Medium-temperature pitch proportioning optimization method and system for graphite electrode

Abstract

The invention provides a medium-temperature pitch proportion optimization method and system for a graphite electrode, and relates to the field of material engineering. The medium-temperature pitch proportion optimization system for the graphite electrode comprises a proportion analysis module which establishes a proportion model of graphite electrode production through mathematical modeling and data analysis according to the particle size distribution of graphite particles and the viscosity and softening point characteristics of pitch, can analyze various parameters in the production process of the graphite electrode in real time, and can optimize the proportion of the pitch in the graphite electrode production process; the optimal asphalt ratio range is calculated; and the data acquisition module is used for acquiring data of key parameters in the production process, including the size, temperature and humidity of graphite particles and the viscosity of asphalt, and is connected with the central control system through a sensor to transmit the data in real time for further analysis. Through the accurate asphalt proportion and optimization process, the strength, thermal stability, oxidation resistance and other physical properties of the graphite electrode can be effectively improved, and the rejection rate is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of materials engineering, and particularly to a method and system for optimizing the ratio of medium-temperature pitch for graphite electrodes. Background Art

[0002] As an important consumable in the electric arc furnace smelting process, graphite electrodes are widely used in industries such as steel and aluminum smelting. The quality of graphite electrodes directly affects the stability and efficiency of the smelting process. Therefore, ensuring the production quality of graphite electrodes is the key to improving smelting production efficiency and reducing costs. The manufacture of graphite electrodes mainly relies on high-quality raw materials and precise mixing ratio processes, especially the mixing ratio of pitch and graphite powder. During the production process, the medium-temperature characteristics of pitch play a crucial role in the performance of the electrodes. Therefore, how to optimize the ratio of pitch and graphite powder, especially the ratio of medium-temperature pitch, has become an important research topic in the production of graphite electrodes.

[0003] In the prior art, during the production process of graphite electrodes, the ratio of pitch to graphite powder mostly relies on experience or manual adjustment, lacking an effective automated system. This traditional ratio method has multiple problems, including a lag in response to changes in temperature, humidity, and raw material composition during the production process, resulting in inaccurate ratios and further affecting the performance and quality of the electrodes. In addition, in the traditional production process, the medium-temperature characteristics of pitch are insufficiently controlled and regulated, and the influence of temperature on the properties of pitch such as fluidity and adhesiveness cannot be fully considered, resulting in poor product consistency and low qualification rates.

[0004] With the continuous development of industrial automation technology and intelligent control systems, more and more enterprises seek to improve the production efficiency and product quality of graphite electrodes through scientific and reasonable ratio optimization methods. However, existing graphite electrode ratio optimization systems often can only be adjusted according to fixed empirical parameters, failing to fully combine real-time monitoring data and dynamic changes in the production environment, lacking precise control and optimization for the ratio of medium-temperature pitch. Therefore, the technical personnel in this field have provided a method and system for optimizing the ratio of medium-temperature pitch for graphite electrodes to solve the problems raised in the above background art. Summary of the Invention

[0005] (1) Technical Problems to be Solved

[0006] Aiming at the deficiencies of the prior art, the present invention provides a method and system for optimizing the ratio of medium-temperature pitch for graphite electrodes, solving the problem that existing optimization ratio systems fail to fully combine real-time monitoring data and dynamic changes in the production environment and lack precise control and optimization for the ratio of medium-temperature pitch.

[0007] (2) Technical Solutions

[0008] To achieve the above object, the present invention is implemented through the following technical solutions: A medium-temperature pitch ratio optimization system for graphite electrodes, comprising:

[0009] A ratio analysis module, according to the particle size distribution of graphite particles, the viscosity and softening point characteristics of pitch, through mathematical modeling and data analysis, establishes a ratio model for the production of graphite electrodes, can analyze various parameters in the production process of graphite electrodes in real time, and calculates the optimal pitch ratio range;

[0010] A data acquisition module, used to collect data of key parameters in the production process, including the size, temperature, humidity of graphite particles and the viscosity of pitch, and is connected to the central control system through sensors to transmit data in real time for further analysis;

