Energy engineering digital platform control method and system based on multi-source data fusion

Abstract

This invention discloses a control method and system for an intelligent digital platform in energy engineering based on multi-source data fusion, specifically relating to the field of data analysis, including data entry, data cleaning and preprocessing, comprehensive evaluation, collaborative analysis, trend analysis, and control. By comprehensively entering, cleaning, and preprocessing coal chemical data, this invention establishes a comprehensive evaluation model, achieving precise monitoring and management of the production process. Collaborative analysis improves the overall performance and stability of the production system, while trend analysis provides forward-looking guidance for future production. Ultimately, the control system can issue risk warnings based on real-time data, ensuring production safety. This invention helps optimize production processes, improve production efficiency, reduce production costs and risks, and provides strong support for the digital transformation of energy engineering.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, and more specifically, to a control method and system for an intelligent energy engineering platform based on multi-source data fusion. Background Technology

[0002] In the current coal chemical industry, data monitoring and analysis are crucial for ensuring production safety and efficiency. Existing technologies mainly rely on sensors, instruments, and other equipment to collect various data in real time during the production process. After preliminary processing and organization, this data is used to assess production status, predict potential problems, and formulate optimization strategies. Specifically, after data collection, it typically undergoes steps such as cleaning, screening, and transformation to facilitate subsequent analysis and modeling. Then, statistical methods or machine learning algorithms are used to analyze and mine the data, extracting valuable information and patterns. Finally, based on these analysis results, operators can adjust production parameters and optimize process flows, thereby improving production efficiency and product quality.

[0003] While existing technologies have met the coal chemical industry's needs for data monitoring and analysis to some extent, they still have many shortcomings. First, existing technologies often can only process data from a single source, lacking in-depth exploration and utilization of the relationships between different data sources. This limits the accuracy of data analysis and prediction, making it difficult to detect and resolve some potential problems in the production process in a timely manner. Second, the processing flow of existing technologies is relatively cumbersome, requiring manual intervention in multiple stages, which not only increases operational complexity but may also lead to data errors and human interference. In addition, existing technologies lack intelligent and automated capabilities, failing to achieve real-time, dynamic adjustment and optimization of the production process. These shortcomings limit the further development of the digital transformation of the coal chemical industry. Summary of the Invention

[0004] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a control method and system for an energy engineering digital intelligence platform based on multi-source data fusion, which solves the problems mentioned in the background art through the following solutions.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a control method for an energy engineering digital intelligence platform based on multi-source data fusion, comprising:

[0006] Step 1: Data Entry: This step involves entering coal chemical data into the target energy engineering data platform, including dynamic parameters of the gasification system, parameters of the deep purification process, indicators for enhancing the synthesis reaction, and key parameters for intelligent control.

[0007] Step 2: Data cleaning and preprocessing: This step cleans the data entered in Step 1, removes data that does not conform to physical and chemical principles or actual production logic, fills in missing values, and finally standardizes the cleaned data.

[0008] Step 3: Comprehensive evaluation: The data processed in Step 2 is comprehensively analyzed by establishing mathematical models, including a comprehensive performance evaluation model for the gasification system, an evaluation model for the effect of the deep purification process, an evaluation model for the degree of enhancement of the synthesis reaction, and an evaluation model for the performance of intelligent control.

[0009] Step 4: Synergy Analysis: Based on the analysis results of Step 3, construct an overall synergy index for coal chemical industry and analyze the factors affecting overall synergy;

[0010] Step 5: Trend Analysis: By collecting various indicators of the target coal chemical project at each time point and the overall synergy indicators of coal chemical industry, a corresponding time series dataset is constructed, and the time series of each indicator is smoothed.

[0011] Step 6: Control: Issue control signals based on the time series dataset established in Step 5.

