Classification method and system of physical and chemical properties of coal-based solid waste based on regional ecological characteristics

Abstract

The present application relates to the field of data processing technology, and discloses a method and system for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics. The method includes: collecting coal-based solid waste data, establishing a resource and ecological database; analyzing the correlation between resource characteristics and ecological elements, obtaining correlation parameters and influencing factors; performing classification modeling, forming a classification model and characteristic prediction; evaluating commercial value, generating value scores and market plans; monitoring the entire life cycle, obtaining circulation data and benefit evaluation; analyzing decisions, and formulating resource management plans. The present application realizes the correlation analysis between coal-based solid waste resource characteristics and regional ecological elements, constructs a scientific classification model, and provides a resource management plan for the entire life cycle, thereby improving the utilization efficiency and management level of coal-based solid waste resources.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics. Background Art

[0002] Coal-based solid waste is solid waste generated during coal mining, washing, and utilization, primarily including gangue, fly ash, coal cinder, and coal slime. With the development of the coal industry, the accumulation of coal-based solid waste has increased annually, occupying significant land resources and causing serious impacts on the ecological environment. Existing technologies primarily rely on empirical classification methods for the management and utilization of coal-based solid waste resources, often based on simple categorization based on physical properties (such as particle size and density) and chemical composition (such as calorific value and ash content). While these traditional methods have facilitated the resource utilization of coal-based solid waste to a certain extent, they lack systematic and scientific approaches, fail to consider the impact of regional ecological characteristics on the physical and chemical properties of coal-based solid waste, and fail to establish a correlation between coal-based solid waste characteristics and the ecological environment. Furthermore, existing classification methods are often static and single-dimensional, lacking dynamic monitoring and full lifecycle management, resulting in inefficient resource utilization.

[0003] The shortcomings of existing technologies are mainly manifested in the following aspects: First, they ignore the role of regional ecological factors in shaping the physical and chemical properties of coal-based solid waste, resulting in a disconnect between classification results and actual application needs; second, there is a lack of correlation analysis between coal-based solid waste resource characteristics and regional ecological factors, which cannot reveal the inherent connection between the two; third, existing classification methods are mostly experience-driven, lacking data support and scientific models, and the classification accuracy is low; fourth, the resource value assessment system is imperfect, making it difficult to achieve optimal resource allocation and maximize value; fifth, the lack of a full life cycle monitoring and benefit evaluation mechanism makes it difficult to effectively manage and continuously optimize the resource utilization process. These shortcomings seriously restrict the efficient utilization and management of coal-based solid waste resources. Summary of the Invention

[0004] This application provides a method and system for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics, which is used to realize the correlation analysis between the characteristics of coal-based solid waste resources and regional ecological factors, construct a scientific classification model, and provide a full life cycle resource management plan, thereby improving the utilization efficiency and management level of coal-based solid waste resources.

[0005] In the first aspect, the present application provides a method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics, and the method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics includes: collecting and digitally processing coal-based solid waste resource data to obtain a coal-based solid waste resource database and a regional ecological characteristic database; based on the coal-based solid waste resource database and the regional ecological characteristic database, performing correlation analysis on the characteristics of coal-based solid waste resources and regional ecological factors to obtain a characteristic correlation parameter set and key influencing factors; based on the characteristic correlation parameter set and the key influencing factors, performing multi-dimensional classification modeling on coal-based solid waste resources to obtain a coal-based solid waste resource classification model and resource characteristic prediction results; based on the coal-based solid waste resource classification model and the resource characteristic prediction results, performing multi-dimensional evaluation of the commercial value of coal-based solid waste resources to obtain a resource value score and a market matching plan; performing full life cycle monitoring of the coal-based solid waste resource utilization process in the market matching plan to obtain resource flow data and multi-dimensional benefit evaluation results; inputting the resource value score, the resource flow data and the multi-dimensional benefit evaluation results into a decision engine for comprehensive analysis to obtain a coal-based solid waste resource management decision plan.

[0006] In a second aspect, the present application provides a classification system for the physical and chemical properties of coal-based solid waste based on regional ecological characteristics, the classification system for the physical and chemical properties of coal-based solid waste based on regional ecological characteristics comprising:

[0007] The processing module is used to collect and digitally process coal-based solid waste resource data to obtain a coal-based solid waste resource database and a regional ecological characteristics database;

[0008] An analysis module, configured to perform correlation analysis between coal-based solid waste resource characteristics and regional ecological factors based on the coal-based solid waste resource database and the regional ecological characteristic database, and obtain a characteristic correlation parameter set and key influencing factors;

[0009] A modeling module, configured to perform multi-dimensional classification modeling of coal-based solid waste resources based on the characteristic association parameter set and the key influencing factors, and obtain a coal-based solid waste resource classification model and resource characteristic prediction results;

[0010] An evaluation module, configured to perform a multi-dimensional evaluation of the commercial value of coal-based solid waste resources based on the coal-based solid waste resource classification model and the resource characteristic prediction results, and obtain a resource value score and a market matching solution;

[0011] A monitoring module is used to monitor the entire life cycle of the coal-based solid waste resource utilization process in the market matching scheme, and obtain resource flow data and multi-dimensional benefit evaluation results;

[0012] The input module is used to input the resource value score, the resource flow data and the multi-dimensional benefit evaluation results into the decision engine for comprehensive analysis to obtain a coal-based solid waste resource management decision plan.

[0013] In the third aspect, a coal-based solid waste physical and chemical property classification device based on regional ecological characteristics is provided, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the coal-based solid waste physical and chemical property classification device based on regional ecological characteristics executes the above-mentioned coal-based solid waste physical and chemical property classification method based on regional ecological characteristics.

[0014] In a fourth aspect, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium, which, when executed on a computer, enables the computer to execute the above-mentioned method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics.

[0015] In the technical solution provided in this application, by collecting and digitally processing coal-based solid waste resource data, a coal-based solid waste resource database and a regional ecological characteristic database are constructed, which provides high-quality basic data support for subsequent analysis and solves the problems of irregular data collection and scattered storage in traditional methods; by conducting correlation analysis on the characteristics of coal-based solid waste resources and regional ecological factors, characteristic correlation parameter sets and key influencing factors are obtained, revealing the intrinsic connection between the physical and chemical properties of coal-based solid waste and the regional ecological environment, especially by applying artificial intelligence algorithms such as multivariate statistical analysis methods, principal component analysis and canonical correlation analysis, the correlation analysis results are highly interpretable and scientific, and the characteristics of these algorithms significantly improve the accuracy of correlation pattern recognition and the accuracy of ecological factor impact measurement; multi-dimensional classification modeling is carried out based on characteristic correlation parameter sets and key influencing factors, and classification models are constructed using intelligent algorithms such as hierarchical clustering, support vector machines and random forests. The characteristics of these algorithms enable the classification process to fully consider the nonlinear relationship and high-dimensional features of the data. The system can greatly improve the accuracy and stability of coal-based solid waste resource classification; through multi-dimensional evaluation of the commercial value of coal-based solid waste resources, resource value scores and market matching plans are obtained, and a bridge from resource classification to value realization is built. The multi-objective optimization algorithm characteristics used in it effectively solve the multi-dimensional balance problem in resource value evaluation; the coal-based solid waste resource utilization process is monitored throughout its life cycle, and the Internet of Things technology and data mining algorithms are used to obtain resource flow data and multi-dimensional benefit evaluation results. The characteristics of these algorithms perform well in processing time series data and benefit evaluation, and provide real-time feedback on resource utilization effects; finally, the resource value scores, resource flow data and multi-dimensional benefit evaluation results are input into the decision engine for comprehensive analysis to obtain a coal-based solid waste resource management decision plan. The algorithm characteristics such as Monte Carlo simulation and hierarchical analysis method enable the decision-making process to have the ability to deal with uncertainty and multi-objective trade-offs, realize full-chain intelligent management from data to decision-making, and comprehensively improve the scientificity, accuracy and efficiency of coal-based solid waste resource management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 This is a schematic diagram of an embodiment of a method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics in an embodiment of the present application;

[0018] Figure 2This is a schematic diagram of an embodiment of a classification system for the physical and chemical properties of coal-based solid waste based on regional ecological characteristics in an embodiment of the present application;

[0019] Figure 3 It is a schematic block diagram of the structure of the coal-based solid waste physical and chemical property classification equipment based on regional ecological characteristics in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The embodiments of the present application provide a method and system for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics. The terms first, second, third, fourth, etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate 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 inclusions, for example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or apparatus.

