System for evaluating influence of blasting engineering on electric power facilities based on machine learning

Abstract

The invention relates to a system for evaluating the influence of blasting engineering on electric power facilities based on machine learning, and belongs to the technical field of information systems. The evaluation system comprises an acquisition unit, a modeling unit and an analysis unit. The acquisition unit is used for acquiring vibration and crushing data of a blasting site and a plurality of detection points around the blasting site in the blasting process and after blasting; the modeling unit establishes a vibration evaluation model and a breakage evaluation model through a machine learning algorithm, and stores the models in a database; and the analysis unit evaluates the influence on the electric power facility under different blasting conditions by utilizing the models and combining the anti-seismic capacity of the electric power facility. The evaluation system determines the weight coefficient of the key parameter through multiple linear regression analysis so as to optimize the accuracy of the model, and can be widely applied to engineering projects needing to consider the influence of blasting on far-end key facilities.

Description

Technical Field

[0001] The present invention belongs to the field of digital information technology, and in particular, relates to a system for evaluating the impact of blasting engineering on power facilities based on machine learning. Background Art

[0002] With the development of modern engineering projects, blasting technology has been widely used in mining, building demolition and infrastructure construction. However, the impact of vibrations generated during blasting on the surrounding environment, especially on key infrastructure such as power facilities, has become an important safety issue. Traditional blasting impact assessment methods mainly rely on empirical formulas and fixed coefficients, which are difficult to accurately reflect the complex situations under different site conditions, resulting in greater uncertainty in the assessment results and may even cause unnecessary safety hazards.

[0003] In recent years, with the advancement of artificial intelligence and machine learning technologies, data-driven prediction models have gradually been applied to the engineering field. These models can automatically adjust and optimize evaluation parameters by learning and training a large amount of historical data, significantly improving the accuracy and reliability of predictions. Therefore, how to apply machine learning technology to the impact assessment of blasting engineering, especially when assessing the impact of blasting on power facilities, has become a research hotspot in the current engineering technology field.

[0004] According to relevant public technologies, the blasting control system with publication number US20200003919A1 analyzes the site phenomena before and after blasting, quantifies the actual destructive force of the blasting and establishes a prediction model to guide the precise implementation of blasting; the technical solution with announcement number CN110910613B proposes a rock microseismic wireless monitoring and early warning system, which realizes instant blasting vibration analysis by establishing real-time communication between satellites and multiple sensors installed in the rock mass; the technical solution with publication number CN109813617A proposes an experimental method for quantitative analysis of rock blasting. By analyzing the images of multiple scans of the specimen, it can perform microscopic analysis of the details in the blasting process.

[0005] The above technical solutions all propose several methods or systems for analyzing the impact of blasting process and blasting parameters, but the proposed analysis methods all require a large amount of data processing, and no technical solution for analyzing the impact of blasting engineering on power equipment is proposed.

[0006] The foregoing discussion of the background art is intended only to facilitate an understanding of the present invention. This discussion does not acknowledge or admit that any of the material referred to is part of the common general knowledge. Summary of the invention

[0007] The purpose of the present invention is to provide a system for evaluating the impact of blasting engineering on power facilities based on machine learning, which belongs to the field of information system technology; the evaluation system includes a collection unit, a modeling unit and an analysis unit; the collection unit is used to collect vibration and fragmentation data of multiple detection points in and around the blasting site during and after the blasting; the modeling unit uses a machine learning algorithm to establish a vibration evaluation model and a fragmentation evaluation model, and stores them in a database; the analysis unit uses these models, combined with the seismic resistance of the power facilities, to evaluate the impact on the power facilities under different blasting conditions. The evaluation system determines the weight coefficients of key parameters through multiple linear regression analysis to optimize the accuracy of the model, and can be widely used in engineering projects that need to consider the impact of blasting on remote key facilities.

[0008] The present invention adopts the following technical solution: a system for evaluating the impact of blasting engineering on power facilities based on machine learning, the evaluation system comprising:

[0009] A collection unit is configured to collect a plurality of detection data from a blasting site and a plurality of detection points in the surrounding area during the blasting process and after the blasting is completed;

[0010] A modeling unit is configured to perform machine learning based on multiple sets of detection data by using a machine learning algorithm to train and establish one or more impact assessment models;

[0011] An analysis unit configured to use the impact assessment model and the earthquake resistance of the power facilities to assess the impact of blasting at a designated blasting condition and a designated location on the power facilities;

[0012] Wherein, the modeling unit includes a modeling subunit A, a modeling subunit B and a database;

[0013] The modeling subunit A is configured to establish a vibration assessment model based on the correlation between the vibration blasting conditions and the vibration data;

[0014] The modeling subunit B is configured to establish a fragmentation assessment model based on the correlation between the fragmentation blasting conditions and the fragmentation data;

