Household garbage resourceful treatment method

Abstract

The invention discloses a household garbage resourceful treatment method. Efficient waste conversion is achieved by constructing an intelligent fuel preparation system. The method comprises the following steps: firstly, collecting garbage component characteristic data in real time by adopting a multi-source sensing technology, and establishing a calorific value prediction model in combination with a dynamic database and a machine learning algorithm; secondly, based on molecular structure characteristic analysis and a multi-objective optimization algorithm, intelligent screening and proportion optimization of the binder are achieved; then, a deep neural network is used for constructing a technological parameter prediction model, and dynamic regulation and control of the sintering process are achieved through a closed-loop feedback mechanism; and finally, comprehensive evaluation of the fuel quality is completed by combining a spectral analysis technology and a mechanical property test. According to the method, intelligent decision making of key links such as garbage component analysis, binder adaptation and process optimization is achieved in a data driving mode, and the technical problems that in a traditional method, heat value prediction is not accurate, the process adaptability is poor, and the product quality is not stable are effectively solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of domestic waste treatment, and particularly relates to a method for resource treatment of domestic waste. Background Art

[0002] Traditional methods for treating domestic waste, such as landfill and direct incineration, have significant drawbacks: landfill occupies land resources and is prone to secondary pollution, while incineration has unstable combustion efficiency and difficult pollutant emission control due to the complex composition and large physical property fluctuations of the waste. Although the existing Refuse Derived Fuel (RDF) technology improves the energy recovery efficiency through the preparation of formed fuels, the following technical bottlenecks still exist in its core links: 1. Insufficient accuracy in calorific value prediction: Traditional methods rely on static empirical models or single-sensor data, making it difficult to dynamically adapt to the real-time changes of key components such as moisture and volatile matter in the waste, resulting in large deviations in fuel calorific value prediction; 2. Low efficiency in binder adaptation: Existing binder screening mostly relies on manual experience or simple physical property matching, lacking quantitative analysis of key indicators such as chemical component compatibility and thermal stability, resulting in insufficient synergistic effect between the binder and the fuel matrix; 3. Coarse control of the sintering process: Fixed sintering parameters (such as temperature and pressure) are difficult to adapt to raw material fluctuations, resulting in unqualified fuel density and mechanical strength, affecting subsequent storage, transportation and combustion performance.

[0003] In addition, the existing technology lacks the systematic integration and closed-loop optimization ability of multi-dimensional data. For example, no real-time feedback mechanism is established to dynamically adjust process parameters, resulting in a lag in the production process response and unsatisfactory control of energy consumption and emissions.

[0004] In view of the above technical analysis, the technical problem to be solved by the present invention is: how to break through the above bottlenecks through an intelligent technology system, realize accurate prediction of calorific value, intelligent adaptation of binders and adaptive optimization of the sintering process in the process of domestic waste resource treatment, so as to comprehensively improve fuel quality, reduce pollution emissions, and form an efficient and stable resource treatment solution. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method for resource treatment of domestic waste. By integrating real-time data from multiple sensors with dynamic database matching and combining probability model analysis, high-precision prediction of the calorific value of domestic waste is achieved, overcoming the static defects of traditional empirical formulas and significantly improving the stability of fuel quality.

[0006] To solve the above technical problems, the technical solution adopted by the present invention is: A method for resource treatment of domestic waste, the steps are as follows: S1. Collect data on the moisture and volatile content in municipal solid waste in real time through sensors. Combine with the pre-established calorific value database to calculate the initial calorific value parameters of the solid formed fuel and obtain the fuel calorific value distribution characteristics. S1.1. Collect data on the moisture content and volatile content in municipal solid waste in real time through sensors to obtain the original data set. S1.2. Use a preprocessing algorithm to denoise and standardize the original data set to obtain the processed data set. S1.3. Obtain the reference data corresponding to the processed data set from the pre-established calorific value database and determine the matching parameters. S1.4. If the deviation between the matching parameters and the processed data set is less than the preset threshold, calculate the initial calorific value of the solid formed fuel through a linear regression algorithm to obtain the calorific value parameters. S1.5. If the deviation is greater than the preset threshold, collect data again. S1.6. Conduct a clustering analysis based on the calorific value parameters to determine the calorific value distribution characteristics. S1.7. Conduct a statistical modeling for the distribution characteristics to obtain the probability model of the distribution characteristics. S1.8. Predict the subsequent data through the probability model to judge the dynamic change trend of the fuel calorific value.

[0007] S2. According to the fuel calorific value distribution characteristics, match the binder type that meets the calorific value requirements from the preset binder database. Use a chemical composition analysis algorithm to determine the molecular structure characteristics of the binder and obtain the suitable binder types. S2.1. Extract key parameters from the fuel calorific value distribution characteristics, use a feature extraction algorithm to generate a parameter set, and obtain the fuel characteristic description. S2.2. According to the fuel characteristic description, query the preset binder database. If there is a record in the database that matches the parameter set, screen out the candidate binder types and determine the preliminary binder list. S2.3. For the preliminary binder list, use a molecular structure analysis algorithm to calculate the chemical composition characteristics of each binder to obtain the molecular structure description. S2.4. Extract the structural feature parameters from the molecular structure description. If the matching degree between the structural feature parameters and the fuel characteristic description is higher than the preset threshold, retain the corresponding binder type to obtain the preferred binder set. S2.5. According to the preferred binder set, calculate the adaptation score of each binder to the fuel calorific value requirement to determine the final binder type. S2.6. For the final binder type, obtain its chemical composition data, generate the binder application parameters, and obtain the suitable process parameters. S2.7. Generate a combination of fuel and binder by adapting the process parameters and determine the feasibility of the combination.

[0008] S3. Based on the neural network model trained with historical sintering data, the effects of different addition amounts on moisture and volatile content are predicted for the appropriate binder type, and the optimal addition amount parameters are determined; S3.1. Obtain a data training set from historical sintering data, including binder type, addition parameters, moisture content, and volatile content; S3.2. Build a neural network model through the data training set, and use the back propagation algorithm to adjust the model weights to obtain a trained neural network model; S3.3. For different types of binders, multiple addition amount parameters are obtained as model inputs, which are input into the trained neural network model to obtain prediction results; S3.4. Extract the output influence values ​​of moisture content and volatile content from the prediction results, and determine whether the output influence values ​​meet the preset threshold range. If so, retain the corresponding addition amount parameter; if not, remove the corresponding addition amount parameter; S3.5. Based on the retained addition amount parameters, a grid search algorithm is used to calculate the output impact value of each parameter combination to obtain the parameter optimization value; S3.6. Determine the optimal addition amount parameters by comparing the parameter optimization values; S3.7. If the output impact value corresponding to the optimal addition amount parameter exceeds the preset threshold range, a new data training set is obtained from the historical sintering data, and the above steps are repeated to obtain a new optimal addition amount parameter.