[0011] An intelligent optimization algorithm module, by adopting an optimization algorithm based on artificial intelligence, can automatically adjust the addition amount of pitch and the mixing time, so that the quality and production efficiency of graphite electrodes reach the best state, and can adaptively adjust production parameters according to historical and current production situations;

[0012] A feedback control module, during the production process, the feedback control module compares the production data monitored in real time with the set target value. Once it is found that the ratio does not meet the predetermined standard, the system will automatically adjust the pitch addition amount or other relevant parameters to ensure the quality stability of graphite electrodes;

[0013] A user interface module, provides a user interaction interface, allows production personnel to view real-time data in the production process as needed, perform manual intervention or set target ratio parameters. At the same time, the system will provide an optimized ratio plan according to the algorithm suggestion for the operator's reference.

[0014] Preferably, the ratio analysis module includes the following steps:

[0015] S1. Determine the analysis target, set performance parameters, including conductivity, compressive strength and thermal stability and actual use conditions, and use them as the reference standard for analysis;

[0016] S2. Select raw materials and key components, conduct a preliminary screening of different types of pitch, carbon materials and other components, and select suitable medium-temperature pitch as the base material according to the softening point and viscosity properties of different pitches;

[0017] S3. Construct a ratio experimental design, determine the proportion range of each raw material, select an experimental design method, set multiple experimental points for each raw material, and by setting different raw material proportions, the influence of each ratio on the performance of graphite electrodes can be systematically evaluated;

[0018] S4. Preparation and testing of proportioned samples. According to the proportion design, prepare experimental samples and conduct various physical and chemical property tests on the samples.

[0019] S5. Data collection and preliminary analysis. Collect all test results, conduct a preliminary analysis of the properties of samples with different proportions, summarize various test data, including conductivity, compressive strength, and heat resistance, and perform preliminary data visualization using charts and statistical tools to analyze the influence trend of different proportions on properties.

[0020] S6. Multivariate regression analysis and model establishment. Based on the experimental data, use regression analysis or response surface method to construct the data relationship between proportion and properties, determine the contribution degree of each raw material component to the properties of graphite electrodes, predict the properties of different proportions through the model, and find the optimal proportion.

[0021] S7. Optimization and sensitivity analysis. Use optimization algorithms to optimize the proportion to minimize or maximize the objective, conduct sensitivity analysis, and evaluate the influence degree of different factors on the optimization objective.

[0022] S8. Verification and adjustment of the optimization plan. Prepare and test the optimized samples, check whether the expected performance requirements are met. If the optimization result is not ideal, adjust the model or proportion plan according to the test feedback and conduct iterative optimization.

[0023] S9. Determination of the final proportion and production implementation. Determine the final asphalt proportion and the proportions of other raw materials, conduct small-scale production, and verify the feasibility of the optimized proportion in large-scale production.

[0024] Preferably, the data acquisition module includes the following steps:

[0025] S1. Determine data acquisition requirements and indicators. Determine the types of data to be collected, including but not limited to temperature, pressure, humidity, raw material proportion, viscosity, conductivity, and compressive strength. Define the accuracy, frequency, and range of data acquisition, and determine which data are collected in real-time and which are collected periodically.

[0026] S2. Select and deploy sensors and measurement devices. Install temperature sensors to monitor the temperature during the production process, install pressure sensors and force sensors to monitor mechanical pressure and deformation parameters in real-time, install flow meters and humidity sensor devices to detect the fluidity and humidity changes of raw materials. For conductivity and compressive strength, select suitable test equipment and connect these sensors and devices to the data acquisition system to ensure the accuracy and real-time of data.