[0021] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In the embodiments of the present application, an embodiment of the method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics includes:

[0022] Step S101: Collect and digitally process coal-based solid waste resource data to obtain a coal-based solid waste resource database and a regional ecological characteristics database;

[0023] Step S102: Based on the coal-based solid waste resource database and the regional ecological characteristic database, correlation analysis is performed on the coal-based solid waste resource characteristics and regional ecological factors to obtain a characteristic correlation parameter set and key influencing factors;

[0024] Step S103: Based on the characteristic association parameter set and key influencing factors, a multi-dimensional classification model is performed on the coal-based solid waste resources to obtain a coal-based solid waste resource classification model and resource characteristic prediction results;

[0025] Step S104: Based on the coal-based solid waste resource classification model and resource characteristic prediction results, a multi-dimensional assessment of the commercial value of the coal-based solid waste resources is performed to obtain a resource value score and a market matching solution;

[0026] Step S105: Conduct full life cycle monitoring of the coal-based solid waste resource utilization process in the market matching solution to obtain resource flow data and multi-dimensional benefit evaluation results;

[0027] Step S106: Input the resource value score, resource flow data and multi-dimensional benefit evaluation results into the decision engine for comprehensive analysis to obtain a coal-based solid waste resource management decision plan.

[0028] It is understandable that the execution subject of this application can be a coal-based solid waste physical and chemical property classification system based on regional ecological characteristics, or a terminal or server, which is not limited here. The embodiment of this application is described by taking the server as the execution subject as an example.

[0029] Specifically, coal-based solid waste resource data is collected and digitized to generate a coal-based solid waste resource database and a regional ecological characteristics database. The data collected in this step primarily includes two categories: the coal-based solid waste resource entity data and the ecological and environmental parameter data of the sampling area. For the coal-based solid waste entity data, the on-site collection end uses a mobile terminal equipped with GPS positioning, QR code encoding, and camera capabilities to record the spatial location information and basic sampling characteristics of the sample, such as sampling depth and on-site humidity. A unique identification code is also generated for each sample, which is used to link fields in subsequent data tables. After the samples enter the laboratory, physical and chemical properties are tested according to standard procedures. Physical properties, such as bulk density, particle size composition, and moisture content, are obtained using standard instruments and procedures such as a particle size analyzer and drying method and converted into structured data fields. Chemical properties, such as sulfur, iron, calcium, magnesium, heavy metal content, and organic matter content, are measured using X-ray fluorescence analysis (XRF) or inductively coupled plasma mass spectrometry (ICP-MS). The resulting data is stored in the database as elemental mass percentages. At the same time, regional ecological characteristic data are obtained through the integration of multi-source data such as remote sensing images, geographic information system (GIS) platforms, and national ecological databases. These data include factors such as climate (average annual precipitation, sunshine duration, average annual temperature, etc.), soil (pH, organic matter content, texture category, etc.), hydrology (watershed type, water body density, etc.) and vegetation (NDVI index, vegetation coverage, etc.). Through spatial overlay technology, these regional data are mapped to sampling points in raster or vector form, thereby establishing a coal-based solid waste resource database and a regional ecological characteristic database with a unique identification code as the connecting field.

[0030] Correlation analysis was conducted between the two databases to extract characteristic correlation parameter sets and key influencing factors. During the data preprocessing phase, the physical and chemical data and ecological data were standardized separately. Using the Min-Max normalization method, physical parameters with different units and dimensions (e.g., particle size range 0.01-5 mm, moisture content 0%-100%) were uniformly converted to comparable values ​​between 0 and 1. Ecological factor parameters were processed in the same manner. A two-dimensional data matrix was then constructed, in which the standardized attribute parameters of coal-based solid waste samples with different behaviors were listed. The Pearson correlation coefficient was used to calculate the linear correlation between the physical and chemical properties of each coal-based solid waste and the ecological parameters of each region. A threshold condition (|r|>0.5, significance p<0.05) was set to select significantly correlated variable pairs. Principal component analysis (PCA) was then applied to the physical and chemical property data. Principal component factors (PCFs) with a cumulative variance contribution of 85% were extracted from the eigenvector matrix. PCFs are comprehensive indicators formed by linear combinations of several highly correlated original variables to reduce redundant features. Canonical correlation analysis (CCA) was further introduced to map the principal component factors to the set of ecological features using canonical variables to identify the maximum correlation structure between the two sets of variables. Finally, feature importance was assessed by introducing the significant parameter pairs and canonical variable pairs obtained above into a random forest model. The random forest model consists of multiple decision trees, each trained with different samples and feature subsets. Information gain was used to assess the average influence of features in the classification task, resulting in the final set of feature-association parameters and key influencing factors.

[0031] A multidimensional classification model for coal-based solid waste resources was constructed using the aforementioned feature set as input variables. The original dataset was first partitioned into training and test sets in a 7:3 ratio. The partitioning process ensured a balanced distribution of samples across different classes to prevent training bias. A hierarchical clustering algorithm was applied to the training set, calculating the silhouette coefficient and Davies-Bouldin index for different numbers of clusters (e.g., 2 to 10). A silhouette coefficient closer to 1 indicates a more reasonable clustering, while a lower Davies-Bouldin index indicates better inter-class separation. The number of clusters was determined by analyzing the inflection points of these two indicators. After determining the number of classes, three algorithms—K-means, support vector machine (SVM), and random forest—were used to build classification models. K-means assigned samples to the cluster closest to the centroid based on the minimum squared error, SVM identified the boundary by finding the hyperplane with the largest margin, and random forest performed classification predictions using an ensemble of decision trees. Each model was trained and evaluated using 10-fold cross-validation, and the model with the highest average F1 score was selected as the final classifier. Finally, based on the mean and standard deviation of samples within each category, a typical characteristic profile is extracted. A resource property prediction model is constructed to predict the category and physical and chemical properties of unknown samples. The predicted results are then evaluated and matched to the market. An indicator system is constructed across three dimensions: economic, environmental, and social. Economic dimensions include alternative material costs and transportation costs; environmental dimensions include pollution factor content and resource utilization efficiency; and social dimensions include job creation estimates and regional resource dependence. The predicted resource category and property data are input into the value assessment model, and a multi-dimensional score is calculated using a linear weighting method. Application scenario analysis is then conducted. For example, solid waste with low calorific value and high calcium content is suitable for building materials, while waste with high moisture content and low pollution factors is suitable for ecological landfill. Based on the application characteristics of each resource category, an application potential matrix is ​​constructed. This is then combined with regional user data (demand volume, resource quality requirements, and transportation radius) for matching calculations. Ultimately, a resource-user matching score and priority supply recommendations are generated.

[0032] By generating an electronic ID for each resource, linking its unique identification code with test data, IoT devices are used to collect real-time status data (such as GPS location, weighing data, temperature and humidity) throughout the resource's generation, transportation, processing, and use stages. This data is combined with environmental sensors deployed in the use area (e.g., PM2.5, water pH, and soil heavy metal content) to collect environmental response data, establishing a comprehensive database of resource flow trajectories and impacts. Subsequently, a multi-dimensional benefit evaluation system is constructed, setting benchmark expectations (e.g., a cost savings of 10 yuan per unit resource and a pollutant reduction of 20%). The difference in these indicators is compared with the actual collected data, and the degree of benefit achievement and deviation is calculated. Finally, historical project data is archived and analyzed to extract patterns that are used to build a knowledge base and predictive mechanism. The aforementioned scoring results (resource value score, flow trajectory data, and multi-dimensional benefit evaluation results) are input into a decision tree model to form a structured decision path. Classification branches are constructed under different conditions, and simulation experiments are conducted to generate a possible path diagram for each branch. A multi-objective optimization strategy is then used to rank and evaluate economic, environmental, and social values. Finally, the analytic hierarchy process (AHP) is introduced to assign different weight combinations for scoring and output the optimal classification and resource allocation path.