[0009] S4. If the optimal addition amount parameter meets the preset sintering energy consumption threshold, the binder addition amount is accurately controlled by the automated batching system, a ratio adjustment instruction is generated, and a fuel raw material with optimized ratio is obtained; S4.1. If the sintering energy consumption data of the fuel raw material exceeds the preset threshold after being obtained by the sensor, the energy consumption data is normalized to obtain a standardized energy consumption value; S4.2. Determine the target range of binder addition by fitting the standardized energy consumption value with the historical mix ratio data through a linear regression algorithm; S4.3. If the deviation between the target range and the current ratio exceeds the preset ratio, the adjustment range is calculated according to the deviation value and a ratio adjustment instruction is generated; S4.4. Execute the ratio adjustment instruction through the automated batching system, update the amount of binder added, and obtain the adjusted fuel raw material; S4.5. Collect real-time sintering data from the adjusted fuel raw materials, compare with the preset energy consumption threshold, and determine whether the ratio adjustment meets the requirements; S4.6. If the real-time sintering data still exceeds the preset threshold, optimize the proportioning parameters through the gradient descent algorithm to generate a new proportioning instruction; S4.7. Record the optimized proportioning data and energy consumption data through the system feedback mechanism to update the historical database.

[0010] S5. Extract samples from the fuel raw materials after proportioning optimization, use infrared spectroscopy analysis technology to detect the moisture and volatile content, and determine whether the preset reduction target is achieved to obtain the reduced fuel base material; S5.1. Obtain samples from the fuel raw materials with optimized proportioning, and use an automatic sampling device to extract fixed-volume samples to obtain an initial sample set; S5.2. Scan the initial sample set through infrared spectroscopy technology to obtain spectral data and determine the characteristic peaks of the moisture content and volatile content; S5.3. If the characteristic peaks match the preset target range, use the principal component analysis algorithm to perform dimensionality reduction processing on the spectral data to obtain a simplified feature set; S5.4. According to the simplified feature set, calculate the proportion values of the moisture content and volatile content, and determine whether the reduction target is achieved; S5.5. If the proportion value is lower than the preset threshold, predict the stability of the fuel base material through the regression analysis algorithm to obtain stable base material parameters; S5.6. Adjust the proportioning scheme using the stable base material parameters to generate a reduced fuel base material; S5.7. Perform secondary detection on the generated fuel base material through infrared spectroscopy technology to determine the reduction effect of the final base material.

[0011] S6. Process the reduced fuel base material through a high-temperature sintering device, monitor the temperature and pressure parameters during the sintering process in real time, and adjust the sintering conditions in combination with the density optimization algorithm to obtain a high-density formed fuel; S6.1. Perform initial processing on the reduced fuel base material through a high-temperature sintering device, obtain the initial sintering temperature and pressure data, and determine the pretreatment state of the base material; S6.2. If the initial sintering temperature exceeds the preset threshold, use the temperature control module to adjust the temperature parameters; S6.3. If the pressure data deviates from the standard range, correct the pressure through the pressure regulating unit to obtain stable sintering environment parameters; S6.4. According to the stable sintering environment parameters, use the density optimization algorithm to calculate the optimal sintering conditions and output the adjusted temperature and pressure control instructions; S6.5. Execute the adjusted temperature and pressure control instructions through the sintering equipment, obtain the dynamic temperature and pressure data during the sintering process in real time, and judge the stability of the sintering process; S6.6. If the dynamic temperature or pressure data fluctuates beyond the preset threshold, re-adjust the sintering parameters through the feedback control module to obtain a stable sintering process state; S6.7. According to the stable sintering process state, continuously operate the sintering equipment, obtain the density data of the final fuel base material, and judge whether the high-density standard is reached; S6.8. Through the shaping process of the fuel base material that meets the high-density standard, obtain the high-density shaped fuel.

[0012] S7. For the high-density shaped fuel, use a mechanical strength testing device to measure its compressive and shear strengths, judge whether it meets the preset abrasion resistance standard, and obtain the solid fuel with optimized strength; S7.1. Obtain a high-density shaped fuel sample, measure its compressive strength and shear strength through a mechanical strength testing device to obtain the initial strength data; S7.2. According to the initial strength data, compare it with the preset abrasion resistance standard. If the compressive strength or shear strength is lower than the preset standard, mark it as a non-conforming sample to obtain a set of non-conforming samples; S7.3. For the set of non-conforming samples, obtain their material composition data, calculate the density distribution of the samples through a density analysis algorithm to obtain the density distribution characteristics; S7.4. According to the density distribution characteristics, use a strength optimization algorithm to adjust the formulation parameters of the shaped fuel to obtain the optimized formulation data; S7.5. Through the optimized formulation data, generate a new shaped fuel sample, and use a mechanical strength testing device to re-measure the compressive strength and shear strength to obtain the updated strength data; S7.6. According to the updated strength data, judge whether it meets the preset abrasion resistance standard. If it meets, output the solid fuel with optimized strength; S7.7. If it does not meet, return to the density distribution characteristic analysis step to re-adjust the formulation parameters; S7.8. Through multiple iterative optimizations, obtain the solid fuel that finally meets the preset abrasion resistance standard to obtain the shaped fuel data with optimized strength.

[0013] S8. Obtain the surface topography data from the solid fuel with optimized strength, analyze its microscopic structure characteristics through an image processing algorithm to determine the anti-wear ability during storage and transportation, and obtain the final fuel with optimized storage and transportation performance; S8.1. Obtain the morphological data from the surface of the solid fuel, use scanning microscopy technology to generate the first morphological image, and obtain the surface morphological features; S8.2. For the first morphological image, use a denoising algorithm to process it, remove noise interference, generate the second morphological image, and obtain clear morphological data; S8.3. Extract the microstructural parameters from the second morphological image, use an edge detection algorithm to identify the grain boundaries and pore distribution, and obtain the microstructural characteristics; S8.4. According to the microstructural characteristics, calculate the grain size and porosity. If the grain size is greater than the preset threshold and the porosity is lower than the preset threshold, then judge that the anti-wear force is relatively high, and obtain the anti-wear force evaluation result; S8.5. For the anti-wear force evaluation result, use a regression analysis algorithm to fit the relationship between the microstructure and the anti-wear force, generate a performance prediction model, and obtain the storage and transportation performance parameters; S8.6. Adjust the fuel formula ratio from the storage and transportation performance parameters. If the anti-wear force is lower than the preset standard, then increase the content of the strengthening component, generate an optimized formula plan, and obtain an improved fuel formula; S8.7. According to the improved fuel formula, re-obtain the surface morphological data, verify the change of the microstructure, judge the improvement of the storage and transportation performance, and obtain the final optimized fuel.