[0027] S3. Synchronization and Timing Management of Data Acquisition, configure the data acquisition system to automatically acquire data at a set frequency, use a clock synchronization system to ensure that the timestamps of all sensors are consistent, and set up a buffer during data acquisition to avoid data loss or overwrite;

[0028] S4. Data Transmission and Storage, configure the data transmission module to transmit data from sensors to the central processing system in real time, configure the data storage system to store the acquired data in a database, and set data storage policies to ensure data security and integrity;

[0029] S5. Data Preprocessing and Quality Control, the raw data acquired may contain noise, errors or missing values, and perform denoising, completion, normalization and anomaly detection on the acquired data respectively;

[0030] S6. Data Analysis and Visualization, use data analysis software to analyze the data, identify the relationships or trends between the data, configure a real-time monitoring dashboard to display real-time data, create charts through data visualization tools to show the relationship between raw material ratios and performance indicators, and generate reports regularly to analyze the impact of different ratios on performance during the production process;

[0031] S7. Data Archiving and Report Generation, archive historical data, generate regular reports, and conduct archiving management;

[0032] S8. Data Security and Permission Management, ensure data security, avoid data leakage or tampering, and the data acquisition system needs to perform access control to ensure that only authorized personnel can access and operate sensitive data.

[0033] Preferably, the intelligent optimization algorithm module includes the following steps:

[0034] S1. Define the optimization objectives and constraints, by minimizing production costs, improving the performance of graphite electrodes, or optimizing multiple objectives simultaneously, through material ratio limitations, process parameter limitations and environmental protection and safety regulations, single-objective optimization or multi-objective optimization can be adopted, determine the weights of the objective functions, and combine multiple constraints for constraint;

[0035] S2. Select one or more optimization algorithms according to the actual situation, combine the genetic algorithm and the particle swarm optimization algorithm, utilize the global search ability of the genetic algorithm and the local search ability of the particle swarm optimization to improve the optimization effect, set the parameters of the optimization algorithm, and perform algorithm tuning;

[0036] S3. Build an optimization model and training data, in order for the optimization algorithm to work effectively, an optimization model must be built and the corresponding training data must be prepared. The inputs of the model are usually raw material ratios and production process parameters, and the outputs are the performance indicators of the products;

[0037] S4. Initialize the optimization algorithm, which requires initializing the algorithm parameters and decision variables;

[0038] S5. Perform optimization iteration and evaluation, execute the optimization algorithm, start iterative search for the optimal solution. The optimization algorithm continuously improves the solution through selection, crossover, and mutation operations until a predetermined stopping condition is reached;

[0039] S6. Convergence judgment and result output. After multiple iterations, the optimization algorithm will obtain an optimal solution or a solution close to the optimal one, judge whether the convergence condition has been reached, and output the optimization result;

[0040] S7. Result verification and feedback adjustment. The optimized ratio plan needs to be verified to ensure its feasibility and effectiveness in actual production;

[0041] S8. System integration and automatic control. Integrate the optimization algorithm module with the production system to achieve automatic optimization and real-time adjustment of the ratio, forming a closed-loop control.

[0042] Preferably, the feedback control module includes the following steps:

[0043] S1. Determine the control objective and feedback signal. First, it is necessary to clarify what the objective of the feedback control is, and which production parameters need to be used as feedback signals for real-time monitoring;

[0044] S2. Design the control strategy. According to the selected objective and feedback signal, design a suitable control strategy, usually based on classical control theory, modern control theory, or adaptive control, fuzzy control;

[0045] S3. Collect real-time production data. Through sensors and data acquisition systems, various parameters in the production process are collected in real time;

[0046] S4. Set the controller parameters. According to the production objective and the design of the control strategy, set the parameters of the feedback controller;

[0047] S5. Real-time monitoring and error calculation. The control system calculates the difference between the real-time collected data and the set target.

[0048] A method for using a medium-temperature pitch ratio optimization system for graphite electrodes includes the following steps:

[0049] S1. Data collection and preliminary analysis. Collect information such as the particle size, humidity of graphite particles, and physical properties of pitch through the data collection module, input these data into the ratio analysis module, and perform preliminary ratio calculation;

[0050] S2. Establish an optimization model, use artificial intelligence algorithms to analyze the interaction between graphite particles and pitch, and establish an optimization model for pitch ratio according to different production requirements and material characteristics to predict the impact of different ratios on the performance of electrodes.

