Intelligent analysis method for influence of oxygen flux on coal combustion process and determination index

By acquiring and preprocessing multi-dimensional data, and combining dynamic models and intelligent diagnostic algorithms, a comprehensive intelligent analysis of oxygen flux on the coal combustion process and judgment indicators was achieved. This solved the problem of insufficient accuracy of analysis results in existing technologies and improved the energy utilization efficiency and scientific regulation of coal combustion systems.

CN122332677APending Publication Date: 2026-07-03CHINA UNIV OF GEOSCIENCES (BEIJING)
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610461774.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-09
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

Existing technologies lack a systematic and comprehensive analysis of the relationship between oxygen flux and the coal combustion process, making it impossible to monitor in real time and provide accurate decision-making basis. This results in insufficient accuracy and comprehensiveness of the analysis results, making it difficult to meet the needs of intelligent industrial transformation and energy conservation and emission reduction.

Method used

By collecting and preprocessing multi-dimensional data, a multi-dimensional data collection matrix is ​​constructed. The coal-fired oxygen transport coupling dynamics model is invoked, and the coal-fired oxygen efficiency multi-factor collaborative algorithm and the oxygen flux coal-fired state intelligent diagnosis algorithm are combined to perform oxygen efficiency quantitative analysis and real-time diagnosis under the multi-factor coupling effect. Multi-source data are integrated for quantitative calculation, and a nonlinear correlation model is constructed to realize comprehensive intelligent analysis of oxygen flux on the coal combustion process and judgment indicators.

Benefits of technology

It achieves precise capture of dynamic changes in oxygen flux, the entire coal combustion process, and various judgment indicators, improving the accuracy and comprehensiveness of analysis results, enhancing dynamic response capabilities, enabling real-time monitoring of the coal combustion process and providing reliable decision-making basis, thus meeting the needs of industrial intelligent transformation and energy conservation and emission reduction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122332677A_ABST
    Figure CN122332677A_ABST
Patent Text Reader

Abstract

This invention discloses an intelligent analysis method for the impact of oxygen flux on the coal combustion process and its judgment indicators. The method includes: collecting real-time dynamic data of oxygen flux, coal quality characteristic parameters, combustion environment parameters, and correlation parameters of the judgment indicators, and constructing a multi-dimensional data acquisition matrix; subsequently, using a dedicated kinetic model to establish a dynamic correlation between oxygen flux and combustion reaction rate and mass transfer efficiency; achieving quantitative analysis of oxygen efficiency through a multi-factor collaborative algorithm; identifying combustion state parameters based on an intelligent diagnostic algorithm; and then integrating the aforementioned analysis results using a multi-characteristic calculation system to complete the quantitative calculation of the impact of oxygen flux on combustion judgment indicators. Finally, a nonlinear correlation model is constructed to achieve comprehensive intelligent analysis. This invention comprehensively improves the energy utilization efficiency and scientific regulation of coal combustion systems, adapting to the actual needs of industrial intelligent transformation and energy conservation and emission reduction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of intelligent analysis technology for coal combustion, and in particular to an intelligent analysis method for the influence of oxygen flux on the coal combustion process and its judgment indicators. Background Technology

[0002] Coal combustion is a core form of energy conversion in industrial production and energy supply. The stability, efficiency, and pollutant emission levels of its combustion process are directly related to energy utilization efficiency and sustainable ecological environment development. Oxygen flux, as a key parameter regulating the coal combustion reaction process, profoundly affects multiple core indicators such as ignition characteristics, combustion intensity, burnout degree, temperature field distribution, and combustion efficiency by altering the reaction conditions on the coal particle surface, the mass transfer laws in the combustion space, and the formation pathways of reaction products. With the accelerated intelligent transformation of industry and the continuous improvement of energy conservation and emission reduction requirements, traditional coal combustion analysis methods based on experience-based control or single-parameter monitoring are no longer adequate for the precise control needs of complex combustion systems. There is an urgent need to develop technical methods that can systematically integrate multi-dimensional parameters, capture multi-factor coupling effects, and achieve dynamic real-time analysis to provide scientific support for the optimized operation of coal combustion systems.

[0003] Existing technologies have two prominent drawbacks: First, they lack a systematic and comprehensive approach to the correlation analysis between oxygen flux and the coal combustion process. They focus only on a single parameter or local reaction stage in isolation, failing to fully consider the synergistic effect of multiple factors such as coal quality characteristics and combustion environment conditions with oxygen flux. This makes it impossible to fully capture the comprehensive impact of dynamic changes in oxygen flux on the entire combustion process and various judgment indicators, resulting in insufficient accuracy and comprehensiveness of the analysis results. Second, the analysis process lacks integration and dynamic response capabilities. It has not formed a complete technical chain from data acquisition, multi-factor analysis, state diagnosis to impact quantification, making it difficult to achieve real-time dynamic monitoring and accurate analysis of the coal combustion process. This makes it impossible to provide a fast and reliable decision-making basis for the immediate control of the combustion system, limiting its application effect in actual industrial scenarios. Summary of the Invention

[0004] In order to overcome the shortcomings and deficiencies of existing technologies, this invention provides an intelligent analysis method for the influence of oxygen flux on the coal combustion process and judgment indicators.

[0005] The technical solution adopted in this invention is an intelligent analysis method for the influence of oxygen flux on the coal combustion process and judgment indicators, comprising the following steps: S1, collecting real-time dynamic data of oxygen flux, coal quality characteristic parameters, combustion environment condition parameters, and judgment indicator correlation parameters during the coal combustion process, constructing a multi-dimensional data acquisition matrix and performing data correlation mapping; S2, based on the collected multi-dimensional data, calling the coal combustion oxygen transport coupling dynamics model to establish a dynamic correlation mechanism between oxygen flux and coal combustion reaction rate and mass transfer efficiency; S3, through a coal combustion oxygen efficiency multi-factor collaborative algorithm, integrating oxygen flux gradient change, coal particle surface reactivity parameters, and combustion space... S4. Using an intelligent diagnostic algorithm for coal combustion state based on oxygen flux, the ignition characteristics, combustion intensity, and burnout degree of the coal combustion process are diagnosed and identified in real time. S5. Based on the multi-characteristic calculation system for coal combustion based on oxygen flux, the analytical results of S2-S4 are integrated to complete the quantitative calculation of the influence of oxygen flux on the coal combustion temperature field distribution, reaction product composition, and combustion efficiency judgment index. S6. Based on the quantitative calculation results of S5, a nonlinear correlation model between oxygen flux and coal combustion judgment index is constructed to complete the comprehensive intelligent analysis of the influence of oxygen flux on the coal combustion process and judgment index.

[0006] Furthermore, the expression for the coal-fuel-oxygen transport coupled dynamics model is as follows: ,in, Let Oxygen flux be the spatiotemporal distribution function. The effective diffusion coefficient of oxygen in the pores of coal particles. For the Laplace operator, The rate constant for the coal-oxygen reaction is... The activation energy for coal combustion reaction, This is the universal gas constant. Let be the spatiotemporal distribution function of temperature in the combustion system. This is the oxygen flux adsorption efficiency factor. For spatial coordinate vectors, It is a time variable.

