Dust control method and device in open-pit mining process

Abstract

The invention discloses a dust control method and device in an open-pit mining process. The method comprises the following steps: receiving dust monitoring data transmitted by a dust monitoring meteorological station; inputting the dust monitoring data into a dust prediction model, and processing the dust monitoring data by using the dust prediction model to obtain a dust distribution condition in the mining environment; analyzing and processing the dust distribution condition by utilizing a prevention and control strategy generation model to obtain a dust prevention and control strategy for preventing and controlling dust in the mining environment; and executing dust control operation according to the dust control strategy, so that the dust concentration of the dust in the mining environment is not higher than the concentration threshold value. The technical problem that dust control is difficult to achieve fixed-point capture and directional control due to the fact that stope dust has the remarkable characteristics of multiple dust sources, large dust production amount, unfixed diffusion mode and direction and the like in the prior art is solved.

Description

Technical Field

[0001] The invention relates to the technical field of dust prevention in open-pit mining, and in particular to a method and device for preventing and controlling dust in an open-pit mining process. Background Art

[0002] Coal open-pit mining is essentially a complex and orderly evolution process from the physical structure space of large-scale earth and stone crushing and transportation to the physical structure space of disposal and reshaping, involving multiple links such as drilling, blasting, mining, transportation, crushing, disposal, etc. In each production link, under the influence of high-intensity destruction and disturbance, the dust in the mining area presents significant characteristics such as multiple dust sources, large dust production, and unfixed diffusion mode and direction, making it difficult to achieve fixed-point capture and directional control of dust prevention and control.

[0003] With regard to the problem in the above-mentioned related technologies that dust in mining areas is difficult to achieve fixed-point capture and directional control due to its significant characteristics such as multiple dust sources, large dust production, and unstable diffusion patterns and directions, no effective solution has been proposed so far. Summary of the invention

[0004] The embodiments of the present invention provide a method and device for dust control in open-pit mining, so as to at least solve the technical problem in the related art that dust control is difficult to achieve fixed-point capture and directional control due to the significant characteristics of dust in the mining area, such as multiple dust sources, large dust production, and unstable diffusion mode and direction.

[0005] According to one aspect of an embodiment of the present invention, a method for preventing and controlling dust in an open-pit mining process is provided, comprising: receiving dust monitoring data transmitted by a dust monitoring meteorological station, wherein the dust monitoring data is data obtained by monitoring a mining environment in an open-pit mining process by a plurality of sensors deployed at the dust monitoring meteorological station; inputting the dust monitoring data into a dust prediction model, so as to process the dust monitoring data using the dust prediction model to obtain a dust distribution condition in the mining environment, wherein the dust prediction model is obtained by training using a plurality of groups of first training data in a machine learning manner, and each of the plurality of groups of first training data comprises: sample dust monitoring data, data corresponding to the sample The dust monitoring data corresponds to a sample dust distribution condition, wherein the dust distribution condition refers to the dust concentration at different spatial positions in the mining environment at different time points; the dust distribution condition is analyzed and processed using a prevention and control strategy generation model to obtain a dust prevention and control strategy for preventing and controlling dust in the mining environment, wherein the prevention and control strategy generation model is trained using multiple groups of second training data using a machine learning method, and each of the multiple groups of second training data includes: a sample dust distribution condition, and a sample dust prevention and control strategy corresponding to the sample dust distribution condition; dust prevention and control operations are performed in accordance with the dust prevention and control strategy, so that the dust concentration of the dust in the mining environment is not higher than a concentration threshold.

[0006] Optionally, receiving dust monitoring data transmitted by a dust monitoring meteorological station includes: receiving a communication connection request sent by the dust monitoring meteorological station; establishing a communication channel for communication transmission with the dust monitoring meteorological station based on the communication connection request; and receiving the dust monitoring data transmitted by the dust monitoring meteorological station based on the communication channel.

[0007] Optionally, before the dust monitoring data is input into the dust prediction model so as to process the dust monitoring data using the dust prediction model to obtain the dust distribution status in the mining environment, the dust prevention and control method in the open-pit mining process also includes: obtaining multiple groups of historical dust monitoring data within a historical time period; performing data cleaning and missing value processing on the multiple groups of historical dust monitoring data to obtain a sample test data set; arranging the multiple groups of historical dust monitoring data according to the collection period to which the collection time belongs to obtain a sample training data set; and using the multiple groups of sample training data in the sample training data set to perform machine learning. Iterative training is performed until an iteration termination condition is reached to obtain an initial dust prediction model, wherein each of the multiple groups of sample training data includes: sample dust monitoring data, and sample dust distribution conditions corresponding to the sample dust monitoring data, and the iteration termination condition includes at least one of the following: the number of iterations reaches a preset number of iterations, and the prediction error is less than an error threshold; a performance evaluation is performed on the initial dust prediction model using a sample test data set to obtain an evaluation result; when the evaluation result indicates that the current performance of the dust prediction model reaches a preset performance indicator, the initial dust prediction model is determined to be the dust prediction model.

[0008] Optionally, the multiple groups of historical dust monitoring data are sorted according to the collection period to which the collection time belongs to obtain a sample training data set, including: dividing the collection period into multiple different collection sub-periods, wherein the period length of each of the collection sub-periods is different; sorting the multiple groups of historical dust monitoring data according to the collection sub-period to which the collection time belongs to obtain multiple sample training data subsets; determining the multiple sample training data subsets as different sample training data sets.

[0009] Optionally, iterative training is performed using multiple groups of sample training data in the sample training data set through machine learning until the iteration termination condition is reached, thereby obtaining an initial dust prediction model, including: discretizing the historical mining environment within the historical time period to obtain multiple grid units, wherein each of the grid units represents a local area in the historical mining environment; determining the historical dust distribution status of each of the grid units within the historical time period based on the multiple groups of sample training data; constructing an Euler model and a partial differential diffusion equation based on the historical dust distribution status of each of the grid units; using the Euler model and the partial differential diffusion equation as loss functions, and iterative training is performed using multiple groups of sample training data in the sample training data set through machine learning until the iteration termination condition is reached, thereby obtaining the initial dust prediction model, wherein the loss function is used to determine the prediction error.

[0010] Optionally, constructing an Euler model and a partial differential diffusion equation according to the historical dust distribution conditions of each of the grid units includes: constructing the Euler model using a first formula according to the historical dust distribution conditions of each of the grid units, wherein the first formula is: represents the rate of change of dust concentration C with time t, D represents the diffusion coefficient, represents the Laplace operator, V represents the wind speed vector, represents the gradient operator, C(x, t) represents the dust concentration of the grid unit with spatial coordinate x at time t; the partial differential diffusion equation is constructed using the second formula according to the historical dust distribution status of each grid unit, wherein the second formula is: C(x, y, t) represents the dust concentration of the grid unit with spatial coordinates (x, y) at time t, and C0 represents the dust concentration at the initial collection time.

[0011] Optionally, performing dust control operations in accordance with the dust control strategy so that the dust concentration of the dust in the mining environment is not higher than a concentration threshold includes at least one of the following: controlling a spray component in accordance with the dust control strategy to perform the dust control operation so that the dust concentration of the dust in the mining environment is not higher than the concentration threshold, wherein the spray component performs the dust control operation by adjusting the spray frequency and the water spray volume in accordance with the dust control strategy; controlling a ventilation component in accordance with the dust control strategy to perform the dust control operation so that the dust concentration of the dust in the mining environment is not higher than the concentration threshold, wherein the ventilation component performs the dust control operation by adjusting the wind direction and the wind speed in accordance with the dust control strategy.

