Method and system for regulating and controlling operation and maintenance of carbon nanofiber-liquid amine carbon capture system

Abstract

The invention discloses an operation and maintenance regulation and control method and system for a carbon nanofiber-liquid amine carbon capture system, and belongs to the field of operation and maintenance regulation and control of carbon capture systems. The operation and maintenance regulation and control method for the carbon nanofiber-liquid amine carbon capture system comprises the following steps: presetting performance indexes; the method comprises the following steps: acquiring operation parameters of a carbon nanofiber-liquid amine carbon capture system, and constructing a fuzzy cognitive network model based on the operation parameters; analyzing the fuzzy cognitive network model by using an intelligent random decision algorithm; the performance of the carbon nanofiber-liquid amine carbon capture system under each working condition is monitored in real time through the cloud platform, and the operation parameters of the carbon nanofiber-liquid amine carbon capture system are optimized; and comparing the performance after the operation parameters are optimized with a preset performance index, if a comparison result accords with the preset performance index, maintaining the current process control, and if the comparison result does not accord with the preset performance index, adjusting the process control. According to the method, the carbon capture efficiency is improved by identifying the key operation variables and constructing the fuzzy cognitive network model.

Description

Technical Field

[0001] The present invention relates to the field of operation, maintenance and control of carbon capture systems, and in particular to a method and system for operation, maintenance and control of a carbon nanofiber-liquid amine carbon capture system. Background Art

[0002] The carbon nanofiber-liquid amine carbon capture system is a highly efficient CO2 capture technology that uses carbon nanofibers (CNFs) as adsorbents and combines them with liquid amines as absorbents to capture carbon dioxide in flue gas. CNFs have been widely studied as adsorbents due to their high specific surface area, good chemical stability and mechanical strength; liquid amines are selected as absorbents due to their efficient CO2 absorption capacity. Flue gas containing CO2 passes through the carbon nanofiber bed, and the CO2 molecules therein are adsorbed by the surface of CNFs. At the same time, the liquid amine contacts the flue gas through spraying or other means to further absorb the remaining CO2. After a period of operation, the adsorption-saturated CNFs and amine solutions need to be regenerated for recycling, which is usually achieved by heating. Heating will cause CO2 to be released back to a gaseous state, while the CNFs and amine solutions will resume activity.

[0003] By precisely controlling and optimizing system operating parameters such as temperature, pressure and chemical concentration to maximize carbon capture efficiency, optimize operating processes and conditions, reduce unnecessary energy consumption, and thus reduce operating costs, prevent system failures through continuous monitoring and maintenance, and ensure long-term stable operation of the system. Through effective carbon capture, CO2 emissions in industrial processes can be reduced to combat climate change.

[0004] However, the models in existing technologies may lack sufficient flexibility and cannot adapt to dynamic changes in the environment and operating conditions, resulting in reduced accuracy of predictions and simulations. Old technologies may lack high-precision prediction tools and cannot accurately simulate and predict the performance of the system under different operating conditions. They lack the ability to dynamically adjust model parameters and cannot perform real-time optimization as the environment and operating conditions change. Existing technologies may fail to effectively optimize operating parameters, resulting in low energy efficiency and carbon capture efficiency of the system, greater energy consumption and environmental impact, and a lack of real-time monitoring and fault prediction mechanisms, resulting in an inability to respond promptly to system performance degradation or potential failures.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In order to overcome the above problems, the present invention aims to propose a carbon nanofiber-liquid amine carbon capture system operation and maintenance control method and system, with the aim of solving the problem that the prior art may fail to effectively optimize the operating parameters, resulting in low energy efficiency and carbon capture efficiency of the system, large energy consumption and environmental impact, lack of real-time monitoring and fault prediction mechanism, resulting in the inability to respond in time to system performance degradation or potential failures.

[0007] To this end, the specific technical solution adopted by the present invention is as follows:

[0008] According to one aspect of the present invention, a carbon nanofiber-liquid amine carbon capture system operation and maintenance control method is provided, and the carbon nanofiber-liquid amine carbon capture system operation and maintenance control method comprises the following steps:

[0009] S1. Debugging the operating parameters of the carbon nanofiber-liquid amine carbon capture system and presetting performance indicators;

[0010] S2. Obtaining the operating parameters of the carbon nanofiber-liquid amine carbon capture system, constructing a fuzzy cognitive network model based on the operating parameters, and predicting the performance of the carbon nanofiber-liquid amine carbon capture system under various operating conditions;

[0011] S3. Use intelligent random decision-making algorithms to complete the analysis of the fuzzy cognitive network model, and formulate and implement process control based on the analysis results;

[0012] S4. Real-time monitoring of the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions through the cloud platform, and dynamically adjusting the process control in combination with the adaptive algorithm to optimize the operating parameters of the carbon nanofiber-liquid amine carbon capture system;

[0013] S5. Compare the performance after optimizing the operating parameters with the preset performance index. If the comparison result meets the preset performance index, maintain the current process control. If it does not meet the preset performance index, adjust the process control.

[0014] The steps of obtaining the operating parameters of the carbon nanofiber-liquid amine carbon capture system, constructing a fuzzy cognitive network model based on the operating parameters, and predicting the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions include:

[0015] S21. Identify the key operating variables of the carbon nanofiber-liquid amine carbon capture system;

[0016] S22, taking the key operating variables as nodes of the fuzzy cognitive network model, and constructing the influence relationship matrix through each node;

[0017] S23, collecting historical operation data of key operation variables, and preprocessing the historical operation data;

[0018] S24, optimizing the parameters of the fuzzy cognitive network model using a genetic algorithm and preprocessed historical operation data, and finding the optimal relationship weight matrix;

[0019] S25. Using the optimized fuzzy cognitive network model, the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions within a preset time in the future is predicted;

[0020] S26. Use the data set to test the fuzzy cognitive network model and adjust the model parameters based on the test results.

[0021] Optionally, taking the key operating variables as nodes of the fuzzy cognitive network model and constructing an influence relationship matrix through each node includes the following steps:

[0022] S221, selecting key operating variables in the carbon nanofiber-liquid amine carbon capture system as nodes of the fuzzy cognitive network model;

[0023] S222, collecting the time series data of each node, and calculating the average value of the time series data in each node;

[0024] S223, based on the average value of the time series data in each node, determine the correlation coefficient between each node using the Pearson correlation coefficient calculation formula;

[0025] S224. Initialize the influence relationship matrix based on the correlation coefficient, analyze whether all elements in the influence relationship matrix reflect the actual interaction between nodes, and adjust the weight of the influence relationship matrix.

[0026] Optionally, the formula for determining the correlation coefficient between nodes using the Pearson correlation coefficient calculation formula is:

[0027]

[0028] In the formula, E ab represents the key operational variables;

[0029] Represents the average value of the time series data in node a;

[0030] Represents the average value of the time series data in node b;

[0031] g at Represents the sample value of the time series data in node a;

[0032] g bt Represents the sample value of the time series data in node b;

[0033] n represents the sample size;

[0034] t represents the observation point.