[0051] S3. Dynamically optimize the ratio. According to the optimization model and real-time feedback data, the intelligent optimization algorithm module adjusts the ratio in real time to ensure the best utilization rate of pitch and the quality of electrodes during the production process.

[0052] S4. Feedback adjustment. During the production process, real-time monitor and feedback data. When there is a deviation, the system will automatically adjust the pitch ratio and other parameters to ensure that the final product meets the expected performance.

[0053] S5. Production process monitoring and optimization. Through the user interface module, production personnel can view the results of ratio optimization at any time. If necessary, they can perform manual intervention or adjust production parameters.

[0054] (III) Beneficial effects

[0055] The present invention provides a method and system for optimizing the medium-temperature pitch ratio of graphite electrodes, with the following beneficial effects:

[0056] 1. In the present invention, through precise pitch ratio and optimization process, the physical properties such as strength, thermal stability, and oxidation resistance of graphite electrodes can be effectively improved, the scrap rate can be reduced, and the intelligent optimization system can reasonably control the addition amount of pitch, avoid overuse, reduce waste of raw materials, and reduce production costs.

[0057] 2. In the present invention, the real-time adjustment and feedback mechanism of the system makes the production process more stable and efficient, reduces the frequency of manual intervention and variability during the production process. By optimizing the pitch ratio and production parameters, it helps to reduce energy consumption and exhaust gas emissions, meeting the requirements of green manufacturing. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a system flowchart of the overall process of the present invention;

[0059] Figure 2 It is a schematic flowchart of the ratio analysis module in the present invention;

[0060] Figure 3 It is a schematic flowchart of the data acquisition module in the present invention;

[0061] Figure 4 It is a schematic flowchart of the intelligent optimization algorithm module in the present invention;

[0062] Figure 5 It is a schematic flowchart of the feedback control module in the present invention. Detailed implementation mode

[0063] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0064] Embodiment 1:

[0065] As Figures 1-5 shown, the embodiment of the present invention provides a medium-temperature asphalt ratio optimization system for graphite electrodes, including:

[0066] A ratio analysis module, according to the particle size distribution of graphite particles, the viscosity and softening point characteristics of asphalt, through mathematical modeling and data analysis, establishes a ratio model for the production of graphite electrodes, can analyze various parameters in the production process of graphite electrodes in real time, and calculates the optimal asphalt ratio range;

[0067] A data acquisition module, used to collect data of key parameters in the production process, including the size, temperature, humidity of graphite particles and the viscosity of asphalt, and is connected to the central control system through sensors to transmit data in real time for further analysis;

[0068] An intelligent optimization algorithm module, by adopting an optimization algorithm based on artificial intelligence, can automatically adjust the addition amount of asphalt and the mixing time, so that the quality and production efficiency of graphite electrodes reach the best state, and can adaptively adjust production parameters according to historical and current production conditions;

[0069] A feedback control module, during the production process, the feedback control module compares the production data monitored in real time with the set target value. Once it is found that the ratio does not meet the predetermined standard, the system will automatically adjust the asphalt addition amount or other relevant parameters to ensure the quality stability of graphite electrodes;

[0070] A user interface module, provides a user interaction interface, allows production personnel to view real-time data in the production process as needed, perform manual intervention or set target ratio parameters. At the same time, the system will provide an optimized ratio plan according to the algorithm suggestion for the operator's reference.

[0071] The ratio analysis module includes the following steps:

[0072] S1. Determine the analysis target, set performance parameters, including conductivity, compressive strength and thermal stability and actual use conditions, and use them as the reference standard for analysis;

[0073] S2. Select raw materials and key components, conduct preliminary screening on different types of asphalt, carbon materials and other components, and select appropriate medium-temperature asphalt as the base material according to the softening point and viscosity properties of different asphalt;

[0074] S3. Construct a proportion experiment design, determine the proportion range of each raw material, select an experiment design method, set multiple experimental points for each raw material, and by setting different raw material proportions, the influence of each proportion on the performance of graphite electrodes can be systematically evaluated;

