Coal-based solid waste resource utilization whole-process intelligent management and control platform and digital twin system

Abstract

The application relates to the technical field of process data analysis and processing, and discloses a coal-based solid waste resourceization full-process intelligent management and control platform and a digital twin system. The platform comprises: an identification module, which identifies the mineral phase of coal-based solid waste through a ray diffractometer to obtain mineral composition classification data; a construction module, which constructs a digital twin model based on the classification data, simulates a dissolution reaction, and obtains weathering and soil formation process data; an establishment module, which establishes a pollutant migration prediction model according to the process data to obtain environmental risk data; an optimization module, which optimizes the risk data through an improved particle swarm-genetic hybrid algorithm to obtain a resourceization path scheme; and an adjustment module, which adjusts process parameters based on the path scheme to obtain full-process management and control instructions. The application solves the problems of lacking accurate mineral phase identification and intelligent classification in the process of coal-based solid waste resourceization, and failing to construct a dynamic prediction model and simulate a weathering and soil formation process in real time based on mineral composition data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of process data analysis and processing, in particular to a coal-based solid waste resourceization full-process intelligent management and control platform and a digital twin system. BACKGROUND

[0002] In the prior art, coal-based solid waste resourceization processing mainly adopts traditional building material manufacturing, combustion power generation and valuable metal recovery methods. These methods usually rely on manual experience to set process parameters, and use periodic sampling detection to monitor the processing process, lacking real-time tracking and intelligent management and control of the physicochemical property changes of coal-based solid waste. Traditional coal gangue and fly ash processing technologies mainly focus on the preparation of a single product, and lack systematic classification and processing methods for coal-based solid waste of different sources and properties, making it difficult to achieve large-scale and efficient resource utilization.

[0003] The prior art has the following deficiencies: first, the intelligent level is limited, most of the existing systems are still in the data collection and simple analysis stage, lacking deep learning and predictive maintenance capabilities, and unable to achieve true adaptive control; second, the environmental risk assessment model is not perfect, especially the long-term prediction capability for complex processes such as pollutant migration and transformation and geological disaster risk evolution in the ecological utilization process of coal-based solid waste; third, the cost-benefit analysis and optimization algorithm are not mature, making it difficult to achieve global optimal configuration of the resourceization path under multi-objective constraint conditions.

[0004] Based on the above technical deficiencies, further analysis found that the existing technology also has deeper problems: how to establish a quantitative relationship model between the mineral phase of coal-based solid waste and the resourceization performance, how to realize dynamic simulation and prediction of the weathering into soil process of coal-based solid waste, how to build a multi-factor coupled environmental risk assessment system, and how to design a multi-objective collaborative optimization intelligent decision algorithm. The solution to these problems requires the organic combination of physical and chemical mechanism modeling, digital twin technology, intelligent optimization algorithm and adaptive control theory to form a full-process intelligent management and control technology system for coal-based solid waste resourceization. SUMMARY

[0005] The present application provides a coal-based solid waste resourceization full-process intelligent management and control platform and a digital twin system, which first solves the technical problem of lack of accurate mineral phase identification and intelligent classification in the resourceization process of coal-based solid waste, and then solves the problem of inability to build a dynamic prediction model and real-time simulation of the weathering into soil process based on mineral composition data, and finally solves the problem of inability to achieve multi-objective collaborative optimization and full-process adaptive control under environmental risk constraints.

[0006] In a first aspect, the present application provides a coal-based solid waste resourceization full-process intelligent management and control platform, which comprises:

[0007] The identification module is configured to perform mineral phase identification processing on the coal-based solid waste by means of a ray diffractometer to obtain coal-based solid waste mineral composition classification data.

[0008] The construction module is configured to construct a mineral phase conversion digital twin model based on the coal-based solid waste mineral composition classification data, and simulate a silicon-aluminum mineral dissolution reaction process to obtain coal gangue weathering into soil process data.

[0009] The establishment module is configured to establish a pollutant migration prediction model according to the coal gangue weathering into soil process data to obtain site environmental risk data.

[0010] The optimization module is configured to perform multi-objective optimization processing on the site environmental risk data by means of an improved particle swarm-genetic hybrid algorithm to obtain a resource utilization path scheme.

[0011] The adjustment module is configured to perform self-adaptive adjustment on coal-based solid waste treatment process parameters based on the resource utilization path scheme to obtain coal-based solid waste resource utilization whole-process management and control instructions.

[0012] In a second aspect, the present application provides a digital twin system, which realizes intelligent management and control of the whole process of coal-based solid waste resource utilization based on the coal-based solid waste resource utilization whole-process intelligent management and control platform.

[0013] In a third aspect, a coal-based solid waste resource utilization whole-process intelligent management and control device is provided, which includes a memory and at least one processor, and the memory stores instructions; the at least one processor invokes the instructions in the memory, so that the coal-based solid waste resource utilization whole-process intelligent management and control device executes the coal-based solid waste resource utilization whole-process intelligent management and control platform described above.

[0014] In a fourth aspect, a computer readable storage medium is provided, which stores instructions, and when the instructions are run on a computer, the computer executes the coal-based solid waste resource utilization whole-process intelligent management and control platform described above.

[0015] In the technical scheme provided in the present application, the coal-based solid waste mineral composition classification data is obtained by using a ray diffraction instrument for mineral phase identification processing of the coal-based solid waste. Compared with the traditional manual sampling and experience judgment method, the ray diffraction technology can accurately identify the content proportion of mineral phases such as quartz, kaolinite and illite, and realizes quantitative classification of the coal-based solid waste according to the molar ratio of silicon dioxide to aluminum oxide, thereby providing accurate basic data support for subsequent resource processing, and effectively solving the problems of inaccurate identification of the nature of the coal-based solid waste and non-uniform classification standards in the prior art. Based on the coal-based solid waste mineral composition classification data, a mineral phase conversion digital twin model is constructed, and a coal gangue weathering into soil process data is obtained by simulating the silicon-aluminum mineral dissolution reaction process. The digital twin technology can reflect the microscopic change process of physical minerals in real time by establishing a virtual mineral lattice and a three-dimensional bonding network structure. Compared with the traditional static analysis method, the digital twin model has the advantages of dynamic prediction and real-time synchronization, and can accurately simulate the mineral dissolution behavior under different temperature and pH conditions, thereby providing scientific theoretical guidance and parameter optimization basis for the rapid weathering of coal gangue into soil. According to the coal gangue weathering into soil process data, a pollutant migration prediction model is established to obtain site environmental risk data. By constructing a three-dimensional groundwater flow numerical model and using a convection diffusion equation to calculate the pollutant transport, the migration path and concentration distribution of heavy metal ions in soil and groundwater can be accurately predicted. Compared with the traditional empirical formula and simplified model, this method considers multiple factors such as soil layering characteristics, hydrogeological conditions and pollutant form transformation, thereby significantly improving the accuracy and reliability of environmental risk assessment.

