimation equation in which the field characteristics are reflected can be set.

At this time, the estimation formula follows a multiple linear regression model through machine learning (machine learning), and the blasting management system 10 of the present invention can perform statistical analysis through a data analysis tool provided through a web service.

First, the first learning unit 120 of the data learning unit 100 may set variables in order to calculate a vibration estimation equation. For example, the first learning unit 120 sets the maximum amount of delay per shot (W), the distance to the vibration meter (D), and the vibration value (V) as variables, and additionally, blasting conditions that may affect vibration generation. Phosphorus average blast delivery speed (Relief Value), rock factor (Rock Factor), etc. can be set as variables of the estimation equation. In addition, the estimation equation generation unit 140 of the data learning unit 100 may find coefficients suitable for deriving the blast vibration estimation equation through a multilinear regression model. Through this, the data learning unit 100 of the present invention can add variables that have not been considered in the conventional estimation method, and can improve estimation accuracy by calculating a more suitable vibration estimation equation.

The second learning unit 130 may set variables in order to calculate the crushing degree estimation formula. For example, the second learning unit 130 may set the charge amount, the charge amount, the rock coefficient, and the like as variables, and additionally set blasting conditions that may affect the occurrence of crushing as variables of the estimation equation. In addition, the estimation formula generating unit 140 of the data learning unit 100 may find coefficients suitable for deriving the blast crushing estimation formula through a multilinear regression model. Through this, the data learning unit 100 of the present invention can add variables that have not been considered in the conventional estimation method, and can improve estimation accuracy by calculating a more suitable vibration estimation equation.

At this time, the first learning unit 120 and the second learning unit 130 may find additional condition variables and analyze correlation and sensitivity through statistical analysis of vibration and crushing corresponding to blasting results.

For example, blasting conditions may include geological information, explosive type information, and the like. Geological information includes rock type, rock specific gravity, uniaxial compressive strength, Young's modulus (or elastic modulus), Poisson's ratio, rock factor, dip angle/direction, and It may include at least one of tensile strength. The rock factor is a factor consisting of at least one of Rock Mass, Vertical Joint Spacing, Joint Plan Angle, Rock Density Influence, and Hardness Factor. it means.

Explosive information includes the type of detonator (e.g., bulk, cartridge, detonator, booster, etc.), explosive energy, relative weight strength (RWS), specific gravity, and relative volume. It may include at least one of relative bulk strength (RBS) width, accuracy, length and size of each line.

Through the above-described method, the blasting management system for analyzing vibration and crushing according to blasting of the present invention automatically collects and stores the design, operation, and blasting results of drilling and blasting, and uses machine learning to determine the characteristics of the blasting site. There is an effect that can provide a guide (eg, vibration and crushing degree estimation formula) of the reflected drilling and blasting design.

In addition, the blasting management system for analyzing vibration and crushing according to blasting of the present invention databases information on blasting operations such as drilling and charging and information on vibration, noise and crushing corresponding to blasting results, and It has the effect of providing the optimal blasting conditions.

In addition, the blasting management system for analyzing vibration and crushability according to blasting according to the present invention has the effect of providing an optimal estimation formula considering the characteristics of the site by applying different weights according to the characteristics of the rock to be blasted. .

In addition, the blasting management system for analyzing vibration and crushing according to blasting according to the present invention has an effect of providing an optimal estimation equation by adding additional variables when additional variables are required.

The functional operations described in this specification and the embodiments related to the present subject matter are implemented in digital electronic circuits, computer software, firmware, or hardware, or in a combination of one or more of them, including the structures disclosed in this specification and their structural equivalents. It is possible.

Embodiments of the subject matter described herein relate to one or more computer program products, that is, one or more computer program instructions encoded on a tangible program medium for execution by or controlling the operation of a data processing device. It can be implemented as a module. A tangible program medium may be a propagated signal or a computer readable medium. A propagated signal is an artificially generated signal, eg a machine generated electrical, optical or electromagnetic signal, generated to encode information for transmission by a computer to an appropriate receiver device. The computer readable medium may be a machine readable storage device, a machine readable storage substrate, a memory device, a combination of materials that affect a machine readable propagating signal, or a combination of one or more of these.

A computer program (also known as a program, software, software application, script, or code) may be written in any form of programming language, including compiled or interpreted language or a priori or procedural language, and may be a stand-alone program or module; It may be deployed in any form, including components, subroutines, or other units suitable for use in a computer environment.