[0035] Optionally, optimizing the parameters of the fuzzy cognitive network model using a genetic algorithm and preprocessed historical operation data and finding the best relationship weight matrix includes the following steps:

[0036] S241, using the influence relationship matrix of the adjusted weight as the chromosome population of the starting point of the genetic algorithm, wherein the chromosomes in the chromosome population represent the relationship weight matrix;

[0037] S242, calculating the fitness of each chromosome using the mean square error between the output of the fuzzy cognitive network model and the actual observation value;

[0038] S243, retaining chromosomes whose fitness is higher than a preset threshold, and performing crossover and mutation operations on the chromosomes;

[0039] S244, continue to execute steps S242-S243 until the predetermined number of iterations is completed, and select the chromosome with the highest fitness from the final chromosome population as the optimal relationship weight matrix.

[0040] Optionally, using the optimized fuzzy cognitive network model to predict the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions within a preset time in the future includes the following steps:

[0041] S261, loading the best relationship weight matrix and configuring the best nodes for the fuzzy cognitive network model;

[0042] S262, inputting the expected operating parameters of the carbon nanofiber-liquid amine carbon capture system within a preset time in the future into the fuzzy cognitive network model;

[0043] S263, using the forward propagation of the loaded fuzzy cognitive network model, calculate the mutual influence between the nodes and predict the state of each node;

[0044] S264. Evaluate the performance of the carbon nanofiber-liquid amine carbon capture system under various preset working conditions based on the output of the fuzzy cognitive network model, and output the prediction results.

[0045] Optionally, using an intelligent random decision algorithm to complete the analysis of the fuzzy cognitive network model, and formulating and implementing process control according to the analysis results includes the following steps:

[0046] S31, integrating the test results and historical data as input, defining the decision tree parameters of the intelligent random decision algorithm;

[0047] S32. Construct random decision tree groups and analyze fuzzy cognitive network models to identify key variables and causal relationships that affect the performance of carbon nanofiber-liquid amine carbon capture system;

[0048] S33. Develop specific process control strategies based on causal relationships and impact paths, and implement process control strategies;

[0049] S34. Integrate process control strategies into actual operations, monitor operating data in actual operations, and adjust control parameters based on feedback.

[0050] Optionally, constructing a random decision tree group and analyzing the fuzzy cognitive network model to identify key variables and causal relationships affecting the performance of the carbon nanofiber-liquid amine carbon capture system includes the following steps:

[0051] S321. In the fuzzy cognitive network model, a subset of variables is randomly selected as a starting point for constructing each random decision tree;

[0052] S322, for each selected variable, randomly determine a split point for dividing data in a random decision tree;

[0053] S323, gradually constructing a random decision tree using randomly selected variables and split points, and selecting a method that maximizes information gain to perform data splitting at each random decision node until a preset maximum tree depth is reached;

[0054] S324, repeating the steps of S321-S323 to generate multiple independent decision trees and form a random decision tree group;

[0055] S325. Summarize the analysis results of the random decision tree group and identify the key variables and causal relationships that appear frequently and have significant impact in most trees.

[0056] Optionally, a specific process control strategy is formulated based on the cause-effect relationship and the impact path, and the implementation of the process control strategy includes the following steps:

[0057] S331. Obtain the causal relationship and impact path that affect the performance of the carbon nanofiber-liquid amine carbon capture system;

[0058] S332. Based on the identified cause-effect relationships, design a process control strategy that includes adjusting operating parameters, optimizing process flows, and improving equipment configuration, and determine the priorities for adjusting operating parameters, optimizing process flows, and improving equipment configuration;

[0059] S334, gradually integrate process control strategies into carbon nanofiber-liquid amine carbon capture system;

[0060] S335. After implementing the process control strategy, the carbon nanofiber-liquid amine carbon capture system is tested and evaluated, feedback information is collected, and the process control strategy is adjusted based on the feedback information.

[0061] Optionally, real-time monitoring of the performance of the carbon nanofiber-liquid amine carbon capture system under various operating conditions through a cloud platform, and dynamically adjusting process control in combination with an adaptive algorithm, and optimizing the operating parameters of the carbon nanofiber-liquid amine carbon capture system include the following steps:

[0062] S41. Continuously monitor the operating data of the carbon nanofiber-liquid amine carbon capture system during actual operation and collect operating data on system performance and environmental variables;

[0063] S42. Regularly analyze and collect operational data on system performance and environmental variables to evaluate the effectiveness of current process control strategies and identify deviations in performance of the carbon nanofiber-liquid amine carbon capture system;

[0064] S43, optimizing the process control strategy using an adaptive algorithm based on the evaluation results;

[0065] S44. Perform a performance evaluation to verify whether the improved control strategy achieves the expected results, and adjust the operating parameters of the carbon nanofiber-liquid amine carbon capture system based on the evaluation results.

[0066] According to another aspect of the present invention, there is also provided a carbon nanofiber-liquid amine carbon capture system operation and maintenance control system, the carbon nanofiber-liquid amine carbon capture system operation and maintenance control system comprising: a performance index setting module, a performance prediction module, a model analysis and process control module, an adaptive control module and a performance comparison and control adjustment module;

[0067] A performance index setting module is used to debug the operating parameters of the carbon nanofiber-liquid amine carbon capture system and preset performance indicators;

[0068] A performance prediction module is used to obtain the operating parameters of the carbon nanofiber-liquid amine carbon capture system, build a fuzzy cognitive network model based on the operating parameters, and predict the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions;

[0069] Model analysis and process control module, which is used to complete the analysis of fuzzy cognitive network model using intelligent random decision-making algorithm, and formulate and implement process control according to the analysis results;

[0070] An adaptive control module is used to monitor the performance of the carbon nanofiber-liquid amine carbon capture system under various operating conditions in real time through a cloud platform, and dynamically adjust process control in combination with an adaptive algorithm to optimize the operating parameters of the carbon nanofiber-liquid amine carbon capture system;

[0071] The performance comparison and control adjustment module is used to compare the performance after optimizing the operating parameters with the preset performance indicators. If the comparison result meets the preset performance indicators, the current process control is maintained; if it does not meet the preset performance indicators, the process control is adjusted.

[0072] Compared with the prior art, this application has the following beneficial effects:

[0073] 1. The present invention can more accurately simulate and predict the performance of the carbon nanofiber-liquid amine carbon capture system under different working conditions by identifying key operating variables and constructing a fuzzy cognitive network model. The historical operating data is used to optimize the model parameters so that the model is closer to the actual situation. The model parameters are optimized by genetic algorithms, and the model can be dynamically adjusted to adapt to the changing environment and operating conditions. When constructing the influence relationship matrix, expert knowledge and statistical analysis methods are combined, and the relationship between data is considered to improve the practicality and reliability of the model. The forward propagation algorithm is used to calculate the mutual influence between nodes, and the dynamic behavior inside the carbon nanofiber-liquid amine carbon capture system can be simulated, providing operators with predictions of future states, thereby guiding operations and optimization strategies. Through accurate prediction and optimization, the operating efficiency and performance of the carbon nanofiber-liquid amine carbon capture system can be improved, energy consumption and costs can be reduced, and carbon capture efficiency can be improved.