[0016] The field environment risk data is processed by the improved particle swarm-genetic hybrid algorithm for multi-objective optimization to obtain a resourceization path scheme. In the application of the improved particle swarm-genetic hybrid algorithm in the field of coal-based solid waste resourceization, the silicon-aluminum activity index, heavy metal leaching toxicity and soil-forming efficiency are taken as optimization objectives, so that the optimal solution can be quickly searched in a complex multi-dimensional parameter space. The global search capability of the particle swarm algorithm and the local optimization characteristics of the genetic algorithm are combined to effectively avoid the defect that the traditional optimization method is easy to fall into local optimization. The adaptive characteristics of the algorithm enable it to dynamically adjust the optimization strategy according to the characteristics of different coal-based solid wastes and environmental constraints. Compared with artificial experience decision-making, the algorithm can comprehensively consider multiple objectives such as economic benefit, environmental safety and technical feasibility, realize the global optimal configuration of the resourceization path, and significantly improve the scientificity and efficiency of decision-making. Based on the resourceization path scheme, coal-based solid waste treatment process parameters are adaptively adjusted to obtain coal-based solid waste resourceization whole-process control instructions. The adaptive adjustment mechanism generates accurate equipment control signals by monitoring the deviation of the process parameters from the target set value in real time, and adopts a proportional-integral-derivative control algorithm. Compared with traditional open-loop control and manual adjustment methods, this method has the advantages of fast response speed, high control accuracy and strong anti-interference ability, and can automatically adjust the process parameters according to the changes in the properties of coal-based solid wastes and fluctuations in environmental conditions, ensuring that the entire resourceization process always operates in an optimal state, effectively solving the problems of process parameter adjustment lag, insufficient control accuracy and poor system stability in the prior art, and realizing intelligent, automatic and fine control of coal-based solid waste resourceization. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor based on these drawings.

[0018] Figure 1 is an embodiment schematic diagram of the coal-based solid waste resourceization whole-process intelligent control platform in the embodiment of the present application.

[0019] Figure 2 is a structural schematic block diagram of the coal-based solid waste resourceization whole-process intelligent control device in the embodiment of the present application. DETAILED DESCRIPTION

[0020] The embodiment of the present application provides a coal-based solid waste resourceization full-process intelligent management and control platform and a digital twin system. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" or "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0021] For ease of understanding, the specific process of the embodiment of the present application is described below. Please refer to Figure 1 One embodiment of the coal-based solid waste resourceization full-process intelligent management and control platform in the embodiment of the present application includes:

[0022] The identification module 101 is configured to perform mineral phase identification processing on the coal-based solid waste by means of a ray diffractometer, to obtain coal-based solid waste mineral composition classification data.

[0023] The construction module 102 is configured to construct a mineral phase conversion digital twin model based on the coal-based solid waste mineral composition classification data, and simulate a silicon-aluminum mineral dissolution reaction process, to obtain coal gangue weathering into soil process data.

[0024] The establishment module 103 is configured to establish a pollutant migration prediction model according to the coal gangue weathering into soil process data, to obtain site environmental risk data.

[0025] The optimization module 104 is configured to perform multi-objective optimization processing on the site environmental risk data by means of an improved particle swarm-genetic hybrid algorithm, to obtain a resourceization path scheme.

[0026] The adjustment module 105 is configured to perform self-adaptive adjustment on coal-based solid waste treatment process parameters based on the resourceization path scheme, to obtain coal-based solid waste resourceization full-process management and control instructions.

[0027] It can be understood that the execution subject of the present application can be a digital twin system, and can also be a terminal or a server, and the specific execution subject is not limited herein. The embodiment of the present application takes a server as an execution subject for example.

[0028] Specifically, the identification module 101 adopts a ray diffractometer to detect the coal-based solid waste sample by two-dimensional scanning, obtains ray diffraction spectrum data with a diffraction angle range of 5° to 80°, extracts characteristic diffraction peak intensity values of quartz, kaolinite and illite through peak identification processing, calculates the mass percentage of silicon dioxide and aluminum oxide and obtains the molar ratio, classifies the coal-based solid waste into three categories of low activity, medium activity and high activity according to the numerical interval, and forms specific mineral composition classification data. The construction module 102 establishes a virtual mineral lattice containing atomic coordinates, bonding relationships and physical property parameters by initializing the spatial positions of silicon atoms and aluminum atoms through molecular coordinate initialization processing, establishing basic tetrahedral units of silicon-oxygen tetrahedron and aluminum-oxygen tetrahedron, forming a three-dimensional bonding network topology through bridge connection assembly by sharing oxygen atoms, and mapping to a digital space. A mineral phase transformation digital twin model is established by setting a real-time data synchronization interface and a state updating algorithm, while setting the boundary condition parameters of reaction temperature and pH value, calculating the silicon-aluminum mineral activation energy parameter, substituting the dissolution reaction kinetics parameter into the silicate dissolution rate equation for iterative calculation, simulating the release process of silicon ions and aluminum ions according to the time step, and generating coal gangue weathering into soil process data by combining microbial metabolism coupling calculation and soil pH value change.

[0029] The establishment module 103 analyzes the soil layering characteristics of the coal gangue weathering into soil process data, extracts the porosity and permeability coefficient parameters to form site hydrogeological parameters, establishes a three-dimensional groundwater flow numerical model to calculate the water head distribution of each node, uses the convection-diffusion equation to calculate and process the pollutant transport, simulates the migration path of heavy metals in soil, and generates site environmental risk data by quantitatively calculating the heavy metal exceeding multiple. The optimization module 104 constructs a multi-objective function expression including the silicon-aluminum activity index, heavy metal leaching toxicity and soil formation efficiency by using the site environmental risk data, initializes the particle swarm population and assigns a position vector and a velocity vector to each particle, wherein the position vector represents the combination of coal-based solid waste treatment process parameters, and through fitness evaluation and velocity update iteration processing, when the particle fitness stagnates, the genetic algorithm crossover mutation operation is started to generate new candidate solutions. Through the Pareto front screening, the process parameter configuration with the best comprehensive performance is selected from the non-dominated solution set to form the resource utilization path scheme.

