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

Abstract

The invention discloses an energy engineering digital intelligent platform control method and system based on multi-source data fusion, and particularly relates to the field of data analysis, comprising data entry, data cleaning and preprocessing, comprehensive evaluation, collaborative analysis, trend analysis and control. The coal chemical industry data are comprehensively recorded, cleaned and preprocessed, the comprehensive evaluation model is established, accurate monitoring and management of the production process are achieved, the overall performance and stability of a production system are improved through collaborative analysis, and prospective guidance is provided for future production through trend analysis. Finally, the control system can give out risk early warning according to real-time data, production safety is ensured, the production process can be optimized, production efficiency can be improved, production cost and risks can be reduced, and powerful support is provided for energy engineering digital-intelligent transformation.

Description

Technical Field

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

[0002] In the current coal chemical industry, data monitoring and analysis are the key to ensuring production safety and efficiency. Existing technologies mainly rely on sensors, instruments and other equipment to collect various types of data in the production process in real time. After preliminary processing and organization, these data are used to evaluate production status, predict potential problems and formulate optimization strategies. Specifically, after data collection, they usually go through steps such as cleaning, screening and conversion to facilitate subsequent analysis and modeling. Then, statistical methods or machine learning algorithms are used to analyze and mine the data to extract valuable information and rules. Finally, based on these analysis results, operators can adjust production parameters and optimize process flow to improve production efficiency and product quality.

[0003] Although existing technologies have met the coal chemical industry's needs for data monitoring and analysis to a certain extent, there are still many shortcomings. First, existing technologies can often only process data from a single source and lack in-depth exploration and utilization of the relationship between different data sources, which limits the accuracy of data analysis and prediction, making it difficult to discover and solve some potential problems in the production process in a timely manner. Secondly, the processing flow of existing technologies is relatively cumbersome and requires manual participation in multiple links, which not only increases the complexity of operations, but also may cause data errors and human interference. In addition, existing technologies lack intelligence and automation capabilities and cannot 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] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an energy engineering digital intelligence platform control method and system based on multi-source data fusion, which solves the problems raised in the above-mentioned background technology through the following scheme.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for controlling an energy engineering digital intelligence platform based on multi-source data fusion, comprising: Step 1: Data entry: used to enter coal chemical data into the target energy engineering digital intelligence platform, including gasification system dynamic parameters, deep purification process parameters, synthesis reaction enhancement indicators and intelligent control key parameters; Step 2: Data cleaning and preprocessing: used to clean the data entered in step 1, eliminate data that does not conform to physical and chemical principles or actual production logic, fill in missing values, and finally standardize the cleaned data; Step 3: Comprehensive evaluation: A mathematical model is established to comprehensively analyze the data processed in step 2, including a gasification system comprehensive performance evaluation model, a deep purification process effect evaluation model, a synthesis reaction enhancement degree evaluation model, and an intelligent control performance evaluation model; Step 4: Synergy analysis: Construct the overall synergy index of coal chemical industry based on the analysis results of step 3, and analyze the factors affecting the overall synergy; Step 5: Trend analysis: By collecting various indicators of the target coal chemical project at each time node and the overall synergy indicators of coal chemical industry, the corresponding time series data set is constructed, and the time series of various indicators are smoothed; Step 6: Control: Send a control signal based on the time series data set established in step 5.

[0006] Preferably, the dynamic parameters of the gasification system include the heat transfer coefficient of the oxygen-enriched preheater diaphragm, the Reynolds number of the slurry layer carbon particles, the Von Karman vortex frequency of the gas-solid two-phase flow and the plasma-assisted gasification ionization degree; the deep purification process parameters include the selective Claus conversion sulfur yield, the MDEA solution circulation load rate, the low-temperature methanol washing CO2 separation selectivity and the trace COS hydrolysis conversion kinetic constant; the synthesis reaction enhancement index includes the microreactor Reynolds-Kolmogorov scale ratio, the porous medium catalyst Thiele modulus, the surface active site TOF and the non-steady-state dynamic response characteristic time; the key parameters of intelligent control include the process control neural network prediction accuracy RMSE, the multivariable coupled Lyapunov stability index, the fuzzy adaptive PID controller gain matrix condition number and the state observer noise covariance matrix trace.