[0012] According to another aspect of an embodiment of the present invention, a dust control device for open-pit mining is provided, comprising: a receiving unit for receiving dust monitoring data transmitted by a dust monitoring meteorological station, wherein the dust monitoring data is data obtained by monitoring the mining environment during open-pit mining by multiple sensors deployed at the dust monitoring meteorological station; a first acquisition unit for inputting the dust monitoring data into a dust prediction model, so as to process the dust monitoring data using the dust prediction model to obtain the dust distribution status in the mining environment, wherein the dust prediction model is obtained by training using multiple groups of first training data using a machine learning method, and each of the multiple groups of first training data includes: sample dust monitoring data, and the The sample dust distribution status corresponding to the sample dust monitoring data, the dust distribution status refers to the dust concentration at different spatial positions in the mining environment at different time points; a second acquisition unit, used to analyze and process the dust distribution status using a prevention and control strategy generation model, to obtain a dust prevention and control strategy for preventing and controlling dust in the mining environment, wherein the prevention and control strategy generation model is trained using multiple groups of second training data using a machine learning method, and each of the multiple groups of second training data includes: sample dust distribution status, and a sample dust prevention and control strategy corresponding to the sample dust distribution status; an execution unit, used to perform dust prevention and control operations according to the dust prevention and control strategy, so that the dust concentration of the dust in the mining environment is not higher than a concentration threshold.

[0013] Optionally, the receiving unit includes: a first receiving module, used to receive a communication connection request sent by the dust monitoring meteorological station; an establishing module, used to establish a communication channel for communication transmission with the dust monitoring meteorological station based on the communication connection request; and a second receiving module, used to receive the dust monitoring data transmitted by the dust monitoring meteorological station based on the communication channel.

[0014] Optionally, the dust prevention and control device in the open-pit mining process also includes: a third acquisition unit, which is used to obtain multiple groups of historical dust monitoring data within a historical time period before inputting the dust monitoring data into the dust prediction model to process the dust monitoring data using the dust prediction model to obtain the dust distribution status in the mining environment; a fourth acquisition unit, which is used to perform data cleaning and missing value processing on the multiple groups of historical dust monitoring data to obtain a sample test data set; a fifth acquisition unit, which is used to sort the multiple groups of historical dust monitoring data according to the collection period to which the collection time belongs to obtain a sample training data set; a sixth acquisition unit, which is used to use the multiple groups of sample training data in the sample training data set Iterative training is performed by machine learning until an iteration termination condition is reached to obtain an initial dust prediction model, wherein each of the multiple groups of sample training data includes: sample dust monitoring data, sample dust distribution conditions corresponding to the sample dust monitoring data, and the iteration termination condition includes at least one of the following: the number of iterations reaches a preset number of iterations, and the prediction error is less than an error threshold; a seventh acquisition unit is used to perform performance evaluation on the initial dust prediction model using a sample test data set to obtain an evaluation result; a determination unit is used to determine that the initial dust prediction model is the dust prediction model when the evaluation result indicates that the current performance of the dust prediction model reaches a preset performance indicator.

[0015] Optionally, the fifth acquisition unit includes: a division module, used to divide the collection period into multiple different collection sub-periods, wherein the period duration of each collection sub-period is different; a first acquisition module, used to sort the multiple groups of historical dust monitoring data according to the collection sub-periods to which the collection time belongs, to obtain multiple sample training data subsets; a first determination module, used to determine that the multiple sample training data subsets are different sample training data sets.

[0016] Optionally, the sixth acquisition unit includes: a second acquisition module, used to discretize the historical mining environment within the historical time period to obtain multiple grid units, wherein each of the grid units represents a local area in the historical mining environment; a second determination module, used to determine the historical dust distribution status of each of the grid units within the historical time period based on multiple groups of sample training data; a construction module, used to construct an Euler model and a partial differential diffusion equation based on the historical dust distribution status of each of the grid units; a third acquisition module, used to use the Euler model and the partial differential diffusion equation as loss functions, and use multiple groups of the sample training data in the sample training data set to perform iterative training through machine learning until the iteration termination condition is reached, so as to obtain the initial dust prediction model, wherein the loss function is used to determine the prediction error.

[0017] Optionally, the construction module includes: a first construction submodule, configured to construct the Euler model using a first formula according to the historical dust distribution status of each grid unit, wherein the first formula is: represents the rate of change of dust concentration C with time t, D represents the diffusion coefficient, represents the Laplace operator, represents the wind speed vector, represents a gradient operator, C(x, t) represents the dust concentration of the grid unit with spatial coordinate x at time t; a second construction submodule is used to construct the partial differential diffusion equation using a second formula according to the historical dust distribution status of each grid unit, wherein the second formula is: C(x, y, t) represents the dust concentration of the grid unit with spatial coordinates (x, y) at time t, and C0 represents the dust concentration at the initial collection time.

[0018] Optionally, the execution unit includes at least one of the following: a first execution module, used to control the spray component to perform the dust control operation according to the dust control strategy, so that the dust concentration of the dust in the mining environment is not higher than the concentration threshold, wherein the spray component performs the dust control operation by adjusting the spray frequency and the water spraying amount according to the dust control strategy; a second execution module, used to control the ventilation component to perform the dust control operation according to the dust control strategy, so that the dust concentration of the dust in the mining environment is not higher than the concentration threshold, wherein the ventilation component performs the dust control operation by adjusting the wind direction and wind speed according to the dust control strategy.

[0019] According to another aspect of an embodiment of the present invention, a dust control system for open-pit mining is provided. The dust control system for open-pit mining uses any one of the above-mentioned dust control methods for open-pit mining.

[0020] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, wherein the computer-readable storage medium includes a stored program, wherein the program executes any one of the above-mentioned dust prevention and control methods in an open-pit mining process.

[0021] According to another aspect of an embodiment of the present invention, a processor is further provided, the processor being used to run a program, wherein when the program is run, any one of the above-mentioned dust prevention and control methods in an open-pit mining process is executed.

[0022] According to another aspect of an embodiment of the present invention, a computer program product is provided, comprising computer instructions, which, when executed by a processor, execute any one of the above-mentioned methods for preventing and controlling dust in an open-pit mining process.