[0030] The adjustment module 105 performs process parameter analysis processing on the resource utilization path scheme, extracts the key control parameters of geopolymer preparation temperature, stirring speed, solid-liquid ratio and activator addition amount, performs deviation calculation on the current detection value and the target set value through real-time process parameter comparison processing, generates corresponding equipment control signals through proportional-integral-derivative control calculation processing, and sends them to each control equipment in the order of the coal-based solid waste treatment process through execution priority sorting and time sequence coordination processing. Form a coal-based solid waste resource utilization whole-process management and control instruction.

[0031] For example, the ray diffraction instrument detection found that the quartz content in the coal gangue sample was the main component, and the characteristic diffraction peak intensity value extracted by peak identification showed that the molar ratio of silicon dioxide to aluminum oxide was 3.2, so it was classified as medium activity solid waste. The digital twin model established the corresponding silicon-oxygen tetrahedral network structure according to this classification data, simulated the gradual acceleration of silicon ion release rate in an alkaline environment, and the microbial metabolism coupling calculation showed that the soil pH gradually neutralized from the original 4.5 to 6.8, and the organic matter content increased over time. The pollutant migration prediction model calculated the groundwater flow field distribution based on the weathering and soil formation process data, and the convection and diffusion equation showed that heavy metal ions were mainly concentrated in the surface soil, and the exceeding standard multiple was controlled within a safe range. The improved particle swarm-genetic hybrid algorithm comprehensively considers three objective functions, and determines the optimal stirring speed as 280 revolutions per minute, the solid-liquid ratio as 1 to 2.5, and the activator addition amount as 8% of the total weight through multiple rounds of iterative optimization. The adaptive adjustment module generates specific equipment control instructions accordingly to ensure that the entire coal-based solid waste resourceization process operates under optimal process parameters.

[0032] In an embodiment, the identification module 101 is configured to:

[0033] perform two-dimensional scanning detection on the coal-based solid waste sample by using a ray diffraction instrument to obtain ray diffraction spectrum data in a diffraction angle range of 5° to 80°;

[0034] perform peak identification processing on the ray diffraction spectrum data to extract characteristic diffraction peak intensity values of quartz, kaolinite, and illite, and obtain a mineral phase qualitative identification result;

[0035] calculate the mass percentage of silicon dioxide and aluminum oxide based on the mineral phase qualitative identification result, and calculate a molar ratio value to obtain a silicon-aluminum ratio quantitative parameter;

[0036] classify the silicon-aluminum ratio quantitative parameter according to a numerical interval, and when the molar ratio value is greater than 4.0, classify it as low-activity solid waste, when the molar ratio value is between 2.0 and 4.0, classify it as medium-activity solid waste, and when the molar ratio value is less than 2.0, classify it as high-activity solid waste, to obtain coal-based solid waste mineral composition classification data.

[0037] Specifically, when the identification module 101 performs two-dimensional scanning detection on the coal-based solid waste sample by using a ray diffraction instrument, the ray diffraction instrument emits X-rays of a specific wavelength to irradiate the surface of the coal-based solid waste sample. When the rays encounter the crystal structure in the sample, diffraction occurs. The diffraction angle range is set to 5° to 80°, covering the characteristic diffraction angles of the main mineral phases in the coal-based solid waste. During the scanning process, the detector records the diffraction intensity values at different angle positions according to a fixed step size, forming ray diffraction spectrum data with diffraction angles as the horizontal coordinates and diffraction intensities as the vertical coordinates.

[0038] The peak position recognition processing stage adopts digital signal processing technology to analyze the ray diffraction spectrum data. First, the background noise and baseline drift in the spectrum are removed through a filtering algorithm, and then a peak detection algorithm is used to identify the significant peak positions in the spectrum. The characteristic diffraction peak of quartz is located at 26.6°, the characteristic diffraction peak of kaolinite is located at 12.3°, and the characteristic diffraction peak of illite is located at 8.8°. The peak position recognition algorithm determines the existence of mineral phases by comparing the deviation of the measured peak position from the standard peak position, and records the intensity values of each characteristic peak. The intensity values reflect the relative content of the corresponding mineral phase in the sample, forming a qualitative mineral phase recognition result.

[0039] When calculating the mass percentage of silicon dioxide and aluminum oxide, based on the intensity values of each mineral phase in the qualitative mineral phase recognition result, the reference intensity method is used for quantitative calculation. Quartz mineral is composed of silicon dioxide only, kaolinite mineral contains silicon dioxide and aluminum oxide components, and illite mineral also contains silicon dioxide and aluminum oxide components. The total content of silicon dioxide and aluminum oxide is obtained by multiplying the intensity values of each mineral phase by the corresponding chemical composition coefficient and summing them up. When calculating the mass percentage, the mass of each component is divided by the total mass of the sample and multiplied by 100. The molar ratio value requires dividing the mass percentage by the corresponding molecular weight. The molecular weight of silicon dioxide is 60.08 grams per mole, and the molecular weight of aluminum oxide is 101.96 grams per mole. The molar ratio value is equal to the number of moles of silicon dioxide divided by the number of moles of aluminum oxide.

[0040] The classification processing of the silicon-aluminum ratio quantitative parameter is based on the relationship between the activity of coal-based solid waste and the molar ratio. When the molar ratio is greater than 4.0, it indicates that the content of silicon dioxide is relatively high and the content of aluminum oxide is low. Such coal-based solid waste has low reactivity in an alkaline environment and is classified as low-activity solid waste. When the molar ratio is between 2.0 and 4.0, the ratio of silicon dioxide to aluminum oxide is relatively balanced, and the reactivity is moderate, classified as medium-activity solid waste. When the molar ratio is less than 2.0, the content of aluminum oxide is relatively high. Such coal-based solid waste has strong reactivity and is classified as high-activity solid waste. The classification result directly affects the selection and addition of activators in the subsequent geopolymer preparation process.

[0041] In a specific embodiment, the construction module 102 includes:

[0042] The processing unit is configured to input the coal-based solid waste mineral composition classification data into a three-dimensional network structure modeling algorithm for spatial configuration processing, establish a bonding network model of silicon-oxygen tetrahedron and aluminum-oxygen tetrahedron, and obtain a mineral phase transformation digital twin model.

[0043] The computing unit is configured to set the boundary condition parameters of the reaction temperature of 20-80 DEG C and the pH value of 8.0-14.0 based on the mineral phase transformation digital twin model, and calculate the activation energy parameters of the silicon-aluminum mineral in the alkaline environment to obtain the dissolution reaction kinetics parameters.

[0044] The iteration unit is configured to substitute the dissolution reaction kinetics parameters into the silicate dissolution rate equation for iterative calculation and processing, simulate the release process of silicon ions and aluminum ions at a time step of 1 hour, and obtain a mineral dissolution process curve.

