A method and system for evaluating the safety of rock-breaking blasting

Abstract

The present invention provides a method and system for evaluating the safety of rock-breaking blasting, which relates to the field of blasting technology. The specific steps include: collecting historical blasting parameters and blasting result parameters, and collecting geological data and environmental data of the blasting area as correction data; using the support vector machine algorithm to establish a dynamic risk assessment model, taking each blasting parameter as the training set and the blasting result parameter as the label to train the model, so as to obtain the dynamic risk assessment model; collecting the blasting parameters of the rock-breaking blasting to be evaluated in real time, inputting them into the model to obtain the predicted parameters of the blasting result, correcting them with the correction data to obtain the comprehensive safety index, and comparing it with the preset safety threshold. When the safety threshold is exceeded, the system issues an alarm. The present invention uses a support vector machine model to evaluate the safety of rock-breaking blasting, reducing the deviation and uncertainty of human judgment.

Description

Technical Field

[0001] The present invention relates to the technical field of blasting, and specifically provides a method and system for evaluating the safety of rock-breaking blasting. Background Art

[0002] In the field of traditional rock-breaking blasting engineering, the evaluation of safety mainly relies on the experience and intuition of engineers. Although this method can meet the engineering requirements to a certain extent, it has significant limitations. First of all, empirical judgments often lack systematicness and consistency. Different engineers may give different evaluation results based on personal experience, resulting in increased uncertainty in decision-making. Secondly, with the increase in engineering complexity, traditional empirical judgment methods are difficult to cope with the changing environment and complex technical parameters, such as the physical properties of rocks, blasting parameters, environmental factors, etc., which may have a significant impact on the safety of blasting.

[0003] In addition, with the development of data acquisition technology, modern rock-breaking blasting engineering can collect a large amount of real-time data, including but not limited to key information such as the hardness of rocks, the amount of blasting explosives, and the blasting location. These data make it possible to adopt more scientific and accurate methods for safety evaluation. However, how to effectively utilize these data, extract valuable information from them, and make accurate safety predictions based on this is a problem that traditional methods are difficult to solve. Support Vector Machine (SVM), as a powerful machine learning tool, can process and analyze high-dimensional data, and learn potential patterns and rules from the data by constructing complex non-linear mapping relationships. Applying the SVM model in rock-breaking blasting engineering can effectively integrate and analyze multi-source data, and achieve accurate prediction and evaluation of blasting safety. This method can not only improve the objectivity and accuracy of the evaluation, but also cope with the data analysis and pattern recognition problems that are difficult to solve by traditional methods, providing a new and more scientific solution for the safety management of rock-breaking blasting engineering.

[0004] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and therefore it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for evaluating the safety of rock-breaking blasting to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] A method and system for evaluating the safety of rock-breaking blasting, the specific steps include:

[0008] Step 1: Collect the blasting parameters and blasting result parameters of multiple historical blasting operations. The blasting parameters include the detonation velocity and the amount of explosive, and the blasting result parameters include the rock fragmentation degree, the vibration intensity, and the maximum flying rock distance. Collect the geological data and environmental data of the blasting area. The geological data is the rock hardness, and the environmental data includes the wind speed and humidity around the blasting point.

[0009] Step 2: Establish a dynamic risk assessment model based on the support vector machine algorithm. Use the blasting parameters of historical blasting operations as the training set and input them into the dynamic risk assessment model, and use the blasting result parameters as labels to train the dynamic risk assessment model.

[0010] Step 3: Real-time collect the blasting parameters of the rock-breaking blasting to be evaluated, input the real-time collected blasting parameters into the trained dynamic risk assessment model to obtain the predicted parameters of the blasting results. Collect the geological data and environmental data of the rock-breaking blasting area to be evaluated. The geological data is the rock hardness, and the environmental data includes the wind speed and humidity around the blasting point.

[0011] Step 4: Use the collected geological data and environmental data of the evaluated rock-breaking blasting area to correct the predicted parameters of the blasting results to obtain a comprehensive safety index. Compare the comprehensive safety index with the safety threshold and give an early warning when it exceeds the safety threshold.

[0012] Further, the specific logic for collecting the detonation velocity of the explosive is as follows:

[0013] Obtain the specific heat ratio, gas constant, detonation temperature, and molar mass of the detonation products of the explosive used in the blasting operation. Generate the detonation velocity of the explosive used in the blasting operation according to the Chapman-Jouguet theory. The formula is:

[0014]

[0015] where D is the detonation velocity in meters per second, γ is the specific heat ratio of the detonation products, R is the gas constant, approximately 8.314 J, T is the detonation temperature in Kelvin, and M is the molar mass of the detonation products in kilograms per mole.

