A blasting construction precision control method and system

Abstract

The present application relates to the technical field of blasting control, in particular to a kind of blasting construction precision control method and system, wherein the method comprises the following steps: obtaining blasting vibration peak speed measured data;Build blasting vibration peak prediction neural network, combined with blasting vibration peak speed measured data and blasting vibration peak prediction neural network, obtain the initial weight and initial threshold of blasting vibration peak prediction neural network, and update blasting vibration peak prediction neural network;Through blasting vibration peak speed measured data, obtain blasting vibration peak prediction neural network training set and blasting vibration peak prediction neural network verification set, train and verify updated blasting vibration peak prediction neural network;Using trained blasting vibration peak prediction neural network, complete blasting vibration peak speed prediction.The present application predicts the blasting vibration peak speed, reflects the propagation law of blasting vibration, solves the problem of accurately and efficiently controlling blasting construction.

Description

Technical Field

[0001] This invention relates to the field of blasting control technology, specifically to a precise control method and system for blasting operations. Background Technology

[0002] With the rapid development of my country's economy, blasting operations are widely used in various engineering projects such as mining, tunnel excavation, building demolition, and site leveling due to their speed and efficiency. However, blasting operations also generate a series of negative impacts, such as blast shock waves, flying rocks, blasting vibrations, dust, and harmful gases. Before blasting operations, it is necessary to accurately predict the peak velocity of blasting vibrations to ensure a reasonable blasting scheme design and achieve the goal of safe construction.

[0003] The research scope of blasting vibration is quite broad, involving the intersection of multiple disciplines and fields, such as rock mechanics, vibration wave propagation modes, spectral analysis of blasting vibration signals, and many other theoretical aspects. Scholars and researchers from various countries have conducted extensive work in this field using methods such as blasting vibration experiments, theoretical derivation and analysis, and blasting vibration signal analysis. In my country, the Sadovsky empirical formula is commonly used to predict blasting vibration. Although it has high universality, the prediction results vary depending on the actual blasting project. Furthermore, by predicting the peak velocity of blasting vibration, the blasting operation can be judged. The ability to accurately predict peak blasting vibration velocity is crucial for ensuring the safe conduct of blasting operations. Predicting the potential threat to the surrounding environment and facilities allows for the implementation of appropriate measures to minimize or avoid damage. Furthermore, monitoring and analyzing peak blasting velocity helps understand the effectiveness of the blasting operation, enabling adjustments and optimization of blasting parameters to improve efficiency and quality. Finally, based on the predicted peak blasting velocity, optimized blasting plans can be developed to reduce the impact of vibration on the surrounding environment and strengthen vibration protection measures, ensuring the safe and smooth execution of blasting operations. Therefore, accurately and efficiently predicting peak blasting vibration velocity is a critical issue that needs to be addressed to precisely control the blasting effect. Summary of the Invention

[0004] To address the shortcomings of existing methods and the demands of practical applications, and to improve the ability to precisely control the effect of blasting operations and solve the problem of accurately and efficiently predicting the peak velocity of blasting vibrations, this invention provides a method for precise control of blasting operations. This method includes the following steps: acquiring measured data of the peak velocity of blasting vibrations; constructing a peak velocity prediction neural network; combining the measured peak velocity data and the neural network to obtain initial weights and initial thresholds for the neural network; updating the neural network using these initial weights and thresholds; obtaining a training set and a validation set for the neural network using the measured peak velocity data; training and validating the updated neural network using these sets; and finally, using the trained neural network to predict the peak velocity of blasting vibrations. This invention, by predicting the peak velocity of blasting vibrations, reflects the propagation law of blasting vibrations, solves the problem of accurately and efficiently controlling blasting operations, and provides a reliable basis for safe blasting.