[0015] The database is configured to store modeling data required by the modeling unit, including multiple sets of vibration blasting conditions and corresponding vibration data, and multiple sets of fragmentation blasting conditions and corresponding fragmentation data;

[0016] The impact assessment model is to combine the parameters fitted by the vibration assessment model and the crushing assessment model of each detection point to predict the impact on the detection point after blasting is carried out under specified blasting conditions and at a specified location;

[0017] Preferably, the vibration blasting conditions include at least: the vibration value of the detection point, the single maximum explosive dosage in continuous blasting, the distance between the blasting point and the detection point, and the site constant;

[0018] Preferably, the fragmentation blasting conditions include at least: the total amount of explosives, the specific charge amount, the rock factor, the relative energy intensity of the explosives, and the ratio of the median size of the blasting fragments;

[0019] Preferably, the acquisition unit includes a plurality of sensors, including at least a plurality of remote sensors disposed at detection points around the power facility to be evaluated;

[0020] Preferably, the sensor in the acquisition unit at least includes: an acceleration sensor; the acceleration sensor includes a sensor for collecting vibration peak acceleration data of the detection object at the detection point in three-dimensional directions; the vibration peak acceleration data includes: horizontal tangential vibration peak acceleration, horizontal radial vibration peak acceleration, and vertical vibration peak acceleration;

[0021] Preferably, the A modeling subunit and the B modeling subunit establish the correlation model between the vibration blasting condition and the vibration data, and the fragmentation blasting condition and the fragmentation data by using multiple linear regression analysis;

[0022] Preferably, the modeling unit establishes a corresponding, independent vibration assessment model and a crushing assessment model for the location of each detection point;

[0023] The modeling subunit A includes selecting one or more parameters in the vibration blasting conditions as variables of the vibration assessment model after analyzing the correlation between the vibration blasting conditions and the vibration data, and setting weight coefficients for each variable in the vibration assessment model to establish a final vibration assessment model;

[0024] The modeling subunit B includes selecting one or more parameters in the crushing blasting conditions as variables of the crushing assessment model after analyzing the correlation between the crushing blasting conditions and the crushing data, and setting weight coefficients for each variable in the crushing assessment model to establish a final crushing assessment model;

[0025] Furthermore, a method for evaluating the impact of blasting engineering on power facilities based on machine learning is proposed, and the evaluation method is applied to the evaluation system; the evaluation method comprises the following steps:

[0026] S100: setting a plurality of detection points, and arranging sensors at the blasting point and the plurality of detection points to obtain values ​​of a plurality of blasting conditions;

[0027] S200: Based on a plurality of blasting conditions that are known or can be determined in advance through experiments, initial values ​​of a plurality of parameters of a vibration assessment model and a crushing assessment model are set, including setting initial values ​​of a plurality of empirical parameters;

[0028] S300: Conduct multiple groups of blasting tests, collect vibration values ​​at multiple test points, and determine the median size of blasting fragments;

[0029] S400: updating weight values ​​of multiple parameters in the vibration assessment model and the crushing assessment model, including updating the values ​​of the empirical parameters;

[0030] S500: Using a corresponding impact assessment model according to the location of the power facility and combining the seismic resistance of the power facility, assess the impact of blasting on the power facility under designated blasting conditions and at a designated location.

[0031] The beneficial effects achieved by the present invention are:

[0032] 1. The evaluation system of this technical solution can dynamically adjust and optimize model parameters based on multiple sets of collected vibration and crushing data by introducing machine learning algorithms. Compared with traditional empirical formulas, machine learning models can more accurately reflect actual site conditions, thereby providing a more reliable assessment of the impact of blasting on power facilities.

[0033] 2. The evaluation system of this technical solution can collect and analyze data at multiple detection points at the same time, comprehensively considering the vibration and crushing effects at different locations; this multi-point monitoring and analysis capability enables the system to comprehensively evaluate the impact of blasting on the entire area surrounding the power facility, ensuring the comprehensiveness and accuracy of the evaluation;

[0034] 3. The evaluation system of this technical solution can automatically update and optimize the evaluation model through multiple linear regression and other data-driven methods to adapt to different blasting conditions and geological characteristics;

[0035] 4. The software and hardware parts of the evaluation system of this technical solution adopt a modular design. The various working modules and components of the hardware part of the system, as well as the instructions, parameters, and algorithms of the software part can be conveniently replaced and / or upgraded later, thereby reducing the construction cost and maintenance cost of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0037] Description of the accompanying drawings: 11-detection point; 111-remote sensor; 12-blasting point; 112-proximal sensor; 20-receiving end; 100-server; 110-acquisition unit; 120-modeling unit; 130-analysis unit; 121-database; 122-modeling subunit A; 124-modeling subunit B; 132-vibration assessment model; 134-crushing assessment model 500-computing architecture; 502-bus; 504-processor; 506-main memory; 508-read-only memory; 510-storage device; 512-display; 514-input device; 516-cursor control device; 518-network device;

