Landfill waste degradation state modeling and identification method and system based on virtual simulation

Abstract

The application relates to the technical field of computer modeling, and provides a landfill garbage degradation state modeling identification method and system based on virtual simulation, which are used to improve the accuracy and real-time performance of garbage degradation state identification. The method comprises the following steps: collecting component composition information and physical and chemical properties of each component of landfill garbage; determining environmental factor dynamic interaction rules according to the interaction mode and influence relationship between different environmental factors of the landfill; collecting real-time environmental monitoring parameters through a corresponding monitoring device cluster according to the rules; creating a multi-physical field virtual simulation model in combination with the component composition information, the physical and chemical properties of each component and the environmental factor dynamic interaction rules; importing the real-time environmental monitoring parameters into the model for collaborative operation to output dynamic evolution data; extracting a garbage degradation state feature vector based on the dynamic evolution data; and inputting the garbage degradation state feature vector into a preset state identification model to output a garbage degradation state identification result corresponding to different degradation stage features.

Description

Technical Field

[0001] This application belongs to the field of computer modeling technology, specifically relating to a method and system for modeling and identifying the degradation state of landfill waste based on virtual simulation. Background Technology

[0002] With the acceleration of urbanization, the amount of waste generated continues to increase. Landfill, as one of the main methods of waste disposal, makes the monitoring and management of its degradation process crucial for environmental safety and resource recovery. Waste degradation is a complex physical, chemical, and biological process involving the decomposition and transformation of waste components and their interaction with environmental factors. Traditional monitoring technologies for the degradation status of waste in landfills often employ single-point or local physical and chemical indicator monitoring. For example, this involves periodically collecting leachate samples from landfills to analyze their chemical composition, or using sensors to monitor environmental factors such as temperature, humidity, and gas concentration within the landfill. The degradation status is then assessed based on this single or local monitoring data. Meanwhile, some technologies attempt to simulate the waste degradation process using mathematical models. However, existing models are often based on simplified assumptions, failing to fully consider the diversity of waste components and the differences in their physicochemical properties, and neglecting to systematically analyze the dynamic interactions between different environmental factors, thus limiting the accuracy and applicability of these models.

[0003] It is evident that existing technologies cannot comprehensively and dynamically reflect the complex relationships between changes in various components, responses to environmental factors, and the generation of degradation products during the waste degradation process, making it difficult to accurately identify the true state of waste degradation in real time. Summary of the Invention

[0004] This application provides a method and system for modeling and identifying the degradation status of landfill waste based on virtual simulation, in order to improve the accuracy and real-time performance of waste degradation status identification.

[0005] This application provides a method for modeling and identifying the degradation state of landfill waste based on virtual simulation, applied to computer equipment. The method includes: Collect information on the composition of landfill waste and the physicochemical properties of each component, and determine the dynamic interaction rules of environmental factors based on the interaction modes and influence relationships between different environmental factors in the landfill. Based on the type of environmental factor in the dynamic interaction rules of the environmental factors, real-time environmental monitoring parameters of the landfill are collected through the corresponding monitoring equipment cluster; By combining the component composition information, the physicochemical properties of each component, and the dynamic interaction rules of the environmental factors, a multiphysics virtual simulation model for landfill waste degradation analysis is created. The real-time environmental monitoring parameters are imported into the multiphysics virtual simulation model, and the dynamic evolution data of the waste degradation process is simulated and output through collaborative computing. The dynamic evolution data includes key change information on the changes of each component, the response of environmental factors, and the generation of degradation products during the waste degradation process. Based on the dynamic evolution data, feature vectors reflecting the degree, rate and trend of waste degradation are extracted through feature correlation analysis. The features of each dimension of the waste degradation state feature vector are correlated with the key change information. The waste degradation state feature vector is input into a preset state recognition model. By performing dimensional correlation analysis and pattern matching on the waste degradation state feature vector, the waste degradation state recognition result of the landfill is output. The waste degradation state recognition result corresponds to the different stages of waste degradation.

[0006] This application provides a computer device including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the above-described method.

[0007] This application provides a computer-readable storage medium including a computer program that, when run on a computer device, causes the computer device to perform the steps of the above-described method.

[0008] This application starts from the essential driving factors of waste degradation and constructs a technology chain covering component attributes, environmental interaction, dynamic simulation, feature extraction and state recognition. It breaks through the limitations of traditional waste degradation state recognition that relies only on single monitoring data or static models, and realizes multi-dimensional, dynamic and accurate simulation and recognition of the waste degradation process, thereby improving the accuracy and real-time performance of waste degradation state recognition. Attached Figure Description

[0009] Figure 1 This is a flowchart illustrating a method for modeling and identifying the degradation state of landfill waste based on virtual simulation, as provided in an embodiment of this application.

[0010] Figure 2 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application.

[0011] Figure 3 This is a functional block diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this application. Obviously, the described embodiments are only some embodiments of the technical solutions of this application, and not all embodiments. Based on the embodiments recorded in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the technical solutions of this application.

[0013] See Figure 1 This is a method for modeling and identifying the degradation status of landfill waste based on virtual simulation provided in the embodiments of this application. This method can be applied to computer equipment, and the specific process is as follows: steps 110-160.

[0014] Step 110: Collect information on the composition of landfill waste and the physicochemical properties of each component. Based on the interaction patterns and influence relationships between different environmental factors in the landfill, determine the dynamic interaction rules of environmental factors.

[0015] The computer equipment first collects the composition information of the waste in the target landfill through a preset component detection module. This composition information includes the proportions of organic, inorganic, and non-degradable components. Organic components include kitchen waste and paper waste, inorganic components include sand and gravel waste and metal waste, and non-degradable components include plastic and rubber waste. Simultaneously, the physicochemical properties of each component are collected, including density, moisture content, pH value, and volatile solids content. Next, the computer equipment collects environmental factor data from the landfill through an environmental factor monitoring module. Environmental factors include temperature, humidity, oxygen concentration, methane concentration, and leachate pH value. Analysis of this data determines the interaction modes and influence relationships between different environmental factors. For example, increased temperature promotes changes in humidity, and decreased oxygen concentration affects methane formation. Based on these interactions and influence relationships, dynamic interaction rules for environmental factors are determined, including the weight of interaction between different environmental factors, response time, and degree of influence.

[0016] Step 120: Based on the type of environmental factor in the dynamic interaction rules of the environmental factors, collect the real-time environmental monitoring parameters of the landfill through the corresponding monitoring equipment cluster.

[0017] The computer equipment first analyzes the dynamic interaction rules of environmental factors to determine the types of environmental factors included, such as temperature, humidity, and oxygen concentration. Next, it calls the corresponding monitoring equipment cluster based on the environmental factor type. This monitoring equipment cluster includes temperature sensor clusters, humidity sensor clusters, oxygen concentration sensor clusters, etc., with each cluster corresponding to one type of environmental factor. Then, the monitoring equipment clusters collect real-time environmental monitoring parameters of the landfill at a preset sampling frequency. These real-time environmental monitoring parameters include the real-time values ​​of each environmental factor, such as the real-time temperature value collected by the temperature sensor cluster and the real-time humidity value collected by the humidity sensor cluster.

[0018] Step 130: Combining the component composition information, the physicochemical properties of each component, and the dynamic interaction rules of the environmental factors, create a multiphysics virtual simulation model for landfill waste degradation analysis.

[0019] Step 131: Perform correlation analysis on the proportion and existing form of each component in the component composition information, and generate a component correlation feature set by combining the reactivity and stability characteristics of each component in the physicochemical properties.

[0020] The computer equipment first extracts the proportion data of each component from the composition information, such as P1 for kitchen waste and P2 for paper waste. Simultaneously, it analyzes the existing forms of each component, including solid, liquid, and gaseous states. Further, it performs correlation analysis on the proportions and existing forms of each component, for example, analyzing the degradation characteristics of kitchen waste with different proportions under different existing forms. Then, it extracts the reactivity and stability characteristics from the physicochemical properties of each component. Reactivity characteristics include the degradation rate constant and activation energy of each component, while stability characteristics include the half-life and decomposition temperature of each component. Finally, it integrates the proportions, existing forms, reactivity characteristics, and stability characteristics of each component to generate a component correlation feature set. This feature set is represented in the form of feature vectors, for example, F1=[P1, M1, R1, S1], where P1 is the proportion of kitchen waste, M1 is the existing form of kitchen waste, R1 is the reactivity characteristic of kitchen waste, and S1 is the stability characteristic of kitchen waste.

[0021] Step 132: Extract the influence weight and priority of each environmental factor from the dynamic interaction rules of the environmental factors, and classify the environmental factors into hierarchical structures according to the influence weight and priority.

[0022] The computer equipment first analyzes the dynamic interaction rules of environmental factors, extracting the influence weight and priority of each environmental factor. The influence weight represents the degree of influence of each environmental factor on the waste degradation process; for example, the influence weight of temperature is W1, and the influence weight of humidity is W2, etc. The priority represents the order in which each environmental factor acts during the waste degradation process; for example, the priority of temperature is higher than that of humidity, etc. Next, the environmental factors are stratified according to their influence weight and priority. Environmental factors with high influence weight and high priority are divided into the first layer, environmental factors with relatively high influence weight and high priority are divided into the second layer, and so on, to obtain the hierarchical structure of environmental factors. The hierarchical structure of environmental factors is represented in the form of a tree structure. For example, the first layer of environmental factors includes temperature and humidity, and the second layer of environmental factors includes oxygen concentration, methane concentration, etc.

[0023] Step 133: Construct a component degradation sub-model based on the component association feature set. The component degradation sub-model is used to describe the degradation behavior of a single component in an isolated environment.

[0024] The computer equipment first extracts feature data of individual components from the component association feature set, such as extracting feature data F1=[P1, M1, R1, S1] for kitchen waste. Next, based on the feature data of individual components, a framework for a component degradation sub-model is constructed, including a degradation kinetics module and a material transformation module. Then, a degradation kinetics model is embedded in the degradation kinetics module, describing the degradation rate change of a single component in an isolated environment based on its reactivity and stability characteristics. A material transformation model is embedded in the material transformation module, describing the material transformation pathway of a single component during degradation based on its physicochemical properties. Finally, parameters are set for the component degradation sub-model based on the feature data of the individual components, such as setting the parameters of the degradation kinetics model according to the degradation rate constant of kitchen waste, thus completing the construction of the component degradation sub-model.