[0007] Preferably, the heat transfer coefficient of the oxygen-enriched preheater diaphragm is measured by thermocouples and heat flow meters to measure the temperature difference and fluid flow rate entering and leaving the heat exchanger, and the heat transfer coefficient is calculated using heat exchange theory. The Reynolds number of the slurry layer carbon particles is determined by a fluid mechanics formula, and the fluid flow rate is measured using a flow meter. A particle size analyzer is used to analyze the particle size, and the Reynolds number is calculated in combination with the dynamic viscosity of the fluid. The Von Karman vortex frequency of the gas-solid two-phase flow is detected by a laser Doppler flowmeter to detect the gas-solid two-phase flow trajectory, and the vortex generated by the flow field is analyzed and the vortex frequency is calculated. The plasma-assisted gasification ionization degree is detected by spectral analysis to detect the ion concentration in the gasification reaction, and then the ionization degree is calculated.

[0008] Preferably, the selective Claus conversion sulfur yield is obtained by collecting the components of the gas inlet and outlet of 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 obtained by monitoring the solution inlet and outlet flow rates using a flowmeter, and measuring the MDEA concentration in combination with acid-base titration to calculate the circulation load rate. The low-temperature methanol washing CO2 separation selectivity is obtained by detecting the concentration changes of CO2 and H2 during the washing process by chromatography, and calculating the separation selectivity in combination with flow 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.

[0009] Preferably, the Reynolds-Kolmogorov scale ratio of the microreactor is measured by a microfluidic system for fluid flow, and the flow characteristics are measured by particle image velocimetry technology to calculate the Reynolds number and the Kolmogorov scale. The Thiele modulus of the porous medium catalyst is obtained by static and dynamic experiments, measuring the diffusion rate and reaction rate of the reactants, and comparing the Thiele modulus. The TOF of the surface active sites is calculated by combining the number of active sites on the catalyst surface through catalytic reaction experiments and monitoring the product generation rate. The non-steady-state dynamic response characteristic time uses a pulse excitation method to monitor the dynamic response of the reaction system, and the time domain analysis method is used to identify the characteristic time.

[0010] Preferably, the process control neural network prediction accuracy RMSE is predicted by inputting real-time process data into a trained neural network, calculating the root mean square error between the predicted value and the actual value, the multivariable coupled Lyapunov stability index is modeled through the system state space, and the Lyapunov index is calculated based on control theory, the fuzzy adaptive PID controller gain matrix condition number is adjusted according to real-time feedback data, the condition number is evaluated by numerical analysis, and the state observer noise covariance matrix trace is obtained by connecting the state observer with the system model, calculating the covariance of the output noise and the state estimation error in real time, and obtaining the matrix trace.

[0011] Preferably, the comprehensive performance evaluation model of the gasification system is used to evaluate the dynamic parameters of the gasification system, which is specifically expressed as: , GS represents the operating performance evaluation value of the gasification system, hct represents the heat transfer coefficient of the oxygen-enriched preheater membrane, Re represents the Reynolds number of carbon particles in the slurry layer, vk represents the VonKarman vortex frequency of the gas-solid two-phase flow, and id represents the degree of ionization of plasma-assisted gasification.

[0012] Preferably, the deep purification process effect evaluation model is used to analyze the deep purification process parameters, which is specifically expressed as: , 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.

[0013] Preferably, the synthetic reaction enhancement degree evaluation model is used to analyze the synthetic reaction enhancement index, which is specifically expressed as: , RE represents the evaluation value of the enhancement degree of the synthesis reaction at the microscopic level, rk represents the Reynolds-Kolmogorov scale ratio of the microreactor, tm represents the Thiele modulus of the porous medium catalyst, tf represents the TOF of the surface active sites, and rt represents the characteristic time of the non-steady-state dynamic response.

[0014] Preferably, the intelligent control performance evaluation model is used to analyze key parameters of intelligent control, which is specifically expressed as: , 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 multivariable coupling Lyapunov stability index, mc represents the condition number of the fuzzy adaptive PID controller gain matrix, and cv represents the trace of the state observer noise covariance matrix.

[0015] Preferably, the overall synergy index of coal chemical industry is marked as T, which is specifically expressed as: .

