A method and system for optimizing the static blasting process based on digital twin

Abstract

The present invention provides a method and system for optimizing the static blasting process based on digital twin, which relates to the technical field of blasting process optimization. The present invention obtains historical static blasting data, analyzes the data before blasting and during blasting to obtain the disturbance fluctuation characteristics and disturbance stress characteristics, analyzes the disturbance fluctuation characteristics and disturbance stress characteristics to obtain the disturbance fluctuation interference coefficient and disturbance stress interference coefficient, and analyzes the disturbance fluctuation interference coefficient and disturbance stress interference coefficient to obtain the blasting rockburst occurrence coefficient; establishes a blasting rockburst prediction model according to the data before blasting and the blasting rockburst occurrence coefficient, and uses the blasting rockburst prediction model to calculate the blasting rockburst occurrence coefficient; takes the maximum of the blasting rockburst occurrence coefficient as the optimization goal, uses the genetic algorithm to optimize the blasting setting data, and selects the group with the minimum blasting rockburst occurrence coefficient as the optimal blasting setting data; the digital twin platform previews the blasting effect.

Description

Technical Field

[0001] The present invention relates to the technical field of blasting process optimization, and specifically provides a method and system for optimizing the static blasting process based on digital twin. Background Art

[0002] Static blasting is a safe and efficient rock-breaking technology, which is widely used in mine exploitation, building demolition and engineering construction. However, the dynamic disturbances during the static blasting process may trigger the instability of the surrounding rock mass or even rock burst phenomenon, resulting in potential safety hazards and economic losses. In the existing technologies, the research on the disturbance fluctuation characteristics and stress characteristics caused by blasting is relatively scattered, and it is impossible to effectively quantify the influence of these disturbances on the stability of the rock mass. At the same time, the traditional blasting process optimization methods mostly rely on empirical design, lacking a comprehensive consideration of the complex mechanical properties of the rock mass in the blasting area, and the optimization results are not accurate enough to meet the requirements of high efficiency and safety. Therefore, how to effectively analyze the influence of dynamic disturbances on the rock mass during the blasting process and realize the optimization of the blasting process based on data driving has become a key problem to be solved urgently in the current technical field.

[0003] In the prior art, the published number CN118070670A discloses an intelligent optimization system for smooth blasting of tunnel drilling and blasting method based on digital twin, specifically including obtaining surrounding rock parameters, tunnel parameters, hole layout parameters and charging parameters; a parameter optimization module, importing the parameters and optimizing the construction process parameters; based on the optimized construction process parameters, constructing an explosive state model, a rock mass state model and an air and water medium state model to preview and verify the blasting effect of each blasting scheme; collecting the images of the crushed stones and the rock wall after blasting, detecting the particle size of the crushed stones and obtaining the overbreak and underbreak degree and the semi-hole retention degree as the reference indexes for evaluating the blasting quality, and evaluating the blasting effect. However, the prior art still has certain limitations. Its focus is mostly on the evaluation of the blasting effect, and the potential impact of blasting on the surrounding environment is not fully considered. This kind of neglect may lead to potential safety hazards and engineering losses, bringing risks to practical applications.

[0004] The above information disclosed in the background art section is only used to strengthen the understanding of the background of the present disclosure, so 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 optimizing the static blasting process based on digital twin 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 for optimizing the static blasting process based on digital twin, the specific steps include:

[0008] Step 1: Obtain historical static blasting data, where the static blasting data includes pre-blasting data and in-blasting data; the pre-blasting data includes lithology data and blasting setting data;

[0009] Step 2: Analyze the pre-blasting data and in-blasting data to obtain disturbance fluctuation characteristics and disturbance stress characteristics. Analyze the disturbance fluctuation characteristics to obtain a disturbance fluctuation interference coefficient, analyze the disturbance stress characteristics to obtain a disturbance stress interference coefficient, and analyze the disturbance fluctuation interference coefficient and the disturbance stress interference coefficient to obtain a blasting rockburst occurrence coefficient;

[0010] Step 3: Use the pre-blasting data as a training set and the blasting rockburst occurrence coefficient as a label to construct a blasting rockburst prediction model, and use the training set to train the blasting rockburst prediction model;

[0011] Step 4: Obtain the lithology data of the area to be blasted, and select a set of historical blasting setting data with the closest fracture toughness as the initial solution. With the minimum blasting rockburst occurrence coefficient as the optimization goal, use the genetic algorithm to optimize the blasting setting data, and select a set with the minimum blasting rockburst occurrence coefficient as the optimal blasting setting data;

[0012] Step 5: Construct a blasting rock model on the digital twin platform according to the lithology data and blasting setting data of the area to be blasted, and preview the blasting effect.