[0016] The specific logic for collecting the rock fragmentation degree is as follows:

[0017] After the blasting, collect rock samples from the blasting area; use a set of standard sieves with different apertures to screen the samples, and the sizes of the sieves are arranged from large to small; record the weights of the rock pieces remaining on each sieve.

[0018] The formula for generating the rock fragmentation degree is:

[0019]

[0020] Among them, S is the degree of rock fragmentation, and x i is the size of the i-th sieve, and w i is the weight of the rock pieces on this sieve;

[0021] The vibration intensity is collected using the formula of the US Bureau of Mines (USBM):

[0022]

[0023] Among them, PPV is the vibration intensity, with the unit of millimeters per second, which refers to the maximum value of the particle velocity during the propagation of the vibration wave generated by blasting. W is the amount of explosive, with the unit of lbs, R is the distance from the blasting point, with the unit of feet, k is an empirical constant, and m is a vibration constant, which needs to be determined through on-site calibration.

[0024] Furthermore, the formula for collecting the distance of flying rocks is as follows:

[0025]

[0026] Among them, M is the maximum distance of flying rocks caused by blasting, with the unit of meters, k is an empirical constant, generally taking values between 10 - 55, and specifically needs to be determined according to the actual on-site environment. W is the amount of explosive, with the unit of lbs;

[0027] The specific logic for collecting rock hardness is as follows:

[0028] The Mohs hardness is used to measure rock hardness: the hardness of the rock is determined by comparing the scratch hardness of minerals. The Mohs hardness scale is 1 - 10, and the specific steps are as follows:

[0029] Use the standard minerals on the Mohs hardness scale to scratch the rock surface, observe whether scratches can be left, and determine the Mohs hardness of the rock according to the hardest mineral that can make scratches and the softest mineral that cannot make scratches;

[0030] The specific logic for obtaining the wind speed and humidity around the blasting point is as follows:

[0031] Select n representative measurement points around the blasting point, covering the four directions of east, south, west, and north, and select measurement points at equal intervals and distances according to the blasting range in each direction;

[0032] Install an anemometer and a hygrometer at the measurement points, ensure that the equipment is horizontal and calibrated;

[0033] Record the wind speed data and humidity data at different measurement points to obtain the average wind speed and average humidity;

[0034] The formula for obtaining the average wind speed is:

[0035]

[0036] Among them, is the average wind speed, v i represents the wind speed measured at the i-th measurement point;

[0037] The formula for obtaining the average humidity is:

[0038]

[0039] Among them, is the average humidity, RH i represents the humidity measured at the i-th measurement point.

[0040] Furthermore, the process of using the support vector machine algorithm to establish a dynamic risk assessment model specifically includes:

[0041] Taking the blasting parameters each time as the training set and the blasting result parameters as the labels; constructing a machine learning model based on the support vector machine, inputting the training set and the labels into the machine learning model, and training the machine learning model to obtain a trained dynamic risk assessment model.

[0042] Furthermore, using the support vector machine algorithm to construct a model, the goal of the support vector machine is to find a hyperplane that can separate data points of different categories, and the decision function can be expressed as:

[0043] f(x) = w T x + b

[0044] Among them, w T is the weight vector, x is the input feature vector, and b is the bias term;

[0045] The training process is carried out by optimizing the following objective function:

[0046]

[0047] Among them, is the regularization term, which controls the complexity of the model, C is the penalty parameter, which controls the trade-off between the training error and the model complexity, and δ i is the slack variable, which represents the error of the i-th data point; the constraint condition is:

[0048] y i (w T x i + b) ≥ 1 - δ i , δ i ≥ 0, i = 1, 2,..., N

[0049] That is, each sample point (x i , yi ) should all be correctly classified with an error not exceeding δ i ;

[0050] To solve the above optimization problem, we introduce the Lagrange multiplier α i , and transform it into a dual problem:

[0051]

[0052] where α i is the Lagrange multiplier, y i is the label of the i-th sample, and x i is the feature vector of the i-th sample; the constraint conditions are:

[0053]

[0054] To handle non-linearly separable data, a Gaussian kernel function is introduced to map the input space to a high-dimensional feature space. The formula is as follows:

[0055]

