Mining intelligent watering dust fall method and system, electronic equipment and storage medium

Abstract

The invention provides a mining intelligent watering dust fall method and system, electronic equipment and a storage medium, and relates to the field of watering dust fall. The method comprises the following steps: acquiring multi-source heterogeneous environment sensing data; preprocessing the multi-source heterogeneous environment sensing data to obtain preprocessed multi-source heterogeneous environment sensing data, and constructing a mining area holographic environment model based on the preprocessed multi-source heterogeneous environment sensing data; based on the holographic environment model of the mining area, extrapolating and estimating the dynamic change trend of the wind dust concentration by using a space-time sequence prediction algorithm to obtain a wind dust concentration distribution prediction result of each area of the mining area in a future time period; according to the technical scheme, dust suppression is taken as an optimization target, water mist parameters and a nozzle arrangement scheme are taken as decision variables, a mining area holographic environment model and a wind dust concentration distribution prediction result are taken as constraint conditions, an optimal spraying strategy meeting dust falling requirements is solved through a heuristic search algorithm, and the dust falling effect is improved and the water consumption is reduced through the technical scheme.

Description

Technical Field

[0001] The present application relates to the field of water sprinkling and dust reduction, and in particular to an intelligent water sprinkling and dust reduction method, system, electronic equipment and storage medium for mining. Background Art

[0002] The dust generated during mining not only seriously affects the working environment and surrounding air quality, but may also endanger the health of workers. In order to suppress dust, spray dust suppression is currently widely used. Existing mine spray dust suppression systems usually operate based on pre-set fixed spray parameters and nozzle layout plans, or simply adjust the spray intensity based on the detection data of a single dust concentration sensor. This method fails to fully consider the complex environmental factors of the mining area. This simple control method results in poor dust suppression effect and high water consumption. Summary of the invention

[0003] The present application provides a method, system, electronic equipment and storage medium for intelligent water sprinkling and dust reduction for mining, which are used to improve the dust reduction effect and reduce water consumption.

[0004] In the first aspect, the present application provides a method for intelligent water sprinkling and dust reduction for mining, comprising: Acquire multi-source heterogeneous environmental perception data through multi-modal sensors deployed in the mining area; Preprocessing the multi-source heterogeneous environmental perception data to obtain preprocessed multi-source heterogeneous environmental perception data, and constructing a mining area holographic environmental model based on the preprocessed multi-source heterogeneous environmental perception data; Based on the holographic environmental model of the mining area, the dynamic change trend of the dust concentration is extrapolated and estimated using the spatiotemporal series prediction algorithm to obtain the predicted results of the dust concentration distribution in each area of ​​the mining area in the future period. With dust suppression as the optimization goal, water mist parameters and nozzle layout plan as decision variables, and the mining area holographic environment model and wind-blown dust concentration distribution prediction results as constraints, the optimal spray strategy that meets the dust suppression needs is solved through a heuristic search algorithm. The optimal spray strategy is used to control the gridded spray array to perform dust suppression operations.

[0005] In the above technical scheme, the present application obtains multi-source heterogeneous environmental perception data through multimodal sensors arranged in the mining area, and constructs a holographic environmental model of the mining area after preprocessing these data, thereby realizing comprehensive perception and accurate modeling of the mining area environment. Based on the holographic environmental model of the mining area, the dynamic change trend of the wind dust concentration is extrapolated and estimated by the spatiotemporal sequence prediction algorithm, which can accurately predict the distribution of wind dust concentration in various areas of the mining area in the future period. Furthermore, with dust suppression as the optimization goal, water mist parameters and nozzle layout scheme are used as decision variables, and the holographic environmental model of the mining area and the predicted results of wind dust concentration distribution are used as constraints. The optimal spray strategy obtained by the heuristic search algorithm can adaptively adjust the spray parameters according to environmental changes and dust distribution prediction results. Finally, the optimal spray strategy is used to control the grid spray array to perform dust reduction operations, realizing intelligent and precise control of the dust reduction process. This dust reduction method based on holographic environmental perception and intelligent optimization decision-making can not only effectively improve the dust reduction effect, but also avoid excessive use of water resources, thereby achieving the dual goals of ensuring the quality of the working environment and saving resources.

[0006] In a second aspect of the present application, a mining intelligent water sprinkling and dust suppression system is provided, the system comprising: A data acquisition module is used to acquire multi-source heterogeneous environmental perception data through multi-modal sensors arranged in the mining area; A preprocessing module is used to preprocess the multi-source heterogeneous environmental perception data to obtain the preprocessed multi-source heterogeneous environmental perception data, and to construct a mining area holographic environment model based on the preprocessed multi-source heterogeneous environmental perception data; The prediction module is used to extrapolate and estimate the dynamic change trend of wind-dust concentration based on the holographic environmental model of the mining area and use the spatiotemporal sequence prediction algorithm to obtain the prediction results of wind-dust concentration distribution in various areas of the mining area in the future period; The spray strategy optimization module is used to optimize dust suppression, use water mist parameters and nozzle layout scheme as decision variables, and use the mining area holographic environment model and wind-blown dust concentration distribution prediction results as constraints to solve the optimal spray strategy that meets the dust suppression requirements through a heuristic search algorithm; The dust reduction operation execution module is used to control the grid spray array with the optimal spray strategy to perform dust reduction operations.

[0007] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above method steps.

[0008] In the fourth aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the above method.

[0009] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. This application obtains multi-source heterogeneous environmental perception data through multimodal sensors arranged in the mining area, and constructs a holographic environmental model of the mining area after preprocessing these data, thereby realizing comprehensive perception and accurate modeling of the mining environment.