[0025] Step 134: Construct an environmental action sub-model based on the environmental factor hierarchy, which is used to describe the regulatory strategies of different levels of environmental factors on degradation behavior.

[0026] The computer equipment first extracts feature data of environmental factors at each level of the environmental factor hierarchy, such as feature data T1 for temperature and H1 for humidity at the first level. Then, based on the feature data of each level of environmental factors, a framework for an environmental action sub-model is constructed. This framework includes an environmental factor input module, a regulation strategy generation module, and a regulation effect output module. Next, an environmental factor data receiving interface is embedded in the environmental factor input module to receive real-time data from each level of environmental factors. A regulation strategy generation model is embedded in the regulation strategy generation module. This model generates regulation strategies for different levels of environmental factors on degradation behavior based on the feature data and dynamic interaction rules of each level of environmental factors, such as regulation strategies for rising temperature and decreasing humidity. A regulation effect prediction model is embedded in the regulation effect output module. This model predicts the impact of the regulation strategies on degradation behavior based on the regulation strategies and the output of the component degradation sub-model. Finally, parameters are set for the environmental action sub-model based on the environmental factor hierarchy and dynamic interaction rules, completing the construction of the environmental action sub-model.

[0027] Step 135: Establish a coupling interface between the component degradation sub-model and the environmental action sub-model. The coupling interface is used to realize bidirectional transmission and real-time adaptation of component degradation data and environmental action data.

[0028] The computer system first analyzes the output data type and format of the component degradation sub-model, which includes the degradation rate and material conversion of individual components. Simultaneously, it analyzes the input data type and format of the environmental impact sub-model, which includes real-time data on environmental factors and regulatory strategies. Then, based on the matching relationship between the output and input data types and formats, a coupling interface framework is established, including a data transmission module and a data adaptation module. The data transmission module embeds a data transmission protocol to enable bidirectional transmission of component degradation data and environmental impact data. The data adaptation module embeds a data adaptation algorithm to convert the output data of the component degradation sub-model into an input data format recognizable by the environmental impact sub-model, and vice versa. Finally, the coupling interface is tested to ensure bidirectional transmission and real-time adaptation of component degradation data and environmental impact data, thus completing the establishment of the coupling interface.

[0029] Step 136: Integrate the component degradation sub-model and the environmental action sub-model through the coupling interface, set the trigger conditions and data interaction frequency for model collaborative operation, and generate the multiphysics virtual simulation model.

[0030] Step 1361: Collect the interaction data between the component degradation sub-model and the environmental action sub-model in historical degradation simulation through the coupling interface, extract rules from the interaction data through the feature association mining algorithm, identify the triggering time, data type matching rules and response delay characteristics of data requests between sub-models under different degradation scenarios, and obtain the sub-model interaction rule set.

[0031] The computer equipment first collects interaction data between the component degradation sub-model and the environmental action sub-model in historical degradation simulations through a coupling interface. This interaction data includes data transmitted from the component degradation sub-model to the environmental action sub-model, data transmitted from the environmental action sub-model to the component degradation sub-model, and data transmission timestamps. Further preprocessing of the interaction data, including data cleaning and standardization, ensures accuracy and consistency. Then, feature association mining algorithms are used to extract rules from the preprocessed interaction data. These algorithms include association rule mining and sequence pattern mining algorithms to identify the triggering timing, data type matching patterns, and response delay characteristics of data requests between sub-models under different degradation scenarios. For example, in the scenario of kitchen waste degradation, the triggering timing for data requests between sub-models is when the temperature change exceeds a preset threshold; the data type matching pattern is that the degradation rate data transmitted by the component degradation sub-model matches the control strategy data transmitted by the environmental action sub-model; and the response delay characteristic is that the data transmission delay time is within a preset range. Finally, the identified triggering timing, data type matching patterns, and response delay characteristics are integrated to obtain a set of sub-model interaction rules, represented in the form of a rule base.

[0032] Step 1362: Construct a sub-model interaction logic mapping table based on the sub-model interaction rule set, establish the corresponding relationship between the output parameter type of the component degradation sub-model and the input requirements of the environmental action sub-model, and mark the scenario adaptation range corresponding to each relationship to determine the scenario orientation of data interaction between sub-models.

[0033] The computer equipment first extracts the output parameter types of the component degradation sub-model and the input requirements of the environmental impact sub-model from the sub-model interaction rules set. The output parameter types of the component degradation sub-model include degradation rate and material conversion amount, while the input requirements of the environmental impact sub-model include real-time data on environmental factors and control strategies. Next, based on the output parameter types of the component degradation sub-model and the input requirements of the environmental impact sub-model, a sub-model interaction logic mapping table is constructed. This table is represented in tabular form, with rows representing the output parameter types of the component degradation sub-model, columns representing the input requirements of the environmental impact sub-model, and cells representing the corresponding relationships. Then, the scenario adaptation range corresponding to each relationship is labeled, including scenarios for the degradation of kitchen waste organic waste and paper waste organic waste, to determine the scenario orientation of data interaction between sub-models. Finally, the sub-model interaction logic mapping table is validated to ensure the accuracy of the relationships and scenario adaptation ranges, completing the construction of the sub-model interaction logic mapping table.

[0034] Step 1363: The semantic parsing module parses the operational status description information of the component degradation sub-model, extracts key state features reflecting changes in the degradation process, and associates and matches the key state features with the activation conditions of the regulation strategy of the environmental action sub-model to generate a collaborative operation trigger condition library.

[0035] The computer equipment first parses the operational status description information of the component degradation sub-model using a semantic parsing module. This description includes the current operational status of the sub-model and changes in the degradation process. Next, it extracts key state features reflecting changes in the degradation process from the operational status description information. These key features include the rate of change of degradation rate and the rate of change of substance conversion. Then, it obtains the activation conditions for the regulation strategies of the environmental action sub-model. These activation conditions include thresholds for changes in environmental factors and thresholds for changes in component degradation rate. Finally, it correlates and matches the key state features with the activation conditions of the regulation strategies. For example, it matches the rate of change of degradation rate with the threshold for change of degradation rate in the activation conditions of the environmental action sub-model's regulation strategies. When the rate of change of degradation rate exceeds the threshold, the corresponding regulation strategy is triggered. Similarly, it matches the rate of change of substance conversion with the threshold for change of substance conversion in the activation conditions of the environmental action sub-model's regulation strategies. When the rate of change of substance conversion exceeds the threshold, the corresponding regulation strategy is triggered. The results of the correlation and matching are integrated to generate a collaborative operation trigger condition library.

[0036] Step 1364: Based on the statistical results of data transmission frequency in the set of interaction patterns of the sub-models, and combined with the trend prediction algorithm, analyze the changing trend of data demand of the sub-models under different degradation stages, and generate a dynamic data interaction frequency adjustment strategy. The dynamic data interaction frequency adjustment strategy adjusts the time interval of data interaction in real time according to the parameter update rate of the component degradation sub-model and the regulation response efficiency of the environmental action sub-model.

[0037] The computer equipment first extracts data transmission frequency statistics from the sub-model interaction patterns. These statistics include the frequency distribution of data transmission between sub-models at different degradation stages. Next, trend prediction algorithms, including time series forecasting and regression analysis, are used to analyze the data transmission frequency statistics to determine the changing trends of sub-model data requirements at different degradation stages. For example, in the initial stage of kitchen waste degradation, the data requirements gradually increase; in the middle stage, they remain stable; and in the later stage, they gradually decrease. Then, based on the parameter update rate of the component degradation sub-model and the regulatory response efficiency of the environmental impact sub-model, the adjustment criteria for the dynamic data interaction frequency adjustment strategy are determined. For example, when the parameter update rate of the component degradation sub-model increases, the data interaction time interval is shortened; when the regulatory response efficiency of the environmental impact sub-model decreases, the data interaction time interval is extended. Finally, based on the changing trends and adjustment criteria, a dynamic data interaction frequency adjustment strategy is generated.

[0038] Step 1365: Import the sub-model interaction logic mapping table, the collaborative operation trigger condition library, and the dynamic data interaction frequency adjustment strategy into the integrated model, and convert them into collaborative operation instructions to be identified by the sub-model through the logic compilation module, thereby completing the integration of the component degradation sub-model and the environmental action sub-model.

[0039] The computer equipment first imports the sub-model interaction logic mapping table, the collaborative operation trigger condition library, and the dynamic data interaction frequency adjustment strategy into the integrated model. The integrated model includes a component degradation sub-model, an environmental action sub-model, and coupling interfaces. Next, it calls the logic compilation module to compile the imported sub-model interaction logic mapping table, collaborative operation trigger condition library, and dynamic data interaction frequency adjustment strategy. The logic compilation module includes a syntax analyzer, a semantic analyzer, and a code generator, converting these into collaborative operation instructions to be recognized by the sub-models. These instructions include data interaction instructions and control strategy execution instructions. Then, the compiled collaborative operation instructions are sent to the component degradation sub-model and the environmental action sub-model to ensure that the two sub-models can perform data interaction and control strategy execution according to the collaborative operation instructions. Finally, the integrated model is tested to ensure that it can operate normally, completing the integration of the component degradation sub-model and the environmental action sub-model.

[0040] Step 1366: Conduct multi-scenario operation tests on the integrated model through simulation and deduction, collect interaction stability data and logical conflict information of the sub-models during the test, locate the logical nodes that cause conflicts by combining feature association analysis, and iteratively correct the sub-model interaction logic mapping table and the collaborative operation trigger condition library based on parameter optimization algorithm.

[0041] The computer equipment first constructs multi-scenario test cases, including scenarios for the degradation of kitchen waste, paper waste, and mixed waste. Next, the integrated model is simulated and tested across multiple scenarios. During testing, interaction stability data and logical conflict information of the sub-models are collected. Interaction stability data includes data transmission success rate and latency, while logical conflict information includes logical contradictions in data interaction between sub-models and logical errors in the execution of control strategies. Then, feature association analysis, including correlation analysis and causal analysis, is used to analyze the interaction stability data and logical conflict information to locate the logical nodes causing conflicts. For example, a logical contradiction may be found in a relationship in the sub-model interaction logic mapping table, or a logical error may be found in a trigger condition in the collaborative operation trigger condition library. Finally, the located logical nodes are iteratively corrected based on parameter optimization algorithms, including genetic algorithms and particle swarm optimization algorithms, to adjust the parameters in the sub-model interaction logic mapping table and the collaborative operation trigger condition library until the model no longer exhibits logical conflicts in multi-scenario testing and the interaction stability data meets preset requirements.