[0014] S9. For the final fuel optimized according to the storage and transportation performance, use a flue gas analyzer to detect the flue gas components emitted during the sintering process, and combine with the emission model to verify whether the flue gas emission is lower than the preset threshold, and obtain a fuel product that meets the reduction and resource utilization goals; S9.1. Obtain the flue gas component data emitted during the sintering process through a flue gas analyzer, and determine the concentration values of each component in the flue gas; S9.2. If the concentration value exceeds the preset threshold, then calculate the deviation value through the emission model to obtain the fuel parameters that need to be adjusted; S9.3. According to the adjusted fuel parameters, generate an optimized fuel formula and determine the fuel composition that meets the reduction goal; S9.4. Use the optimized fuel formula to simulate the sintering process, verify whether the flue gas emission is lower than the preset threshold through the simulation data, and judge the applicability of the fuel formula; S9.5. If the simulation data meets the preset threshold, then through the resource utilization goal constraint, calculate the resource utilization rate of the fuel product to obtain the degree of realization of the resource utilization goal; S9.6. According to the resource utilization rate, adjust the fuel production parameters, generate the final fuel product, and determine the fuel characteristics that meet the reduction and resource utilization goals; S9.7. Conduct an actual sintering test on the final fuel product through a flue gas analyzer, verify the flue gas component data, and judge the emission control effect.

[0015] The present invention can achieve the following beneficial effects: 1. By fusing real-time data from multiple sensors with a dynamic database match and combining probability model analysis, high-precision prediction of the calorific value of domestic waste is achieved, overcoming the static defects of traditional empirical formulas and significantly improving the stability of fuel quality.

[0016] 2. Based on quantitative analysis of molecular structure characteristics and multi-objective optimization algorithms, scientific matching of the type and addition amount of binders is achieved, breaking through the blindness of manual screening and ensuring the chemical compatibility and thermal stability of the fuel matrix.

[0017] 3. Through neural network model prediction and real-time feedback mechanisms, key parameters such as sintering temperature and pressure are dynamically optimized to form a full-process closed-loop control of "monitoring - analysis - adjustment", significantly improving the fuel density and mechanical strength, while reducing energy consumption and pollutant emissions. Specific implementation manners

[0018] A method for resource treatment of domestic waste, and the specific method is as follows: Step S1: Real-time collect data on the moisture and volatile content in domestic waste through sensors, combine with a pre-established calorific value database, calculate the initial calorific value parameters of the solid formed fuel, and obtain the fuel calorific value distribution characteristics.

[0019] Real-time collect data on the moisture content and volatile content in domestic waste through sensors to obtain an original data set. Use a preprocessing algorithm to denoise and standardize the original data set to obtain a processed data set. Obtain reference data corresponding to the processed data set from a pre-established calorific value database, and determine the matching parameters. If the deviation between the matching parameters and the processed data set is less than a preset threshold, calculate the initial calorific value of the solid formed fuel through a linear regression algorithm to obtain the calorific value parameters; if the deviation is greater than the preset threshold, re-collect the data. Perform cluster analysis based on the calorific value parameters to determine the calorific value distribution characteristics. Conduct statistical modeling for the distribution characteristics to obtain a probability model of the distribution characteristics. Use the probability model to predict subsequent data and judge the dynamic change trend of the fuel calorific value.

[0020] Linear regression calculation formula for calorific value: ; Symbol definitions: : Calorific value (MJ / kg); : Moisture content (%); : Volatile content (%); , , is the regression coefficient; is the error term. Median filtering denoising formula: ; where is the denoised data, is as the center of the continuous original data points.

[0021] Specifically, the real-time acquisition of the moisture content and volatile content in domestic waste is the basis for predicting the calorific value of solid briquette fuel.

[0022] Exemplarily, the sensor can adopt near-infrared spectroscopy technology to analyze the moisture and volatile content in the garbage through spectral reflection characteristics.

[0023] For example, install a sensor on the conveyor belt of the garbage treatment plant, collect data once per second, and obtain an original data set with a moisture content of 40% and a volatile content of 35%.

[0024] In addition, the original data often contains outliers due to environmental noise or equipment jitter, so preprocessing is required.

[0025] In this embodiment, the preprocessing algorithm can adopt median filtering denoising and Z-score standardization.

[0026] Specifically, median filtering effectively smooths the noise by replacing the outlier with the median of 5 consecutive data points; Z-score standardization converts the moisture and volatile data into a distribution with a mean of 0 and a standard deviation of 1, facilitating subsequent analysis.

[0027] Z-score standardization formula: ; where is the standardized data, is the original data, is the data mean, is the data standard deviation.

[0028] For example, the processed data set may show a standardized value of 0.8 for the moisture content and 0.6 for the volatile content. This preprocessing ensures data consistency and improves the matching accuracy.

[0029] Preferably, when obtaining reference data from the calorific value database, the corresponding parameters can be determined by the feature vector matching method.

[0030] For example, a record with a calorific value of 18 MJ / kg when the moisture content is 0.7 and the volatile matter content is 0.5 is stored in the database. The deviation calculation of the matching parameters is based on the Euclidean distance. If the deviation is less than the preset threshold of 0.2, the data is considered reliable. Conversely, if the deviation is 0.4, the data needs to be recollected to avoid prediction errors. This mechanism ensures data quality.

[0031] In this embodiment, the linear regression algorithm is used to calculate the initial calorific value.

[0032] For example, based on the processed data set and reference data, the regression model fits the linear relationship between moisture and volatile matter and calorific value, and predicts the calorific value to be 17.8 MJ / kg. This method is simple and efficient in calculation and suitable for real-time applications.

[0033] Cluster analysis can use the K-means algorithm to determine the distribution characteristics of calorific value.

[0034] For example, the calorific value data is divided into three categories: high, medium, and low, which are concentrated around 20 MJ / kg, 18 MJ / kg, and 15 MJ / kg respectively, reflecting the heterogeneity of the waste components. This distribution characteristic provides a basis for subsequent modeling.

[0035] Specifically, statistical modeling can describe the calorific value distribution through a Gaussian mixture model.

[0036] For example, the model fits a normal distribution with a mean of 18 MJ / kg and a standard deviation of 2 MJ / kg, characterizing the probability characteristics of the calorific value. This model can quantify uncertainty and improve the robustness of prediction.

[0037] For example, when the probability model is used to predict subsequent data, based on the newly collected moisture content of 38% and volatile matter content of 36%, the predicted calorific value is 18.2 MJ / kg, and its dynamic trend is judged to be stable. This prediction helps to optimize the fuel ratio and improve the combustion efficiency.

[0038] In this embodiment, the dynamic trend analysis combines time series methods.

[0039] For example, the predicted data for a continuous week shows that the calorific value fluctuates between 17.5 and 18.5 MJ / kg, indicating that the waste components are stable. This analysis provides a basis for the operation adjustment of the waste treatment plant and reduces energy consumption.

[0040] In addition, the integration of the above methods realizes the closed-loop management from data collection to prediction, which not only improves the accuracy of calorific value prediction but also optimizes the resource utilization efficiency of solid formed fuels.