[0016] Preferably, the step 4 quantifies the factors affecting the overall synergy by establishing corresponding adaptability indicators, which are set as vectors , f m Represents the mth influencing factor. Using the multivariate linear regression analysis method, a regression model between the synergy index T and the influencing factors is established, which is 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.

[0017] Preferably, the time series data set is specifically expressed as: {(t1, GS1, DP1, RE1, IC1, T1), (t2, GS2, DP2, RE2, IC2, T2), …, (t n , G.S. n , DP n , R.E. n ,IC n , T n )}, t n Indicates the nth time node.

[0018] Preferably, the step 5 smoothes the time series of each indicator by a moving average method, and the moving average calculation formula is specifically expressed as: , M GS，t It represents the moving average value of GS index in the tth period, and k is the number of moving average items.

[0019] Preferably, when any of the indicators GS, DP, RE and IC exceeds the preset threshold range for at least three cycles and shows a trend of deterioration, or when the indicator T exceeds the preset threshold range, a risk warning signal is sent to the management terminal.

[0020] Preferably, an energy engineering digital intelligence platform control system based on multi-source data fusion 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.

[0021] Preferably, the administrator terminal specifically includes a mobile phone APP and a PC terminal.

[0022] Preferably, the data entry module is used to enter coal chemical data into the target energy engineering digital intelligence platform, including gasification system dynamic parameters, deep purification process parameters, synthesis reaction enhancement indicators and intelligent control key parameters; The data cleaning and preprocessing module is used to clean the data entered by the data entry module, remove the data that does not conform to the physical and chemical principles or the actual production logic, fill in the missing values, and finally standardize the cleaned data; The comprehensive evaluation module comprehensively analyzes the data processed by the data cleaning and preprocessing module by establishing a mathematical model, including a gasification system comprehensive performance evaluation model, a deep purification process effect evaluation model, a synthesis reaction enhancement degree evaluation model, and an intelligent control performance evaluation model; The synergy analysis module constructs the overall synergy index of coal chemical industry according to the analysis results of the comprehensive evaluation module, and analyzes the factors affecting the overall synergy; The trend analysis module collects various indicators of the target coal chemical project at various time nodes and the overall synergy indicators of the coal chemical industry, constructs a corresponding time series data set, and smoothes the time series of various indicators; The control module sends a control signal according to the time series data set established by the trend analysis module.

[0023] 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.

[0024] Technical effects and advantages of the present invention: The present invention comprehensively and meticulously inputs coal chemical data, including gasification system dynamic parameters, deep purification process parameters, synthesis reaction enhancement indicators and intelligent control key parameters, to provide a rich and accurate information basis for subsequent data processing and analysis, which is helpful to achieve comprehensive monitoring and precise management of the coal chemical production process; by cleaning and preprocessing the input data, eliminating data that does not conform to physical and chemical principles or actual production logic, filling in missing values, and then standardizing the cleaned data, the quality and availability of the data can be significantly improved, which helps to reduce errors and uncertainties in data analysis and provide reliable data support for subsequent mathematical model establishment and comprehensive analysis; by establishing a comprehensive performance evaluation model for the gasification system, a deep purification process effect evaluation model, a synthesis reaction enhancement degree evaluation model and an intelligent control performance evaluation model, in-depth quantitative analysis can be performed on each link in the coal chemical production process, which is helpful to timely discover problems and bottlenecks in the production process and to optimize the production flow By constructing the overall synergy index of coal chemical industry and analyzing the factors affecting the overall synergy, the overall grasp and synergistic optimization of the coal chemical production process can be achieved, which is helpful to 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 index of coal chemical industry, constructing the corresponding time series data set, and smoothing the time series of various indicators, the performance of each link and the overall synergy trend over time can be observed, which is helpful to predict future production conditions and provide forward-looking guidance for the formulation and adjustment of production plans; according to the results of trend analysis, when any indicator is found to exceed the preset threshold range and shows a trend of deterioration, or when the overall synergy index exceeds the preset threshold range, the system will promptly send a risk warning signal to the management terminal, which will help managers to respond quickly and take effective measures to prevent production accidents and ensure the stability and safety of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a schematic diagram of the structure of the method of the present invention.