[0074] 2. The present invention can more accurately predict and identify key variables and causal relationships that affect the performance of the carbon nanofiber-liquid amine carbon capture system by constructing a group of random decision trees; by utilizing an intelligent random decision-making algorithm, the model can continuously learn from new data and feedback, thereby adapting to changes in the carbon nanofiber-liquid amine carbon capture system and environmental changes, and ensuring continuous optimization of process control strategies; through cost-benefit analysis, risk assessment, and implementation difficulty assessment, the priority of control strategies can be determined, which is conducive to the optimal allocation of resources, and the risk can be reduced through gradual integration during the implementation process; by implementing process control strategies and conducting tests and evaluations, feedback information can be continuously collected and the strategy can be adjusted accordingly, thereby continuously optimizing the performance of the carbon nanofiber-liquid amine carbon capture system; by utilizing historical data and advanced analysis techniques, such as regression analysis, principal component analysis, or machine learning algorithms, it can be ensured that decisions are based on data, thereby improving the objectivity and accuracy of decisions.

[0075] 3. The cloud platform of the present invention can collect and analyze operating data in real time to ensure immediate understanding of the status of the carbon nanofiber-liquid amine carbon capture system; adaptive algorithms such as reinforcement learning or fuzzy logic control can dynamically adjust operating parameters according to real-time data to achieve immediate response and optimization. Real-time monitoring data can help predict potential failures and performance degradation, and adjust operating parameters or perform maintenance in a timely manner, thereby reducing the downtime and maintenance costs of the carbon nanofiber-liquid amine carbon capture system. In-depth analysis of the collected data using big data analysis and machine learning technology can more accurately identify performance trends and cyclical changes, provide data-driven decision support, and thus optimize overall operating efficiency. Adaptive algorithms can optimize operating parameters such as temperature, pressure, and flow rate to improve energy efficiency and carbon capture efficiency while reducing energy consumption and environmental impact. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] The above characteristics, features and advantages of the present invention and their implementation methods and methods will become more clearly understood in conjunction with the following description of the embodiments, which are described in detail in conjunction with the accompanying drawings. Herein, a schematic diagram is shown:

[0077] Figure 1 is a flow chart of a method for operating, maintaining and controlling a carbon nanofiber-liquid amine carbon capture system according to an embodiment of the present invention;

[0078] Figure 2 It is a principle block diagram of a carbon nanofiber-liquid amine carbon capture system operation and maintenance control system according to an embodiment of the present invention.

[0079] In the figure:

[0080] 1. Performance index setting module; 2. Performance prediction module; 3. Model analysis and process control module; 4. Adaptive control module; 5. Performance comparison and control adjustment module. DETAILED DESCRIPTION

[0081] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0082] According to an embodiment of the present invention, a method and system for operating and maintaining a carbon nanofiber-liquid amine carbon capture system are provided.

[0083] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a carbon nanofiber-liquid amine carbon capture system operation and maintenance control method is provided, and the carbon nanofiber-liquid amine carbon capture system operation and maintenance control method comprises the following steps:

[0084] S1. Debug the operating parameters of the carbon nanofiber-liquid amine carbon capture system and preset performance indicators.

[0085] It should be explained that the carbon nanofiber-liquid amine carbon capture system is a technology specially designed to capture and store carbon dioxide (CO2) from industrial emissions. The carbon nanofiber-liquid amine carbon capture system combines two materials or technologies, carbon nanofiber and liquid amine, to improve the efficiency and performance of carbon capture. The following is a detailed introduction to its main components and working principles:

[0086] 1) The main components include carbon nanofibers and liquid amine solutions; carbon nanofibers are a material with a high specific surface area and a porous structure, which makes them very suitable as adsorbents to capture gas molecules such as carbon dioxide; liquid amine technology is a mature CO2 capture technology, in which liquid amine solutions can effectively absorb carbon dioxide in the environment.

[0087] 2) The working principle is as follows: In the carbon nanofiber-liquid amine carbon capture system, industrial waste gas containing CO2 first passes through a reactor containing carbon nanofibers; carbon nanofibers can initially adsorb CO2 in the waste gas due to their high surface area and porous properties; after being pretreated by carbon nanofibers, the gas further passes through a liquid amine solution; the liquid amine solution can chemically adsorb and react to absorb the remaining CO2;

[0088] The combined approach described above leverages the strengths of both technologies, improving carbon capture efficiency and potentially reducing energy consumption and operating costs.

[0089] Determine the key operating parameters that need to be debugged, such as gas flow rate, carbon nanofiber filling density, liquid amine concentration and flow rate, etc. The key operating parameters directly affect the CO2 capture efficiency and energy consumption of the carbon nanofiber-liquid amine carbon capture system. Use sensors and data acquisition to monitor the operating status in real time, collect data on temperature, pressure, CO2 concentration, etc., and use computer simulation tools such as CFD (computational fluid dynamics) simulation to predict the impact of different operating parameters on the performance of the carbon nanofiber-liquid amine carbon capture system to optimize parameter settings;

[0090] According to industrial standards and environmental protection requirements, define the performance indicators that carbon nanofiber-liquid amine carbon capture should achieve, such as CO2 capture efficiency, system stability, energy consumption, etc., compare with existing technologies or competitive systems, set performance benchmarks, and set up monitoring to continuously track these performance indicators to ensure that the operation of carbon nanofiber-liquid amine carbon capture meets the preset standards.

[0091] S2. Obtain the operating parameters of the carbon nanofiber-liquid amine carbon capture system, construct a fuzzy cognitive network model based on the operating parameters, and predict the performance of the carbon nanofiber-liquid amine carbon capture system under various operating conditions.

[0092] The steps of obtaining the operating parameters of the carbon nanofiber-liquid amine carbon capture system, constructing a fuzzy cognitive network model based on the operating parameters, and predicting the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions include:

[0093] S21. Identify the key operating variables of the carbon nanofiber-liquid amine carbon capture system.

[0094] S22. The key operational variables are used as nodes of the fuzzy cognitive network model, and an influence relationship matrix is ​​constructed through each node.

[0095] Preferably, taking the key operating variables as nodes of the fuzzy cognitive network model and constructing an influence relationship matrix through each node includes the following steps:

[0096] S221, selecting key operating variables in the carbon nanofiber-liquid amine carbon capture system as nodes of the fuzzy cognitive network model;

[0097] S222, collecting the time series data of each node, and calculating the average value of the time series data in each node;

[0098] S223, based on the average value of the time series data in each node, determine the correlation coefficient between each node using the Pearson correlation coefficient calculation formula;

[0099] S224. Initialize the influence relationship matrix based on the correlation coefficient, analyze whether all elements in the influence relationship matrix reflect the actual interaction between nodes, and adjust the weight of the influence relationship matrix.

[0100] Preferably, the formula for determining the correlation coefficient between nodes using the Pearson correlation coefficient calculation formula is:

[0101]

[0102] In the formula, E ab represents the key operational variables;

[0103] Represents the average value of the time series data in node a;

[0104] Represents the average value of the time series data in node b;

[0105] g at Represents the sample value of the time series data in node a;

[0106] g bt Represents the sample value of the time series data in node b;

[0107] n represents the sample size;

[0108] t represents the observation point.