[0007] Furthermore, the expression for the coal combustion oxygen efficiency multi-factor collaborative algorithm is as follows: ,in, The synergistic coefficient of coal combustion and oxygen efficiency. , , These are multi-factor weighting coefficients. This represents the change in oxygen flux. For time intervals, It is a coal-quality reactive factor. The oxygen concentration uniformity factor in the combustion space. This represents the maximum oxygen flux value. This is the minimum oxygen flux value. This is the density factor of reaction sites on the surface of coal particles.

[0008] Furthermore, the expression for the intelligent diagnosis algorithm for oxygen flux and coal combustion state is as follows: ,in, This is the diagnostic coefficient for coal combustion status. , , , For diagnostic weighting coefficients, The characteristic parameter of coal particle ignition delay. It is an oxygen flux-dependent combustion intensity function. This is a parameter for the completeness of the coal combustion reaction. Let be the burnout characteristic function under the influence of oxygen flux. This is a correlation factor for combustion product components.

[0009] Furthermore, the characteristic parameter coupling expression of the oxygen flux coal combustion multi-characteristic calculation system is as follows: ,in, This is a comprehensive quantitative value of multiple characteristics of coal combustion. , , The characteristic coupling coefficient, It is a time-dependent combustion temperature parameter. These are parameters representing the concentration of combustion product components. This is a time series of the oxygen efficiency synergy coefficient. To calculate the start time, To calculate the termination time, This is a time series of oxygen flux gradient.

[0010] Furthermore, the intelligent analysis correlation expression for the impact of oxygen flux on coal combustion judgment indicators is as follows: ,in, To influence the analysis of quantitative indices, , For correlation weight coefficients, , Oxygen flux parameters under different operating conditions. For the first Oxygen flux response function for each judgment index. For the first One combustion determination index parameter, For the first The gradient of the change of each judgment indicator For the first Oxygen flux correlation function for each combustion process parameter For the first One combustion process parameter, , These represent the number of judgment indicators and process parameters, respectively.

[0011] Further, step S3 includes the following sub-steps: S31, based on the dynamic data of oxygen flux, coal particle pore structure parameters, and combustion environment pressure parameters collected during coal combustion, determine the basic input parameter set in the coal combustion oxygen efficiency multi-factor collaborative algorithm, and establish a preliminary mapping relationship between each parameter and oxygen efficiency through data correlation analysis; S32, combined with the spatiotemporal distribution characteristics of oxygen flux, dynamically calibrate the coal quality reactivity factor and the oxygen concentration distribution uniformity factor in the combustion space to eliminate coupling interference between parameters; S33, substitute the calibrated multi-factor parameters into the coal combustion oxygen efficiency multi-factor collaborative algorithm, and perform oxygen efficiency quantification analysis through hierarchical iterative calculation; S34, verify the validity of the quantification analysis results, remove abnormal data points, and correct algorithm calculation deviations.

[0012] Further, S4 includes the following sub-steps: S41, extracting ignition characteristic parameters, combustion intensity parameters, burnout parameters, and dynamic changes in oxygen flux during the coal combustion process to construct an intelligent diagnostic input dataset; S42, based on the intelligent diagnostic algorithm for coal combustion state using oxygen flux, setting diagnostic threshold ranges and parameter association rules to establish a multi-dimensional diagnostic model; S43, substituting the input dataset into the diagnostic model, and performing real-time identification of the coal combustion state through feature matching and logical reasoning; S44, generating a state diagnostic report based on the identification results, clarifying the degree of influence and correlation law of oxygen flux on each combustion state parameter.

[0013] Further, S5 includes the following sub-steps: S51, integrating the kinetic model analysis results of S2, the oxygen efficiency quantification data of S3, and the state diagnosis information of S4 to construct a multi-source data fusion matrix; S52, calling the core calculation module of the oxygen flux coal combustion multi-characteristic calculation system, and setting the calculation dimensions and accuracy requirements for temperature field distribution, reaction product composition, and combustion efficiency judgment indicators; S53, quantifying the correlation between oxygen flux and each judgment indicator through the system's built-in multi-parameter coupling calculation logic; S54, outputting the calculation results and performing data formatting processing to provide standardized data support for the construction of the nonlinear correlation model in S6.

[0014] A method for intelligent analysis of the impact of oxygen flux on coal combustion process and its judgment indicators is proposed. This method is implemented through different units, including: a multi-dimensional oxygen flux data acquisition and preprocessing unit, a coal-fired oxygen transport coupled dynamics model construction and solution unit, a coal-fired oxygen efficiency multi-factor collaborative algorithm calculation unit, an intelligent oxygen flux-coal combustion state diagnosis unit, a core processing unit for an oxygen flux-coal combustion multi-characteristic calculation system, and an intelligent analysis and result output unit for oxygen flux impact. The multi-dimensional oxygen flux data acquisition and preprocessing unit and the coal-fired oxygen transport coupled dynamics model construction and solution unit are bidirectionally connected via a data bus for real-time data transmission and model feedback adjustment. The model construction and solution unit, the coal-fired oxygen efficiency multi-factor collaborative algorithm calculation unit, and the oxygen flux coal-fired state intelligent diagnosis unit are sequentially connected to form a stepped data processing link, completing the progressive analysis from model analysis to state diagnosis. The core processing unit of the oxygen flux coal-fired multi-characteristic calculation system establishes data interaction channels with the coal-fired oxygen efficiency multi-factor collaborative algorithm calculation unit and the oxygen flux coal-fired state intelligent diagnosis unit, respectively, to integrate multi-source processing results and perform quantitative calculations. The oxygen flux impact intelligent analysis and result output unit is unidirectionally connected to the core processing unit of the oxygen flux coal-fired multi-characteristic calculation system, receives quantitative calculation data, constructs a nonlinear correlation model, and finally outputs intelligent analysis results.

[0015] Beneficial Effects: This invention proposes an intelligent analysis method for the impact of oxygen flux on the coal combustion process and its judgment indicators. By integrating various key parameters related to coal combustion through multi-dimensional data collection, and utilizing a dedicated model, algorithm, and computing system, it forms a closed-loop analysis from data processing to impact quantification. This breaks through the limitations of traditional techniques that isolate and analyze single parameters, fully integrating the synergistic effects of multi-dimensional factors and oxygen flux. It accurately captures the correlation mechanism between dynamic changes in oxygen flux and the entire coal combustion process and various judgment indicators, significantly improving the accuracy and comprehensiveness of the analysis results. Simultaneously, this method, with its tiered data processing link and multi-unit integrated architecture, achieves integrated processing from data acquisition, multi-factor analysis, state diagnosis to impact quantification, significantly enhancing the dynamic response capability of the analysis process. It can monitor the coal combustion process in real time and quickly output accurate analysis results, providing a reliable decision-making basis for the immediate optimization and control of the combustion system. This effectively solves the problems of insufficient integration and lack of dynamic response in existing technologies, comprehensively improving the energy utilization efficiency and scientific control of coal combustion systems, and adapting to the actual needs of industrial intelligent transformation and energy conservation and emission reduction. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the overall process of the method of the present invention. Figure 2 This is a flowchart of method step S3 of the present invention; Figure 3 This is a flowchart of method step S4 of the present invention; Figure 4 This is a flowchart of step S5 of the method of the present invention; Figure 5 This is a diagram showing the system unit composition of the present invention. Detailed Implementation