[0010] 2. This application is based on the holographic environmental model of the mining area, and uses a spatiotemporal sequence prediction algorithm to extrapolate and estimate the dynamic change trend of the wind dust concentration, which can accurately predict the distribution of wind dust concentration in various areas of the mining area in the future period. Furthermore, with dust suppression as the optimization goal, water mist parameters and nozzle layout schemes are used as decision variables, and the holographic environmental model of the mining area and the predicted results of wind dust concentration distribution are used as constraints. The optimal spray strategy obtained by the heuristic search algorithm can adaptively adjust the spray parameters according to environmental changes and dust distribution prediction results.

[0011] 3. This application uses the optimal spray strategy to control the grid spray array to perform dust reduction operations, realizing intelligent and precise control of the dust reduction process. This dust reduction method based on holographic environmental perception and intelligent optimization decision-making can not only effectively improve the dust reduction effect, but also avoid excessive use of water resources, thereby achieving the dual purpose of ensuring the quality of the working environment and saving resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic diagram of a process flow of an intelligent water sprinkling and dust reduction method for mining provided in an embodiment of the present application; Figure 2 An architecture diagram of an intelligent water sprinkling and dust suppression system for mining provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0013] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0014] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0015] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0016] For further information, see Figure 1 , Figure 1 A flow chart of a method for intelligent water sprinkling and dust reduction for mining provided in an embodiment of the present application. The system can be implemented by a computer program or can be run as an independent tool application. Specifically, in an embodiment of the present application, the method can be applied on a server, but can also be applied to electronic devices such as servers. A method for intelligent water sprinkling and dust reduction for mining includes the following steps: S101, acquiring multi-source heterogeneous environmental perception data through multi-modal sensors arranged in the mining area; Specifically, in the specific implementation, multimodal sensors are first arranged in the mining area, including infrared thermal imaging sensors, dust concentration sensors, wind speed and direction sensors, and three-dimensional laser scanners. Among them, the infrared thermal imaging sensor is arranged at a high place in the mining area to collect heat source distribution data in the mining area; the dust concentration sensor is arranged in the main operation area and key positions of the mining area to monitor the dust content in the air in real time; the wind speed and direction sensor is arranged on the key path of air flow in the mining area to measure air flow parameters; the three-dimensional laser scanner is used to obtain spatial data of the topography of the mining area. These sensors work together to collect multi-source heterogeneous environmental perception data in the mining area in real time, among which the multi-source heterogeneous environmental perception data includes infrared thermal imaging image data, dust concentration data, wind speed and direction data, and three-dimensional data of the mining area. Through this collaborative arrangement and data collection method of multimodal sensors, all-round and multi-angle perception information of the mining area environment is obtained, providing a complete data foundation for the subsequent construction of an accurate holographic environmental model of the mining area. The use of multimodal sensors to collect multi-source heterogeneous environmental perception data overcomes the limitations of information acquisition by a single sensor and achieves comprehensive monitoring of the environmental status of the mining area.

[0017] S102, preprocessing the multi-source heterogeneous environmental perception data to obtain preprocessed multi-source heterogeneous environmental perception data, and constructing a mining area holographic environment model based on the preprocessed multi-source heterogeneous environmental perception data; Specifically, in order to ensure data quality and model accuracy, the acquired multi-source heterogeneous environmental perception data needs to be preprocessed. In the preprocessing stage, the multi-source heterogeneous environmental perception data is first denoised, and the random interference in the sensor acquisition process is eliminated by filtering algorithms; then the data is normalized to unify different types of perception data into the same numerical range; finally, data completion is performed to repair data missing caused by sensor failure or communication interruption. After preprocessing, a mining area holographic environment model is constructed based on the preprocessed multi-source heterogeneous environmental perception data. During the construction process, a deep neural network is used to fuse the preprocessed multi-source heterogeneous environmental perception data, and information of different dimensions such as infrared thermal imaging data, dust concentration data, wind speed and direction data, and mining area three-dimensional data are uniformly mapped to the mining area holographic environment model. Through this data preprocessing and model construction method, not only the availability of the original data is improved, but also the effective fusion of multi-source heterogeneous environmental perception data is realized, and finally a mining area holographic environment model that accurately reflects the environmental status of the mining area is constructed.

[0018] Based on the above embodiment, as an optional embodiment, preprocessing the multi-source heterogeneous environment perception data to obtain the preprocessed multi-source heterogeneous environment perception data includes: Performing spatiotemporal synchronization on multi-source heterogeneous environmental perception data to obtain synchronized multi-source heterogeneous environmental perception data; The synchronized multi-source heterogeneous environmental perception data is cleaned to obtain preprocessed multi-source heterogeneous environmental perception data.

[0019] Specifically, since the multi-source heterogeneous environmental perception data comes from different sensors, there are differences in their collection time and spatial location, it is necessary to first perform spatiotemporal synchronization on the multi-source heterogeneous environmental perception data. In the spatiotemporal synchronization process, the data collected by different sensors are aligned according to a unified time tag, and the asynchronously collected data are synchronized to the same time point through timestamp matching; at the same time, based on the spatial layout information of the sensor, a unified spatial coordinate system is established, and the perception data scattered in different spatial locations are mapped to the same coordinate system to obtain the synchronized multi-source heterogeneous environmental perception data. Then, the synchronized multi-source heterogeneous environmental perception data is cleaned, outliers are identified and eliminated through statistical analysis methods, missing data are repaired using data interpolation algorithms, and data noise is eliminated using filtering algorithms, and finally the preprocessed multi-source heterogeneous environmental perception data is obtained. This preprocessing method combining spatiotemporal synchronization and data cleaning solves the inconsistency problem of multi-source heterogeneous environmental perception data in the temporal and spatial dimensions, improves data quality, and lays a reliable data foundation for the subsequent construction of a holographic environmental model of a mining area.