[0041] For example, accurate calorific value data can guide the adjustment of combustion parameters of incinerators, reduce emissions and improve energy recovery rates. Through the coordination of multiple links in this technical chain, the reliability and practicality of the prediction results are ensured.

[0042] Step S2: According to the calorific value distribution characteristics of the fuel, match the binder type that meets the calorific value requirements from the preset binder database, and use the chemical composition analysis algorithm to determine the molecular structure characteristics of the binder to obtain the suitable binder type.

[0043] Extract key parameters from the calorific value distribution characteristics of the fuel, use the feature extraction algorithm to generate a parameter set, and obtain the fuel property description. According to the fuel property description, query the preset binder database. If there are records in the database that match the parameter set, then screen out the candidate binder types to determine the preliminary binder list. For the preliminary binder list, use the molecular structure analysis algorithm to calculate the chemical composition characteristics of each binder to obtain the molecular structure description. Extract the structural feature parameters from the molecular structure description. If the matching degree of the structural feature parameters and the fuel property description is higher than the preset threshold, then retain the corresponding binder type to obtain the preferred binder set. According to the preferred binder set, calculate the adaptation score of each binder to the fuel calorific value requirement to determine the final binder type. For the final binder type, obtain its chemical composition data, generate the binder application parameters, and obtain the suitable process parameters. Through the suitable process parameters, generate the combination plan of the fuel and the binder, and judge the feasibility description of the combination plan.

[0044] Specifically, based on the fuel calorific value distribution characteristics, in the binder matching process, candidate binders that meet the target calorific value range are first screened through a preset database. For example, when the fuel calorific value is concentrated at 18 MJ / kg, the database retrieves 5 candidate binders such as lignosulfonate and starch derivatives, and their suitable calorific value ranges are 17 - 19 MJ / kg. Chemical composition analysis uses Raman spectroscopy combined with the principal component analysis algorithm. For example, spectral data in the 300 - 1800 cm^-1 band is collected for the lignosulfonate sample. After PCA dimensionality reduction, the first 3 principal components (cumulative contribution rate 92%) are extracted and matched with the standard spectral map in the database. When the similarity exceeds 0.85, it is determined that the molecular structures are consistent. The binder suitability evaluation introduces a fuzzy logic algorithm, setting three input variables: calorific value matching degree, chemical compatibility, and thermal stability, with variable weights of 0.5, 0.3, and 0.2 respectively. The evaluation results are quantified through membership functions. For example, the comprehensive score of a certain starch derivative reaches 0.78, exceeding the threshold of 0.7 and being selected as the optimal binder. In the dynamic optimization link, the genetic algorithm is used to adjust the binder ratio, with the minimum calorific value deviation as the objective function, the population size set to 50, and the best ratio obtained after 20 generations of iteration is 65% lignosulfonate and 35% bentonite. At this time, the predicted calorific value deviation drops to 0.3 MJ / kg. The database synchronization update mechanism is implemented through SQL triggers. When new binder detection data is added, its spectral feature vector is automatically calculated and indexed. For example, after adding polyvinyl alcohol data, the system completes feature extraction within 0.2 seconds and classifies it into the alcohol binder partition.

[0045] Step S3, for the types of suitable binders, based on the neural network model trained with historical sintering data, predict the effects of different addition amounts on the moisture and volatile content, and determine the optimal addition amount parameters. The neural network prediction model is constructed as follows: 3 - layer MLP network structure: Let the input vector (here , that is, the binder type and addition amount), the number of neurons in the hidden layer is , and the number of neurons in the output layer is (here , that is, the predicted values of moisture content and volatile content).

[0046] ; ; ; ; Where: : The weight matrix from the input layer to the hidden layer; : The hidden layer bias; : The weight matrix from the hidden layer to the output layer; : Output layer bias; : Corrected linear unit activation function; : Sigmoid activation function.

[0047] A data training set is obtained from historical sintering data, including binder type, addition amount parameter, moisture content and volatile content. A neural network model is constructed through the data training set, and the model weight is adjusted by the back propagation algorithm to obtain a trained neural network model. For different types of binders, multiple addition amount parameters are obtained as model inputs, and input into the trained neural network model to obtain prediction results. The output influence values ​​of moisture content and volatile content are extracted from the prediction results to determine whether the output influence values ​​meet the preset threshold range. If they meet, the corresponding addition amount parameters are retained, and if they do not meet, the corresponding addition amount parameters are eliminated. According to the retained addition amount parameters, the grid search algorithm is used to calculate the output influence values ​​of each parameter combination to obtain the parameter optimization value. The optimal addition amount parameters are determined by comparing the parameter optimization values. If the output influence value corresponding to the optimal addition amount parameter exceeds the preset threshold range, a new data training set is obtained from the historical sintering data, and the above steps are repeated to obtain a new optimal addition amount parameter.

[0048] Specifically, based on the historical sintering data, by constructing a neural network model, the effect of different binder additions on moisture and volatile content can be predicted. First, the sintering data of different binder types (such as polyvinyl alcohol, carboxymethyl cellulose, etc.) and their addition amounts (such as 0.5%, 1.0%, 1.5%, etc.) in the past five years were collected, including the measured values ​​of moisture content and volatile content. Using these data, a multi-layer perceptron (MLP) neural network was trained, with the input layer being the binder type and addition amount, and the output layer being the moisture and volatile content. The network weights were optimized by the back propagation algorithm, with the learning rate set to 0.01 and the number of iterations set to 1000 to ensure model convergence. After the training was completed, the model performance was evaluated using the cross-validation method, and the mean square error (MSE) was calculated to be 0.02, indicating that the model had a high prediction accuracy. Next, the trained model was used to predict the moisture and volatile content at different binder addition amounts. For example, when the carboxymethyl cellulose addition amount was 1.2%, the predicted moisture content was 3.8% and the volatile content was 5.2%. By analyzing the prediction results, the optimal addition parameters are determined. For example, the optimal addition of carboxymethyl cellulose is 1.0%, at which the moisture content is 3.5% and the volatile content is 4.8%, which meets the sintering process requirements. The entire process is automatically processed by information technology without manual intervention, ensuring the accuracy and efficiency of the data.

[0049] Step S4, if the optimal addition amount parameter meets the preset sintering energy consumption threshold, the binder addition amount is precisely controlled through the automated batching system to generate a ratio adjustment instruction, and the fuel raw material with optimized ratio is obtained.

[0050] The ratio optimization control model is as follows: Energy consumption normalization: ; Gradient descent update: ; Step size .

[0051] If the sintering energy consumption data of the fuel raw material exceeds the preset threshold after being obtained by the sensor, the energy consumption data is normalized to obtain the standardized energy consumption value. The standardized energy consumption value and the historical ratio data are fitted through the linear regression algorithm to determine the target range of the binder addition amount. If the deviation between the target range and the current ratio exceeds the preset ratio, the adjustment amplitude is calculated according to the deviation value to generate a ratio adjustment instruction. The ratio adjustment instruction is executed through the automated batching system to update the binder addition amount, and the adjusted fuel raw material is obtained. The real-time sintering data is collected from the adjusted fuel raw material, compared with the preset energy consumption threshold, and it is judged whether the ratio adjustment meets the requirements. If the real-time sintering data still exceeds the preset threshold, the ratio parameters are optimized through the gradient descent algorithm to generate a new ratio instruction. The optimized ratio data and energy consumption data are recorded through the system feedback mechanism to update the historical database.