[0109] It should be explained that the key operating variables that affect the performance of the carbon nanofiber-liquid amine carbon capture system, such as CO2 concentration, gas flow rate, carbon nanofiber filling density and liquid amine flow rate, are determined through historical operating data of the carbon nanofiber-liquid amine carbon capture system, expert experience and preliminary experimental research. Data analysis software and statistical methods are used to analyze historical data to determine which variables have the greatest impact on the performance of the carbon nanofiber-liquid amine carbon capture system. Analysis of variance (ANOVA) and regression analysis are used to identify variables that have a significant impact on the performance of the carbon nanofiber-liquid amine carbon capture system. It is understood how each operating variable affects the working efficiency and capture efficiency of the entire carbon nanofiber-liquid amine carbon capture system. The identified key operating variables are used as nodes of the network model. For example, through expert The discussion of the expert group and the literature research are used to determine the potential influence relationship between these variables, and the influence relationship matrix is ​​constructed. The most representative and influential variables are selected from the identified key variables as model nodes. The time series data of the selected nodes are collected, including daily operation data and test data under specific conditions. The statistical indicators of the time series data of each node, such as the mean and variance, are calculated to provide basic data for subsequent analysis. The linear correlation between the nodes is analyzed using the Pearson correlation coefficient formula. This coefficient ranges from -1 to 1. The larger the value, the stronger the positive correlation, and the smaller the value, the stronger the negative correlation. Based on the calculated correlation coefficient, the influence relationship matrix is ​​preliminarily constructed. Each element in the matrix represents the degree of influence of one node on another node.

[0110] Initialize the influence relationship matrix based on the correlation coefficient, analyze whether all elements in the influence relationship matrix reflect the actual interaction between nodes, and adjust the weight of the influence relationship matrix as follows:

[0111] In the step of analyzing and adjusting the influence relationship matrix, the weights in the matrix are first set preliminarily by calculating the Pearson correlation coefficient, which reflects the linear correlation between the nodes (key operating variables) in the fuzzy cognitive network model. Then, these preliminary weights need to be reviewed by an expert team and verified in combination with actual operating experience and the performance data of the carbon nanofiber-liquid amine carbon capture system. Experts may adjust the weights according to the complexity or nonlinear characteristics of the actual interactions to ensure that the matrix more accurately reflects the actual influence relationship between the nodes. This process may involve multiple rounds of adjustments, and the predictive accuracy of the model needs to be re-evaluated after each adjustment until the performance of the matrix appears reasonable and effective in both simulation and actual operation. This method combines statistical analysis, expert knowledge and actual operating data. It is a dynamic optimization process that aims to continuously improve the application value and predictive accuracy of the model.

[0112] S23. Collect historical operation data of key operation variables and pre-process the historical operation data.

[0113] S24. Use genetic algorithms and preprocessed historical operation data to optimize the parameters of the fuzzy cognitive network model and find the optimal relationship weight matrix.

[0114] Preferably, optimizing the parameters of the fuzzy cognitive network model using a genetic algorithm and preprocessed historical operation data and finding the best relationship weight matrix includes the following steps:

[0115] S241, using the influence relationship matrix of the adjusted weight as the chromosome population of the starting point of the genetic algorithm, wherein the chromosomes in the chromosome population represent the relationship weight matrix;

[0116] S242, calculating the fitness of each chromosome using the mean square error between the output of the fuzzy cognitive network model and the actual observation value;

[0117] S243, retaining chromosomes whose fitness is higher than a preset threshold, and performing crossover and mutation operations on the chromosomes;

[0118] S244, continue to execute steps S242-S243 until the predetermined number of iterations is completed, and select the chromosome with the highest fitness from the final chromosome population as the optimal relationship weight matrix.

[0119] It should be explained that first of all, it is necessary to collect historical data of key operating variables from the actual operation of the carbon nanofiber-liquid amine carbon capture system, including temperature, pressure, flow rate, etc. These data usually come from sensors and data loggers, and clean and standardize the collected data, including removing outliers, filling missing values, data normalization, etc., because accurate input data is the key to the success of the optimization algorithm. Use data processing technology to ensure data quality and provide an accurate basis for subsequent analysis. By adjusting the data scale to eliminate the impact of different units, the model is made more stable and efficient. Based on the adjusted influence relationship matrix, a chromosome population is created. Each chromosome represents a set of possible relationship weight matrices. The fitness of each chromosome is calculated, usually by comparing the mean square error between the predicted output of the fuzzy cognitive network model and the actual observed value. According to the influence of the preprocessing The relationship matrix sets the initial population, and these matrices now serve as the genes of each chromosome in the genetic algorithm. In the genetic algorithm, the genes of each chromosome represent a weight value, and the entire chromosome represents the weight matrix of the entire network. The mean square error between the model output and the actual data is used as the fitness function. The smaller the error, the higher the fitness. Chromosomes are selected for reproduction based on fitness, and a new generation of chromosomes is generated through crossover and mutation operations to explore the solution space and increase the diversity of the population. Fitness evaluation and genetic operations are repeated until the predetermined number of iterations is reached or the fitness is no longer significantly improved. The chromosome with the highest fitness is selected from the final population as the optimal relationship weight matrix; the genetic algorithm is a search optimization algorithm that simulates the natural selection process. It is widely used to solve complex optimization problems, especially for problems with large parameter spaces and diverse possible solutions.

[0120] S25. Use the optimized fuzzy cognitive network model to predict the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions within a preset time in the future.

[0121] S26. Use the data set to test the fuzzy cognitive network model and adjust the model parameters based on the test results.

[0122] Preferably, using the optimized fuzzy cognitive network model to predict the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions within a preset time in the future includes the following steps:

[0123] S261, loading the best relationship weight matrix and configuring the best nodes for the fuzzy cognitive network model;

[0124] S262, inputting the expected operating parameters of the carbon nanofiber-liquid amine carbon capture system within a preset time in the future into the fuzzy cognitive network model;

[0125] S263, using the forward propagation of the loaded fuzzy cognitive network model, calculate the mutual influence between the nodes and predict the state of each node;

[0126] S264. Evaluate the performance of the carbon nanofiber-liquid amine carbon capture system under various preset working conditions based on the output of the fuzzy cognitive network model, and output the prediction results.