[0056] where K(x i , x j ) is the Gaussian kernel function, x i and x j are two feature vectors in the input space, representing the square of the Euclidean distance between the vectors x i and x j , and σ is the bandwidth parameter of the Gaussian kernel, controlling the width of the Gaussian function;

[0057] The dual problem after introducing the kernel function is:

[0058]

[0059] By solving the above dual problem, the Lagrange multiplier α i can be obtained, and the decision function of the support vector machine can be expressed as:

[0060]

[0061] Furthermore, the specific logic for obtaining the prediction parameters of the blasting result is as follows:

[0062] The blasting parameters of the rock-breaking blasting to be evaluated are collected in real time, including the detonation velocity and the amount of explosive of the explosive, and they are input into the trained dynamic risk model, and the prediction parameters of the blasting result are output. The prediction parameters of the blasting result include the rock fragmentation degree S f , the vibration intensity PPV f and the maximum flying rock distance M f .

[0063] Furthermore, the prediction parameters of the blasting result are corrected using the correction data, and the logic for obtaining the comprehensive safety index is as follows:

[0064] Compare the obtained average wind speed with the preset wind speed threshold. If it exceeds the threshold range, calculate the difference Δv between the average wind speed and the preset wind speed range;

[0065] Compare the obtained average humidity with the preset humidity threshold. If it exceeds the threshold range, calculate the difference ΔRH between the average humidity and the preset humidity range;

[0066] The formula is as follows:

[0067]

[0068] Among them, QS is the comprehensive safety index, S f is the predicted rock fragmentation degree, PPV f is the predicted vibration intensity, M f is the predicted flying rock distance, and α, β, γ are the preset proportionality coefficients of S f , PPV f , M f respectively, and α, β, γ are all greater than zero. Δv is the difference between the average wind speed and the preset wind speed range, Δ is the difference between the average humidity and the preset humidity range, ρ is the preset proportionality coefficient of the reciprocal of the sum of Δv and ΔRH, and ρ is greater than zero. C1 and C2 are constant correction exponents.

[0069] Furthermore, compare the comprehensive safety index QS with the preset safety threshold QY, including:

[0070] When QS ≤ QY, it indicates that the safety threshold has not been exceeded and it is in a safe state;

[0071] When QS > QY, it indicates that the safety threshold has been exceeded, and the system automatically issues an alarm, and relevant personnel should handle it immediately.

[0072] A rock-breaking blasting safety evaluation system includes:

[0073] A data acquisition module that collects blasting parameters and blasting result parameters of multiple historical blasting operations. The blasting parameters include the detonation velocity and the amount of explosive, and the blasting result parameters include rock fragmentation degree, vibration intensity, and maximum flying rock distance. It also collects geological data and environmental data of the blasting area. The geological data is the rock hardness, and the environmental data includes the wind speed and humidity around the blasting point;

[0074] A model construction module that builds a dynamic risk assessment model based on the support vector machine algorithm. The blasting parameters of historical blasting operations are used as the training set and input into the dynamic risk assessment model, and the blasting result parameters are used as labels to train the dynamic risk assessment model.

[0075] A prediction module that collects the blasting parameters of the rock-breaking blasting to be evaluated in real time, inputs the real-time collected blasting parameters into the trained dynamic risk assessment model to obtain the predicted parameters of the blasting results, and collects the geological data and environmental data of the rock-breaking blasting area to be evaluated. The geological data is the rock hardness, and the environmental data includes the wind speed and humidity around the blasting point.

[0076] A comprehensive evaluation module that uses the collected geological data and environmental data of the rock-breaking blasting area to correct the predicted parameters of the blasting results, obtains the comprehensive safety index, compares the comprehensive safety index with the safety threshold, and issues a warning when the safety threshold is exceeded.

[0077] Compared with the prior art, the beneficial effects of the present invention are:

[0078] Using a support vector machine model for the safety evaluation of rock-breaking blasting can significantly improve the objectivity and accuracy of the evaluation. Through machine learning algorithms, the SVM model can automatically extract key features and patterns from a large amount of historical data, predict and evaluate the safety of different blasting schemes, and reduce the deviation and uncertainty of human judgment. In addition, the high efficiency of this model enables the safety evaluation to be completed in a short time, greatly improving the efficiency of engineering decision-making. The application of this technology not only ensures the safety of the project, but also improves the management level and technological content of the entire blasting project, contributing to the technological progress of related fields. Description of the Drawings

[0079] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0080] Figure 2 It is a schematic diagram of the overall system module of the present invention. Detailed Embodiments

[0081] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the following further describes the present invention in detail with reference to specific embodiments.