A computer program does not necessarily correspond to a file on a file device. A program may be contained within a single file provided to the requested program, or within multiple interacting files (e.g., one or more of which stores a module, subprogram, or piece of code), or within a file holding other programs or data. may be stored within a part (eg, one or more scripts stored within a markup language document).

A computer program may be deployed to be executed on a single computer or multiple computers located at one site or distributed across multiple sites and interconnected by a communication network.

Additionally, the logic flow and structural block diagrams described in this patent document describe corresponding actions and/or specific methods supported by corresponding functions and steps supported by the disclosed structural means. It can also be used to build software structures and algorithms and their equivalents.

The processes and logic flows described herein can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output.

Processors suitable for the execution of computer programs include, for example, both general and special purpose microprocessors and any one or more processors of any type of digital computer. Generally, a processor will receive instructions and data from either read-only memory or random access memory or both.

The core elements of a computer are one or more memory devices for storing instructions and data and a processor for executing instructions. Also, a computer is generally operable to receive data from or transfer data to one or more mass storage devices for storing data, such as magnetic, magneto-optical disks or optical disks, or to perform both such operations. combined with or will include them. However, a computer need not have such a device.

The present description presents the best mode of the invention and provides examples to illustrate the invention and to enable those skilled in the art to make and use the invention. The specification thus prepared does not limit the invention to the specific terms presented.

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art or those having ordinary knowledge in the art do not deviate from the spirit and technical scope of the present invention described in the claims to be described later. It will be understood that the present invention can be variously modified and changed within the scope not specified.

Therefore, the technical scope of the present invention is not limited to the contents described in the detailed description of the specification, but should be defined by the claims.

Claims (9)

1. Using machine learning, a data learning unit for generating a result estimation equation by learning based on vibration data and crushing degree data according to blasting conditions;

   a blasting design unit for generating a blasting design including at least one of drilling information, charge information, and initial time information;

   a result prediction unit for generating estimation data by inputting the blasting design into the result estimation equation;

   a data collection unit for collecting result data according to blasting performed according to the blasting design; and

   Characterized in that it comprises an analysis unit for analyzing the difference by comparing the result data and the estimated data,

   Blasting management system.
2. According to claim 1,

   The result estimation equation includes a vibration estimation equation and a crushing degree estimation equation,

   The estimation data includes vibration estimation data and crushability estimation data,

   Characterized in that the result data includes vibration result data and crushing result data,

   Blasting management system.
3. According to claim 2,

   The data learning unit,

   a database for storing the vibration data and the crushability data;

   a first learning unit for learning a first correlation between a first blasting condition and the vibration data;

   a second learning unit for learning a second correlation between a second blasting condition and the crushing degree data; and

   Characterized in that, based on the first correlation and the second correlation, an estimation equation generator for setting coefficients of the vibration estimation equation and the crushability estimation equation,

   Blasting management system.
4. According to claim 3,

   The database stores the first blasting condition, the second blasting condition, the vibration result data and the crushing result data of the result data,

   The first learning unit and the second learning unit proceed with learning based on the vibration result data and the crushing result data,

   Characterized in that the estimation equation generation unit resets the coefficients of the vibration estimation equation and the crushability estimation equation,

   Blasting management system.
5. According to claim 4,

   The first blasting condition includes at least one of a maximum delay per charge, a distance to a vibration measuring device, a vibration value, an average blasting transmission speed, and a rock coefficient;

   Characterized in that the second blasting condition includes at least one of a charge amount, a specific charge amount, and a rock coefficient,

   Blasting management system.
6. According to claim 5,

   The estimation formula generation unit adds variables affecting vibration and crushability to the vibration estimation formula and the crushability estimation formula using a multilinear regression model, and sets coefficients for the added variables. doing,

   Blasting management system.
7. According to claim 6,

   The first learning unit sets the maximum delay per charge, the distance to the vibration meter, the vibration value, the average blast transmission speed, and the rock coefficient as variables for the vibration estimation equation,

   Characterized in that the estimation equation generation unit generates the vibration estimation equation by deriving coefficients for each variable,

   Blasting management system.
8. According to claim 6,

   The second learning unit sets the charge amount, the specific charge amount, and the rock coefficient as variables for the crushing degree estimation equation,

   Characterized in that the estimation equation generation unit generates the crushability estimation equation by deriving coefficients for each variable,

   Blasting management system.
9. According to claim 1,

   Characterized in that the blasting design unit proceeds with blasting design for a new blasting site based on the analysis result of the analysis unit.

   Blasting management system.

Images