[0038] Figure 1 A schematic diagram of the architecture of the evaluation system according to an embodiment of the present invention;

[0039] Figure 2 is a schematic diagram of the arrangement of the evaluation system described in an embodiment of the present invention;

[0040] Figure 3 is a schematic diagram of the architecture of the modeling unit described in an embodiment of the present invention;

[0041] Figure 4 Schematic diagram of three-axis vibration peak acceleration in an embodiment of the present invention;

[0042] Figure 5 Schematic diagram of the framework of the computer system used in the embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with its embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. For those skilled in the art, after reviewing the following detailed description, other systems, methods and / or features of the present embodiment will become apparent. It is intended that all such additional systems, methods, features and advantages are included in this specification. Included within the scope of the present invention and protected by the appended claims. Additional features of the disclosed embodiments are described in the following detailed description, and these features will be apparent from the following detailed description.

[0044] The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there are terms such as "upper", "lower", "left", "right" and the like indicating the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, it is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or component referred to must have a specific orientation. The invention is constructed and operated in a specific orientation, so the terms describing the positional relationship in the drawings are only used for exemplary description and cannot be understood as a limitation of this patent. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to the specific circumstances.

[0045] Embodiment 1: For example, as shown in the attached Figure 1 As shown, a system for evaluating the impact of blasting engineering on power facilities based on machine learning is proposed, and the evaluation system includes:

[0046] The collection unit 110 is configured to collect a plurality of detection data from a blasting site and a plurality of detection points in the surrounding area during the blasting process and after the blasting is completed;

[0047] The modeling unit 120 is configured to perform machine learning based on multiple sets of detection data by using a machine learning algorithm, train and establish one or more impact assessment models;

[0048] The analysis unit 130 is configured to use the impact assessment model and the earthquake resistance of the power facility to assess the impact of the blasting at the designated blasting conditions and the designated location on the power facility;

[0049] Wherein, the modeling unit includes a modeling subunit A, a modeling subunit B and a database;

[0050] The modeling subunit A is configured to establish a vibration assessment model based on the correlation between the vibration blasting conditions and the vibration data;

[0051] The modeling subunit B is configured to establish a fragmentation assessment model based on the correlation between the fragmentation blasting conditions and the fragmentation data;

[0052] The database is configured to store modeling data required by the modeling unit, including multiple sets of vibration blasting conditions and corresponding vibration data, and multiple sets of fragmentation blasting conditions and corresponding fragmentation data;

[0053] The impact assessment model combines the parameters fitted by the vibration assessment model and the crushing assessment model of each detection point to predict the impact on the detection point after blasting is carried out under designated blasting conditions and at a designated location;

[0054] Preferably, the vibration blasting conditions include at least: the vibration value of the detection point, the single maximum explosive dosage in continuous blasting, the distance between the blasting point and the detection point, and the site constant;

[0055] Preferably, the fragmentation blasting conditions include at least: the total amount of explosives, the specific charge amount, the rock factor, the relative energy intensity of the explosives, and the ratio of the median size of the blasting fragments;

[0056] Preferably, the acquisition unit includes a plurality of sensors, including at least a plurality of remote sensors disposed at detection points around the power facility to be evaluated;

[0057] Preferably, the sensor in the acquisition unit at least includes: an acceleration sensor; the acceleration sensor includes a sensor for collecting vibration peak acceleration data of the detection object at the detection point in three-dimensional directions; the vibration peak acceleration data includes: horizontal tangential vibration peak acceleration, horizontal radial vibration peak acceleration, and vertical vibration peak acceleration;

[0058] Preferably, the A modeling subunit and the B modeling subunit establish the correlation model between the vibration blasting condition and the vibration data, and the fragmentation blasting condition and the fragmentation data by using multiple linear regression analysis;

[0059] Preferably, the modeling unit establishes a corresponding, independent vibration assessment model and a crushing assessment model for the location of each detection point;

[0060] The modeling subunit A includes selecting one or more parameters in the vibration blasting conditions as variables of the vibration assessment model after analyzing the correlation between the vibration blasting conditions and the vibration data, and setting weight coefficients for each variable in the vibration assessment model to establish a final vibration assessment model;

[0061] The modeling subunit B includes selecting one or more parameters in the crushing blasting conditions as variables of the crushing assessment model after analyzing the correlation between the crushing blasting conditions and the crushing data, and setting weight coefficients for each variable in the crushing assessment model to establish a final crushing assessment model;

[0062] Furthermore, a method for evaluating the impact of blasting engineering on power facilities based on machine learning is proposed, and the evaluation method is applied to the evaluation system; the evaluation method comprises the following steps:

[0063] S100: setting a plurality of detection points, and arranging sensors at the blasting point and the plurality of detection points to obtain values ​​of a plurality of blasting conditions;

