Linkage analysis method, system, medium and equipment for blasting parameters and crushing lumpiness

Abstract

The invention discloses a linkage analysis method and system for blasting parameters and fragmentation lumpiness, a medium and equipment, and relates to the technical field of mining. The method comprises the following steps: constructing a target relation model between blasting parameters and fragmentation lumpiness; geological data of a mine are obtained, and blasting parameters are determined based on the geological data; determining crushing lumpiness according to the blasting parameters and the target relation model; determining equipment energy consumption of each operation link based on the blasting parameters and the crushing lumpiness; and determining a target energy-saving decision based on the equipment energy consumption of each operation link. By implementing the technical scheme provided by the invention, the energy consumption in the mining process is reduced.

Description

Technical Field

[0001] The present application relates to the field of mining technology, and in particular to a method, system, medium and equipment for linkage analysis of blasting parameters and fragmentation size. Background Art

[0002] In mining engineering, blasting, as a commonly used rock crushing method, has a decisive influence on the efficiency and cost control of the entire mining process. Blasting not only involves how to effectively break down rocks, but also how to optimize energy use and reduce operating costs.

[0003] Traditional blasting technology mainly relies on experience and trial and error to determine blasting parameters, such as charge, hole depth, arrangement, etc. These parameters directly affect the fragmentation after blasting, and thus affect the efficiency of loading, transportation and further crushing. However, this experience-based method often fails to achieve the optimal use of energy. For example, the selection of blasting parameters may not be able to best match the subsequent crushing and processing requirements, which may lead to high energy consumption in the entire mining process. Summary of the invention

[0004] The present application provides a method, system, medium and equipment for linkage analysis of blasting parameters and fragmentation size, so as to reduce energy consumption in the mining process.

[0005] In a first aspect, the present application provides a linkage analysis method for blasting parameters and fragmentation size, the method comprising: Construct the target relationship model between blasting parameters and fragmentation size; Acquiring geological data of the mine, and determining blasting parameters based on the geological data; Determine the fragmentation size according to the blasting parameters and the target relationship model; Based on the blasting parameters and the fragmentation size, determine the energy consumption of equipment in each operation link; The target energy-saving decision is determined based on the equipment energy consumption of each operation link.

[0006] By adopting the above technical scheme and constructing a target relationship model between blasting parameters and fragmentation, the intrinsic relationship between the two can be accurately grasped, laying the foundation for the optimization of blasting parameters. Based on geological data, more reasonable blasting parameters can be determined to improve blasting effects. The target relationship model can then be used to predict the fragmentation size corresponding to the blasting parameters. Then, based on the optimized blasting parameters and the predicted fragmentation size, the energy consumption of equipment in each operation link can be more accurately evaluated. The optimization of blasting parameters is combined with the determination of the energy consumption of equipment in subsequent links, thereby achieving coordinated optimization of blasting operations and subsequent processing links. Target energy-saving decisions are made through the energy consumption of equipment in each operation link, breaking through the limitations of traditional blasting technology that mainly relies on experience to determine blasting parameters, reducing the energy consumption of the overall mining process, and achieving energy saving and consumption reduction.

[0007] Optionally, the constructing of a target relationship model between blasting parameters and fragmentation size includes: Acquire historical blasting data, and divide the historical blasting data into a training set and a validation set, wherein the historical blasting data includes blasting parameters and fragmentation data corresponding to the blasting parameters; Based on the historical blasting data, a machine learning algorithm is used to construct a relationship model between the blasting parameters and the fragmentation size; The association model is trained based on the training set, and the trained association model is verified based on the verification set to obtain a target relationship model between blasting parameters and fragmentation size.

[0008] By adopting the above technical solution, by acquiring historical blasting data, a relationship model between blasting parameters and fragmentation size is constructed using a machine learning algorithm, and the model is trained based on a training set and verified based on a verification set, thereby obtaining a target relationship model that accurately grasps the intrinsic relationship between the two. This data-driven modeling method based on historical data learning and trained and verified can overcome the defects of traditional reliance on experience judgment and describe the mapping relationship between blasting parameters and fragmentation size in a more scientific and accurate manner.

[0009] Optionally, determining blasting parameters based on the geological data includes: extracting key geological parameters related to blasting parameters from the geological data; Based on the key geological parameters and a preset blasting parameter calculation model, initial blasting parameters are obtained; The initial blasting parameters are adjusted based on the mining requirements of the mine and the preset blasting standards to obtain blasting parameters.

[0010] By adopting the above technical scheme, key geological parameters related to blasting parameters, such as rock hardness, crack development, etc., are extracted from geological data, avoiding simply ignoring the influence of geological conditions. Then, based on the extracted key geological parameters and the preset blasting parameter calculation model, preliminary recommended values ​​of blasting parameters can be obtained, which is more objective than simple empirical judgment. Then, the initial blasting parameters are combined with the actual mining requirements and blasting standards of the mine for adjustment and optimization, and the blasting parameters finally determined are more reasonable and feasible.

[0011] Optionally, determining the fragmentation size according to the blasting parameters and the target relationship model includes: Inputting the blasting parameters into the target relationship model to obtain the fragmentation distribution; Based on the fragmentation distribution, an average fragmentation size and a maximum fragmentation size are calculated; Determining whether the average crushing size and the maximum crushing size both meet preset crushing requirements; If the crushing requirement is not met, the blasting parameters are adjusted at least once, and the adjusted blasting parameters are input into the target relationship model for iteration until the obtained crushing fragmentation meets the crushing requirement or reaches a preset number of iterations, and the crushing fragmentation is output.