[0020] S103, based on the holographic environment model of the mining area, the dynamic change trend of the dust concentration is extrapolated and estimated using the spatiotemporal sequence prediction algorithm to obtain the predicted results of the dust concentration distribution in each area of ​​the mining area in the future period; Specifically, after obtaining the holographic environmental model of the mining area, in order to achieve forward-looking control of dust distribution, the spatiotemporal sequence prediction algorithm is used to extrapolate and estimate the dynamic change trend of wind dust concentration. In the specific implementation, the wind dust concentration data sequence of the historical period is first extracted from the holographic environmental model of the mining area. These sequence data contain the wind dust concentration values ​​at different time points and different spatial positions. Then, the extracted data sequence is input into the spatiotemporal sequence prediction algorithm, which establishes a prediction model by analyzing the changing law of wind dust concentration in time and space dimensions. The spatiotemporal sequence prediction algorithm comprehensively considers the temporal continuity and spatial correlation, models the changing trend of wind dust concentration, and then extrapolates and calculates the predicted results of wind dust concentration distribution in various regions of the mining area in the future period. This prediction method based on the holographic environmental model of the mining area makes full use of the spatiotemporal change law contained in the historical monitoring data, not only accurately predicts the time evolution trend of wind dust concentration, but also reflects the spatial correlation characteristics between different regions, providing an important decision-making basis for the subsequent formulation of the optimal spray strategy.

[0021] Based on the above embodiment, as an optional embodiment, the multi-source heterogeneous environmental perception data includes infrared thermal imaging image data, dust concentration data, wind speed and direction data, and three-dimensional data of the mining area; the mining area holographic environment model is constructed based on the pre-processed multi-source heterogeneous environmental perception data, including: Based on infrared thermal imaging image data, a heat source distribution model covering the entire mining area is generated through heat map fitting; Determine dust concentration distribution based on dust concentration data; Determine the wind flow lines inside the mining area based on wind speed and direction data; Based on the dust concentration distribution and wind field streamlines inside the mining area, a dust concentration model is constructed to reflect the current state and historical change trends; Construct a 3D model of the mining area based on the 3D data of the mining area; The heat source distribution model, dust concentration model and mining area three-dimensional model are semantically associated to obtain a holographic environment model of the mining area.

[0022] Specifically, in order to build a complete holographic environment model of the mining area, it is necessary to deeply integrate multi-source heterogeneous environmental perception data. First, the discrete temperature measurement point data is expanded to the entire mining area space through the heat map fitting technology using infrared thermal imaging image data to generate a continuous heat source distribution model, which reflects the temperature distribution status of each area in the mining area. Secondly, according to the dust concentration data collected by dust sensors distributed throughout the mining area, the dust concentration distribution of the entire mining area is determined by the spatial interpolation method. At the same time, based on the wind speed and wind direction data collected by the wind speed and wind direction sensors, the wind field streamlines inside the mining area are determined by the computational fluid dynamics method, reflecting the path and intensity of air flow. On this basis, the dust concentration distribution is combined with the wind field streamlines inside the mining area to construct a wind dust concentration model, which not only reflects the dust distribution status at the current moment, but also includes the change trend reflected by historical data. In addition, the three-dimensional data of the mining area obtained by laser scanning and other technologies are used to construct an accurate three-dimensional model of the mining area, including the spatial layout information of the topography and various facilities. Finally, the heat source distribution model, dust concentration model and mining area three-dimensional model are associated and fused through semantic association technology to establish a unified mining area holographic environment model. This multi-model fusion method realizes the comprehensive expression of mining area environmental elements, enables the mining area holographic environment model to fully reflect the environmental status of the mining area, and provides comprehensive environmental information support for subsequent dust control decisions.

[0023] Based on the above embodiment, as an optional embodiment, the heat source distribution model, the dust concentration model and the three-dimensional model of the mining area are semantically associated to obtain a holographic environment model of the mining area, including: S201, constructing a unified spatiotemporal reference frame, uniformly registering the coordinate systems of the heat source distribution model, the dust concentration model and the three-dimensional model of the mining area with the spatiotemporal reference frame, and obtaining the registered heat source distribution model, the registered dust concentration model and the registered three-dimensional model of the mining area respectively; Specifically, since the heat source distribution model, the dust concentration model and the three-dimensional model of the mining area are constructed based on different data sources and each uses an independent coordinate system, in order to achieve accurate association between the models, it is necessary to unify these models into the same space-time reference frame. When constructing a unified space-time reference frame, a three-dimensional rectangular coordinate system with a fixed reference point in the mining area as the origin is first established, and the time axis is used as the fourth dimension to form a complete four-dimensional space-time reference frame. Then, the temperature field data of the heat source distribution model is mapped to the space-time reference frame through coordinate transformation to obtain the registered heat source distribution model; similarly, the dust concentration data and wind field streamline data in the dust concentration model are coordinate transformed and time aligned to obtain the registered dust concentration model; the same coordinate transformation operation is performed on the spatial geometric data of the three-dimensional model of the mining area to obtain the registered three-dimensional model of the mining area. This registration method based on a unified space-time reference frame solves the problems of spatial registration and temporal alignment between different models, so that each model can be superimposed and associated in the same space-time reference system. Analysis, laying the foundation for building a complete holographic environment model of the mining area.

[0024] S202, respectively extracting key features from the registered heat source distribution model, the registered dust concentration model, and the registered mining area three-dimensional model, and establishing semantic correspondences between the key features; Specifically, in order to establish deep associations between models, it is necessary to extract key features from each registered model and establish semantic correspondences. Extract thermal field features such as high temperature areas and temperature gradients from the registered heat source distribution model; extract dust accumulation areas, diffusion paths, wind field vortices and other features from the registered wind-dust concentration model; extract spatial features such as terrain undulations, equipment locations, and operating areas from the registered three-dimensional model of the mining area. After extracting these key features, the correspondence between the features is determined through semantic analysis, such as establishing an association between the spatial overlap between high temperature areas and dust accumulation areas, mapping the causal relationship between wind field vortices and terrain undulations, and establishing a connection between the correlation between equipment locations and local temperature anomalies. By establishing these semantic correspondences, the association expression between different model features is realized, so that each model is no longer an independent information island, but forms an interconnected knowledge network, providing more comprehensive and in-depth information support for subsequent environmental state analysis and control decisions.