[0075] S4. Preparation and testing of proportion samples, prepare experimental samples according to the proportion design, and conduct various physical and chemical property tests on the samples;

[0076] S5. Data collection and preliminary analysis, collect all test results, conduct preliminary analysis on the performance of samples with different proportions, summarize various test data, including conductivity, compressive strength and heat resistance, and use charts and statistical tools for preliminary data visualization to analyze the influence trend of different proportions on performance;

[0077] S6. Multivariate regression analysis and model establishment, based on experimental data, use regression analysis or response surface method to construct the data relationship between proportion and performance, determine the contribution degree of each raw material component to the performance of graphite electrodes, predict the performance of different proportions through the model, and find the optimal proportion;

[0078] S7. Optimization and sensitivity analysis, use optimization algorithms to optimize the proportion to minimize or maximize the objective, conduct sensitivity analysis, and evaluate the influence degree of different factors on the optimization objective;

[0079] S8. Verification and adjustment of the optimization plan, prepare and test the optimized samples, check whether the expected performance requirements are met, if the optimization result is not ideal, adjust the model or proportion plan according to the test feedback, and conduct iterative optimization;

[0080] S9. Determination of the final proportion and implementation of production, determine the final asphalt proportion and the proportion of other raw materials, conduct small-batch production, and verify the feasibility of the optimized proportion in large-scale production.

[0081] The data acquisition module includes the following steps:

[0082] S1. Determine data acquisition requirements and indicators, determine the types of data to be collected, including but not limited to temperature, pressure, humidity, raw material proportion, viscosity, conductivity and compressive strength, define the accuracy, frequency and range of data acquisition, and determine which data are collected in real time and which are collected periodically;

[0083] S2. Select and deploy sensors and measurement devices. Install temperature sensors to monitor the temperature during the production process, install pressure sensors and force sensors to monitor mechanical pressure and deformation parameters in real time, install flow meters and humidity sensor devices to detect the fluidity and humidity changes of raw materials. For conductivity and compressive strength, select suitable test equipment. Connect these sensors and devices to the data acquisition system to ensure the accuracy and real-time nature of the data;

[0084] S3. Synchronization and timing management of data acquisition. Configure the data acquisition system to be able to automatically acquire data at a set frequency. Use a clock synchronization system to ensure that the timestamps of each sensor are consistent. Set up a buffer during the data acquisition process to avoid data loss or overwriting;

[0085] S4. Data transmission and storage. Configure the data transmission module to transmit data from the sensors to the central processing system in real time. Configure the data storage system to store the acquired data in a database. Set the data storage strategy to ensure the security and integrity of the data;

[0086] S5. Data preprocessing and quality control. The raw data acquired may contain noise, errors or missing values. Perform denoising, completion, standardization and anomaly detection on the acquired data respectively;

[0087] S6. Data analysis and visualization. Use data analysis software to analyze the data, identify the relationships or trends between the data. Configure a real-time monitoring dashboard to display real-time data. Make charts through data visualization tools to show the relationship between the raw material ratio and performance indicators. Generate reports regularly to analyze the impact of different ratios on performance during the production process;

[0088] S7. Data archiving and report generation. Archive the historical data, generate regular reports, and conduct archiving management;

[0089] S8. Data security and permission management. Ensure the security of the data to avoid data leakage or tampering. The data acquisition system needs to perform access control to ensure that only authorized personnel can access and operate sensitive data.

[0090] The intelligent optimization algorithm module includes the following steps:

[0091] S1. Define the optimization objectives and constraints. By minimizing production costs, improving the performance of graphite electrodes, or optimizing multiple objectives simultaneously, through material ratio limitations, process parameter limitations, and environmental protection and safety regulations, single-objective optimization or multi-objective optimization can be adopted. Determine the weights of the objective functions and perform constraints in combination with various constraints;

[0092] S2. Select one or more optimization algorithms according to the actual situation, combine the genetic algorithm with the particle swarm optimization algorithm, utilize the global search ability of the genetic algorithm and the local search ability of the particle swarm optimization to improve the optimization effect, set the parameters of the optimization algorithm, and perform algorithm tuning;