[0042] Step 1367: After the correction is completed, the target integration rules and operating parameters are solidified to generate a multiphysics virtual simulation model with autonomous collaborative capabilities; wherein, the target integration rules include at least the iteratively corrected sub-model interaction logic mapping table and the collaborative operation trigger condition library.

[0043] The computer equipment first verifies the revised sub-model interaction logic mapping table and collaborative operation trigger condition library to ensure they function correctly in multi-scenario testing without logical conflicts. Next, the revised sub-model interaction logic mapping table and collaborative operation trigger condition library are defined as the target integration rules, along with the model's operating parameters, including data interaction frequency and control strategy execution time. Then, the target integration rules and operating parameters are solidified, either by writing them into the model's configuration file or embedding them into the model's code. Finally, the solidified model is tested to ensure it possesses autonomous collaborative capabilities and can generate a multiphysics virtual simulation model.

[0044] Step 137: Initialize the integrated multiphysics virtual simulation model by entering the basic parameters in the component association feature set and the initial conditions in the environmental factor hierarchy into the multiphysics virtual simulation model.

[0045] The computer equipment first extracts basic parameters from the component correlation feature set, including the proportion and physicochemical properties of each component. It then extracts initial conditions from the environmental factor hierarchy, including the initial values ​​of each environmental factor. Next, the extracted basic parameters and initial conditions are entered into the configuration module of the multiphysics virtual simulation model, which stores the model's basic parameters and initial conditions. The entered basic parameters and initial conditions are then verified to ensure their accuracy and consistency. Finally, the multiphysics virtual simulation model is started, allowing it to initialize and run according to the entered basic parameters and initial conditions, completing the initial configuration of the multiphysics virtual simulation model.

[0046] Step 140: Import the real-time environmental monitoring parameters into the multiphysics virtual simulation model, and output the dynamic evolution data of the waste degradation process through collaborative computation. The dynamic evolution data includes key change information on the changes of each component, the response of environmental factors, and the generation of degradation products during the waste degradation process.

[0047] Step 141: Classify and organize the real-time environmental monitoring parameters according to the type of environmental factors, and divide the real-time environmental monitoring parameters into different parameter subsets, each parameter subset corresponding to the monitoring data of a type of environmental factor.

[0048] The computer equipment first analyzes the real-time environmental monitoring parameters to determine the types of environmental factors they contain, such as temperature, humidity, and oxygen concentration. Next, it categorizes and organizes the real-time environmental monitoring parameters according to the type of environmental factor, grouping monitoring data belonging to the same environmental factor type into a parameter subset. For example, all real-time temperature values ​​collected by temperature sensors are grouped into a temperature parameter subset, and all real-time humidity values ​​collected by humidity sensors are grouped into a humidity parameter subset. Then, each parameter subset is labeled with information including the type of environmental factor corresponding to the parameter subset and the collection time.

[0049] Step 142: Set data preprocessing rules for each parameter subset, and use the data preprocessing rules to remove abnormal data points in the parameter subset and retain valid monitoring data that meet the model input requirements.

[0050] The computer equipment first extracts data features from the parameter subsets, including the mean, variance, maximum, and minimum values. Next, based on these features, data preprocessing rules are set for each parameter subset. These rules include criteria for identifying outliers and methods for data standardization. For example, for the temperature parameter subset, an outlier is identified when the temperature value exceeds a preset range, and the standardization method converts the temperature value to a value between 0 and 1. Similarly, for the humidity parameter subset, an outlier is identified when the humidity value exceeds a preset range, and the standardization method converts the humidity value to a value between 0 and 1. Finally, the data in the parameter subsets is processed using these preprocessing rules to remove outliers and retain valid monitoring data that meets the model's input requirements.

[0051] Step 143: According to the hierarchical structure of the environmental action sub-model in the multiphysics virtual simulation model, the corresponding effective monitoring data are sequentially imported into the environmental action sub-model at each level, and the collaborative operation strategy of the multiphysics virtual simulation model is started to trigger the data interaction between the component degradation sub-model and the environmental action sub-model. The degradation behavior data and environmental regulation data are transmitted in real time through the coupling interface.

[0052] The computer equipment first analyzes the hierarchical structure of the environmental sub-models in the multiphysics virtual simulation model, determining the types of environmental factors corresponding to each level. For example, the first-level environmental sub-model corresponds to temperature and humidity, while the second-level model corresponds to oxygen concentration and methane concentration. Next, based on the hierarchical structure of the environmental sub-models, the corresponding valid monitoring data is sequentially imported into each level. For instance, valid monitoring data for the temperature parameter subset is imported into the first-level environmental sub-model, the valid monitoring data for the humidity parameter subset is imported into the first-level environmental sub-model, and the valid monitoring data for the oxygen concentration parameter subset is imported into the second-level environmental sub-model. Then, the collaborative operation strategy of the multiphysics virtual simulation model is activated. This strategy includes triggering conditions for data interaction between sub-models and the frequency of data interaction. It triggers data interaction between the component degradation sub-model and the environmental sub-model, enabling real-time transmission of degradation behavior data and environmental control data through a coupling interface. For example, the component degradation sub-model transmits degradation behavior data to the environmental sub-model, and the environmental sub-model generates environmental control data based on the degradation behavior data and transmits it back to the component degradation sub-model. Finally, the data interaction process is monitored to ensure that degradation behavior data and environmental control data can be transmitted in real time without data loss or delay.

[0053] Step 144: Perform collaborative computation based on the preset time step, calculate the degradation change of each component, the response value of environmental factors and the amount of degradation products generated in each time step, record the intermediate data in the computation process and obtain the computation results for each time step.

[0054] The computer equipment first determines a preset time step, which may include hours or days. Then, based on the preset time step, it performs collaborative computation. Within each time step, the component degradation sub-model calculates the degradation changes of each component based on the environmental regulation data transmitted by the environmental action sub-model. The environmental action sub-model calculates the response values ​​of environmental factors based on the degradation behavior data transmitted by the component degradation sub-model, and simultaneously calculates the amount of degradation products generated. Then, intermediate data during the computation process is recorded, including the degradation changes of each component, the response values ​​of environmental factors, and the amount of degradation products generated, thus obtaining the computation results for each time step.

[0055] Step 145: For the calculation results of each time step, organize the key change information of each component change, environmental factor response and degradation product generation according to time series to obtain stage evolution data fragments.

[0056] The computer equipment first extracts key change information on component changes, environmental factor responses, and degradation product generation from the calculation results at each time step. This key change information includes the degradation amount of each component, the response value of environmental factors, and the amount of degradation products generated. Next, the extracted key change information is organized into a time series, including the chronological order of the time steps. For example, key change information from the first time step is placed at the beginning of the time series, and key change information from the second time step is placed at the second, and so on. Then, the key change information organized into a time series is labeled with data such as the time step and the type of key change information. Finally, the organized key change information is identified as stage-specific evolutionary data segments.

[0057] Step 146: Connect and integrate the evolutionary data segments of all time steps, and supplement the correlation information between each evolutionary data segment to generate dynamic evolutionary data of the waste degradation process.

[0058] The computer equipment first concatenates evolutionary data segments across all time steps according to time series, linking the first time step segment with the second, the second with the third, and so on. Next, it analyzes the correlations between these data segments, including relationships between component changes, environmental factor responses, and degradation product formation. For example, the amount of component degradation change in the first time step affects the environmental factor response value in the second time step, and the environmental factor response value in the second time step affects the amount of degradation product formation in the third time step. Then, the analyzed correlation information is added to the concatenated evolutionary data segments to ensure clear visibility of these relationships. Finally, the evolutionary data segments with added correlation information are identified as the dynamic evolutionary data of the waste degradation process. This dynamic evolutionary data is represented in time series format and includes key information on changes in components, environmental factor responses, and degradation product formation during waste degradation.

[0059] Step 150: Based on the dynamic evolution data, extract the waste degradation state feature vector reflecting the degree of waste degradation, degradation rate and degradation trend through feature association analysis. The features of each dimension of the waste degradation state feature vector are associated with the key change information.

[0060] Step 151: Decompose the dynamic evolution data into component change sub-data, environmental factor response sub-data, and degradation product generation sub-data. Each sub-data corresponds to a time-series record of a type of key change information.

[0061] The computer equipment first analyzes the dynamic evolution data to determine the types of key change information it contains. These key change information types include component changes, environmental factor responses, and degradation product generation. Next, based on the key change information types, the dynamic evolution data is broken down into component change sub-data, environmental factor response sub-data, and degradation product generation sub-data. The component change sub-data corresponds to the time-series records of key change information related to component changes, the environmental factor response sub-data corresponds to the time-series records of key change information related to environmental factor responses, and the degradation product generation sub-data corresponds to the time-series records of key change information related to degradation product generation. Then, the decomposed sub-data is labeled, with the label including the corresponding key change information type and time series.

[0062] Step 152: Perform correlation analysis on the content change trajectories of each component in the component change sub-data to identify the synergistic or inhibitory degradation relationships between different components and generate component correlation features; perform trend analysis on the environmental factor numerical fluctuation trajectory in the environmental factor response sub-data to capture the immediate and delayed effects of environmental factors on degradation behavior and generate environmental response features; perform pattern mining on the product types and generation trajectories in the degradation product generation sub-data to extract the correspondence between product generation and component degradation and generate product correlation features.