[0082] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention shall have the ordinary meanings understood by those of ordinary skill in the field to which the present invention pertains. The "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. The terms such as "comprising" or "including" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0083] Embodiment:

[0084] Please refer to Figure 1 , the present invention provides a technical solution:

[0085] A method for evaluating the safety of rock-breaking blasting, the specific steps include:

[0086] Step 1: Collect the blasting parameters and blasting result parameters of multiple historical blasting operations. The blasting parameters include the detonation velocity and the amount of explosive, and the blasting result parameters include the degree of rock fragmentation, the vibration intensity and the flying rock distance. Collect the geological data and environmental data of the blasting area. The geological data is the rock hardness, and the environmental data includes the wind speed and humidity around the blasting point;

[0087] In this embodiment, the specific logic for collecting the detonation velocity of the explosive is:

[0088] Obtain the specific heat ratio, gas constant, detonation temperature and molar mass of the detonation products of the explosive used in the blasting operation, and generate the detonation velocity of the explosive used in the blasting operation according to the Chapman-Jouguet theory. The formula is:

[0089]

[0090] Among them, D is the detonation velocity, with the unit of meters per second. The detonation velocity is an important index to measure the power of the explosive. The higher the detonation velocity, the stronger the destructive power of the explosive. γ is the specific heat ratio of the detonation products, R is the gas constant, approximately 8.314 J, T is the detonation temperature, with the unit of Kelvin, and M is the molar mass of the detonation products, with the unit of kg / mol; when the detonation temperature T increases, the detonation velocity D increases, that is, it shows that T and D are positively correlated; γ, T, and M can be obtained by looking up the detonation theory and the thermodynamic data table;

[0091] The specific logic for collecting the degree of rock fragmentation is:

[0092] After blasting, collect rock samples from the blasting area; sieve the samples using a set of standard sieves with different aperture sizes, arranged from largest to smallest; record the weight of the rock pieces remaining on each sieve;

[0093] The formula for generating the degree of rock fragmentation is:

[0094]

[0095] where S is the degree of rock fragmentation, x i is the size of the i-th sieve, w i is the weight of the rock pieces on that sieve;

[0096] The degree of rock fragmentation is an important indicator to measure the blasting effect, which describes the degree of fragmentation of the rock after blasting. The fragmentation distribution method used in this embodiment is one of the most commonly used methods to evaluate the degree of rock fragmentation. It collects rock samples after blasting, sieves them using standard sieves, and then calculates the proportion of rock pieces of different sizes based on the sieving results;

[0097] Collect the vibration intensity using the formula of the U.S. Bureau of Mines (USBM):

[0098]

[0099] where PPV is the vibration intensity, in millimeters per second, which refers to the maximum value of the particle velocity during the propagation of the blasting vibration wave. W is the amount of explosive, in lbs, R is the distance from the blasting point, in feet, k is an empirical constant, and m is a vibration constant that needs to be determined through on-site calibration; when the amount of explosive W increases, the vibration intensity PPV will increase accordingly. When the distance R from the blasting point increases, the vibration intensity will decrease, that is, it shows that W and PPV are positively correlated, and R and PPV are negatively correlated; the distance R from the blasting point can be directly measured using a measuring tool, and the amount of explosive W can be obtained according to the blasting design plan;

[0100] The formula for collecting the distance of flying rocks is as follows:

[0101]

[0102] where M is the maximum distance of flying rocks caused by blasting, in meters. In blasting operations, flying rocks are an important safety hazard, and evaluating the distance of flying rocks is particularly important for ensuring on-site safety. k is an empirical constant, generally taking values between 10 - 55, which specifically needs to be determined according to the actual on-site environment. W is the amount of explosive, in lbs; when the amount of explosive W increases, the maximum distance M of the flying rocks caused by blasting increases, that is, it shows that W and M are positively correlated;

[0103] The specific logic for collecting rock hardness is as follows:

[0104] The Mohs hardness is used to measure the rock hardness: the hardness of the rock is determined by comparing the scratch hardness of minerals. The Mohs hardness scale is 1 - 10, and the specific steps are as follows:

[0105] Use the standard minerals on the Mohs hardness scale to scratch the rock surface, observe whether scratches can be left, and determine the Mohs hardness of the rock according to the hardest mineral that can make scratches and the softest mineral that cannot make scratches;