[0127] It should be explained that the optimal weight matrix obtained after genetic algorithm optimization is imported into the fuzzy cognitive network model. The weight matrix determines the interaction strength between the nodes in the model. At the same time, the parameter settings of the nodes, such as fuzzy rules, membership functions, etc., are adjusted according to the optimization results to ensure the optimal performance of the model. The nodes in the fuzzy cognitive network model represent the variables in the carbon nanofiber-liquid amine carbon capture system, and the weight matrix represents the mutual influence between the variables. The membership function is used to process fuzzy logic and determine the fuzzy relationship between input and output. According to the preset future operating conditions, the expected operating parameters (such as temperature, pressure, flow rate, etc.) of the carbon nanofiber-liquid amine carbon capture system are input as input data sets into the fuzzy cognitive network model. The selection and setting of input parameters are crucial to the prediction results of the model. The forward propagation algorithm of the fuzzy cognitive network model is used to calculate the input parameters through the configured nodes and weight matrix to obtain the state of each node (i.e., the output value); the interaction and propagation process between the variables. Forward propagation is a basic algorithm in neural networks, which is used for the calculation process from the input layer to the output layer; in fuzzy cognitive networks, this process is also used to calculate the output value of the node, analyze the output of the fuzzy cognitive network model, and evaluate the performance indicators of the carbon nanofiber-liquid amine carbon capture system under various preset working conditions, such as CO2 capture efficiency, energy consumption, etc. These indicators and prediction results are sorted out and output to provide a basis for the operation and optimization of the carbon nanofiber-liquid amine carbon capture system.

[0128] S3. Use intelligent random decision-making algorithms to complete the analysis of the fuzzy cognitive network model, and formulate and implement process control based on the analysis results.

[0129] Preferably, the analysis of the fuzzy cognitive network model is completed by using an intelligent random decision algorithm, and the process control is formulated and implemented according to the analysis results, including the following steps:

[0130] S31. Integrate test results and historical data as input to define decision tree parameters of the intelligent random decision algorithm.

[0131] S32. Construct a random decision tree group and analyze the fuzzy cognitive network model to identify the key variables and causal relationships that affect the performance of the carbon nanofiber-liquid amine carbon capture system.

[0132] Preferably, constructing a random decision tree group and analyzing the fuzzy cognitive network model to identify key variables and causal relationships that affect the performance of the carbon nanofiber-liquid amine carbon capture system includes the following steps:

[0133] S321. In the fuzzy cognitive network model, a subset of variables is randomly selected as a starting point for constructing each random decision tree;

[0134] S322, for each selected variable, randomly determine a split point for dividing data in a random decision tree;

[0135] S323, gradually constructing a random decision tree using randomly selected variables and split points, and selecting a method that maximizes information gain to perform data splitting at each random decision node until a preset maximum tree depth is reached;

[0136] S324, repeating the steps of S321-S323 to generate multiple independent decision trees and form a random decision tree group;

[0137] S325. Summarize the analysis results of the random decision tree group and identify the key variables and causal relationships that appear frequently and have significant impact in most trees.

[0138] It should be explained that the key factors and their interrelationships that affect the performance of the carbon nanofiber-liquid amine carbon capture system are identified and verified through data analysis and modeling techniques, such as structural equation modeling (SEM) or cause-and-effect diagrams. This usually involves collecting historical operating data, using statistical methods to determine the correlation between variables, and establishing a causal model. Causal analysis is a method used to determine how one event (cause) leads to another event (effect). In the carbon nanofiber-liquid amine carbon capture system, understanding the causal relationship between variables is crucial to developing an effective control strategy. Based on the causal relationship identified in S331, a series of control strategies are designed, including adjusting operating parameters (such as temperature, pressure, flow rate, etc.), optimizing process flow (such as improving material flow or energy flow), and improving equipment configuration (such as Replace high-performance materials or components), determine the priorities of these strategies through cost-benefit analysis, risk assessment and implementation difficulty assessment. The design of process control strategies needs to take into account technical, economic and operational factors. Priority determination helps to optimally allocate resources and ensure that key issues are resolved first. Implement control strategies in stages, first test them on a small scale and then gradually expand them. Ensure the compatibility of new strategies with existing carbon nanofiber-liquid amine carbon capture systems, and reduce implementation risks through gradual integration. After implementing new control strategies, test and evaluate the carbon nanofiber-liquid amine carbon capture systems to verify the effectiveness of the strategies. Evaluate the actual effects of the strategies by collecting operating data, performance indicators and user feedback. Based on these feedback information, adjust the strategies to further improve performance.

[0139] S33. Develop specific process control strategies based on cause-effect relationships and impact paths, and implement process control strategies.

[0140] Preferably, a specific process control strategy is formulated based on the causal relationship and the impact path, and the implementation of the process control strategy includes the following steps:

[0141] S331. Obtain the causal relationship and impact path that affect the performance of the carbon nanofiber-liquid amine carbon capture system;

[0142] S332. Based on the identified cause-effect relationships, design a process control strategy that includes adjusting operating parameters, optimizing process flows, and improving equipment configuration, and determine the priorities for adjusting operating parameters, optimizing process flows, and improving equipment configuration;

[0143] S334, gradually integrate process control strategies into carbon nanofiber-liquid amine carbon capture system;

[0144] S335. After implementing the process control strategy, the carbon nanofiber-liquid amine carbon capture system is tested and evaluated, feedback information is collected, and the process control strategy is adjusted based on the feedback information.

[0145] It should be explained that historical data and advanced analytical techniques, such as regression analysis, principal component analysis (PCA) or machine learning algorithms, are used to identify which variables have a significant impact on the performance of the carbon nanofiber-liquid amine carbon capture system. By constructing a causal diagram or a structural equation model, the direct and indirect relationships between variables are visualized, the impact path is determined, and a sensitivity analysis is performed to evaluate the impact of different parameter changes on the performance of the carbon nanofiber-liquid amine carbon capture system. According to the key factors identified in step S331, specific control strategies are designed, such as adjusting operating parameters (such as temperature, pressure, flow rate, etc.), optimizing process flows (such as improving the utilization efficiency of materials and energy), and improving equipment configuration (such as replacing high-performance adsorbents or improving High automation level of equipment), through methods such as multi-criteria decision analysis (MCDM), taking into account factors such as cost, benefit, implementation difficulty and risk, determine priorities for different control strategies, and adopt a step-by-step implementation approach. First, test the effectiveness of the strategy on a small scale, and then gradually expand it to the entire carbon nanofiber-liquid amine carbon capture system to ensure the compatibility of the new strategy with the existing carbon nanofiber-liquid amine carbon capture system, and continuously monitor and adjust it during the implementation process. After the implementation of the new control strategy, test the changes in the performance of the carbon nanofiber-liquid amine carbon capture system through actual operation, collect operating data, performance indicators and user feedback, evaluate the effectiveness of the strategy, and adjust the control strategy according to the test and evaluation results to optimize the performance.

[0146] S34. Integrate process control strategies into actual operations, monitor operating data in actual operations, and adjust control parameters based on feedback.

[0147] S4. Real-time monitoring of the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions is performed through the cloud platform, and the process control is dynamically adjusted in combination with an adaptive algorithm to optimize the operating parameters of the carbon nanofiber-liquid amine carbon capture system.

[0148] Preferably, the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions is monitored in real time by a cloud platform, and the process control is dynamically adjusted in combination with an adaptive algorithm to optimize the operating parameters of the carbon nanofiber-liquid amine carbon capture system, including the following steps:

[0149] S41. Continuously monitor the operating data of the carbon nanofiber-liquid amine carbon capture system during actual operation and collect operating data on system performance and environmental variables;

[0150] S42. Regularly analyze and collect operational data on system performance and environmental variables to evaluate the effectiveness of current process control strategies and identify deviations in performance of the carbon nanofiber-liquid amine carbon capture system;

[0151] S43, optimizing the process control strategy using an adaptive algorithm based on the evaluation results;

[0152] S44. Perform a performance evaluation to verify whether the improved control strategy achieves the expected results, and adjust the operating parameters of the carbon nanofiber-liquid amine carbon capture system based on the evaluation results.