[0012] Preferably, the dynamic parameters of the gasification system include the heat transfer coefficient of the oxygen-enriched preheater membrane, the Reynolds number of carbon particles in the slurry layer, the Von Karman vortex frequency of the gas-solid two-phase flow, and the degree of ionization of plasma-assisted gasification; the deep purification process parameters include the selective Claus conversion sulfur yield, the MDEA solution circulating load rate, the selectivity of CO2 separation by low-temperature methanol washing, and the kinetic constant of trace COS hydrolysis conversion; the synthesis reaction enhancement indicators include the Reynolds-Kolmogorov scale ratio of the microreactor, the Thiele modulus of the porous medium catalyst, the TOF of the surface active sites, and the unsteady-state dynamic response characteristic time; and the key parameters of intelligent control include the process control neural network prediction accuracy RMSE, the multivariable coupling Lyapunov stability index, the condition number of the gain matrix of the fuzzy adaptive PID controller, and the trace of the noise covariance matrix of the state observer.

[0013] Preferably, the heat transfer coefficient of the oxygen-enriched preheater diaphragm is measured using thermocouples and heat flow meters to measure the temperature difference and fluid flow rate at the inlet and outlet of the heat exchanger. The heat transfer coefficient is calculated using heat transfer theory. The Reynolds number of carbon particles in the slurry layer is calculated using fluid dynamics formulas. The fluid velocity is measured using a flow meter, and particle size is analyzed using a particle size analyzer. The Reynolds number is calculated by combining the dynamic viscosity of the fluid. The Von Karman vortex frequency of the gas-solid two-phase flow is detected using a laser Doppler velocity meter to detect the gas-solid two-phase flow trajectory, analyze the vortices generated in the flow field, and calculate the vortex frequency. The plasma-assisted gasification ionization degree is calculated by detecting the ion concentration in the gasification reaction through spectral analysis.

[0014] Preferably, the selective Claus conversion sulfur yield is calculated by collecting the composition of the gas entering and leaving the reactor, quantitatively analyzing the concentrations of SO2 and H2S by gas chromatography, and calculating the sulfur conversion rate. The MDEA solution circulation load rate is calculated by monitoring the inflow and outflow flow rates of the solution using a flow meter, measuring the concentration of MDEA by acid-base titration, and calculating the circulation load rate. The low-temperature methanol washing CO2 separation selectivity is calculated by detecting the concentration changes of CO2 and H2 during the washing process by chromatography, and calculating the separation selectivity by combining flow rate and temperature conditions. The trace COS hydrolysis conversion kinetic constant is obtained by using a continuous flow reactor with FTIR to monitor the concentration changes of COS in the hydrolysis reaction and obtaining the kinetic constant through the reaction rate equation.

[0015] Preferably, the Reynolds-Kolmogorov scale ratio of the microreactor is determined by fluid flow through a microfluidic system, and the flow characteristics are measured using particle image velocimetry to calculate the Reynolds number and Kolmogorov scale. The Thiele modulus of the porous media catalyst is obtained by measuring the diffusion rate and reaction rate of the reactants through static and dynamic experiments, and comparing the results. The Time-of-Flight (TOF) of the surface active sites is calculated by combining the number of active sites on the catalyst surface with catalytic reaction experiments and monitoring the product formation rate. The characteristic time of the unsteady-state dynamic response is monitored using a pulse excitation method to monitor the dynamic response of the reaction system, and the characteristic time is identified using a time-domain analysis method.

[0016] Preferably, the process control neural network prediction accuracy (RMSE) is calculated by inputting real-time process data into a trained neural network for prediction, and the root mean square error between the predicted and actual values ​​is calculated. The multivariable coupling Lyapunov stability index is calculated based on control theory through system state-space modeling. The condition number of the fuzzy adaptive PID controller gain matrix is ​​adjusted according to real-time feedback data, and the condition number is evaluated through numerical analysis. The trace of the state observer noise covariance matrix is ​​obtained by connecting the state observer and the system model, and the covariance between the output noise and the state estimation error is calculated in real time.

[0017] Preferably, the comprehensive performance evaluation model for the gasification system is used to evaluate the dynamic parameters of the gasification system, specifically expressed as follows: GS represents the performance evaluation value of the gasification system, htc represents the heat transfer coefficient of the oxygen-enriched preheater diaphragm, Re represents the Reynolds number of carbon particles in the slurry layer, vk represents the Von Karman vortex frequency of the gas-solid two-phase flow, and id represents the degree of ionization of plasma-assisted gasification.