[0023] In an embodiment of the present invention, dust monitoring data transmitted by a dust monitoring meteorological station is received, wherein the dust monitoring data is data obtained by monitoring the mining environment during open-pit mining using multiple sensors deployed at the dust monitoring meteorological station; the dust monitoring data is input into a dust prediction model, so that the dust monitoring data is processed using the dust prediction model to obtain dust distribution conditions in the mining environment, wherein the dust prediction model is trained using multiple groups of first training data using a machine learning method, and each of the multiple groups of first training data includes: sample dust monitoring data, sample dust distribution conditions corresponding to the sample dust monitoring data, and the dust distribution conditions refer to dust concentrations at different spatial positions in the mining environment at different time points; the dust distribution conditions are analyzed and processed using a prevention and control strategy generation model to obtain a dust prevention and control strategy for preventing and controlling dust in the mining environment; dust prevention and control operations are performed according to the dust prevention and control strategy to ensure that the dust concentration in the mining environment is not higher than a concentration threshold. Through the above technical scheme, the dust data collected by monitoring the on-site mining environment using the machine learning trained model is processed to generate the corresponding prevention and control strategy, and the purpose of dust prevention and control is carried out according to the strategy. The technical effect of using the model to monitor and analyze the dust concentration and diffusion trend in real time and formulate prevention and control measures in time is realized, which improves the efficiency and quality of dust prevention and control, provides safety protection for open-pit coal mining, and solves the technical problem in related technologies that dust prevention and control is difficult to achieve fixed-point capture and directional control due to the significant characteristics of dust in the mining area, such as multiple dust sources, large dust production, and non-fixed diffusion mode and direction. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0025] Figure 1 It is a hardware structure block diagram of a mobile terminal of a dust prevention and control method in an open-pit mining process according to an embodiment of the present invention;

[0026] Figure 2 is a flow chart of a dust prevention and control method in an open-pit mining process according to an embodiment of the present invention;

[0027] Figure 3 Schematic diagram of a dust control device in an open-pit mining process according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] As introduced in the background technology, in the related technology, dust in the mining field has many significant characteristics such as multiple dust sources, large dust production, and unfixed diffusion mode and direction, which makes it difficult to achieve fixed-point capture and directional control of dust. In view of the above defects, a method and device for dust control in open-pit mining are provided in an embodiment of the present invention.

[0031] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0032] The method embodiments provided in the embodiments of the present invention can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal for a dust prevention method in an open-pit mining process according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0033] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the dust prevention and control method in the open-pit mining process in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] According to an embodiment of the present invention, a method embodiment of a dust control method in an open-pit mining process is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0035] Figure 2 : is a flow chart of a dust prevention method in an open-pit mining process according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0036] Step S202, receiving dust monitoring data transmitted by a dust monitoring weather station, wherein the dust monitoring data is data obtained by a plurality of sensors deployed at the dust monitoring weather station to monitor the mining environment during open-pit mining.

[0037] In this embodiment, a dust monitoring weather station can be deployed. The weather station can specifically include various sensors for obtaining wind speed data, wind direction data, temperature and humidity data, and dust concentration data. The anemometer, wind vane, temperature sensor, and humidity sensor are all commercially available mature sensors, and the dust concentration sensor can actually be a mine dust sampler, a direct-reading dust meter, and a mine dust sensor. The dust monitoring weather station is equipped with solar panels to power various sensors. At the same time, a communication unit is deployed on the weather station, so that multiple weather stations can communicate with the host computer and send monitoring data in real time. In addition to the wind speed, wind direction, temperature, and relative humidity described above, the monitoring data can also include rainfall information. The data collected by the dust monitoring weather station during the monitoring process can be transmitted to the host computer.

[0038] According to the above embodiment of the present invention, in the above step S202, dust monitoring data transmitted by the dust monitoring meteorological station is received, including: receiving a communication connection request sent by the dust monitoring meteorological station; establishing a communication channel for communication transmission with the dust monitoring meteorological station based on the communication connection request; and receiving dust monitoring data transmitted by the dust monitoring meteorological station based on the communication channel.

[0039] Specifically, when the host computer receives a communication connection request sent by the dust monitoring meteorological station, it can establish a communication channel for communication transmission with the dust monitoring meteorological station based on the connection request, so as to receive dust monitoring data transmitted by the dust monitoring meteorological station through the communication channel.

[0040] Step S204, input the dust monitoring data into the dust prediction model, so as to process the dust monitoring data using the dust prediction model to obtain the dust distribution status in the mining environment, wherein the dust prediction model is trained using multiple groups of first training data using machine learning, and each of the multiple groups of first training data includes: sample dust monitoring data, and sample dust distribution status corresponding to the sample dust monitoring data, and the dust distribution status refers to the dust concentration at different spatial positions in the mining environment at different time points.

[0041] In this embodiment, a machine learning method can be used to construct and train a dust prediction model, so that the dust prediction model can be used to predict the dust distribution conditions in the mining environment based on dust monitoring data. The dust distribution conditions here may include but are not limited to: dust concentration, dust diffusion trend, etc.

[0042] According to the above embodiment of the present invention, before the above step S204, that is, before the dust monitoring data is input into the dust prediction model to process the dust monitoring data using the dust prediction model to obtain the dust distribution status in the mining environment, the dust prevention and control method in the open-pit mining process also includes: obtaining multiple groups of historical dust monitoring data within a historical time period; performing data cleaning and missing value processing on the multiple groups of historical dust monitoring data to obtain a sample test data set; arranging the multiple groups of historical dust monitoring data according to the collection period to which the collection time belongs to obtain a sample training data set; using the multiple groups of sample training data in the sample training data set to obtain a sample training data set; The training data is iteratively trained by machine learning until the iteration termination condition is reached to obtain an initial dust prediction model, wherein each group of multiple groups of sample training data includes: sample dust monitoring data, sample dust distribution conditions corresponding to the sample dust monitoring data, and the iteration termination condition includes at least one of the following: the number of iterations reaches a preset number of iterations, and the prediction error is less than an error threshold; the performance of the initial dust prediction model is evaluated using the sample test data set to obtain an evaluation result; when the evaluation result indicates that the current performance of the dust prediction model reaches the preset performance index, the initial dust prediction model is determined to be the dust prediction model.

[0043] Specifically, when training the dust prediction model, after receiving the monitoring data sent by the meteorological station, the upper computer can first clean the monitoring data collected in the sampling period (4-8h) and process the missing values ​​to form a validation set (i.e., a sample test data set), and then introduce the historical data of a period (year or quarter) corresponding to the monitoring data entry stored in the remote server to form a training set (i.e., multiple groups of sample training data); then, iterative training is performed based on the training set using machine learning until the iteration termination condition is reached, and the model currently trained is determined to be the initial dust prediction model; thereafter, the validation set can be used to evaluate the performance of the initial dust prediction model, and the difference between the predicted results and the actual monitoring data is compared, so that when the performance can reach the preset performance index, it can be understood that the difference between the predicted results and the actual results of the initial dust prediction model meets the error requirement (i.e., the prediction error is less than the error threshold), and the initial dust prediction model is determined to be the dust prediction model, and the dust prediction model can be formally used for prediction.

[0044] In addition, when the host computer processes the received dust monitoring data, it can perform data missing value processing and normalization processing on it, as follows:

[0045] 1) Data missing value processing: In the process of pollution data and meteorological data monitoring, data may be missing due to sensor failure, network interruption, storage failure, etc. These low-quality data will affect the learning results of the model and cause the final prediction accuracy to be low. Therefore, the data needs to be preprocessed before model training. There are many methods for missing data processing, which can be roughly divided into two categories: tuple deletion and data filling: ① Tuple deletion method, that is, directly deleting the missing data pairs. This method is effective when the data volume is large and the missing values ​​are small. However, this method ensures data integrity by reducing the data volume, which may discard some information hidden in the missing values. If the data volume is small, it will cause serious damage to the data quality; ② Data filling method, that is, using special data to fill in the missing records. The simpler methods include maximum filling method and mean filling method. The maximum filling method counts the data of a certain time step before and after the missing data, and selects the maximum value to fill the missing data. This method only considers the characteristics of the single data around the missing value; the mean filling method selects the data within a certain time range before and after the missing value, and calculates the average value to fill the gap. In theory, it considers the missing data around The overall characteristics of the data can also be used to fill in missing data based on the statistical laws of the data. Commonly used methods include regression method, maximum expectation value method, multiple filling method, etc. The regression method simulates the linear relationship of the entire data set, and establishes a regression equation for the entire data set to obtain the number of missing data; the maximum expectation value method is an iterative method for calculating the maximum likelihood estimate. In each iteration cycle, the expected value and parameter value are calculated alternately until the parameter value change between two iterations is less than the threshold. This method is suitable for samples with large amounts of data, but the calculation is complex and converges slowly. The core idea of ​​the multiple filling method is to generate multiple sets of candidate data by simulating the distribution of missing data, and then use mathematical statistics to analyze the data set after filling and improving with multiple sets of candidate data, and select the candidate data with the best analysis results for filling the final data set. Considering that air pollution data and meteorological data change slowly over time in most cases, there is generally no sudden change in values. Therefore, the mean method with a relatively simple calculation process is used to process missing values. The missing values ​​are filled by calculating the average value of the data in a certain time range before and after the missing values, which can achieve a better restoration effect.