[0106] The specific logic for obtaining the wind speed and humidity around the blasting point is as follows:

[0107] Select n representative measurement points around the blasting point, covering the four directions of east, south, west, and north, and select the measurement points at equal quantity and equal distance according to the blasting range in each direction;

[0108] Install an anemometer and a hygrometer at the measurement points, ensure the equipment is horizontal and calibrate it;

[0109] Record the wind speed data and humidity data at different measurement points to obtain the average wind speed and average humidity;

[0110] The formula for obtaining the average wind speed is:

[0111]

[0112] where is the average wind speed, v i represents the wind speed measured at the i-th measurement point;

[0113] The formula for obtaining the average humidity is:

[0114]

[0115] where is the average humidity, RH i represents the humidity measured at the i-th measurement point.

[0116] Step 2: Establish a dynamic risk assessment model based on the support vector machine algorithm. Use the blasting parameters of historical blasting operations as the training set and input them into the dynamic risk assessment model, and use the blasting result parameters as labels to train the dynamic risk assessment model;

[0117] In this embodiment, the process of using the support vector machine algorithm to establish a dynamic risk assessment model specifically includes:

[0118] Take the blasting parameters each time as the training set and the blasting result parameters as the labels; construct a machine learning model based on support vector machines, input the training set and labels into the machine learning model, and train the machine learning model to obtain a trained dynamic risk assessment model.

[0119] Use the support vector machine algorithm to build the model. The goal of the support vector machine is to find a hyperplane that can separate data points of different classes. The decision function can be expressed as:

[0120] f(x) = w T x + b

[0121] where w T is the weight vector, x is the input feature vector, and b is the bias term;

[0122] The training process is carried out by optimizing the following objective function:

[0123]

[0124] where is the regularization term, which controls the complexity of the model, C is the penalty parameter, which controls the trade-off between the training error and the model complexity, and δ i is the slack variable, representing the error of the i-th data point; the constraint condition is:

[0125] y i (w T x i + b) ≥ 1 - δ i , δ i ≥ 0, i = 1, 2,..., N

[0126] That is, each sample point (x i , y i ) should be correctly classified, and its error does not exceed δ i ;

[0127] To solve the above optimization problem, we introduce the Lagrange multiplier α i , and transform it into a dual problem:

[0128]

[0129] where α i is the Lagrange multiplier, y i is the label of the i-th sample, and x i is the feature vector of the i-th sample; the constraint condition is:

[0130]

[0131] To process non-linearly separable data, the Gaussian kernel function is introduced to map the input space to a high-dimensional feature space. The formula is as follows:

[0132]

[0133] where K(x i , x j ) is the Gaussian kernel function, x i and x j are two feature vectors in the input space, representing the square of the Euclidean distance between the vectors x i and x j . σ is the bandwidth parameter of the Gaussian kernel, which controls the width of the Gaussian function;

[0134] The dual problem after introducing the kernel function is:

[0135]

[0136] By solving the above dual problem, the Lagrange multiplier α i can be obtained, and the decision function of the support vector machine can be expressed as:

[0137]

[0138] Step 3: Real-time collect the blasting parameters of the rock-breaking blasting to be evaluated, input the real-time collected blasting parameters into the trained dynamic risk assessment model to obtain the prediction parameters of the blasting result, and collect the geological data and environmental data of the rock-breaking blasting area to be evaluated. The geological data is the rock hardness, and the environmental data includes the wind speed and humidity around the blasting point;

[0139] In this embodiment, the specific logic for obtaining the prediction parameters of the blasting result is as follows:

[0140] Real-time collect the blasting parameters of the rock-breaking blasting to be evaluated, including the detonation velocity and explosive amount of the explosive, input them into the trained dynamic risk model, and output the prediction parameters of the blasting result. The prediction parameters of the blasting result include the rock fragmentation degree S f , the vibration intensity PPV f and the flying rock distance M f .