[0052] Specifically, during the sintering process, when the optimal addition amount parameter meets the preset sintering energy consumption threshold, the automated batching system calculates by combining the preset energy consumption model through real-time monitoring of data such as the temperature, pressure, and raw material composition in the sintering furnace.

[0053] For example, when the temperature in the sintering furnace reaches 1200 °C, the pressure is 1.2 MPa, and the binder content in the raw material is 5%, the system calculates through the algorithm that the current energy consumption is 850 kJ / kg, which is lower than the preset threshold of 900 kJ / kg. At this time, the system precisely adjusts the addition amount of the binder from 5% to 4.8% according to the energy consumption model and raw material composition analysis to further reduce the energy consumption. The adjusted ratio instruction is sent to the batching equipment in real time through the automated control system to ensure precise control of the binder addition amount. At the same time, the system continuously monitors the adjusted energy consumption data. If the energy consumption drops to 840 kJ / kg, it indicates that the ratio optimization is successful. The system generates the final ratio optimization instruction and transports the optimized fuel raw material to the next process. The whole process is realized through the automated system without manual intervention, ensuring the stability of the sintering process and the optimization of energy consumption.

[0054] Step S5: Extract samples from the fuel raw materials with optimized ratios, detect the moisture and volatile content using infrared spectroscopy analysis technology, determine whether the preset reduction target is achieved, and obtain the fuel base material with reduced quantity.

[0055] Obtain samples from the fuel raw materials with optimized ratios, extract fixed - volume samples using an automatic sampling device to obtain an initial sample set. Scan the initial sample set through infrared spectroscopy technology to obtain spectral data, and determine the characteristic peaks of the moisture content and volatile content. If the characteristic peaks match the preset target range, use the principal component analysis algorithm to perform dimensionality reduction processing on the spectral data to obtain a simplified feature set. According to the simplified feature set, calculate the proportion values of the moisture content and volatile content, and determine whether the reduction target is achieved. If the proportion value is lower than the preset threshold, predict the stability of the fuel base material through the regression analysis algorithm to obtain stable base material parameters. Adjust the ratio scheme using the stable base material parameters to generate the fuel base material with reduced quantity. Perform secondary detection on the generated fuel base material through infrared spectroscopy technology to determine the reduction effect of the final base material.

[0056] Specifically, in the fuel raw materials with optimized ratios, extract samples through an automated sampling system to ensure the representativeness and consistency of the samples. Detect the samples using infrared spectroscopy analysis technology. By setting infrared spectral bands with wavelengths of 2.9 microns and 6.1 microns, detect the moisture and volatile content respectively. Use spectral analysis software to convert the spectral data into absorption spectra through the Fourier transform algorithm, and then calculate the specific content of moisture and volatile through the standard curve method.

[0057] For example, the measured moisture content of a certain sample is 5.3% and the volatile content is 12.7%. Compare the detection results with the preset reduction target, where the preset target is that the moisture content is lower than 6% and the volatile content is lower than 15%. Through data analysis algorithms, determine whether the current sample reaches the reduction target. If it reaches, mark the sample as a qualified fuel base material with reduced quantity. If it does not reach, adjust the raw material ratio through an optimization algorithm, re - sample and detect until the preset target is met. Finally, store the qualified fuel base material with reduced quantity in a special container for subsequent use. The entire process is realized through an automated control system to ensure the accuracy of data and the efficiency of processing.

[0058] Step S6: Process the fuel base material with reduced quantity through a high - temperature sintering device, monitor the temperature and pressure parameters during the sintering process in real - time, and adjust the sintering conditions in combination with the density optimization algorithm to obtain a high - density formed fuel.

[0059] The initial treatment of the reduced fuel base material is carried out by a high-temperature sintering device to obtain the initial sintering temperature and pressure data, and determine the pretreatment state of the base material. If the initial sintering temperature exceeds the preset threshold, the temperature control module is used to adjust the temperature parameters; if the pressure data deviates from the standard range, the pressure is corrected by the pressure regulating unit to obtain stable sintering environment parameters. According to the stable sintering environment parameters, the density optimization algorithm is used to calculate the optimal sintering conditions, and the adjusted temperature and pressure control instructions are output. The adjusted temperature and pressure control instructions are executed by the sintering device, and the dynamic temperature and pressure data during the sintering process are obtained in real time to judge the stability of the sintering process. If the dynamic temperature or pressure data fluctuates beyond the preset threshold, the sintering parameters are readjusted through the feedback control module to obtain a stable sintering process state. According to the stable sintering process state, the sintering device is continuously operated to obtain the density data of the final fuel base material, and it is judged whether the high-density standard is reached. By shaping the fuel base material that meets the high-density standard, high-density shaped fuel is obtained.

[0060] Specifically, in the high-temperature sintering device, the reduced fuel base material is placed in a sintering furnace at 1600 degrees Celsius. The temperature data is collected in real time by a thermocouple with a sampling frequency of 10 Hz. At the same time, the pressure sensor monitors the pressure in the furnace at a frequency of 5 Hz, and the data is transmitted to the central control system through the industrial Internet of Things. The system uses a density optimization algorithm based on gradient descent. When the real-time monitoring shows that the density is lower than 95%, the algorithm automatically adjusts the sintering parameters. For example, the heating rate is increased from 5 degrees Celsius per minute to 8 degrees Celsius, and a constant pressure of 2 MPa is maintained for 30 minutes when the pressure reaches 2 MPa. The crystal phase structure of the sintered body is analyzed online by an X-ray diffractometer. If the detected porosity is higher than 3%, the secondary sintering process is triggered, and the temperature is raised to 1650 degrees Celsius and a pressure of 2.5 MPa is applied for 20 minutes. During the sintering process, the machine learning model analyzes the correlation between historical data and current process parameters. For example, when the particle size distribution D50 of the base material is 50 microns, the model recommends using a two-stage sintering curve, first preheating at 1400 degrees Celsius for 15 minutes, and then rising to the target temperature at 10 degrees Celsius per minute. Finally, the system verifies through three-dimensional CT scanning that the density of the sintered body reaches more than 98%, and the compressive strength exceeds 300 MPa, meeting the technical standards of high-density shaped fuel. The process parameters and quality inspection data of the whole process are recorded in the blockchain database to ensure the traceability of production batches.

[0061] The formula for analyzing the porosity by an X-ray diffractometer: Let the relationship between the diffraction peak intensity and the porosity be , where is the measured diffraction peak intensity, is the diffraction peak intensity without pores, is the absorption coefficient, is the sample thickness, and the porosity can be deduced by this formula .