[0013] Furthermore, the lithology data includes the density, shear modulus, elastic modulus, Poisson's ratio, porosity, fracture toughness of the rock mass, and the static stress of the surrounding rock mass; the blasting setting data includes the borehole diameter, hole depth, hole spacing, the mixing ratio of the expansive agent and water, and the filling rate of the expansive agent; the in-blasting data includes the dynamic disturbance wave of the surrounding rock mass and the dynamic stress of the surrounding rock mass;

[0014] The density, shear modulus, elastic modulus, Poisson's ratio, porosity, and fracture toughness are measured by sending rock samples to the laboratory. Expand the static blasting area to three-fourths of the original. The non-static blasting area in the expanded area is defined as the surrounding area, and the rock mass in the surrounding area is the surrounding rock mass; the static stress and dynamic stress of the surrounding rock mass after blasting are obtained by stress sensors evenly arranged in the surrounding area; the dynamic disturbance wave of the surrounding rock mass is obtained by a geophone; stop collecting the dynamic disturbance wave and dynamic stress of the surrounding rock mass until the static blasting is completed or a rockburst phenomenon occurs.

[0015] Furthermore, the disturbance fluctuation characteristics include the rise-decay time difference, power spectral density, and spectral entropy, and the disturbance stress characteristics include the average static-dynamic stress difference and the average dynamic stress variance;

[0016] The specific logic for calculating the rise and decay time difference is as follows: separately count the time of each segment of the dynamic disturbance wave of the surrounding rock mass from the wave trough to the wave peak or from the wave peak to the wave trough, and record it as the rise and decay time; calculate the distribution variance of the rise and decay time, and record the distribution variance of the rise and decay time as the rise and decay time difference. The formula is:

[0017]

[0018] where XS is the rise and decay time difference, T i is the i-th rise and decay time, N is the total number of rise and decay times, and i is the index of the rise and decay time;

[0019] The logic for obtaining the power spectral density and spectral entropy is as follows: perform a Fourier transform on the dynamic disturbance wave of the surrounding rock mass to transform the dynamic disturbance wave of the surrounding rock mass into the form of the sum of a series of complex numbers, obtain the frequency spectrum of the dynamic disturbance wave of the surrounding rock mass, and analyze the frequency spectrum of the dynamic disturbance wave of the surrounding rock mass to obtain the power spectral density and spectral entropy. The formula is:

[0020]

[0021] where RX is the power spectral density of the dynamic disturbance wave of the surrounding rock mass, RB is the spectral entropy of the dynamic disturbance wave of the surrounding rock mass, X(k) is the frequency spectrum of the dynamic disturbance wave of the surrounding rock mass, and Re is the spectral energy; n is the total number of frequencies, and k is the frequency index;

[0022] The logic for obtaining the disturbance stress characteristics is as follows: calculate the average value of the dynamic stress collected by each stress sensor during the static blasting process, first subtract the average value of the above dynamic stress from the static stress, and then perform an absolute value operation to obtain the average dynamic and static stress difference; first perform an average value operation on the dynamic stress collected by each stress sensor during the static blasting process, and then calculate the variance of the average values of the dynamic stresses of all stress sensors to obtain the average dynamic stress variance. The formula is:

[0023]

[0024] where FY is the average dynamic and static stress difference, FPO is the average dynamic stress variance, FD l is the average dynamic stress of the l-th stress sensor, FD jl is the dynamic stress collected by the l-th stress sensor for the j-th time, FD 0l is the static stress of the l-th sensor, M is the total number of stress sensors, m is the number of acquisitions, l is the index of the stress sensor, and j is the index of the acquisition times.

[0025] Furthermore, the formula for generating the disturbance wave interference coefficient is:

[0026]

[0027] Among them, DFL is the disturbance fluctuation interference coefficient, XS is the rise and decay time difference, RX is the power spectral density of the dynamic disturbance wave of the surrounding rock mass, and RB is the spectral entropy of the dynamic disturbance wave of the surrounding rock mass;

[0028] The formula for generating the disturbance stress interference coefficient is:

[0029]

[0030] Among them, DFK is the disturbance stress interference coefficient, FY is the average static and dynamic stress difference, and FPO is the average dynamic stress variance.