[0005] Optionally, the precise control method for blasting construction further includes the following steps: preprocessing the measured peak velocity data of the blasting vibration; the preprocessing of the measured peak velocity data of the blasting vibration satisfies the following formula: Where F(x) represents the improved wavelet threshold function, x represents the original wavelet coefficients, |·| represents the absolute value function, j represents the wavelet decomposition level, and α j The adaptive threshold represents the number of wavelet decomposition levels for wavelet j. σ j N represents the standard deviation of the noise at layer j. j This represents the number of wavelet coefficients in the j-th layer. This invention improves the accuracy of subsequent processing results obtained from the measured data by preprocessing the peak velocity data of blasting vibrations.

[0006] Optionally, the step of combining the measured peak velocity data of blasting vibration and the peak velocity prediction neural network to obtain the initial weights and initial thresholds of the blasting vibration prediction neural network includes the following steps: forming an initial population using the weights and thresholds of the blasting vibration prediction neural network as individuals; evaluating the individuals to obtain their fitness; performing a first adjustment and a second adjustment on the individuals based on their fitness to obtain a new population; evaluating the individuals in the new population until the iteration stopping condition is met to obtain the initial weights and initial thresholds of the blasting vibration prediction neural network. The initial weights and initial thresholds of the blasting vibration prediction neural network obtained through the steps of this invention accelerate the training speed of the blasting vibration prediction neural network, improve the training effect of the blasting vibration prediction neural network, and solve the problem of neural networks easily forming local optima.

[0007] Optionally, a first adjustment is performed on the individual, satisfying the following formula: in, X represents the individual position after the first adjustment is performed on the individual in the (t+1)th iteration. t Let λ represent the position of an individual in the t-th iteration, T represent the maximum number of iterations, λ represent a random number in the range (0,1), and ω represent the position of an individual in the range (t-th iteration). t Let P represent the weight coefficient of an individual in the t-th iteration, c1 represent the first learning factor, λ1 and λ2 represent random numbers in the range [0,1], c2 represent the second learning factor, and P... t G represents the historical best position of an individual in the t-th iteration. t This represents the historical optimal position of the group at the t-th iteration. The first adjustment in this invention adjusts the impact of the previous iteration based on the number of iterations, expanding the search range in the early stage of iteration and optimizing the search speed in the later stage of iteration, effectively solving the problem of neural networks easily forming local optima.

[0008] Optionally, the weighting coefficients satisfy the following formula: Where, ω t ω represents the weight coefficient of an individual in the t-th iteration. min ω represents the minimum weight threshold. max f represents the maximum weight threshold. t This represents the fitness of an individual at the t-th iteration. This represents the minimum fitness value of an individual at the t-th iteration. Let represent the average fitness of an individual at the t-th iteration. N represents the number of individuals. This represents the fitness of the i-th individual at the t-th iteration. By setting piecewise weight coefficients, this invention avoids premature convergence of the neural network, which leads to inaccurate training and poor predictive ability. It ensures a larger population search space in the early stages, facilitating global search, and enables refined local search tasks in later stages, further improving the computational efficiency and accuracy of this invention.

[0009] Optionally, the first learning factor satisfies the following formula: Where c1 represents the first learning factor, This represents the initial value of the first learning factor. The first learning factor represents the end value, t represents the current iteration number, and T represents the maximum iteration number; the second learning factor satisfies the following formula: Where c2 represents the second learning factor, This represents the initial value of the second learning factor. This indicates the end value of the second learning factor. This invention sets a first learning factor to influence local search capability and a second learning factor to influence global search capability, further satisfying the requirement of high global search capability in the early stages and low search capability in the later stages.

[0010] Optionally, a second adjustment is performed on the individual, satisfying the following formula: in, X represents the individual position after the second adjustment is performed on the individual in the (t+1)th iteration. t Let G represent the position of an individual in the t-th iteration, β represent the step size of the individual, and G... t f represents the historical optimal position of the population at the t-th iteration. t This represents the fitness of an individual at the t-th iteration. Let ||t|| represent the minimum fitness value of an individual at the t-th iteration, and ||·|| represent the Euclidean distance. This invention, through a second adjustment, further refines the search optimization range, thereby improving the accuracy of the invention.