[0046] 2) Normalization: Usually, the training data contains multiple features, and the dimensions and magnitudes of each feature are different. If the sample values ​​of some features are very different from those of other features, it may lead to slow convergence during model training and reduce the accuracy of model training. Therefore, data normalization is required before model training. Data normalization aims to make the data dimensionless and scale it to the same interval, so that each feature is comparable, and the trend and relative size of the scaled data do not change. Deviation standardization and z-score standardization are commonly used data normalization methods, and different methods are suitable for different scenarios. Deviation standardization is to linearly scale the original sample data so that it is distributed between 0 and 1, which is suitable for data that is distributed in a limited range. The z-score standardization method is to subtract the difference between the sample mean of all original sample data and then calculate the quotient with the sample standard deviation, so that all data are converted to values ​​near 0. This method is suitable for situations where the data distribution range is wide and there is no obvious boundary, and the maximum or minimum value exceeds the normal value range.

[0047] In a specific embodiment of the present invention, multiple groups of historical dust monitoring data are sorted according to the collection period to which the collection time belongs to obtain a sample training data set, including: dividing the collection period into multiple different collection sub-periods, wherein the period length of each collection sub-period is different; sorting multiple groups of historical dust monitoring data according to the collection sub-period to which the collection time belongs to obtain multiple sample training data subsets; determining the multiple sample training data subsets as different sample training data sets.

[0048] Specifically, in the training process of supervised machine learning, the data set can be divided into three parts according to the three stages of model training: the first part is the training set, which is used for the initial training of the model. During the training process, an appropriate model parameter tuning method is used to allow the model to autonomously adjust and determine the network weights to obtain the initial training model. Of course, the same training set includes a first subset, a second subset, a third subset, and a fourth subset corresponding to different time periods; the second part is the validation set, which uses the validation data set to evaluate the prediction deviation of the model, and adjusts the model again according to the prediction effect obtained on the validation set, including the model's network node number, learning rate and other hyperparameters, or redesigns the network model to achieve the optimal result; the third part is the test set. After the model passes the test of the validation set, the test set data is used to finally test the prediction effect of the model. The test set in the present invention can be composed of the current monitoring data of all meteorological stations in the current mine. By dividing and using the three data sets separately, the model prediction accuracy can be improved and the risk of overfitting can be greatly reduced.

[0049] In another specific embodiment of the present invention, iterative training is performed using multiple groups of sample training data in a sample training data set through machine learning until an iteration termination condition is reached, thereby obtaining an initial dust prediction model, including: discretizing the historical mining environment within the historical time period to obtain multiple grid units, wherein each grid unit represents a local area in the historical mining environment; determining the historical dust distribution status of each grid unit within the historical time period based on the multiple groups of sample training data; constructing an Euler model and a partial differential diffusion equation based on the historical dust distribution status of each grid unit; using the Euler model and the partial differential diffusion equation as loss functions, and iterative training is performed using multiple groups of sample training data in the sample training data set through machine learning until an iteration termination condition is reached, thereby obtaining an initial dust prediction model, wherein the loss function is used to determine the prediction error.

[0050] Specifically, in the process of using a sample training data set to train the obtained dust prediction model by machine learning, the machine learning algorithm model can be trained with the training set. During the training process, the constructed Euler model can be used as part of the loss function, and the constraints of the partial differential diffusion equation can be added. In each training iteration, until the loss function is greater than 0 and less than 1, it should be noted here that the residuals of the partial differential diffusion equation can be approximately solved by numerical methods (such as finite difference method or finite element method), and then these residuals are used as part of the loss function and optimized together with the error of dust concentration prediction.

[0051] In the above embodiment of the present invention, the Euler model and the partial differential diffusion equation are constructed according to the historical dust distribution conditions of each grid unit, including: constructing the Euler model using the first formula according to the historical dust distribution conditions of each grid unit, wherein the first formula is: represents the rate of change of dust concentration C with time t, D represents the diffusion coefficient, represents the Laplace operator, V represents the wind speed vector, represents the gradient operator, C(x, t) represents the dust concentration of the grid cell with spatial coordinate x at time t; the partial differential diffusion equation is constructed using the second formula according to the historical dust distribution of each grid cell, where the second formula is: C(x, y, t) represents the dust concentration of the grid cell with spatial coordinates (x, y) at time t, and C0 represents the dust concentration at the initial collection moment.

[0052] Specifically, the process of constructing the Euler model is as follows: the mine environment is discretized into grid cells, which can be three-dimensional orthogonal grids. Each grid cell represents a local area in the mine operation space. The concentration at the boundary and node of each local area can be used to describe the distribution of particles or gases. It is worth noting that the mine environment has artificially specified boundary conditions to limit the solution range of the Euler diffusion model; the expression of the Euler model is: In the formula, It represents the rate of change of dust concentration C with time t, and D represents the diffusion coefficient. Since the type of dust in the mine is certain, the diffusion coefficient can be specified in advance according to the specific materials in the mine. represents the Laplace operator, V represents the wind speed vector, represents the gradient operator, C(x, t) represents the dust concentration of the grid cell with spatial coordinate x at time t; the partial differential diffusion equation is constructed using the second formula according to the historical dust distribution of each grid cell, where the second formula is: C(x, y, t) represents the dust concentration of the grid cell with spatial coordinates (x, y) at time t, and C0 represents the dust concentration at the initial collection moment.

[0053] In addition, the partial differential diffusion equation can be defined according to the Gaussian diffusion model to obtain the residual of the equation. The expression of the partial differential diffusion equation is as follows: Where C(x, y, t) represents the dust concentration of the grid unit with spatial coordinates (x, y) at time t, and C0 represents the dust concentration at the initial collection time.