[0031] Furthermore, by analyzing the disturbance fluctuation interference coefficient and the disturbance stress interference coefficient, the blasting rockburst occurrence coefficient is obtained; the formula for generating the blasting rockburst occurrence coefficient is:

[0032] YBF = DFL + DFK

[0033] Among them, YBF is the blasting rockburst occurrence coefficient, DFL is the disturbance fluctuation interference coefficient, and DFK is the disturbance stress interference coefficient.

[0034] The present invention further provides a static blasting process optimization system based on digital twin. The system is used to implement the static blasting process optimization method based on digital twin, and specifically includes:

[0035] A data acquisition module for acquiring historical static blasting data. The static blasting data includes pre-blasting data and in-blasting data; the pre-blasting data includes lithology data and blasting setting data;

[0036] A comprehensive analysis module for analyzing the pre-blasting data and the in-blasting data to obtain the disturbance fluctuation characteristics and the disturbance stress characteristics, analyzing the disturbance fluctuation characteristics to obtain the disturbance fluctuation interference coefficient, analyzing the disturbance stress characteristics to obtain the disturbance stress interference coefficient, and analyzing the disturbance fluctuation interference coefficient and the disturbance stress interference coefficient to obtain the blasting rockburst occurrence coefficient;

[0037] A model construction module for constructing a blasting rockburst prediction model with the pre-blasting data as the training set and the blasting rockburst occurrence coefficient as the label, and training the blasting rockburst prediction model with the training set;

[0038] A data optimization module for acquiring the lithology data of the area to be blasted, selecting a set of historical blasting setting data with the closest fracture toughness as the initial solution, taking the minimum blasting rockburst occurrence coefficient as the optimization target, and using the genetic algorithm to optimize the blasting setting data, and selecting a set with the minimum blasting rockburst occurrence coefficient as the optimal blasting setting data;

[0039] A digital twin module is used to construct a blasting rock model on a digital twin platform based on the lithology data and blasting setting data of the area to be blasted, and preview the blasting effect.

[0040] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0041] According to the present invention, by finely quantifying and predicting the disturbance wave and disturbance stress characteristics in the whole process of blasting, the design of blasting parameters is optimized, which not only significantly improves the blasting efficiency and reduces the risk of rockburst, but also fully considers the potential impact of blasting on the surrounding environment. Through preview and simulation verification, double guarantees of safety and benefit are achieved, thus effectively avoiding potential safety hazards and engineering losses. Description of the Drawings

[0042] Figure 1 It is a schematic diagram of the overall method flow of the present invention.

[0043] Figure 2 It is a schematic diagram of the overall system structure of the present invention. Detailed Embodiments

[0044] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with specific embodiments.

[0045] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those with ordinary skills in the field to which the present invention belongs. The "first", "second", and similar terms used in the present invention do not represent any order, quantity, or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "linked" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right", etc. are only used to represent relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0046] Embodiment:

[0047] Please refer to Figure 1 , the present invention provides a technical solution:

[0048] An optimization method for static blasting technology based on digital twin, the specific steps include:

[0049] Step 1: Obtain historical static blasting data, where the static blasting data includes pre-blasting data and in-blasting data; the pre-blasting data includes lithology data and blasting setting data;

[0050] Further, the lithology data includes the density, shear modulus, elastic modulus, Poisson's ratio, porosity, fracture toughness of the rock mass, and the static stress of the surrounding rock mass; the blasting setting data includes the borehole diameter, hole depth, hole spacing, the mixing ratio of the expansive agent and water, and the filling rate of the expansive agent; the data during blasting includes the dynamic disturbance wave of the surrounding rock mass and the dynamic stress of the surrounding rock mass;

[0051] The density, shear modulus, elastic modulus, Poisson's ratio, porosity, and fracture toughness are determined by sending rock samples to the laboratory. The static blasting area is expanded to three - fourths of the original. The non - static - blasting area in the expanded area is defined as the surrounding area, and the rock mass in the surrounding area is the surrounding rock mass. The static stress and dynamic stress of the surrounding rock mass are obtained through stress sensors evenly arranged in the surrounding area. The dynamic disturbance wave of the surrounding rock mass is obtained through geophones. The acquisition of the dynamic disturbance wave and dynamic stress of the surrounding rock mass ends until the static blasting is completed or a rockburst phenomenon occurs.