[0026] Figure 2 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] refer to Figure 1 The energy engineering digital intelligence platform control method based on multi-source data fusion shown in the figure includes the following specific steps: Step 1: Data entry: used to enter coal chemical data into the target energy engineering digital intelligence platform, including gasification system dynamic parameters, deep purification process parameters, synthesis reaction enhancement indicators and key parameters of intelligent control.

[0029] The dynamic parameters of the gasification system include the heat transfer coefficient of the oxygen-enriched preheater diaphragm, the Reynolds number of the slurry layer carbon particles, the Von Karman vortex frequency of the gas-solid two-phase flow and the plasma-assisted gasification ionization degree; the deep purification process parameters include the selective Claus conversion sulfur yield, the MDEA solution circulation 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 microreactor Reynolds-Kolmogorov scale ratio, the porous medium catalyst Thiele modulus, the surface active site TOF and the non-steady-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 fuzzy adaptive PID controller gain matrix condition number and the state observer noise covariance matrix trace.

[0030] The heat transfer coefficient of the oxygen-enriched preheater diaphragm is measured by thermocouples and heat flow meters to measure the temperature difference and fluid flow rate entering and leaving the heat exchanger, and the heat transfer coefficient is calculated by applying heat exchange theory. The Reynolds number of the slurry layer carbon particles is calculated by a fluid mechanics formula, and the fluid flow rate is measured by a flow meter. The particle size analyzer is used to analyze the particle size, and the Reynolds number is calculated in combination with the dynamic viscosity of the fluid. The Von Karman vortex frequency of the gas-solid two-phase flow is detected by a laser Doppler flowmeter to detect the gas-solid two-phase flow trajectory, and the vortex generated by the flow field is analyzed and the vortex frequency is calculated. The plasma-assisted gasification ionization degree is detected by spectral analysis to detect the ion concentration in the gasification reaction, and then the ionization degree is calculated.

[0031] The selective Claus conversion sulfur yield is obtained by collecting the components of the gas inlet and outlet of 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 obtained by monitoring the solution inlet and outlet flow rates using a flow meter, and measuring the MDEA concentration in combination with acid-base titration to calculate the circulation load rate. The low-temperature methanol washing CO2 separation selectivity is obtained by detecting the concentration changes of CO2 and H2 during the washing process by chromatography, and calculating the separation selectivity in combination with flow 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 the kinetic constant is obtained through the reaction rate equation.

[0032] The Reynolds-Kolmogorov scale ratio of the microreactor is measured by a microfluidic system for fluid flow, and the flow characteristics are measured by particle image velocimetry technology to calculate the Reynolds number and the Kolmogorov scale. The Thiele modulus of the porous medium catalyst is obtained by static and dynamic experiments, and the diffusion velocity and reaction rate of the reactants are measured and compared to obtain the Thiele modulus. The TOF of the surface active site is calculated by combining the number of active sites on the catalyst surface through catalytic reaction experiments and monitoring the product generation rate. The non-steady-state dynamic response characteristic time uses a pulse excitation method to monitor the dynamic response of the reaction system, and the time domain analysis method is used to identify the characteristic time.

[0033] The process control neural network prediction accuracy RMSE is predicted by inputting real-time process data into a trained neural network, and the root mean square error between the predicted value and the actual value is calculated. The multivariable coupled Lyapunov stability index is modeled through the system state space, and the Lyapunov index is calculated based on control theory. The fuzzy adaptive PID controller gain matrix condition number adjusts the gain of the fuzzy adaptive PID controller according to real-time feedback data, and the condition number is evaluated through numerical analysis. The state observer noise covariance matrix trace is obtained by connecting the state observer with the system model, and the covariance of the output noise and the state estimation error is calculated in real time to obtain the matrix trace.

[0034] Step 2: Data cleaning and preprocessing: used to clean the data entered in step 1, eliminate data that does not conform to physical and chemical principles or actual production logic, fill in missing values, and finally standardize the cleaned data.

[0035] Step 3: Comprehensive evaluation: A mathematical model is established to comprehensively analyze the data processed in step 2, including a comprehensive performance evaluation model for the gasification system, a deep purification process effect evaluation model, a synthesis reaction enhancement degree evaluation model, and an intelligent control performance evaluation model.