[0093] S3. Build an optimization model and training data. To enable the optimization algorithm to work effectively, it is necessary to build an optimization model and prepare the corresponding training data. The input of the model is usually the raw material ratio and production process parameters, and the output is the performance index of the product;

[0094] S4. Initialize the optimization algorithm, and it is necessary to initialize the algorithm parameters and decision variables;

[0095] S5. Perform optimization iteration and evaluation. Execute the optimization algorithm, start iterative search for the optimal solution. The optimization algorithm continuously improves the solution through selection, crossover, and mutation operations until the predetermined stop condition is reached;

[0096] S6. Convergence judgment and result output. After multiple iterations, the optimization algorithm will obtain an optimal solution or a solution close to the optimal one. Judge whether the convergence condition has been reached and output the optimization result;

[0097] S7. Result verification and feedback adjustment. The optimized ratio scheme needs to be verified to ensure its feasibility and effectiveness in actual production;

[0098] S8. System integration and automatic control. Integrate the optimization algorithm module with the production system to achieve automatic optimization and real-time adjustment of the ratio, and form a closed-loop control.

[0099] The feedback control module includes the following steps:

[0100] S1. Determine the control objective and feedback signal. First, it is necessary to clarify what the objective of the feedback control is, and which production parameters need to be used as feedback signals for real-time monitoring;

[0101] S2. Design the control strategy. According to the selected objective and feedback signal, design a suitable control strategy, usually based on classical control theory, modern control theory, or adaptive control, fuzzy control;

[0102] S3. Collect real-time production data. Through sensors and data acquisition systems, various parameters in the production process are collected in real time;

[0103] S4. Set the controller parameters. According to the production objective and the design of the control strategy, set the parameters of the feedback controller;

[0104] S5. Real-time monitoring and error calculation. The control system calculates the difference between the real-time collected data and the set target.

[0105] A method for using a medium-temperature asphalt ratio optimization system for graphite electrodes, comprising the following steps:

[0106] S1. Data collection and preliminary analysis: Collect information such as the particle size, humidity of graphite particles, and physical properties of asphalt through the data collection module, and input these data into the ratio analysis module for preliminary ratio calculation;

[0107] S2. Establish an optimization model: Use artificial intelligence algorithms to analyze the interaction between graphite particles and asphalt, and establish an optimization model for asphalt ratio according to different production requirements and material characteristics to predict the impact of different ratios on electrode performance;

[0108] S3. Dynamically optimize the ratio: According to the optimization model and real-time feedback data, the intelligent optimization algorithm module adjusts the ratio in real time to ensure the best utilization rate of asphalt and the quality of electrodes during the production process;

[0109] S4. Feedback adjustment: During the production process, monitor the feedback data in real time. When deviations occur, the system will automatically adjust the asphalt ratio and other parameters to ensure that the final product meets the expected performance;

[0110] S5. Production process monitoring and optimization: Through the user interface module, production personnel can view the results of ratio optimization at any time. If necessary, they can perform manual intervention or adjust production parameters.

[0111] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A medium-temperature pitch ratio optimization system for graphite electrodes, characterized in that: Including: A ratio analysis module that, based on the particle size distribution of graphite particles, the viscosity and softening point characteristics of pitch, establishes a ratio model for the production of graphite electrodes through mathematical modeling and data analysis. It can analyze various parameters in the production process of graphite electrodes in real time and calculate the optimal pitch ratio range; A data acquisition module for collecting data on key parameters in the production process, including the size, temperature, humidity of graphite particles, and the viscosity of pitch, and connecting to the central control system through sensors to transmit data in real time for further analysis; An intelligent optimization algorithm module that, by adopting an optimization algorithm based on artificial intelligence, can automatically adjust the addition amount of pitch and the mixing time to make the quality and production efficiency of graphite electrodes reach the optimal state, and can adaptively adjust production parameters according to historical and current production situations; A feedback control module that, during the production process, compares the production data monitored in real time with the set target values. Once it is found that the ratio does not meet the predetermined standard, the system will automatically adjust the pitch addition amount or other relevant parameters to ensure the quality stability of graphite electrodes; A user interface module that provides a user interaction interface, allowing production personnel to view real-time data in the production process as needed, perform manual intervention or set target ratio parameters. At the same time, the system will provide an optimized ratio plan according to algorithm suggestions for operators to refer to.