[0063] The computer equipment first extracts the content change trajectories of each component from the component change sub-data. These trajectories include the content changes of each component at different time steps. Next, correlation analysis is performed on these component content change trajectories, including correlation analysis and causal analysis, to identify synergistic or inhibitory degradation relationships between different components. For example, there is a synergistic degradation relationship between kitchen waste and paper waste, and an inhibitory degradation relationship between kitchen waste and non-degradable plastic waste. Based on these relationships, component correlation features are generated, represented as feature vectors. Then, the environmental factor numerical fluctuation trajectory is extracted from the environmental factor response sub-data. This trajectory includes the numerical changes of environmental factors at different time steps. Trend analysis is performed on these trajectory, including time series analysis and regression analysis, to capture the immediate and delayed effects of environmental factors on degradation behavior. For example, the immediate effect of increased temperature on the degradation behavior of kitchen waste is an accelerated degradation rate, while the delayed effect of increased temperature on the degradation behavior of paper waste is an accelerated degradation rate after a certain period. Based on these effects, environmental response features are generated, represented as feature vectors. Product types and generation trajectories are extracted from the degradation product generation subdata. Product types include methane, carbon dioxide, etc. Generation trajectories include changes in the amount of products generated at different time steps. The product types and generation trajectories are analyzed through pattern mining, including cluster analysis and association rule mining, to extract the correspondence between product generation and component degradation. For example, the degradation of kitchen waste produces methane, while the degradation of paper waste produces carbon dioxide. Based on the above correspondence, product association features are generated.

[0064] Step 153: Import the component association features, the environmental response features, and the product association features into the feature association space to generate a feature association map. In the feature association map, nodes represent each feature, and edges represent the association strength between features.

[0065] Step 1531: Create a three-dimensional feature association space using the component degradation dimension, environmental action dimension, and product generation dimension as spatial coordinate axes. Map the component association features, environmental response features, and product association features to the coordinate axes of the corresponding dimensions to obtain the initial coordinate points of the features.

[0066] The computer equipment first determines the spatial coordinate axes of the three-dimensional feature association space, namely the component degradation dimension, the environmental effect dimension, and the product generation dimension. Next, the component-related features are mapped to the coordinate axis of the component degradation dimension, the environmental response features to the coordinate axis of the environmental effect dimension, and the product-related features to the coordinate axis of the product generation dimension, obtaining the initial coordinate points of the features. The coordinate values ​​of the initial coordinate points are determined based on the values ​​of each feature. For example, if the value of the component-related feature is 'a', its coordinate value on the component degradation dimension axis is 'a'; if the value of the environmental response feature is 'b', its coordinate value on the environmental effect dimension axis is 'b'; and if the value of the product-related feature is 'c', its coordinate value on the product generation dimension axis is 'c'. Therefore, the coordinates of the initial coordinate points are (a, b, c). Then, the initial coordinate points are verified to ensure their mapping positions are accurate, and the initial coordinate points are displayed in the three-dimensional feature association space.

[0067] Step 1532: Calculate the spatial distance and feature attribute similarity between any two initial coordinate points of features; where spatial distance reflects the physical correlation between features, and feature attribute similarity reflects the consistency of features in data change patterns.

[0068] The computer device first extracts any two initial feature coordinate points from the three-dimensional feature association space, such as initial feature coordinate points A (a1, b1, c1) and B (a2, b2, c2). Next, it calculates the spatial distance between initial feature coordinate points A and B. Methods for calculating spatial distance include Euclidean distance and Manhattan distance. For example, using Euclidean distance reflects the physical correlation between features; the smaller the spatial distance, the stronger the physical correlation. Then, it calculates the feature attribute similarity between initial feature coordinate points A and B. Methods for calculating feature attribute similarity include cosine similarity and Pearson correlation coefficient. For example, using cosine similarity reflects the consistency of features in data variation patterns; the greater the feature attribute similarity, the higher the consistency of features in data variation patterns.

[0069] Step 1533: Set the association strength calculation rules, take the product of the reciprocal of the spatial distance and the similarity of the feature attributes as the initial association strength between features, and normalize the initial association strength to obtain the standardized association strength.

[0070] The computer equipment first sets the association strength calculation rules, which include the product of the reciprocal of spatial distance and the similarity of feature attributes. Next, it calculates the initial association strength between features according to the association strength calculation rules: Initial association strength = (1 / spatial distance) × feature attribute similarity. For example, if the spatial distance between initial coordinate points A and B is d, and the feature attribute similarity is s, then the initial association strength = (1 / d) × s. Then, the initial association strength is normalized. Normalization methods include min-max normalization and z-score normalization. For example, using min-max normalization, the standardized association strength = (initial association strength - minimum initial association strength) / (maximum initial association strength - minimum initial association strength), where the minimum initial association strength is the minimum value among all initial association strengths between features, and the maximum initial association strength is the maximum value among all initial association strengths between features.

[0071] Step 1534: Using the initial coordinate point of each feature as a feature node, establish an association edge between two feature nodes whose standardized association strength is greater than the preset association strength, and mark the corresponding standardized association strength value on the association edge to obtain the initial feature association map.

[0072] The computer equipment first determines a preset association strength, which is determined based on actual needs. Next, it traverses all initial feature coordinates in the 3D feature association space, treating each initial feature coordinate as a feature node. Then, for any two feature nodes, it checks if the standardized association strength between them is greater than the preset association strength. If it is, an association edge is established between the two feature nodes, and the corresponding standardized association strength value is labeled on the association edge. All established association edges and labeled standardized association strength values ​​are integrated to obtain the initial feature association map.

[0073] Step 1535: Traverse each feature node in the initial feature association graph and check whether there is a conflict between the feature node and its adjacent feature nodes. A conflict is manifested as the same feature node having a strong association with two feature nodes with opposite semantics. If a conflict exists, recalculate the standardized association strength of the conflicting association edges. In the calculation, the frequency weight of the feature in the dynamically evolving data is introduced. The higher the frequency of the feature, the greater the weight. The standardized association strength is corrected by adjusting the weight. The initial feature association graph is updated by retaining the association edges with higher standardized association strength after correction and deleting the association edges with lower standardized association strength after correction, until there are no conflicting association edges in the initial feature association graph. The feature association graph is used to present the effective association relationships and association strengths between each feature.

[0074] The computer device first traverses each feature node in the initial feature association graph, checking for conflicts between the node and its adjacent nodes. For example, a single feature node may have strong associations with two semantically opposite feature nodes, such as degradation-cooperating feature nodes and degradation-inhibiting feature nodes. Next, if conflicts exist, the frequency of feature occurrence is extracted from the dynamic evolution data. Frequency includes the number of times a feature appears in the dynamic evolution data, and a frequency weight is introduced, with higher frequencies having higher weights. Then, the standardized association strength of conflicting edges is recalculated, using methods such as multiplying the original standardized association strength by the frequency weight, thus adjusting the standardized association strength. Edges with higher standardized association strength after adjustment are retained, while those with lower strength are deleted to update the initial feature association graph. This process is repeated until no conflicting edges remain in the initial feature association graph, resulting in the feature association graph, which is used to represent the effective association relationships and strengths between features.

[0075] Step 154: Combining the degree of waste degradation, degradation rate and degradation trend, determine the core features that meet the correlation conditions from the feature correlation map and generate a core feature set.

[0076] The computer equipment first determines evaluation indicators for the degree, rate, and trend of waste degradation. These indicators include the degradation changes of each component, the response values ​​of environmental factors, and the amount of degradation products generated. Next, based on these indicators, features related to the degree, rate, and trend of waste degradation are selected from a feature correlation map. For example, features related to the degradation changes of each component, the response values ​​of environmental factors, and the amount of degradation products generated are selected. Then, correlation conditions are determined, including a correlation coefficient between the feature and the degree, rate, and trend of waste degradation that is greater than a preset threshold. From the selected features, core features that meet the correlation conditions are identified, and these core features are integrated to generate a core feature set.

[0077] Step 155: Sort and classify each feature in the core feature set according to a preset dimension, assign a dimension weight matching the correlation strength to each feature, and generate the waste degradation state feature vector through the normalization of the feature dimensions. Each dimension feature of the waste degradation state feature vector corresponds to a core feature expression of a key change information.

[0078] The computer equipment first determines preset dimensions, including component degradation, environmental response, and byproduct generation dimensions. Next, the features in the core feature set are classified and sorted according to these preset dimensions. For example, features related to component degradation are grouped into one category, features related to environmental response into another, and features related to byproduct generation into a third, and then sorted according to their importance. Then, each feature is assigned a dimensional weight matching its correlation strength; the stronger the correlation, the greater the dimensional weight. For example, if the correlation strength of a feature is s, the dimensional weight is w=s. A waste degradation state feature vector is generated through feature dimension normalization. This normalization includes converting the values ​​of each feature to values ​​between 0 and 1. Each dimension of the waste degradation state feature vector corresponds to a core feature expression of key change information. For example, the first dimension of the waste degradation state feature vector corresponds to the core feature of the component degradation dimension, the second dimension corresponds to the core feature of the environmental response dimension, and the third dimension corresponds to the core feature of the byproduct generation dimension, and so on.

[0079] Step 160: Input the waste degradation state feature vector into a preset state recognition model, and output the waste degradation state recognition result of the landfill by performing dimensional correlation analysis and pattern matching on the waste degradation state feature vector. The waste degradation state recognition result corresponds to the different stages of waste degradation.

[0080] Step 161: Normalize the features of each dimension of the waste degradation state feature vector to obtain a normalized feature vector.

[0081] The computer equipment first extracts the numerical values ​​of each dimension of features from the feature vector of waste degradation status. Further, the numerical values ​​of each dimension of features are normalized. Normalization methods include min-max normalization and z-score normalization. For example, when using min-max normalization to process the numerical values ​​of each dimension of features, the normalized value = (original value - minimum value) / (maximum value - minimum value), where the minimum value is the minimum value among the numerical values ​​of that dimension of features, and the maximum value is the maximum value among the numerical values ​​of that dimension of features. Then, the normalized numerical values ​​of each dimension of features are integrated to obtain the normalized feature vector.

[0082] Step 162: Call the dimensional correlation analysis sub-model in the state recognition model, extract the rate of change and direction of change of each dimension feature in the normalized feature vector, and calculate the change coordination coefficient between any two dimension features. A positive coordination coefficient indicates that the feature change trends are consistent, and a negative coordination coefficient indicates that the feature change trends are opposite.