[0052] Step 2: Analyze the data before blasting and the data during blasting to obtain the disturbance wave characteristics and disturbance stress characteristics. Analyze the disturbance wave characteristics to obtain the disturbance wave interference coefficient, analyze the disturbance stress characteristics to obtain the disturbance stress interference coefficient, and analyze the disturbance wave interference coefficient and the disturbance stress interference coefficient to obtain the blasting rockburst occurrence coefficient;

[0053] The disturbance wave characteristics include the rise - decay time difference, power spectral density, and spectral entropy. The disturbance stress characteristics include the average static - dynamic stress difference and the average dynamic stress variance;

[0054] The specific logic for calculating the rise - decay time difference is as follows: respectively count the time for each segment of the dynamic disturbance wave of the surrounding rock mass from the wave trough to the wave peak or from the wave peak to the wave trough, and record it as the rise - decay time. Calculate the distribution variance of the rise - decay time, and record the distribution variance of the rise - decay time as the rise - decay time difference. The formula is:

[0055]

[0056] where XS is the rise - decay time difference, T i is the i - th rise - decay time, N is the total number of rise - decay times, and i is the index of the rise - decay time. The rise - decay time difference reflects the distribution consistency of the rise - decay time in the dynamic disturbance wave of the surrounding rock mass. The smaller its value, the stronger the distribution consistency of the rise - decay time in the dynamic disturbance wave of the surrounding rock mass.

[0057] The logic for obtaining the power spectral density and spectral entropy is as follows: perform a Fourier transform on the dynamic disturbance wave of the surrounding rock mass to transform the dynamic disturbance wave of the surrounding rock mass into the form of the sum of a series of complex numbers, obtain the frequency spectrum of the dynamic disturbance wave of the surrounding rock mass, and analyze the frequency spectrum of the dynamic disturbance wave of the surrounding rock mass to obtain the power spectral density and spectral entropy. The formula is:

[0058]

[0059] Among them, RX is the power spectral density of the dynamic disturbance wave of the surrounding rock mass, RB is the spectral entropy of the dynamic disturbance wave of the surrounding rock mass, X(k) is the spectrum of the dynamic disturbance wave of the surrounding rock mass, and Re is the spectral energy; n is the total number of frequencies, k is the frequency index. The power spectral density of the dynamic disturbance wave of the surrounding rock mass reflects the energy concentration of the dynamic disturbance wave of the surrounding rock mass. The larger the value, the more concentrated the energy of the dynamic disturbance wave of the surrounding rock mass, and the easier it is to cause rockburst phenomena; the spectral entropy represents the degree of uniformity of the energy distribution in the spectrum, which reflects the complexity or disorder of the dynamic disturbance wave of the surrounding rock mass in the frequency domain. The larger its value, the more uniform the energy is distributed in the spectrum, the signal contains more frequency components, indicating that the disturbance is more complex and the randomness is greater; it is easier to cause rockburst phenomena.

[0060] The logic for obtaining the disturbance stress characteristics is as follows: Calculate the average value of the dynamic stress collected by each stress sensor during the static blasting process. First, subtract the average value of the above dynamic stress from the static stress, and then perform an absolute value operation to obtain the average dynamic-static stress difference; first, perform an average value operation on the dynamic stress collected by each stress sensor during the static blasting process, and then calculate the variance of the average values of the dynamic stresses of all stress sensors to obtain the average dynamic stress variance; the formula is:

[0061]

[0062] Among them, FY is the average dynamic-static stress difference, FPO is the average dynamic stress variance, FD l is the average dynamic stress of the l-th stress sensor, FD jl is the dynamic stress collected by the l-th stress sensor for the j-th time, FD 0l is the static stress of the l-th sensor, M is the total number of stress sensors, m is the number of acquisitions, l is the stress sensor index, and j is the acquisition number index.

[0063] The average dynamic-static stress difference measures the overall difference between the dynamic stress generated during blasting and the static stress before blasting. The comparison between the static stress and the dynamic stress can reveal the degree of disturbance of the blasting process to the rock mass. The larger its value, the greater the overall difference and the degree of disturbance, and the easier it is to cause rockburst phenomena; the average dynamic stress variance reflects the fluctuation degree of the average value of the dynamic stress of each sensor relative to the overall average value. If FPO is large, it means that the distribution of the dynamic stresses of different sensors is uneven, indicating that the disturbance intensity difference of the blasting to different positions of the rock mass is large, and it is easier to cause rockburst phenomena.