[0036] The comprehensive performance evaluation model of the gasification system is used to evaluate the dynamic parameters of the gasification system, which is specifically expressed as: , GS represents the operating performance evaluation value of the gasification system, hct represents the heat transfer coefficient of the oxygen-enriched preheater membrane, Re represents the Reynolds number of carbon particles in the slurry layer, vk represents the VonKarman vortex frequency of the gas-solid two-phase flow, and id represents the degree of ionization of plasma-assisted gasification.

[0037] The comprehensive performance evaluation model of the gasification system represents the coupling term between heat transfer and turbulence intensity, Indicates the nonlinear relationship between ionization degree and flow characteristics, It represents the overall transmission efficiency of the system. It indicates the comprehensive fluctuation intensity of dynamic parameters of gasification system.

[0038] The deep purification process effect evaluation model is used to analyze the deep purification process parameters, which is specifically expressed as: , 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.

[0039] The deep purification process effect evaluation model represents the periodic effect of conversion rate and cycle load, represents the coupling of dynamics and basic process parameters, represents the relationship between separation selectivity and reaction rate, Indicates the overall synergistic performance of the deep purification process.

[0040] The synthetic reaction strengthening degree evaluation model is used to analyze the synthetic reaction strengthening index, which is specifically expressed as: , RE represents the evaluation value of the enhancement degree of the synthesis reaction at the microscopic level, rk represents the Reynolds-Kolmogorov scale ratio of the microreactor, tm represents the Thiele modulus of the porous medium catalyst, tf represents the TOF of the surface active sites, and rt represents the characteristic time of the non-steady-state dynamic response.

[0041] In the synthetic reaction enhancement degree evaluation model represents the exponential relationship between microscopic scale and catalytic efficiency, represents the coupling of dynamic response and mass transfer effect, It represents the characterization of microscopic dynamic performance. Represents the diffusion-reaction-response comprehensive characteristics.

[0042] The intelligent control performance evaluation model is used to analyze the key parameters of intelligent control, which is specifically expressed as: , 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 multivariable coupling Lyapunov stability index, mc represents the condition number of the fuzzy adaptive PID controller gain matrix, and cv represents the trace of the state observer noise covariance matrix.

[0043] The intelligent control performance evaluation model represents the nonlinear relationship between prediction accuracy and system stability, represents the coupling of stability and observation performance, represents the relationship between controller performance and noise impact, Represents the overall performance attenuation characteristics of the intelligent control system.

[0044] Step 4: Synergy analysis: Construct the overall synergy index of coal chemical industry based on the analysis results of step 3, and analyze the factors affecting the overall synergy.

[0045] The overall synergy index of coal chemical industry is marked as T, which is specifically expressed as: .

[0046] The overall synergy index of coal chemical industry combines the performance indicators of each link by means of geometric mean, reflecting the overall effect of the coordinated operation of each link of coal chemical industry from gasification, purification, synthesis to intelligent control.

[0047] Step 4 quantifies the factors affecting the overall synergy by establishing corresponding adaptability indicators, which are set as vectors , f m Represents the mth influencing factor. Using the multivariate linear regression analysis method, a regression model between the synergy index T and the influencing factors is established, which is 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.

[0048] The step 4 determines the degree and direction of the influence of each factor on the overall synergy by estimating the size and significance of the regression coefficient, and finds out the key factors affecting the synergy of various links in the coal chemical industry.

[0049] Step 5: Trend analysis: By collecting various indicators of the target coal chemical project at each time node and the overall synergy indicators of coal chemical industry, the corresponding time series data set is constructed, and the time series of various indicators are smoothed.

[0050] The time series data set is specifically expressed as: {(t1, GS1, DP1, RE1, IC1, T1), (t2, GS2, DP2, RE2, IC2, T2), …, (t n , G.S. n , DP n , R.E. n ,IC n , T n )}, t n Indicates the nth time node; The step 5 smoothes the time series of each indicator by using the moving average method. The moving average calculation formula is specifically expressed as: , M GS，t It represents the moving average value of GS index in the tth period, and k is the number of moving average items.

[0051] The step 5 also performs moving average processing on the DP, RE, IC and T indicators in the same manner, which will not be listed one by one in this embodiment.