[0083] The computer device first invokes the dimensional correlation analysis sub-model within the state recognition model. This sub-model includes modules for calculating the rate of change, identifying the direction of change, and calculating the coordination coefficient. Next, the rate of change calculation module extracts the rate of change for each dimension of the normalized feature vector. This rate of change includes the ratio of the change in the value of each dimension within adjacent time steps to its original value. Then, the direction of change identification module extracts the direction of change for each dimension of the normalized feature vector, including increases and decreases. Finally, the coordination coefficient calculation module calculates the coordination coefficient between any two dimensions. The calculation method for the coordination coefficient includes correlation coefficients, etc. A positive coordination coefficient indicates that the feature changes in the same direction, while a negative coordination coefficient indicates that the feature changes in opposite directions.

[0084] Step 163: Based on the change synergy coefficient, generate a matrix whose rows and columns correspond to the dimensions of the normalized feature vectors, and whose elements are the dimensional correlation matrices of the change synergy coefficients of the two corresponding dimensional features.

[0085] The computer equipment first determines the number of dimensions of the normalized feature vector, for example, the normalized feature vector has n dimensions. Next, it generates a dimensionality correlation matrix based on the coefficients of variation. The dimensionality correlation matrix has n rows and n columns, and its elements are the coefficients of variation between corresponding two dimensional features. For example, the element in the i-th row and j-th column of the dimensionality correlation matrix is ​​the coefficient of variation between dimensional feature i and dimensional feature j. Then, the dimensionality correlation matrix is ​​validated to ensure the accuracy and consistency of its elements.

[0086] Step 164: Obtain the preset degradation state pattern library in the state recognition model. The degradation state pattern library contains standard dimension correlation matrices and standard feature vector templates corresponding to different degradation stages. Each degradation stage corresponds to a unique combination of standard patterns.

[0087] Step 1641: Collect historical waste degradation data from multiple different landfills, and select valid historical data containing complete degradation cycles and certified monitoring information from the historical waste degradation data. The valid historical data includes historical component composition information, historical environmental monitoring parameters, historical dynamic evolution data, and corresponding actual degradation status records.

[0088] The computer equipment first collects historical waste degradation data from multiple different landfills through a data acquisition module. This historical data includes historical component composition information, historical environmental monitoring parameters, historical dynamic evolution data, and corresponding records of actual degradation status. The historical waste degradation data is then further filtered based on criteria such as including a complete degradation cycle and certified monitoring information. A complete degradation cycle includes the entire process from landfill to completion of degradation, and certified monitoring information includes monitoring data certified by authoritative institutions. Finally, the filtered historical waste degradation data is determined as valid historical data. Valid historical data includes historical component composition information, historical environmental monitoring parameters, historical dynamic evolution data, and corresponding records of actual degradation status.

[0089] Step 1642: Perform feature association analysis to extract the historical dynamic evolution data in the effective historical data, and generate a historical waste degradation state feature vector. The features of each dimension of the historical waste degradation state feature vector are associated with the historical key change information.

[0090] The computer equipment first extracts historical dynamic evolution data from valid historical data. This data includes sub-data on historical component changes, historical environmental factor responses, and historical degradation product generation. Further, feature association analysis is performed on the historical dynamic evolution data. The method for feature association analysis is the same as that described in step 150, including data preprocessing, feature association analysis, and feature organization, generating a feature vector of historical waste degradation states. Then, key historical change information is identified, including historical component changes, historical environmental factor responses, and historical degradation product generation.

[0091] Step 1643: Classify the historical waste degradation state feature vectors according to the actual degradation state records to obtain a set of historical feature vectors for each degradation stage, with each category corresponding to a degradation stage.

[0092] The computer equipment first extracts actual degradation status records from valid historical data, including the initial, intermediate, and final stages of waste degradation. Next, based on these records, the historical waste degradation status feature vectors are classified. For example, feature vectors belonging to the initial stage are grouped into one category, those belonging to the intermediate stage into another, and those belonging to the final stage into yet another, resulting in a set of historical feature vectors for each degradation stage. Finally, the set of historical feature vectors for each stage is validated to ensure accurate classification without errors or omissions.

[0093] Step 1644: Normalize the historical waste degradation state feature vectors in the historical feature vector set of each degradation stage to obtain a normalized historical feature vector subset for each degradation stage.

[0094] The computer equipment first extracts historical waste degradation state feature vectors from the historical feature vector set of each degradation stage. The historical waste degradation state feature vectors are then normalized using the same method as described in step 161, including min-max normalization, z-score normalization, etc., to obtain a normalized subset of historical feature vectors for each degradation stage.

[0095] Step 1645: For each normalized historical feature vector subset, calculate the mean and standard deviation of the dimensional features of all normalized historical feature vectors in the subset. Generate a standard feature vector template for this degradation stage with the mean of the dimensional features as the core and the standard deviation as the fluctuation range. The standard feature vector template reflects the typical distribution of feature vectors in this degradation stage.

[0096] The computer equipment first extracts all normalized historical feature vectors from the normalized historical feature vector subsets of each degradation stage. Next, it calculates the mean and standard deviation of each normalized historical feature vector's dimensional features. The mean of a dimensional feature is the average value of that feature across all normalized historical feature vectors, and the standard deviation represents the dispersion of that feature across all normalized historical feature vectors. Then, using the mean of the dimensional features as the core and the standard deviation as the fluctuation range, a standard feature vector template for that degradation stage is generated. Each dimensional feature value in the standard feature vector template is the mean of the dimensional feature, and the fluctuation range is the mean plus or minus the standard deviation.

[0097] Step 1646: Calculate the change synergy coefficient for any two normalized historical feature vectors in each normalized historical feature vector subset to obtain the set of historical dimension correlation matrices for this degradation stage.

[0098] The computer device first extracts any two normalized historical feature vectors from the subset of normalized historical feature vectors for each degradation stage. Next, it calculates the change coordination coefficient between these two normalized historical feature vectors. The calculation method for the change coordination coefficient is the same as that described in step 162, including extracting the rate and direction of change of each dimension feature and calculating the change coordination coefficient between any two dimension features. Then, the calculated change coordination coefficients are used to form a historical dimension correlation matrix. The number of rows and columns in the historical dimension correlation matrix is ​​equal to the number of dimensions of the normalized historical feature vectors, and the matrix elements are the change coordination coefficients of corresponding two dimension features. All calculated historical dimension correlation matrices are integrated to obtain the set of historical dimension correlation matrices for that degradation stage.

[0099] Step 1647: Calculate the mean of the elements of all historical dimension association matrices in the set of historical dimension association matrices, and generate the standard dimension association matrix for this degradation stage. The standard dimension association matrix reflects the typical association relationships of each dimension feature in this degradation stage.

[0100] The computer device first extracts all historical dimensional association matrices from the set of historical dimensional association matrices for this degradation stage. Next, it calculates the mean of each element in all historical dimensional association matrices; the mean is the average of the element across all historical dimensional association matrices. Then, it uses these calculated mean values ​​to construct a standard dimensional association matrix. The number of rows and columns in the standard dimensional association matrix equals the number of dimensions in the normalized historical feature vectors, and the matrix elements are the mean values ​​of the corresponding two dimensional features.

[0101] Step 1648: Combine the standard feature vector template of each degradation stage with the corresponding standard dimension association matrix to obtain the standard pattern combination of that degradation stage.

[0102] The computer equipment first extracts corresponding data from the standard feature vector templates and standard dimensional correlation matrices of each degradation stage. Next, it combines the standard feature vector templates of each degradation stage with the corresponding standard dimensional correlation matrices to obtain the standard pattern combination for that degradation stage. The standard pattern combination includes the standard feature vector template and the corresponding standard dimensional correlation matrix.

[0103] Step 1649: Establish an index directory based on the standard pattern combinations of all collected degradation stages; wherein the index directory uses the name of the degradation stage as the index keyword, which points to the standard pattern combination of the degradation stage, and integrates the index directory with the standard pattern combinations to generate the degradation state pattern library.

[0104] The computer equipment first determines the names of all degradation stages, such as the initial stage of waste degradation, the intermediate stage of waste degradation, and the final stage of waste degradation. Next, using the degradation stage names as index keywords, an index directory is created, where each index keyword points to a standard pattern combination for that degradation stage. Then, the index directory and the standard pattern combinations are integrated to generate a degradation state pattern library, which includes the index directory and the corresponding standard pattern combinations.

[0105] Step 16410: Set up an update interface for the degradation state pattern library and import new valid historical data according to a set cycle to update the standard pattern combinations in the pattern library.

[0106] The computer equipment first sets up an update interface for the degradation state pattern library. This interface includes a data import interface and a data processing interface, used to import new, valid historical data and update the standard pattern combinations in the library. Next, a set period is determined, which may be monthly or yearly. Then, new, valid historical data is imported according to the set period. This new data includes newly collected historical waste degradation data containing complete degradation cycles and certified monitoring information. The updated interface processes the imported new, valid historical data to update the standard pattern combinations in the library.

[0107] Step 165: Perform similarity matching between the dimensional correlation matrix and each standard dimensional correlation matrix in the degradation state pattern library to calculate the matrix similarity; and perform feature matching between the normalized feature vector and the corresponding standard feature vector template to calculate the feature matching degree.

[0108] The computer device first extracts the standard dimensional correlation matrices from the degradation state pattern library. Next, it performs similarity matching between the dimensional correlation matrices and the standard dimensional correlation matrices, using methods such as cosine similarity and Euclidean distance to calculate the matrix similarity, which represents the degree of similarity between the dimensional correlation matrices and the standard dimensional correlation matrices. Then, it extracts the corresponding standard feature vector templates from the degradation state pattern library and performs feature matching between the normalized feature vectors and the corresponding standard feature vector templates, using methods such as cosine similarity and Euclidean distance to calculate the feature matching degree, which represents the degree of similarity between the normalized feature vectors and the corresponding standard feature vector templates.

[0109] Step 166: According to the preset comprehensive matching degree calculation rules, the matrix similarity and the feature matching degree are weighted and summed according to a preset ratio to obtain the comprehensive matching degree. The target standard pattern combination with the highest comprehensive matching degree is selected, and the degradation stage corresponding to the target standard pattern combination is determined as the preliminary identification result.