[0012] By adopting the above technical solution, the determined blasting parameters are input into the constructed target relationship model, and the corresponding fragmentation distribution can be predicted. Based on the distribution, the average fragmentation and maximum fragmentation are calculated, and then compared with the preset fragmentation requirements. If the requirements are not met, the blasting parameters are adjusted and re-entered into the model for iterative calculation until a satisfactory fragmentation result is obtained or the preset maximum number of iterations is reached. This closed-loop optimization process of prediction first and verification later realizes the precise matching of blasting parameters and subsequent fragmentation effects. Unlike the traditional method that relies solely on empirical judgment, it can more accurately and objectively predict the fragmentation distribution corresponding to the blasting parameters, and find the optimal solution through iterative adjustment of the model, ensuring that the fragmentation results can meet the processing requirements.

[0013] Optionally, determining the equipment energy consumption of each operation link based on the blasting parameters and the fragmentation size includes: Acquire multi-dimensional data of equipment in each of the operation links, wherein the multi-dimensional data at least includes equipment vibration, equipment noise and equipment temperature; Based on the blasting parameters and the fragmentation size, determining a standard range corresponding to the multi-dimensional data of each of the devices; Calculating the deviation values ​​of the multi-dimensional data from the corresponding standard range respectively; The equipment energy consumption of each operation link is calculated according to the deviation value.

[0014] By adopting the above technical solution, based on the optimized blasting parameters and predicted fragmentation, the standard range of multi-dimensional data of the equipment in each operation link under ideal working conditions can be determined, such as equipment vibration, noise, temperature, etc. By obtaining these multi-dimensional data of the equipment during actual operation and calculating the deviation values ​​from the corresponding standard ranges, the actual operating status of the equipment can be more accurately evaluated, and then the actual energy consumption level of the equipment in each link can be calculated based on the deviation values. The optimized blasting parameters and predicted fragmentation can more accurately reflect the ideal operating conditions of the subsequent processes, providing a reliable reference benchmark for evaluating energy consumption.

[0015] Optionally, calculating the equipment energy consumption of each operation link according to the deviation value includes: Establish a corresponding relationship map between multi-dimensional data deviation values ​​and energy consumption increments; Positioning each of the deviation values ​​in the corresponding relationship map to obtain a positioning result corresponding to each of the deviation values; Based on each of the positioning results, extracting a corresponding energy consumption increment value; The energy consumption increment values ​​are added to the rated energy consumption of the equipment to obtain the equipment energy consumption of each operation link.

[0016] By adopting the above technical solution, the energy consumption estimation method based on graph positioning can more comprehensively and accurately describe the nonlinear relationship between the deviation value and energy consumption compared to traditional methods such as simple linear fitting, avoiding the energy consumption estimation deviation caused by inaccurate fitting. At the same time, by combining the data deviation values ​​of multiple dimensions for comprehensive positioning, the influence of various working conditions can be fully considered, so that the final energy consumption value is closer to the actual situation.

[0017] Optionally, the target energy-saving decision is determined based on the equipment energy consumption of each operation link, including: Construct an energy consumption scheduling model based on ant colony optimization algorithm; Based on the energy consumption scheduling model, determining an optimal energy consumption path; Based on the optimal energy consumption path, generate a device operation schedule and a power adjustment plan; A target energy-saving decision is made by combining the equipment operation schedule and the power regulation scheme.

[0018] By adopting the above technical solutions, through intelligent modeling algorithms and system scheduling optimization, we have developed efficient and energy-saving operation modes for each equipment while ensuring production needs, thus achieving energy conservation and consumption reduction in the mining production process.

[0019] In a second aspect of the present application, a linkage analysis system for blasting parameters and fragmentation size is provided, the system comprising: A model building module is used to build a target relationship model between blasting parameters and fragmentation size; A blasting parameter determination module, used to obtain geological data of the mine and determine blasting parameters based on the geological data; A fragmentation determination module, used to determine the fragmentation according to the blasting parameters and the target relationship model; An equipment energy consumption determination module, used to determine the equipment energy consumption of each operation link based on the blasting parameters and the fragmentation size; The energy-saving decision determination module is used to determine the target energy-saving decision based on the equipment energy consumption of each operation link.

[0020] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above method steps.

[0021] In a fourth aspect of the present application, an electronic device is provided, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0022] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By constructing a target relationship model between blasting parameters and fragmentation, this application can accurately grasp the intrinsic relationship between the two, lay the foundation for the optimization of blasting parameters, and determine more reasonable blasting parameters based on geological data to improve blasting effects. The target relationship model can then be used to predict the fragmentation size corresponding to the blasting parameters. Then, based on the optimized blasting parameters and the predicted fragmentation size, the energy consumption of equipment in each operation link can be more accurately evaluated. The optimization of blasting parameters is combined with the determination of the energy consumption of equipment in subsequent links, thereby achieving coordinated optimization of blasting operations and subsequent processing links. Target energy-saving decisions are made through the energy consumption of equipment in each operation link, breaking through the limitations of traditional blasting technology that mainly relies on experience to determine blasting parameters, reducing the energy consumption of the overall mining process, and achieving energy saving and consumption reduction. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of a linkage analysis method of blasting parameters and fragmentation size provided in an embodiment of the present application; Figure 2 It is a module schematic diagram of a linkage analysis system of blasting parameters and fragmentation size provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0024] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0025] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0026] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0027] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0028] The following will provide a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0029] Please refer to Figure 1 , a flowchart of a method for linkage analysis of blasting parameters and fragmentation size is proposed. The method can be implemented by a computer program, a single-chip microcomputer, or run on a linkage analysis system of blasting parameters and fragmentation size. The computer program can be integrated in a computer device or run as an independent tool application. Specifically, the method includes steps 10 to 50, and the steps are as follows: Step 10: Construct the target relationship model between blasting parameters and fragmentation size.

[0030] In the embodiment of the present application, blasting parameters refer to a series of key values ​​used to control and describe the blasting process in mine blasting operations. The blasting parameters include but are not limited to single-hole charge, total charge, hole diameter, hole spacing, row spacing, hole depth, charging structure and detonation method.