[0011] Optionally, the evaluation of the individual to obtain the fitness of the individual satisfies the following formula: Where f represents individual fitness, n represents the sample size, and x i Let x represent the measured value of the i-th sample. avg Represents the sample mean. This represents the predicted value of the i-th sample. The fitness obtained through this invention can effectively and accurately evaluate all individuals, and its calculation method is simple, further ensuring the accuracy and efficiency of the final optimization result.

[0012] Optionally, constructing the peak blasting vibration prediction neural network includes the following steps: determining the topology of the peak blasting vibration prediction neural network through trial and error; setting the input layer activation function, hidden layer activation function, output layer activation function, training function, and learning rate of the peak blasting vibration prediction neural network. The peak blasting vibration prediction neural network constructed by this invention has a simple structure, is easy to set up, is practical, convenient, and runs quickly, further improving the prediction efficiency of this invention.

[0013] Secondly, to efficiently execute the precise control method for blasting construction provided by this invention, this invention also provides a precise control system for blasting construction, including a processor, an input device, an output device, and a memory. The processor, input device, output device, and memory are interconnected. The memory stores a computer program containing program instructions. The processor is configured to call the program instructions to execute the precise control method for blasting construction as described in the first aspect of this invention. The precise control system for blasting construction of this invention has a compact structure and stable performance, and can stably execute the precise control method for blasting construction provided by this invention, further enhancing the overall applicability and practical application capability of this invention. Attached Figure Description

[0014] Figure 1 This is a flowchart of a precise control method for blasting construction according to the present invention;

[0015] Figure 2 This is a framework diagram of a precision control system for blasting operations according to the present invention;

[0016] Figure 3 This is a schematic diagram of a precision control device for blasting operations provided as an example. Detailed Implementation

[0017] Specific embodiments of the present invention will now be described in detail. It should be noted that the embodiments described herein are for illustrative purposes only and are not intended to limit the invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be apparent to those skilled in the art that these specific details are not necessary to practice the invention. In other instances, well-known circuits, software, or methods have not been specifically described to avoid obscuring the invention.

[0018] Throughout this specification, references to "an embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with that embodiment or example is included in at least one embodiment of the invention. Therefore, the phrases "in an embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily refer to the same embodiment or example. Furthermore, specific features, structures, or characteristics can be combined in one or more embodiments or examples in any suitable combination and / or sub-combination. Moreover, those skilled in the art will understand that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale.

[0019] Please see Figure 1 , Figure 1 This is a flowchart of a precise control method for blasting construction according to the present invention. To improve the ability to precisely control the effect of blasting construction and solve the problem of accurately and efficiently predicting the peak velocity of blasting vibration, the present invention provides a precise control method for blasting construction, such as... Figure 1 As shown, the method includes the following steps:

[0020] S1. Obtain the measured peak velocity data of the blasting vibration.

[0021] In one embodiment, step S1 involves acquiring measured peak velocity data of blasting vibration by using a blasting vibration meter to monitor the peak velocity of blasting vibration in three directions: horizontal radial, horizontal tangential, and vertical, to obtain blasting vibration waveforms under different blasting parameters. After the blasting is completed, the collected data is organized and imported into a computer for data storage.

[0022] It should be understood that the location of monitoring points during blasting vibration monitoring has a crucial impact on the monitoring results. Only by selecting and recording reasonable coordinate positions can monitoring data relevant to the research objective be obtained. In this embodiment, the principles for arranging the blasting vibration meter are as follows: First, monitoring personnel should be within a safe zone, and the instrument should be placed in the optimal location to prevent it from being buried by blast piles from other blasting areas. Second, after the blasting vibration meter is installed and begins data collection, it should be kept as free from interference as possible to ensure monitoring effectiveness and the accuracy and authenticity of the data. Finally, the blasting vibration meter should be arranged at appropriate distances, and the coordinates of the arranged monitoring points should be recorded using a GPS positioning system to obtain accurate blast center distances.