[0018] Preferably, the deep purification process effect evaluation model is used to analyze the deep purification process parameters, specifically expressed as follows: DP represents the purification effect evaluation value of the deep purification process, cr represents the selective Claus conversion sulfur yield, cl represents the MDEA solution circulation load rate, ss represents the low-temperature methanol washing CO2 separation selectivity, and kr represents the trace COS hydrolysis conversion kinetic constant.

[0019] Preferably, the synthesis reaction enhancement assessment model is used to analyze the synthesis reaction enhancement index, specifically expressed as follows: RE represents the assessment value of the enhancement of the synthesis reaction at the micro level, rk represents the Reynolds-Kolmogorov scale ratio of the microreactor, tm represents the Thiele modulus of the porous media catalyst, tf represents the TOF of the surface active sites, and rt represents the characteristic time of the unsteady dynamic response.

[0020] Preferably, the intelligent control performance evaluation model is used to analyze key parameters of intelligent control, specifically expressed as follows: IC represents the performance evaluation value of the intelligent control system, pe represents the prediction accuracy RMSE of the process control neural network, ls represents the Lyapunov stability index of multivariable coupling, mc represents the condition number of the gain matrix of the fuzzy adaptive PID controller, and cv represents the trace of the noise covariance matrix of the state observer.

[0021] Preferably, the overall synergy index of coal chemical industry is denoted as T, and is specifically represented as follows: .

[0022] Preferably, step 4 quantifies the factors affecting overall synergy by establishing corresponding adaptability indicators, and sets them as vectors. f m Let m be the m-th influencing factor. Using multiple linear regression analysis, a regression model is established between the synergy index T and the influencing factors, specifically expressed as: β0 represents the intercept term, β i (i=1,2,…,m) represents the regression coefficient of the i-th influencing factor, and ε represents the random error term.

[0023] Preferably, the time series dataset is specifically represented as: {(t1, GS1, DP1, RE1, IC1, T1), (t2, GS2, DP2, RE2, IC2, T2), ..., (t n GS n DP n RE n IC n T n )}, t n This represents the nth time node.

[0024] Preferably, step 5 smooths the time series of each indicator using the moving average method. The moving average calculation formula is specifically expressed as follows: M GS，t This represents the moving average of the GS index in period t, where k is the number of terms in the moving average.

[0025] Preferably, when any of the indicators GS, DP, RE, and IC exceed the preset threshold range for at least three periods and shows a deteriorating trend, or when indicator T exceeds the preset threshold range, a risk warning signal is issued to the management personnel terminal.

[0026] Preferably, an energy engineering digital intelligence platform control system based on multi-source data fusion includes a data input module, a data cleaning and preprocessing module, a comprehensive evaluation module, a collaborative analysis module, a trend analysis module, and a control module.

[0027] Preferably, the management personnel terminal specifically includes a mobile APP and a PC.

[0028] Preferably, the data entry module is used to enter coal chemical data into the target energy engineering digital platform, including dynamic parameters of the gasification system, parameters of the deep purification process, indicators of the synthesis reaction enhancement, and key parameters of intelligent control.

[0029] The data cleaning and preprocessing module is used to clean the data entered by the data entry module, remove data that does not conform to physical and chemical principles or actual production logic, fill in missing values, and finally standardize the cleaned data.

[0030] The comprehensive evaluation module establishes mathematical models to comprehensively analyze the data processed by the data cleaning and preprocessing module, including a comprehensive performance evaluation model for the gasification system, an evaluation model for the effect of deep purification process, an evaluation model for the degree of enhancement of the synthesis reaction, and an evaluation model for the performance of intelligent control.

[0031] The collaborative analysis module constructs an overall collaborative performance index for coal chemical industry based on the analysis results of the comprehensive evaluation module, and analyzes the factors affecting the overall collaborative performance.

[0032] The trend analysis module collects various indicators of the target coal chemical project at each time point, as well as the overall synergy indicators of coal chemical industry, to construct a corresponding time series dataset, and smooths the time series of each indicator.

[0033] The control module issues control signals based on the time series dataset established by the trend analysis module.

[0034] Preferably, the operating environment of the energy engineering digital intelligence platform control system based on multi-source data fusion includes a cloud host and a GPU large model simulator.