[0031] In the present embodiment, the fragmentation refers to the degree of rock fragmentation after blasting, and is usually used to measure the blasting effect. The fragmentation includes but is not limited to the fragmentation distribution, the average fragmentation, and the maximum fragmentation.

[0032] The target relationship model in the embodiment of the present application refers to a relationship model between blasting parameters and fragmentation, which can predict the fragmentation according to given blasting parameters.

[0033] Specifically, historical blasting data, including blasting parameters and corresponding fragmentation data, are obtained. These data reflect the actual situation of past blasting operations and provide a reliable basis for model construction. Subsequently, the historical blasting data are divided into training sets and validation sets to ensure the generalization ability of the model and avoid overfitting problems. Then, a machine learning algorithm is used to construct a relationship model between blasting parameters and fragmentation. The selection of machine learning algorithms is based on their powerful pattern recognition and nonlinear relationship modeling capabilities, which can effectively capture the complex intrinsic relationship between blasting parameters and fragmentation. In the process of model construction, the training set is used to train the association model, and the model parameters are continuously adjusted through iterative optimization algorithms so that it can accurately reflect the influence of blasting parameters on fragmentation. After training, the validation set is used to verify the model to evaluate the prediction accuracy and stability of the model. Through repeated training and validation processes, a target relationship model with better performance is finally obtained, which can accurately predict the fragmentation distribution, average fragmentation and maximum fragmentation according to given blasting parameters.

[0034] Based on the above embodiment, as an optional embodiment, the step of constructing a target relationship model between blasting parameters and fragmentation size may further include the following steps: Step 101: Acquire historical blasting data, and divide the historical blasting data into a training set and a validation set. The historical blasting data includes blasting parameters and fragmentation data corresponding to the blasting parameters.

[0035] Specifically, historical blasting data are extracted from the mine's blasting record database. These data usually include blasting parameters and corresponding fragmentation data. In the process of data acquisition, attention should be paid to the integrity and representativeness of the data to ensure that data samples under different geological conditions and different blasting schemes are covered. Then the acquired historical blasting data are preprocessed, including removing outliers, filling missing values, standardization and other operations to improve data quality. Subsequently, random sampling or stratified sampling methods are used to divide the processed historical blasting data into training sets and validation sets. For example, 70%-80% of the data is used as a training set, and the remaining 20%-30% is used as a validation set. This division method ensures that the model has enough data to learn the relationship between blasting parameters and fragmentation during the training process, while retaining a portion of independent data for evaluating model performance.

[0036] Step 102: Based on historical blasting data, a machine learning algorithm is used to construct a relationship model between blasting parameters and fragmentation.

[0037] Specifically, considering the complexity and nonlinear characteristics of the blasting process, this embodiment uses a deep neural network (DNN) as the basic algorithm to construct a relational model. DNN has a powerful nonlinear mapping capability and can effectively capture the complex relationship between blasting parameters and fragmentation. When constructing the structure of the relational model, the input layer corresponds to the blasting parameters (including single hole charge, total charge, hole diameter, hole spacing, row spacing, hole depth, charge structure and detonation method), the output layer corresponds to the fragmentation data (including fragmentation distribution, average fragmentation and maximum fragmentation), and the hidden layer is designed with a multi-layer structure, and each layer uses the ReLU activation function to enhance the nonlinear expression ability of the model.

[0038] Step 103: Train the association model based on the training set, and verify the trained association model based on the verification set to obtain a target relationship model between blasting parameters and fragmentation size.

[0039] Specifically, the training set is used to train the associated model. The training process uses the batch gradient descent method to divide the training data into multiple small batches and input them into the model batch by batch. In each iteration, the model calculates the error between the predicted value and the actual fragmentation, and then adjusts the model parameters through the back propagation algorithm to minimize the prediction error. In order to improve the training effect, an adaptive learning rate strategy is adopted, such as the Adam optimizer, which can automatically adjust the learning rate according to the training process. At the same time, an early stopping mechanism is introduced to monitor the performance on the validation set. When the validation error no longer decreases, the training is stopped to avoid overfitting. After the training is completed, the validation set is used to comprehensively evaluate the model. The evaluation indicators include mean absolute error (MAE), root mean square error (RMSE) and determination coefficient (R²), which fully reflect the performance of the model in predicting the fragmentation distribution, average fragmentation and maximum fragmentation. If the verification result does not meet the preset accuracy requirements, it is necessary to return to adjust the model structure or hyperparameters and retrain.

[0040] Step 20: Obtain geological data of the mine and determine blasting parameters based on the geological data.

[0041] In the embodiment of the present application, geological data refers to a series of parameters and information describing the geological characteristics of the mine blasting area, including but not limited to rock type, rock strength (such as rock compressive strength), rock density, degree of joint development (such as joint spacing) and stratigraphic structure.

[0042] Specifically, the geological data of the mine is first obtained through geological exploration and drilling sampling. In order to improve the accuracy and representativeness of the data, multi-point sampling and comprehensive analysis methods are used to ensure that the geological data obtained can fully reflect the geological characteristics of the blasting area. Next, the acquired geological data is processed and analyzed to extract key geological parameters related to blasting parameters. These key parameters may include rock compressive strength, rock density, joint spacing, etc. In the data processing process, geostatistical methods such as Kriging interpolation are used to reasonably estimate the data between sampling points to form a complete geological parameter distribution map. Based on the processed key geological parameters and combined with the preset blasting parameter calculation model, the blasting parameters are preliminarily determined. This calculation model is based on long-term practical experience and theoretical research, and can quickly give initial blasting parameter recommendations based on geological parameters, including single hole charge, total charge, hole diameter, hole spacing, row spacing, hole depth, charge structure and detonation method. However, the parameters obtained by relying solely on the calculation model may not be accurate enough, so it is necessary to further adjust them in combination with the specific mining requirements of the mine and the preset blasting standards to obtain the blasting parameters. This adjustment process takes into account production goals, safety requirements, environmental impacts and other factors to ensure that the final blasting parameters are not only adapted to geological conditions, but also meet actual production needs.