[0033] In the embodiments of the present application, a coal-based solid waste resource database and a regional ecological characteristic database are constructed by collecting and digitally processing coal-based solid waste resource data, providing high-quality basic data support for subsequent analysis and solving the problems of irregular data collection and scattered storage in traditional methods; by performing correlation analysis on the characteristics of coal-based solid waste resources and regional ecological factors, characteristic correlation parameter sets and key influencing factors are obtained, revealing the intrinsic connection between the physical and chemical properties of coal-based solid waste and the regional ecological environment, especially by applying artificial intelligence algorithms such as multivariate statistical analysis methods, principal component analysis and canonical correlation analysis, so that the correlation analysis results are highly interpretable and scientific, and the characteristics of these algorithms significantly improve the accuracy of correlation pattern recognition and the accuracy of ecological factor impact measurement; multidimensional classification modeling is performed based on characteristic correlation parameter sets and key influencing factors, and classification models are constructed using intelligent algorithms such as hierarchical clustering, support vector machines and random forests. The characteristics of these algorithms enable the classification process to fully consider the nonlinear relationship and high-dimensional characteristics of the data. , which greatly improved the accuracy and stability of coal-based solid waste resource classification; through multi-dimensional evaluation of the commercial value of coal-based solid waste resources, resource value scores and market matching plans were obtained, and a bridge from resource classification to value realization was built. The multi-objective optimization algorithm characteristics used effectively solved the multi-dimensional balance problem in resource value evaluation; the coal-based solid waste resource utilization process was monitored throughout its life cycle, and the Internet of Things technology and data mining algorithms were used to obtain resource flow data and multi-dimensional benefit evaluation results. The characteristics of these algorithms performed well in processing time series data and benefit evaluation, and provided real-time feedback on resource utilization effects; finally, the resource value scores, resource flow data and multi-dimensional benefit evaluation results were input into the decision engine for comprehensive analysis to obtain a coal-based solid waste resource management decision plan. The algorithm characteristics such as Monte Carlo simulation and hierarchical analysis method enable the decision-making process to have the ability to deal with uncertainty and multi-objective trade-offs, realize full-chain intelligent management from data to decision-making, and comprehensively improve the scientificity, accuracy and efficiency of coal-based solid waste resource management.

[0034] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0035] Collect coal-based solid waste samples on site to obtain original coal-based solid waste samples and sampling point location data;

[0036] Encode and preprocess the original coal-based solid waste samples to obtain standardized coal-based solid waste samples and sample unique identification codes;

[0037] Physical property testing of standardized coal-based solid waste samples was performed to obtain physical property parameters of coal-based solid waste including particle composition, bulk density and porosity;

[0038] Conduct chemical composition analysis on standardized coal-based solid waste samples to obtain chemical characteristic parameters of coal-based solid waste including elemental composition, organic matter content and heavy metal content;

[0039] Based on the sampling point location data, ecological element data is collected in the corresponding area to obtain the original data of regional ecological characteristics including climate data, terrain data and vegetation cover data;

[0040] The sample unique identification code, coal-based solid waste physical property parameters, coal-based solid waste chemical property parameters and regional ecological characteristics original data are standardized, integrated and stored to obtain a coal-based solid waste resource database and a regional ecological characteristics database.

[0041] Specifically, during on-site collection of coal-based solid waste, systematic sampling is carried out at locations such as coal mine goafs, waste rock dumps, or coal chemical tailings discharge areas using handheld terminal devices with positioning and sampling recording functions. Each sampling operation records the latitude and longitude information, altitude, on-site photos, sampling depth, and basic description of the sampling point. This information is then bound to a collection record sheet. The sample numbering rule is area code + sampling batch + serial number to form a unique identification code. For example, the sample number is B0401-23-07, where B0401 is the area code, 23 is the sampling year, and 07 is the serial number of the day.

[0042] The collected raw samples then undergo pretreatment, which includes impurity removal, homogenous mixing, drying to constant weight (at 105°C for 24 hours), and particle size screening. After pretreatment, a unique sample number is entered into the sample registration system and the processing status is set to Standardized. This status indicates that the sample has met uniform conditions for analysis, eliminating detection bias caused by moisture fluctuations and impurity interference.

[0043] After pretreatment, samples are sent for physical property testing and chemical property analysis. Physical property testing includes particle composition analysis, bulk density measurement, and porosity calculation. Particle composition is determined using a laser particle size analyzer, which outputs particle size percentiles such as D10, D50, and D90. Bulk density is calculated by weighing samples filled in standard test molds. Porosity is calculated using mercury intrusion porosimetry as a percentage of total pore volume. Physical test data is recorded in the Laboratory Information Management System (LIMS) and automatically linked to the sample number to generate a parameter data sheet, such as D50 particle size = 0.35mm, bulk density = 1.47g / cm³, and porosity = 28.5%.

[0044] Chemical composition analysis includes determination of elemental composition, organic matter content, and heavy metal content. Elemental composition is determined using XRF (X-ray fluorescence spectroscopy) to detect major inorganic elements such as Si, Al, Fe, and Ca. Organic matter content is measured by potassium dichromate-sulfuric acid oxidation titration and expressed as a percentage of total organic carbon (TOC). Heavy metal content, including Zn, Pb, Cr, and Cd, is analyzed using ICP-MS (inductively coupled plasma mass spectrometry) and is expressed in mg / kg. Each parameter result in this phase is associated with its test method number, instrument number, and tester to ensure data traceability and structure.

[0045] After obtaining the physical and chemical parameters of the samples, we further collected regional ecological characteristic data based on the location coordinates of the sampling points. This ecological factor information was primarily acquired through a spatial information management platform and remote sensing data interface. Climate data, including average annual precipitation, average annual temperature, and relative humidity, was imported from a meteorological satellite database and extracted as raster values ​​based on the geocoding of the sampling points. Topographic data was extracted from a DEM (digital elevation model) for slope, aspect, and elevation. Vegetation data was obtained from remotely sensed NDVI values, which served as a quantitative indicator of vegetation coverage. All ecological factors were aligned with the sample coordinates through spatial interpolation or raster resampling. For example, the area corresponding to a sampling point had an average annual rainfall of 980 mm, an NDVI of 0.65, and a slope of 12.7°. These data were uniformly coded and integrated along with the sample number B0401-23-07.

[0046] The unique sample number, along with physical, chemical, and ecological parameter sets, is stored in two main database tables using a standard structure: the Coal-Based Solid Waste Resource Database and the Regional Ecological Characteristics Database. In the Coal-Based Solid Waste Resource Database, each row corresponds to a sample number and contains attribute fields such as D10, D50, bulk density, porosity, SiO2%, Fe2O3%, organic matter%, and Zn content, totaling no fewer than 30 fields. In the Regional Ecological Characteristics Database, the sample number serves as the foreign key field, and the record fields include no fewer than 15 ecological information fields, including average annual rainfall, NDVI, slope, and soil pH. The sample number serves as the connecting key between data tables, creating a unified primary key structure. During data import, all fields undergo type verification (e.g., physical parameters require numeric floating-point format, and unit consistency is checked) through the data standardization module. Missing values ​​are filled using mean interpolation. Outliers are screened using box plots and marked in an outlier flag table for manual review.

[0047] For example, a coal-based solid waste sample numbered C0311-24-09 had a median particle size (D50) of 0.42 mm, a bulk density of 1.55 g / cm³, and a Zn content of 305 mg / kg. The sampling site was located at an altitude of 430 meters, with an average annual temperature of 11.2°C and an NDVI of 0.58. After acquiring these data using a laser particle size analyzer, ICP-MS, and a GIS spatial positioning system, a data cleaning program removed outliers in the bulk density (marking those outside the IQR range) and replaced them with the median bulk density of other samples in the area, 1.51 g / cm³. After integration, the sample record was written to a database and linked to regional ecological characteristic data. In subsequent analyses, it served as standardized input data with comprehensive physical, chemical, and ecological attributes for the next stage of feature analysis and modeling and classification. This process embodies the entire process from field sampling to the establishment of a standardized data structure, ensuring logical consistency between physical, chemical, and ecological factors and operability in computational processing.

[0048] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0049] Standardize the physical and chemical property parameters of coal-based solid waste in the coal-based solid waste resource database to obtain a standardized coal-based solid waste property data set;

[0050] Standardize the ecological factor parameters in the regional ecological characteristics database to obtain a standardized regional ecological characteristics dataset;

[0051] Based on the standardized coal-based solid waste characteristic data set and the standardized regional ecological characteristic data set, the correlation coefficient matrix between the physical and chemical properties of coal-based solid waste and regional ecological factors was calculated, and significant correlation parameter pairs were obtained;

[0052] The principal component analysis method was applied to the standardized coal-based solid waste characteristic data set to reduce the dimensionality, and the principal component factors of coal-based solid waste characteristics with a cumulative variance contribution rate of not less than 85% were obtained;

[0053] Based on the principal component factors of coal-based solid waste characteristics and the standardized regional ecological characteristics dataset, a canonical correlation analysis was conducted to obtain the typical correlation pattern between coal-based solid waste characteristics and regional ecological factors;

[0054] According to the typical correlation patterns and significantly correlated parameter pairs, the random forest algorithm is used to calculate the feature importance index to obtain the feature association parameter set and key influencing factors.