[0035] The technical effects and advantages of this invention are as follows:

[0036] This invention provides a rich and accurate information foundation for subsequent data processing and analysis by comprehensively and meticulously recording coal chemical data, including dynamic parameters of the gasification system, parameters of deep purification processes, indicators of enhanced synthesis reactions, and key parameters of intelligent control. This facilitates comprehensive monitoring and precise management of the coal chemical production process. By cleaning and preprocessing the entered data, removing data that does not conform to physicochemical principles or actual production logic, filling in missing values, and then standardizing the cleaned data, the quality and usability of the data can be significantly improved. This helps reduce errors and uncertainties in data analysis and provides reliable data support for subsequent mathematical model building and comprehensive analysis. By establishing comprehensive performance evaluation models for the gasification system, evaluation models for the effects of deep purification processes, evaluation models for the degree of enhancement of synthesis reactions, and evaluation models for intelligent control performance, in-depth quantitative analysis of each link in the coal chemical production process can be conducted. This helps to identify problems and bottlenecks in the production process in a timely manner, and optimize the production flow. This provides a scientific basis for improving production efficiency. By constructing overall synergy indicators for coal chemical industry and analyzing factors affecting overall synergy, a holistic understanding and synergistic optimization of the coal chemical production process can be achieved, which helps improve the overall performance and stability of the production system and reduce production costs and risks. By collecting various indicators of the target coal chemical project at each time node and the overall synergy indicators of coal chemical industry, a corresponding time series dataset is constructed, and the time series of each indicator is smoothed. This allows observation of the changing trends of the performance of each link and the overall synergy over time, which helps predict future production conditions and provides forward-looking guidance for formulating and adjusting production plans. Based on the results of trend analysis, when any indicator is found to exceed the preset threshold range and show a deteriorating trend, or when the overall synergy indicator exceeds the preset threshold range, the system will promptly issue a risk warning signal to the management personnel terminal. This helps management personnel respond quickly and take effective measures to prevent production accidents and ensure the stability and safety of the production process. Attached Figure Description

[0037] Figure 1 This is a schematic diagram of the method structure of the present invention.

[0038] Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] refer to Figure 1 The control method for an energy engineering digital intelligence platform based on multi-source data fusion, as shown, includes the following steps:

[0041] Step 1: Data Entry: This step involves entering coal chemical data into the target energy engineering digital platform, including dynamic parameters of the gasification system, parameters of the deep purification process, indicators of the synthesis reaction enhancement, and key parameters of intelligent control.

[0042] The dynamic parameters of the gasification system include the heat transfer coefficient of the oxygen-enriched preheater membrane, the Reynolds number of carbon particles in the slurry layer, the Von Karman vortex frequency of the gas-solid two-phase flow, and the degree of ionization of plasma-assisted gasification. The deep purification process parameters include the selective Claus conversion sulfur yield, the MDEA solution circulating load rate, the selectivity of CO2 separation by low-temperature methanol washing, and the kinetic constant of trace COS hydrolysis conversion. The synthesis reaction enhancement indicators include the Reynolds-Kolmogorov scale ratio of the microreactor, the Thiele modulus of the porous medium catalyst, the TOF of the surface active sites, and the unsteady-state dynamic response characteristic time. The key parameters of intelligent control include the prediction accuracy RMSE of the process control neural network, the Lyapunov stability index of multivariable coupling, the condition number of the gain matrix of the fuzzy adaptive PID controller, and the trace of the noise covariance matrix of the state observer.

[0043] The heat transfer coefficient of the oxygen-enriched preheater diaphragm is measured using thermocouples and heat flow meters to measure the temperature difference and fluid flow rate at the inlet and outlet of the heat exchanger. The heat transfer coefficient is calculated using heat transfer theory. The Reynolds number of carbon particles in the slurry layer is calculated using fluid dynamics formulas. The fluid velocity is measured using a flow meter, and particle size is analyzed using a particle size analyzer. The Reynolds number is calculated by combining the dynamic viscosity of the fluid. The Von Karman vortex frequency of the gas-solid two-phase flow is detected using a laser Doppler velocity meter to detect the gas-solid two-phase flow trajectory, analyze the vortices generated in the flow field, and calculate the vortex frequency. The ionization degree of plasma-assisted gasification is calculated by detecting the ion concentration in the gasification reaction through spectral analysis.