[0043] Based on the above embodiment, as an optional embodiment, the step of determining blasting parameters based on geological data may further include the following steps: Step 201: extract key geological parameters related to blasting parameters from geological data.

[0044] Specifically, the original geological data obtained are systematically analyzed and processed. These original geological data usually include rock type, rock strength, rock density, joint development, stratigraphic structure and other information. By using geostatistical methods such as variogram analysis and Kriging interpolation, the data between sampling points are reasonably estimated to form a continuous geological parameter distribution map. Next, based on the long-term accumulated blasting experience and theoretical research, the key geological parameters that have the most significant impact on the blasting effect are determined. The key geological parameters include rock compressive strength, rock density, joint spacing, rock solidity coefficient, etc. In order to improve the accuracy and efficiency of parameter extraction, this embodiment uses machine learning algorithms, such as principal component analysis (PCA) and random forest methods, to automatically identify and extract these key parameters from massive geological data. In the process of parameter extraction, the correlation and interaction between parameters are also considered to ensure that the extracted parameters can fully reflect the impact of geological conditions on the blasting effect.

[0045] Step 202: Obtain initial blasting parameters based on key geological parameters and a preset blasting parameter calculation model.

[0046] Specifically, it is necessary to first establish a preset blasting parameter calculation model, which is constructed based on long-term blasting practice experience and theoretical research, and can reflect the complex relationship between key geological parameters and blasting parameters. The input of the model includes extracted key geological parameters, such as rock compressive strength, rock density, joint spacing and rock solidity coefficient; the output of the model is a set of initial blasting parameters, including single hole charge, total charge, hole diameter, hole spacing, row spacing, hole depth, charge structure and detonation method. In order to improve the accuracy and adaptability of the calculation model, this embodiment uses a machine learning algorithm, such as support vector regression (SVR) or random forest regression, to train and optimize the model. This method can automatically learn and adjust the model parameters to better adapt to the geological conditions and blasting requirements of different mining areas. During the calculation process, the model will consider the weights and interactions of each key geological parameter, and obtain the most suitable initial blasting parameters through complex mathematical operations. In addition, in order to deal with possible geological anomalies, the model also provides an anomaly detection mechanism. When the input geological parameters deviate significantly from the normal range, a warning will be triggered and manual review will be recommended.

[0047] Step 203: adjusting the initial blasting parameters based on the mining requirements of the mine and the preset blasting standards to obtain blasting parameters.

[0048] Specifically, it is necessary to first clarify the mining requirements of the mine, which include target output, crushing size requirements, slope stability requirements, etc. At the same time, it is also necessary to consider the preset blasting standards, such as vibration limitation, flying rock control, noise control and other safety and environmental protection indicators. Then a multi-objective optimization model is established, taking the initial blasting parameters, mine mining requirements and blasting standards as input. This model uses intelligent optimization methods such as genetic algorithms or particle swarm optimization algorithms to find the optimal blasting parameter combination that meets all constraints through iterative calculations. During the optimization process, the model will fine-tune the initial blasting parameters, such as adjusting the single-hole charge, hole spacing, row spacing, etc., to balance the production efficiency, crushing effect, safety and environmental protection and other requirements. In order to improve the accuracy of the adjustment, this embodiment introduces a sensitivity analysis module to evaluate the degree of influence of each blasting parameter on the final result, so as to give priority to adjusting the parameters with greater influence.

[0049] Step 30: Determine the fragmentation size according to the blasting parameters and the target relationship model.

[0050] Specifically, the determined blasting parameters are input into a pre-built target relationship model, which can accurately reflect the complex nonlinear relationship between the blasting parameters and the fragmentation size. The output of the target relationship model is the predicted fragmentation size distribution, including key indicators such as the average fragmentation size and the maximum fragmentation size. In order to improve the accuracy of the prediction, this embodiment adopts an integrated learning method, such as a random forest or a gradient boosting tree, to integrate the prediction results of multiple sub-models to reduce the error that may be caused by a single model. After obtaining the fragmentation size distribution, the system will automatically determine whether it meets the preset fragmentation requirements. These requirements are usually determined by subsequent loading, transportation and crushing processes, such as the maximum size does not exceed a given size, or the proportion of a specific particle size range reaches a certain proportion. If the predicted fragmentation size does not meet the requirements, the system will start the parameter optimization program to fine-tune the blasting parameters. This process uses an iterative optimization algorithm, such as a genetic algorithm or a particle swarm optimization, to find the optimal blasting parameter combination that can meet the fragmentation requirements through multiple adjustments and predictions, thereby obtaining the final fragmentation size.

[0051] Based on the above embodiment, as an optional embodiment, the step of determining adjacent detection reagent groups based on the addition parameters of each detection reagent and calculating the influence value between each adjacent detection reagent group may further include the following steps: Step 301: Input blasting parameters into the target relationship model to obtain the fragmentation distribution.

[0052] Specifically, the blasting parameters are input into the target relationship model. During the model processing, the system will automatically consider the interaction between the blasting parameters and their combined impact on the fragmentation size. The model can output a detailed fragmentation size distribution, including key indicators such as the proportion of rocks in different particle size ranges, average fragmentation size, and maximum fragmentation size.

[0053] Step 302: Based on the fragmentation distribution, the average fragmentation size and the maximum fragmentation size are calculated.