[0025] S203, based on the semantic correspondence, semantically associate the registered heat source distribution model, the registered dust concentration model and the registered mining area three-dimensional model to obtain a mining area holographic environment model.

[0026] Specifically, after completing the extraction of key features and establishing semantic correspondence, it is necessary to semantically associate the registered heat source distribution model, the registered wind dust concentration model and the registered three-dimensional model of the mining area to construct a unified holographic environmental model of the mining area. Through the semantic association technology, the temperature field data in the heat source distribution model is associated with the dust distribution and wind field data in the wind dust concentration model at the semantic level, and at the same time, these environmental element data are corresponding to the spatial entities in the three-dimensional model of the mining area. In the process of semantic association, based on the established semantic correspondence, the data of each model are fused, so that environmental elements such as temperature field, dust concentration, wind field streamlines and the spatial entities of the mining area form an organic and unified expression. This semantic association method realizes the deep fusion of multi-source heterogeneous data, so that the holographic environmental model of the mining area not only contains the complete information of various environmental elements, but also reflects the correlation between the elements, which can fully reflect the overall state and dynamic change characteristics of the mining area environment, and provide a unified environmental cognition basis for dust control in the mining area.

[0027] Based on the above embodiment, as an optional embodiment, determining the wind field streamlines inside the mining area based on wind speed and direction data includes: S301, using wind speed and direction data as boundary conditions and initial conditions, establishing an air flow mathematical model describing the air flow inside the mining area; Specifically, in order to accurately describe the air flow state inside the mining area, it is necessary to establish an air flow mathematical model based on wind speed and direction data. In the modeling process, the wind speed and direction data collected from the wind speed and direction sensors are first used as boundary conditions. These data reflect the air flow state at the boundary of the mining area; at the same time, the wind speed and direction data at a certain moment are used as initial conditions to represent the wind field distribution state inside the mining area at the beginning of the calculation. Based on these boundary conditions and initial conditions, the Navier-Stokes equations are used to describe the dynamic characteristics of air flow. This equation group contains basic physical laws such as conservation of momentum, conservation of mass, and conservation of energy. By establishing an air flow mathematical model, a quantitative description of the air flow law inside the mining area is achieved, which lays a theoretical foundation for the subsequent calculation of the wind field streamline distribution, so that the air flow state inside the mining area can be accurately predicted and analyzed.

[0028] S302, spatially discretizing the air flow mathematical model, dividing the interior of the mining area into regular or irregular grid units, and forming a discretized equation group suitable for numerical solution; Specifically, since the mathematical model of air flow is a continuous set of partial differential equations, spatial discretization is required to achieve numerical solution. During the spatial discretization process, the internal space of the mining area is divided into a large number of grid units according to the terrain characteristics of the mining area and the requirements of calculation accuracy. Regular grid division is used for areas with regular terrain, and irregular grid division is used for areas with complex terrain to ensure that the grid can accurately fit the spatial geometric characteristics of the mining area. In each grid unit, the continuous mathematical model of air flow is converted into discrete algebraic equations, including the discrete representation of physical quantities such as velocity and pressure at the grid nodes, and the conversion of spatial derivatives into differential form. Through this spatial discretization process, a discretized set of equations consisting of a large number of algebraic equations is formed, realizing the transformation from continuous problems to discrete problems, creating conditions for the subsequent use of numerical methods to solve wind field distribution.

[0029] S303, selecting a suitable turbulence model, closing the Reynolds stress term in the discretized equation group, and obtaining a complete wind field numerical simulation control equation group; Specifically, the air flow inside the mining area has obvious turbulent characteristics, and Reynolds stress terms describing turbulent pulsation are generated in the discretized equations. These terms need to be closed through the turbulence model. In view of the characteristics of air flow in the mining area, the standard k-ε turbulence model is selected to close the Reynolds stress terms. This model describes the turbulent characteristics by introducing two transport equations: turbulent kinetic energy k and turbulent dissipation rate ε. In the closing process, the Reynolds stress terms are expressed as a function of the mean flow field gradient, and the turbulent viscosity coefficient is introduced to establish the relationship between turbulent stress and the mean flow field deformation rate. Through this turbulence model closing treatment, a complete wind field numerical simulation control equation group including momentum equation, continuity equation, k equation and ε equation is obtained, so that the equation group forms a closed system, which provides a mathematical basis for accurately simulating turbulent air flow inside the mining area.

[0030] S304, using a numerical discretization method, spatially discretizing the wind field numerical simulation control equation group to obtain a wind field discretization control equation group; Specifically, in order to achieve the numerical solution of the control equations of the wind farm numerical simulation, it is necessary to use the numerical discretization method for spatial discretization. The finite volume method is used to discretize the convection term, diffusion term and source term in the control equations of the wind farm numerical simulation. Each grid unit is used as a control volume, and the equations are integrated within the control volume. The upwind format is used to discretize the convection term to ensure the stability of the calculation, the central difference format is used to discretize the diffusion term to ensure the calculation accuracy, and the piecewise linear approximation is used to discretize the source term to ensure physical rationality. Through the numerical discretization method, the control equations of the wind farm numerical simulation are transformed into the discretized control equations of the wind farm. This equation is an algebraic equation group composed of physical quantities of each grid node, which realizes the transformation from continuous control equations to discrete control equations, laying the foundation for the subsequent solution of wind field distribution.

[0031] S305, using a time-marching format to time-discretize the wind field discretization control equation group to form an algebraic equation group for solving wind field streamlines; Specifically, in order to achieve the numerical solution of the control equations of the wind farm numerical simulation, it is necessary to use the numerical discretization method for spatial discretization. The finite volume method is used to discretize the convection term, diffusion term and source term in the control equations of the wind farm numerical simulation. Each grid unit is used as a control volume, and the equations are integrated within the control volume. The upwind format is used to discretize the convection term to ensure the stability of the calculation, the central difference format is used to discretize the diffusion term to ensure the calculation accuracy, and the piecewise linear approximation is used to discretize the source term to ensure physical rationality. Through the numerical discretization method, the control equations of the wind farm numerical simulation are transformed into the discretized control equations of the wind farm. This equation is an algebraic equation group composed of physical quantities of each grid node, which realizes the transformation from continuous control equations to discrete control equations, laying the foundation for the subsequent solution of wind field distribution.