[0141] Step 4: Use the collected geological data and environmental data of the rock-breaking blasting area to correct the prediction parameters of the blasting result to obtain the comprehensive safety index, compare the comprehensive safety index with the safety threshold, and give an early warning when it exceeds the safety threshold;

[0142] In this embodiment, the logic for correcting the prediction parameters of the blasting result using the correction data to obtain the comprehensive safety index is as follows:

[0143] Compare the obtained average wind speed with a preset wind speed threshold. If it exceeds the threshold range, calculate the difference Δv between the average wind speed and the preset wind speed range;

[0144] Compare the obtained average humidity with a preset humidity threshold. If it exceeds the threshold range, calculate the difference ΔRH between the average humidity and the preset humidity range;

[0145] The formula is as follows:

[0146]

[0147] Where QS is the comprehensive safety index, S f is the predicted rock fragmentation degree, PPV f is the predicted vibration intensity, M f is the predicted maximum flying rock distance, and α, β, γ are the preset proportionality coefficients of S f , PPV f , M f respectively, and α, β, γ are all greater than zero. Δv is the difference between the average wind speed and the preset wind speed range, ΔRH is the difference between the average humidity and the preset humidity range, ρ is the preset proportionality coefficient of the reciprocal of the sum of Δv and ΔRH, and ρ is greater than zero. C1 and C2 are constant correction exponents; when S f , PPV f , M f increase, the comprehensive safety index QS will increase accordingly. When Δv and ΔRH increase, the comprehensive safety index QS will decrease accordingly, that is, it shows that S f , PPV f , M f are positively correlated with QS, and Δv, ΔRH are negatively correlated with QS;

[0148] In this embodiment, comparing the comprehensive safety index QS with a preset safety threshold QY includes:

[0149] When QS ≤ QY, it indicates that the safety threshold is not exceeded and it is in a safe state;

[0150] When QS > QY, it indicates that the safety threshold is exceeded, and the system automatically issues an alarm, and relevant personnel immediately handle it.

[0151] By comparing QS and QY in real time, the system can timely detect potential safety risks. When QS > QY, the system automatically issues an alarm to ensure that relevant personnel can respond quickly and take necessary preventive or countermeasures, thereby reducing or avoiding the occurrence of safety accidents.

[0152] The present invention also provides a rock-breaking blasting safety evaluation system, which is used to execute the above-mentioned rock-breaking blasting safety evaluation method, including:

[0153] A data acquisition module that collects blasting parameters and blasting result parameters of multiple historical blasting operations. The blasting parameters include the detonation velocity and the amount of explosive, and the blasting result parameters include the rock fragmentation degree, the vibration intensity, and the flying rock distance. It also collects geological data and environmental data of the blasting area. The geological data is the rock hardness, and the environmental data includes the wind speed and humidity around the blasting point.

[0154] A model construction module that establishes a dynamic risk assessment model based on the support vector machine algorithm. The blasting parameters of historical blasting operations are used as the training set and input into the dynamic risk assessment model, and the blasting result parameters are used as labels to train the dynamic risk assessment model.

[0155] A prediction module that real-time collects the blasting parameters of the rock-breaking blasting to be evaluated and inputs the real-time collected blasting parameters into the trained dynamic risk assessment model to obtain the predicted parameters of the blasting results. It also collects the geological data and environmental data of the rock-breaking blasting area to be evaluated. The geological data is the rock hardness, and the environmental data includes the wind speed and humidity around the blasting point.

[0156] A comprehensive evaluation module that uses the collected geological data and environmental data of the rock-breaking blasting area to correct the predicted parameters of the blasting results, obtains a comprehensive safety index, compares the comprehensive safety index with the safety threshold, and issues a warning when it exceeds the safety threshold.

[0157] The specific values of α, β, γ, and ρ in the formula are generally determined by those skilled in the art according to the actual situation. Those skilled in the art collect multiple groups of sample data and set corresponding preset proportional coefficients for each group of sample data. Substitute the set preset proportional coefficients and the collected sample data into the formula. Through repeated experiments and parameter adjustments, observe the accuracy of the model output and the rationality of the results, gradually adjust these factor coefficients, and compare the performance and effects of the model under different parameter settings to find the optimal coefficient combination. Screen and take the average value of the calculated factor coefficients to obtain the values of α, β, γ, and ρ.

[0158] In addition, the size of the preset factor coefficient is a specific value obtained by quantifying each parameter. It is for the convenience of subsequent comparison. Regarding the size of the coefficient, it depends on the amount of sample data and the initial setting of the corresponding preset proportional coefficients for each group of sample data by those skilled in the art, and it is not unique as long as it does not affect the proportional relationship between the parameter and the quantified value.

[0159] The above formulas are all dimensionless and take their numerical calculations. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0160] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0161] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units. They may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0162] As described above, the above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all of them should be covered by the protection scope of the present application.