[0054] Specifically, the broken fragmentation distribution data obtained by the target relationship model is usually presented in a discrete form, indicating the mass or volume percentage of rocks in different particle size ranges. In order to improve the accuracy of the calculation, this embodiment uses a numerical integration method to continuously process discrete data, and uses spline interpolation technology to construct a continuous particle size distribution curve, ensuring the accuracy and reliability of subsequent calculations. After obtaining a continuous particle size distribution curve, the weighted average method is used to calculate the average broken fragmentation. Specifically, the median of each particle size interval is multiplied by the mass or volume percentage of the interval, and then all intervals are summed to obtain the average broken fragmentation. This method takes into account the distribution of the entire particle size range and can more accurately reflect the overall crushing effect. For the calculation of the maximum broken fragmentation, this method introduces the extreme value theory of statistics. By fitting the tail of the particle size distribution curve with a generalized extreme value distribution (GEV), the maximum fragmentation exceeding a given probability threshold (such as 99.9%) is estimated. This method can not only give a point estimate of the maximum broken fragmentation, but also provide a confidence interval, which more comprehensively describes the possible range of the maximum fragmentation.

[0055] Step 303: Determine whether the average crushing size and the maximum crushing size both meet the preset crushing requirements.

[0056] Specifically, it is necessary to first clarify the preset crushing requirements. The crushing requirements are determined by subsequent loading, transportation, and crushing processes, including the target range of the average crushing size and the upper limit of the maximum crushing size. These requirements should take into account factors such as equipment capacity, production efficiency, and product quality. The calculated average crushing size and maximum crushing size are compared with the preset requirements. This embodiment uses a fuzzy logic system for judgment. This method can handle the ambiguity and uncertainty that may exist in the crushing requirements. For example, for the average crushing size, fuzzy sets such as "better", "general", and "poor" can be set, and specific values ​​can be mapped to these sets through membership functions. For the maximum crushing size, a fuzzy threshold can be set to take into account measurement and calculation errors. In the judgment process, the system will consider the satisfaction degree of the average crushing size and the maximum crushing size at the same time, and give a comprehensive evaluation result.

[0057] Step 304: If the crushing requirement is not met, the blasting parameters are adjusted at least once, and the adjusted blasting parameters are input into the target relationship model for iteration until the obtained crushing fragmentation meets the crushing requirement or reaches a preset number of iterations, and the crushing fragmentation is output.

[0058] Specifically, if the above-mentioned judgment result does not meet the crushing requirements, the blasting parameter adjustment program is started. This embodiment uses intelligent optimization algorithms, such as genetic algorithms or particle swarm optimization algorithms, to guide parameter adjustment. These algorithms can efficiently search for optimal solutions in complex multidimensional parameter spaces and adapt to the nonlinear characteristics of blasting parameter optimization. During the adjustment process, different weights and constraints are assigned to each parameter in consideration of the sensitivity and adjustable range of different blasting parameters. For example, the single-hole charge and charging structure may be more sensitive than the hole spacing and row spacing, so they are given a higher adjustment priority. After each parameter adjustment, the new blasting parameter set is input into the target relationship model to re-predict the fragmentation distribution. This process uses parallel computing technology to simultaneously evaluate multiple sets of parameter combinations, greatly improving the optimization efficiency. During the iteration process, the system will continue to track and record the effect of each adjustment, and construct a parameter sensitivity map to guide the subsequent adjustment direction. At the same time, adaptive control of the optimization process is achieved by dynamically adjusting the learning rate. In order to balance the optimization effect and computational cost, a predetermined upper limit of the number of iterations or convergence conditions is set. When a solution or an upper limit of the number of iterations that meets the fragmentation requirements is reached, the optimal fragmentation result and its corresponding blasting parameters are output.

[0059] Step 40: Based on the blasting parameters and the fragmentation size, determine the energy consumption of the equipment in each operation link.

[0060] Equipment energy consumption in the embodiment of the present application refers to the energy consumed by the equipment in each operation link of mining, which can be calculated from the multi-dimensional data of the equipment, including equipment vibration, equipment noise and equipment temperature.

[0061] Specifically, it is necessary to establish a comprehensive energy consumption prediction model, which takes the optimized blasting parameters and the predicted distribution of broken fragmentation as input and outputs the predicted value of equipment energy consumption in each operation link. This embodiment adopts a multi-level machine learning model architecture, including sub-models of major operation links such as loading, transportation, crushing and screening. Each sub-model has been trained with a large amount of historical data and can accurately capture the energy consumption characteristics of the link. In the process of model construction, considering the mutual influence between different operation links, a recurrent neural network (RNN) structure is introduced to simulate the continuity of the production process and the coupling relationship between each link. For the loading link, the model focuses on the impact of the distribution of broken fragmentation on the loading efficiency, and predicts the energy consumption of the loading equipment by analyzing the bucket filling degree and loading cycle. The energy consumption prediction of the transportation link is based on the transportation distance, road conditions and the characteristics of the loaded materials (such as average fragmentation and loose coefficient). The energy consumption prediction of the crushing link focuses on the matching degree between the feed particle size and the crushing equipment parameters, and estimates the energy consumption of the crushing equipment by analyzing the crushing ratio and product particle size distribution. The energy consumption prediction of the screening process takes into account the screening difficulty and efficiency, and is calculated based on the feed characteristics and screening equipment parameters.

[0062] In another feasible embodiment, multi-dimensional data of equipment in each operation link can also be obtained, including but not limited to equipment vibration, equipment noise and equipment temperature. These data are collected in real time through a sensor network installed on the equipment and preliminarily processed using edge computing technology to ensure the timeliness and reliability of the data. Based on the blasting parameters and the predicted fragmentation, the standard range corresponding to the multi-dimensional data of each device is determined. A machine learning algorithm, such as support vector regression (SVR) or random forest, can be used to establish a mapping relationship between blasting parameters, fragmentation and equipment operating parameters, and the deviation values ​​of the multi-dimensional data and the corresponding standard range are calculated respectively. A nonlinear mapping relationship between the deviation value and the energy consumption increment is established, and each energy consumption increment value is added to the rated energy consumption of the equipment to obtain the equipment energy consumption of each operation link.