[0062] Step S7: For the high-density formed fuel, use a mechanical strength testing device to measure its compressive and shear strengths, and determine whether it meets the preset abrasion resistance standard to obtain a solid fuel with optimized strength.

[0063] Obtain a high-density formed fuel sample, measure its compressive strength and shear strength through a mechanical strength testing device to obtain initial strength data. According to the initial strength data, compare it with the preset abrasion resistance standard. If the compressive strength or shear strength is lower than the preset standard, mark it as a non-conforming sample to obtain a set of non-conforming samples. For the set of non-conforming samples, obtain its material composition data, calculate the density distribution of the samples through a density analysis algorithm to obtain the density distribution characteristics. According to the density distribution characteristics, use a strength optimization algorithm to adjust the formulation parameters of the formed fuel to obtain optimized formulation data. Through the optimized formulation data, generate a new formed fuel sample, and use a mechanical strength testing device to re-measure the compressive strength and shear strength to obtain updated strength data. According to the updated strength data, determine whether it meets the preset abrasion resistance standard. If it meets, output the solid fuel with optimized strength; if it does not meet, return to the density distribution characteristic analysis step to readjust the formulation parameters. Through multiple iterative optimizations, obtain the solid fuel that finally meets the preset abrasion resistance standard to obtain the formed fuel data with optimized strength.

[0064] Specifically, when measuring the mechanical strength of highly dense formed fuel, first, a universal material testing machine is used for compressive strength testing. The loading rate is set at 2 mm per minute, and the stress-strain curve of the fuel sample during compression is recorded. Loading is stopped when the stress reaches 50 MPa, and the compressive strength is calculated by dividing the peak stress by the initial cross-sectional area. If the result is higher than the preset standard value of 40 MPa, it is judged as qualified. For the shear strength test, a double-sided shear fixture is used to apply a shear force at a rate of 1 mm per minute until the sample breaks, and the shear strength is obtained according to the ratio of the maximum shear force to the shear area, which is required to be not less than 15 MPa to meet the anti-wear standard. The strength data is fitted by the least squares method to obtain a strength distribution model, and the analysis of variance is used to evaluate the influence of different forming pressures (such as 200 MPa, 250 MPa, 300 MPa) on the strength. When the p-value is less than 0.05, it is considered that the change in pressure has a significant impact on the strength. Based on the regression analysis results, the forming process parameters are optimized. For example, when the pressure is increased to 280 MPa, the compressive strength can be increased by 12%. At the same time, the particle swarm algorithm is used to perform multi-objective optimization with the weighted sum of the compressive strength and the shear strength as the objective function, and the weight coefficients are set as 0.6 and 0.4 respectively. After 50 iterations, the optimal forming pressure is 290 MPa. At this time, the compressive strength reaches 55 MPa, and the shear strength reaches 18 MPa, fully meeting the preset standard. Finally, the stress distribution of the fuel during transportation is simulated by finite element method to verify the anti-wear performance of the optimized fuel under dynamic load. The simulation results show that the maximum von Mises stress is 38 MPa, which is lower than the material yield strength, ensuring the reliability of practical applications.

[0065] Analysis of variance (ANOVA) is used to evaluate the influence of factors on strength: Let the strength data of different groups (such as different forming pressure groups) be , ( is the number of groups), ( is the number of samples in the th group). The total sum of squares , the sum of squares between groups , and the sum of squares within groups . Calculate , where , ( ), and by comparing the value with the critical value, it is judged whether the factor has a significant influence on the strength.

[0066] Step S8: Obtain the surface topography data from the solid fuel with optimized strength, analyze its microstructural characteristics through image processing algorithms, determine the anti-wear ability during storage and transportation, and obtain the final fuel with optimized storage and transportation performance.

[0067] Obtain the morphological data from the surface of the solid fuel, use scanning microscopy technology to generate the first morphological image, and obtain the surface morphological characteristics. For the first morphological image, use a denoising algorithm to process it, remove noise interference, generate the second morphological image, and obtain clear morphological data. Extract the microstructure parameters from the second morphological image, use an edge detection algorithm to identify the grain boundaries and pore distribution, and obtain the microstructure characteristics. According to the microstructure characteristics, calculate the grain size and porosity. If the grain size is greater than the preset threshold and the porosity is lower than the preset threshold, then judge that the anti-wear force is higher, and obtain the anti-wear force evaluation result. For the anti-wear force evaluation result, use a regression analysis algorithm to fit the relationship between the microstructure and the anti-wear force, generate a performance prediction model, and obtain the storage and transportation performance parameters. Adjust the fuel formula ratio according to the storage and transportation performance parameters. If the anti-wear force is lower than the preset standard, then increase the content of the strengthening component, generate an optimized formula plan, and obtain an improved fuel formula. According to the improved fuel formula, re-obtain the surface morphological data, verify the change of the microstructure, judge the improvement of the storage and transportation performance, and obtain the final optimized fuel.

[0068] Step S9, for the final fuel optimized according to the storage and transportation performance, use a flue gas analyzer to detect the components of the flue gas discharged during the sintering process, and combine with the emission model to verify whether the flue gas emission is lower than the preset threshold, and obtain a fuel product that meets the goals of reduction and resource utilization.

[0069] Obtain the flue gas component data discharged during the sintering process through a flue gas analyzer, and determine the concentration values of each component in the flue gas. If the concentration value exceeds the preset threshold, then calculate the deviation value through the emission model to obtain the fuel parameters that need to be adjusted. According to the adjusted fuel parameters, generate an optimized fuel formula, and determine the fuel composition that meets the reduction goal. Use the optimized fuel formula to simulate the sintering process, and verify whether the flue gas emission is lower than the preset threshold through the simulation data to judge the applicability of the fuel formula. If the simulation data meets the preset threshold, then through the constraint of the resource utilization goal, calculate the resource utilization rate of the fuel product to obtain the degree of realization of the resource utilization goal. According to the resource utilization rate, adjust the fuel production parameters, generate the final fuel product, and determine the fuel characteristics that meet the goals of reduction and resource utilization. Conduct an actual sintering test on the final fuel product through a flue gas analyzer to verify the flue gas component data and judge the emission control effect.

[0070] Specifically, during the selection process of the final fuel optimized for storage and transportation performance, first use a flue gas analyzer to monitor the components of the flue gas discharged during the sintering process in real time, and the detection items include key indicators such as carbon dioxide, carbon monoxide, nitrogen oxides, and sulfur oxides.