[0045] The coupling unit is configured to perform microbial metabolic coupling calculation and processing on the mineral dissolution process curve, combine the soil pH change and the organic matter accumulation rate, and obtain coal gangue weathering into soil process data.

[0046] Specifically, when the processing unit of the construction module 102 inputs the coal-based solid waste mineral composition classification data into the three-dimensional network structure modeling algorithm, first, the classification data is subjected to molecular coordinate initialization processing, and the position coordinates of silicon atoms and aluminum atoms in the three-dimensional space are allocated according to the mineral phase content proportion identified by the identification module. The three-dimensional network structure modeling algorithm uses crystallographic principles to establish the spatial relationship between atoms. Each silicon atom is connected to four oxygen atoms in a tetrahedral geometry to form a silicon-oxygen tetrahedron. Each aluminum atom is also connected to four oxygen atoms to form an aluminum-oxygen tetrahedron. The basic tetrahedral unit is connected by sharing oxygen atoms to form a three-dimensional bonding network with a network topology. The three-dimensional bonding network topology is then mapped into a digital space to establish a virtual mineral lattice containing atomic coordinates, bonding relationships, and physical property parameters. The digital mineral structure model establishes a dynamic correspondence between the physical mineral and the virtual model by setting a real-time data synchronization interface and a state updating algorithm, forming a mineral phase transformation digital twin model.

[0047] When the computing unit sets the boundary condition parameters based on the mineral phase transformation digital twin model, the reaction temperature range is set to 20-80 DEG C, covering the temperature variation range of coal-based solid waste in natural environment and industrial treatment conditions. The pH value is set to 8.0-14.0, corresponding to the chemical environment of coal-based solid waste under the action of alkaline activator. The boundary condition parameters directly affect the reaction activity and dissolution behavior of silicon-aluminum minerals. The activation energy parameter calculation is based on the Arrhenius equation principle. The activation energy value is determined by analyzing the reaction rate constant variation law under different temperature conditions. The activation energy parameter of silicon-aluminum mineral in alkaline environment reflects the energy threshold required for mineral lattice structure destruction and ion release. The higher the activation energy value, the more difficult the mineral is to be dissolved in alkaline solution. The lower the activation energy value, the easier the mineral is to dissolve. The dissolution reaction kinetics parameters include reaction rate constant, activation energy, reaction order, and other key values.

[0048] When the iteration unit substitutes the dissolution reaction kinetics parameters into the silicate dissolution rate equation for iterative calculation, the silicate dissolution rate equation describes the relationship between the release speed of silicon ions and aluminum ions from the mineral lattice and time, and the time step is set to 1 hour to ensure a balance between calculation accuracy and calculation efficiency. The iterative calculation process repeats the dissolution rate calculation at fixed time intervals, and each iteration updates the dissolution rate at the current time based on the ion concentration and mineral surface state at the previous time. The silicon ion release process is influenced by the mineral surface area, solution concentration gradient, and temperature conditions. The aluminum ion release process also follows similar kinetics but has different reaction parameters. The iterative calculation continues until the preset simulation time length is reached. The simulation results are output in the form of ion concentration curves over time, forming a mineral dissolution progress curve.

[0049] When the coupling unit performs microbial metabolic coupling calculation on the mineral dissolution progress curve, organic acids produced by microbial metabolism can accelerate the chemical weathering of minerals. At the same time, microbial respiration consumes oxygen and produces carbon dioxide, changing the chemical environment of the soil. The microbial metabolic coupling calculation introduces biological factors into the original chemical dissolution model by modifying the parameters of the dissolution rate equation to reflect the influence of microbial activity. The soil pH change data is derived from the combined effect of microbial acid production and mineral dissolution to release basic ions. The organic matter accumulation rate reflects the process of microbial decomposition and the accumulation of metabolic products in the soil. The coupling calculation unifies the chemical weathering process and the biological weathering process in the same mathematical model. The generated coal gangue weathering into soil progress data contains information on mineral composition changes, ion concentration evolution, acid-base adjustment, and organic matter content growth in multiple dimensions.

[0050] In a specific embodiment, the processing unit is configured to:

[0051] The coal-based solid waste mineral composition classification data is subjected to molecular coordinate initialization processing, and the spatial positions of silicon atoms and aluminum atoms are allocated according to the mineral phase content ratio to obtain atomic spatial coordinate parameters.

[0052] Based on the atomic spatial coordinate parameters, a tetrahedral geometric structure is established, each silicon atom is connected with four oxygen atoms to form a silicon-oxygen tetrahedron, and each aluminum atom is connected with four oxygen atoms to form an aluminum-oxygen tetrahedron, to obtain a basic tetrahedral unit.

[0053] The basic tetrahedral unit is subjected to network connection processing, and the silicon-oxygen tetrahedron and the aluminum-oxygen tetrahedron are bridged and assembled by sharing oxygen atoms to obtain a three-dimensional bonding network topology.

[0054] The three-dimensional bonding network topology is mapped into a digital space to establish a virtual mineral lattice containing atomic coordinates, bonding relationships, and physical property parameters, and a digital mineral structure model is obtained.

[0055] The real-time data synchronization interface and the state updating algorithm are set for the digitized mineral structure model, a dynamic corresponding relationship between the physical mineral and the virtual model is established, and a mineral phase conversion digital twin model is obtained.