[0064] Furthermore, the formula for generating the disturbance fluctuation interference coefficient is:

[0065]

[0066] Among them, DFL is the disturbance fluctuation interference coefficient, XS is the rise-decay time difference, RX is the power spectral density of the dynamic disturbance wave of the surrounding rock mass, and RB is the spectral entropy of the dynamic disturbance wave of the surrounding rock mass; the disturbance fluctuation interference coefficient reflects the degree of influence of the dynamic disturbance wave on the rock mass. The larger its value, the greater the degree of influence of the dynamic disturbance wave on the rock mass, and the more likely the rock mass is to have a rockburst phenomenon. The generation of this coefficient can provide an important basis for judging whether a rockburst phenomenon will occur during the static blasting process and can also provide an important basis for optimizing the process parameters of static blasting.

[0067] The rise-decay time difference reflects the distribution consistency of the rise-decay time in the dynamic disturbance wave of the surrounding rock mass. The smaller its value, the stronger the distribution consistency of the rise-decay time in the dynamic disturbance wave of the surrounding rock mass, the more regular the disturbance signal, and the lower the probability of triggering a rockburst phenomenon. The power spectral density of the dynamic disturbance wave of the surrounding rock mass reflects the energy concentration of the dynamic disturbance wave of the surrounding rock mass. The larger the value, the more concentrated the energy of the dynamic disturbance wave of the surrounding rock mass, and the more likely it is to cause a rockburst phenomenon. The spectral entropy represents the degree of uniformity of the energy distribution in the spectrum, which reflects the complexity or disorder of the dynamic disturbance wave of the surrounding rock mass in the frequency domain. The larger its value, the more evenly the energy is distributed in the spectrum, the signal contains more frequency components, indicating that the disturbance is more complex and random, and it is more likely to cause a rockburst phenomenon. Among them, XS and RB reflect the regularity degree of the dynamic disturbance wave from different levels, so they are coupled by multiplication. There is usually a natural physical phenomenon in dynamic disturbance signals (such as the dynamic disturbance wave of the surrounding rock mass): when the energy intensity, complexity or asymmetry of the disturbance wave increases, its interference effect on the system will increase rapidly; on the contrary, when these characteristics are weak, the interference effect will decrease sharply. The exponential form can just capture this non-linear response characteristic well, so the invention adopts to represent the disturbance fluctuation interference coefficient.

[0068] The formula for generating the disturbance stress interference coefficient is:

[0069]

[0070] Among them, DFK is the disturbance stress interference coefficient, FY is the average dynamic-static stress difference, and FPO is the average dynamic stress variance. The disturbance stress interference coefficient is used to quantify the comprehensive influence degree of the rock mass subjected to stress disturbance. The smaller the value, the greater the interference of the stress disturbance on the rock mass, and the easier it is to trigger the rock burst phenomenon. The average dynamic-static stress difference measures the overall difference between the dynamic stress generated during blasting and the static stress before blasting. The comparison between the static stress and the dynamic stress can reveal the disturbance degree of the blasting process on the rock mass. The larger its value, the greater the overall difference and the disturbance degree, and the easier it is to lead to the rock burst phenomenon; the average dynamic stress variance reflects the fluctuation degree of the average dynamic stress of each sensor relative to the overall average value. If FPO is large, it means that the dynamic stress distribution of different sensors is uneven, indicating that the disturbance intensity of blasting on different positions of the rock mass is quite different, and it is easier to lead to the rock burst phenomenon. FPO describes the uneven distribution of dynamic stress among different sensors. If FPO is large, it means that the distribution of dynamic stress shows significant fluctuations in space, and the stress differences at different positions are large. The exponential form e FPO gives the FPO a non-linear amplification effect: when the volatility DFK of the dynamic stress increases, the disturbance effect will be more significant, so DFK will decrease rapidly.

[0071] Furthermore, by analyzing the disturbance fluctuation interference coefficient and the disturbance stress interference coefficient, the blasting rock burst occurrence coefficient is obtained; the formula for generating the blasting rock burst occurrence coefficient is:

[0072] YBF = DFL + DFK

[0073] Among them, YBF is the blasting rock burst occurrence coefficient, DFL is the disturbance fluctuation interference coefficient, and DFK is the disturbance stress interference coefficient.