[0017] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0018] like Figure 1 As shown, an intelligent analysis method for the influence of oxygen flux on coal combustion process and judgment indicators includes the following steps: S1, collecting real-time dynamic data of oxygen flux, coal quality characteristic parameters, combustion environment condition parameters and judgment indicator correlation parameters during coal combustion, constructing a multi-dimensional data acquisition matrix and performing data correlation mapping; Specifically, step S1 involves comprehensive collection and correlation mapping of multi-dimensional data. During implementation, a high-precision sensor array deployed in different areas of the combustion furnace is used to collect dynamic oxygen flux data in real time. The collection frequency is set to 20 times per second, covering an oxygen flux range of 0 to 1000. Simultaneously, coal quality characteristic parameters are collected, including the industrial analysis composition, elemental composition, and pore structure parameters of the coal. The pore structure parameters include pore size distribution and porosity. The pore size distribution measurement range is 2 nanometers to 500 nanometers, and the porosity measurement accuracy is controlled within ±0.5%. Combustion environment parameters include the pressure, initial temperature, and airflow velocity of the combustion space. The pressure collection range is 0.1 MPa to 1.0 MPa, the temperature collection range is 25 degrees Celsius to 1500 degrees Celsius, and the airflow velocity collection range is 0.5 meters per second to 10 meters per second. The correlation parameters for the judgment indicators include ignition delay time, peak combustion temperature, burnout rate, and content of reaction product components. After data collection, a multi-dimensional data acquisition matrix is ​​constructed according to data type, including oxygen flux data columns, coal quality characteristic parameter columns, combustion environment condition parameter columns, and judgment index related parameter columns. Through data association algorithms, mapping relationships between different types of parameters are established, clarifying the corresponding correlation dimensions between oxygen flux data and coal quality characteristics, combustion environment conditions, and judgment index related parameters. This ensures the accuracy and relevance of data retrieval during subsequent analysis, providing comprehensive and reliable basic data support for subsequent model construction and algorithm calculation. The implementation of this step can achieve complete capture of key parameters related to coal combustion and avoid analytical biases caused by missing data.

[0019] S2, based on the collected multi-dimensional data, calls the coal combustion oxygen transport coupling dynamics model to establish a dynamic correlation mechanism between oxygen flux and coal combustion reaction rate and mass transfer efficiency; Specifically, step S2, based on the multi-dimensional data acquisition matrix constructed in S1, initiates the calculation of the coal-fired oxygen transport coupling kinetic model. During implementation, real-time dynamic data of oxygen flux, porosity and reactivity-related parameters from coal quality characteristics, and temperature and pressure parameters from the combustion environment are first extracted from the data matrix. These parameters are used as input variables for the model. During model calculation, the focus is on characterizing the transport law of oxygen flux within coal particles and the combustion space, and the coupling effect between the coal and oxygen reaction. A dynamic correlation between oxygen flux and coal combustion reaction rate is established through model calculation. The reaction rate is calculated based on the spatiotemporal variation trend of oxygen flux, combined with parameters such as the number of active sites on the coal particle surface and the activation energy of the reaction, dynamically outputting reaction rate variation curves under different oxygen flux conditions. Simultaneously, a correlation mechanism between oxygen flux and mass transfer efficiency is established. Mass transfer efficiency includes the diffusion efficiency of oxygen in the pores of coal particles and the diffusion efficiency of combustion products. The model quantifies the efficiency value of mass transfer under different oxygen flux levels by analyzing the matching relationship between the oxygen flux gradient and pore structure parameters. The implementation of this step involves calling a preset model calculation module through computer programming. After inputting the collected multi-dimensional data, the iteration step size of the model calculation is set to 0.01 seconds and the number of iterations is 1000 to ensure the convergence of the calculation results. This reveals the fundamental influence mechanism of oxygen flux on the core reaction process of coal combustion, providing kinetic theoretical support for subsequent oxygen efficiency analysis and state diagnosis, and giving subsequent analysis a clear physicochemical basis.

[0020] S3 uses a multi-factor collaborative algorithm for coal combustion oxygen efficiency to integrate oxygen flux gradient change, coal particle surface reactivity parameters, and oxygen concentration distribution parameters in the combustion space to perform quantitative analysis of oxygen efficiency under the coupling effect of multiple factors. Specifically, step S3 uses a multi-factor collaborative algorithm for coal combustion oxygen efficiency to achieve quantitative analysis of oxygen efficiency. During implementation, key input parameters are first extracted from the data collected in S1 and the model output results in S2, including the oxygen flux gradient change, with a calculation period of 1 second. The gradient change is calculated by the difference in oxygen flux between two adjacent collection times, with a value range of -50 to 50. The coal particle surface reactivity parameter is determined based on the volatile matter content, fixed carbon content, and specific surface area of ​​coal particles in the coal quality analysis. The specific surface area is measured using the BET method with a measurement accuracy of ±0.1 square meters per gram. The oxygen concentration distribution parameter in the combustion space is obtained by interpolating the oxygen concentration data from multiple spatial measurement points to obtain a distribution matrix. The number of measurement points is set to 20, which are evenly distributed in the combustion space. After inputting these parameters into the algorithm, the magnitudes of each parameter are first normalized to a range of 0 to 1. Then, each factor is assigned a corresponding weight according to a preset weighting rule: 30% for oxygen flux gradient change, 40% for coal particle surface reactivity parameters, and 30% for oxygen concentration distribution parameters in the combustion space. The quantification of the synergistic effect of multiple factors is achieved through weighted summation and coupling operations. The algorithm employs a hierarchical computational architecture. First, the contribution of each individual factor to oxygen efficiency is calculated. Then, the interaction between factors is corrected using a coupling coefficient, which is dynamically adjusted based on the combustion environment temperature, ranging from 0.8 to 1.2. The iteration step is 0.005 seconds, stopping when the change in the calculation result is less than 0.001. This step overcomes the limitations of single-factor analysis, comprehensively considering the synergistic effect of multiple factors on oxygen efficiency. The quantification results accurately reflect the actual effect of oxygen flux under different operating conditions, providing a core quantitative basis for subsequent combustion state diagnosis.