[0064] S200: Based on a plurality of blasting conditions that are known or can be determined in advance through experiments, initial values ​​of a plurality of parameters of a vibration assessment model and a crushing assessment model are set, including setting initial values ​​of a plurality of empirical parameters;

[0065] S300: Conduct multiple groups of blasting tests, collect vibration values ​​at multiple test points, and determine the median size of blasting fragments;

[0066] S400: updating weight values ​​of multiple parameters in the vibration assessment model and the crushing assessment model, including updating the values ​​of the empirical parameters;

[0067] S500: using a corresponding impact assessment model according to the location of the power facility and combining the seismic resistance of the power facility, assessing the impact of blasting at a designated blasting condition and location on the power facility;

[0068] More specifically, as attached Figure 2 , which is a schematic diagram showing an exemplary evaluation system constructed according to the present technical solution;

[0069] The server 100 is configured as a computer system, and the computer system is provided with a software and hardware environment that meets the computing requirements of the modeling unit 120 and the analysis unit 130;

[0070] The server 100 can be connected to the receiving end 20 in communication; the receiving end 20 is connected to the remote sensor 111 disposed at the detection point 11 in communication; and the receiving end 20 is also connected to the near-end sensor 112 disposed at the blasting point 12 in communication; in an exemplary embodiment, the communication between the server 100 and the receiving end 20, and between the receiving end 20 and the plurality of sensors can be based on a wireless or wired network connection mode for data transmission;

[0071] Exemplarily, the server 100 may include a wireless communication network module for a network, such as a mobile communication network, a Wi-Fi communication network, a telecommunication network, and a Bluetooth communication network; however, the present disclosure is not limited thereto, and within the scope of achieving the purpose of the present disclosure, the server 100 may include various communication modules;

[0072] When blasting is performed, the remote sensor 111 and the near sensor 112 will collect real-time data and transmit it to the receiving end 20 in real time; the receiving end 20 will further transmit the sensing data to the server 100, and based on the sensing data, the server 100 can perform blasting design and update the learning model;

[0073] The technicians can finely adjust the blasting conditions and perform blasting to obtain a result slightly smaller than or equal to the median size of the blasting fragments and a result slightly smaller than or equal to the target vibration value; so that the server 100 can collect multiple sets of data to update the evaluation model;

[0074] In the process of blasting, as a measurable factor for evaluating the surrounding power facilities, preferably, the explosion power can be judged based on the two characteristics of vibration and fragmentation generated by the blasting; wherein the vibration and fragmentation have different characteristics respectively;

[0075] Vibration factors mainly involve the seismic waves generated by blasting and the impact on the surrounding environment, such as buildings and power facilities. The magnitude and spread of vibrations depend on multiple factors, such as the amount of explosives used, distance, and rock properties. Vibration estimation is usually used to ensure that blasting activities will not cause damage to surrounding structures.

[0076] The fragmentation factor mainly refers to the degree of fragmentation of rocks or other materials after blasting, which is closely related to the amount of explosives, rock characteristics, blasting technology, etc. The fragmentation estimation is mainly used to optimize the blasting effect to obtain the ideal fragment size distribution;

[0077] When calculating the values ​​of vibration and crushing, different variables and models need to be used, and the two are governed by different variables; therefore, in order to improve the accuracy of prediction in this technical solution, these variables and models are processed separately;

[0078] Based on the above reasons, in a preferred exemplary embodiment, as shown in the attached Figure 3 As shown, a framework diagram of the modeling unit 120 is shown;

[0079] Preferably, the modeling unit 120 includes a database 121, a modeling subunit A 122, and a modeling subunit B 124; the modeling subunit A 122 establishes a vibration assessment model 132 based on the correlation between vibration blasting conditions and vibration data; on the other hand, the modeling subunit B 124 establishes a crushing assessment model 134 based on the correlation between crushing blasting conditions and crushing data;

[0080] The database 121 may be used to store multiple sets of blasting conditions and corresponding data; and the database 121 includes a vibration assessment model 132 and / or a crushing assessment model 134 for storing multiple detection points.

[0081] By analyzing and calculating these multiple collected variables in two independent modeling units, the vibration and fragmentation estimation equations can be fitted more accurately; this can better reflect the complexity and diversity of actual blasting conditions;

[0082] Further, in a preferred exemplary embodiment, for a specified detection point, a basic vibration evaluation equation is shown in the following formula (1):

[0083]

[0084] In formula (1), V is the maximum vibration propagation velocity calculated at the detection point, which is used to measure the intensity of the vibration wave generated by the blasting when it propagates to the measurement point. It is an important parameter for evaluating the impact of blasting on the environment or surrounding structures.