[0055] Specifically, sample data from the coal-based solid waste resource database was grouped for training and validation of supervised and unsupervised learning. The sample dataset was randomly divided into training and test datasets in a 7:3 ratio to ensure sufficient data for model construction and generalization. This partitioning ensured that the samples were representative in terms of spatial location and type distribution. A stratified sampling strategy was used for the partitioning, with stratification based on regional ecological characteristics or preliminary classification labels followed by random partitioning to prevent a single type of sample from being overrepresented in the training or test dataset, potentially leading to model bias. After obtaining the training dataset, a hierarchical clustering algorithm was used to perform exploratory grouping analysis of the samples. Hierarchical clustering is a bottom-up clustering method based on a distance metric between samples. By calculating the Euclidean or Mahalanobis distance between samples to form a distance matrix, the closest sample groups are merged, ultimately forming a tree-like cluster structure. The cluster structure was visualized by plotting a dendrogram, and the silhouette coefficient and Davies-Bouldin index were calculated for each number of clusters. The silhouette coefficient represents the difference between the closeness of a sample to its center and the separation of its centers from its center. Its value ranges from -1 to 1, with closer values ​​to 1 indicating more reasonable clustering. The Davies-Bouldin index reflects the ratio of inter-cluster distance to intra-cluster closeness, with smaller values ​​indicating better clustering. The optimal number of clusters is determined by analyzing the inflection points of these two indices. For example, when the number of clusters is 4, the silhouette coefficient reaches a maximum of 0.71 and the Davies-Bouldin index reaches a minimum of 0.37, resulting in a final number of 4 clusters. Using the feature association parameter set and key influencing factors as model input variables, a K-means clustering model, a support vector machine (SVM) model, and a random forest classification model were constructed, respectively. The K-means model sets the class center and iteratively adjusts sample assignment to minimize the squared distance from the sample to the class center. The SVM model constructs an optimal hyperplane to demarcate class boundaries in a high-dimensional space, maximizing the separation between samples of different classes. The random forest model consists of several decision trees, each constructed from a random subset of the training set, and uses a majority voting mechanism to determine the sample class. Each model was trained on the training set, and its performance was evaluated on the test set using a 10-fold cross-validation method. Evaluation metrics included accuracy, recall, precision, and F1-score. The F1-score, a balanced metric that comprehensively considers both accuracy and recall, is commonly used for imbalanced datasets. The average F1 score of each model was compared, and the model with the highest score was selected as the final classification model. For example, in this example, the random forest model achieved an average F1 score of 0.91 in the 10-fold cross-validation, significantly higher than the K-means model (0.83) and the SVM (0.87). Therefore, the random forest model was selected as the optimal classification model.

[0056] After classification, the characteristic parameters of each sample category were statistically analyzed to extract a descriptive profile. Statistical indicators included the mean, median, standard deviation, and interquartile range of each parameter within each category. For example, for a resource category, the average Zn content was 280 mg / kg, the median particle size D50 was 0.38 mm, the bulk density was 1.52 g / cm³, the average NDVI was 0.61, and the average slope was 12.1°. These statistical features enabled the construction of a typical physicochemical and ecological profile for each category, providing a reference for subsequent classification of new samples. The category profile was stored in a structured table, with key parameter ranges independently recorded for each category. Based on this category profile and previously identified key influencing factors, a resource property prediction model was developed. This model uses the sample's ecological parameters and selected physicochemical parameters as input to predict selected physicochemical properties of untested samples (such as missing heavy metal content or porosity). For example, Zn content in a certain category is negatively correlated with NDVI, with each 0.1 unit decrease in NDVI associated with an average increase of 27 mg / kg in Zn content. This allows for the construction of multivariate regression or random forest-based regression models for property prediction. Property prediction models are used to supplement physical and chemical parameters when sample testing is incomplete or during the rapid estimation phase. Their output complements the output of the classification model, providing a complete description of sample attributes.

[0057] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0058] The sample data in the coal-based solid waste resource database is randomly divided into a training data set and a test data set in a ratio of 7:3 to obtain the coal-based solid waste resource training set and test set;

[0059] A hierarchical clustering algorithm was applied to the coal-based solid waste resource training set. The optimal clustering value was determined by calculating the silhouette coefficient and Davies-Bouldin index, and the number of classifications of coal-based solid waste resources was obtained.

[0060] Based on the feature association parameter set and key influencing factors, a classification model including K-means clustering, support vector machine and random forest was constructed. The optimal performance model was selected through cross-validation to obtain the optimal classification model for coal-based solid waste resources.

[0061] Conduct statistical analysis on the characteristic parameters of each category of resources, calculate the characteristic distribution characteristics of each category, and obtain the characteristic description files of each category of resources;

[0062] Based on the characteristic description archives and key influencing factors, a resource characteristic prediction model was constructed, and the characteristics of coal-based solid waste samples were predicted to obtain the resource characteristic prediction results.

[0063] Specifically, the coal-based solid waste resource sample data is partitioned to provide a dataset for model training and evaluation. This process randomly divides the sample dataset into training and test datasets in a 7:3 ratio. To ensure consistent class distribution between the training and test sets, stratified sampling is typically employed. This ensures that each class of coal-based solid waste sample is represented in equal proportions in both the training and test sets, thus avoiding model bias due to sample imbalance. For example, if a particular class of coal-based solid waste resource accounts for 40% of the total data, the proportion of samples of that class should be maintained in both the training and test sets. This ensures the representativeness of the training set and reduces data imbalance issues that may arise from random partitioning. After obtaining the training dataset, the next step is to apply a hierarchical clustering algorithm to the training set. Clustering performance evaluation metrics are then used to determine the optimal number of clusters. Hierarchical clustering is an algorithm that groups samples based on similarity or distance between them, ultimately forming a hierarchical tree structure (cluster tree). The key to this process is to calculate the distance metric between samples (usually Euclidean distance), and then merge samples or subsets based on the closeness of the distance. By constructing a cluster tree, we can evaluate different numbers of clusters and select the optimal number of clusters using the silhouette coefficient and Davies-Bouldin index.

[0064] The Silhouette Score measures each sample's closeness to other samples of the same class and its separation from samples of other classes. The value of this coefficient ranges from -1 to 1, with values ​​closer to 1 indicating better classification. To calculate the Silhouette Score, for each sample, the average distance between it and samples of the same class is first calculated, followed by the average distance between it and the sample of the closest class. The Silhouette Score is the ratio of the difference between these two values ​​to the maximum. The Davies-Bouldin Index measures the closeness of samples within a class and the separation between samples between classes; smaller values ​​indicate better clustering.

[0065] By calculating the Silhouette Coefficient and Davies-Bouldin Index for different numbers of clusters, the optimal number of clusters can be determined. For example, in one experiment, the hierarchical clustering algorithm achieved Silhouette Coefficients of 0.67, 0.75, and 0.70 for 3, 4, and 5 clusters, respectively, while Davies-Bouldin Indexes were 0.83, 0.72, and 0.78. Since the Silhouette Coefficient was maximized and the Davies-Bouldin Index was minimized when the number of clusters was 4, 4 was chosen as the final number of clusters. After determining the number of clusters, classification models were constructed using machine learning algorithms such as K-means clustering, support vector machines (SVMs), and random forests based on the feature association parameter set and key influencing factors of the training set. The K-means clustering algorithm clusters samples based on the distance between samples and class centroids. In each iteration, samples are assigned to the corresponding class centroids based on the class centroids with the smallest distance, and the class centroids are recalculated for each class. A support vector machine (SVM) is a binary classification model that performs classification by constructing a hyperplane that maximizes the margin between classes. For multi-class problems, SVMs are often extended using a one-on-one or one-on-many strategy. A random forest is a decision tree-based ensemble learning algorithm that generates multiple decision trees and ultimately generates a class prediction using a majority voting mechanism. Each decision tree is constructed based on random sampling of data and random selection of features, thereby increasing model robustness.