Claims

1. A rock blasting safety evaluation method, characterized in that: The specific steps include: Step 1: Collect blasting parameters and blasting result parameters of multiple historical blasting operations, the blasting parameters include the detonation velocity and amount of explosives, the blasting result parameters include rock fragmentation, vibration intensity and maximum flying rock distance, collect geological data and environmental data of the blasting area, the geological data is rock hardness, and the environmental data includes wind speed and humidity around the blasting point; Step 2: Establish a dynamic risk assessment model based on the support vector machine algorithm, input the blasting parameters of historical blasting operations as a training set into the dynamic risk assessment model, and use the blasting result parameters as labels to train the dynamic risk assessment model; Step 3: Collect the blasting parameters of the rock-breaking blasting to be evaluated in real time, input the real-time collected blasting parameters into the trained dynamic risk assessment model, obtain the prediction parameters of the blasting results, and collect geological data and environmental data of the rock-breaking blasting area to be evaluated, wherein the geological data is the rock hardness, and the environmental data includes the wind speed and humidity around the blasting point; Step 4: Use the collected geological data and environmental data of the rock-breaking blasting area to correct the prediction parameters of the blasting results, obtain a comprehensive safety index, compare the comprehensive safety index with the safety threshold, and issue an early warning when the safety threshold is exceeded; The specific logic for obtaining the prediction parameters of blasting results is: The blasting parameters of the rock blasting to be evaluated, including the detonation velocity and amount of explosives, are collected in real time, and are input into the trained dynamic risk model to output the predicted parameters of the blasting results, including the rock fragmentation degree S f , vibration intensity PPV f and the maximum flying stone distance M f ; The logic for correcting the prediction parameters of blasting results by using the corrected data to obtain the comprehensive safety index is as follows: The obtained average wind speed is compared with the preset wind speed threshold. If it exceeds the threshold range, the difference Δv between the average wind speed and the preset wind speed range is calculated; The obtained average humidity is compared with the preset humidity threshold, and if it exceeds the threshold range, the difference ΔRH between the average humidity and the preset humidity range is calculated; The formula is as follows: Among them, QS is the comprehensive safety index, S f is the predicted rock fragmentation, PPV f is the predicted vibration intensity, M f is the predicted maximum flying rock distance, α, β, and γ are S f , PPV f 、M f is a preset proportional coefficient, and α, β, and γ are all greater than zero, Δv is the difference between the average wind speed and the preset wind speed range, ΔRH is the difference between the average humidity and the preset humidity range, ρ is a preset proportional coefficient of the reciprocal of the sum of Δv and ΔRH, and ρ is greater than zero, and C1 and C2 are constant correction exponents.

2. A rock blasting safety assessment method according to claim 1, characterized in that: The specific logic for collecting explosive detonation velocity is: The specific heat ratio, gas constant, detonation temperature and molar mass of the detonation products of the explosives used in blasting operations are obtained, and the detonation velocity of the explosives used in blasting operations is generated according to the Chapman-Jouguet theory. The formula is: Where D is the detonation velocity in meters per second (m / s), γ is the specific heat ratio of the detonation products, R is the gas constant, which is approximately 8.314 J, T is the detonation temperature in Kelvin, and M is the molar mass of the detonation products in kg / mol; The specific logic for collecting rock fragmentation is: After blasting, collect rock samples from the blasting area; sieve the samples using a set of standard sieves with different apertures, arranged from large to small; record the weight of the rock pieces that stay on each sieve; The formula for generating rock fragmentation is: Among them, S is the rock fragmentation, x i is the size of the ith screen, w i is the weight of the rock mass on the screen; The vibration intensity is collected using the U.S. Bureau of Mines (USBM) formula: Where PPV is the vibration intensity in millimeters per second, W is the amount of explosive in lbs, R is the distance from the blasting point in feet, k is an empirical constant, and m is the vibration constant, which needs to be determined through on-site calibration.