[0054] It should be noted that the Euler model here uses C(x, t) to represent the dust concentration, while the partial differential diffusion equation uses C(x, y, t) to represent the dust concentration. The main difference lies in the dimension of describing dust diffusion. The Euler model is usually used to describe the movement of continuous fluids, where "x" represents the spatial coordinate and "t" represents time. C(x, t) is used here because the model may simplify the problem in the initial stage and only consider one-dimensional coordinates in space (for example, dust diffusion only along the wind direction or a specific direction). This can simplify calculations in some cases and improve the training efficiency of the model. However, the one-dimensional model may not be able to fully capture the complexity of dust diffusion in the mine, especially when dust diffusion is affected by multi-directional wind flow and terrain; the use of C(x, y, t) in the partial differential diffusion equation indicates that the equation describes the process of dust diffusion in two-dimensional space (x and y coordinates), which is usually to more accurately simulate the movement and diffusion of dust in the air above the open-pit mine, especially when considering the wind speed vector V, the wind speed vector not only has one direction (such as the x direction in the one-dimensional model), but may have wind flow in any direction on the horizontal plane, so it is necessary to describe the change of dust concentration in a two-dimensional coordinate system; in practical applications, especially in an environment such as an open-pit mine with complex terrain and multi-directional wind flow, the use of C(x, y, t) can more comprehensively reflect the diffusion law of dust in space, especially under different wind directions and wind speeds. Such an equation can describe the diffusion of dust in the x and y directions, as well as its changes over time, which is more in line with the real physical process of pollutant diffusion in the atmosphere.

[0055] In general, the difference between C(x, t) and C(x, y, t) reflects the different complexity of the model in describing the spatial dimension. The latter describes the dust diffusion in two-dimensional space and can more accurately simulate and predict the distribution of dust in the mine. If we consider that the actual mine may require a three-dimensional spatial model to more accurately describe the diffusion of dust in space (i.e. C(x, y, t)), then this enhanced dimension will further improve the accuracy of the prediction; however, increasing the dimension will make the model more complex and the computational cost will increase accordingly; therefore, when designing the model, it is necessary to balance the complexity of the model and the prediction accuracy based on actual needs and computing resources.

[0056] Step S206, using the prevention and control strategy generation model to analyze and process the dust distribution status to obtain a dust prevention and control strategy for preventing and controlling dust in the mining environment, wherein the prevention and control strategy generation model is trained using multiple groups of second training data using a machine learning method, and each of the multiple groups of second training data includes: sample dust distribution status, and a sample dust prevention and control strategy corresponding to the sample dust distribution status.

[0057] In this embodiment, after using the dust prediction model to predict the dust distribution conditions in the mining environment based on the dust monitoring data, the prevention and control strategy generation model can be used to analyze and process the predicted dust distribution conditions to generate a strategy for preventing and controlling dust in the mining environment; the prevention and control strategy generation model here is also trained by machine learning using the corresponding data training set.

[0058] Step S208, performing dust prevention operations according to the dust prevention strategy, so that the dust concentration in the mining environment is not higher than the concentration threshold.

[0059] In this embodiment, corresponding dust prevention and control operations may be performed according to the dust prevention and control strategy obtained above, so as to prevent or control the dust in the mining environment and ensure the safety of the mining environment.

[0060] According to the above embodiment of the present invention, in the above step S208, dust control operations are performed according to the dust control strategy so that the dust concentration of dust in the mining environment is not higher than the concentration threshold, including at least one of the following: controlling the spray component to perform dust control operations according to the dust control strategy so that the dust concentration of dust in the mining environment is not higher than the concentration threshold, wherein the spray component performs dust control operations by adjusting the spray frequency and water spray volume according to the dust control strategy; controlling the ventilation component to perform dust control operations according to the dust control strategy so that the dust concentration of dust in the mining environment is not higher than the concentration threshold, wherein the ventilation component performs dust control operations by adjusting the wind direction and wind speed according to the dust control strategy.

[0061] Specifically, the host computer can control the corresponding components to perform operations according to the dust control strategy to prevent and control dust; for example, the operation of the spray system can be dynamically adjusted according to the predicted dust concentration distribution, such as increasing the spray frequency or water spray volume in areas with predicted higher dust concentrations to reduce the generation and spread of dust; the ventilation system can also be adjusted or natural ventilation can be increased according to wind direction and wind speed predictions to guide airflow from low dust source areas to high dust source areas, thereby reducing the continued accumulation of dust in high concentration areas; of course, there are many other ways to prevent or control dust, which are not specifically limited here.

[0062] It should be noted that the dust control in the open-pit mining environment provided by the above-mentioned embodiment of the present invention is a dynamic process. The dust prediction model in the host computer can make real-time predictions on the dust distribution status based on the data collected in real time by the dust monitoring meteorological station and transmitted through the communication channel. Then, the prevention and control strategy generation model can also analyze and process the dust distribution status based on the real-time prediction, and generate corresponding prevention and control strategies, so that the host computer can prevent and control dust according to the generated strategies, forming a real-time dynamic process.

[0063] From the above, it can be seen that through the technical solution provided by the above embodiment of the present invention, dust monitoring data transmitted by a dust monitoring meteorological station can be received, wherein the dust monitoring data is data obtained by monitoring the mining environment during open-pit mining by multiple sensors deployed at the dust monitoring meteorological station; the dust monitoring data is input into a dust prediction model, and the dust monitoring data is processed by the dust prediction model to obtain the dust distribution status in the mining environment, wherein the dust prediction model is trained using multiple groups of first training data using a machine learning method, and each of the multiple groups of first training data includes: sample dust monitoring data, and sample dust distribution status corresponding to the sample dust monitoring data, and the dust distribution status refers to the distribution of dust at different times The dust concentration at different spatial locations in the mining environment is calculated; the dust distribution status is analyzed and processed using the prevention and control strategy generation model to obtain a dust prevention and control strategy for preventing and controlling dust in the mining environment; dust prevention and control operations are performed according to the dust prevention and control strategy to ensure that the dust concentration in the mining environment is not higher than the concentration threshold. The purpose of using the machine learning trained model to monitor the on-site mining environment and process the dust data collected to generate a corresponding prevention and control strategy, and then performing dust prevention and control according to the strategy is achieved. The technical effect of using the model to monitor and analyze dust concentration and diffusion trends in real time and formulate prevention and control measures in a timely manner is achieved, which improves the efficiency and quality of dust prevention and control and provides safety guarantees for open-pit coal mining.

[0064] Therefore, the technical solution provided by the above-mentioned embodiment of the present invention solves the technical problem in the related technology that dust prevention and control is difficult to achieve fixed-point capture and directional control due to the significant characteristics of dust in the mining area, such as multiple dust sources, large dust production, and unstable diffusion mode and direction.

[0065] In the above embodiments of the present invention, when training a dust prediction model or a control strategy generation model, the corresponding data set can be used to train the machine learning model to obtain the corresponding model; the machine learning model used here can include but is not limited to any of the following: (1) Random Forest (RF): RF is an integrated technology that can perform regression and classification tasks. It uses a bagging method to combine an integrated decision tree and use it to predict the final result. As a weaker learner in RF, the decision tree (DT) algorithm performs learning by partitioning the feature space. The partitioning rule is selected to minimize the difference in the same subgroup, which is measured by Gini impurity or entropy. The partitioning is performed until the standard is met, and then the DT model is constructed. Pruning can be used to eliminate branches that have little effect or those that have no difference in the generalization ability of DT. The main disadvantage of the DT algorithm is that its prediction performance is usually not as good as other ML technologies, such as ANN; RF is proposed to solve the weaknesses of a single DT model, and can improve the prediction accuracy without significantly increasing the amount of calculation. In addition, due to the idea of ​​integration, RF is actually equivalent to sampling both samples and features, so overfitting can be avoided. In RF, a large number of DT models are constructed and combined. For each of these DT models, it is built on different training (through sampling with replacement), more specifically, each training set has the same size as the original training set, but different internal instances, and the features used in each training set are not the same. All DT models will use the prepared training set. For the prediction of a new instance, all DT models will make a prediction and final result using majority weighting; (2) Gradient Boosting Machine (GBM): GBM is an ensemble algorithm that combines DT models together using gradient boosting. A DT model is a flowchart-like graph that shows various results based on a series of decisions. It consists of a root node, some branches, and leaf nodes. The root node contains all the data instances in the training set. According to the decision rules in the branch, the data instances are continuously classified until they reach the leaf node. The leaf node is the prediction result of the DT model. The decision rules are determined to maintain the similarity of each subgroup. DT can be used for both regression problems and classification problems. In gradient boosting, weak learners (DT models) are continuously fitted to more accurately predict the output. The newly established DT model is designed to be maximally correlated with the negative gradient of the selected loss function. That is, continuous error fitting is performed by establishing a new DT model. The model will continue until the stopping conditions such as the maximum DT model are met. The purpose is to integrate these base learners to continuously reduce the overall loss function of the model and continuously improve the model. Compared with traditional Boost ing models (such as Adaboost), GBM has greater flexibility in the choice of loss function.