[0021] S4 utilizes an intelligent diagnostic algorithm for oxygen flux and coal combustion status to perform real-time diagnosis and identification of ignition characteristics, combustion intensity, and burnout status parameters during the coal combustion process. Specifically, step S4 utilizes an intelligent diagnostic algorithm for coal combustion state based on oxygen flux to perform real-time diagnostic identification of combustion state parameters. During implementation, a diagnostic input dataset is first constructed. The data originates from ignition characteristic parameters (including ignition temperature and ignition delay time), combustion intensity parameters (including combustion rate and heat release rate), burnout parameters (including unburned carbon content and burnout time), and dynamic changes in oxygen flux collected in step S1. The data sampling frequency remains consistent with step S1 at 20 times per second. Simultaneously, the oxygen efficiency quantification results output from step S3 are incorporated as auxiliary diagnostic parameters. Subsequently, the core parameters of the diagnostic algorithm are set, including diagnostic threshold ranges. Based on experimental data of combustion characteristics for different coal types, the ignition temperature threshold range is preset to 300°C to 600°C, the combustion intensity threshold range is 100 to 1000, and the burnout threshold range is 0 to 100. Parameter association rules are established based on the chemical reaction mechanism of coal combustion and extensive experimental data, clarifying the correlation strength and trend of oxygen flux changes with each state parameter. The algorithm employs a combination of feature extraction and logical reasoning. First, it extracts oxygen flux variation features and state parameter variation features from the input data. Feature matching determines the preliminary combustion state category. Then, the logical reasoning module refines the preliminary diagnostic results, eliminating the influence of interfering factors. The diagnostic results are output once per second, including ignition characteristic level, combustion intensity level, burnout level, and corresponding confidence levels. The confidence threshold is set to 0.8; if the level falls below this threshold, a data re-acquisition and re-diagnosis process is triggered. This step enables real-time monitoring and accurate judgment of the coal combustion process, promptly capturing combustion state fluctuations caused by oxygen flux changes. This provides targeted state data support for subsequent multi-characteristic calculations, ensuring the analysis process can dynamically respond to changes in the combustion state.

[0022] S5, based on the oxygen flux coal combustion multi-characteristic calculation system, integrates the analytical results of S2-S4 to complete the quantitative calculation of the influence of oxygen flux on coal combustion temperature field distribution, reaction product composition, and combustion efficiency judgment index. Specifically, step S5 utilizes the oxygen flux coal combustion multi-characteristic calculation system to quantify the impact of oxygen flux on the judgment indicators. During implementation, multi-source data is first integrated, including the analytical results of the coal combustion oxygen transport coupling kinetic model in S2 (reaction rate, mass transfer efficiency data), the oxygen efficiency quantification data in S3, and the state diagnosis information in S4 (ignition characteristics, combustion intensity, burnout level, and confidence level). A multi-source data fusion matrix is ​​constructed, with the matrix's row dimension representing time series (with 0.1-second intervals) and the column dimension representing various parameter types. Data fusion employs a weighted average method, with weights allocated according to the reliability level of the parameters: model analytical results have a weight of 0.4, oxygen efficiency quantification data has a weight of 0.3, and state diagnosis information has a weight of 0.3. Subsequently, the system's core calculation module is invoked to set the calculation dimensions for the judgment indicators. The temperature field distribution calculation dimensions include three-dimensional spatial coordinates (x-axis 0 to 10 meters, y-axis 0 to 10 meters, z-axis 0 to 5 meters) and a time dimension (0 to 100 seconds), with calculation accuracy controlled within ±1 degree Celsius. The reaction product composition calculation includes major components such as carbon monoxide, carbon dioxide, and nitrogen oxides, with a calculation accuracy of ±0.1%. The combustion efficiency calculation is based on the ratio of input heat to effective output heat. The input heat considers the lower heating value of coal and the energy carried by oxygen, while the effective output heat is calculated through temperature field distribution and heat dissipation loss. The system establishes a quantitative relationship between oxygen flux and various judgment indicators through its built-in multi-parameter coupled calculation logic. The calculation process adopts the finite element analysis method, with a mesh generation accuracy of 0.1 m × 0.1 m × 0.1 m, iteratively calculating until the convergence error of the calculation results for each indicator is less than 0.5%. This step realizes the quantitative characterization of the impact of oxygen flux on key judgment indicators of coal combustion, integrates the analysis results of previous steps, forms comprehensive quantitative data on the impact, and provides core calculation support for the final intelligent analysis.

[0023] Based on the quantitative calculation results of S5, S6 constructs a nonlinear correlation model between oxygen flux and coal combustion judgment indicators, and completes a comprehensive intelligent analysis of the impact of oxygen flux on the coal combustion process and judgment indicators.

[0024] Specifically, step S6 constructs a nonlinear correlation model based on the quantitative calculation results of S5 to achieve a comprehensive intelligent analysis of the impact of oxygen flux on the coal combustion process and judgment indicators. During implementation, the quantitative data output from S5 is first preprocessed to remove outliers (using the 3σ criterion, where σ is the standard deviation of the data), retaining valid data samples with a sample size of no less than 10,000 sets. The data includes quantitative results for different oxygen flux values ​​(0 to 1000) and under different coal qualities and operating conditions. Then, a suitable nonlinear modeling method is selected, employing a hybrid modeling approach combining multiple nonlinear regression and machine learning algorithms based on data characteristics. The model input variables are oxygen flux parameters, coal quality characteristics, and key parameters of the combustion environment and operating conditions. The output variables are the quantitative results of various judgment indicators (temperature field distribution characteristics, reaction product component content, combustion efficiency, etc.). The modeling process begins by dividing the model into training and testing sets with a ratio of 8:2. The training set is used for model parameter optimization using gradient descent with a learning rate of 0.001 and 10,000 iterations. The testing set is used for model performance validation, with validation metrics including the coefficient of determination (R²) and mean absolute error (MAE). R² must be greater than 0.95, and MAE must be less than 5%. After model construction, inputting oxygen flux and related parameters under any operating condition will output the analysis results of the impact of oxygen flux on the combustion process and judgment indicators, including predicted values, sensitivity of impact, and optimal oxygen flux range for each indicator. This step integrates the analysis results of all preceding steps to form a complete intelligent analysis model, achieving a direct mapping from input parameters to impact results. This provides comprehensive and accurate decision-making basis for the optimization and control of the combustion system, ultimately achieving the goal of intelligent and quantitative analysis of the impact of oxygen flux.

[0025] Preferably, the expression for the coal-fuel-oxygen transport coupled dynamics model is as follows: ,in, Let Oxygen flux be the spatiotemporal distribution function. The effective diffusion coefficient of oxygen in the pores of coal particles. For the Laplace operator, The rate constant for the coal-oxygen reaction is... The activation energy for coal combustion reaction, This is the universal gas constant. Let be the spatiotemporal distribution function of temperature in the combustion system. This is the oxygen flux adsorption efficiency factor. For spatial coordinate vectors, It is a time variable.

[0026] Specifically, the coal-fired oxygen transport coupled kinetic model is based on the law of conservation of mass and the principle of reaction kinetics, combined with the transport law of oxygen in the pores of coal particles and the heterogeneous reaction characteristics of coal and oxygen. Since it is necessary to simultaneously characterize the spatiotemporal evolution of oxygen flux and the dynamic feedback of combustion reaction, the coupling relationship is constructed through partial differential equations. The diffusion term originates from the superposition effect of molecular diffusion and Knudsen diffusion of oxygen in the pores, the reaction term introduces temperature dependence based on the Arrhenius equation, and the introduction of the adsorption efficiency factor is to correct the non-ideality of oxygen adsorption-reaction on the surface of coal particles. This derivation logic conforms to the modeling paradigm of multi-field coupled problems. Key parameter values ​​were determined during modeling: the effective diffusion coefficient of oxygen in coal particle pores was calculated based on coal particle porosity, pore size distribution, and gas molecule motion rate, ranging from one ten-millionth to one hundred-thousandth; the coal-oxygen reaction rate constant was fitted using experimental data from over 500 sets of different coal qualities and temperatures; the activation energy was determined through thermogravimetric experiments at temperatures ranging from 25°C to 1500°C, repeated three times and averaged; the oxygen flux adsorption efficiency factor was dynamically calibrated every 0.1 seconds, combining coal particle surface characteristics and oxygen partial pressure. The model implementation employed computer programming and the finite volume method, discretizing the combustion space into 10,000 grids with a time step of 0.01 seconds, iterating until the difference between adjacent results was less than one millionth, accurately characterizing the coupling mechanism of oxygen transfer and combustion reaction, breaking through the limitations of traditional models, and providing kinetic data with an error within ±3%, supporting subsequent oxygen efficiency analysis.