[0153] It should be explained that sensors installed at various key points of the system, such as temperature sensors, pressure sensors, flow meters and CO2 concentration sensors, are used to collect real-time operating data of the carbon nanofiber-liquid amine carbon capture system. Through the Industrial Internet of Things (IIoT) technology, these data are transmitted to the cloud platform to achieve remote monitoring and data storage. The cloud platform has data pre-processing capabilities and can perform preliminary analysis on the collected data to identify potential problems more quickly. Big data analysis tools and machine learning algorithms are used to regularly analyze the collected data to identify trends and periodic changes in the performance of the carbon nanofiber-liquid amine carbon capture system. By comparing actual performance with expected performance, the effectiveness of the current process control strategy is evaluated and any performance deviations are identified. Determine the optimization needs and the direction of control strategy adjustment. Based on the evaluation results of S42, apply adaptive algorithms (such as reinforcement learning, fuzzy logic or PID controller) to adjust and optimize the process control strategy. The adaptive algorithm can automatically adjust the control parameters according to the real-time data and preset goals to improve the performance of the carbon nanofiber-liquid amine carbon capture system. Implementing these algorithms on the cloud platform can achieve rapid iteration and real-time updating of control strategies. After the implementation of the new control strategy, its effect is tested through a series of performance evaluations. The evaluation can be carried out by comparing the actual performance with the set goals, cost-benefit analysis, environmental impact assessment and other methods. According to the evaluation results, further adjust and optimize the control parameters to ensure that the carbon nanofiber-liquid amine carbon capture system achieves the best performance.

[0154] In the carbon nanofiber-liquid amine carbon capture system, the specific implementation steps and contents of adaptive algorithms, such as reinforcement learning and fuzzy logic control, to automatically adjust the operating parameters include:

[0155] 1) Reinforcement Learning:

[0156] Data collection: The carbon nanofiber-liquid amine carbon capture system collects key parameters such as CO2 capture rate, energy consumption, temperature, etc. in real time through sensors;

[0157] Reward mechanism: Set up a reward function, use the performance goals of the carbon nanofiber-liquid amine carbon capture system (such as improving CO2 capture efficiency and reducing energy consumption) as evaluation criteria, and reward those operating states that achieve or exceed the expected results;

[0158] Strategy optimization: The algorithm tries different configurations of operating parameters through exploration and exploitation mechanisms, and learns how to adjust the parameters to maximize rewards;

[0159] Implementation adjustments: Based on the learning results, the algorithm adjusts the parameters of the carbon nanofiber-liquid amine carbon capture system in real time and optimizes the operating strategy to adapt to environmental changes and actual working conditions.

[0160] 2) Fuzzy logic control:

[0161] Fuzzified input: converting real-time monitored numerical data (e.g., temperature, pressure) into fuzzy values ​​that represent how they belong to a predefined fuzzy set (e.g., low, medium, high)

[0162] Establish a rule base: According to the design and objectives of the carbon nanofiber-liquid amine carbon capture system, a set of fuzzy logic rules are established. These rules describe the operating parameter adjustments corresponding to different fuzzy input combinations; Reasoning mechanism: Through fuzzy logic reasoning, the most suitable operating parameter adjustments are calculated according to the current fuzzy input and rule base; Defuzzification: The fuzzy logic reasoning results are converted into specific operating parameters for the actual adjustment of the carbon nanofiber-liquid amine carbon capture system.

[0163] S5. Compare the performance after optimizing the operating parameters with the preset performance indicators. If the comparison result meets the preset performance indicators, maintain the current process control; if it does not meet the preset performance indicators, adjust the process control.

[0164] Specific examples are as follows:

[0165] A chemical plant is operating a carbon nanofiber-liquid amine carbon capture system to improve CO2 capture efficiency and reduce energy consumption. To achieve this goal, the plant decided to use a fuzzy cognitive network model and adaptive algorithm to optimize the operation of the carbon nanofiber-liquid amine carbon capture system; debug the operating parameters of the carbon nanofiber-liquid amine carbon capture system, and preset performance indicators;

[0166] The factory collected the operating data of the carbon nanofiber-liquid amine carbon capture system through sensors, including temperature, pressure, flow rate, etc.; using these data, the factory determined the key operating variables that affect the performance of the carbon nanofiber-liquid amine carbon capture system, such as CO2 concentration, gas flow rate, carbon nanofiber filling density and liquid amine flow rate; then, the factory used methods such as analysis of variance (ANOVA) and regression analysis to determine the optimal setting range of these key variables; at the same time, the factory set the performance indicators that the carbon nanofiber-liquid amine carbon capture system should achieve according to industrial standards and environmental protection requirements, such as CO2 capture efficiency, stability and energy consumption;

[0167] Obtain the operating parameters of the carbon nanofiber-liquid amine carbon capture system, build a fuzzy cognitive network model based on the operating parameters, and predict the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions;

[0168] The plant collected historical data of key operating variables and preprocessed the data, including cleaning and normalization. Then, the plant used genetic algorithms and preprocessed historical data to optimize the parameters of the fuzzy cognitive network model and found the optimal relationship weight matrix. Then, the plant used the optimized model to predict the performance of the carbon nanofiber-liquid amine carbon capture system under various operating conditions within a preset time in the future.

[0169] Use intelligent random decision-making algorithms to complete the analysis of fuzzy cognitive network models, and formulate and implement process control based on the analysis results;

[0170] The plant constructed a random decision tree group and analyzed the fuzzy cognitive network model to identify the key variables and causal relationships that affect the performance of the carbon nanofiber-liquid amine carbon capture system. Then, based on these causal relationships, the plant designed specific process control strategies, including adjusting operating parameters, optimizing process flows, and improving equipment configuration. The plant gradually integrated the control strategies into the carbon nanofiber-liquid amine carbon capture system and conducted tests and evaluations.

[0171] The cloud platform monitors the system's performance in real time under various operating conditions, and combines adaptive algorithms to dynamically adjust process control and optimize the operating parameters of the carbon nanofiber-liquid amine carbon capture system;

[0172] The plant uses a cloud platform to monitor the operating data of the carbon nanofiber-liquid amine carbon capture system in real time, and regularly analyzes this data to evaluate the effectiveness of the current process control strategy. Based on the evaluation results, the plant uses adaptive algorithms to optimize the process control strategy. For example, the plant uses adaptive algorithms such as reinforcement learning and fuzzy logic control to automatically adjust operating parameters based on real-time data and preset goals to optimize the performance of the carbon nanofiber-liquid amine carbon capture system.

[0173] Compare the performance after optimizing the operating parameters with the preset performance index. If the comparison result meets the preset performance index, maintain the current process control. If it does not meet the preset performance index, adjust the process control.