[0023] In the embodiment, the measured peak velocity data of blasting vibration in step S1 includes the distance from the blast center, vertical height, number of blast holes, row spacing between blast holes, blast hole depth, maximum charge in the same section, minimum resistance line length, and peak velocity data of mass particles in three directions obtained by the blasting vibration meter.

[0024] Furthermore, after obtaining the measured peak velocity data of the blasting vibration, the measured peak velocity data is preprocessed; the preprocessing of the measured peak velocity data satisfies the following formula: Where F(x) represents the improved wavelet threshold function, x represents the original wavelet coefficients, |·| represents the absolute value function, j represents the wavelet decomposition level, and α j Indicates an adaptive threshold. σ j N represents the standard deviation of the noise at layer j. j This represents the number of wavelet coefficients in the j-th layer.

[0025] S2. Construct a peak blasting vibration prediction neural network. Combine the measured peak blasting vibration velocity data with the peak blasting vibration prediction neural network to obtain the initial weights and initial thresholds of the peak blasting vibration prediction neural network. Then, update the peak blasting vibration prediction neural network using the initial weights and initial thresholds.

[0026] In one embodiment, the construction of the peak blasting vibration prediction neural network in step S2 includes the following steps: determining the topology of the peak blasting vibration prediction neural network by trial and error; setting the input layer activation function, hidden layer activation function, output layer activation function, training function, and learning rate of the peak blasting vibration prediction neural network.

[0027] Furthermore, in this embodiment, the peak blasting vibration prediction neural network is specifically a multi-layer feedforward network trained using an error backpropagation algorithm. The topology of the peak blasting vibration prediction neural network includes an input layer, a hidden layer, and an output layer. The input layer includes 7 nodes, and the input data are the blast center distance, vertical height, number of boreholes, row spacing between boreholes, borehole depth, maximum charge per segment, and minimum resistance line length, respectively. The number of nodes in the hidden layer is determined by trial and error. The output layer includes 3 nodes, and the output data are the peak blasting vibration velocities in the horizontal radial (X direction), horizontal tangential (Y direction), and vertical (Z direction), respectively. In this embodiment, the optimal topology of the peak blasting vibration prediction neural network is 7-12-3.

[0028] Furthermore, in this embodiment, the input layer activation function and output layer activation function of the blasting vibration peak prediction neural network are set to tansig functions. Specifically, Set the hidden layer activation function to the pureline function, the training function to the trainlm function, and the learning rate to 0.0001.

[0029] In another optional embodiment, step S2, which combines the measured peak velocity data of the blasting vibration with the peak velocity prediction neural network to obtain the initial weights and initial thresholds of the peak velocity prediction neural network, includes the following steps: forming an initial population using the weights and thresholds of the peak velocity prediction neural network as individuals; evaluating the individuals to obtain their fitness; performing a first adjustment and a second adjustment on the individuals based on their fitness to obtain a new population; evaluating the individuals in the new population until the iteration stopping condition is met to obtain the initial weights and initial thresholds of the peak velocity prediction neural network.

[0030] Furthermore, the evaluation of the individual to obtain the fitness of the individual satisfies the following formula: Where f represents individual fitness, n represents the sample size, and x i Let x represent the measured value of the i-th sample. avg Represents the sample mean. This represents the predicted value of the i-th sample.

[0031] Furthermore, based on the fitness ranking of individuals during the iteration process, the first adjustment is performed on the top half of the individuals with the highest fitness values. The first adjustment satisfies the following formula: in, X represents the individual position after the first adjustment is performed on the individual in the (t+1)th iteration. t Let λ represent the position of an individual in the t-th iteration, T represent the maximum number of iterations, λ represent a random number in the range (0,1), and ω represent the position of an individual in the range (t-th iteration). t Let P represent the weight coefficient of an individual in the t-th iteration, c1 represent the first learning factor, λ1 and λ2 represent random numbers in the range [0,1], c2 represent the second learning factor, and P... t G represents the historical best position of an individual in the t-th iteration. t This represents the historical best position of the group at the t-th iteration.