[0044] The selective Claus conversion sulfur yield was calculated by collecting the composition of the inlet and outlet gases of the reactor, quantitatively analyzing the concentrations of SO2 and H2S using gas chromatography, and calculating the sulfur conversion rate. The MDEA solution circulation load rate was calculated by monitoring the inlet and outlet flow rates of the solution using a flow meter, measuring the MDEA concentration using acid-base titration, and calculating the circulation load rate. The low-temperature methanol washing CO2 separation selectivity was calculated by detecting the concentration changes of CO2 and H2 during the washing process using chromatography, and calculating the separation selectivity based on flow rate and temperature conditions. The trace COS hydrolysis conversion kinetic constant was obtained by using a continuous flow reactor with FTIR to monitor the concentration changes of COS in the hydrolysis reaction and obtaining the kinetic constant through the reaction rate equation.

[0045] The Reynolds-Kolmogorov scale ratio of the microreactor is controlled by a microfluidic system for fluid flow, and the flow characteristics are measured using particle image velocimetry to calculate the Reynolds number and Kolmogorov scale. The Thiele modulus of the porous media catalyst is obtained by measuring the diffusion rate and reaction rate of the reactants through static and dynamic experiments. The Time-of-Flight (TOF) of the surface active sites is calculated by combining the number of active sites on the catalyst surface with the catalytic reaction experiments and monitoring the product formation rate. The characteristic time of the unsteady-state dynamic response is monitored using a pulse excitation method to monitor the dynamic response of the reaction system, and the characteristic time is identified using time-domain analysis.

[0046] The process control neural network prediction accuracy (RMSE) is calculated by inputting real-time process data into a trained neural network for prediction, and the root mean square error between the predicted and actual values ​​is calculated. The multivariable coupling Lyapunov stability index is calculated based on control theory through system state-space modeling. The condition number of the fuzzy adaptive PID controller gain matrix is ​​adjusted according to real-time feedback data, and the condition number is evaluated through numerical analysis. The trace of the state observer noise covariance matrix is ​​obtained by connecting the state observer and the system model, and calculating the covariance of the output noise and the state estimation error in real time.

[0047] Step 2: Data cleaning and preprocessing: This step cleans the data entered in Step 1, removes data that does not conform to physical and chemical principles or actual production logic, fills in missing values, and finally standardizes the cleaned data.

[0048] Step 3: Comprehensive evaluation: The data processed in Step 2 is comprehensively analyzed by establishing mathematical models, including a comprehensive performance evaluation model for the gasification system, an evaluation model for the effect of the deep purification process, an evaluation model for the degree of enhancement of the synthesis reaction, and an evaluation model for the performance of intelligent control.

[0049] The comprehensive performance evaluation model for the gasification system is used to evaluate the dynamic parameters of the gasification system, specifically as follows: GS represents the performance evaluation value of the gasification system, ht c denoted by , Re represents the Reynolds number of carbon particles in the slurry layer, vk represents the Von Karman vortex frequency of the gas-solid two-phase flow, and id represents the degree of ionization of plasma-assisted gasification.

[0050] In the comprehensive performance evaluation model of the gasification system This represents the coupling term between heat transfer and turbulence intensity. This indicates the nonlinear relationship between ionization degree and flow characteristics. This represents the overall transmission efficiency of the system. This indicates the overall fluctuation intensity of dynamic parameters in the gasification system.

[0051] The deep purification process effect evaluation model is used to analyze the parameters of the deep purification process, specifically expressed as follows: DP represents the purification effect evaluation value of the deep purification process, cr represents the selective Claus conversion sulfur yield, cl represents the MDEA solution circulation load rate, ss represents the low-temperature methanol washing CO2 separation selectivity, and kr represents the trace COS hydrolysis conversion kinetic constant.

[0052] In the deep purification process effect evaluation model This indicates the periodic effect of conversion rate on cyclic load. This indicates the coupling between dynamics and basic process parameters. This indicates the correlation between separation selectivity and reaction rate. This indicates the overall synergistic performance of the deep purification process.

[0053] The synthesis reaction enhancement assessment model is used to analyze the synthesis reaction enhancement index, specifically expressed as follows: RE represents the assessment value of the enhancement of the synthesis reaction at the micro level, rk represents the Reynolds-Kolmogorov scale ratio of the microreactor, tm represents the Thiele modulus of the porous media catalyst, tf represents the TOF of the surface active sites, and rt represents the characteristic time of the unsteady dynamic response.