[0027] Preferably, the expression for the coal combustion oxygen efficiency multi-factor collaborative algorithm is: ,in, The synergistic coefficient of coal combustion and oxygen efficiency. , , These are multi-factor weighting coefficients. This represents the change in oxygen flux. For time intervals, It is a coal-quality reactive factor. The oxygen concentration uniformity factor in the combustion space. This represents the maximum oxygen flux value. This is the minimum oxygen flux value. This is the density factor of reaction sites on the surface of coal particles.

[0028] Specifically, the multi-factor synergistic algorithm for coal combustion oxygen efficiency is based on the multi-factor coupling theory and the weighted summation principle. Since oxygen efficiency is jointly affected by changes in oxygen flux, coal quality activity, and oxygen concentration distribution, and these factors interact, a multi-factor fusion method is used through linear weighting and nonlinear transformation. Logarithmic transformation is used to weaken the influence of extreme oxygen flux values, and square operations are used to enhance the contribution of coal particle surface reaction sites. This derivation is reasonable because it closely aligns with the mechanism of action of each factor on oxygen efficiency. Parameter values ​​during modeling: multi-factor weight coefficients were determined using the analytic hierarchy process (AHP), with scores from 5 experts and a consistency check index less than 0.1; coal quality reactivity factors were calculated using a weighted average of volatile matter yield, fixed carbon content, and pyrolysis rate (0.3:0.4:0.3); the oxygen concentration distribution uniformity factor in the combustion space was determined based on the coefficient of variation of data from 20 measurement points, ranging from 0 to 1; the maximum and minimum oxygen fluxes were extracted using a 10-second sliding window; and the coal particle surface reaction site density factor was determined by specific surface area measurement and active site titration under 0.1 mol / L reagent and 25°C conditions. The algorithm is implemented using modular programming. First, the parameters are standardized to 0 to 1. Then, the factors are coupled through dynamic weights (adjusted every 0.5 seconds according to the temperature and oxygen flux gradients). The computation time is controlled within 0.005 seconds. It fully integrates the multi-dimensional synergistic influences, accurately reflects the true oxygen efficiency level under different working conditions, and provides a core basis for condition diagnosis.

[0029] Preferably, the expression for the intelligent diagnosis algorithm for oxygen flux and coal combustion state is: ,in, This is the diagnostic coefficient for coal combustion status. , , , For diagnostic weighting coefficients, The characteristic parameter of coal particle ignition delay. It is an oxygen flux-dependent combustion intensity function. This is a parameter for the completeness of the coal combustion reaction. Let be the burnout characteristic function under the influence of oxygen flux. This is a correlation factor for combustion product components.

[0030] Specifically, the intelligent diagnostic algorithm for coal combustion state based on oxygen flux is grounded in feature fusion and logical reasoning theory. Since it requires comprehensive judgment of combustion state through multiple parameters, a ratio form is used to construct the diagnostic coefficient. The numerator integrates the correlation features between oxygen flux and core combustion state parameters, while the denominator introduces a suppression term to balance interference factors. This structure effectively amplifies state differences and reduces noise impact, conforming to the parameter fusion logic of intelligent diagnostic algorithms. Parameter values ​​during modeling: the diagnostic weight coefficient was obtained by training a support vector machine with 10,000 sets of experimental data covering various combustion conditions; the coal particle ignition delay feature parameter was measured using high-speed photography at 1000 frames per second with an accuracy of 0.001 seconds; the oxygen flux-dependent combustion intensity function was constructed through correlation experiments with 10 oxygen flux gradients, each with 5 minutes of stable combustion; the coal combustion reaction completeness parameter was measured using gas chromatography with an accuracy of ±0.01%; the burnout characteristic function was obtained by exponentially fitting the relationship between burnout time and oxygen flux, with a goodness of fit greater than 0.98; the combustion product component correlation factor was determined according to the product variation law under different oxygen fluxes, ranging from 0.5 to 2.0. The algorithm employs principal component analysis to extract the top 5 features with a cumulative variance contribution rate greater than 90%, and combines them with more than 200 production rules to construct a logical reasoning module. The diagnostic response time is less than 0.1 seconds and the accuracy rate is greater than 95%, enabling rapid and accurate identification of combustion state fluctuations and providing targeted data support for multi-characteristic calculations.

[0031] Preferably, the characteristic parameter coupling expression of the oxygen flux coal combustion multi-characteristic calculation system is as follows: ,in, This is a comprehensive quantitative value of multiple characteristics of coal combustion. , , The characteristic coupling coefficient, It is a time-dependent combustion temperature parameter. These are parameters representing the concentration of combustion product components. This is a time series of the oxygen efficiency synergy coefficient. To calculate the start time, To calculate the termination time, This is a time series of oxygen flux gradient.

[0032] Specifically, the characteristic parameter coupling expression of the oxygen flux coal combustion multi-characteristic calculation system is based on the principles of energy conservation and multi-parameter integration. Because it is necessary to quantify the cumulative impact of oxygen flux on multiple combustion characteristics, a time-integrated form is used to integrate key parameters such as temperature, product composition, and oxygen efficiency. The linear term characterizes the direct correlation between oxygen flux and temperature and products; the cubic term reflects the nonlinear enhancement effect of oxygen flux; and the gradient term reflects the influence of the spatial distribution of oxygen flux. This derivation is comprehensive because it covers the temporal evolution and coupling relationship of multiple characteristics. Parameter values ​​during modeling: the characteristic coupling coefficient was determined through 125 sets of orthogonal experiments at five levels involving three factors: oxygen flux, combustion temperature, and coal quality characteristics, to determine the optimal combination; the time-dependent combustion temperature parameter was collected 10 times per second by a distributed sensor (one per cubic meter); the combustion product component concentration parameter was measured by an online monitoring device with a response time of less than 0.5 seconds, ranging from 0 to 100%; the oxygen efficiency synergy coefficient time series was extracted from step S3 at 0.1-second intervals; and the oxygen flux gradient time series was calculated using the central difference method from three consecutive acquisition points. The system adopts a parallel computing architecture and is divided into data preprocessing, parameter coupling calculation, and result output modules. The integration accuracy is set to one ten-thousandth, and the results are formatted into a three-dimensional data matrix to realize the quantification of multiple characteristics and the analysis of time cumulative effects, providing standardized data for subsequent nonlinear correlation modeling.