[0174] After optimizing the operating parameters, the plant compared the performance of the carbon nanofiber-liquid amine carbon capture system with the preset performance indicators; if the comparison results met the preset performance indicators, the plant maintained the current process control; if they did not meet the preset performance indicators, the plant adjusted the process control.

[0175] According to another embodiment of the present invention, Figure 2 As shown, a carbon nanofiber-liquid amine carbon capture system operation and maintenance control system is also provided, and the carbon nanofiber-liquid amine carbon capture system operation and maintenance control system includes: a performance index setting module 1, a performance prediction module 2, a model analysis and process control module 3, an adaptive control module 4 and a performance comparison and control adjustment module 5;

[0176] The performance index setting module 1 is used to adjust the operating parameters of the carbon nanofiber-liquid amine carbon capture system and preset the performance index;

[0177] Performance prediction module 2, used to obtain the operating parameters of the carbon nanofiber-liquid amine carbon capture system, build a fuzzy cognitive network model based on the operating parameters, and predict the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions;

[0178] Model analysis and process control module 3, used to complete the analysis of the fuzzy cognitive network model using an intelligent random decision algorithm, and formulate and implement process control based on the analysis results;

[0179] The adaptive control module 4 is used to monitor the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions in real time through the cloud platform, and dynamically adjust the process control in combination with the adaptive algorithm to optimize the operating parameters of the carbon nanofiber-liquid amine carbon capture system;

[0180] The performance comparison and control adjustment module 5 is used to compare the performance after optimizing the operating parameters with the preset performance index. If the comparison result meets the preset performance index, the current process control is maintained; if it does not meet the preset performance index, the process control is adjusted.

[0181] In summary, with the help of the above technical solutions of the present invention, the present invention can more accurately simulate and predict the performance of the carbon nanofiber-liquid amine carbon capture system under different working conditions by identifying key operating variables and constructing a fuzzy cognitive network model, and optimize the model parameters by using historical operating data to make the model closer to the actual situation. By optimizing the model parameters through genetic algorithms, the model can be dynamically adjusted to adapt to the changing environment and operating conditions. When constructing the influence relationship matrix, expert knowledge and statistical analysis methods are combined, the relationship between data is considered, and the practicality and reliability of the model are improved. The mutual influence between nodes is calculated by the forward propagation algorithm, which can simulate the carbon nanofiber-liquid amine carbon capture system. The dynamic behavior inside the liquid amine carbon capture system provides operators with predictions of future states, thereby guiding operations and optimization strategies. Through accurate prediction and optimization, the operating efficiency and performance of the carbon nanofiber-liquid amine carbon capture system can be improved, energy consumption and costs can be reduced, and carbon capture efficiency can be improved at the same time. By constructing a random decision tree group, the present invention can more accurately predict and identify key variables and causal relationships that affect the performance of the carbon nanofiber-liquid amine carbon capture system. By using an intelligent random decision algorithm, the model can continuously learn from new data and feedback, thereby adapting to changes in the carbon nanofiber-liquid amine carbon capture system and environmental changes, ensuring continuous optimization of process control strategies. Benefit analysis, risk assessment and implementation difficulty assessment can determine the priority of control strategies, help optimize resource allocation, and reduce risks through gradual integration during implementation. By implementing process control strategies and conducting tests and evaluations, feedback information can be continuously collected and strategies can be adjusted accordingly, thereby continuously optimizing the performance of the carbon nanofiber-liquid amine carbon capture system. The use of historical data and advanced analysis techniques, such as regression analysis, principal component analysis or machine learning algorithms, can ensure that decisions are based on data, thereby improving the objectivity and accuracy of decisions. The cloud platform of the present invention can collect and analyze operating data in real time to ensure that the status of the carbon nanofiber-liquid amine carbon capture system is immediately understood. Adaptive algorithms such as reinforcement learning or fuzzy logic control can dynamically adjust operating parameters based on real-time data to achieve immediate response and optimization. Real-time monitoring data can help predict potential failures and performance degradation, and adjust operating parameters or perform maintenance in a timely manner, thereby reducing the downtime and maintenance costs of the carbon nanofiber-liquid amine carbon capture system. In-depth analysis of the collected data using big data analysis and machine learning technology can more accurately identify performance trends and cyclical changes, provide data-driven decision support, and thus optimize overall operating efficiency. Adaptive algorithms can optimize operating parameters such as temperature, pressure, and flow rate to improve energy efficiency and carbon capture efficiency while reducing energy consumption and environmental impact.

[0182] Although the present invention has been disclosed as above with preferred embodiments, the embodiments are merely examples for the convenience of description and are not intended to limit the present invention. Those skilled in the art may make several changes and modifications without departing from the spirit and scope of the present invention. The scope of protection claimed by the present invention shall be based on the claims.

Claims

1. A method for operation and maintenance of a carbon nanofiber-liquid amine carbon capture system, characterized in that: The carbon nanofiber-liquid amine carbon capture system operation and maintenance control method comprises the following steps: S1. Debugging the operating parameters of the carbon nanofiber-liquid amine carbon capture system and presetting performance indicators; S2. Obtaining the operating parameters of the carbon nanofiber-liquid amine carbon capture system, constructing a fuzzy cognitive network model based on the operating parameters, and predicting the performance of the carbon nanofiber-liquid amine carbon capture system under various operating conditions; S3. Use intelligent random decision-making algorithms to complete the analysis of the fuzzy cognitive network model, and formulate and implement process control based on the analysis results; S4. Real-time monitoring of the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions through the cloud platform, and dynamically adjusting the process control in combination with the adaptive algorithm to optimize the operating parameters of the carbon nanofiber-liquid amine carbon capture system; S5. Compare the performance after optimizing the operating parameters with the preset performance index. If the comparison result meets the preset performance index, maintain the current process control. If it does not meet the preset performance index, adjust the process control. The method of obtaining the operating parameters of the carbon nanofiber-liquid amine carbon capture system, constructing a fuzzy cognitive network model based on the operating parameters, and predicting the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions comprises the following steps: S21. Identify the key operating variables of the carbon nanofiber-liquid amine carbon capture system; S22, taking the key operating variables as nodes of the fuzzy cognitive network model, and constructing the influence relationship matrix through each node; S23, collecting historical operation data of key operation variables, and preprocessing the historical operation data; S24, optimizing the parameters of the fuzzy cognitive network model using a genetic algorithm and preprocessed historical operation data, and finding the optimal relationship weight matrix; S25. Using the optimized fuzzy cognitive network model, the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions within a preset time in the future is predicted; S26. Use the data set to test the fuzzy cognitive network model and adjust the model parameters based on the test results.

2. The method for operation, maintenance and control of a carbon nanofiber-liquid amine carbon capture system according to claim 1, characterized in that: The method of using the key operating variables as nodes of the fuzzy cognitive network model and constructing an influence relationship matrix through each node includes the following steps: S221, selecting key operating variables in the carbon nanofiber-liquid amine carbon capture system as nodes of the fuzzy cognitive network model; S222, collecting the time series data of each node, and calculating the average value of the time series data in each node; S223, based on the average value of the time series data in each node, determine the correlation coefficient between each node using the Pearson correlation coefficient calculation formula; S224. Initialize the influence relationship matrix based on the correlation coefficient, analyze whether all elements in the influence relationship matrix reflect the actual interaction between nodes, and adjust the weight of the influence relationship matrix.