[0054] The synthetic reaction enhancement assessment model This represents the exponential relationship between the microscopic scale and catalytic efficiency. This indicates the coupling between dynamic response and mass transfer effect. This represents the characterization of microscopic dynamic properties. This represents the integrated characteristics of diffusion-reaction-response.

[0055] The intelligent control performance evaluation model is used to analyze key parameters of intelligent control, specifically expressed as follows: IC represents the performance evaluation value of the intelligent control system, pe represents the prediction accuracy RMSE of the process control neural network, ls represents the Lyapunov stability index of multivariable coupling, mc represents the condition number of the gain matrix of the fuzzy adaptive PID controller, and cv represents the trace of the noise covariance matrix of the state observer.

[0056] In the intelligent control performance evaluation model This indicates a nonlinear relationship between prediction accuracy and system stability. This indicates the coupling between stability and observation performance. This indicates the relationship between controller performance and noise impact. This indicates the overall performance degradation characteristics of the intelligent control system.

[0057] Step 4: Synergy Analysis: Based on the analysis results of Step 3, construct an overall synergy index for coal chemical industry and analyze the factors affecting overall synergy.

[0058] The overall synergistic index of coal chemical industry is denoted as T, and is specifically represented as follows: .

[0059] The overall synergy index of coal chemical industry integrates the performance indicators of each link through geometric averaging, reflecting the overall effect of the coordinated operation of each link in coal chemical industry from gasification, purification, synthesis to intelligent control.

[0060] Step 4 quantifies the factors affecting overall synergy by establishing corresponding adaptability indicators, which are then set as vectors. f m Let m be the m-th influencing factor. Using multiple linear regression analysis, a regression model is established between the synergy index T and the influencing factors, specifically expressed as: β0 represents the intercept term, β i (i=1,2,…,m) represents the regression coefficient of the i-th influencing factor, and ε represents the random error term.

[0061] Step 4 determines the degree and direction of influence of each factor on the overall synergy by estimating the magnitude and significance of the regression coefficients, and identifies the key factors affecting the synergy of each link in the coal chemical industry.

[0062] Step 5: Trend Analysis: By collecting various indicators of the target coal chemical project at each time point and the overall synergy indicators of coal chemical industry, a corresponding time series dataset is constructed, and the time series of each indicator is smoothed.

[0063] The time series dataset is specifically represented as: {(t1, GS1, DP1, RE1, IC1, T1), (t2, GS2, DP2, RE2, IC2, T2), ..., (t n GS n DP n RE n IC n T n )}, t n This represents the nth time node;

[0064] Step 5 smooths the time series of each indicator using the moving average method. The moving average calculation formula is as follows: M GS，t This represents the moving average of the GS index in period t, where k is the number of terms in the moving average.

[0065] Step 5 applies the same moving average processing to the DP, RE, IC, and T indices; however, this embodiment will not list them all.

[0066] Step 5 involves analyzing the sequence of moving averages of various indicators to observe the changing trends of performance in each stage and overall synergy over time, thereby determining the development status of the coal chemical project at different stages and whether it is undergoing continuous optimization and improvement or facing potential problems.

[0067] Step 6: Control: Issue control signals based on the time series dataset established in Step 5.

[0068] When any of the indicators GS, DP, RE, and IC exceed the preset threshold range for at least three periods and shows a worsening trend, or when indicator T exceeds the preset threshold range, a risk warning signal is issued to the management personnel terminal.

[0069] The management personnel terminals specifically include mobile apps and PCs.

[0070] refer to Figure 2 A digital platform control system for energy engineering based on multi-source data fusion includes a data input module, a data cleaning and preprocessing module, a comprehensive evaluation module, a collaborative analysis module, a trend analysis module, and a control module.

[0071] The data entry module is used to input coal chemical data into the target energy engineering digital platform, including dynamic parameters of the gasification system, parameters of deep purification process, indicators of synthesis reaction enhancement, and key parameters of intelligent control.

[0072] The data cleaning and preprocessing module is used to clean the data entered by the data entry module, remove data that does not conform to physical and chemical principles or actual production logic, fill in missing values, and finally standardize the cleaned data.