[0033] Preferably, the intelligent analysis correlation expression for the impact of oxygen flux on coal combustion judgment indicators is as follows: ,in, To influence the analysis of quantitative indices, , For correlation weight coefficients, , Oxygen flux parameters under different operating conditions. For the first Oxygen flux response function for each judgment index. For the first One combustion determination index parameter, For the first The gradient of the change of each judgment indicator For the first Oxygen flux correlation function for each combustion process parameter For the first One combustion process parameter, , These represent the number of judgment indicators and process parameters, respectively.

[0034] Specifically, the intelligent analysis correlation expression for the impact of oxygen flux on combustion assessment indicators is based on correlation analysis and normalization theory. Due to the need to quantify the complex correlation between oxygen flux and multiple assessment indicators and process parameters, the numerator and denominator are combined into ratios of the assessment indicator response and the process parameter correlation, respectively. The numerator incorporates the indicator change gradient to enhance sensitivity, while the denominator uses a squared term to weaken the redundant influence of process parameters. This derivation logic aligns with the modeling approach of multivariate impact assessment and can effectively separate the dominant role of oxygen flux. Parameter values ​​during modeling: the correlation weight coefficients are determined through multivariate regression analysis, covering parameter combinations under different operating conditions; the oxygen flux parameter is taken from real-time monitoring values ​​of a multi-dimensional data acquisition matrix; the oxygen flux response function of the assessment indicators and the oxygen flux correlation function of the process parameters are both obtained by fitting a large amount of experimental data; the number of assessment indicators and process parameters is set according to actual analysis needs to ensure coverage of core influencing factors. The algorithm is implemented by first dividing the training and testing sets into an 8:2 ratio. The model parameters are then optimized using gradient descent with a learning rate of 0.001 and 10,000 iterations. The validation criteria are a coefficient of determination greater than 0.95 and a mean absolute error less than 5%. This expression comprehensively quantifies the impact of oxygen flux on combustion performance indicators, providing a precise assessment basis for optimizing and controlling combustion systems, thus meeting the needs of intelligent industrial transformation.

[0035] Preferred, such as Figure 2 As shown, step S3 includes the following sub-steps: S31, based on the dynamic data of oxygen flux, coal particle pore structure parameters, and combustion environment pressure parameters collected during coal combustion, determine the basic input parameter set in the coal combustion oxygen efficiency multi-factor collaborative algorithm, and establish a preliminary mapping relationship between each parameter and oxygen efficiency through data correlation analysis; S32, combined with the spatiotemporal distribution characteristics of oxygen flux, dynamically calibrate the coal quality reactivity factor and the oxygen concentration distribution uniformity factor in the combustion space to eliminate coupling interference between parameters; S33, substitute the calibrated multi-factor parameters into the coal combustion oxygen efficiency multi-factor collaborative algorithm, and perform oxygen efficiency quantification analysis through hierarchical iterative calculation; S34, verify the validity of the quantification analysis results, remove abnormal data points, and correct the algorithm calculation deviation.

[0036] Specifically, the implementation process of the coal combustion oxygen efficiency multi-factor collaborative algorithm in step S3 includes four sub-steps. S31 first extracts dynamic oxygen flux data, coal particle pore structure parameters (pore size distribution measurement range 2 nm to 500 nm, porosity measurement accuracy ±0.5%), and combustion environment pressure parameters (acquisition range 0.1 MPa to 1.0 MPa) from the multi-dimensional data acquisition matrix to construct a basic input parameter set. The Pearson correlation coefficient method is used to establish a preliminary mapping relationship between each parameter and oxygen efficiency, with the correlation coefficient calculation accuracy retained to four decimal places. S32 combines the spatiotemporal distribution characteristics of oxygen flux (gradient change data at a acquisition frequency of 20 times per second) to analyze coal quality reactivity factors and combustion space oxygen concentration. The distribution uniformity factor is dynamically calibrated, and the least squares method is used to eliminate coupling interference between parameters. The calibration iteration step is set to 0.005 seconds. In S33, the calibrated multi-factor parameters are substituted into the algorithm according to preset weights (oxygen flux gradient 30%, coal quality activity 40%, oxygen concentration distribution 30%). Oxygen efficiency quantification is achieved through three-layer iterative calculation: the first layer calculates the contribution value of a single factor, the second layer corrects the interaction of factors, and the third layer outputs the comprehensive quantification result. In S34, the 3σ criterion is used to verify the validity of the quantification result, and outlier data points deviating from the mean by more than three standard deviations are removed. The algorithm calculation deviation is corrected by linear interpolation, and the data error after correction is controlled within ±2%. This step-by-step implementation ensures the accuracy of the input, the scientific nature of the calculation, and the reliability of the results of the multi-factor collaborative algorithm through progressive operations, providing high-precision oxygen efficiency data support for subsequent combustion state diagnosis.

[0037] Preferred, such as Figure 3 As shown, step S4 includes the following sub-steps: S41, extracting ignition characteristic parameters, combustion intensity parameters, burnout parameters, and dynamic changes in oxygen flux during the coal combustion process to construct an intelligent diagnostic input dataset; S42, based on the oxygen flux coal combustion state intelligent diagnostic algorithm, setting diagnostic threshold ranges and parameter association rules to establish a multi-dimensional diagnostic model; S43, substituting the input dataset into the diagnostic model, and performing real-time identification of the coal combustion state through feature matching and logical reasoning; S44, generating a state diagnostic report based on the identification results, clarifying the degree of influence and correlation law of oxygen flux on each combustion state parameter.

[0038] Specifically, the implementation process of the intelligent diagnostic algorithm for oxygen flux and coal combustion status in step S4 is standardized through four sub-steps: S41 extracts the ignition characteristic parameters (ignition temperature 300°C to 600°C, ignition delay time measurement accuracy 0.001 seconds), combustion intensity parameters (combustion rate acquisition frequency 20 times per second), burnout parameters (unburned carbon content measurement accuracy ±0.1%) and dynamic changes in oxygen flux collected in S1, and integrates the oxygen efficiency quantification results output in S3 to construct an intelligent diagnostic input dataset including more than 10,000 samples; S42, based on the core logic of the diagnostic algorithm, sets the ignition temperature threshold range of 300°C to 600°C, the combustion intensity threshold range of 100 to 1000, and the combustion rate... The burnout threshold ranges from 0 to 100. Based on the chemical reaction mechanism of coal combustion, more than 200 parameter association rules are established to clarify the correlation strength threshold between oxygen flux changes and various state parameters. In step S43, the input dataset is divided into training and testing sets in an 8:2 ratio and substituted into the multi-dimensional diagnostic model. Feature matching is performed using the K-nearest neighbor algorithm (K value set to 5). The initial diagnostic results are corrected using a logical reasoning module. During the reasoning process, a secondary matching is triggered when the confidence level falls below 0.8. Step S44 generates a state diagnostic report based on the final identification results, including ignition characteristic level, combustion intensity level, burnout level, and corresponding confidence levels. This clarifies the impact of every 10-unit change in oxygen flux on each combustion state parameter. The report is output once per second. This step-by-step implementation, through a complete process of data extraction, model setting, real-time identification, and report generation, achieves accurate and rapid diagnosis of coal combustion status, promptly capturing combustion state fluctuations caused by oxygen flux, and providing targeted data for subsequent multi-characteristic calculations.