[0071] For example, the results of a certain detection show that the carbon dioxide concentration is 12.5%, carbon monoxide is 0.8%, nitrogen oxides are 150 ppm, and sulfur oxides are 80 ppm. These data are input into an emission model, which is based on a multiple linear regression algorithm and obtains the relationship between each component and the fuel ratio through training with historical data. The model predicts that the emission values under the current fuel ratio are 12.3% for carbon dioxide, 0.75% for carbon monoxide, 145 ppm for nitrogen oxides, and 75 ppm for sulfur oxides, which are basically consistent with the measured values. Then, the system compares the predicted values with the preset thresholds (12.8% for carbon dioxide, 0.85% for carbon monoxide, 160 ppm for nitrogen oxides, and 90 ppm for sulfur oxides) and finds that all indicators are lower than the thresholds, indicating that the current fuel ratio meets the requirements of reduction. To further optimize the resource utilization goal, the system uses a genetic algorithm to iteratively optimize the fuel ratio. After 100 iterations, the optimal ratio is obtained as 60% pulverized coal, 20% biomass, and 20% waste plastic. Finally, through re-detection with a flue gas analyzer, it is confirmed that under the optimized fuel ratio, the carbon dioxide concentration drops to 11.8%, carbon monoxide is 0.7%, nitrogen oxides are 140 ppm, and sulfur oxides are 70 ppm, all of which are lower than the preset thresholds, achieving the dual goals of reduction and resource utilization.

[0072] The above embodiments are only the preferred technical solutions of the present invention and should not be regarded as limitations on the present invention. The protection scope of the present invention shall be the technical solutions recorded in the claims, including equivalent replacement solutions of the technical features in the technical solutions recorded in the claims. That is, equivalent replacement improvements within this scope are also within the protection scope of the present invention.

Claims

1. A method for resource treatment of domestic waste, characterized in that It includes the following steps: S1. Real-time collect data on the moisture and volatile content in domestic waste through sensors, combine with a pre-established calorific value database, calculate the initial calorific value parameters of the solid briquette fuel, and obtain the fuel calorific value distribution characteristics; S2. According to the fuel calorific value distribution characteristics, match the binder type that meets the calorific value requirements from a preset binder database, and use a chemical composition analysis algorithm to determine the molecular structure characteristics of the binder, so as to obtain the suitable binder type; S3. For the suitable binder type, based on a neural network model trained with historical sintering data, predict the influence of different addition amounts on the moisture and volatile content, and determine the optimal addition amount parameter; S4. If the optimal addition amount parameter meets the preset sintering energy consumption threshold, precisely control the binder addition amount through an automated batching system, generate a ratio adjustment instruction, and obtain the fuel raw material with optimized ratio; S5. Extract samples from the fuel raw material with optimized ratio, use infrared spectroscopy analysis technology to detect the moisture and volatile content, judge whether the preset reduction target is achieved, and obtain the reduced fuel base material; S6. Process the reduced fuel base material through a high-temperature sintering device, real-time monitor the temperature and pressure parameters during the sintering process, and adjust the sintering conditions in combination with a density optimization algorithm to obtain a high-density briquette fuel; S7. For the high-density briquette fuel, use a mechanical strength testing device to measure its compressive and shear strengths, judge whether it meets the preset abrasion resistance standard, and obtain a solid fuel with optimized strength; S8. Obtain the surface topography data from the solid fuel with optimized strength, analyze its microscopic structure characteristics through an image processing algorithm, determine the abrasion resistance during storage and transportation, and obtain the final fuel with optimized storage and transportation performance; S9. According to the final fuel with optimized storage and transportation performance, use a flue gas analyzer to detect the flue gas components emitted during the sintering process, and verify whether the flue gas emissions are lower than the preset threshold in combination with an emission model, so as to obtain a fuel product that meets the reduction and resource utilization goals.

2. The method for resource treatment of domestic waste according to claim 1, characterized in that, The said S1 includes: S1.

1. Real-time collect data on the moisture content and volatile content in domestic waste through sensors to obtain an original data set; S1.

2. Use a preprocessing algorithm to denoise and standardize the original data set to obtain a processed data set; S1.

3. Obtain the reference data corresponding to the processed data set from a pre-established calorific value database, and determine the matching parameters; S1.

4. If the deviation between the matching parameters and the processed data set is less than the preset threshold, calculate the initial calorific value of the solid briquette fuel through a linear regression algorithm to obtain the calorific value parameters; S1.

5. If the deviation is greater than the preset threshold, re-collect the data; S1.

6. Conduct cluster analysis according to the calorific value parameters to determine the calorific value distribution characteristics; S1.

7. Conduct statistical modeling for the distribution characteristics to obtain a probability model of the distribution characteristics; S1.

8. Predict the subsequent data through the probability model to judge the dynamic change trend of the fuel calorific value.

3. A method for resource treatment of domestic waste according to claim 1, characterized in that The said S2 includes: S2.

1. Extract key parameters from the fuel calorific value distribution characteristics, generate parameter sets using feature extraction algorithms, and obtain fuel characteristic descriptions; S2.

2. According to the fuel characteristic description, query the preset binder database. If there is a record matching the parameter set in the database, select the candidate binder types and determine the preliminary binder list; S2.

3. For the preliminary list of binders, use a molecular structure analysis algorithm to calculate the chemical composition characteristics of each binder and obtain a molecular structure description; S2.

4. Extracting structural characteristic parameters from the molecular structure description, if the matching degree between the structural characteristic parameters and the fuel characteristic description is higher than a preset threshold, retaining the corresponding binder type, and obtaining a preferred binder set; S2.

5. Calculate the matching score of each binder with the fuel calorific value requirement according to the preferred binder set, and determine the final binder type; S2.

6. Obtain chemical composition data of the final binder type, generate binder application parameters, and obtain suitable process parameters; S2.

7. Generate a combination of fuel and binder by adapting the process parameters and determine the feasibility of the combination.

4. A method for resource treatment of domestic waste according to claim 1, characterized in that, The S3 includes: S3.

1. Obtain a data training set from historical sintering data, including binder type, addition parameters, moisture content, and volatile content; S3.

2. Build a neural network model through the data training set, and use the back propagation algorithm to adjust the model weights to obtain a trained neural network model; S3.

3. For different types of binders, multiple addition amount parameters are obtained as model inputs, which are input into the trained neural network model to obtain prediction results; S3.

4. Extract the output influence values ​​of moisture content and volatile content from the prediction results, and determine whether the output influence values ​​meet the preset threshold range. If so, retain the corresponding addition amount parameter; if not, remove the corresponding addition amount parameter; S3.

5. Based on the retained addition amount parameters, a grid search algorithm is used to calculate the output impact value of each parameter combination to obtain the parameter optimization value; S3.

6. Determine the optimal addition amount parameters by comparing the parameter optimization values; S3.

7. If the output impact value corresponding to the optimal addition amount parameter exceeds the preset threshold range, a new data training set is obtained from the historical sintering data, and the above steps are repeated to obtain a new optimal addition amount parameter.

5. A method for resource treatment of domestic waste according to claim 1, characterized in that, The S4 includes: S4.

1. If the sintering energy consumption data of the fuel raw material exceeds the preset threshold after being obtained by the sensor, the energy consumption data is normalized to obtain a standardized energy consumption value; S4.