[0056] Specifically, the processing unit performs molecular coordinate initialization processing, receives the coal-based solid waste mineral composition classification data output by the identification module, which contains the content ratio information of mineral phases such as quartz, kaolinite, and illite, and the molecular coordinate initialization processing first determines the total number of silicon atoms and aluminum atoms according to the chemical composition of each mineral phase. The quartz mineral is composed of silicon-oxygen bonds, so it contributes to the number of silicon atoms. The kaolinite and illite minerals contain both silicon atoms and aluminum atoms. The processing unit calculates the number ratio of silicon atoms and aluminum atoms according to the stoichiometric relationship. Then, a random distribution algorithm is used to assign initial coordinate positions to each atom in a three-dimensional space. The spatial coordinate parameters are represented in a Cartesian coordinate system, and the position of each atom is determined by three values x, y, and z. The minimum distance constraint between atoms ensures that adjacent atoms do not overlap or collide. After the assignment is complete, an atomic spatial coordinate parameter dataset containing the spatial position information of all silicon atoms and aluminum atoms is formed. When establishing the tetrahedral geometry, the processing unit starts to build the basic structural unit based on the atomic spatial coordinate parameters. In the formation process of silicon-oxygen tetrahedra, each silicon atom acts as a central atom and is connected to four surrounding oxygen atoms through covalent bonds. The position of the oxygen atom is selected according to the tetrahedral geometric constraint condition. The silicon-oxygen bond length is set to a fixed value, and the bond angle follows the standard angle of 109.5 degrees of the tetrahedron. The formation process of aluminum-oxygen tetrahedra is similar to that of silicon-oxygen tetrahedra, but uses different bond length parameters. The aluminum-oxygen bond length is slightly larger than the silicon-oxygen bond length, reflecting the ionic radius characteristics of aluminum atoms. The establishment process of the tetrahedral geometry determines the exact position of each oxygen atom relative to the central atom through geometric calculation. After completion, the basic tetrahedral unit set is obtained, which is composed of independent silicon-oxygen tetrahedral units and aluminum-oxygen tetrahedral units. In the network connection processing stage, the processing unit performs bridge connection and assembly operations on the basic tetrahedral units. The bridge connection process realizes the connection between different tetrahedra by sharing oxygen atoms. The shared oxygen atom becomes a bridge connecting two tetrahedra. An oxygen atom belongs to two adjacent tetrahedral structures at the same time. The network connection algorithm first identifies tetrahedral pairs that meet the connection conditions, including spatial distance constraints and geometric angle constraints. The tetrahedra that meet the conditions are connected by adjusting the position of the oxygen atom. The basic geometric shape of the tetrahedron remains unchanged during the bridge connection process. After the connection is completed, a network structure is formed by connecting multiple tetrahedra through shared oxygen atoms. The three-dimensional bonding network topology has branch and ring connection characteristics. The topological properties of the network reflect the crystal structure characteristics of the mineral. The processing unit records each connection relationship and network node information to form the topological structure data.The processing unit in the digital space mapping process converts the three-dimensional bonding network topology into a computer-processable digital representation. The mapping process includes the digital storage of coordinate data, the graph theory representation of bonding relationships, and the database association of physical property parameters. The virtual mineral lattice exists in the form of data structures in the digital space, including an atomic coordinate matrix that records the three-dimensional position of each atom, a bonding relationship matrix that describes the connection between atoms, and a physical and chemical property database that stores the physical and chemical properties related to each atom and bond. The digital mineral structure model completely describes the microstructure characteristics of the virtual mineral through the combination of these data structures.

[0057] The real-time data synchronization interface and state update algorithm enable the digital mineral structure model to have dynamic response capabilities. The real-time data synchronization interface is responsible for receiving real-time data from physical detection devices, including temperature sensors, pH detectors, ion concentration monitors, and other devices. The state update algorithm adjusts the relevant parameters in the virtual model based on the received real-time data. Temperature changes affect atomic vibration amplitude and bond stability, pH changes affect ion charge state and reaction activity, and ion concentration changes affect chemical equilibrium and reaction direction. The algorithm converts these external changes into model parameter adjustments through pre-set physical and chemical laws, ensuring that the virtual model always reflects the current state of the physical mineral. The mineral phase transformation digital twin model achieves consistency between the virtual and real through this synchronization mechanism.

[0058] In a specific embodiment, the establishment module 103 is configured to:

[0059] The coal gangue weathering into soil process data is subjected to soil layering characteristic analysis and processing to extract porosity and permeability coefficient parameters, and site hydrogeological parameters are obtained.

[0060] A three-dimensional groundwater flow numerical model is established based on the site hydrogeological parameters, water head distribution of each node is calculated, and groundwater flow field distribution data are obtained.

[0061] The groundwater flow field distribution data are subjected to pollutant transport calculation and processing using the convection-diffusion equation, and pollutant concentration distribution results are obtained.

[0062] The pollutant concentration distribution results are subjected to risk assessment quantification processing, heavy metal exceedance multiples are calculated, and site environmental risk data are obtained.

[0063] Specifically, when the soil layering characteristic analysis processing is performed by the establishing module 103, the coal gangue weathering into soil process data output by the constructing module is received, which contains the mineral composition change, particle size distribution and chemical composition evolution information of different depth soil layers. The soil layering characteristic analysis processing first divides the weathering into soil process data according to the depth dimension. The surface soil is most strongly affected by weathering, the middle layer soil is in a weathering transition state, and the bottom layer soil retains the original coal gangue characteristics. The porosity parameter is calculated by analyzing the proportional relationship between the solid particles and the void volume in each soil layer. The soil layer with higher weathering degree has more pore space due to the crushing and rearrangement of mineral particles, and the porosity value increases accordingly. The permeability coefficient parameter reflects the ability of the soil layer to conduct water. The permeability coefficient is calculated by analyzing the soil particle size distribution and pore connectivity. The soil layer with high fine particle content has smaller permeability coefficient, and the soil layer mainly composed of coarse particles has larger permeability coefficient. The site hydrogeological parameter set contains key values such as porosity, permeability coefficient, water content and unit weight of each soil layer. When the three-dimensional groundwater flow numerical model is established, the establishing module establishes a mathematical model describing the law of groundwater movement based on the site hydrogeological parameters. The three-dimensional groundwater flow numerical model divides the study area into three-dimensional grid elements, each grid element is assigned corresponding hydrogeological parameters, groundwater flow follows Darcy's law, and water head distribution calculation is realized by solving the groundwater flow equation set. The water head distribution of each node reflects the potential energy distribution state of groundwater in three-dimensional space. The water head gradient drives groundwater to flow from high water head area to low water head area. The numerical model solves the partial differential equation set by finite difference method or finite element method, and the calculation process considers the constraints of boundary conditions and initial conditions. The groundwater flow field distribution data represents the flow direction and flow rate of each point in the form of velocity vector field.

[0064] The module for establishing is used for inputting the groundwater flow field distribution data as an input condition when performing the pollutant transport calculation and processing of the convection diffusion equation, the convection diffusion equation describes the migration process of the pollutant in the groundwater, the convection term reflects the transmission process of the pollutant flowing with the groundwater, and the diffusion term reflects the molecular diffusion and mechanical dispersion of the pollutant due to the concentration gradient. The pollutant transport calculation and processing need to set the position, intensity and duration of the pollution source, the heavy metal ions such as cadmium, lead and arsenic in the coal-based solid waste are taken as the main pollutants for tracking calculation, the calculation process is performed in a time stepping manner, the concentration distribution of the pollutant is updated in each time step, the concentration distribution is jointly affected by the groundwater flow rate, the diffusion coefficient and the reaction parameter, different heavy metal ions have different migration characteristics and environmental behaviors, and the concentration distribution result of the pollutant is in the form of a three-dimensional concentration field, which presents the change law of the pollutant concentration of each monitoring point with time. The module for establishing in the risk assessment quantization processing stage is used for performing the environmental risk quantization analysis on the pollutant concentration distribution result, the heavy metal exceeding standard multiple is calculated by comparing the actual concentration with the environmental standard limit value, the groundwater quality standard stipulates the maximum allowable concentration of various heavy metal ions, the exceeding standard multiple is equal to the actual concentration divided by the standard limit value, the exceeding standard multiple greater than 1 indicates that there is an environmental risk, the greater the exceeding standard multiple, the higher the risk degree, the risk assessment quantization processing also considers the toxicity weight and exposure path of the pollutant, and comprehensively evaluates the human health risk and the ecological environmental risk. The site environmental risk data contains the risk grade, the exceeding standard multiple and the influence range and other information of each monitoring point.