[0073] The comprehensive evaluation module establishes mathematical models to comprehensively analyze the data processed by the data cleaning and preprocessing module, including a comprehensive performance evaluation model for the gasification system, an evaluation model for the effect of deep purification process, an evaluation model for the degree of enhancement of the synthesis reaction, and an evaluation model for the performance of intelligent control.

[0074] The collaborative analysis module constructs an overall collaborative performance index for coal chemical industry based on the analysis results of the comprehensive evaluation module, and analyzes the factors affecting the overall collaborative performance.

[0075] The trend analysis module collects various indicators of the target coal chemical project at each time point, as well as the overall synergy indicators of coal chemical industry, to construct a corresponding time series dataset, and smooths the time series of each indicator.

[0076] The control module issues control signals based on the time series dataset established by the trend analysis module.

[0077] The operating environment of the energy engineering digital intelligence platform control system based on multi-source data fusion includes a cloud host and a GPU large model simulator.

[0078] This invention provides a rich and accurate information foundation for subsequent data processing and analysis by comprehensively and meticulously recording coal chemical data, including dynamic parameters of the gasification system, parameters of deep purification processes, indicators of enhanced synthesis reactions, and key parameters of intelligent control. This facilitates comprehensive monitoring and precise management of the coal chemical production process. By cleaning and preprocessing the entered data, removing data that does not conform to physicochemical principles or actual production logic, filling in missing values, and then standardizing the cleaned data, the quality and usability of the data can be significantly improved. This helps reduce errors and uncertainties in data analysis and provides reliable data support for subsequent mathematical model building and comprehensive analysis. By establishing comprehensive performance evaluation models for the gasification system, evaluation models for the effects of deep purification processes, evaluation models for the degree of enhancement of synthesis reactions, and evaluation models for intelligent control performance, in-depth quantitative analysis of each link in the coal chemical production process can be conducted. This helps to identify problems and bottlenecks in the production process in a timely manner, and optimize the production flow. This provides a scientific basis for improving production efficiency. By constructing overall synergy indicators for coal chemical industry and analyzing factors affecting overall synergy, a holistic understanding and synergistic optimization of the coal chemical production process can be achieved, which helps improve the overall performance and stability of the production system and reduce production costs and risks. By collecting various indicators of the target coal chemical project at each time node and the overall synergy indicators of coal chemical industry, a corresponding time series dataset is constructed, and the time series of each indicator is smoothed. This allows observation of the changing trends of the performance of each link and the overall synergy over time, which helps predict future production conditions and provides forward-looking guidance for formulating and adjusting production plans. Based on the results of trend analysis, when any indicator is found to exceed the preset threshold range and show a deteriorating trend, or when the overall synergy indicator exceeds the preset threshold range, the system will promptly issue a risk warning signal to the management personnel terminal. This helps management personnel respond quickly and take effective measures to prevent production accidents and ensure the stability and safety of the production process.

[0079] Secondly: The accompanying drawings of the embodiments disclosed in this invention only involve the structures involved in the embodiments disclosed in this invention. Other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of this invention can be combined with each other.