[0085] K is a site constant, which reflects the geological conditions, soil type and other characteristics of a specific blasting site. When K is selected based on experience, the value range of K can range from 0.675 to 4.14; S represents the distance between the detection point and the blasting point; Z is the maximum amount of explosives used in each blasting in continuous blasting; β is the attenuation coefficient and β is greater than 0, which is used to reflect the attenuation rate of vibration with distance, and its value is usually selected based on experience;

[0086] However, the site constant K varies according to the site. The site constant K and the attenuation coefficient β usually need to be calibrated according to the field data. However, due to the complexity of the site, the K value and β value that should be taken at different detection points usually have certain differences. However, in actual experience, it is generally impossible to accurately determine the K value that should be taken at each detection point.

[0087] Further, in an exemplary embodiment, after the blasting is completed, the effect of the blasting is further evaluated by physically inspecting the objects after the blasting, such as the degree of fragmentation of rocks and minerals at the blasting point;

[0088] Preferably, the inspection method of the degree of crushing includes visual inspection, sieve analysis and three-dimensional scanning measurement;

[0089] Preferably, a basic evaluation model for fragment size is shown in the following formula (2):

[0090]

[0091] In formula (2), x 50 It is a key parameter in blasting engineering, used to describe the median fragment size of the material after blasting. It means that among the fragments of the material after blasting, 50% of the fragment size is less than or equal to x. 50 This specific value;

[0092] A is the rock factor, which is used to measure the blastability of rock. The calculation formula of A includes multiple rock characteristic indicators, and its calculation method is usually:

[0093] A=0.06*(RMD+JF+RDI+HF), formula (3);

[0094] In formula (3), RMD is the quality descriptor of rock or blasted material, JF is the joint characteristic coefficient, RDI is the density influence factor, and HF is the hardness factor. These three parameters are based on the properties of rock and can be accurately measured through experiments. However, since the properties of rock or blasted material may be uneven or cannot be accurately measured, only similar values ​​can be selected;

[0095] C(A) is the correction factor for rock factor A. Rock factor A is based on the physical and mechanical properties of the rock itself. In the actual blasting process, it is necessary to further correct the errors in the different blasting effects even for the same rock properties based on site conditions, equipment configuration, construction methods, etc.; generally, the value of C(A) is an empirical value, and the common value range is 0.6 to 2.

[0096] A t A is the delay time factor, which reflects the influence of the delay time between each blasting on the blasting effect in continuous blasting; t Factors are usually derived based on a large amount of field experimental data and experience. Under different blasting scenarios and conditions, A t The value of is usually selected from empirical records, so it is necessary for researchers to have more blasting experience or analyze historical data to determine the most appropriate value;

[0097] Q is the total amount of explosives used in continuous blasting; q is the specific charge, that is, the amount of explosives used per unit volume of rock;

[0098] RWS is the relative energy strength of explosives, which is used to characterize the ratio of the energy output of the actual explosives used to the standard explosives (such as TNT). It is determined by taking the model and formula standard of the explosives actually used for blasting.

[0099] The fragment size value is related to subjective blasting conditions, that is, the charge amount, the type of explosives selected, the blasting delay time, etc.; it is also related to objective blasting conditions, such as rock properties; therefore, based on x 50 The calculation of the typical fragment size represented by the measured value can be used to reversely deduce the optimized values ​​of other parameters that are usually taken empirically;

[0100] There is a certain difference between vibration and crushing in the nature of blasting;

[0101] The calculation of vibration mainly focuses on the impact of blasting on the surrounding environment and structures, such as buildings or power facilities. The intensity and propagation characteristics of vibration are mainly affected by factors such as the distance between the blasting point and the measurement point, the amount of explosives, and the geological conditions of the site. The core of vibration assessment is to ensure that blasting will not cause damage to the surrounding environment that exceeds safety standards.

[0102] The calculation of fragmentation focuses on the fragmentation effect of blasting on objects in the target area, such as rocks and minerals. The fragmentation effect is mainly determined by factors such as the power of the blasting, the charging method, and the properties of the rock. The purpose of fragmentation assessment is to optimize the blasting design to achieve an ideal fragmentation distribution, thereby improving mining efficiency or building demolition effects.