[0065] In an embodiment, the optimization module 104 is configured to:

[0066] perform target function construction processing on the site environmental risk data to obtain a multi-objective function expression;

[0067] initialize a particle swarm population based on the multi-objective function expression, and assign a position vector and a velocity vector to each particle, wherein the position vector represents a combination of the coal-based solid waste treatment process parameters, and an initial particle swarm population is obtained;

[0068] perform fitness evaluation and velocity update iteration processing on the initial particle swarm population, start a genetic algorithm crossover mutation operation when the particle fitness stagnates, generate a new candidate solution and update the global optimal position, and obtain an optimization iteration result;

[0069] perform a Pareto front screening processing on the optimization iteration result, select a process parameter configuration with the best comprehensive performance from the non-dominated solution set, and obtain a resourceization path scheme.

[0070] Specifically, the optimization module 104 receives the site environment risk data output by the establishment module when performing the objective function construction process, which contains key information such as heavy metal exceeding multiple, pollution influence range, and environmental risk level, etc. The objective function construction process converts multiple optimization objectives in the coal-based solid waste resourceization process into mathematical expressions. The silicon-aluminum activity index is used as the first optimization objective to reflect the reaction activity of coal-based solid waste in the preparation process of geopolymer. The higher the activity index, the better the resource utilization efficiency. The heavy metal leaching toxicity is used as the second optimization objective to reflect the environmental safety in the ecological utilization process of coal-based solid waste. The lower the leaching toxicity, the smaller the environmental risk. The soil formation efficiency is used as the third optimization objective to reflect the speed of weathering of coal gangue into available soil. The higher the soil formation efficiency, the shorter the ecological restoration period. The multi-objective function expression linearly or nonlinearly combines the three single-objective functions through weight coefficients, which are dynamically adjusted according to actual application requirements and environmental risk levels. During the particle swarm population initialization process, the optimization module creates an initial population of particle swarm algorithm based on the multi-objective function expression. Each particle represents a combination scheme of coal-based solid waste treatment process parameters. The position vector contains key process parameters such as geopolymer preparation temperature, stirring speed, solid-liquid ratio, activator addition amount, and coal gangue pretreatment time. Each dimension of the position vector corresponds to a specific process parameter value. The velocity vector represents the moving direction and speed of the particle in the parameter space. The dimension of the velocity vector is consistent with that of the position vector. The initial particle swarm population is randomly assigned position vectors and velocity vectors within the preset parameter range by a random number generator. The population size is determined according to the complexity of the optimization problem and the limitation of computing resources.

[0071] During the fitness evaluation and velocity update iteration process, the optimization module calculates the fitness of each particle in the initial particle swarm population. The fitness value is calculated by substituting the particle's position vector into the multi-objective function expression. The fitness value reflects the comprehensive performance of the current process parameter combination. The velocity update follows the standard update formula of the particle swarm algorithm. The velocity of each particle is attracted by the individual historical optimal position and the global historical optimal position. During the velocity update process, the inertia weight and learning factor parameters are introduced to adjust the exploration ability and convergence speed of the particle. The position update is achieved by adding the current position and the updated velocity. The iteration process repeatedly performs the fitness evaluation, velocity update, and position update operations. When the global optimal fitness does not significantly improve for several consecutive generations, it is judged that the particle fitness is stagnant. The stagnation detection triggers the starting condition of the genetic algorithm crossover and mutation operations. The crossover operation generates new candidate solutions by randomly selecting two particles and exchanging part of their position vectors. The mutation operation generates new candidate solutions by adding random perturbations to random dimensions of the particle position vector. The new candidate solutions replace the particles with poor fitness in the population and update the global optimal position. The optimization iteration result contains the particle swarm population and the corresponding fitness distribution after multiple iterations.

[0072] The Pareto frontier screening processing stage optimization module screens the multi-objective optimization solution of the optimization iteration result. The Pareto frontier is a set of non-dominated solutions in a multi-objective optimization problem. A non-dominated solution refers to a solution that is not completely dominated by other solutions in all objective functions. The screening process first determines the dominance relationship of all particles in the population. The dominance relationship is determined by comparing the performance of two solutions in each objective function. If solution A is not worse than solution B in all objective functions and is better than solution B in at least one objective function, then solution A dominates solution B. The non-dominated solution set contains all solutions that are not dominated by other solutions. The Pareto frontier screening selects solutions that are uniformly distributed and representative from the non-dominated solution set as candidate solutions. The selection process considers the crowding distance and diversity index between solutions. The crowding distance reflects the density of solutions in the objective space, and the diversity index ensures that the selected solutions cover the entire Pareto frontier. The optimal process parameter configuration is determined by considering the importance of each objective function and the actual constraint conditions from the Pareto frontier. The resourceization path scheme includes the optimal process parameter configuration and the corresponding expected performance indicators.

[0073] In a specific embodiment, the adjustment module 105 is configured to:

[0074] The resourceization path scheme is subjected to process parameter analysis processing to extract key control parameters such as geopolymer preparation temperature, stirring speed, solid-liquid ratio, and activator addition amount, and obtain target process parameter set values.

[0075] Based on the target process parameter set values, real-time process parameter comparison processing is performed to calculate the deviation between the current detection values and the target set values, and obtain parameter adjustment deviation amounts.

[0076] The parameter adjustment deviation amounts are subjected to proportional-integral-derivative control calculation processing to generate corresponding device control signals and obtain process parameter adjustment instructions.

[0077] The process parameter adjustment instructions are subjected to execution priority sorting and timing coordination processing, and are sent to each control device in the order of the coal-based solid waste treatment process to obtain coal-based solid waste resourceization whole-process management and control instructions.