[0032] S306, solving the algebraic equation group to obtain a discrete numerical solution of the mine wind field, and based on the discrete numerical solution of the mine wind field, using a streamline tracing algorithm, gradually tracing the wind field streamlines from the mine air outlet to the upstream to obtain the wind field streamlines inside the mine.

[0033] Specifically, in order to obtain the wind field streamline distribution inside the mining area, it is first necessary to solve the algebraic equations to obtain the discrete numerical solution of the wind field. The SIMPLE algorithm is used to solve the algebraic equations. The algorithm realizes the numerical solution of the equations through iterative correction of the velocity field and pressure field. The momentum equation and the pressure correction equation are solved respectively in each iterative step until the calculation results converge. After obtaining the discrete numerical solution of the wind field, the streamline tracking algorithm is used to determine the wind field streamline distribution. The algorithm starts from the position of the mine outlet and gradually tracks the motion trajectory of air particles in the upstream direction based on the velocity field information. During the tracking process, the fourth-order Runge-Kutta integral method is used to calculate the motion trajectory of air particles. The position of the particles at each moment is determined by time stepping, and finally the complete wind field streamline distribution inside the mining area is obtained, realizing the visual expression of the air flow path inside the mining area.

[0034] Based on the above embodiment, as an optional embodiment, a dust concentration model reflecting the current state and historical change trend is constructed based on the dust concentration distribution and the wind field streamlines inside the mining area, including: S401, mapping and associating dust concentration data with wind field streamlines inside the mining area to form an initial distribution of wind dust concentration, and using the initial distribution of wind dust concentration as an initial condition of a wind dust concentration model; Specifically, in order to construct the wind dust concentration model, it is necessary to map and associate the dust concentration data with the wind field streamlines inside the mining area. First, according to the spatial position information of the dust concentration monitoring points, the dust concentration data of each monitoring point is extended to the entire calculation domain through the spatial interpolation method to obtain a continuous dust concentration distribution field. Then the dust concentration distribution field is spatially corresponded with the obtained wind field streamlines inside the mining area, and the dust concentration value at the corresponding position is calibrated on each wind field streamline to form an initial distribution of dust concentration that reflects the distribution characteristics of dust in the wind field. This mapping and association process establishes the spatial relationship between dust concentration and wind field flow, and uses the initial distribution of dust concentration as the initial condition of the dust concentration model, which provides a starting state for the subsequent simulation of dust transport in the wind field.

[0035] S402, based on the wind field streamlines, establish a convection-diffusion equation describing the spatial transport of dust, and use the convection-diffusion equation as a dust concentration control equation of the dust concentration model; Specifically, in order to describe the transport process of dust in the wind field, it is necessary to establish a convection-diffusion equation based on the wind field streamlines. The equation contains two main parts: the convection term and the diffusion term. The convection term describes the transport process of dust flowing with the wind field, and the diffusion term describes the diffusion process of dust due to the concentration gradient. When establishing the convection-diffusion equation, the velocity field information provided by the wind field streamlines is substituted into the convection term, and a suitable diffusion coefficient is set to characterize the diffusion characteristics of the dust. At the same time, the physical processes such as dust sedimentation and flocculation are considered, and these processes are represented as the source terms of the equation. The established convection-diffusion equation is used as the wind dust concentration control equation of the wind dust concentration model. This equation fully describes the transport law of dust in the mining area space and provides a mathematical basis for predicting the spatiotemporal evolution of dust concentration.

[0036] S403, performing time-space discretization on the dust concentration control equation to form a set of discrete algebraic equations for dust concentration; Specifically, in order to achieve the numerical solution of the dust concentration control equation, the equation needs to be discretized in time and space. In the spatial dimension, the finite volume method is used to discretize the control equation, the calculation domain is divided into grid cells, and the equation is integrally discretized on each grid cell. The convection term in the equation is discretized using the upwind format to ensure numerical stability, and the diffusion term is discretized using the central difference format to ensure calculation accuracy. In the time dimension, the implicit time marching format is used for discretization, and the relationship between dust concentrations between adjacent time steps is established. Through the space-time discretization, the dust concentration control equation is transformed into a set of discrete algebraic equations for dust concentration. This set of equations reflects the mathematical relationship between the evolution of dust concentration over time at each grid node, and provides a specific calculation method for solving the dust concentration distribution.

[0037] S404, using the initial conditions as constraints, solving the discrete algebraic equations for dust concentration, and obtaining the numerical solution for the dust concentration inside the wind field streamline at each discrete time step; Specifically, in order to obtain the spatiotemporal distribution of dust concentration inside the wind field streamlines, it is necessary to solve the discrete algebraic equations for dust concentration. The initial distribution of dust concentration is substituted into the equations as the initial condition, and the iterative solution method is used for numerical calculation. In the solution process, the pursuit method is used to solve the linear equations generated by the spatiotemporal discretization, and the dust concentration distribution at each time step is calculated by advancing time step by time. In the solution of each time step, the convergence criterion is set to control the iterative process, and the solution of the current time step is completed when the calculated residual is less than the preset threshold. In this way, the numerical solution of the dust concentration inside the wind field streamlines at each discrete time step is obtained, which realizes a complete description of the spatiotemporal evolution characteristics of the dust concentration, and provides a data basis for the subsequent analysis of the dust diffusion law.

[0038] S405, constructing a dust concentration model based on the numerical solution of dust concentration.