[0103] From the above two evaluation calculation formulas, namely formula (1) and formula (2), it can be seen that the calculation of both vibration and crushing involves the amount of explosives and some geological related parameters. However, the two involve more different parameter conditions in calculation. Therefore, by dividing the evaluation of blasting impact into two independent evaluation models and using two independent modeling units to learn and train the evaluation models, the calculation accuracy of each can be improved; if the two are evaluated by using a unified calculation model, it is easy to cause the parameters in the calculation model to be unable to accurately fit or overfit;

[0104] However, the above equations (1) and (2) are only the basic framework of the evaluation equation. The variables therein can be added or deleted as described in the following text, and additional weight values ​​can be set for the variables to achieve better regression analysis prediction results; this will be further explained below;

[0105] Preferably, each detection point may have its own independent impact assessment model 128; the impact assessment model 128 may be an assessment model after comprehensive consideration based on the vibration assessment model 132 and the crushing assessment model 134 established at the detection point, as well as the electrical characteristics of the equipment at the detection point, such as the shockproof capability;

[0106] In a preferred exemplary embodiment, the A modeling subunit 122 and the B modeling subunit 124 can add multiple parameters affecting vibration and crushing as variables to the calculation equations of the vibration assessment model 132 and the crushing assessment model 134 by using multiple linear regression analysis, and can set additional weights of the variables, which will be described in detail below;

[0107] Regression analysis is a statistical analysis method that assumes a mathematical model to study the functional relationship between variables, estimates the model from the data of the measured variables, and can select the method of equation that minimizes the residual error in multiple regression lines, such as the least squares method; in this case, the regression line does not mean a linear expression of a linear equation in fact, but a linear combination formed by variables and coefficients, and can be a two-dimensional or more curve equation in the form of polynomial regression;

[0108] The purpose of the multiple linear regression model is to create a regression model for predicting a dependent variable with multiple independent variables; in this case, multiple independent variables can be generated first, and then only important variables are left through the method of variable selection; important variables can be selected from the prediction model through variable selection, and variables that cause errors or unnecessary variables can be removed, thereby improving the prediction performance of the evaluation system proposed according to the technical solution;

[0109] Preferably, forward selection, backward elimination, stepwise selection, etc. can be used as the variable selection method;

[0110] Preferably, the modeling unit 120 can select the best evaluation model by calculating and comparing the AIC values ​​of the Akaike Information Criterion when different variables and variable values ​​are selected;

[0111] Preferably, the A modeling subunit 122 and the B modeling subunit 124 may use a recurrent neural network (RNN) to generate a classification model based on machine learning to derive a vibration assessment model 132 and a crushing assessment model 134, thereby automatically analyzing data features; the RNN neural network may be effectively used to analyze data features, analyze the correlation between blasting conditions and blasting results by performing signal classification and pattern recognition, select variables of the estimation equation in the blasting conditions, and calculate coefficients; however, the present disclosure is not limited thereto, and according to exemplary embodiments, the modeling unit 120 of the present disclosure may perform learning and analysis in various ways;

[0112] Furthermore, the vibration assessment model 132 and the crushing assessment model 134 are not limited to the parameters shown in the above equations (1) and (2) as variables; additional parameters, such as noise values, building heights, ambient temperature values, etc., can be added to calculate and predict blasting results under different blasting conditions.

[0113] Embodiment 2: This embodiment should be understood to include at least all the features of any of the above embodiments, and further improve upon them;

[0114] In a preferred exemplary embodiment, the vibration acceleration of the vibration point is more temporary and representative; therefore, the basic form of the vibration evaluation equation of formula (1) can be transformed from the vibration peak velocity to the vibration peak acceleration a as the dependent variable, that is:

[0115]

[0116] Furthermore, the vibration peak accelerations in three orthogonal directions may be decomposed and calculated respectively; preferably, the vibration peak accelerations in the three directions may be respectively:

[0117] Horizontal tangential vibration peak acceleration: refers to the vibration peak acceleration in the horizontal plane, tangential to the blasting center, reflecting the propagation and impact of the vibration wave in the horizontal direction, and is usually used to analyze the lateral impact of blasting on surrounding buildings;

[0118] Horizontal radial vibration peak acceleration: refers to the vibration peak acceleration extending outward from the blasting center on the horizontal plane; it reflects the propagation intensity of the vibration wave in the radial direction and is usually used to evaluate the direct impact of the main vibration energy generated by the blasting on the surrounding structure;

[0119] Vertical vibration peak acceleration: refers to the vibration peak acceleration in the direction perpendicular to the horizontal plane; this component is usually related to the up and down ground vibration caused by blasting, and is particularly important for the building's basic structure and foundation;

[0120] These vibration peak acceleration measurements are used to evaluate the impact of explosions on electronic equipment in different directions. By arranging sensors at monitoring points and collecting vibration peak acceleration data in the above three directions, a comprehensive analysis of explosion vibrations can be performed.