[0078] Specifically, when the adjustment module 105 performs the process parameter analysis process, it receives the resource path scheme output by the optimization module, which contains the optimal process parameter configuration and expected performance indicators determined after multi-objective optimization. The process parameter analysis process first analyzes the data structure of the resource path scheme to identify the types and value ranges of each process parameter contained therein. The geopolymer preparation temperature is a key control parameter that affects the dissolution rate of silicon-aluminum minerals and the reactivity of the polymerization reaction. The temperature parameter is extracted from the scheme and converted into a temperature set value that can be recognized by the control equipment. The stirring speed parameter controls the mixing uniformity and mass transfer efficiency of the reaction system. The speed parameter needs to consider the mechanical limitations and power constraints of the equipment after extraction. The solid-liquid ratio parameter determines the ratio of coal-based solid waste to liquid phase activator. The solid-liquid ratio value directly affects the flowability and reaction completeness of the reaction slurry. The activator addition amount parameter controls the strength and duration of the alkaline environment. The addition amount parameter needs to be dynamically adjusted according to the silicon-aluminum ratio of the coal-based solid waste. The target process parameter set value is obtained by converting these key control parameters into a standardized numerical format and assigning them to the corresponding control loop. In the real-time process parameter comparison process, the adjustment module establishes a parameter monitoring and comparison mechanism based on the target process parameter set value. Real-time process parameter detection is achieved through temperature sensors, speed encoders, flow meters, and concentration detectors deployed in the production site. The current detection values are transmitted to the adjustment module in a standardized data format for processing. The comparison process calculates the deviation by comparing the current detection value with the target set value. The deviation calculation uses the difference operation, i.e., the deviation equals the target set value minus the current detection value. A positive deviation indicates that the current parameter is lower than the target value and needs to be increased. A negative deviation indicates that the current parameter is higher than the target value and needs to be decreased. The parameter adjustment deviation includes information such as the deviation value, deviation direction, and deviation change rate. The deviation change rate is calculated by taking the derivative of the deviation value over multiple consecutive sampling periods, reflecting the trend and speed of parameter change.

[0079] The proportional-integral-derivative control calculation processing stage adjustment module inputs the parameter adjustment deviation into a proportional-integral-derivative control algorithm for control signal generation. The proportional-integral-derivative control algorithm is a classical closed-loop control method. A proportional element generates a control action proportional to the current deviation according to the size of the current deviation. A proportional coefficient determines the sensitivity and response strength of the controller to the deviation. An integral element accumulates the historical deviation for calculation to eliminate the steady-state error of the system. An integral time constant affects the strength of the integral action and the stability of the system. A derivative element generates a leading control action according to the rate of change of the deviation to improve the dynamic response characteristics of the system. A derivative time constant determines the influence degree of the derivative action. The outputs of the proportional, integral, and derivative elements are weighted and summed to obtain the total control output. The control output is converted into a device control signal after amplitude limiting and filtering processing. The device control signal contains control direction, control amplitude, and execution time elements. The process parameter adjustment instruction is output in the form of a digital signal or an analog signal to a field execution device. The execution priority sequencing and timing coordination processing stage adjustment module manages and coordinates the process parameter adjustment instruction. The execution priority sequencing determines the execution order according to the influence degree of the process parameter on the overall performance and the urgency of adjustment. Temperature control usually has a high execution priority due to large thermal inertia. The stirring speed regulation has a relatively low priority due to fast response speed. The activator addition amount regulation involves chemical reaction equilibrium and needs to be coordinated with other parameters. The timing coordination processing considers the mutual influence and constraint relationship between different control loops to avoid system disturbance caused by simultaneous execution of multiple control actions. The timing coordination algorithm arranges the sending time of the control instruction according to the process sequence of the coal-based solid waste treatment process to ensure that each control device executes the adjustment action according to a reasonable time interval and logical sequence. The coal-based solid waste resourceization full-process control instruction integrates the adjustment requirements and execution plans of all process parameters to form a complete device control scheme.

[0080] The embodiment of the present application provides a digital twin system, which realizes intelligent management and control of the coal-based solid waste resourceization full process based on a coal-based solid waste resourceization full-process intelligent management and control platform.

[0081] With reference to Figure 2 In the embodiment of the present application, a coal-based solid waste resourceization full-process intelligent management and control device is also provided. The coal-based solid waste resourceization full-process intelligent management and control device can be a server, and its internal structure can be as shown in Figure 2The coal-based solid waste resourceization whole-process intelligent management and control device shown in the figure includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. The processor of the computer is used to provide calculation and control capabilities. The memory of the coal-based solid waste resourceization whole-process intelligent management and control device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the coal-based solid waste resourceization whole-process intelligent management and control device is used to store the corresponding data in this embodiment. The network interface of the coal-based solid waste resourceization whole-process intelligent management and control device is used to communicate with external terminals through network connection. The computer program is executed by the processor to realize the above method.

[0082] Those skilled in the art can understand that, Figure 2 The structure shown in the figure is only a block diagram of part of the structure related to the present application scheme, and does not constitute a limitation on the coal-based solid waste resourceization whole-process intelligent management and control device to which the present application scheme is applied.

[0083] The present application also provides a computer readable storage medium, which can be a non-volatile computer readable storage medium, and can also be a volatile computer readable storage medium, and the computer readable storage medium stores instructions, which, when executed on a computer, cause the computer to perform the steps of the coal-based solid waste resourceization whole-process intelligent management and control platform.

[0084] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-mentioned system, system and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0085] The integrated unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical scheme of the present application or the part that essentially contributes to the prior art or the whole or part of the technical scheme can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a coal-based solid waste resourceization whole-process intelligent management and control device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0086] The above examples are only used to illustrate the technical solutions of the present application, but not to limit the present application; although the present application has been described in detail with reference to the foregoing examples, those ordinarily skilled in the art should understand: the technical solutions recorded in the foregoing examples can still be modified, or some technical features can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A coal-based solid waste resource utilization full-process intelligent management and control platform, characterized in that, The platform comprises: An identification module configured to perform mineral phase identification processing on the coal-based solid waste by means of a ray diffractometer to obtain coal-based solid waste mineral composition classification data; A construction module configured to construct a mineral phase transformation digital twin model based on the coal-based solid waste mineral composition classification data, and simulate a silicon-aluminum mineral dissolution reaction process to obtain coal gangue weathering into soil process data; An establishment module configured to establish a pollutant migration prediction model according to the coal gangue weathering into soil process data to obtain site environmental risk data; An optimization module configured to perform multi-objective optimization processing on the site environmental risk data by means of an improved particle swarm-genetic hybrid algorithm to obtain a resource utilization path scheme; An adjustment module configured to perform adaptive adjustment on coal-based solid waste treatment process parameters based on the resource utilization path scheme to obtain coal-based solid waste resource utilization whole-process management and control instructions.