3. A method for operation and maintenance of a carbon nanofiber-liquid amine carbon capture system according to claim 2, characterized in that: The formula for determining the correlation coefficient between nodes using the Pearson correlation coefficient calculation formula is: In the formula, E ab represents the key operational variables; Represents the average value of the time series data in node a; Represents the average value of the time series data in node b; g at Represents the sample value of the time series data in node a; g bt Represents the sample value of the time series data in node b; n represents the sample size; t represents the observation point.

4. A method for operation and maintenance of a carbon nanofiber-liquid amine carbon capture system according to claim 3, characterized in that: The method of optimizing the parameters of the fuzzy cognitive network model by using the genetic algorithm and the preprocessed historical operation data and finding the best relationship weight matrix includes the following steps: S241, using the influence relationship matrix of the adjusted weight as the chromosome population of the starting point of the genetic algorithm, wherein the chromosomes in the chromosome population represent the relationship weight matrix; S242, calculating the fitness of each chromosome using the mean square error between the output of the fuzzy cognitive network model and the actual observation value; S243, retaining chromosomes whose fitness is higher than a preset threshold, and performing crossover and mutation operations on the chromosomes; S244, continue to execute steps S242-S243 until the predetermined number of iterations is completed, and select the chromosome with the highest fitness from the final chromosome population as the optimal relationship weight matrix.

5. A method for operation and maintenance of a carbon nanofiber-liquid amine carbon capture system according to claim 4, characterized in that: The method of using the optimized fuzzy cognitive network model to predict the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions in the future preset time includes the following steps: S261, loading the best relationship weight matrix and configuring the best nodes for the fuzzy cognitive network model; S262, inputting the expected operating parameters of the carbon nanofiber-liquid amine carbon capture system within a preset time in the future into the fuzzy cognitive network model; S263, using the forward propagation of the loaded fuzzy cognitive network model, calculate the mutual influence between the nodes and predict the state of each node; S264. Evaluate the performance of the carbon nanofiber-liquid amine carbon capture system under various preset working conditions based on the output of the fuzzy cognitive network model, and output the prediction results.

6. The method for operation and maintenance of a carbon nanofiber-liquid amine carbon capture system according to claim 1, characterized in that: The method of using an intelligent random decision-making algorithm to analyze the fuzzy cognitive network model and formulating and implementing process control according to the analysis results includes the following steps: S31, integrating the test results and historical data as input, defining the decision tree parameters of the intelligent random decision algorithm; S32. Construct random decision tree groups and analyze fuzzy cognitive network models to identify key variables and causal relationships that affect the performance of carbon nanofiber-liquid amine carbon capture system; S33. Develop specific process control strategies based on causal relationships and impact paths, and implement process control strategies; S34. Integrate process control strategies into actual operations, monitor operating data in actual operations, and adjust control parameters based on feedback.

7. A method for operation, maintenance and control of a carbon nanofiber-liquid amine carbon capture system according to claim 6, characterized in that: The construction of a random decision tree group and analysis of a fuzzy cognitive network model to identify key variables and causal relationships affecting the performance of the carbon nanofiber-liquid amine carbon capture system includes the following steps: S321. In the fuzzy cognitive network model, a subset of variables is randomly selected as a starting point for constructing each random decision tree; S322, for each selected variable, randomly determine a split point for dividing data in a random decision tree; S323, gradually constructing a random decision tree using randomly selected variables and split points, and selecting a method that maximizes information gain to perform data splitting at each random decision node until a preset maximum tree depth is reached; S324, repeating the steps of S321-S323 to generate multiple independent decision trees and form a random decision tree group; S325. Summarize the analysis results of the random decision tree group and identify the key variables and causal relationships that appear frequently and have significant impact in most trees.

8. A method for operation, maintenance and control of a carbon nanofiber-liquid amine carbon capture system according to claim 7, characterized in that: The specific process control strategy is formulated based on the causal relationship and the impact path, and the implementation of the process control strategy includes the following steps: S331. Obtain the causal relationship and impact path that affect the performance of the carbon nanofiber-liquid amine carbon capture system; S332. Based on the identified cause-effect relationships, design a process control strategy that includes adjusting operating parameters, optimizing process flows, and improving equipment configuration, and determine the priorities for adjusting operating parameters, optimizing process flows, and improving equipment configuration; S334, gradually integrate process control strategies into carbon nanofiber-liquid amine carbon capture system; S335. After implementing the process control strategy, the carbon nanofiber-liquid amine carbon capture system is tested and evaluated, feedback information is collected, and the process control strategy is adjusted based on the feedback information.

9. The method for operation, maintenance and control of a carbon nanofiber-liquid amine carbon capture system according to claim 1, characterized in that: The real-time monitoring of the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions through the cloud platform and the dynamic adjustment of process control in combination with the adaptive algorithm to optimize the operating parameters of the carbon nanofiber-liquid amine carbon capture system include the following steps: S41. Continuously monitor the operating data of the carbon nanofiber-liquid amine carbon capture system during actual operation and collect operating data on system performance and environmental variables; S42. Regularly analyze and collect operational data on system performance and environmental variables to evaluate the effectiveness of current process control strategies and identify deviations in performance of the carbon nanofiber-liquid amine carbon capture system; S43, optimizing the process control strategy using an adaptive algorithm based on the evaluation results; S44. Perform a performance evaluation to verify whether the improved control strategy achieves the expected results, and adjust the operating parameters of the carbon nanofiber-liquid amine carbon capture system based on the evaluation results.

10. A carbon nanofiber-liquid amine carbon capture system operation and maintenance control system, used to implement the carbon nanofiber-liquid amine carbon capture system operation and maintenance control method according to any one of claims 1 to 9, characterized in that: The carbon nanofiber-liquid amine carbon capture system operation and maintenance control system includes: a performance index setting module, a performance prediction module, a model analysis and process control module, an adaptive control module and a performance comparison and control adjustment module; A performance index setting module is used to debug the operating parameters of the carbon nanofiber-liquid amine carbon capture system and preset performance indicators; A performance prediction module is used to obtain the operating parameters of the carbon nanofiber-liquid amine carbon capture system, build a fuzzy cognitive network model based on the operating parameters, and predict the performance of the carbon nanofiber-liquid amine carbon capture system under various working conditions; Model analysis and process control module, which is used to complete the analysis of fuzzy cognitive network model using intelligent random decision-making algorithm, and formulate and implement process control according to the analysis results; An adaptive control module is used to monitor the performance of the carbon nanofiber-liquid amine carbon capture system under various operating conditions in real time through a cloud platform, and dynamically adjust process control in combination with an adaptive algorithm to optimize the operating parameters of the carbon nanofiber-liquid amine carbon capture system; The performance comparison and control adjustment module is used to compare the performance after optimizing the operating parameters with the preset performance indicators. If the comparison result meets the preset performance indicators, the current process control is maintained; if it does not meet the preset performance indicators, the process control is adjusted.

Images