[0066] During model training, cross-validation is used to evaluate the model. Cross-validation involves partitioning the dataset into multiple subsets. Each subset is used as the test set, while the remaining subsets are used as the training set. Model performance metrics are calculated and averaged to assess model stability and accuracy. Evaluation metrics include accuracy, precision, recall, and F1 score. K-means, SVM, and random forest models are cross-validated on the training set to compare their performance. The model with the best performance is selected as the final classifier.

[0067] After training the optimal classification model, the next task is to statistically analyze the characteristics of each resource category, calculate the characteristic distribution characteristics of each category, and generate a characteristic profile. The characteristic profile contains statistics for each characteristic parameter within each category, such as mean, standard deviation, maximum, and minimum values. These statistics enable us to understand the characteristic distribution of different types of coal-based solid waste, providing a reference for subsequent prediction of new samples. For example, the Zn content of a certain type of coal-based solid waste may be concentrated between 250-300 mg / kg, the bulk density is 1.55 g / cm³, the NDVI is 0.65, and the porosity is 30%. These statistics provide an important benchmark for the classification and characteristic prediction of new samples.

[0068] Based on the characteristic description archive and key influencing factors, a resource property prediction model is constructed. This model is primarily used to predict the properties of untested samples, such as the heavy metal content and particle size distribution of coal-based solid waste. By inputting standardized features into the prediction model, the model can output predicted values ​​for the properties of the coal-based solid waste sample. This process is typically performed using a regression model (such as a random forest-based regression). For example, if a new sample has an NDVI of 0.62, a particle size D50 of 0.35 mm, and a bulk density of 1.50 g / cm³, when input into the prediction model, the model may predict a Zn content of 290 mg / kg with an error range of ±5 mg / kg. The prediction results can provide guidance for resource management and utilization.

[0069] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0070] Construct a multi-dimensional value assessment framework for coal-based solid waste resources that includes economic value, environmental value, and social value dimensions, conduct hierarchical quantification of resource characteristic prediction results, and obtain a coal-based solid waste resource value assessment indicator system;

[0071] Based on the coal-based solid waste resource classification model, the application scenarios of various types of coal-based solid waste resources were analyzed to obtain the application potential matrix of coal-based solid waste resources;

[0072] Calculate the economic benefits of each application scenario in the coal-based solid waste resource application potential matrix to obtain the return on investment and payback period data under different utilization methods;

[0073] Based on the return on investment and payback period data, the economic feasibility of each application scenario is ranked, and the top three application scenarios are selected to obtain the resource utilization path for priority development;

[0074] Build a regional market demand database, match and analyze the demand parameters of potential users in the region with the priority resource utilization paths, and obtain a resource-user matching score;

[0075] Based on the resource-user matching score and the coal-based solid waste resource value assessment index system, a comprehensive resource value score and the optimal market matching plan are generated.

[0076] Specifically, a multi-dimensional value assessment framework for coal-based solid waste resources is constructed, encompassing economic value, environmental value, and social value dimensions. In the economic dimension, factors such as the direct utilization value, processing value-added potential, and substitution costs of coal-based solid waste are mainly considered; in the environmental dimension, attention is paid to the environmental risks, eco-friendliness, and carbon emission reduction potential of coal-based solid waste; and the social value dimension focuses on social benefits such as the employment contribution and regional economic development potential of coal-based solid waste. Based on the assessment indicators of different dimensions, a multi-level weighting system is used to conduct a comprehensive assessment of each dimension. For example, the assessment of economic value can include the application value of coal-based solid waste in building materials, soil remediation, energy recovery, and other fields, while the environmental value assessment involves the positive impact of resource recycling on the environment, such as reducing pollution, saving energy, and reducing emissions.

[0077] Based on the predicted results of the characteristics of coal-based solid waste, a hierarchical quantitative method is used to quantify the characteristics of each coal-based solid waste sample and construct an index system for evaluating the value of coal-based solid waste resources. For example, the physical and chemical properties of a coal-based solid waste sample, such as heavy metal content, particle size, moisture content, and its impact on the ecological environment, can be converted into specific values ​​through a scoring system. The economic dimension may calculate the potential market value of the sample based on its comprehensive characteristics, the environmental dimension calculates its potential to reduce environmental pollution or carbon emissions, and the social value dimension scores based on the social benefits of the resource in actual application.

[0078] Based on the coal-based solid waste resource classification model, an application scenario analysis was conducted for various types of coal-based solid waste resources, resulting in a coal-based solid waste resource application potential matrix. Application scenario analysis involves conducting a feasibility analysis of different resource applications based on the physical and chemical properties, ecological and environmental requirements, and market demand of coal-based solid waste. For example, a type of coal-based solid waste rich in organic matter and low in heavy metals may be suitable for soil improvement and organic fertilizer production; while a type of coal-based solid waste with a small particle size and high calorific value may be suitable for energy recovery or building materials production. Based on the characteristics of each application scenario, an application potential matrix was constructed, classifying different types of coal-based solid waste according to their suitability in each application scenario and assessing their potential market demand. Based on the coal-based solid waste resource application potential matrix, economic benefits were calculated for each application scenario, generating the rate of return (IRR) and payback period (payback period) for different utilization options. For example, if a type of coal-based solid waste is used to produce building materials, the initial investment includes equipment procurement, transportation, and processing costs, while the subsequent return is the revenue generated from the sale of building materials. By calculating these economic parameters, the financial feasibility of the application scenario can be predicted and support can be provided for decision making.

[0079] After obtaining economic benefit calculation data for different application scenarios, the economic feasibility of each application scenario is ranked based on return on investment and payback period, and the top three application scenarios are selected as priority resource utilization paths for development. The goal of this stage is to identify the application scenarios with the highest economic returns and the shortest payback periods, thereby providing direction for the efficient utilization of coal-based solid waste resources. For example, after comparing several application scenarios, assuming that the return on investment for a certain coal-based solid waste in the energy recovery field is 15% and the payback period is 4 years, while the return on investment in the soil remediation field is 10% and the payback period is 6 years, the energy recovery application scenario will obviously be prioritized.

[0080] Next, by constructing a regional market demand database, we match the demand parameters of potential users within the region with the prioritized resource utilization pathways, generating a resource-user match score. This database includes parameters such as user demand, resource quality requirements, and procurement capacity across different regions. For example, a building materials company in a given region may have high requirements for coal-based solid waste particle size and moisture content, while an agricultural company may be more concerned with its organic matter content. Based on this, a matching algorithm is used to align prioritized development pathways with market demand, yielding a match score for each resource application scenario and market demand.

[0081] Combining the resource-user matching score with the previously established coal-based solid waste resource value assessment index system, a comprehensive resource value score and optimal market matching solution are generated. This comprehensive scoring process takes into account the economic, environmental, and social value of coal-based solid waste resources, as well as their market suitability and potential. Through this multi-dimensional comprehensive assessment, a coal-based solid waste resource utilization solution that best meets regional market needs and has high economic and social value can be identified, further promoting the efficient utilization and sustainable development of coal-based solid waste.

[0082] For example, for a certain coal-based solid waste sample, assuming that its application potential in the field of building materials production is 0.85 (according to the application potential matrix), its economic benefit calculation shows that the return on investment is 16%, the payback period is 3.5 years, and the application scenario is highly matched with market demand. The final comprehensive resource value score is 90 and the resource-user matching score is 85, indicating that it has high commercial value and market prospects in this field. Therefore, it can be given priority as the main application scenario in this area.

[0083] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0084] Apply electronic tag technology to identify and manage coal-based solid waste resources in the market matching plan, record the unique identification code and basic characteristic parameters of the resources, and obtain an electronic ID card for the coal-based solid waste resources;

[0085] Based on the electronic ID card of coal-based solid waste resources and IoT sensing equipment, data is collected on the entire process of resource generation, collection, transportation, processing and final application to obtain the flow trajectory data of coal-based solid waste resources;

[0086] Deploy environmental monitoring sensor networks in coal-based solid waste resource application areas to monitor air quality, water quality, and soil conditions in real time, and obtain dynamic data on environmental impacts;

[0087] Based on the data on the circulation trajectory of coal-based solid waste resources and the dynamic data on environmental impact, a multi-dimensional benefit evaluation system with economic benefit indicators, environmental benefit indicators and social benefit indicators was constructed to obtain the quantitative standard for the utilization benefit of coal-based solid waste resources;

[0088] Compare and analyze the quantitative standards for the utilization of coal-based solid waste resources with the preset targets, calculate the achievement rate and deviation value of each benefit indicator, and obtain the benefit realization score and gap analysis results;

[0089] Based on the benefit realization score and gap analysis results, machine learning algorithms are applied to conduct pattern mining and regularity summary on historical project data to obtain resource flow data and multi-dimensional benefit evaluation results.