[0074] The blasting rock burst occurrence coefficient reflects the influence degree of the dynamic disturbance and stress disturbance generated by static blasting on the occurrence of rock burst in the surrounding rock mass. The larger its value, the easier it is to occur the rock burst phenomenon. The disturbance fluctuation interference coefficient reflects the influence degree of the dynamic disturbance wave on the rock mass. When DFL is large, it indicates that the disturbance wave generated by blasting has a high intensity, complexity or asymmetry, and the interference effect on the rock mass increases significantly, which will cause the expansion of microcracks inside the rock mass and the redistribution of stress, and may ultimately trigger the instantaneous failure of the rock mass; the disturbance stress interference coefficient is used to quantify the comprehensive influence degree of the rock mass subjected to stress disturbance, specifically including indicating the strong change of the blasting disturbance on the static stress field of the rock mass (average dynamic-static stress difference) and the uneven distribution of the dynamic stress of the rock mass, resulting in a higher disturbance load on the surrounding rock mass (average dynamic stress variance). The strong stress disturbance may lead to local stress concentration in the rock mass, reaching the fracture condition, thus triggering the rock burst.

[0075] Step 3: Using the data before blasting as the training set and the coefficient of rockburst occurrence during blasting as the label, construct a blasting rockburst prediction model, and use the training set to train the blasting rockburst prediction model;

[0076] The blasting rockburst prediction model adopts a feedforward neural network. Using the coefficient of rockburst occurrence during blasting as the label, the blasting rockburst prediction model is trained and optimized with the training set. Specifically, it includes an input layer, a hidden layer, an output layer, and an activation function. The input layer is responsible for receiving the data of the training set; the hidden layer is used to process the data of the training set; it consists of multiple layers, each layer contains 4 time nodes, and the time nodes of each hidden layer are connected to the previous layer through weights, which are used for feature abstraction and non-linear transformation of the input training set; by using the ReLu activation function, a non-linear relationship is introduced so that the model can fit complex feature relationships; an independent neuron is set in the output layer, which is responsible for converting the local and high-level feature representations extracted by the hidden layer for outputting the coefficient of rockburst occurrence during blasting; the root mean square error loss function is adopted; the input data is calculated through the network once to obtain the output result, the loss function is calculated according to the predicted value and the true value, the gradient of the loss function with respect to each weight and bias is calculated through the chain rule, and the gradient descent algorithm is used to update the weights and biases of the network to minimize the loss function.

[0077] Step 4: Obtain the lithology data of the area to be blasted, select a set of historical blasting setting data with the closest fracture toughness as the initial solution, take the minimum coefficient of rockburst occurrence during blasting as the optimization goal, use the genetic algorithm to optimize the blasting setting data, and select a set with the minimum coefficient of rockburst occurrence during blasting as the optimal blasting setting data;

[0078] The genetic algorithm can optimize the blasting setting data by using the existing technology. Specifically, it includes: obtaining the lithology data of the area to be blasted, selecting a set of historical blasting setting data with the closest fracture toughness as the initial solution according to the fracture toughness, and constructing an initial population containing multiple sets of blasting setting data. Taking the calculated value of the coefficient of rockburst occurrence during blasting as the optimization goal, setting it as a minimization problem, and iteratively generating a new population through the selection, crossover, and mutation operations of the genetic algorithm. In each generation, the individuals of the population are screened according to the magnitude of the coefficient of rockburst occurrence during blasting, and the blasting parameters are continuously optimized until the preset convergence condition or the maximum number of iterations is reached. Finally, a set of blasting parameters that minimizes the coefficient of rockburst occurrence during blasting is selected as the optimal solution;

[0079] Step 5: Construct a blasting rock model on the digital twin platform according to the lithology data and blasting setting data of the area to be blasted, and preview the blasting effect.