[0039] Specifically, in order to construct a wind-dust concentration model, it is necessary to perform data processing and model construction based on the obtained numerical solution of dust concentration. First, the numerical solution of dust concentration at each discrete time step is sorted into time series to establish a data set describing the temporal variation characteristics of dust concentration. Then, in the spatial dimension, the numerical solution of dust concentration on the wind field streamline is extended to the entire calculation domain through a three-dimensional interpolation method to form a continuous dust concentration distribution field. By combining time series data and spatial distribution fields, a wind-dust concentration model that reflects the spatiotemporal evolution characteristics of dust concentration is constructed. This model not only includes the dust concentration state at the current moment, but also records the historical change trend, realizing a complete expression of the distribution law of wind-dust in the mining area.

[0040] On the basis of the above embodiment, as an optional embodiment, taking dust suppression as the optimization goal, taking water mist parameters and nozzle layout scheme as decision variables, taking the mining area holographic environment model and the predicted results of wind dust concentration distribution as constraints, the optimal spray strategy that meets the dust suppression requirements is solved through a heuristic search algorithm, including: S501, establishing a mathematical model with dust concentration minimization as the optimization goal, and vectorizing the water mist parameters and the nozzle layout plan to obtain decision variables; Specifically, in order to achieve optimal control of dust suppression, a mathematical model with minimization of dust concentration as the optimization goal is first established. The objective function of this model is composed of the spatial integral of the dust concentration in the monitoring area, and the dust reduction effect is optimized by minimizing the objective function. In the construction of decision variables, the water mist parameters including spray pressure, flow rate, droplet size and other characteristic quantities are composed of parameter vectors, and the nozzle layout scheme including nozzle spatial coordinates, spray angle, coverage range and other characteristic quantities are composed of layout vectors. The two vectors together constitute a complete decision variable. This vectorized representation method converts water mist parameters and nozzle layout schemes into quantifiable numerical forms, which is convenient for subsequent optimization algorithms to perform numerical calculations and scheme searches, and lays a mathematical foundation for solving the optimal spray strategy.

[0041] S502, converting the mining area holographic environment model and the prediction results of the dust concentration distribution into the value constraints of the decision variables, and using the value constraints as constraint conditions; Specifically, in order to ensure the practical feasibility of the optimization results, it is necessary to convert the mining area holographic environment model and the predicted results of the dust concentration distribution into constraints. Based on the terrain information, equipment layout, and working space in the mining area holographic environment model, the spatial constraints of the nozzle layout are established to ensure that the nozzle installation position avoids the equipment movement area and the working interference area. According to the predicted results of the dust concentration distribution, the spatial distribution characteristics of the high-concentration area are extracted and converted into constraints on the spray coverage range. At the same time, considering the physical limitations of the water mist parameters, such as the spray pressure does not exceed the system's bearing capacity, the flow rate meets the water supply capacity, and the droplet size is controlled within the effective capture range, these limitations are converted into constraints on the value of the water mist parameters. These constraints together constitute the feasible domain of the decision variables, ensuring that the optimized spray strategy not only meets the actual engineering requirements but also has a good dust reduction effect.

[0042] S503, randomly generating a certain number of random water mist parameters and random nozzle layout schemes as an initial population, each individual corresponding to a complete set of candidate spray strategies; Specifically, in order to start the optimization solution process, an initial population needs to be generated as the search starting point. Within the range allowed by the constraints, the initial values ​​of the water mist parameters, including spray pressure, flow rate, and droplet size, are generated by a random number generator. At the same time, in the area that meets the spatial constraints, the spatial coordinates, spray angle, coverage range and other layout parameters of the nozzle are randomly generated. Each set of randomly generated water mist parameters and nozzle layout schemes together constitutes a candidate spray strategy, which is an individual in the population. Through multiple random generations, an initial population containing multiple candidate spray strategies is formed. These initial populations provide a diverse search starting point for subsequent optimization iterations, increasing the probability of finding the global optimal solution.

[0043] S504, based on the holographic environment model of the mining area, predict the dust reduction effect of each candidate spray strategy through a numerical simulation method, and calculate the fitness value of the individual according to the optimization objective function; Specifically, in order to evaluate the performance of each candidate spray strategy, it is necessary to evaluate the dust reduction effect of each strategy. Based on the three-dimensional calculation domain constructed by the holographic environment model of the mining area, the computational fluid dynamics method is used to numerically simulate the interaction between water mist and dust, and calculate the capture efficiency and suppression effect of water mist on dust. During the simulation process, the water mist parameters and nozzle layout scheme in the candidate spray strategy are input into the calculation model as boundary conditions, and the dust concentration distribution after spraying is obtained by solving the gas-solid two-phase flow equation. The simulated dust concentration is substituted into the optimization objective function, and the fitness value characterizing the dust reduction effect is calculated. In this way, a quantitative evaluation of each candidate spray strategy is achieved, providing a selection basis for subsequent optimization iterations.

[0044] S505, genetic operations are performed on the initial population to produce a new generation of population through survival of the fittest, until the preset termination conditions are met and the optimal spray strategy is obtained.

[0045] Specifically, in order to obtain the optimal spray strategy, the initial population is iteratively optimized. First, the individuals in the population are sorted according to the fitness value, and the individuals with higher fitness values ​​are selected as parents. The water mist parameters and nozzle layout scheme of the selected parent individuals are reorganized through the crossover operation to produce offspring individuals with excellent characteristics of the parents. At the same time, the parameters of some offspring individuals are randomly perturbed through mutation operations to increase population diversity. After merging the parent and offspring individuals, the fitness value is calculated again and the optimal individual is selected to form a new generation of population. Repeat the above genetic operation process until the maximum number of iterations is reached or the optimal fitness value changes for multiple consecutive generations are less than the threshold and other termination conditions. The individual with the highest fitness value finally obtained is the optimal spray strategy that meets the dust reduction requirements. This strategy achieves the best dust suppression effect under given constraints.