2. Determine the target range of binder addition by fitting the standardized energy consumption value with the historical mix ratio data through a linear regression algorithm; S4.

3. If the deviation between the target range and the current ratio exceeds the preset ratio, the adjustment range is calculated according to the deviation value and a ratio adjustment instruction is generated; S4.

4. Execute the ratio adjustment instruction through the automated batching system, update the amount of binder added, and obtain the adjusted fuel raw material; S4.

5. Collect real-time sintering data from the adjusted fuel raw materials, compare with the preset energy consumption threshold, and determine whether the ratio adjustment meets the requirements; S4.

6. If the real-time sintering data still exceeds the preset threshold, optimize the mixing ratio parameters through the gradient descent algorithm to generate a new mixing ratio instruction; S4.

7. Record the optimized mixing ratio data and energy consumption data through the system feedback mechanism to update the historical database.

6. A method for resource treatment of domestic waste according to claim 1, characterized in that, The above S5 includes: S5.

1. Obtain samples from the fuel raw materials with optimized mixing ratios, and use an automatic sampling device to extract samples of a fixed volume to obtain an initial sample set; S5.

2. Scan the initial sample set through infrared spectroscopy technology to obtain spectral data, and determine the characteristic peaks of the moisture content and volatile component content; S5.

3. If the characteristic peaks match the preset target range, perform dimensionality reduction processing on the spectral data using the principal component analysis algorithm to obtain a simplified feature set; S5.

4. According to the simplified feature set, calculate the ratio values of the moisture content and volatile component content, and determine whether the reduction target is achieved; S5.

5. If the ratio value is lower than the preset threshold, predict the stability of the fuel base material through the regression analysis algorithm to obtain stable base material parameters; S5.

6. Adjust the mixing ratio scheme using the stable base material parameters to generate a reduced fuel base material; S5.

7. Perform secondary detection on the generated fuel base material through infrared spectroscopy technology to determine the reduction effect of the final base material.

7. A method for resource treatment of domestic waste according to claim 1, characterized in that The above S6 includes: S6.

1. Perform initial processing on the reduced fuel base material through a high-temperature sintering device to obtain the initial sintering temperature and pressure data, and determine the pretreatment state of the base material; S6.

2. If the initial sintering temperature exceeds the preset threshold, use the temperature control module to adjust the temperature parameters; S6.

3. If the pressure data deviates from the standard range, correct the pressure through the pressure regulating unit to obtain stable sintering environment parameters; S6.

4. According to the stable sintering environment parameters, calculate the optimal sintering conditions using the density optimization algorithm, and output the adjusted temperature and pressure control instructions; S6.

5. Execute the adjusted temperature and pressure control instructions through the sintering device, and obtain the dynamic temperature and pressure data during the sintering process in real time to judge the stability of the sintering process; S6.

6. If the dynamic temperature or pressure data fluctuates beyond the preset threshold, readjust the sintering parameters through the feedback control module to obtain a stable sintering process state; S6.

7. According to the stable sintering process state, continuously operate the sintering device to obtain the density data of the final fuel base material, and determine whether the high-density standard is reached; S6.

8. Through the forming process of the fuel base material that meets the high-density standard, obtain a high-density formed fuel.

8. A method for resource treatment of domestic waste according to claim 1, characterized in that, The above S7 includes: S7.

1. Obtain a high-density formed fuel sample, and measure its compressive strength and shear strength through a mechanical strength testing device to obtain initial strength data; S7.

2. According to the initial strength data, compare it with the preset abrasion resistance standard. If the compressive strength or shear strength is lower than the preset standard, mark it as a non-conforming sample to obtain a non-conforming sample set; S7.

3. For the non-conforming sample set, obtain its material composition data, and calculate the density distribution of the samples through the density analysis algorithm to obtain the density distribution characteristics; S7.

4. According to the density distribution characteristics, adopt an intensity optimization algorithm to adjust the formulation parameters of the formed fuel, and obtain the optimized formulation data; S7.

5. Generate new formed fuel samples based on the optimized formulation data, and re-measure the compressive strength and shear strength using a mechanical strength testing device to obtain the updated strength data; S7.

6. According to the updated strength data, judge whether the preset anti-wear standard is met. If it is met, output the solid fuel with optimized strength; S7.

7. If not, return to the density distribution characteristic analysis step and readjust the formulation parameters; S7.

8. Through multiple iterative optimizations, obtain the solid fuel that finally meets the preset anti-wear standard, and obtain the formed fuel data with optimized strength.

9. A method for resource treatment of domestic waste according to claim 1, characterized in that The above S8 includes: S8.

1. Obtain the topography data from the surface of the solid fuel, adopt scanning microscopy technology to generate the first topography image, and obtain the surface topography characteristics; S8.

2. For the first topography image, adopt a denoising algorithm to process it, remove the noise interference, generate the second topography image, and obtain the clear topography data; S8.

3. Extract the microstructure parameters from the second topography image, adopt an edge detection algorithm to identify the grain boundaries and pore distribution, and obtain the microstructure characteristics; S8.

4. According to the microstructure characteristics, calculate the grain size and porosity. If the grain size is greater than the preset threshold and the porosity is lower than the preset threshold, judge that the anti-wear force is higher, and obtain the anti-wear force evaluation result; S8.

5. For the anti-wear force evaluation result, adopt a regression analysis algorithm to fit the relationship between the microstructure and the anti-wear force, generate a performance prediction model, and obtain the storage and transportation performance parameters; S8.

6. Adjust the fuel formulation ratio from the storage and transportation performance parameters. If the anti-wear force is lower than the preset standard, increase the content of the strengthening component, generate an optimized formulation plan, and obtain the improved fuel formulation; S8.

7. According to the improved fuel formulation, re-obtain the surface topography data, verify the microstructure change, judge the improvement of the storage and transportation performance, and obtain the final optimized fuel.

10. A method for resource treatment of domestic waste according to claim 1, characterized in that, The above S9 includes: S9.

1. Obtain the flue gas composition data emitted during the sintering process through a flue gas analyzer, and determine the concentration values of each component in the flue gas; S9.

2. If the concentration value exceeds the preset threshold, calculate the deviation value through an emission model to obtain the fuel parameters that need to be adjusted; S9.

3. According to the adjusted fuel parameters, generate an optimized fuel formulation, and determine the fuel composition that meets the reduction target; S9.

4. Adopt the optimized fuel formulation to simulate the sintering process, and verify whether the flue gas emission is lower than the preset threshold through the simulation data to judge the applicability of the fuel formulation; S9.

5. If the simulation data meets the preset threshold, calculate the resource utilization rate of the fuel product through the resource utilization target constraint to obtain the degree of realization of the resource utilization target; S9.

6. According to the resource utilization rate, adjust the fuel production parameters, generate the final fuel product, and determine the fuel characteristics that meet the reduction and resource utilization targets; S9.

7. Conduct an actual sintering test on the final fuel product through a flue gas analyzer to verify the flue gas composition data and judge the emission control effect.