[0121] Embodiment 3: This embodiment should be understood to include at least all the features of any of the above embodiments, and further improve upon them;

[0122] For example, as shown in the attached Figure 5 As shown, an implementation of a computer system 500 used in the evaluation system is described; the computer system 500 can be applied to the data storage, calculation and result output process of each working module in the identification and judgment system;

[0123] Illustratively, computer system 500 includes a bus 502 or other communication mechanism for communicating information, one or more processors 504 coupled to bus 502 for processing information; processor 504 may be, for example, one or more general-purpose microprocessors;

[0124] The computer system 500 also includes a main memory 506, such as a random access memory (RAM), a cache, and / or other dynamic storage device, coupled to the bus 502 for storing information and instructions to be executed by the processor 504; the main memory 506 may also be used to store temporary variables or other intermediate information during the execution of instructions to be executed by the processor 504; these instructions, when stored in a storage medium accessible to the processor 504, present the computer system 500 as a special-purpose machine customized to perform the operations specified in the instructions;

[0125] The computer system 500 may also include a read-only memory (ROM) 508 or other static storage device coupled to the bus 502 for storing static information and instructions for the processor 504; a storage device 510 such as a disk, an optical disk, or a USB drive (flash drive) will be coupled to the bus 502 for storing information and instructions;

[0126] And further, coupled to the bus 502 may also include a display 122 for displaying various information, data, media, etc., an input device 514 for allowing a user of the computer system 500 to control, manipulate, and / or interact with the computer system 500;

[0127] A preferred way to interact with the management system may be through a cursor control device 516, such as a computer mouse or similar control / navigation mechanism;

[0128] Furthermore, the computer system 500 may also include a network device 518 coupled to the bus 502; wherein the network device 518 may include, for example, a wired network card, a wireless network card, a switching chip, a router, a switch, and other components;

[0129] In general, the terms "engine", "component", "system", "database", etc., as used herein, may refer to logic embodied in hardware or firmware, or to a collection of software instructions, possibly with entry and exit points, written in a programming language such as Java, C, or C++; software components may be compiled and linked into executable programs, installed in a dynamic link library, or may be written in an interpreted programming language (e.g., BASIC, Perl, or Python); it should be understood that software components may be called from other components or from themselves, and / or may be called in response to detected events or interrupts;

[0130] Software components configured to execute on a computing device may be provided on a computer-readable medium, such as a compact disc, digital video disc, flash drive, diskette, or any other tangible medium, or as a digital download (and may be initially stored in a compressed or installable format that requires installation, decompression, or decryption prior to execution); such software code may be stored in part or in whole on a memory device of the executing computing device for execution by the computing device; software instructions may be embedded in firmware, such as an EPROM; it is also understood that hardware components may be composed of connected logic units (such as gates and flip-flops), and / or may be composed of programmable units (such as programmable gate arrays or processors);

[0131] Computer system 500 includes the techniques described herein that may be implemented using custom hardwired logic, one or more ASICs or FPGAs, firmware, and / or program logic that, in combination with the computer system, renders computer system 500 a special-purpose computing device;

[0132] According to one or more embodiments, the techniques herein may be performed by computer system 500 in response to processor 504 executing one or more sequences of one or more instructions contained in main memory 506; such instructions may be read into main memory 506 from another storage medium, such as storage device 510; execution of the sequences of instructions contained in main memory 506 causes processor 504 to perform the process steps described herein; in alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions;

[0133] As used herein, the term "non-transitory media" and similar terms refer to any media that store data and / or instructions that cause a machine to operate in a specific manner; such non-transitory media may include non-volatile media and / or volatile media; non-volatile media include, for example, optical or magnetic disks, such as storage device 510; volatile media include dynamic memory, such as main memory 506;

[0134] Among them, common forms of non-transitory media include, for example, floppy disks, diskettes, hard disks, solid-state drives, magnetic tapes or any other magnetic data storage medium, CD-ROMs, any other optical data storage medium, any physical medium having a pattern of holes, RAM, PROM and EPROM, FLASH-EPROM, NVRAM, any other memory chip or cartridge, and network versions thereof;

[0135] Non-transient media are distinct from transmission media but may be used in conjunction with transmission media; transmission media participate in the transmission of information between non-transient media; for example, transmission media include coaxial cables, copper wires, and optical fibers, including the wires that make up bus 502; transmission media may also take the form of sound waves or light waves, such as radio waves and infrared data communications.

[0136] Although the present invention has been described above with reference to various embodiments, it should be understood that many changes and modifications may be made without departing from the scope of the present invention. That is, the methods, systems and devices discussed above are examples. Various configurations may appropriately omit, replace or add various processes or components. For example, in alternative configurations, the method may be performed in an order different from the order described, and / or various components may be added, omitted and / or combined. Moreover, the features described with respect to certain configurations may be combined in various other configurations, such as different aspects and elements of the configurations may be combined in a similar manner. In addition, the elements therein may be updated as the technology develops, i.e., many elements are examples and do not limit the scope of the present disclosure or claims.

[0137] Specific details are given in the specification to provide a thorough understanding of the exemplary configurations including implementations. However, the configurations may be practiced without these specific details. For example, well-known circuits, processes, algorithms, structures, and techniques have been shown without unnecessary details to avoid obscuring the configurations. This description provides only example configurations and does not limit the scope, applicability, or configurations of the claims. On the contrary, the foregoing description of the configurations will provide those skilled in the art with an enabling description for implementing the described techniques. Various changes may be made to the functions and arrangements of the elements without departing from the spirit or scope of the present disclosure.