2. The coal-based solid waste resource utilization full-process intelligent management and control platform according to claim 1, characterized in that, The identification module is configured to: perform two-dimensional scanning detection on a coal-based solid waste sample by means of a ray diffractometer to obtain ray diffraction spectrum data in a diffraction angle range of 5° to 80°; perform peak position identification processing on the ray diffraction spectrum data to extract characteristic diffraction peak intensity values of quartz, kaolinite and illite, and obtain mineral phase qualitative identification results; calculate mass percentages of silicon dioxide and aluminum trioxide based on the mineral phase qualitative identification results, and calculate molar ratio values to obtain silicon-aluminum ratio quantitative parameters; perform classification processing on the silicon-aluminum ratio quantitative parameters according to numerical intervals, and classify as low-activity solid waste when the molar ratio value is greater than 4.0, as medium-activity solid waste when the molar ratio value is between 2.0 and 4.0, and as high-activity solid waste when the molar ratio value is less than 2.0, to obtain coal-based solid waste mineral composition classification data. 3.The coal-based solid waste resource utilization full-process intelligent management and control platform according to claim 1, characterized in that, The construction module comprises: a processing unit configured to input the coal-based solid waste mineral composition classification data into a three-dimensional network structure modeling algorithm to perform spatial configuration processing, establish a bonding network model of silicon-oxygen tetrahedra and aluminum-oxygen tetrahedra, and obtain a mineral phase transformation digital twin model; a calculation unit configured to set boundary condition parameters of a reaction temperature of 20°C to 80°C and a pH value of 8.0 to 14.0 based on the mineral phase transformation digital twin model, and calculate activation energy parameters of silicon-aluminum minerals in an alkaline environment to obtain dissolution reaction kinetics parameters; an iteration unit configured to substitute the dissolution reaction kinetics parameters into a silicate dissolution rate equation to perform iterative calculation processing, simulate a release process of silicon ions and aluminum ions at a time step interval of 1 hour, and obtain a mineral dissolution process curve; a coupling unit configured to perform microbial metabolic coupling calculation processing on the mineral dissolution process curve, combine soil pH changes and organic matter accumulation rates, and obtain coal gangue weathering into soil process data.

4. The coal-based solid waste resource utilization full-process intelligent management and control platform according to claim 3, characterized in that, The processing unit is configured to: perform molecular coordinate initialization processing on the coal-based solid waste mineral composition classification data, assign spatial positions of silicon atoms and aluminum atoms according to mineral phase content proportions, and obtain atomic spatial coordinate parameters; establish a tetrahedral geometric structure based on the atomic spatial coordinate parameters, connect each silicon atom with four oxygen atoms to form a silicon-oxygen tetrahedron, and connect each aluminum atom with four oxygen atoms to form an aluminum-oxygen tetrahedron, to obtain a basic tetrahedral unit; The base tetrahedral unit is subjected to network connection processing, silicon-oxygen tetrahedrons and aluminum-oxygen tetrahedrons are bridged and assembled in a manner of sharing oxygen atoms, and a three-dimensional bonded network topology structure is obtained; The three-dimensional bonded network topology structure is mapped into a digital space, a virtual mineral lattice containing atomic coordinates, bonding relationships and physical property parameters is established, and a digital mineral structure model is obtained; The digital mineral structure model is provided with a real-time data synchronization interface and a state updating algorithm, a dynamic correspondence relationship between a physical mineral and a virtual model is established, and a mineral phase conversion digital twin model is obtained. 5.The coal-based solid waste resource utilization full-process intelligent management and control platform according to claim 1, characterized in that, The establishment module is configured to: perform soil layering characteristic analysis processing on the coal gangue weathering into soil process data, extract porosity and permeability coefficient parameters, and obtain site hydrogeological parameters; establish a three-dimensional groundwater flow numerical model based on the site hydrogeological parameters, calculate the water head distribution of each node, and obtain groundwater flow field distribution data; perform contaminant transport calculation processing on the groundwater flow field distribution data using a convection-diffusion equation, and obtain contaminant concentration distribution results; perform risk assessment quantification processing on the contaminant concentration distribution results, calculate the heavy metal exceeding multiple, and obtain site environmental risk data. 6.The coal-based solid waste resource utilization full-process intelligent management and control platform according to claim 1, characterized in that, The optimization module is configured to: perform target function construction processing on the site environmental risk data, and obtain a multi-objective function expression; initialize a particle swarm population based on the multi-objective function expression, assign a position vector and a velocity vector to each particle, wherein the position vector represents a combination of coal-based solid waste treatment process parameters, and obtain an initial particle swarm population; perform fitness evaluation and velocity update iteration processing on the initial particle swarm population, start genetic algorithm crossover mutation operation when the particle fitness stagnates, generate a new candidate solution and update the global optimal position, and obtain optimization iteration results; perform Pareto front screening processing on the optimization iteration results, select the process parameter configuration with the optimal comprehensive performance from the non-dominated solution set, and obtain a resource utilization path scheme.

7. The coal-based solid waste resource utilization full-process intelligent management and control platform according to claim 1, characterized in that, The adjustment module is configured to: perform process parameter analysis processing on the resource utilization path scheme, extract key control parameters such as geopolymer preparation temperature, stirring speed, solid-liquid ratio and activator addition amount, and obtain target process parameter set values; perform real-time process parameter comparison processing based on the target process parameter set values, calculate the deviation between the current detection value and the target set value, and obtain a parameter adjustment deviation amount; perform proportional-integral-derivative control calculation processing on the parameter adjustment deviation amount, generate corresponding device control signals, and obtain process parameter adjustment instructions; perform execution priority sorting and time sequence coordination processing on the process parameter adjustment instructions, send them to each control device in accordance with the coal-based solid waste treatment flow sequence, and obtain coal-based solid waste resource utilization whole-process management and control instructions.

8. A digital twin system, characterized in that, The coal-based solid waste resource utilization whole-process intelligent management and control platform based on any one of claims 1-7 realizes intelligent management and control of the coal-based solid waste resource utilization whole process.

9. A coal-based solid waste resource utilization full-process intelligent management and control device, characterized in that, A computer program product is provided, which includes a memory and a processor, the memory storing a computer program capable of running on the processor, and the processor implementing the coal-based solid waste resource utilization whole-process intelligent management and control platform of any one of claims 1-7 when executing the computer program.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by a processor, causes the processor to perform the coal-based solid waste resource utilization whole-process intelligent management and control platform as claimed in any one of claims 1 to 7.

Images