[0052] The step 5 analyzes the moving average sequence of each indicator, observes the performance of each link and the changing trend of the overall synergy over time, and judges the development trend of the coal chemical project at different stages, whether it is in continuous optimization and improvement or facing potential problems.

[0053] Step 6: Control: Send a control signal based on the time series data set established in step 5.

[0054] When any of the indicators GS, DP, RE and IC exceeds the preset threshold range for at least three cycles and shows a trend of deterioration, or when the indicator T exceeds the preset threshold range, a risk warning signal is sent to the management terminal.

[0055] The management terminal specifically includes a mobile phone APP and a PC terminal.

[0056] refer to Figure 2 , an energy engineering digital intelligence platform control system based on multi-source data fusion, including 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.

[0057] The data entry module is used to enter coal chemical data into the target energy engineering digital intelligence platform, including gasification system dynamic parameters, deep purification process parameters, synthesis reaction enhancement indicators and intelligent control key parameters; The data cleaning and preprocessing module is used to clean the data entered by the data entry module, remove the data that does not conform to the physical and chemical principles or the actual production logic, fill in the missing values, and finally standardize the cleaned data; The comprehensive evaluation module comprehensively analyzes the data processed by the data cleaning and preprocessing module by establishing a mathematical model, including a gasification system comprehensive performance evaluation model, a deep purification process effect evaluation model, a synthesis reaction enhancement degree evaluation model, and an intelligent control performance evaluation model; The synergy analysis module constructs the overall synergy index of coal chemical industry according to the analysis results of the comprehensive evaluation module, and analyzes the factors affecting the overall synergy; The trend analysis module collects various indicators of the target coal chemical project at various time nodes and the overall synergy indicators of the coal chemical industry, constructs a corresponding time series data set, and smoothes the time series of various indicators; The control module sends a control signal according to the time series data set established by the trend analysis module.

[0058] 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.

[0059] The present invention comprehensively and meticulously inputs coal chemical data, including gasification system dynamic parameters, deep purification process parameters, synthesis reaction enhancement indicators and intelligent control key parameters, to provide a rich and accurate information basis for subsequent data processing and analysis, which is helpful to achieve comprehensive monitoring and precise management of the coal chemical production process; by cleaning and preprocessing the input data, eliminating data that does not conform to physical and chemical principles or actual production logic, filling in missing values, and then standardizing the cleaned data, the quality and availability of the data can be significantly improved, which helps to reduce errors and uncertainties in data analysis and provide reliable data support for subsequent mathematical model establishment and comprehensive analysis; by establishing a comprehensive performance evaluation model for the gasification system, a deep purification process effect evaluation model, a synthesis reaction enhancement degree evaluation model and an intelligent control performance evaluation model, in-depth quantitative analysis can be performed on each link in the coal chemical production process, which is helpful to timely discover problems and bottlenecks in the production process and to optimize the production flow By constructing the overall synergy index of coal chemical industry and analyzing the factors affecting the overall synergy, the overall grasp and synergistic optimization of the coal chemical production process can be achieved, which is helpful to 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 index of coal chemical industry, constructing the corresponding time series data set, and smoothing the time series of various indicators, the performance of each link and the overall synergy trend over time can be observed, which is helpful to predict future production conditions and provide forward-looking guidance for the formulation and adjustment of production plans; according to the results of trend analysis, when any indicator is found to exceed the preset threshold range and shows a trend of deterioration, or when the overall synergy index exceeds the preset threshold range, the system will promptly send a risk warning signal to the management terminal, which will help managers to respond quickly and take effective measures to prevent production accidents and ensure the stability and safety of the production process.

[0060] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other; Finally: 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 in the protection scope of the present invention.

Claims

1. A control method for energy engineering digital intelligence platform based on multi-source data fusion, characterized in that: include: Step 1: Data entry: used to enter coal chemical data into the target energy engineering digital intelligence platform, including gasification system dynamic parameters, deep purification process parameters, synthesis reaction enhancement indicators and intelligent control key parameters; Step 2: Data cleaning and preprocessing: used to clean the data entered in step 1, eliminate data that does not conform to physical and chemical principles or actual production logic, fill in missing values, and finally standardize the cleaned data; Step 3: Comprehensive evaluation: A mathematical model is established to comprehensively analyze the data processed in step 2, including a gasification system comprehensive performance evaluation model, a deep purification process effect evaluation model, a synthesis reaction enhancement degree evaluation model, and an intelligent control performance evaluation model; Step 4: Synergy analysis: Construct the overall synergy index of coal chemical industry based on the analysis results of step 3, and analyze the factors affecting the overall synergy; Step 5: Trend analysis: By collecting various indicators of the target coal chemical project at each time node and the overall synergy indicators of coal chemical industry, the corresponding time series data set is constructed, and the time series of various indicators are smoothed; Step 6: Control: Send a control signal based on the time series data set established in step 5.