[0090] Specifically, electronic tagging technology is used to identify and manage coal-based solid waste resources. Each batch of coal-based solid waste resources is assigned a unique identification code, which is used throughout the data collection, processing, and storage process to ensure the traceability and independence of each sample. Using electronic tags (such as RFID tags), the basic characteristic parameters of each coal-based solid waste sample, such as sampling location, sampling time, and physicochemical properties (such as particle composition, heavy metal content, and bulk density), are recorded to generate a "coal-based solid waste resource electronic ID card." This process provides data support for subsequent flow tracking, monitoring, and management.

[0091] Using electronic identification cards for coal-based solid waste resources and IoT-enabled sensor devices, data is collected throughout the entire process of coal-based solid waste generation, from collection, transportation, processing, to final application, generating data on the waste's flow trajectory. For example, during the collection phase, sensors with GPS positioning capabilities record the waste's geographic location. During transportation, IoT technology collects real-time information such as the temperature, humidity, and load capacity of transport vehicles to ensure real-time monitoring of the quality and quantity of the waste. During processing, sensors record data such as the temperature and processing time of the waste. This information is ultimately uploaded to a central database, forming a digital record of the waste's flow, ensuring data transparency and traceability at every stage. In areas where coal-based solid waste resources are used, an environmental monitoring sensor network is deployed to monitor the impact of coal-based solid waste utilization on the surrounding environment in real time. This monitoring network includes air quality sensors, water quality sensors, and soil condition sensors. Air quality sensors monitor the concentrations of pollutants such as PM2.5 and CO2 in real time; water quality sensors monitor parameters such as heavy metal ions, dissolved oxygen, and pH; and soil sensors measure indicators such as heavy metal content, pH, and soil moisture. These environmental monitoring data provide real-time data support for ecological impact assessments of coal-based solid waste resources and lay the foundation for subsequent environmental risk warnings.

[0092] After collecting data on the flow trajectory and environmental impact of coal-based solid waste resources, a multidimensional benefit evaluation system was constructed, comprising economic, environmental, and social benefit indicators. Economic benefit indicators primarily include cost savings, return on investment, and improved production efficiency from coal-based solid waste resources; environmental benefit indicators cover the degree of environmental improvement after resource recovery, such as reduced pollutants and carbon emissions; and social benefit indicators include job creation, local economic development, and health impacts. By quantifying these indicators, a benefit evaluation standard for coal-based solid waste resource utilization was established, providing a scientific basis for resource management decisions. The quantified benefit standards for coal-based solid waste resource utilization were compared and analyzed against pre-set targets. These targets could include environmental standards, economic return rates, and social benefit targets for coal-based solid waste resource utilization. For each type of coal-based solid waste resource, the system calculates the achievement rate and deviation value for each benefit indicator through benefit realization scoring and gap analysis. For example, if the expected carbon emission reduction target for a particular type of coal-based solid waste is 50 tons, but the actual emission reduction is 48 tons, a gap of -2 tons, the benefit realization score will be affected. This analysis result helps managers understand the efficiency deviations in the resource utilization process and adjust resource management strategies in a timely manner.

[0093] Based on benefit realization scores and gap analysis results, machine learning algorithms are applied to historical project data to identify patterns and summarize regularities. Through training and analysis of extensive historical project data, machine learning algorithms can identify underlying patterns in resource flow, environmental monitoring, and economic benefits, providing guidance for future coal-based solid waste resource management. For example, the algorithm may identify a region where a particular type of coal-based solid waste recycling process has high recovery efficiency and significant environmental benefits. Based on these patterns, the algorithm will provide optimization recommendations for future projects, ensuring more efficient and environmentally friendly resource utilization paths.

[0094] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0095] The resource value scores, resource flow data, and multi-dimensional benefit evaluation results were standardized and converted into decision input parameters with a unified dimension to obtain a comprehensive decision-making dataset for coal-based solid waste resources.

[0096] A decision tree model was constructed based on the comprehensive decision-making dataset of coal-based solid waste resources. A hierarchical analysis was conducted on resource classification, utilization methods, and value realization paths to obtain a decision tree for coal-based solid waste resource management.

[0097] Applying the Monte Carlo simulation method to the decision tree for coal-based solid waste resource management, we generated multiple rounds of scenario simulation data under different decision paths and obtained a decision risk probability distribution map.

[0098] Based on the decision risk probability distribution diagram and multi-objective optimization algorithm, the goals of maximizing economic benefits, minimizing environmental risks and optimizing social values ​​are weighed and calculated to obtain the Pareto optimal decision solution set;

[0099] Applying the analytic hierarchy process to the Pareto optimal decision-making solution set, combined with regional development needs and policy-oriented factors, a comprehensive evaluation was conducted to obtain the optimal decision-making solution for coal-based solid waste resource management;

[0100] The optimal decision-making plan for coal-based solid waste resource management is matched with historical successful cases, key success factors and execution paths are extracted, and a decision-making plan for coal-based solid waste resource management is obtained.

[0101] Specifically, data standardization is performed on resource value scores, resource flow data, and multi-dimensional benefit evaluation results. The purpose of this process is to eliminate the difficulty of comparison between different indicators due to different dimensions, and to ensure that the input parameters of each decision are processed under a unified dimension. Common standardization methods include Min-Max normalization or Z-score normalization. For example, the resource value score may range from 0 to 100, the amount of flow data ranges widely, and the results of the benefit evaluation may vary greatly between different units. By uniformly converting these data into standardized values ​​between 0 and 1, the fairness and accuracy of subsequent analysis can be ensured. After standardization, a unified dimension coal-based solid waste resource comprehensive decision-making data set is obtained. This data set contains the value of various resources, flow data, and benefit evaluation information, providing basic data for subsequent decision support.

[0102] Based on this comprehensive decision dataset, a decision tree model is constructed to perform a hierarchical analysis of resource classification, utilization methods, and value realization paths. The decision tree model is a common classification and regression analysis method. By classifying and hierarchically analyzing different resource utilization paths, it can clearly demonstrate resource selection and value realization methods under different decision paths. For example, in a decision tree for a specific type of coal-based solid waste, a hierarchical screening process might be performed based on the physical and chemical properties of the resource (such as particle size and moisture content) as well as the economic benefits and environmental impact of the application scenario, ultimately determining the most appropriate resource utilization path. Each level of the decision tree corresponds to a decision node, and nodes are connected by judgment conditions, ultimately forming a complete decision path tree. After the decision tree is constructed, multiple rounds of scenario simulations are performed using the Monte Carlo simulation method. This method randomly generates different input parameters (such as economic benefits and environmental impact) to simulate the possible outcomes of different decision paths, generating multiple rounds of scenario simulation data. For example, during the simulation process, factors such as market demand for resources, resource price fluctuations, and changes in the policy environment may be changed to obtain resource utilization results under multiple simulation scenarios. Monte Carlo simulation uses multiple random samplings to assign a probability distribution to each decision path, ultimately generating a decision risk probability distribution map. This map shows the probability distribution of indicators such as economic benefits and environmental impact under different decision paths, helping decision makers understand the risks and benefits of different paths.

[0103] Based on the results of Monte Carlo simulations, a multi-objective optimization algorithm is used to weigh the trade-offs between maximizing economic benefits, minimizing environmental risks, and optimizing social value. These objectives are often conflicting. For example, in some cases, increasing economic benefits may require sacrificing environmental protection or social benefits. Multi-objective optimization algorithms allow for a comprehensive consideration of these conflicting objectives to find the optimal balance between them. Leveraging the concept of Pareto optimal solutions, the optimization algorithm generates a set of Pareto-optimal decision solutions that achieve the optimal balance between economic benefits, environmental risks, and social value—maximizing one objective without sacrificing the others.

[0104] The Analytic Hierarchy Process (AHP) was applied to further evaluate the Pareto-optimal set of decision options. The AHP is a decision analysis method that breaks down complex decision-making problems into multiple levels. Different decision options are weighted and scored by constructing a judgment matrix. Based on regional development needs and policy-driven factors, each option is scored and a comprehensive evaluation is derived using expert scoring and weight analysis. The AHP helps comprehensively assess the feasibility of each option from different dimensions. For example, if a particular option has advantages in economic benefits but scores low in environmental risk control, the weights of each objective can be appropriately adjusted based on the region's policy orientation to arrive at the most appropriate decision option.