[0063] Based on the above embodiment, as an optional embodiment, the step of determining the equipment energy consumption of each operation link based on the blasting parameters and the crushing fragmentation size further includes the following steps: Step 401: Acquire multi-dimensional data of equipment in each operation link, where the multi-dimensional data at least includes equipment vibration, equipment noise, and equipment temperature.

[0064] Specifically, multiple types of sensors are installed on key equipment in each operation link, including but not limited to vibration sensors, acoustic sensors, and temperature sensors. The data collected by each sensor is used as multi-dimensional data of the equipment. The selection and arrangement of these sensors need to consider the characteristics of the equipment and the working environment to ensure the accuracy and representativeness of data collection. For example, for large-scale crushing equipment, it may be necessary to install vibration sensors at multiple key points to fully capture the vibration characteristics of the equipment. This embodiment uses Industrial Internet of Things (IIoT) technology to build a data acquisition network. Each sensor is equipped with a microprocessor that can perform preliminary data processing and compression to reduce the transmission load.

[0065] Step 402: Based on the blasting parameters and the fragmentation size, determine the standard range corresponding to the multi-dimensional data of each device.

[0066] Specifically, a multivariate mapping model is constructed, and the blasting parameters and fragmentation are used as inputs to output the standard range of multi-dimensional data of each device. This embodiment adopts deep learning technology, especially the hybrid architecture of multi-layer perceptron (MLP) and long short-term memory network (LSTM), to capture the nonlinear relationship between blasting parameters, fragmentation and equipment operating parameters. The input layer of the model includes key blasting parameters (such as single hole charge, hole spacing, row spacing, etc.) and fragmentation distribution characteristics (such as average particle size, maximum particle size, particle size distribution curve parameters, etc.). The hidden layer adopts a multi-layer perceptron structure to extract the complex interactive relationship between input features. Considering the time series of the equipment operation state, the output layer of the model adopts an LSTM structure, which can capture the dynamic characteristics of equipment parameters changing over time. The model outputs the standard range of multi-dimensional data (including vibration, noise, temperature, etc.) of each device. These ranges are not fixed thresholds, but dynamic intervals that change with blasting parameters and fragmentation.

[0067] Step 403: Calculate the deviation values ​​between the multi-dimensional data and the corresponding standard range respectively.

[0068] Specifically, the acquired multi-dimensional data (including equipment vibration, equipment noise, and equipment temperature, etc.) are preprocessed to ensure the quality and comparability of the data. This embodiment uses adaptive filtering technology to reduce the noise of the original data, such as using a Kalman filter or a wavelet transform to eliminate the influence of random noise and instantaneous interference. For different types of data, a specific processing method is adopted: spectral analysis is performed on the vibration data to extract the characteristic frequency and amplitude; noise data is calculated. In order to deal with the dimensional differences of data of different dimensions, this method introduces data standardization. For the data of each dimension, the Z-score standardization method is adopted, that is, the original data is converted into a standard normal distribution with a mean of 0 and a standard deviation of 1. This processing makes the deviation values ​​of different dimensions comparable, which is conducive to subsequent comprehensive analysis. When calculating the deviation value, considering that the standard range may be an interval rather than a single value, this embodiment designs a flexible deviation calculation method. For data points that fall within the standard range, their deviation values ​​are set to 0; for data points that exceed the range, their distance from the range boundary is calculated as the deviation value. This method not only takes into account the reasonable fluctuation range, but also accurately quantifies the degree of exceeding the standard. Calculate the equivalent continuous sound level; perform time series analysis on temperature data to identify temperature change trends.

[0069] Step 404: Calculate the equipment energy consumption of each operation link according to the deviation value.

[0070] Specifically, a correspondence map between multi-dimensional data deviation values ​​and energy consumption increments is constructed. This map is a multi-dimensional mapping model constructed based on a large amount of historical operating data and expert knowledge. Each deviation value is located in the correspondence map. This step uses a nearest neighbor search algorithm, such as a KD tree or a ball tree, to quickly find the historical data point closest to the current deviation value in a high-dimensional space. Based on the positioning results, the corresponding energy consumption increment value is extracted. Here, an interpolation algorithm, such as multi-dimensional linear interpolation or radial basis function interpolation, is used to perform smoothing estimation between discrete historical data points to obtain a more accurate energy consumption increment prediction. Finally, the extracted energy consumption increment value is added to the rated energy consumption of the equipment to obtain the equipment energy consumption of each operation link. In order to adapt to different working conditions, this method also introduces a dynamic baseline adjustment mechanism to dynamically adjust the rated energy consumption according to seasonal changes, equipment aging and other factors.

[0071] Step 50: Determine the target energy-saving decision based on the equipment energy consumption of each operation link.

[0072] In the embodiment of the present application, the target energy-saving decision refers to a specific strategy and optimal solution formulated to reduce energy consumption based on the energy consumption analysis of equipment in each operating link.

[0073] Specifically, a multi-objective optimization algorithm can be used to balance multiple goals such as reducing energy consumption, improving production efficiency, and extending equipment life. The objective functions of the optimization model include minimizing total energy consumption, maximizing production output, and minimizing equipment maintenance costs. Constraints include production quality requirements, safety standards, and environmental protection restrictions. In order to deal with the uncertainty in the objective function, fuzzy logic theory is introduced to convert qualitative management goals into quantifiable optimization parameters. In the specific target energy-saving decision-making process, the system will identify energy consumption hotspots and potential energy-saving opportunities based on the energy consumption analysis results. For example, for high-energy-consuming equipment, it may be recommended to adjust operating parameters, optimize start-stop strategies, or upgrade equipment; for links with low energy utilization efficiency, it may be recommended to improve process flow or introduce new technologies. At the same time, the system will also consider the peak-valley price difference of energy, formulate a staggered production plan, and further reduce energy costs.