[0110] The computer equipment first determines the preset comprehensive matching degree calculation rules, which include weighted summation of matrix similarity and feature matching degree according to preset ratios. Next, it calculates the comprehensive matching degree according to the preset rules: Comprehensive matching degree = (Matrix similarity × Weight 1) + (Feature matching degree × Weight 2), where Weight 1 and Weight 2 are preset ratios, and Weight 1 + Weight 2 = 1. Then, it selects the target standard pattern combination with the highest comprehensive matching degree; this target standard pattern combination is the standard pattern combination with the highest comprehensive matching degree. The degradation stage corresponding to the target standard pattern combination is determined as the preliminary identification result, including the initial stage of waste degradation, the middle stage of waste degradation, and the later stage of waste degradation.

[0111] Step 167: Perform stage feature verification on the preliminary identification results. Check whether the degradation stage features corresponding to the preliminary identification results correspond to the key change information in the dynamic evolution data. If they correspond, output the preliminary identification results as the waste degradation state identification results. If they do not correspond, return to perform dimensional correlation analysis and pattern matching processing again.

[0112] The computer system first extracts corresponding degradation stage features from the preliminary identification results. These features include the degradation changes of each component, the response values ​​of environmental factors, and the amount of degradation products generated. Next, it extracts key change information from the dynamic evolution data, including the degradation changes of each component, the response values ​​of environmental factors, and the amount of degradation products generated. Then, it checks whether the degradation stage features corresponding to the preliminary identification results correspond to the key change information in the dynamic evolution data. A correspondence is indicated when the degradation changes of each component in the degradation stage features match those in the key change information, when the response values ​​of environmental factors in the degradation stage features match those in the key change information, and when the amount of degradation products generated in the degradation stage features matches that in the key change information. If a correspondence is found, the preliminary identification result is output as the waste degradation state identification result. If a correspondence is not found, the system returns to perform dimensional correlation analysis and pattern matching processing again until the degradation stage features corresponding to the preliminary identification results correspond to the key change information in the dynamic evolution data.

[0113] Step 170: After outputting the waste degradation status identification result of the landfill, obtain the historical degradation status data and the environmental intervention records of the same period corresponding to the waste degradation status identification result, compare the features of the waste degradation status identification result and the historical degradation status data, and extract multidimensional deviation information in the dimensions of degradation degree, rate and trend.

[0114] The computer equipment first retrieves historical degradation status data and concurrent environmental intervention records corresponding to the waste degradation status identification results from the database. The historical degradation status data includes historical waste degradation status feature vectors and historical degradation stages, while the concurrent environmental intervention records include environmental control measures and control periods. Next, the waste degradation status identification results are compared with the historical degradation status data using methods such as correlation analysis and difference analysis. This comparison extracts multidimensional deviation information in the dimensions of degradation degree, rate, and trend. The multidimensional deviation information includes deviations in degradation degree, degradation rate, and degradation trend.

[0115] Step 171: Associate and map the multidimensional deviation information with the concurrent environmental intervention records to identify the key intervention factors and intervention intensity characteristics that lead to the deviation, and generate deviation intervention correlation data.

[0116] The computer equipment first extracts the type and degree of deviation from the multidimensional deviation information. Deviation types include degradation degree deviation, degradation rate deviation, and degradation trend deviation, while deviation degree includes the magnitude of the deviation. Next, it extracts environmental intervention factors and intervention intensity from contemporaneous environmental intervention records. Environmental intervention factors include temperature control and humidity control, while intervention intensity includes the degree of control. Then, it performs a correlation mapping between the multidimensional deviation information and the contemporaneous environmental intervention records. Correlation mapping methods include correlation analysis and causal analysis to identify key intervention factors and intervention intensity characteristics that lead to the deviation. Key intervention factors are the main environmental intervention factors causing the deviation, and intervention intensity characteristics are the magnitude of the intervention intensity of the key intervention factors. Finally, the identified key intervention factors and intervention intensity characteristics are integrated to generate deviation intervention correlation data.

[0117] Step 172: Determine the feature correction space based on the deviation intervention correlation data, import the state identification feature vector corresponding to the waste degradation state identification result into the feature correction space, and adjust each dimension of the state identification feature vector through deviation compensation processing to obtain the corrected degradation state feature vector.

[0118] The computer equipment first extracts key intervention factors and intervention intensity features from the deviation intervention correlation data. Next, it determines a feature correction space based on these factors and intensity features, including the correction range for each dimension of the features. Then, the state identification feature vector corresponding to the waste degradation state identification results is imported into the feature correction space; this vector includes the values ​​of each dimension of the features. Deviation compensation processing is then applied to adjust each dimension of the state identification feature vector. This adjustment includes adjusting the values ​​of each dimension based on the key intervention factors and intensity features, resulting in a corrected degradation state feature vector. The corrected feature vector more accurately reflects the waste degradation state.

[0119] Step 173: Input the corrected degradation state feature vector back into the multiphysics virtual simulation model to trigger the adaptive update of the model parameters, so that the updated multiphysics virtual simulation model outputs dynamic evolution update data that matches the actual degradation state.

[0120] The computer system first preprocesses the corrected degradation state feature vector, including data cleaning and standardization, to ensure accuracy and consistency. Next, the preprocessed, corrected degradation state feature vector is input back into the multiphysics virtual simulation model, triggering adaptive updates to the model parameters, including parameters from the degradation kinetics model and the material transformation model. Then, the multiphysics virtual simulation model adaptively updates its parameters based on the back-input corrected degradation state feature vector, making the model parameters more accurately reflect the waste degradation state. The updated multiphysics virtual simulation model outputs dynamically updated data that matches the actual degradation state. This data includes changes in the degradation of each component, responses to environmental factors, and the amount of degradation products generated, all matching the actual degradation state.

[0121] Step 180: After outputting the waste degradation status identification result of the landfill, call the preset degradation product environmental impact association library, match the waste degradation status identification result with the degradation stage impact mapping relationship in the degradation product environmental impact association library, and extract the potential environmental impact type and impact range characteristics corresponding to the waste degradation status identification result.

[0122] The computer equipment first accesses a pre-defined environmental impact association library for degradation products. This library includes potential environmental impact types and impact range characteristics corresponding to different degradation stages. Next, it analyzes the library to determine the degradation stage impact mapping relationships. These mapping relationships represent the relationship between different degradation stages and their corresponding potential environmental impact types and impact range characteristics. Then, the waste degradation status identification results are matched with the degradation stage impact mapping relationships in the environmental impact association library. Matching methods include keyword matching and similarity matching. The potential environmental impact types and impact range characteristics corresponding to the waste degradation status identification results are extracted. Potential environmental impact types include air pollution and water pollution, and impact range characteristics include the affected geographical area.

[0123] Step 181: Collect basic monitoring data of the surrounding environment of the landfill, align the basic monitoring data with the potential environmental impact types in terms of dimensions, and generate an environmental impact assessment feature set through feature fusion processing. The environmental impact assessment feature set contains the correlation data between impact factors and environmental responses.

[0124] The computer equipment first collects basic monitoring data of the environment surrounding the landfill through the environmental monitoring module. This basic monitoring data includes air quality monitoring data and water quality monitoring data. Further data preprocessing is performed on the basic monitoring data, including data cleaning and standardization, to ensure data accuracy and consistency. Then, the preprocessed basic monitoring data is dimensionally aligned with potential environmental impact types. Dimensional alignment methods include matching the dimensions of the basic monitoring data with the dimensions of the potential environmental impact types. An environmental impact assessment feature set is generated through feature fusion processing. Feature fusion processing methods include principal component analysis and factor analysis. The environmental impact assessment feature set contains correlation data between impact factors and environmental responses. Impact factors include air pollutant concentrations and water pollutant concentrations, while environmental responses include changes in air quality and water quality.

[0125] Step 182: Input the environmental impact assessment feature set into the environmental risk classification model, and output the environmental risk level and risk-dominant factor corresponding to the waste degradation state through feature weight allocation and risk threshold comparison.

[0126] The computer equipment first preprocesses the environmental impact assessment feature set, including data cleaning and standardization, to ensure data accuracy and consistency. Next, the preprocessed feature set is input into an environmental risk grading model, which includes a feature weight allocation module and a risk threshold comparison module. Then, the feature weight allocation module assigns weights to each feature in the environmental impact assessment feature set using methods such as the analytic hierarchy process (AHP) and entropy weighting. The weight allocation results reflect the degree of influence of each feature on environmental risk. Finally, the risk threshold comparison module compares the values ​​of each feature in the environmental impact assessment feature set with preset risk thresholds, outputting the environmental risk level and dominant risk factor corresponding to the waste degradation state. Environmental risk levels include low risk, medium risk, and high risk, and the dominant risk factor is the main influencing factor leading to environmental risk.

[0127] Step 183: Based on the environmental risk level and the risk-dominant factor, match the corresponding combination of intervention measures from the preset control strategy library to generate a waste degradation control scheme that includes the implementation sequence of measures, target objects and expected effects. The output parameters of the waste degradation control scheme are used as environmental factor inputs to the multiphysics virtual simulation model.

[0128] The computer equipment first extracts intervention combination combinations from a pre-set control strategy library, which includes intervention combination combinations corresponding to different environmental risk levels and risk-dominant factors. Next, it matches corresponding intervention combination combinations from the control strategy library based on the environmental risk level and risk-dominant factors, using methods such as keyword matching and similarity matching. Then, the matched intervention combination combinations are processed to generate a waste degradation control scheme that includes the implementation sequence of measures, the target of the intervention, and the expected effects. The implementation sequence includes the order in which the intervention measures are implemented; the target includes the objectives of the intervention; and the expected effects include the anticipated effects of the intervention. The output parameters of the waste degradation control scheme are used as environmental factor inputs to a multiphysics virtual simulation model, ensuring that the multiphysics virtual simulation model can adjust according to the waste degradation control scheme and output more accurate dynamic evolution data.

[0129] Step 190: After outputting the waste degradation status identification results of the landfill, collect spatial location data of different areas of the landfill and the corresponding waste degradation status identification results, and couple the spatial location data with the waste degradation status identification results to generate spatial status association data. The spatial status association data includes degradation stage distribution information of different coordinate points.

[0130] The computer equipment first collects spatial location data for different areas of the landfill through a spatial positioning module. This spatial location data includes coordinate information for each area. Next, it collects corresponding waste degradation status identification results through a waste degradation status identification module. These results include the degradation stages of waste in different areas. Then, the spatial location data and the waste degradation status identification results are coupled. Coupling methods include associating and storing the spatial location data and the waste degradation status identification results to generate spatial status association data. This spatial status association data contains degradation stage distribution information for different coordinate points.