[0039] Preferred, such as Figure 4 As shown, S5 includes the following sub-steps: S51, integrating the kinetic model analysis results of S2, the oxygen efficiency quantification data of S3, and the state diagnosis information of S4 to construct a multi-source data fusion matrix; S52, calling the core calculation module of the oxygen flux coal combustion multi-characteristic calculation system, and setting the calculation dimensions and accuracy requirements of temperature field distribution, reaction product composition, and combustion efficiency judgment indicators; S53, quantifying the correlation between oxygen flux and various judgment indicators through the system's built-in multi-parameter coupling calculation logic; S54, outputting the calculation results and performing data formatting processing to provide standardized data support for the construction of the nonlinear correlation model in S6.

[0040] Specifically, the oxygen flux coal combustion multi-characteristic calculation system operation process in step S5 is executed in four sub-steps: S51 integrates the kinetic model analysis results from S2 (reaction rate, mass transfer efficiency data, time step 0.01 seconds), S3 oxygen efficiency quantification data (updated every 0.1 seconds), and S4 state diagnostic information (level data output once per second). A multi-source data fusion matrix is ​​constructed using a weighted average method, with a matrix dimension of 1000 rows (time series) × 50 columns (parameter types), and the weight allocation is 0.4 for model results, 0.3 for oxygen efficiency data, and 0.3 for diagnostic information; S52 calls the system's core calculation module, sets the calculation dimensions of the judgment index, and sets the temperature field distribution according to x-axis 0 to 10 meters, y-axis 0 to 10 meters, ... The system employs a three-dimensional spatial division from 0 to 5 meters along the z-axis, with a calculation accuracy of ±1 degree Celsius. The reaction product components include carbon monoxide and carbon dioxide, with a calculation accuracy of ±0.1%. Combustion efficiency is calculated based on the input-to-output heat ratio. In step S53, the system utilizes its built-in multi-parameter coupled calculation logic and employs finite element analysis to quantify the correlation between oxygen flux and various performance indicators. The mesh division accuracy is 0.1 m × 0.1 m × 0.1 m, and iterative calculations stop when the convergence error is less than 0.5%. Step S54 formats the calculation results according to time series and parameter type, converting them into standardized CSV format data, retaining three decimal places. This provides structurally unified and accurate data support for the construction of the nonlinear correlation model in step S6. This step-by-step implementation, through multi-source data integration, calculation parameter configuration, precise quantification, and data formatting, ensures that the multi-characteristic calculation system can comprehensively integrate the results of previous analyses, achieving a quantitative and systematic characterization of the impact of oxygen flux on combustion performance indicators.

[0041] like Figure 5As shown, an intelligent analysis method for the impact of oxygen flux on coal combustion process and judgment indicators is proposed. This method is implemented through different units, including: a multi-dimensional oxygen flux data acquisition and preprocessing unit, a coal-fired oxygen transport coupling dynamics model construction and solution unit, a coal-fired oxygen efficiency multi-factor collaborative algorithm calculation unit, an intelligent oxygen flux coal-fired state diagnosis unit, a core processing unit for an oxygen flux coal-fired multi-characteristic calculation system, and an intelligent analysis and result output unit for oxygen flux impact. The multi-dimensional oxygen flux data acquisition and preprocessing unit and the coal-fired oxygen transport coupling dynamics model construction and solution unit are bidirectionally connected via a data bus for real-time data transmission and model feedback adjustment. The dynamic model construction and solution unit, the coal-fired oxygen efficiency multi-factor collaborative algorithm calculation unit, and the oxygen flux coal-fired state intelligent diagnosis unit are sequentially connected to form a stepped data processing link, completing the progressive analysis from model analysis to state diagnosis. The core processing unit of the oxygen flux coal-fired multi-characteristic calculation system establishes data interaction channels with the coal-fired oxygen efficiency multi-factor collaborative algorithm calculation unit and the oxygen flux coal-fired state intelligent diagnosis unit, respectively, to integrate multi-source processing results and perform quantitative calculations. The oxygen flux impact intelligent analysis and result output unit is unidirectionally connected to the core processing unit of the oxygen flux coal-fired multi-characteristic calculation system, receives quantitative calculation data, constructs a nonlinear correlation model, and finally outputs intelligent analysis results.

[0042] An intelligent analysis method for the impact of oxygen flux on coal combustion processes and judgment indicators is proposed. This method integrates multi-dimensional key parameters to construct a complete data system and utilizes a technical framework to achieve full-process coverage from data acquisition to impact quantification, breaking through the limitations of traditional techniques that isolate and analyze single parameters. The method deeply integrates the synergistic effects of oxygen flux with coal quality characteristics, combustion environment, and other factors, comprehensively capturing the integrated impact of dynamic changes in oxygen flux on the entire combustion process. Simultaneously, through tiered data processing and a multi-unit integrated architecture, it achieves real-time diagnosis of combustion status and accurate quantification of judgment indicators, significantly improving the comprehensiveness and reliability of the analysis results.

[0043] This method addresses the lack of systematic approach in traditional analysis by comprehensively characterizing the correlation mechanism between oxygen flux, combustion process, and judgment indicators through multi-factor fusion analysis and a complete technical chain, eliminating biases caused by single-dimensional analysis. Addressing the shortcomings of existing technologies in integration and dynamic response, it constructs a closed-loop system from data acquisition and model analysis to result output using a multi-unit collaborative architecture and real-time data processing logic. This enables dynamic monitoring and rapid analysis of the combustion process, providing a reliable basis for real-time control of the combustion system. It effectively adapts to the actual needs of industrial intelligent transformation and energy conservation and emission reduction, significantly improving the scientific nature of coal combustion system control and energy utilization efficiency.

[0044] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," "link," and "fix" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0045] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An intelligent analysis method for the influence of oxygen flux on the coal combustion process and the determination index, characterized in that, Includes the following steps: S1 collects real-time dynamic data of oxygen flux, coal quality characteristics, combustion environment conditions, and judgment index correlation parameters during coal combustion, constructs a multi-dimensional data acquisition matrix, and performs data correlation mapping. S2, based on the collected multi-dimensional data, calls the coal combustion oxygen transport coupling dynamics model to establish a dynamic correlation mechanism between oxygen flux and coal combustion reaction rate and mass transfer efficiency; S3 uses a multi-factor collaborative algorithm for coal combustion oxygen efficiency to integrate oxygen flux gradient change, coal particle surface reactivity parameters, and oxygen concentration distribution parameters in the combustion space to perform quantitative analysis of oxygen efficiency under the coupling effect of multiple factors. S4 utilizes an intelligent diagnostic algorithm for oxygen flux and coal combustion status to perform real-time diagnosis and identification of ignition characteristics, combustion intensity, and burnout status parameters during the coal combustion process. S5, based on the oxygen flux coal combustion multi-characteristic calculation system, integrates the analytical results of S2-S4 to complete the quantitative calculation of the influence of oxygen flux on coal combustion temperature field distribution, reaction product composition, and combustion efficiency judgment index. Based on the quantitative calculation results of S5, S6 constructs a nonlinear correlation model between oxygen flux and coal combustion judgment indicators, and completes a comprehensive intelligent analysis of the impact of oxygen flux on the coal combustion process and judgment indicators.