[0080] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A control method for an intelligent digital platform for energy engineering based on multi-source data fusion, characterized in that, include: Step 1: Data Entry: This step involves entering coal chemical data into the target energy engineering data platform, including dynamic parameters of the gasification system, parameters of the deep purification process, indicators for enhancing the synthesis reaction, and key parameters for intelligent control. The dynamic parameters of the gasification system include the heat transfer coefficient of the oxygen-enriched preheater membrane, the Reynolds number of carbon particles in the slurry layer, the Von Karman vortex frequency of the gas-solid two-phase flow, and the degree of ionization of plasma-assisted gasification. The deep purification process parameters include the selective Claus conversion sulfur yield, the MDEA solution circulating load rate, the low-temperature methanol washing CO2 separation selectivity, and the trace COS hydrolysis conversion kinetic constant. The synthesis reaction enhancement indicators include the Reynolds-Kolmogorov scale ratio of the microreactor, the Thiele modulus of the porous medium catalyst, the TOF of the surface active sites, and the unsteady-state dynamic response characteristic time. The key parameters of intelligent control include the process control neural network prediction accuracy RMSE, the multivariable coupling Lyapunov stability index, the condition number of the fuzzy adaptive PID controller gain matrix, and the trace of the noise covariance matrix of the state observer. Step 2: Data cleaning and preprocessing: This step cleans the data entered in Step 1, removes data that does not conform to physical and chemical principles or actual production logic, fills in missing values, and finally standardizes the cleaned data. Step 3: Comprehensive evaluation: The data processed in Step 2 is comprehensively analyzed by establishing mathematical models, including a comprehensive performance evaluation model for the gasification system, an evaluation model for the effect of the deep purification process, an evaluation model for the degree of enhancement of the synthesis reaction, and an evaluation model for the performance of intelligent control. The comprehensive performance evaluation model for the gasification system is used to evaluate the dynamic parameters of the gasification system, specifically as follows: GS represents the performance evaluation value of the gasification system. denoted by , Re represents the Reynolds number of carbon particles in the slurry layer, vk represents the Von Karman vortex frequency of the gas-solid two-phase flow, and id represents the degree of ionization of plasma-assisted gasification. The deep purification process effect evaluation model is used to analyze the parameters of the deep purification process, specifically expressed as follows: DP represents the purification effect evaluation value of the deep purification process, cr represents the selective Claus conversion sulfur yield, cl represents the MDEA solution circulation load rate, ss represents the low-temperature methanol washing CO2 separation selectivity, and kr represents the trace COS hydrolysis conversion kinetic constant. The synthesis reaction enhancement assessment model is used to analyze the synthesis reaction enhancement index, specifically expressed as follows: RE represents the assessment value of the enhancement of the synthesis reaction at the micro level, rk represents the Reynolds-Kolmogorov scale ratio of the microreactor, tm represents the Thiele modulus of the porous media catalyst, tf represents the TOF of the surface active sites, and rt represents the characteristic time of the unsteady-state dynamic response. The intelligent control performance evaluation model is used to analyze key parameters of intelligent control, specifically expressed as follows: IC represents the performance evaluation value of the intelligent control system, pe represents the prediction accuracy RMSE of the process control neural network, ls represents the Lyapunov stability index of multivariable coupling, mc represents the condition number of the gain matrix of the fuzzy adaptive PID controller, and cv represents the trace of the noise covariance matrix of the state observer. Step 4: Synergy Analysis: Based on the analysis results of Step 3, construct an overall synergy index for coal chemical industry and analyze the factors affecting overall synergy; Step 5: Trend Analysis: By collecting various indicators of the target coal chemical project at each time point and the overall synergy indicators of coal chemical industry, a corresponding time series dataset is constructed, and the time series of each indicator is smoothed. Step 6: Control: Issue control signals based on the time series dataset established in Step 5.

2. The energy engineering digital intelligence platform control method based on multi-source data fusion according to claim 1, characterized in that: The overall synergistic index of coal chemical industry is denoted as T, and is specifically represented as follows: ; Step 4 quantifies the factors affecting overall synergy by establishing corresponding adaptability indicators, which are then set as vectors. f m Let m be the m-th influencing factor. Using multiple linear regression analysis, a regression model is established between the synergy index T and the influencing factors, specifically expressed as: β0 represents the intercept term, β i (i=1,2,…,m) represents the regression coefficient of the i-th influencing factor, and ε represents the random error term.

3. The energy engineering digital intelligence platform control method based on multi-source data fusion according to claim 1, characterized in that: The time series dataset is specifically represented as: {(t1, GS1, DP1, RE1, IC1, T1), (t2, GS2, DP2, RE2, IC2, T2), ..., (t n GS n DP n RE n IC n T n )}, t n This represents the nth time node; Step 5 smooths the time series of each indicator using the moving average method. The moving average calculation formula is as follows: M GS，t This represents the moving average of the GS index in period t, where k is the number of terms in the moving average.

4. A control system for an energy engineering digital intelligence platform based on multi-source data fusion, used to implement the control method for an energy engineering digital intelligence platform based on multi-source data fusion as described in any one of claims 1-3, characterized in that, include: The system includes a data entry module, a data cleaning and preprocessing module, a comprehensive evaluation module, a collaborative analysis module, a trend analysis module, and a control module.

Images