[0131] Step 191: Perform spatial interpolation on the spatial state correlation data to complete the degradation state characteristics of unmonitored areas and generate a spatial distribution map of the global waste degradation state. Each spatial unit in the spatial distribution map of the global waste degradation state is labeled with the corresponding degradation state identification result and feature confidence level.

[0132] The computer equipment first extracts the spatial location data of the monitored areas and the corresponding waste degradation status identification results from the spatial state correlation data. Further spatial interpolation processing is performed on the spatial state correlation data, using methods such as Kriging interpolation and inverse distance weighted interpolation, to complete the degradation status characteristics of unmonitored areas. Unmonitored areas are those areas in the landfill where no waste degradation status identification results were collected. Then, a global waste degradation status spatial distribution map is generated, which includes the waste degradation status identification results and feature confidence scores for all areas of the landfill. The feature confidence score represents the reliability of the waste degradation status identification results.

[0133] Step 192: Extract spatial correlation features from the spatial distribution map of the global waste degradation state, identify the spatial diffusion pattern and aggregation area characteristics of the degradation state, and generate spatial evolution trend data.

[0134] The computer equipment first extracts spatial correlation features from the spatial distribution map of waste degradation status across the entire region. These features include the correlation between waste degradation status in different areas. Further analysis of these spatial correlation features is conducted using methods such as spatial autocorrelation analysis and cluster analysis to identify the spatial diffusion patterns and aggregation characteristics of waste degradation status. Spatial diffusion patterns refer to the way waste degradation status spreads within landfills, while aggregation characteristics identify the areas where waste degradation status accumulates within landfills. Then, the identified spatial diffusion patterns and aggregation characteristics are integrated to generate spatial evolution trend data, which is represented in the form of time-series data.

[0135] Step 193: Combine the spatial evolution trend data with the waste degradation state identification results, and use time-series prediction processing to deduce the trajectory of global degradation state changes within a preset period, and output a waste degradation state prediction report including regional early warning and evolution nodes.

[0136] The computer equipment first combines spatial evolution trend data with the waste degradation status identification results. This combination method includes associating and storing the spatial evolution trend data with the waste degradation status identification results. Next, it uses time-series predictive processing to extrapolate the overall degradation status change trajectory within a preset period. The time-series predictive processing methods include time series prediction algorithms and regression analysis algorithms, with preset periods including months and years. Then, based on the extrapolated overall degradation status change trajectory, it outputs a waste degradation status prediction report that includes regional early warnings and evolution nodes. Regional early warnings identify areas in the landfill that require key attention, and evolution nodes represent critical time points where the waste degradation status changes.

[0137] This application's embodiments start from the essential driving factors of waste degradation and construct a technology chain covering component attributes, environmental interaction, dynamic simulation, feature extraction, and state recognition. It breaks through the limitations of traditional waste degradation state recognition that relies only on single monitoring data or static models, and realizes multi-dimensional, dynamic, and precise simulation and recognition of the waste degradation process, thereby improving the accuracy and real-time performance of waste degradation state recognition.

[0138] Based on the same inventive concept, embodiments of this application also provide a computer device. See also... Figure 2 As shown, it is a schematic diagram of the structure of a possible computer device provided in an embodiment of this application. Figure 2 In this system, computer device 200 includes a processor 210 and a memory 220. The processor 210 and the memory 220 are interconnected via a communication bus. The memory 220 stores computer programs that can be executed by the processor 210. By executing the instructions stored in the memory 220, the processor 210 can perform the steps of the aforementioned method for modeling and identifying the degradation status of landfill waste based on virtual simulation.

[0139] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium including a computer program. When the computer program is run on a computer device, it causes the computer device to perform the steps of the aforementioned virtual simulation-based landfill waste degradation state modeling and identification method. In some possible implementations, various aspects of the virtual simulation-based landfill waste degradation state modeling and identification method provided in this application can also be implemented as a program product, including a computer program. When the program product is run on a computer device, it causes the computer device to perform the steps of the aforementioned virtual simulation-based landfill waste degradation state modeling and identification method. For example, the computer device can perform actions such as... Figure 1The steps are shown in the diagram. The computer-readable storage medium includes volatile or non-volatile or a combination thereof, and may be removable or non-removable. Examples of computer-readable storage media include, but are not limited to, phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random-access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), flash memory or other memory technologies, CD-ROM, Digital Video Disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium.

[0140] like Figure 3 The diagram shown is a functional block diagram of the computer device provided in this application embodiment. The computer device includes a virtual simulation-based landfill waste degradation state modeling and identification device, which includes: The multidimensional data acquisition module is used to collect information on the composition of landfill waste and the physicochemical properties of each component. Based on the interaction modes and influence relationships between different environmental factors in the landfill, the dynamic interaction rules of environmental factors are determined. The monitoring parameter acquisition module is used to acquire real-time environmental monitoring parameters of the landfill through the corresponding monitoring equipment cluster according to the type of environmental factor in the dynamic interaction rules of the environmental factors. The simulation model creation module is used to create a multiphysics virtual simulation model for landfill waste degradation analysis by combining the component composition information, the physicochemical properties of each component and the dynamic interaction rules of the environmental factors. The dynamic evolution analysis module is used to import the real-time environmental monitoring parameters into the multiphysics virtual simulation model, and output dynamic evolution data of the waste degradation process through collaborative computation. The dynamic evolution data includes key change information on the changes of each component, environmental factor response and degradation product generation during the waste degradation process. The degradation state extraction module is used to extract a waste degradation state feature vector reflecting the degree of waste degradation, degradation rate and degradation trend based on the dynamic evolution data through feature association analysis. The features of each dimension of the waste degradation state feature vector are associated with the key change information. The degradation state identification module is used to input the waste degradation state feature vector into a preset state identification model, and output the waste degradation state identification result of the landfill by performing dimensional correlation analysis and pattern matching processing on the waste degradation state feature vector. The waste degradation state identification result corresponds to the characteristics of different stages of waste degradation.

[0141] Accordingly, this application also provides a computer program product, which includes a computer program or instructions that, when executed by a processor, cause the processor to implement the steps in the above method embodiments. It should be understood that each step or combination of steps in the above method flow can be implemented by the computer program or instructions. Furthermore, these computer programs or instructions can be applied to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device, enabling the processor of the general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to function as an apparatus for implementing the corresponding functions in the above method embodiments.

[0142] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0143] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0144] Finally, it should be noted that the above are merely embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for modeling and identifying the degradation state of landfill waste based on virtual simulation, characterized in that, The method includes: Collect information on the composition of landfill waste and the physicochemical properties of each component, and determine the dynamic interaction rules of environmental factors based on the interaction modes and influence relationships between different environmental factors in the landfill. Based on the type of environmental factor in the dynamic interaction rules of the environmental factors, real-time environmental monitoring parameters of the landfill are collected through the corresponding monitoring equipment cluster; Combining the component composition information, the physicochemical properties of each component, and the dynamic interaction rules of the environmental factors, a multiphysics virtual simulation model for landfill waste degradation analysis is created: A correlation analysis is performed on the proportion and form of each component in the component composition information; combined with the reactivity and stability characteristics of each component's physicochemical properties, a component correlation feature set is generated; the influence weight and priority of each environmental factor are extracted from the dynamic interaction rules of the environmental factors; the environmental factors are then stratified according to the influence weight and priority to obtain an environmental factor hierarchical structure; a component degradation sub-model is constructed based on the component correlation feature set, which describes the degradation behavior of a single component in an isolated environment; based on the environmental... An environmental sub-model is constructed using a factor hierarchy structure. This sub-model describes the regulatory strategies of different levels of environmental factors on degradation behavior. A coupling interface is established between the component degradation sub-model and the environmental sub-model. This interface enables bidirectional transmission and real-time adaptation of component degradation data and environmental data. The component degradation sub-model and the environmental sub-model are integrated through this coupling interface. Triggering conditions and data interaction frequencies for collaborative model operation are set to generate the multiphysics virtual simulation model. The integrated multiphysics virtual simulation model is initialized by inputting the basic parameters from the component association feature set and the initial conditions from the environmental factor hierarchy structure into the multiphysics virtual simulation model. The real-time environmental monitoring parameters are imported into the multiphysics virtual simulation model, and the dynamic evolution data of the waste degradation process is simulated and output through collaborative computation. The dynamic evolution data includes key change information on the changes of each component, the response of environmental factors, and the generation of degradation products during the waste degradation process. Based on the dynamic evolution data, feature vectors reflecting the degree, rate and trend of waste degradation are extracted through feature correlation analysis. The features of each dimension of the waste degradation state feature vector are correlated with the key change information. The waste degradation state feature vector is input into a preset state recognition model. By performing dimensional correlation analysis and pattern matching on the waste degradation state feature vector, the waste degradation state recognition result of the landfill is output. The waste degradation state recognition result corresponds to the different stages of waste degradation. The process of integrating the component degradation sub-model and the environmental action sub-model through the coupling interface, setting the trigger conditions and data interaction frequency for model collaborative operation, and generating the multiphysics virtual simulation model includes: The interaction data between the component degradation sub-model and the environmental action sub-model in historical degradation simulation is collected through the coupling interface. The interaction data is then processed by a feature association mining algorithm to extract rules, identify the triggering timing, data type matching rules and response delay characteristics of data requests between sub-models under different degradation scenarios, and obtain a set of sub-model interaction rules. Based on the set of sub-model interaction rules, a sub-model interaction logic mapping table is constructed. The corresponding relationship between the output parameter types of the component degradation sub-model and the input requirements of the environmental action sub-model is established. The scenario adaptation range corresponding to each relationship is marked to determine the scenario orientation of data interaction between sub-models. The semantic parsing module parses the operational status description information of the component degradation sub-model, extracts key status features reflecting changes in the degradation process, and associates and matches these key status features with the activation conditions of the regulation strategy of the environmental action sub-model to generate a collaborative operation trigger condition library. Based on the statistical results of data transmission frequency in the set of interaction patterns of the sub-models, and combined with the trend prediction algorithm, the changing trend of data demand of the sub-models under different degradation stages is analyzed, and a dynamic data interaction frequency adjustment strategy is generated. The dynamic data interaction frequency adjustment strategy adjusts the time interval of data interaction in real time according to the parameter update rate of the component degradation sub-model and the regulation response efficiency of the environmental action sub-model. The sub-model interaction logic mapping table, the collaborative operation trigger condition library, and the dynamic data interaction frequency adjustment strategy are imported into the integrated model and transformed into collaborative operation instructions to be identified by the sub-model through the logic compilation module, thereby completing the integration of the component degradation sub-model and the environmental action sub-model. The integrated model was tested in multiple scenarios through simulation and deduction. During the test, the interaction stability data and logical conflict information of the sub-models were collected. The logical nodes that caused the conflict were located by combining feature association analysis. The interaction logic mapping table of the sub-models and the collaborative operation trigger condition library were iteratively corrected based on the parameter optimization algorithm. After the correction is completed, the target integration rules and operating parameters are solidified to generate a multiphysics virtual simulation model with autonomous collaborative capabilities; wherein, the target integration rules include at least the iteratively corrected sub-model interaction logic mapping table and the collaborative operation trigger condition library.