[0066] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0067] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0068] According to an embodiment of the present invention, a dust control device in an open-pit mining process for implementing the above-mentioned dust control method in an open-pit mining process is also provided. Figure 3 Schematic diagram of a dust control device in an open-pit mining process according to an embodiment of the present invention. Figure 3 As shown, the device comprises: a receiving unit 31, a first acquiring unit 33, a second acquiring unit 35 and an executing unit 37. The dust prevention and control device in the open-pit mining process is described in detail below.

[0069] The receiving unit 31 is used to receive dust monitoring data transmitted by a dust monitoring meteorological station, wherein the dust monitoring data is data obtained by a plurality of sensors deployed in the dust monitoring meteorological station to monitor the mining environment during open-pit mining.

[0070] The first acquisition unit 33 is used to input the dust monitoring data into the dust prediction model so as to process the dust monitoring data using the dust prediction model to obtain the dust distribution status in the mining environment, wherein the dust prediction model is trained using multiple groups of first training data using a machine learning method, and each of the multiple groups of first training data includes: sample dust monitoring data, and sample dust distribution status corresponding to the sample dust monitoring data, and the dust distribution status refers to the dust concentration at different spatial positions in the mining environment at different time points.

[0071] The second acquisition unit 35 is used to analyze and process the dust distribution status using the prevention and control strategy generation model to obtain a dust prevention and control strategy for preventing and controlling dust in the mining environment, wherein the prevention and control strategy generation model is trained using multiple groups of second training data using a machine learning method, and each of the multiple groups of second training data includes: a sample dust distribution status and a sample dust prevention and control strategy corresponding to the sample dust distribution status.

[0072] The execution unit 37 is used to execute dust prevention operations according to the dust prevention strategy so that the dust concentration in the mining environment is not higher than the concentration threshold.

[0073] It should be noted here that the above-mentioned receiving unit 31, first acquisition unit 33, second acquisition unit 35 and execution unit 37 correspond to steps S202 to S208 in the above-mentioned embodiments, and the four units and the corresponding steps implement the same instances and application scenarios, but are not limited to the contents disclosed in the above-mentioned embodiments.

[0074] From the above, it can be seen that in the scheme recorded in the above-mentioned embodiment of the present invention, a receiving unit can be used to receive dust monitoring data transmitted by a dust monitoring meteorological station, wherein the dust monitoring data is data obtained by monitoring the mining environment during open-pit mining by multiple sensors deployed in the dust monitoring meteorological station; then the dust monitoring data is input into a dust prediction model using a first acquisition unit, so as to process the dust monitoring data using the dust prediction model to obtain the dust distribution status in the mining environment, wherein the dust prediction model is trained using multiple groups of first training data using a machine learning method, and each of the multiple groups of first training data includes: sample dust monitoring data, sample dust distribution status corresponding to the sample dust monitoring data, and the dust distribution status refers to the dust distribution status of the mining environment opened at different time points. The dust concentration at different spatial positions in the mining environment is analyzed and processed by the second acquisition unit using the prevention and control strategy generation model to obtain a dust prevention and control strategy for preventing and controlling dust in the mining environment; finally, the execution unit is used to perform dust prevention and control operations according to the dust prevention and control strategy, so that the dust concentration in the mining environment is not higher than the concentration threshold, and the purpose of using the machine learning trained model to monitor the on-site mining environment to collect dust data is achieved to generate a corresponding prevention and control strategy, and dust prevention is carried out according to the strategy. The technical effect of using the model to monitor and analyze dust concentration and diffusion trends in real time and formulate prevention and control measures in a timely manner is realized, which improves the efficiency and quality of dust prevention and control and provides safety guarantees for open-pit coal mining.

[0075] Therefore, the technical solution provided by the above-mentioned embodiment of the present invention solves the technical problem in the related technology that dust prevention and control is difficult to achieve fixed-point capture and directional control due to the significant characteristics of dust in the mining area, such as multiple dust sources, large dust production, and unstable diffusion mode and direction.

[0076] In an optional embodiment, the receiving unit includes: a first receiving module for receiving a communication connection request sent by a dust monitoring meteorological station; an establishing module for establishing a communication channel for communication transmission with the dust monitoring meteorological station based on the communication connection request; and a second receiving module for receiving dust monitoring data transmitted by the dust monitoring meteorological station based on the communication channel.

[0077] In an optional embodiment, the dust control device in the open-pit mining process also includes: a third acquisition unit, which is used to obtain multiple groups of historical dust monitoring data within a historical time period before inputting the dust monitoring data into the dust prediction model to process the dust monitoring data using the dust prediction model to obtain the dust distribution status in the mining environment; a fourth acquisition unit, which is used to perform data cleaning and missing value processing on the multiple groups of historical dust monitoring data to obtain a sample test data set; a fifth acquisition unit, which is used to sort the multiple groups of historical dust monitoring data according to the collection period to which the collection time belongs, to obtain a sample training data set; and a sixth acquisition unit, which is used to use the multiple groups of sample training data in the sample training data set to obtain a sample test data set. The training data is iteratively trained by machine learning until an iteration termination condition is reached to obtain an initial dust prediction model, wherein each of the multiple groups of sample training data includes: sample dust monitoring data, sample dust distribution conditions corresponding to the sample dust monitoring data, and the iteration termination condition includes at least one of the following: the number of iterations reaches a preset number of iterations, and the prediction error is less than an error threshold; a seventh acquisition unit is used to perform performance evaluation on the initial dust prediction model using a sample test data set to obtain an evaluation result; a determination unit is used to determine that the initial dust prediction model is the dust prediction model when the evaluation result indicates that the current performance of the dust prediction model reaches a preset performance indicator.

[0078] In an optional embodiment, the fifth acquisition unit includes: a division module, used to divide the collection period into multiple different collection sub-periods, wherein the period duration of each collection sub-period is different; a first acquisition module, used to sort multiple groups of historical dust monitoring data according to the collection sub-periods to which the collection time belongs, to obtain multiple sample training data subsets; a first determination module, used to determine that the multiple sample training data subsets are different sample training data sets.