[0046] S104, taking dust suppression as the optimization goal, water mist parameters and nozzle layout plan as decision variables, and the holographic environment model of the mining area and the predicted results of wind-blown dust concentration distribution as constraints, the optimal spray strategy that meets the dust suppression requirements is solved through a heuristic search algorithm; Specifically, in order to achieve precise dust reduction, the optimal spray strategy is solved based on the holographic environmental model of the mining area and the predicted results of the wind-blown dust concentration distribution. In the specific implementation, the water mist parameters and the nozzle layout scheme are set as decision variables, where the water mist parameters include spray pressure, flow rate and spray angle, and the nozzle layout scheme includes the spatial position and orientation angle of the nozzle. With dust suppression as the optimization goal, the dust reduction effect and water consumption are comprehensively considered when constructing the objective function, and the environmental parameters and the predicted results of the wind-blown dust concentration distribution in the holographic environmental model of the mining area are taken as constraints. In the solution process, the heuristic search algorithm continuously adjusts the water mist parameters and the nozzle layout scheme through iterative optimization, evaluates the dust reduction effect and water use efficiency under each scheme, and finally finds the optimal spray strategy that meets the dust reduction needs. This control scheme design method based on multi-objective optimization makes full use of the environmental information provided by the holographic environmental model of the mining area and the predicted results of the wind-blown dust concentration distribution, realizes the coordinated optimization of dust reduction effect and resource utilization efficiency, and obtains the optimal spray strategy that can effectively suppress dust and save water.

[0047] S105, using the optimal spray strategy to control the grid spray array to perform dust reduction operations.

[0048] Specifically, after obtaining the optimal spray strategy, the optimal spray strategy is converted into specific control instructions through the industrial controller to accurately control the grid spray array. The grid spray array consists of multiple intelligent nozzles, which are evenly distributed in the mining area in a grid shape. Each nozzle is equipped with an independent actuator, which can adjust parameters such as spray pressure, flow rate and spray angle according to the control instructions. When performing dust suppression operations, the industrial controller decomposes the water mist parameters and nozzle layout scheme in the optimal spray strategy into specific control parameters for each nozzle, and issues control instructions in real time through the fieldbus network. After the grid spray array receives the control instructions, each nozzle operates in coordination to form a three-dimensional spray field covering the key areas of the mining area, achieving precise suppression of dust. This grid spray control method based on the optimal spray strategy enables the dust suppression system to dynamically adjust the spray parameters according to the real-time environmental conditions, improves the adaptability and control accuracy of the system, and achieves the goal of good dust suppression effect and low water consumption.

[0049] On the other hand, the present application also provides a mining intelligent water sprinkling and dust suppression system, such as Figure 2 , the system comprises: The data acquisition module 1 is used to acquire multi-source heterogeneous environmental perception data through multi-modal sensors arranged in the mining area; Preprocessing module 2 is used to preprocess the multi-source heterogeneous environmental perception data to obtain the preprocessed multi-source heterogeneous environmental perception data, and to construct a mining area holographic environment model based on the preprocessed multi-source heterogeneous environmental perception data; Prediction module 3 is used to extrapolate and estimate the dynamic change trend of wind dust concentration based on the holographic environment model of the mining area and use the spatiotemporal sequence prediction algorithm to obtain the prediction results of wind dust concentration distribution in various areas of the mining area in the future period; Spray strategy optimization module 4 is used to take dust suppression as the optimization goal, water mist parameters and nozzle layout plan as decision variables, and the holographic environment model of the mining area and the predicted results of wind-blown dust concentration distribution as constraints, and solve the optimal spray strategy that meets the dust suppression requirements through a heuristic search algorithm; The dust reduction operation execution module 5 is used to control the grid spray array with the optimal spray strategy to perform the dust reduction operation.

[0050] Please refer to Figure 3 The application also discloses an electronic device. Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0051] The communication bus 302 is used to realize the connection and communication between these components.

[0052] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0053] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WIFI interface).

[0054] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field~Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0055] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read~Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally be at least one storage system located away from the aforementioned processor 301. Refer to Figure 3The memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for a flocculant addition analysis method.

[0056] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program storing the intelligent water sprinkling and dust reduction method for mining in the memory 305. When executed by one or more processors 301, the electronic device 300 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to 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 know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application. In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0057] In the several implementations provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the system embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of the system or unit can be electrical or other forms.

[0058] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0059] The present application also provides a computer storage medium that can store multiple instructions, which are suitable for being loaded and executed by a processor as described above. Figure 1 The mining intelligent water sprinkling dust reduction method of the embodiment shown in the figure can be found in the specific implementation process. Figure 1 The specific description of the illustrated embodiment will not be repeated here.

[0060] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0061] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0062] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0063] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. An intelligent water sprinkling and dust reduction method for mining, characterized in that: The method comprises: Acquire multi-source heterogeneous environmental perception data through multi-modal sensors deployed in the mining area; Preprocessing the multi-source heterogeneous environmental perception data to obtain preprocessed multi-source heterogeneous environmental perception data, and constructing a mining area holographic environment model based on the preprocessed multi-source heterogeneous environmental perception data; Based on the holographic environment model of the mining area, the dynamic change trend of the dust concentration is extrapolated and estimated using the spatiotemporal sequence prediction algorithm to obtain the predicted results of the dust concentration distribution in each area of ​​the mining area in the future period; Taking dust suppression as the optimization goal, water mist parameters and nozzle layout plan as decision variables, and the holographic environment model of the mining area and the predicted results of the wind-blown dust concentration distribution as constraints, the optimal spray strategy that meets the dust suppression requirements is solved through a heuristic search algorithm; The optimal spray strategy is used to control the gridded spray array to perform dust reduction operations.

2. The method according to claim 1, characterized in that Preprocessing the multi-source heterogeneous environment perception data to obtain preprocessed multi-source heterogeneous environment perception data includes: Performing spatiotemporal synchronization on the multi-source heterogeneous environmental perception data to obtain synchronized multi-source heterogeneous environmental perception data; The synchronized multi-source heterogeneous environment perception data is cleaned to obtain the pre-processed multi-source heterogeneous environment perception data.