[0074] Based on the above embodiment, as an optional embodiment, the step of determining the target energy-saving decision based on the equipment energy consumption of each operation link further includes the following steps: Step 501: Construct an energy consumption scheduling model based on the ant colony optimization algorithm.

[0075] Step 502: Determine the optimal energy consumption path based on the energy consumption scheduling model.

[0076] Specifically, first, an energy consumption scheduling model based on the ant colony optimization algorithm is constructed. The energy consumption scheduling model regards the equipment of each operation link as a node in the network, and the energy and material flow between the equipment as the path. The pheromone of the ant colony algorithm is defined as energy efficiency, and the path length corresponds to the energy consumption. The objective function of the model includes minimizing total energy consumption, maximizing production efficiency, and balancing equipment load. Constraints include production requirements, equipment operation restrictions, and energy supply restrictions. In order to improve the adaptability of the model, this embodiment introduces an adaptive parameter adjustment mechanism, which can dynamically adjust the pheromone volatility rate and heuristic information weight according to feedback during the search process. Based on the constructed energy consumption scheduling model, the improved ant colony algorithm is used to determine the optimal energy consumption path. The improvements include introducing an elite ant strategy to retain the optimal solution in each iteration; using a crossover operation to increase the diversity of solutions; and using a local search algorithm to further optimize the global optimal solution to obtain the optimal energy consumption path.

[0077] Step 503: Generate a device operation schedule and power adjustment plan based on the optimal energy consumption path.

[0078] Specifically, when generating the equipment operation schedule, this embodiment takes into account the additional energy consumption and wear caused by the start and stop of the equipment. By introducing the start and stop penalty factor, the model tends to generate a schedule with fewer start and stop times, thereby reducing energy waste and extending the life of the equipment. At the same time, in order to cope with the uncertainty in the production process and considering the fluctuation range of key parameters (such as production demand and equipment efficiency), a schedule with a certain fault tolerance is generated. In the formulation of the power regulation scheme, a dynamic programming algorithm is used to optimize the power curve of each device. The algorithm divides the time into several discrete time periods and finds the optimal power level in each time period. In order to ensure the smoothness of power regulation and the safe operation of the equipment, power change rate limits and equipment operating point constraints are added to the model. At the same time, considering the time-varying characteristics of energy prices, this method introduces a time-differentiated electricity price model to further optimize energy costs while ensuring the minimum total energy consumption.

[0079] Step 504: Formulate a target energy-saving decision based on the equipment operation schedule and the power adjustment plan.

[0080] Specifically, key energy-saving opportunities are identified based on the equipment operation schedule and power regulation plan. For example, for equipment that starts and stops frequently, it may be recommended to adopt new soft start technology or optimize production scheduling; for equipment that runs at low load for a long time, it may be recommended to update equipment or improve processes. At the same time, the system will also consider the peak and valley price difference of energy and formulate staggered production plans to further reduce energy costs. In order to ensure the feasibility of decisions, this method designs a hierarchical implementation strategy, which divides energy-saving measures into three levels: short-term, medium-term and long-term. Short-term measures mainly focus on operation optimization, medium-term measures involve equipment modification and process adjustment, and long-term measures include technological innovation and process reengineering.

[0081] See also Figure 3 , is a module schematic diagram of a linkage analysis system of blasting parameters and fragmentation size provided in an embodiment of the present application, the linkage analysis system of blasting parameters and fragmentation size may include: a model building module, a blasting parameter determination module, a fragmentation size determination module, an equipment energy consumption determination module and an energy-saving decision determination module, wherein: A model building module is used to build a target relationship model between blasting parameters and fragmentation size; A blasting parameter determination module, used to obtain geological data of the mine and determine blasting parameters based on the geological data; A fragmentation determination module, used to determine the fragmentation according to the blasting parameters and the target relationship model; An equipment energy consumption determination module, used to determine the equipment energy consumption of each operation link based on the blasting parameters and the fragmentation size; The energy-saving decision determination module is used to determine the target energy-saving decision based on the equipment energy consumption of each operation link.

[0082] Optionally, the model building module is also used to obtain historical blasting data, divide the historical blasting data into a training set and a verification set, the historical blasting data including blasting parameters and fragmentation data corresponding to the blasting parameters; based on the historical blasting data, use a machine learning algorithm to build a relationship model between the blasting parameters and the fragmentation; train the association model based on the training set, and verify the trained association model based on the verification set to obtain a target relationship model between blasting parameters and fragmentation.

[0083] Optionally, the blasting parameter determination module is also used to extract key geological parameters related to blasting parameters from the geological data; obtain initial blasting parameters based on the key geological parameters and a preset blasting parameter calculation model; and adjust the initial blasting parameters based on the mining requirements of the mine and preset blasting standards to obtain blasting parameters.

[0084] Optionally, the fragmentation size determination module is also used to input the blasting parameters into the target relationship model to obtain a fragmentation size distribution; based on the fragmentation size distribution, calculate the average fragmentation size and the maximum fragmentation size; determine whether the average fragmentation size and the maximum fragmentation size both meet preset fragmentation requirements; if the fragmentation requirements are not met, adjust the blasting parameters at least once, and input the adjusted blasting parameters into the target relationship model for iteration until the obtained fragmentation size meets the fragmentation requirements or reaches a preset number of iterations, and output the fragmentation size.

[0085] Optionally, the equipment energy consumption determination module is further used to obtain multi-dimensional data of the equipment of each operation link, wherein the multi-dimensional data at least includes equipment vibration, equipment noise and equipment temperature; based on the blasting parameters and the crushing fragmentation, determine the standard range corresponding to the multi-dimensional data of each equipment; The deviation values ​​between the multi-dimensional data and the corresponding standard range are calculated respectively; and the equipment energy consumption of each operation link is calculated according to the deviation values.