[0079] In an optional embodiment, the sixth acquisition unit includes: a second acquisition module, which is used to discretize the historical mining environment within the historical time period to obtain multiple grid units, wherein each grid unit represents a local area in the historical mining environment; a second determination module, which is used to determine the historical dust distribution status of each grid unit within the historical time period based on multiple groups of sample training data; a construction module, which is used to construct an Euler model and a partial differential diffusion equation based on the historical dust distribution status of each grid unit; a third acquisition module, which is used to use the Euler model and the partial differential diffusion equation as loss functions, and use multiple groups of sample training data in the sample training data set to perform iterative training through machine learning until the iteration termination condition is reached, and an initial dust prediction model is obtained, wherein the loss function is used to determine the prediction error.

[0080] In an optional embodiment, the construction module includes: a first construction submodule, which is used to construct the Euler model using a first formula according to the historical dust distribution status of each grid unit, wherein the first formula is: represents the rate of change of dust concentration C with time t, D represents the diffusion coefficient, represents the Laplace operator, V represents the wind speed vector, represents the gradient operator, C(x, t) represents the dust concentration of the grid cell with spatial coordinate x at time t; the second construction submodule is used to construct the partial differential diffusion equation using the second formula according to the historical dust distribution status of each grid cell, where the second formula is: C(x, y, t) represents the dust concentration of the grid cell with spatial coordinates (x, y) at time t, and C0 represents the dust concentration at the initial collection moment.

[0081] In an optional embodiment, the execution unit includes at least one of the following: a first execution module, used to control the spray component to perform dust control operations according to the dust control strategy, so that the dust concentration of dust in the mining environment is not higher than the concentration threshold, wherein the spray component performs the dust control operation by adjusting the spray frequency and the water spraying amount according to the dust control strategy; a second execution module, used to control the ventilation component to perform dust control operations according to the dust control strategy, so that the dust concentration of dust in the mining environment is not higher than the concentration threshold, wherein the ventilation component performs the dust control operation by adjusting the wind direction and wind speed according to the dust control strategy.

[0082] According to another aspect of an embodiment of the present invention, a dust control system for open-pit mining is further provided. The dust control system for open-pit mining uses any one of the above-mentioned dust control methods for open-pit mining.

[0083] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, the computer-readable storage medium comprising a stored program, wherein the program executes any one of the above-mentioned dust prevention and control methods in an open-pit mining process.

[0084] Optionally, in this embodiment, the computer-readable storage medium may be located in any one of the computer terminals in a computer terminal group in a computer network, or in any one of the communication devices in a communication device group.

[0085] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: receiving dust monitoring data transmitted by a dust monitoring meteorological station, wherein the dust monitoring data is data obtained by monitoring the mining environment during open-pit mining using multiple sensors deployed at the dust monitoring meteorological station; inputting the dust monitoring data into a dust prediction model, so as to process the dust monitoring data using the dust prediction model to obtain the dust distribution status in the mining environment, wherein the dust prediction model is trained using multiple sets of first training data using a machine learning method, and each of the multiple sets of first training data includes: sample dust monitoring data , sample dust distribution conditions corresponding to the sample dust monitoring data, the dust distribution conditions refer to the dust concentrations at different spatial locations in the mining environment at different time points; using a prevention and control strategy generation model to analyze and process the dust distribution conditions to obtain a dust prevention and control strategy for preventing and controlling dust in the mining environment, wherein the prevention and control strategy generation model is trained using multiple groups of second training data using a machine learning method, and each of the multiple groups of second training data includes: sample dust distribution conditions, sample dust prevention and control strategies corresponding to the sample dust distribution conditions; performing dust prevention and control operations in accordance with the dust prevention and control strategies to ensure that the dust concentration in the mining environment is no higher than a concentration threshold.

[0086] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: receiving a communication connection request sent by a dust monitoring meteorological station; establishing a communication channel for communication transmission with the dust monitoring meteorological station based on the communication connection request; and receiving dust monitoring data transmitted by the dust monitoring meteorological station based on the communication channel.

[0087] Optionally, in this embodiment, a computer-readable storage medium is configured to store program codes for executing the following steps: obtaining multiple groups of historical dust monitoring data within a historical time period; performing data cleaning and missing value processing on multiple groups of historical dust monitoring data to obtain a sample test data set; sorting multiple groups of historical dust monitoring data according to the collection period to which the collection time belongs to obtain a sample training data set; using multiple groups of sample training data in the sample training data set to perform iterative training through machine learning until an iteration termination condition is reached, thereby obtaining an initial dust prediction model, wherein each of the multiple groups of sample training data includes: sample dust monitoring data, and sample dust distribution conditions corresponding to the sample dust monitoring data, and the iteration termination condition includes at least one of the following: the number of iterations reaches a preset number of iterations, and the prediction error is less than an error threshold; using the sample test data set to perform performance evaluation on the initial dust prediction model to obtain an evaluation result; when the evaluation result indicates that the current performance of the dust prediction model reaches a preset performance indicator, the initial dust prediction model is determined to be the dust prediction model.

[0088] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: dividing the collection period into multiple different collection sub-periods, wherein the period length of each collection sub-period is different; sorting multiple groups of historical dust monitoring data according to the collection sub-periods to which the collection time belongs, to obtain multiple sample training data subsets; determining the multiple sample training data subsets as different sample training data sets.

[0089] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: discretizing the historical mining environment within the historical time period to obtain multiple grid units, wherein each grid unit represents a local area in the historical mining environment; determining the historical dust distribution status of each grid unit within the historical time period based on multiple groups of sample training data; constructing an Euler model and a partial differential diffusion equation based on the historical dust distribution status of each grid unit; using the Euler model and the partial differential diffusion equation as loss functions, and using multiple groups of sample training data in the sample training data set to perform iterative training through machine learning until the iteration termination condition is reached, thereby obtaining an initial dust prediction model, wherein the loss function is used to determine the prediction error.

[0090] Optionally, in this embodiment, the computer-readable storage medium is configured to store a program code for executing the following steps: constructing an Euler model using a first formula according to the historical dust distribution conditions of each grid unit, wherein the first formula is: represents the rate of change of dust concentration C with time t, D represents the diffusion coefficient, represents the Laplace operator, V represents the wind speed vector, represents the gradient operator, C(x, t) represents the dust concentration of the grid cell with spatial coordinate x at time t; the partial differential diffusion equation is constructed using the second formula according to the historical dust distribution of each grid cell, where the second formula is: C(x, y, t) represents the dust concentration of the grid cell with spatial coordinates (x, y) at time t, and C0 represents the dust concentration at the initial collection moment.

[0091] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: controlling the spray component to perform dust control operations in accordance with a dust control strategy so that the dust concentration of dust in the mining environment is not higher than a concentration threshold, wherein the spray component performs dust control operations by adjusting the spray frequency and the water spray volume in accordance with the dust control strategy; controlling the ventilation component to perform dust control operations in accordance with the dust control strategy so that the dust concentration of dust in the mining environment is not higher than a concentration threshold, wherein the ventilation component performs dust control operations by adjusting the wind direction and wind speed in accordance with the dust control strategy.

[0092] According to another aspect of an embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein when the program is run, any one of the above-mentioned dust prevention and control methods in the open-pit mining process is executed.

[0093] According to another aspect of an embodiment of the present invention, a computer program product is also provided, comprising computer instructions, which, when executed by a processor, execute any one of the above-mentioned dust prevention and control methods in an open-pit mining process.

[0094] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0095] In the above embodiments of the present invention, 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.