3. The method according to claim 1, characterized in that: The multi-source heterogeneous environmental perception data includes infrared thermal imaging image data, dust concentration data, wind speed and direction data, and three-dimensional data of the mining area; the mining area holographic environment model is constructed based on the pre-processed multi-source heterogeneous environmental perception data, including: Based on the infrared thermal imaging image data, a heat source distribution model covering the entire mining area is generated by thermal map fitting; determining dust concentration distribution based on the dust concentration data; Determining wind field streamlines within the mining area based on the wind speed and wind direction data; Based on the dust concentration distribution and the wind field streamlines inside the mining area, a dust concentration model reflecting the current state and historical change trend is constructed; Constructing a three-dimensional model of the mining area based on the three-dimensional data of the mining area; The heat source distribution model, the dust concentration model and the three-dimensional model of the mining area are semantically associated to obtain the holographic environment model of the mining area.

4. The method according to claim 3, characterized in that The semantic association of the heat source distribution model, the dust concentration model and the three-dimensional model of the mining area to obtain the holographic environment model of the mining area includes: Constructing a unified spatiotemporal reference frame, uniformly registering the coordinate systems of the heat source distribution model, the wind dust concentration model and the three-dimensional model of the mining area with the spatiotemporal reference frame, and obtaining a registered heat source distribution model, a registered wind dust concentration model and a registered three-dimensional model of the mining area respectively; Respectively extracting key features from the registered heat source distribution model, the registered dust concentration model, and the registered mining area three-dimensional model, and establishing semantic correspondences between the key features; Based on the semantic correspondence, the registered heat source distribution model, the registered dust concentration model and the registered mining area three-dimensional model are semantically associated to obtain the mining area holographic environment model.

5. The method according to claim 3, characterized in that: Determining the wind field streamlines inside the mining area based on the wind speed and wind direction data includes: Using the wind speed and direction data as boundary conditions and initial conditions, an air flow mathematical model describing the air flow inside the mining area is established; The air flow mathematical model is spatially discretized, and the interior of the mining area is divided into regular or irregular grid units to form a discretized equation group suitable for numerical solution; Selecting a suitable turbulence model, closing the Reynolds stress term in the discretized equation group, and obtaining a complete wind field numerical simulation control equation group; Using a numerical discretization method, the wind field numerical simulation control equation group is spatially discretized to obtain a wind field discretization control equation group; The wind field discretization control equations are time discretized using a time marching format to form an algebraic equation group for solving wind field streamlines; The algebraic equations are solved to obtain a discrete numerical solution of the mine wind field. Based on the discrete numerical solution of the mine wind field, a streamline tracing algorithm is used to gradually trace the wind field streamlines from the mine air outlet to the upstream to obtain the wind field streamlines inside the mine.

6. The method according to claim 3, characterized in that The dust concentration model reflecting the current state and historical change trend is constructed based on the dust concentration distribution and the wind field streamlines inside the mining area, including: Mapping and associating the dust concentration data with the wind field streamlines inside the mining area to form an initial distribution of wind dust concentration, and using the initial distribution of wind dust concentration as an initial condition of the wind dust concentration model; Based on the wind field streamlines, a convection-diffusion equation describing the spatial transport of dust is established, and the convection-diffusion equation is used as a dust concentration control equation of the dust concentration model; Discretizing the dust concentration control equation in time and space to form a set of discrete algebraic equations for dust concentration; The initial conditions are used as constraints to solve the dust concentration discrete algebraic equations to obtain a numerical solution for the dust concentration inside the wind field streamline at each discrete time step; The wind dust concentration model is constructed based on the numerical solution of the dust concentration.

7. The method according to claim 1, characterized in that The optimization goal is to suppress dust, the water mist parameters and the nozzle layout plan are used as decision variables, the holographic environment model of the mining area and the predicted results of the wind dust concentration distribution are used as constraints, and the optimal spray strategy that meets the dust suppression requirements is solved by a heuristic search algorithm, including: Establishing a mathematical model with minimization of dust concentration as the optimization goal, and vectorizing the water mist parameters and the nozzle layout scheme to obtain the decision variables; Converting the mining area holographic environment model and the wind-dust concentration distribution prediction result into value constraints of decision variables, and using the value constraints as the constraint conditions; A certain number of random water mist parameters and random nozzle layout schemes are randomly generated as the initial population, and each individual corresponds to a complete set of candidate spray strategies; Based on the holographic environment model of the mining area, the dust reduction effect of each candidate spray strategy is predicted by a numerical simulation method, and the fitness value of the individual is calculated according to the optimization objective function; The initial population is genetically manipulated to produce a new generation of population through survival of the fittest, until a preset termination condition is met, thereby obtaining the optimal spray strategy.

8. An intelligent water sprinkling and dust suppression system for mining, characterized in that: The system comprises: A data acquisition module is used to acquire multi-source heterogeneous environmental perception data through multi-modal sensors arranged in the mining area; A preprocessing module, used for preprocessing the multi-source heterogeneous environment perception data to obtain preprocessed multi-source heterogeneous environment perception data, and constructing a mining area holographic environment model based on the preprocessed multi-source heterogeneous environment perception data; A prediction module is used to extrapolate and estimate the dynamic change trend of wind dust concentration based on the holographic environment model of the mining area by using a spatiotemporal sequence prediction algorithm to obtain the prediction results of wind dust concentration distribution in various areas of the mining area in the future period; A spray strategy optimization module is used to solve the optimal spray strategy that meets the dust suppression requirements by using a heuristic search algorithm, taking dust suppression as the optimization goal, water mist parameters and nozzle layout scheme as decision variables, and the holographic environment model of the mining area and the predicted results of the wind-blown dust concentration distribution as constraints; The dust reduction operation execution module is used to control the grid spray array with the optimal spray strategy to perform the dust reduction operation.

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

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

Images