[0138] In summary, it is intended that the above detailed description is considered to be illustrative rather than restrictive, and it should be understood that the above embodiments should be understood to be only used to illustrate the present invention and not to limit the scope of protection of the present invention. After reading the contents of the present invention, the technician can make various changes or modifications to the present invention, and these equivalent changes and modifications also fall within the scope defined by the claims of the present invention.

Claims

1. A machine learning-based blasting engineering impact assessment system for power facilities, characterized in that: The evaluation system comprises: A collection unit is configured to collect a plurality of detection data from a blasting site and a plurality of detection points in the surrounding area during the blasting process and after the blasting is completed; A modeling unit is configured to perform machine learning based on multiple sets of detection data by using a machine learning algorithm to train and establish one or more impact assessment models; An analysis unit configured to use the impact assessment model and the earthquake resistance of the power facilities to assess the impact of blasting at a designated blasting condition and a designated location on the power facilities; Wherein, the modeling unit includes a modeling subunit A, a modeling subunit B and a database; The modeling subunit A is configured to establish a vibration assessment model based on the correlation between the vibration blasting conditions and the vibration data; The modeling subunit B is configured to establish a fragmentation assessment model based on the correlation between the fragmentation blasting conditions and the fragmentation data; The database is configured to store modeling data required by the modeling unit, including multiple sets of vibration blasting conditions and corresponding vibration data, and multiple sets of fragmentation blasting conditions and corresponding fragmentation data; The impact assessment model integrates the parameters fitted by the vibration assessment model and the crushing assessment model of each detection point to predict the impact on the detection point after blasting is carried out under designated blasting conditions and at a designated location.

2. The evaluation system according to claim 1, characterized in that: The vibration blasting conditions at least include: the vibration value of the detection point, the single maximum explosive usage in continuous blasting, the distance between the blasting point and the detection point, and the site constant.

3. The evaluation system according to claim 2, characterized in that: The fragmentation blasting conditions include at least: the total amount of explosives, the specific charge amount, the rock factor, the relative energy intensity of the explosives, and the ratio of the median size of the blasting fragments.

4. The evaluation system according to claim 3, characterized in that: The acquisition unit includes a plurality of sensors, including at least a plurality of remote sensors arranged at detection points around the power facility to be evaluated.

5. The evaluation system according to claim 4, characterized in that: The sensor in the acquisition unit includes at least: an acceleration sensor; the acceleration sensor includes a sensor for collecting vibration peak acceleration data of the detection object in three-dimensional directions at the detection point; the vibration peak acceleration data includes: horizontal tangential vibration peak acceleration, horizontal radial vibration peak acceleration, and vertical vibration peak acceleration.

6. The evaluation system according to claim 5, characterized in that: The modeling subunit A and the modeling subunit B establish the correlation model between the vibration blasting condition and the vibration data, and the crushing blasting condition and the crushing data by using multiple linear regression analysis.

7. The evaluation system according to claim 6, characterized in that: The modeling unit establishes a corresponding, independent vibration assessment model and a crushing assessment model for the location of each detection point.

8. The evaluation system according to claim 7, characterized in that: The modeling subunit A includes selecting one or more parameters in the vibration blasting conditions as variables of the vibration assessment model after analyzing the correlation between the vibration blasting conditions and the vibration data, and setting weight coefficients for each variable in the vibration assessment model to establish a final vibration assessment model.

9. The evaluation system according to claim 8, characterized in that: The modeling subunit B includes selecting one or more parameters in the crushing blasting conditions as variables of the crushing assessment model after analyzing the correlation between the crushing blasting conditions and the crushing data, and setting weight coefficients for each variable in the crushing assessment model to establish a final crushing assessment model.

10. A method for assessing the impact of blasting engineering on power facilities based on machine learning, characterized in that: The evaluation method is applied to the evaluation system as claimed in claim 9; the evaluation method comprises the following steps: S100: setting a plurality of detection points, and arranging sensors at the blasting point and the plurality of detection points to obtain values ​​of a plurality of blasting conditions; S200: Based on a plurality of blasting conditions that are known or can be determined in advance through experiments, initial values ​​of a plurality of parameters of a vibration assessment model and a crushing assessment model are set, including setting initial values ​​of a plurality of empirical parameters; S300: Conduct multiple groups of blasting tests, collect vibration values ​​at multiple test points, and determine the median size of blasting fragments; S400: updating weight values ​​of multiple parameters in the vibration assessment model and the crushing assessment model, including updating the values ​​of the empirical parameters; S500: Using a corresponding impact assessment model according to the location of the power facility and combining the seismic resistance of the power facility, assess the impact of blasting on the power facility under designated blasting conditions and at a designated location.

Images