[0032] Furthermore, the weighting coefficients satisfy the following formula: Where, ω t ω represents the weight coefficient of an individual in the t-th iteration. min ω represents the minimum weight threshold. max f represents the maximum weight threshold. t This represents the fitness of an individual at the t-th iteration. This represents the minimum fitness value of an individual at the t-th iteration. Let represent the average fitness of an individual at the t-th iteration. N represents the number of individuals. Let represent the fitness of the i-th individual in the t-th iteration.

[0033] In yet another optional embodiment, the first learning factor satisfies the following formula: Where c1 represents the first learning factor, This represents the initial value of the first learning factor. The first learning factor represents the end value, t represents the current iteration number, and T represents the maximum iteration number; the second learning factor satisfies the following formula: Where c2 represents the second learning factor, This represents the initial value of the second learning factor. This represents the end value of the second learning factor. In this embodiment, In other embodiments, these values ​​may also be adjusted based on experience or practice.

[0034] In another embodiment, based on the fitness ranking of individuals during the iteration process, a second adjustment is performed on the bottom half of the individuals with the lowest fitness values. The second adjustment satisfies the following formula: in, X represents the individual position after the second adjustment is performed on the individual in the (t+1)th iteration. t Let G represent the position of an individual in the t-th iteration, β represent the step size of the individual, and G... t f represents the historical optimal position of the population at the t-th iteration. t This represents the fitness of an individual at the t-th iteration. Let represent the minimum fitness value of an individual at the t-th iteration, and ∥·∥ represent the Euclidean distance. In other embodiments, depending on computational capabilities or other requirements, a first adjustment and a second adjustment can be performed on all individuals during the iteration process to form a new population.

[0035] In this embodiment, individuals in the new population are evaluated until the iteration stop conditions are met, including setting the number of iterations to the maximum number of iterations and the difference in fitness between the best individuals in two adjacent iterations reaching a set threshold.

[0036] S3. Using the measured peak velocity data of the blasting vibration, obtain the training set and the validation set of the blasting vibration peak prediction neural network. Use the training set and the validation set of the blasting vibration peak prediction neural network to train and validate the updated blasting vibration peak prediction neural network.

[0037] In one embodiment, step S3, obtaining the training set and validation set of the peak blasting vibration prediction neural network using the measured peak blasting vibration velocity data, includes normalizing the measured peak blasting vibration velocity data. The normalization process satisfies the following formula: Where ε represents the original data before normalization, ε * ε represents the data after normalization. max ε represents the maximum value of the original data before normalization. min This represents the minimum value of the original data before normalization.

[0038] In this embodiment, the training set and the validation set of the blasting vibration peak velocity prediction neural network account for 80% and 30% of the measured blasting vibration peak velocity data, respectively, and are composed of randomly selected data.

[0039] S4. Using the trained blasting vibration peak prediction neural network, complete the prediction of blasting vibration peak velocity.

[0040] In one optional embodiment, accurate data on the detonation center distance, vertical height, number of boreholes, row spacing between boreholes, borehole depth, maximum charge per section, and minimum resistance line length are acquired and input into a trained blasting vibration peak velocity prediction neural network to obtain blasting vibration peak velocities in three directions. The blasting vibration peak velocities can be used to assess the safety of blasting operations, control the adverse effects of blasting vibrations on the surrounding environment, and ensure that the blasting seismic wave velocity does not exceed safety standards. Simultaneously, based on the monitoring data, the safety of blasting operations can also be assessed, and suggestions for blasting optimization and enhanced blasting vibration protection can be proposed.