[0096] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, 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 interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0097] 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 units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0098] In addition, each functional unit in each embodiment of the present invention 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.

[0099] 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 storage medium. Based on this understanding, the technical solution of the present invention, in essence, 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, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0100] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for preventing and controlling dust in open-pit mining, characterized in that: include: Receiving dust monitoring data transmitted by a dust monitoring meteorological station, wherein the dust monitoring data is data obtained by monitoring the mining environment during open-pit mining by a plurality of sensors deployed at the dust monitoring meteorological station; The dust monitoring data is input into a dust prediction model, so as to process the dust monitoring data using the dust prediction model to obtain the dust distribution status in the mining environment, wherein the dust prediction model is trained by using a plurality of sets of first training data in a machine learning manner, and each of the plurality of sets of first training data includes: sample dust monitoring data, and sample dust distribution status corresponding to the sample dust monitoring data, wherein the dust distribution status refers to the dust concentration at different spatial positions in the mining environment at different time points; The dust distribution condition is analyzed and processed by using a prevention and control strategy generation model to obtain a dust prevention and control strategy for preventing and controlling dust in a mining environment, wherein the prevention and control strategy generation model is obtained by training using multiple sets of second training data in a machine learning manner, and each of the multiple sets of second training data includes: a sample dust distribution condition and a sample dust prevention and control strategy corresponding to the sample dust distribution condition; Dust prevention operations are performed according to the dust prevention strategy so that the dust concentration of the dust in the mining environment is not higher than a concentration threshold.

2. The dust prevention method in open-pit mining according to claim 1, characterized in that: Receive dust monitoring data transmitted by the dust monitoring weather station, including: Receiving a communication connection request sent by the dust monitoring weather station; Establishing a communication channel for communication transmission with the dust monitoring meteorological station based on the communication connection request; The dust monitoring data transmitted by the dust monitoring weather station is received based on the communication channel.

3. The dust prevention method in open-pit mining according to claim 1, characterized in that: Before inputting the dust monitoring data into the dust prediction model to process the dust monitoring data using the dust prediction model to obtain the dust distribution status in the mining environment, the method further includes: Obtain multiple sets of historical dust monitoring data within a historical period; Performing data cleaning and missing value processing on multiple groups of historical dust monitoring data to obtain a sample test data set; Arrange the multiple groups of historical dust monitoring data according to the collection period to which the collection time belongs, to obtain a sample training data set; Iterative training is performed by machine learning using multiple groups of sample training data in the sample training data set until an iteration termination condition is reached to obtain an initial dust prediction model, wherein each group of the multiple groups of sample training data includes: sample dust monitoring data, and sample dust distribution conditions corresponding to the sample dust monitoring data, and the iteration termination condition includes at least one of the following: the number of iterations reaches a preset number of iterations, and the prediction error is less than an error threshold; Using a sample test data set to perform a performance evaluation on the initial dust prediction model to obtain an evaluation result; In a case where the evaluation result indicates that the current performance of the dust prediction model reaches a preset performance index, the initial dust prediction model is determined to be the dust prediction model.

4. The dust prevention method in open-pit mining according to claim 3, characterized in that: The multiple groups of historical dust monitoring data are sorted according to the collection period to which the collection time belongs, to obtain a sample training data set, including: Dividing the acquisition cycle into a plurality of different acquisition sub-cycles, wherein each of the acquisition sub-cycles has a different cycle length; Arrange the multiple groups of historical dust monitoring data according to the collection sub-period to which the collection time belongs, to obtain multiple sample training data subsets; Determine the plurality of sample training data subsets as different sample training data sets.

5. The dust prevention method in open-pit mining according to claim 3, characterized in that: Iterative training is performed using multiple groups of sample training data in the sample training data set by machine learning until an iteration termination condition is reached, thereby obtaining an initial dust prediction model, including: Discretely gridding the historical mining environment within the historical time period to obtain a plurality of grid units, wherein each of the grid units represents a local area in the historical mining environment; Determine the historical dust distribution status of each grid unit in the historical time period according to the multiple groups of sample training data; Constructing an Euler model and a partial differential diffusion equation according to the historical dust distribution conditions of each of the grid cells; The Euler model and the partial differential diffusion equation are used as loss functions, and multiple groups of sample training data in the sample training data set are used to perform iterative training through machine learning until the iteration termination condition is reached, so as to obtain the initial dust prediction model, wherein the loss function is used to determine the prediction error.

6. The dust prevention method in open-pit mining according to claim 5, characterized in that: According to the historical dust distribution conditions of each grid unit, an Euler model and a partial differential diffusion equation are constructed, including: The Euler model is constructed using a first formula according to the historical dust distribution status of each grid unit, wherein the first formula is: represents the rate of change of dust concentration C with time t, D represents the diffusion coefficient, represents the Laplace operator, V represents the wind speed vector, represents a gradient operator, C(x, t) represents the dust concentration of the grid cell with spatial coordinate x at time t; The partial differential diffusion equation is constructed using a second formula according to the historical dust distribution status of each grid unit, wherein the second formula is: C(x, y, t) represents the dust concentration of the grid unit with spatial coordinates (x, y) at time t, and C0 represents the dust concentration at the initial collection time.

7. The dust control method in open-pit mining according to claim 1, characterized in that: Performing dust control operations according to the dust control strategy so that the dust concentration of the dust in the mining environment is not higher than a concentration threshold value includes at least one of the following: controlling the spray component to perform the dust control operation according to the dust control strategy so that the dust concentration of the dust in the mining environment is not higher than the concentration threshold, wherein the spray component performs the dust control operation by adjusting the spray frequency and the water spraying amount according to the dust control strategy; The ventilation component is controlled to perform the dust control operation according to the dust control strategy so that the dust concentration of the dust in the mining environment is not higher than the concentration threshold, wherein the ventilation component performs the dust control operation by adjusting the wind direction and wind speed according to the dust control strategy.

8. A dust control device in open-pit mining, characterized in that: include: A receiving unit, used to receive dust monitoring data transmitted by a dust monitoring meteorological station, wherein the dust monitoring data is data obtained by monitoring the mining environment during open-pit mining by a plurality of sensors deployed at the dust monitoring meteorological station; A first acquisition unit is used to input the dust monitoring data into a dust prediction model, so as to process the dust monitoring data using the dust prediction model to obtain the dust distribution status in the mining environment, wherein the dust prediction model is trained by using a plurality of groups of first training data in a machine learning manner, and each of the plurality of groups of first training data includes: sample dust monitoring data, and sample dust distribution status corresponding to the sample dust monitoring data, wherein the dust distribution status refers to dust concentrations at different spatial positions in the mining environment at different time points; a second acquisition unit, configured to analyze and process the dust distribution condition by using a prevention and control strategy generation model to obtain a dust prevention and control strategy for preventing and controlling dust in a mining environment, wherein the prevention and control strategy generation model is obtained by training using a plurality of sets of second training data in a machine learning manner, and each of the plurality of sets of second training data includes: a sample dust distribution condition and a sample dust prevention and control strategy corresponding to the sample dust distribution condition; An execution unit is used to execute dust prevention operations according to the dust prevention strategy so that the dust concentration of the dust in the mining environment is not higher than a concentration threshold.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the dust prevention and control method in an open-pit mining process as described in any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by the processor, the dust prevention and control method in the open-pit mining process described in any one of claims 1 to 7 is performed.

Images