2. The medium-temperature pitch ratio optimization system for graphite electrodes according to claim 1, characterized in that: The ratio analysis module includes the following steps: S1. Determine the analysis objectives, set performance parameters, including conductivity, compressive strength, and thermal stability and actual usage conditions, and use them as reference standards for analysis; S2. Select raw materials and key components, conduct a preliminary screening of different types of pitch, carbon materials, and other components, and select suitable medium-temperature pitch as the base material according to the softening point and viscosity properties of different pitches; S3. Construct a ratio experimental design, determine the proportion range of each raw material, select an experimental design method, set multiple experimental points for each raw material, and systematically evaluate the influence of each ratio on the performance of graphite electrodes by setting different raw material ratios; S4. Preparation and testing of ratio samples, prepare experimental samples according to the ratio design, and conduct various physical and chemical performance tests on the samples; S5. Data collection and preliminary analysis, collect all test results, conduct a preliminary analysis of the performance of samples with different ratios, summarize various test data, including conductivity, compressive strength, and heat resistance, and use charts and statistical tools for preliminary data visualization to analyze the influence trend of different ratios on performance; S6. Multivariate regression analysis and model establishment, based on experimental data, use regression analysis or response surface method to construct the data relationship between ratio and performance, determine the contribution degree of each raw material component to the performance of graphite electrodes, predict the performance of different ratios through the model, and find the optimal ratio; S7. Optimization and sensitivity analysis, use an optimization algorithm to optimize the ratio to minimize or maximize the objective, conduct sensitivity analysis, and evaluate the influence degree of different factors on the optimization objective; S8. Verification and adjustment of the optimization plan, prepare and test the optimized samples, check whether the expected performance requirements are met. If the optimization result is not ideal, adjust the model or formulation according to the test feedback and perform iterative optimization; S9. Determination of the final formulation and production implementation, determine the final asphalt formulation and the proportions of other raw materials, conduct small-scale production, and verify the feasibility of the optimized formulation in large-scale production.

3. The medium-temperature pitch ratio optimization system for graphite electrodes according to claim 1, wherein: The data acquisition module includes the following steps: S1. Determine the data acquisition requirements and metrics, determine the types of data to be collected, including but not limited to temperature, pressure, humidity, raw material ratio, viscosity, conductivity, and compressive strength, define the accuracy, frequency, and range of data acquisition, and determine which data are collected in real-time and which are collected periodically; S2. Select and deploy sensors and measurement devices, install temperature sensors to monitor the temperature during the production process, install pressure sensors and force sensors to monitor mechanical pressure and deformation parameters in real-time, install flow meters and humidity sensor devices to detect the fluidity and humidity changes of raw materials, and select suitable test devices for conductivity and compressive strength. Connect these sensors and devices to the data acquisition system to ensure the accuracy and real-time of the data; S3. Synchronization and timing management of data acquisition, configure the data acquisition system to automatically collect data at the set frequency, use a clock synchronization system to ensure the consistency of the timestamps of each sensor, and set up a buffer during the data acquisition process to avoid data loss or overwriting; S4. Data transmission and storage, configure the data transmission module to transmit data from the sensors to the central processing system in real-time, configure the data storage system to store the collected data in the database, and set the data storage strategy to ensure the security and integrity of the data; S5. Data preprocessing and quality control, the collected raw data may contain noise, errors, or missing values. Denoise, complete, standardize, and detect anomalies for the collected data respectively; S6. Data analysis and visualization, use data analysis software to analyze the data, identify the relationships or trends between the data, configure a real-time monitoring dashboard to display real-time data, create charts through data visualization tools to show the relationship between the raw material ratio and performance indicators, and generate reports regularly to analyze the impact of different formulations on performance during the production process; S7. Data archiving and report generation, archive the historical data, generate regular reports, and conduct archiving management; S8. Data security and access control, ensure the security of the data, prevent data leakage or tampering. The data acquisition system needs to perform access control to ensure that only authorized personnel can access and operate sensitive data.