[0041] Please see Figure 2 , Figure 2 This is a framework diagram of a precision control system for blasting construction according to the present invention. In an embodiment, to efficiently execute the precision control method for blasting construction provided by the present invention, the present invention also provides a precision control system for blasting construction, including: an input device, an output device, a processor, and a memory. The input device, output device, processor, and memory are interconnected. The memory contains program instructions, which are used for the steps of the precision control method for blasting construction. The precision control system for blasting construction of the present invention has a compact structure and stable performance, and can stably execute the precision control method for blasting construction of the present invention, further improving the overall applicability and practical application capability of the present invention.

[0042] In an optional embodiment, the processor may be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. Input devices can be used to acquire data. Output devices can be used to output the results obtained by storing program instructions contained in a computer program in the memory provided by this invention. The memory may include read-only memory and random access memory, and provide instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.

[0043] In yet another alternative embodiment, please refer to Figure 3 , Figure 3 This embodiment provides a schematic diagram of a precision control device for blasting operations. To efficiently execute the precision control method for blasting operations provided by this invention, this embodiment also provides a precision control device for blasting operations, such as... Figure 3 As shown, it includes:

[0044] The memory 10 is used to store computer programs; the processor 20 is used to execute the computer programs to implement the above-mentioned precise control method for blasting construction.

[0045] The system includes a memory 10, a processor 20, a communication interface 31, and a communication bus 32. The memory 10, processor 20, and communication interface 31 communicate with each other through the communication bus 32.

[0046] In this embodiment, the memory 10 is used to store one or more programs. The programs may include program code, which includes computer operation instructions. In this embodiment, the memory 10 may store programs for performing the following functions: acquiring measured peak velocity data of blasting vibration; constructing a peak velocity prediction neural network for blasting vibration; combining the measured peak velocity data and the neural network to obtain initial weights and initial thresholds for the neural network; updating the neural network using the initial weights and initial thresholds; obtaining a training set and a validation set for the neural network using the measured peak velocity data; training and validating the updated neural network using the training set and validation set; and using the trained neural network to predict the peak velocity of blasting vibration.

[0047] In one possible implementation, the memory 10 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; and the data storage area may store data created during use.

[0048] Furthermore, memory 10 may include read-only memory and random access memory, providing instructions and data to the processor. A portion of the memory may also include NVRAM. The memory stores operating systems and operating instructions, executable modules, or data structures, or subsets thereof, or extended sets thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and handling hardware-based tasks.

[0049] Processor 20 can be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field-programmable gate array, or other programmable logic device. Processor 20 can be a microprocessor or any conventional processor. Processor 20 can call programs stored in memory 10.

[0050] Communication interface 31 can be an interface for the communication module, used to connect with other devices or systems.

[0051] Of course, it should be noted that, Figure 3 The structure shown does not constitute a limitation on the precision control equipment for blasting operations in this embodiment. In practical applications, precision control equipment for blasting operations may include more advanced technologies. Figure 3 More or fewer components as shown, or combinations of certain components.

[0052] The embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described precise control method for blasting construction.

[0053] The storage medium can include various media that can store program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0054] In summary, this invention, by predicting the peak velocity of blasting vibrations, reveals the propagation law of blasting vibrations and solves the problem of accurately and efficiently controlling blasting operations, providing a reliable basis for safe blasting. Therefore, this invention effectively overcomes the various shortcomings of existing technologies and has high industrial application value.