2. According to claim 1, a method for controlling an energy engineering digital intelligence platform based on multi-source data fusion is characterized in that: The dynamic parameters of the gasification system include the heat transfer coefficient of the oxygen-enriched preheater diaphragm, the Reynolds number of the slurry layer carbon particles, the Von Karman vortex frequency of the gas-solid two-phase flow and the plasma-assisted gasification ionization degree; the deep purification process parameters include the selective Claus conversion sulfur yield, the MDEA solution circulation 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 microreactor Reynolds-Kolmogorov scale ratio, the porous medium catalyst Thiele modulus, the surface active site TOF and the non-steady-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 fuzzy adaptive PID controller gain matrix condition number and the state observer noise covariance matrix trace.

3. According to claim 1, a method for controlling an energy engineering digital intelligence platform based on multi-source data fusion is characterized in that: The comprehensive performance evaluation model of the gasification system is used to evaluate the dynamic parameters of the gasification system, which is specifically expressed as: , GS represents the operating performance evaluation value of the gasification system, hct represents the heat transfer coefficient of the oxygen-enriched preheater membrane, 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 ionization degree of plasma-assisted gasification.

4. According to claim 1, a method for controlling an energy engineering digital intelligence platform based on multi-source data fusion is characterized in that: The deep purification process effect evaluation model is used to analyze the deep purification process parameters, which is specifically expressed as: , 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.

5. According to claim 1, a method for controlling an energy engineering digital intelligence platform based on multi-source data fusion is characterized in that: The synthetic reaction strengthening degree evaluation model is used to analyze the synthetic reaction strengthening index, which is specifically expressed as: , RE represents the evaluation value of the enhancement degree of the synthesis reaction at the microscopic level, rk represents the Reynolds-Kolmogorov scale ratio of the microreactor, tm represents the Thiele modulus of the porous medium catalyst, tf represents the TOF of the surface active sites, and rt represents the characteristic time of the non-steady-state dynamic response.

6. The energy engineering digital intelligence platform control method based on multi-source data fusion according to claim 1 is characterized by: The intelligent control performance evaluation model is used to analyze the key parameters of intelligent control, which is specifically expressed as: , 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 multivariable coupling Lyapunov stability index, mc represents the condition number of the fuzzy adaptive PID controller gain matrix, and cv represents the trace of the state observer noise covariance matrix.

7. The energy engineering digital intelligence platform control method based on multi-source data fusion according to claim 1 is characterized by: The overall synergy index of coal chemical industry is marked as T, which is specifically expressed as: ; Step 4 quantifies the factors affecting the overall synergy by establishing corresponding adaptability indicators, which are set as vectors , f m Represents the mth influencing factor. Using the multivariate linear regression analysis method, a regression model between the synergy index T and the influencing factors is established, which is 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.

8. The energy engineering digital intelligence platform control method based on multi-source data fusion according to claim 1 is characterized by: The time series data set is specifically expressed as: {(t1, GS1, DP1, RE1, IC1, T1), (t2, GS2, DP2, RE2, IC2, T2), …, (t n , G.S. n , DP n , R.E. n ,IC n , T n )}, t n Indicates the nth time node; The step 5 smoothes the time series of each indicator by using the moving average method. The moving average calculation formula is specifically expressed as: , M GS，t It represents the moving average value of GS index in the tth period, and k is the number of moving average items.

9. An energy engineering digital intelligence platform control system based on multi-source data fusion, used to implement an energy engineering digital intelligence platform control method based on multi-source data fusion as described in any one of claims 1-8, characterized in that: include: Data entry module, data cleaning and preprocessing module, comprehensive evaluation module, collaborative analysis module, trend analysis module and control module.

Images