[0080] The present invention further provides a static blasting process optimization system based on digital twin. The system is used to implement the static blasting process optimization method based on digital twin, and specifically includes:

[0081] A data acquisition module for acquiring historical static blasting data, where the static blasting data includes pre-blasting data and in-blasting data; the pre-blasting data includes lithology data and blasting setting data;

[0082] A comprehensive analysis module for analyzing the pre-blasting data and in-blasting data to obtain disturbance fluctuation characteristics and disturbance stress characteristics, analyzing the disturbance fluctuation characteristics to obtain a disturbance fluctuation interference coefficient, analyzing the disturbance stress characteristics to obtain a disturbance stress interference coefficient, and analyzing the disturbance fluctuation interference coefficient and the disturbance stress interference coefficient to obtain a blasting rockburst occurrence coefficient;

[0083] A model construction module for constructing a blasting rockburst prediction model with the pre-blasting data as the training set and the blasting rockburst occurrence coefficient as the label, and training the blasting rockburst prediction model using the training set;

[0084] A data optimization module for obtaining the lithology data of the area to be blasted, selecting a set of historical blasting setting data with the closest fracture toughness as the initial solution, taking the minimum blasting rockburst occurrence coefficient as the optimization goal, and using the genetic algorithm to optimize the blasting setting data, and selecting a set with the minimum blasting rockburst occurrence coefficient as the optimal blasting setting data;

[0085] A digital twin module for constructing a blasting rock model on the digital twin platform according to the lithology data and blasting setting data of the area to be blasted, and previewing the blasting effect.

[0086] The above formulas are all dimensionless and take their numerical values for calculation. 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.

[0087] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. 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 can realize that the units and algorithm steps of each example described in combination 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.

[0088] 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 can 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.

[0089] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application should cover any changes or substitutions that can be easily thought of within the protection scope of the present application.

Claims

1. An optimization method for static blasting process based on digital twin, characterized in that, The specific steps include: Step 1: Obtain historical static blasting data, where the static blasting data includes pre-blasting data and in-blasting data; the pre-blasting data includes lithology data and blasting setting data; Step 2: Analyze the pre-blasting data and in-blasting data to obtain disturbance fluctuation characteristics and disturbance stress characteristics, analyze the disturbance fluctuation characteristics to obtain a disturbance fluctuation interference coefficient, analyze the disturbance stress characteristics to obtain a disturbance stress interference coefficient, and analyze the disturbance fluctuation interference coefficient and the disturbance stress interference coefficient to obtain a blasting rockburst occurrence coefficient; Step 3: Use the pre-blasting data as input and the blasting rockburst occurrence coefficient as a label to construct a blasting rockburst prediction model. Use the pre-blasting data in the historical static blasting data to form a training set, and use the training set to train the blasting rockburst prediction model; Step 4: Obtain the lithology data of the area to be blasted, and select a set of historical blasting setting data with the closest fracture toughness as the initial solution. With the minimum blasting rockburst occurrence coefficient as the optimization goal, use the genetic algorithm to optimize the blasting setting data, and select a set with the minimum blasting rockburst occurrence coefficient as the optimal blasting setting data; Step 5: Construct a blasting rock model on the digital twin platform based on the lithology data and blasting setting data of the area to be blasted, and preview the blasting effect; The disturbance fluctuation characteristics include rise-decay time difference, power spectral density, and spectral entropy, and the disturbance stress characteristics include average dynamic-static stress difference and average dynamic stress variance; The logic for calculating the rise-decay time difference is: separately count the time of each segment of the dynamic disturbance wave of the surrounding rock mass from the wave valley to the wave peak or from the wave peak to the wave valley, and record it as the rise-decay time; calculate the distribution variance of the rise-decay time, and record the distribution variance of the rise-decay time as the rise-decay time difference. The formula is: Among them, XS is the rise and decay time difference, T i is the i-th rise and decay time, N is the total number of rise and decay times, and i is the index of the rise and decay time; The logic for obtaining the disturbance stress characteristics is: calculate the average value of the dynamic stress collected by each stress sensor during the static blasting process, first subtract the static stress from the average value of the above dynamic stress, and then take the absolute value operation to obtain the average dynamic-static stress difference; first take the average value operation on the dynamic stress collected by each stress sensor during the static blasting process, and then calculate the variance of the average value of the dynamic stress of all stress sensors to obtain the average dynamic stress variance; the formula is: Among them, FY is the average dynamic and static stress difference, FPO is the average dynamic stress variance, and FD l is the average dynamic stress of the l-th stress sensor, and FD jl is the dynamic stress collected by the l-th stress sensor for the j-th time, and FD 0l is the static stress of the l-th sensor, M is the total number of stress sensors, m is the number of acquisitions, l is the stress sensor index, and j is the acquisition number index; The formula for generating the disturbance fluctuation interference coefficient is: where DFL is the disturbance fluctuation interference coefficient, RX is the power spectral density of the dynamic disturbance wave of the surrounding rock mass, and RB is the spectral entropy of the dynamic disturbance wave of the surrounding rock mass; The formula for generating the disturbance stress interference coefficient is: where DFK is the disturbance stress interference coefficient.