[0105] The optimal decision-making plan is pattern-matched with historical success cases, extracting key success factors and execution paths from historical data. By analyzing past success cases, the system can identify which strategies, technologies, and management measures have been successful under similar conditions and apply these factors to current decision-making. For example, in the recycling of coal-based solid waste resources, some regions have successfully achieved a balance between high economic benefits and low environmental risks by optimizing transportation routes, improving processing efficiency, and strengthening environmental monitoring. Summarizing these experiences and incorporating them into current decision-making can effectively improve the implementation of the plan.

[0106] The above describes the classification method of physical and chemical properties of coal-based solid waste based on regional ecological characteristics in the embodiment of the present application. The following describes the classification system of physical and chemical properties of coal-based solid waste based on regional ecological characteristics in the embodiment of the present application. Figure 2 In the embodiments of the present application, an embodiment of the coal-based solid waste physical and chemical property classification system based on regional ecological characteristics includes:

[0107] Processing module 201 is used to collect and digitally process coal-based solid waste resource data to obtain a coal-based solid waste resource database and a regional ecological characteristics database;

[0108] An analysis module 202 is configured to perform a correlation analysis between the characteristics of coal-based solid waste resources and regional ecological factors based on the coal-based solid waste resource database and the regional ecological characteristics database, and obtain a characteristic correlation parameter set and key influencing factors;

[0109] A modeling module 203 is configured to perform multi-dimensional classification modeling of coal-based solid waste resources based on the characteristic association parameter set and the key influencing factors, thereby obtaining a coal-based solid waste resource classification model and resource characteristic prediction results;

[0110] An evaluation module 204 is configured to perform a multi-dimensional evaluation of the commercial value of coal-based solid waste resources based on the coal-based solid waste resource classification model and the resource characteristic prediction results, thereby obtaining a resource value score and a market matching solution;

[0111] Monitoring module 205, for monitoring the coal-based solid waste resource utilization process in the market matching scheme throughout its life cycle, and obtaining resource flow data and multi-dimensional benefit evaluation results;

[0112] The input module 206 is used to input the resource value score, the resource flow data and the multi-dimensional benefit evaluation results into the decision engine for comprehensive analysis to obtain a coal-based solid waste resource management decision plan.

[0113] Through the collaborative cooperation of the above-mentioned components, by collecting and digitally processing coal-based solid waste resource data, a coal-based solid waste resource database and a regional ecological characteristic database were constructed, providing high-quality basic data support for subsequent analysis and solving the problems of irregular data collection and scattered storage in traditional methods; by conducting correlation analysis on the characteristics of coal-based solid waste resources and regional ecological factors, characteristic correlation parameter sets and key influencing factors were obtained, revealing the intrinsic connection between the physical and chemical properties of coal-based solid waste and the regional ecological environment, especially by applying artificial intelligence algorithms such as multivariate statistical analysis methods, principal component analysis and canonical correlation analysis, the correlation analysis results are highly interpretable and scientific, and the characteristics of these algorithms significantly improve the accuracy of correlation pattern recognition and the accuracy of ecological factor impact measurement; multi-dimensional classification modeling is carried out based on characteristic correlation parameter sets and key influencing factors, and classification models are constructed using intelligent algorithms such as hierarchical clustering, support vector machines and random forests. The characteristics of these algorithms enable the classification process to fully consider the nonlinear relationship and high The multi-dimensional characteristics greatly improve the accuracy and stability of coal-based solid waste resource classification; through multi-dimensional evaluation of the commercial value of coal-based solid waste resources, resource value scores and market matching plans are obtained, and a bridge from resource classification to value realization is built. The multi-objective optimization algorithm characteristics used in it effectively solve the multi-dimensional balance problem in resource value evaluation; the coal-based solid waste resource utilization process is monitored throughout its life cycle, and the Internet of Things technology and data mining algorithms are used to obtain resource flow data and multi-dimensional benefit evaluation results. The characteristics of these algorithms perform well in processing time series data and benefit evaluation, and provide real-time feedback on resource utilization effects; finally, the resource value scores, resource flow data and multi-dimensional benefit evaluation results are input into the decision engine for comprehensive analysis to obtain a coal-based solid waste resource management decision plan. The algorithm characteristics such as Monte Carlo simulation and hierarchical analysis method enable the decision-making process to have the ability to deal with uncertainty and multi-objective trade-offs, realize full-chain intelligent management from data to decision-making, and comprehensively improve the scientificity, accuracy and efficiency of coal-based solid waste resource management.

[0114] above Figure 2 The coal-based solid waste physical and chemical property classification system based on regional ecological characteristics in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The coal-based solid waste physical and chemical property classification equipment based on regional ecological characteristics in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0115] Figure 3This is a schematic diagram of the structure of a device for classifying coal-based solid waste based on the physical and chemical properties of regional ecological characteristics, provided by an embodiment of the present invention. This device 300 can vary significantly depending on its configuration or performance. It may include one or more central processing units (CPUs) 310 (e.g., one or more processors), a memory 320, and one or more storage media 330 (e.g., one or more mass storage devices) for storing application programs 333 or data 332. The memory 320 and storage media 330 may be either transient or persistent storage. The program stored in the storage medium 330 may include one or more modules (not shown), each of which may include a series of instructions for operating the device 300 based on the physical and chemical properties of regional ecological characteristics. Furthermore, the processor 310 can be configured to communicate with the storage medium 330 and execute a series of instruction operations in the storage medium 330 on the coal-based solid waste physical and chemical properties classification device 300 based on regional ecological characteristics to implement the steps of the above-mentioned coal-based solid waste physical and chemical properties classification method based on regional ecological characteristics.

[0116] The coal-based solid waste physical and chemical property classification device 300 based on regional ecological characteristics may also include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input and output interfaces 360, and / or one or more operating systems 331, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be understood by those skilled in the art that Figure 3 The structure of the coal-based solid waste physical and chemical property classification equipment based on regional ecological characteristics shown does not constitute a limitation of the coal-based solid waste physical and chemical property classification equipment based on regional ecological characteristics provided by the present invention, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0117] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions. When the instructions are run on a computer, the computer executes the steps of the method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics.

[0118] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0119] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a device for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0120] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics, characterized in that: The method comprises: Collect and digitize coal-based solid waste resource data to obtain a coal-based solid waste resource database and a regional ecological characteristics database; Based on the coal-based solid waste resource database and the regional ecological characteristic database, correlation analysis is performed on the coal-based solid waste resource characteristics and regional ecological factors to obtain a characteristic correlation parameter set and key influencing factors; Based on the characteristic association parameter set and the key influencing factors, a multi-dimensional classification model is performed on the coal-based solid waste resources to obtain a coal-based solid waste resource classification model and resource characteristic prediction results; Based on the coal-based solid waste resource classification model and the resource characteristics prediction results, a multi-dimensional evaluation of the commercial value of coal-based solid waste resources is conducted to obtain a resource value score and a market matching solution; Conduct full life cycle monitoring of the coal-based solid waste resource utilization process in the market matching scheme to obtain resource flow data and multi-dimensional benefit evaluation results; The resource value score, the resource flow data and the multi-dimensional benefit evaluation results are input into a decision engine for comprehensive analysis to obtain a coal-based solid waste resource management decision plan.

2. The method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics according to claim 1 is characterized in that: The coal-based solid waste resource data is collected and digitally processed to obtain a coal-based solid waste resource database and a regional ecological characteristics database, including: Collect coal-based solid waste samples on site to obtain original coal-based solid waste samples and sampling point location data; Coding and preprocessing the original coal-based solid waste sample to obtain a standardized coal-based solid waste sample and a unique sample identification code; Performing physical property testing on the standardized coal-based solid waste sample to obtain physical property parameters of the coal-based solid waste including particle composition, bulk density, and porosity; Performing chemical composition analysis on the standardized coal-based solid waste sample to obtain chemical characteristic parameters of the coal-based solid waste including elemental composition, organic matter content, and heavy metal content; Collecting ecological element data in the area corresponding to the sampling point location data to obtain original data of regional ecological characteristics including climate data, terrain data and vegetation cover data; The sample unique identification code, the physical property parameters of the coal-based solid waste, the chemical property parameters of the coal-based solid waste and the original data of the regional ecological characteristics are standardized, integrated and stored to obtain a coal-based solid waste resource database and a regional ecological characteristics database.