2. The method as described in claim 1, characterized in that, The step of importing the real-time environmental monitoring parameters into the multiphysics virtual simulation model and simulating and outputting dynamic evolution data of the waste degradation process through collaborative computation includes: The real-time environmental monitoring parameters are classified and organized according to the type of environmental factors, and the real-time environmental monitoring parameters are divided into different parameter subsets, each parameter subset corresponding to the monitoring data of a type of environmental factor. Set data preprocessing rules for each parameter subset, and use these rules to remove outlier data points from the parameter subset while retaining valid monitoring data that meets the model input requirements. According to the hierarchical structure of the environmental action sub-model in the multiphysics virtual simulation model, the corresponding effective monitoring data are sequentially imported into the environmental action sub-model at each level, and the collaborative operation strategy of the multiphysics virtual simulation model is activated, triggering data interaction between the component degradation sub-model and the environmental action sub-model. Real-time transmission of degradation behavior data and environmental regulation data is achieved through the coupling interface. Cooperative computation is performed based on a preset time step. Within each time step, the degradation change of each component, the response value of environmental factors, and the amount of degradation products generated are calculated. Intermediate data during the computation process are recorded to obtain the computation results for each time step. For the calculation results at each time step, the key change information of each component change, environmental factor response and degradation product generation is organized according to time series to obtain staged evolution data fragments; By concatenating and integrating evolutionary data fragments of all time steps and supplementing the correlation information between each evolutionary data fragment, dynamic evolutionary data of the waste degradation process is generated.

3. The method as described in claim 1, characterized in that, The step of extracting a waste degradation state feature vector reflecting the degree, rate, and trend of waste degradation based on the dynamic evolution data through feature correlation analysis includes: The dynamic evolution data is decomposed into component change sub-data, environmental factor response sub-data, and degradation product generation sub-data, with each sub-data corresponding to a time-series record of a type of key change information; Correlation analysis is performed on the content change trajectories of each component in the component change sub-data to identify synergistic or inhibitory degradation relationships between different components and generate component correlation features; trend analysis is performed on the environmental factor numerical fluctuation trajectory in the environmental factor response sub-data to capture the immediate and delayed effects of environmental factors on degradation behavior and generate environmental response features; and regularity mining is performed on the product types and generation trajectories in the degradation product generation sub-data to extract the correspondence between product generation and component degradation and generate product correlation features. The component association features, the environmental response features, and the product association features are imported into the feature association space to generate a feature association graph. In the feature association graph, nodes represent each feature, and edges represent the association strength between features. By combining the degree of waste degradation, degradation rate and degradation trend, core features that meet the correlation conditions are determined from the feature correlation map and a core feature set is generated; Each feature in the core feature set is classified and sorted according to a preset dimension, and each feature is assigned a dimension weight that matches the correlation strength. The waste degradation state feature vector is generated through the normalization of the feature dimensions. Each dimension feature of the waste degradation state feature vector corresponds to a core feature expression of a key change information.

4. The method as described in claim 3, characterized in that, The step of importing the component association features, the environmental response features, and the product association features into a feature association space to generate a feature association graph, where nodes represent features and edges represent the association strength between features, includes: A three-dimensional feature association space is created using the component degradation dimension, environmental action dimension, and product generation dimension as spatial coordinate axes. The component association features, environmental response features, and product association features are mapped to the coordinate axes of the corresponding dimensions to obtain the initial coordinate points of the features. Calculate the spatial distance and feature attribute similarity between any two initial coordinate points of features; where spatial distance reflects the physical correlation between features, and feature attribute similarity reflects the consistency of features in data variation patterns. A rule for calculating the association strength is set, and the product of the reciprocal of the spatial distance and the similarity of the feature attributes is used as the initial association strength between features. The initial association strength is then normalized to obtain the standardized association strength. Using the initial coordinates of each feature as a feature node, establish an association edge between two feature nodes whose standardized association strength is greater than the preset association strength, and label the corresponding standardized association strength value on the association edge to obtain the initial feature association map; Traverse each feature node in the initial feature association graph and check whether there is a conflict between the feature node and its adjacent feature nodes. A conflict is manifested as the same feature node having a strong association with two feature nodes with opposite semantics. If a conflict exists, the standardized association strength of the conflict-related edges is recalculated. During the calculation, the frequency weight of the features in the dynamically evolving data is introduced. The higher the frequency of a feature, the greater its weight. The standardized association strength is corrected by adjusting the weight. The initial feature association graph is updated by retaining the association edges with higher correlation strength after correction and deleting the association edges with lower correlation strength after correction and standardization, until there are no conflicting association edges in the initial feature association graph. The feature association graph is used to present the effective association relationships and association strengths between each feature.

5. The method as described in claim 1, characterized in that, The step of inputting the waste degradation state feature vector into a preset state recognition model, and outputting the waste degradation state recognition result of the landfill by performing dimensional correlation analysis and pattern matching on the waste degradation state feature vector, includes: The features of each dimension of the waste degradation state feature vector are normalized to obtain a normalized feature vector; The dimensional correlation analysis sub-model in the state recognition model is invoked to extract the rate of change and direction of change of each dimension feature in the normalized feature vector. The change coordination coefficient between any two dimension features is calculated. A positive coordination coefficient indicates that the feature change trends are consistent, and a negative coordination coefficient indicates that the feature change trends are opposite. Based on the aforementioned change synergy coefficients, a matrix is ​​generated in which both rows and columns correspond to the dimensions of the normalized feature vectors, and the matrix elements are dimension correlation matrices of the change synergy coefficients corresponding to the two dimensional features. Obtain a preset degradation state pattern library in the state recognition model. The degradation state pattern library contains standard dimension correlation matrices and standard feature vector templates corresponding to different degradation stages. Each degradation stage corresponds to a unique combination of standard patterns. The dimensional correlation matrix is ​​matched with each standard dimensional correlation matrix in the degradation state pattern library to calculate the matrix similarity; and the normalized feature vector is matched with the corresponding standard feature vector template to calculate the feature matching degree. According to the preset comprehensive matching degree calculation rules, the matrix similarity and the feature matching degree are weighted and summed according to a preset ratio to obtain the comprehensive matching degree. The target standard pattern combination with the highest comprehensive matching degree is selected, and the degradation stage corresponding to the target standard pattern combination is determined as the preliminary identification result. The preliminary identification results are verified by stage features. It is checked whether the degradation stage features corresponding to the preliminary identification results correspond to the key change information in the dynamic evolution data. If they correspond, the preliminary identification results are output as the waste degradation state identification results. If they do not correspond, the process is returned to perform dimensional correlation analysis and pattern matching again.

6. The method as described in claim 5, characterized in that, The step involves acquiring a preset degradation state pattern library in the state recognition model. This library contains standard dimensional correlation matrices and standard feature vector templates corresponding to different degradation stages. Each degradation stage corresponds to a unique combination of standard patterns, including: Collect historical waste degradation data from multiple different landfills, and filter out valid historical data containing complete degradation cycles and certified monitoring information from the historical waste degradation data. The valid historical data includes historical component composition information, historical environmental monitoring parameters, historical dynamic evolution data and corresponding actual degradation status records. Feature correlation analysis is performed on the historical dynamic evolution data in the effective historical data to extract historical waste degradation state feature vectors. The features of each dimension of the historical waste degradation state feature vectors are correlated with the key historical change information. The historical waste degradation state feature vectors are classified according to the actual degradation state records to obtain a set of historical feature vectors for each degradation stage, with each category corresponding to a degradation stage. Normalize the historical waste degradation state feature vectors in the historical feature vector set of each degradation stage to obtain a normalized historical feature vector subset for each degradation stage; For each normalized historical feature vector subset, calculate the mean and standard deviation of the dimensional features of all normalized historical feature vectors in the subset. Using the mean of the dimensional features as the core and the standard deviation as the fluctuation range, generate a standard feature vector template for this degradation stage. The standard feature vector template reflects the typical distribution of feature vectors in this degradation stage. For any two normalized historical feature vectors in each normalized historical feature vector subset, calculate the change synergy coefficient to obtain the set of historical dimension correlation matrices for that degradation stage; Calculate the mean of the elements of all historical dimension association matrices in the set of historical dimension association matrices, and generate the standard dimension association matrix for this degradation stage. The standard dimension association matrix reflects the typical association relationships of each dimension feature in this degradation stage. The standard feature vector template of each degradation stage is combined with the corresponding standard dimension association matrix to obtain the standard pattern combination of that degradation stage. An index directory is established based on the standard pattern combinations of all collected degradation stages; wherein, the index directory uses the name of the degradation stage as the index keyword, which points to the standard pattern combination of the degradation stage; the index directory and the standard pattern combinations are integrated to generate the degradation state pattern library. An update interface is set for the degradation state pattern library, and new valid historical data is imported according to a set period to update the standard pattern combinations in the pattern library.

7. A computer device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the virtual simulation-based landfill waste degradation state modeling and identification method according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a computer program that, when run on a computer device, causes the computer device to perform the steps of the virtual simulation-based landfill waste degradation state modeling and identification method according to any one of claims 1 to 6.

Images