[0055] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for precise control of blasting operations, characterized in that, The aforementioned method for precise control of blasting operations includes the following steps: Obtain measured data of peak velocity of blasting vibration; A peak blasting vibration prediction neural network is constructed. The initial weights and initial thresholds of the peak blasting vibration prediction neural network are obtained by combining the measured peak blasting vibration velocity data and the peak blasting vibration prediction neural network. The peak blasting vibration prediction neural network is then updated using the initial weights and initial thresholds. Using the measured peak velocity data of the blasting vibration, a training set and a validation set for the peak velocity prediction neural network of the blasting vibration are obtained. The updated peak velocity prediction neural network of the blasting vibration is then trained and validated using the training set and the validation set. The peak velocity of blasting vibration is predicted by using a trained neural network for predicting peak blasting vibration. The process of combining the measured peak velocity data of blasting vibration with the peak velocity prediction neural network to obtain the initial weights and initial thresholds of the peak velocity prediction neural network includes the following steps: The weights and thresholds of the aforementioned peak blasting vibration prediction neural network are used as individuals to form an initial population; Evaluate the individual to obtain its fitness; Based on the fitness, the individuals are subjected to a first adjustment and a second adjustment to obtain a new population; Evaluate the individuals in the new group until the iteration stopping condition is met, and obtain the initial weights and initial thresholds of the blasting vibration peak prediction neural network; The first adjustment is performed on the individual, satisfying the following formula: ， in, Indicates the first In the next iteration, the first adjusted individual position is applied to the individual. This represents the position of an individual at the t-th iteration. Indicates the maximum number of iterations. Represents a random number in the range (0,1). Indicates the first The weight coefficient of an individual in the next iteration Indicates the first learning factor. express random numbers, Indicates the second learning factor. Indicates the first The historical best position of an individual in the next iteration. Indicates the first The historical best position of the group at the next iteration; A second adjustment is performed on the individual, satisfying the following formula: ， in, Indicates the first In the next iteration, the second adjusted individual position is applied to the individual. This represents the position of an individual at the t-th iteration. This represents the step length of an individual's movement. Indicates the first The historical best position of the group at the next iteration. Indicates the first Individual fitness at the next iteration Indicates the first The minimum fitness of an individual is reached in the next iteration. This represents the Euclidean distance.

2. The method for precise control of blasting operations according to claim 1, characterized in that, It also includes the following steps: The measured peak velocity data of the blasting vibration is preprocessed; the preprocessing of the measured peak velocity data of the blasting vibration satisfies the following formula: ， in, This represents the improved wavelet threshold function. Represents the original wavelet coefficients. Represents the absolute value function. Indicates the wavelet decomposition level. Indicates the first Adaptive threshold for wavelet decomposition level , Indicates the first Standard deviation of layer noise Indicates the first The number of layer wavelet coefficients.

3. The method for precise control of blasting operations according to claim 1, characterized in that, The weighting coefficients satisfy the following formula: ， in, Indicates the first The weight coefficient of an individual in the next iteration This represents the minimum weight threshold. This represents the maximum weight threshold. Indicates the first Individual fitness at the next iteration Indicates the first The minimum fitness of an individual is reached in the next iteration. Indicates the first The average fitness of an individual at the nth iteration. , Indicates the number of individuals. Indicates the first During the nth iteration The fitness of an individual.

4. The method for precise control of blasting operations according to claim 1, characterized in that, The first learning factor satisfies the following formula: ， in, Indicates the first learning factor. This represents the initial value of the first learning factor. This indicates the end value of the first learning factor. Indicates the current iteration number. Indicates the maximum number of iterations; The second learning factor satisfies the following formula: ， in, Indicates the second learning factor. This represents the initial value of the second learning factor. This indicates the end value of the second learning factor.

5. The method for precise control of blasting operations according to claim 1, characterized in that, The individual is evaluated to obtain its fitness, which satisfies the following formula: ， in, Indicates individual fitness. Indicates the number of samples. Indicates the first Measured values ​​of a sample Represents the sample mean. Indicates the first The predicted value for each sample.

6. The method for precise control of blasting operations according to claim 1, characterized in that, The construction of the peak blasting vibration prediction neural network includes the following steps: The topology of the neural network for predicting peak blasting vibration was determined by trial and error. The input layer activation function, hidden layer activation function, output layer activation function, training function, and learning rate of the neural network for predicting peak blasting vibration are set.

7. A precision control system for blasting operations, characterized in that, The precision control system for blasting construction includes: an input device, an output device, a processor, and a memory. The input device, output device, processor, and memory are interconnected. The memory includes program instructions, which are used to execute the steps of the precision control method for blasting construction according to any one of claims 1-6.

Images