2. The intelligent analysis method for the influence of oxygen flux on coal combustion process and judgment indicators according to claim 1, characterized in that, The coal combustion oxygen transport coupled kinetics model expression is: wherein, is an oxygen flux spatiotemporal distribution function, is an effective diffusion coefficient of oxygen in coal particle pores, is a Laplace operator, is a coal-oxygen reaction rate constant, is a coal combustion reaction activation energy, is a universal gas constant, is a combustion system temperature spatiotemporal distribution function, is an oxygen flux adsorption efficiency factor, is a spatial coordinate vector, is a time variable.

3. The intelligent analysis method for the influence of oxygen flux on coal combustion process and judgment indicators according to claim 1, characterized in that, The expression for the coal combustion oxygen efficiency multi-factor collaborative algorithm is as follows: ,in, The synergistic coefficient of coal combustion and oxygen efficiency. , , These are multi-factor weighting coefficients. This represents the change in oxygen flux. For time intervals, It is a coal-quality reactive factor. The oxygen concentration uniformity factor in the combustion space. This represents the maximum oxygen flux value. This is the minimum oxygen flux value. This is the density factor of reaction sites on the surface of coal particles.

4. The intelligent analysis method for the influence of oxygen flux on coal combustion process and judgment indicators according to claim 1, characterized in that, The expression for the intelligent diagnostic algorithm for oxygen flux and coal combustion status is as follows: ,in, This is the diagnostic coefficient for coal combustion status. , , , For diagnostic weighting coefficients, The characteristic parameter for coal particle ignition delay. It is an oxygen flux-dependent combustion intensity function. This is a parameter for the completeness of the coal combustion reaction. Let be the burnout characteristic function under the influence of oxygen flux. This is a correlation factor for combustion product components.

5. The intelligent analysis method for the influence of oxygen flux on coal combustion process and judgment indicators according to claim 1, characterized in that, The characteristic parameter coupling expression of the oxygen flux coal combustion multi-characteristic calculation system is as follows: ,in, This is a comprehensive quantitative value of multiple characteristics of coal combustion. , , The characteristic coupling coefficient, It is a time-dependent combustion temperature parameter. These are parameters representing the concentration of combustion product components. This is a time series of the oxygen efficiency synergy coefficient. To calculate the start time, To calculate the termination time, This is a time series of oxygen flux gradient.

6. The intelligent analysis method for the influence of oxygen flux on coal combustion process and judgment indicators according to claim 1, characterized in that, The intelligent analysis correlation expression for the impact of oxygen flux on coal combustion judgment indicators is as follows: ,in, To influence the analysis of quantitative indices, , For correlation weight coefficients, , Oxygen flux parameters under different operating conditions. For the first Oxygen flux response function for each judgment index. For the first One combustion determination index parameter, For the first The gradient of the change of each judgment indicator For the first Oxygen flux correlation function for each combustion process parameter For the first One combustion process parameter, , These represent the number of judgment indicators and process parameters, respectively.

7. The intelligent analysis method for the influence of oxygen flux on coal combustion process and judgment indicators according to claim 1, characterized in that, S3 includes the following sub-steps: S31, based on the dynamic data of oxygen flux, coal particle pore structure parameters, and combustion environment pressure parameters collected during coal combustion, determine the basic input parameter set in the coal combustion oxygen efficiency multi-factor collaborative algorithm, and establish a preliminary mapping relationship between each parameter and oxygen efficiency through data correlation analysis; S32, combined with the spatiotemporal distribution characteristics of oxygen flux, dynamically calibrate the coal quality reactivity factor and the oxygen concentration distribution uniformity factor in the combustion space to eliminate coupling interference between parameters; S33, substitute the calibrated multi-factor parameters into the coal combustion oxygen efficiency multi-factor collaborative algorithm, and perform oxygen efficiency quantification analysis through hierarchical iterative calculation; S34, verify the validity of the quantification analysis results, remove abnormal data points, and correct the algorithm calculation deviation.

8. The intelligent analysis method for the influence of oxygen flux on coal combustion process and judgment indicators according to claim 1, characterized in that, S4 includes the following sub-steps: S41, extracting ignition characteristic parameters, combustion intensity parameters, burnout parameters, and dynamic changes in oxygen flux during the coal combustion process to construct an intelligent diagnostic input dataset; S42, based on the intelligent diagnostic algorithm for coal combustion state using oxygen flux, setting diagnostic threshold ranges and parameter correlation rules to establish a multi-dimensional diagnostic model; S43, substituting the input dataset into the diagnostic model, and performing real-time identification of the coal combustion state through feature matching and logical reasoning; S44, generating a state diagnostic report based on the identification results, clarifying the degree of influence and correlation patterns of oxygen flux on various combustion state parameters.

9. The intelligent analysis method for the influence of oxygen flux on coal combustion process and judgment indicators according to claim 1, characterized in that, S5 includes the following sub-steps: S51, integrating the kinetic model analysis results from S2, the oxygen efficiency quantification data from S3, and the state diagnostic information from S4 to construct a multi-source data fusion matrix; S52, calling the core calculation module of the oxygen flux coal combustion multi-characteristic calculation system, and setting the calculation dimensions and accuracy requirements for temperature field distribution, reaction product composition, and combustion efficiency judgment indicators; S53, quantifying the correlation between oxygen flux and various judgment indicators through the system's built-in multi-parameter coupling calculation logic; S54, outputting the calculation results and performing data formatting processing to provide standardized data support for the construction of the nonlinear correlation model in S6.

10. The intelligent analysis method for the influence of oxygen flux on coal combustion process and judgment indicators according to any one of claims 1-9, characterized in that, This method is implemented through different units, including: a multi-dimensional oxygen flux data acquisition and preprocessing unit, a coal-fired oxygen transport coupled dynamics model construction and solution unit, a coal-fired oxygen efficiency multi-factor collaborative algorithm calculation unit, an oxygen flux coal-fired state intelligent diagnosis unit, an oxygen flux coal-fired multi-characteristic calculation system core processing unit, and an oxygen flux impact intelligent analysis and result output unit. The oxygen flux multi-dimensional data acquisition and preprocessing unit and the coal-fired oxygen transport coupled dynamics model construction and solution unit are bidirectionally connected via a data bus to perform real-time transmission of acquired data and model feedback adjustment; the coal-fired oxygen transport coupled dynamics model construction and solution unit, the coal-fired... The oxygen efficiency multi-factor collaborative algorithm calculation unit and the oxygen flux coal combustion state intelligent diagnosis unit are connected in series to form a stepped data processing link, completing the progressive analysis from model analysis to state diagnosis. The core processing unit of the oxygen flux coal combustion multi-characteristic calculation system establishes data interaction channels with the coal combustion oxygen efficiency multi-factor collaborative algorithm calculation unit and the oxygen flux coal combustion state intelligent diagnosis unit, respectively, to integrate multi-source processing results and perform quantitative calculations. The oxygen flux impact intelligent analysis and result output unit is unidirectionally connected to the core processing unit of the oxygen flux coal combustion multi-characteristic calculation system, receives quantitative calculation data, constructs a nonlinear correlation model, and finally outputs intelligent analysis results.