4. The medium-temperature pitch ratio optimization system for graphite electrodes according to claim 1, characterized in that: The intelligent optimization algorithm module includes the following steps: S1. Define the optimization objectives and constraints, by minimizing production costs, improving the performance of graphite electrodes, or optimizing multiple objectives simultaneously, through material ratio limitations, process parameter limitations, and environmental protection and safety regulations, single-objective optimization or multi-objective optimization can be adopted. Determine the weights of the objective functions and combine multiple constraints for constraint; S2. Select one or more optimization algorithms according to the actual situation, combine the genetic algorithm with the particle swarm optimization algorithm, utilize the global search ability of the genetic algorithm and the local search ability of the particle swarm optimization to improve the optimization effect, set the parameters of the optimization algorithm, and perform algorithm tuning; S3. Construct an optimization model and training data. In order for the optimization algorithm to work effectively, it is necessary to construct an optimization model and prepare the corresponding training data. The input of the model is usually the raw material ratio and production process parameters, and the output is the performance index of the product; S4. Initialize the optimization algorithm, and it is necessary to initialize the algorithm parameters and decision variables; S5. Perform optimization iteration and evaluation. Execute the optimization algorithm, start iterative search for the optimal solution. The optimization algorithm continuously improves the solution through selection, crossover, and mutation operations until the predetermined stopping condition is reached; S6. Convergence judgment and result output. After multiple iterations, the optimization algorithm will obtain an optimal solution or a solution close to the optimal one. Judge whether the convergence condition has been reached and output the optimization result; S7. Result verification and feedback adjustment. The optimized ratio plan needs to be verified to ensure its feasibility and effect in actual production; S8. System integration and automatic control. Integrate the optimization algorithm module with the production system to achieve automatic optimization and real-time adjustment of the ratio, and form a closed-loop control.

5. The medium-temperature pitch ratio optimization system for graphite electrodes according to claim 1, wherein: The feedback control module includes the following steps: S1. Determine the control objective and feedback signal. First, it is necessary to clarify what the objective of the feedback control is, and which production parameters need to be used as feedback signals for real-time monitoring; S2. Design the control strategy. According to the selected objective and feedback signal, design a suitable control strategy, usually based on classical control theory, modern control theory, or adaptive control, fuzzy control; S3. Collect real-time production data. Through sensors and data acquisition systems, collect various parameters in the production process in real time; S4. Set the controller parameters. According to the production objective and the design of the control strategy, set the parameters of the feedback controller; S5. Real-time monitoring and error calculation. The control system will calculate the difference between the real-time collected data and the set target.

6. A method for using a medium-temperature pitch ratio optimization system for graphite electrodes, characterized in that: It includes the following steps: S1. Data collection and preliminary analysis. Collect information such as the particle size, humidity of graphite particles, and physical properties of asphalt through the data collection module, input these data into the ratio analysis module, and perform preliminary ratio calculation; S2. Establish an optimization model. Use artificial intelligence algorithms to analyze the interaction between graphite particles and asphalt, and establish an optimization model for asphalt ratio according to different production requirements and material characteristics to predict the influence of different ratios on the electrode performance; S3. Dynamically optimize the ratio. According to the optimization model and real-time feedback data, the intelligent optimization algorithm module adjusts the ratio in real time to ensure the best utilization rate of asphalt and the quality of the electrode during the production process; S4. Feedback adjustment. During the production process, monitor the feedback data in real time. When a deviation occurs, the system will automatically adjust the asphalt ratio and other parameters to ensure that the final product meets the expected performance; S5. Production process monitoring and optimization. Through the user interface module, production personnel can view the results of ratio optimization at any time. If necessary, they can perform manual intervention or adjust production parameters.

Images