3. The method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics according to claim 1 is characterized in that: Based on the coal-based solid waste resource database and the regional ecological characteristics database, correlation analysis is performed on the coal-based solid waste resource characteristics and regional ecological factors to obtain characteristic correlation parameter sets and key influencing factors, including: Standardizing the physical and chemical property parameters of coal-based solid waste in the coal-based solid waste resource database to obtain a standardized coal-based solid waste property data set; Standardizing the ecological factor parameters in the regional ecological characteristic database to obtain a standardized regional ecological characteristic dataset; Based on the standardized coal-based solid waste characteristic data set and the standardized regional ecological characteristic data set, the correlation coefficient matrix between the physical and chemical properties of coal-based solid waste and regional ecological factors is calculated to obtain significant correlation parameter pairs; Applying the principal component analysis method to the standardized coal-based solid waste characteristic data set to perform dimensionality reduction processing to obtain the coal-based solid waste characteristic principal component factors with a cumulative variance contribution rate of not less than 85%; Based on the principal component factors of the coal-based solid waste characteristics and the standardized regional ecological characteristic data set, a canonical correlation analysis is performed to obtain a typical correlation pattern between the coal-based solid waste characteristics and regional ecological factors; According to the typical correlation pattern and the significantly correlated parameter pair, a random forest algorithm is used to calculate the feature importance index to obtain a feature association parameter set and key influencing factors.

4. The method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics according to claim 1 is characterized in that: The multi-dimensional classification modeling of coal-based solid waste resources is performed based on the characteristic association parameter set and the key influencing factors to obtain a coal-based solid waste resource classification model and resource characteristic prediction results, including: The sample data in the coal-based solid waste resource database is randomly divided into a training data set and a test data set in a ratio of 7:3 to obtain a coal-based solid waste resource training set and a test set; Applying a hierarchical clustering algorithm to the coal-based solid waste resource training set, determining the optimal clustering value by calculating the silhouette coefficient and the Davies-Bouldin index, and obtaining the number of classifications of the coal-based solid waste resources; Based on the feature association parameter set and the key influencing factors, a classification model including K-means clustering, support vector machine and random forest is constructed, and the optimal performance model is selected through cross-validation to obtain the optimal classification model for coal-based solid waste resources; Conduct statistical analysis on the characteristic parameters of each category of resources, calculate the characteristic distribution characteristics of each category, and obtain the characteristic description files of each category of resources; Based on the characteristic description archive and the key influencing factors, a resource characteristic prediction model is constructed, and characteristic prediction is performed on coal-based solid waste samples to obtain resource characteristic prediction results.

5. The method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics according to claim 1 is characterized in that: Based on the coal-based solid waste resource classification model and the resource characteristics prediction results, a multi-dimensional assessment of the commercial value of coal-based solid waste resources is performed to obtain a resource value score and a market matching solution, including: Construct a multi-dimensional value assessment framework for coal-based solid waste resources that includes economic value, environmental value, and social value dimensions, perform hierarchical quantification on the resource characteristic prediction results, and obtain a coal-based solid waste resource value assessment indicator system; Based on the coal-based solid waste resource classification model, the application scenarios of various types of coal-based solid waste resources are analyzed to obtain the application potential matrix of coal-based solid waste resources; Calculate the economic benefits of each application scenario in the coal-based solid waste resource application potential matrix to obtain the return on investment and payback period data under different utilization methods; Based on the ROI and payback period data, the economic feasibility of each application scenario is ranked, and the top three application scenarios are selected to obtain the resource utilization path for priority development; Construct a regional market demand database, match and analyze the demand parameters of potential users in the region with the resource utilization paths of the priority development, and obtain a resource-user matching score; Based on the resource-user matching score and the coal-based solid waste resource value assessment index system, a comprehensive resource value score and an optimal market matching solution are generated.

6. The method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics according to claim 1 is characterized in that: The whole life cycle monitoring of the coal-based solid waste resource utilization process in the market matching scheme is carried out to obtain resource flow data and multi-dimensional benefit evaluation results, including: Apply electronic tag technology to identify and manage the coal-based solid waste resources in the market matching solution, record the unique identification code and basic characteristic parameters of the resources, and obtain an electronic ID card for the coal-based solid waste resources; Based on the electronic ID card of coal-based solid waste resources and IoT sensor equipment, data is collected on the entire process of resource generation, collection, transportation, processing and final application to obtain the flow trajectory data of coal-based solid waste resources; Deploy an environmental monitoring sensor network in the coal-based solid waste resource application area to monitor air quality, water quality and soil conditions in real time and obtain dynamic data on environmental impacts; Based on the coal-based solid waste resource flow trajectory data and the environmental impact dynamic data, a multi-dimensional benefit evaluation system with economic benefit indicators, environmental benefit indicators, and social benefit indicators is constructed to obtain a quantitative standard for the utilization benefit of coal-based solid waste resources; Compare and analyze the coal-based solid waste resource utilization benefit quantification standards with the preset targets, calculate the achievement rate and deviation value of each benefit indicator, and obtain the benefit realization score and gap analysis results; Based on the benefit realization score and the gap analysis results, a machine learning algorithm is applied to perform pattern mining and regularity summary on historical project data to obtain resource flow data and multi-dimensional benefit evaluation results.

7. The method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics according to claim 1 is characterized in that: The resource value score, the resource flow data, and the multi-dimensional benefit evaluation results are input into a decision engine for comprehensive analysis to obtain a coal-based solid waste resource management decision plan, including: Performing data standardization on the resource value score, the resource flow data, and the multi-dimensional benefit evaluation results, converting them into decision input parameters of a unified dimension, and obtaining a comprehensive decision-making data set for coal-based solid waste resources; A decision tree model is constructed based on the comprehensive decision-making data set of coal-based solid waste resources, and a hierarchical analysis is performed on resource classification, utilization mode and value realization path to obtain a decision tree for coal-based solid waste resource management; Applying the Monte Carlo simulation method to the coal-based solid waste resource management decision tree to generate multiple rounds of scenario simulation data under different decision paths and obtain a decision risk probability distribution map; Based on the decision risk probability distribution diagram and the multi-objective optimization algorithm, a trade-off calculation is performed on the objectives of maximizing economic benefits, minimizing environmental risks, and optimizing social values ​​to obtain a Pareto optimal decision solution set; Applying the analytic hierarchy process to the Pareto optimal decision solution set, and conducting a comprehensive evaluation based on regional development needs and policy-oriented factors, the optimal decision solution for coal-based solid waste resource management is obtained; The optimal decision-making plan for coal-based solid waste resource management is pattern matched with historical successful cases, key success factors and execution paths are extracted, and a decision-making plan for coal-based solid waste resource management is obtained.

8. A classification system for the physical and chemical properties of coal-based solid waste based on regional ecological characteristics, characterized by: For implementing the method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics according to any one of claims 1 to 7, the physical and chemical properties classification system for coal-based solid waste based on regional ecological characteristics comprises: The processing module is used to collect and digitally process coal-based solid waste resource data to obtain a coal-based solid waste resource database and a regional ecological characteristics database; An analysis module, configured to perform correlation analysis between coal-based solid waste resource characteristics and regional ecological factors based on the coal-based solid waste resource database and the regional ecological characteristic database, and obtain a characteristic correlation parameter set and key influencing factors; A modeling module, configured to perform multi-dimensional classification modeling of coal-based solid waste resources based on the characteristic association parameter set and the key influencing factors, and obtain a coal-based solid waste resource classification model and resource characteristic prediction results; An evaluation module, configured to perform a multi-dimensional evaluation of the commercial value of coal-based solid waste resources based on the coal-based solid waste resource classification model and the resource characteristic prediction results, and obtain a resource value score and a market matching solution; A monitoring module is used to monitor the entire life cycle of the coal-based solid waste resource utilization process in the market matching scheme, and obtain resource flow data and multi-dimensional benefit evaluation results; The input module is used to input the resource value score, the resource flow data and the multi-dimensional benefit evaluation results into the decision engine for comprehensive analysis to obtain a coal-based solid waste resource management decision plan.

9. A device for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics, characterized in that: It includes a memory and a processor, the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the processor executes the method for classifying the physical and chemical properties of coal-based solid waste based on regional ecological characteristics as described in any one of claims 1 to 7.

Images