3. A rock blasting safety assessment method according to claim 1, characterized in that: The formula for collecting the maximum flying rock distance is as follows: Where M is the maximum flying rock distance caused by blasting, in meters, k is an empirical constant that needs to be determined based on the actual on-site environment, and W is the amount of explosives, in lbs; The specific logic for collecting rock hardness is: Measuring rock hardness using the Mohs hardness scale: The hardness of a rock is determined by comparing the scratch hardness of minerals on a Mohs hardness scale of 1-10. The specific steps are as follows: Use standard minerals on the Mohs hardness scale to scratch the surface of the rock and see if it can leave a scratch. Determine the Mohs hardness of the rock based on the hardest mineral that can leave a scratch and the softest mineral that cannot leave a scratch. The specific logic for obtaining the wind speed and humidity around the blasting point is: Select n representative measurement points around the blasting point, covering the four directions of southeast, northwest, and northwest, and select measurement points in equal quantities and distances in each direction according to the blasting range; Install the anemometer and hygrometer at the measurement point, making sure the equipment is level and calibrated; Record wind speed data and humidity data at different measurement points to obtain average wind speed and average humidity; The formula for obtaining the average wind speed is: in, is the average wind speed, v i represents the wind speed measured at the i-th measurement point; The formula for obtaining the average humidity is: in, is the average humidity, RH i represents the humidity measured at the i-th measurement point.

4. A rock blasting safety assessment method according to claim 1, characterized in that: The process of establishing a dynamic risk assessment model based on the support vector machine algorithm specifically includes: The blasting parameters of each time are used as training sets, and the blasting result parameters are used as labels; a machine learning model based on support vector machine is constructed, and the training set and labels are input into the machine learning model. The machine learning model is trained to obtain a trained dynamic risk assessment model.

5. A rock blasting safety assessment method according to claim 4, characterized in that: The support vector machine algorithm is used to build the model. The goal of the support vector machine is to find a hyperplane that can separate data points of different categories. The decision function can be expressed as: f(x)=w T x+b Among them, w T is the weight vector, x is the input feature vector, and b is the bias term; The training process is performed by optimizing the following objective function: in, is a regularization term that controls the complexity of the model, C is a penalty parameter that controls the trade-off between training error and model complexity, and δ i is a slack variable, representing the error of the i-th data point; the constraints are: y i (w T x i +b)≥1-δ i ,d i ≥0,i=1,2,…,N That is, each sample point (x i ,y i ) should be correctly classified with an error no greater than δ i ; In order to solve the above optimization problem, we introduce the Lagrange multiplier α i , and transform it into a dual problem: Among them, α i is the Lagrange multiplier, y i is the label of the i-th sample, x i is the feature vector of the i-th sample; the constraints are: To process nonlinearly separable data, the Gaussian kernel function is introduced to map the input space to a high-dimensional feature space. The formula is as follows: Among them, K(x i ,x j ) is the Gaussian kernel function, x i and x j are two eigenvectors in the input space, representing the vector x i and x j The square of the Euclidean distance between them, σ is the bandwidth parameter of the Gaussian kernel, which controls the width of the Gaussian function; The dual problem after introducing the kernel function is: By solving the above dual problem, we can get the Lagrange multiplier α i , the decision function of the support vector machine can be expressed as: 。 6. A rock blasting safety assessment method according to claim 1, characterized in that: Compare the comprehensive safety index QS with the preset safety threshold QY, including: When QS≤QY, it means that the safety threshold is not exceeded and the system is in a safe state. When QS>QY, it means that the safety threshold is exceeded, the system automatically issues an alarm, and relevant personnel handle it immediately.

7. A rock blasting safety assessment system, characterized by: The rock breaking blasting safety assessment system is used to execute a rock breaking blasting safety assessment method according to any one of claims 1 to 6, comprising: The data acquisition module collects blasting parameters and blasting result parameters of multiple historical blasting operations, wherein the blasting parameters include the detonation velocity and amount of explosives, and the blasting result parameters include rock fragmentation, vibration intensity and maximum flying rock distance, and collects geological data and environmental data of the blasting area, wherein the geological data includes rock hardness, and the environmental data includes wind speed and humidity around the blasting point; The model building module builds a dynamic risk assessment model based on the support vector machine algorithm, inputs the blasting parameters of historical blasting operations as training sets into the dynamic risk assessment model, and uses the blasting result parameters as labels to train the dynamic risk assessment model; The prediction module collects the blasting parameters of the rock-breaking blasting to be evaluated in real time, inputs the real-time collected blasting parameters into the trained dynamic risk assessment model, obtains the prediction parameters of the blasting results, and collects the geological data and environmental data of the rock-breaking blasting area to be evaluated, wherein the geological data is the rock hardness, and the environmental data includes the wind speed and humidity around the blasting point; The comprehensive assessment module uses the collected geological data and environmental data of the rock-breaking blasting area to correct the prediction parameters of the blasting results, obtain a comprehensive safety index, compare the comprehensive safety index with the safety threshold, and issue an early warning when the safety threshold is exceeded.

Images