2. The optimized method for static blasting process based on digital twin according to claim 1, characterized in that: The lithology data includes the density, shear modulus, elastic modulus, Poisson's ratio, porosity, fracture toughness of the rock mass, and the static stress of the surrounding rock mass; the blasting setting data includes the borehole diameter, hole depth, hole spacing, mixing ratio of the expansive agent and water, and filling rate of the expansive agent; the in-blasting data includes the dynamic disturbance wave of the surrounding rock mass and the dynamic stress of the surrounding rock mass; The density, shear modulus, elastic modulus, Poisson's ratio, porosity, and fracture toughness are obtained by sending rock samples to a laboratory for measurement. The static blasting area is expanded to four-thirds of the original, and the non-static blasting area in the expanded area is defined as the surrounding area, and the rock mass in the surrounding area is the surrounding rock mass. The static stress and dynamic stress of the surrounding rock mass are obtained by stress sensors evenly arranged in the surrounding area. The dynamic disturbance wave of the surrounding rock mass is obtained by a geophone. The acquisition of the dynamic disturbance wave and dynamic stress of the surrounding rock mass is terminated until the static blasting is completed or a rock burst phenomenon occurs.

3. The optimized method for static blasting process based on digital twin according to claim 2, characterized in that: The logic for obtaining the power spectral density and spectral entropy is as follows: Perform a Fourier transform on the dynamic disturbance wave of the surrounding rock mass to transform the dynamic disturbance wave of the surrounding rock mass into the form of the sum of a series of complex numbers, obtain the spectrum of the dynamic disturbance wave of the surrounding rock mass, and analyze the spectrum of the dynamic disturbance wave of the surrounding rock mass to obtain the power spectral density and spectral entropy. The formula is: where RX is the power spectral density of the dynamic disturbance wave of the surrounding rock mass, RB is the spectral entropy of the dynamic disturbance wave of the surrounding rock mass, X(k) is the spectrum of the dynamic disturbance wave of the surrounding rock mass, Re is the spectral energy; n is the total number of frequencies, and k is the frequency index.

4. The method for optimizing the static blasting process based on digital twin according to claim 1, wherein: Analyze the disturbance wave interference coefficient and the disturbance stress interference coefficient to obtain the blasting rock burst occurrence coefficient. The formula for generating the blasting rock burst occurrence coefficient is: YBF = DFL + DFK where YBF is the blasting rock burst occurrence coefficient, DFL is the disturbance wave interference coefficient, and DFK is the disturbance stress interference coefficient.

5. A static blasting process optimization system based on digital twin, characterized in that: The system is used to implement the static blasting process optimization method based on digital twin described in any one of claims 1-4, specifically including: A data acquisition module, used to acquire historical static blasting data, and the static blasting data includes pre-blasting data and in-blasting data; the pre-blasting data includes lithology data and blasting setting data; A comprehensive analysis module, used to analyze the pre-blasting data and in-blasting data to obtain the disturbance wave characteristics and disturbance stress characteristics, analyze the disturbance wave characteristics to obtain the disturbance wave interference coefficient, analyze the disturbance stress characteristics to obtain the disturbance stress interference coefficient, and analyze the disturbance wave interference coefficient and the disturbance stress interference coefficient to obtain the blasting rock burst occurrence coefficient; A model construction module, used to construct a blasting rock burst prediction model with the pre-blasting data as the training set and the blasting rock burst occurrence coefficient as the label, and use the training set to train the blasting rock burst prediction model; A data optimization module, used to acquire the lithology data of the area to be blasted, select a set of historical blasting setting data with the closest fracture toughness as the initial solution, take the minimum blasting rock burst occurrence coefficient as the optimization goal, use the genetic algorithm to optimize the blasting setting data, and select a set with the minimum blasting rock burst occurrence coefficient as the optimal blasting setting data; A digital twin module, used to construct a blasting rock model on the digital twin platform according to the lithology data and blasting setting data of the area to be blasted, and preview the blasting effect.

Images