[0086] Optionally, the equipment energy consumption determination module is also used to establish a correspondence map between multi-dimensional data deviation values ​​and energy consumption increments; locate each of the deviation values ​​in the correspondence map to obtain a positioning result corresponding to each of the deviation values; based on each of the positioning results, extract the corresponding energy consumption increment value; add each of the energy consumption increment values ​​to the rated energy consumption of the equipment to obtain the equipment energy consumption of each operation link.

[0087] Optionally, the energy-saving decision determination module is also used to construct an energy consumption scheduling model based on the ant colony optimization algorithm; based on the energy consumption scheduling model, determine the optimal energy consumption path; based on the optimal energy consumption path, generate an equipment operation schedule and a power adjustment plan; and formulate a target energy-saving decision in combination with the equipment operation schedule and the power adjustment plan.

[0088] It should be noted that: when the system provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0089] An embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded by a processor and executing a linkage analysis method of blasting parameters and fragmentation size in the above embodiment. The specific execution process can be found in the specific description of the above embodiment, which will not be repeated here.

[0090] Please refer to Figure 3 The application also discloses an electronic device. Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0091] The communication bus 302 is used to realize the connection and communication between these components.

[0092] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0093] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0094] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0095] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 The memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for a linkage analysis method of blasting parameters and fragmentation size.

[0096] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program stored in the memory 305 for a linkage analysis method of blasting parameters and fragmentation size. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described order of actions, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0097] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0098] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0099] 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, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0101] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0102] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0103] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A linkage analysis method for blasting parameters and fragmentation size, characterized in that: include: Construct the target relationship model between blasting parameters and fragmentation size; Acquiring geological data of the mine, and determining blasting parameters based on the geological data; Determine the fragmentation size according to the blasting parameters and the target relationship model; Based on the blasting parameters and the fragmentation size, determine the energy consumption of equipment in each operation link; The target energy-saving decision is determined based on the equipment energy consumption of each operation link.

2. The linkage analysis method of blasting parameters and fragmentation size according to claim 1 is characterized in that: The method of constructing a target relationship model between blasting parameters and fragmentation size includes: Acquire historical blasting data, and divide the historical blasting data into a training set and a validation set, wherein the historical blasting data includes blasting parameters and fragmentation data corresponding to the blasting parameters; Based on the historical blasting data, a machine learning algorithm is used to construct a relationship model between the blasting parameters and the fragmentation size; The association model is trained based on the training set, and the trained association model is verified based on the verification set to obtain a target relationship model between blasting parameters and fragmentation size.

3. The linkage analysis method of blasting parameters and fragmentation size according to claim 1 is characterized in that: The step of determining blasting parameters based on the geological data comprises: extracting key geological parameters related to blasting parameters from the geological data; Based on the key geological parameters and a preset blasting parameter calculation model, initial blasting parameters are obtained; The initial blasting parameters are adjusted based on the mining requirements of the mine and the preset blasting standards to obtain blasting parameters.

4. The linkage analysis method of blasting parameters and fragmentation size according to claim 1 is characterized in that: The determining of the fragmentation size according to the blasting parameters and the target relationship model includes: Inputting the blasting parameters into the target relationship model to obtain the fragmentation distribution; Based on the fragmentation distribution, an average fragmentation size and a maximum fragmentation size are calculated; Determining whether the average crushing size and the maximum crushing size both meet preset crushing requirements; If the crushing requirement is not met, the blasting parameters are adjusted at least once, and the adjusted blasting parameters are input into the target relationship model for iteration until the obtained crushing fragmentation meets the crushing requirement or reaches a preset number of iterations, and the crushing fragmentation is output.

5. The linkage analysis method of blasting parameters and fragmentation size according to claim 1 is characterized in that: The determining of the equipment energy consumption of each operation link based on the blasting parameters and the fragmentation size includes: Acquire multi-dimensional data of equipment in each of the operation links, wherein the multi-dimensional data at least includes equipment vibration, equipment noise and equipment temperature; Based on the blasting parameters and the fragmentation size, determining a standard range corresponding to the multi-dimensional data of each of the devices; Calculating the deviation values ​​of the multi-dimensional data from the corresponding standard range respectively; The equipment energy consumption of each operation link is calculated according to the deviation value.

6. The linkage analysis method of blasting parameters and fragmentation size according to claim 5 is characterized in that: The calculating the equipment energy consumption of each operation link according to the deviation value includes: Establish a corresponding relationship map between multi-dimensional data deviation values ​​and energy consumption increments; Positioning each of the deviation values ​​in the corresponding relationship map to obtain a positioning result corresponding to each of the deviation values; Based on each of the positioning results, extracting a corresponding energy consumption increment value; The energy consumption increment values ​​are added to the rated energy consumption of the equipment to obtain the equipment energy consumption of each operation link.

7. The linkage analysis method of blasting parameters and fragmentation size according to claim 1 is characterized in that: The target energy-saving decision is determined based on the equipment energy consumption of each operation link, including: Construct an energy consumption scheduling model based on ant colony optimization algorithm; Based on the energy consumption scheduling model, determining an optimal energy consumption path; Based on the optimal energy consumption path, generate a device operation schedule and a power adjustment plan; A target energy-saving decision is made by combining the equipment operation schedule and the power regulation scheme.

8. A linkage analysis system for blasting parameters and fragmentation size, characterized in that: The system comprises: A model building module is used to build a target relationship model between blasting parameters and fragmentation size; A blasting parameter determination module, used to obtain geological data of the mine and determine blasting parameters based on the geological data; A fragmentation determination module, used to determine the fragmentation according to the blasting parameters and the target relationship model; An equipment energy consumption determination module, used to determine the equipment energy consumption of each operation link based on the blasting parameters and the fragmentation size; The energy-saving decision determination module is used to determine the target energy-saving decision based on the equipment energy consumption of each operation link.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

Images