Blast furnace pulverized coal combustion efficiency optimization method and system based on deep learning

Abstract

The invention relates to the technical field of blast furnace combustion optimization, in particular to a blast furnace pulverized coal combustion efficiency optimization method and system based on deep learning, which not only can significantly improve the blast furnace pulverized coal combustion efficiency, but also can enhance the economic benefit and environmental protection performance of the whole steel production. The method comprises the following steps: acquiring blast furnace combustion condition monitoring data and surrounding environment condition monitoring data in real time; performing feature extraction on the blast furnace combustion condition monitoring data and the surrounding environment condition monitoring data by using a pre-trained pulverized coal combustion efficiency influence feature extraction model to obtain a pulverized coal combustion efficiency influence feature set; acquiring combined pulverized coal injection ratio data participating in combustion in the blast furnace in real time, wherein the combined pulverized coal injection ratio data comprises pulverized coal types and proportions thereof; and based on the combined pulverized coal injection ratio data, respectively calling pulverized coal combustion efficiency influence analysis models corresponding to the pulverized coal types from the pulverized coal model database.

Description

Technical Field

[0001] The present invention relates to the technical field of blast furnace combustion optimization, and in particular to a method and system for optimizing blast furnace coal powder combustion efficiency based on deep learning. Background Art

[0002] In modern steel production, the blast furnace is the core equipment for ironmaking, and its operating efficiency directly affects the production capacity and cost of the entire steel production line. Blast furnace coal powder combustion is a key link in the blast furnace smelting process. Its combustion efficiency is not only related to the thermal efficiency of the blast furnace, but also directly affects the stable operation of the blast furnace and product quality.

[0003] In the existing methods for optimizing blast furnace pulverized coal combustion efficiency, the evaluation of pulverized coal combustion efficiency is often carried out after the combustion process is completed, resulting in the inability to adjust combustion parameters in a timely manner to optimize efficiency; at the same time, the adjustment of coal injection ratio is usually based on fixed experience and formulas, and lacks the ability to dynamically adjust according to real-time data. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a blast furnace coal powder combustion efficiency optimization method and system based on deep learning, which can not only significantly improve the blast furnace coal powder combustion efficiency, but also enhance the economic benefits and environmental protection performance of the entire steel production.

[0005] In a first aspect, the present invention provides a method for optimizing blast furnace coal powder combustion efficiency based on deep learning, the method comprising:

[0006] Obtain real-time monitoring data of blast furnace combustion conditions and surrounding environment conditions;

[0007] Using the pre-trained pulverized coal combustion efficiency impact feature extraction model, feature extraction is performed on the blast furnace combustion condition monitoring data and the surrounding environment condition monitoring data to obtain the pulverized coal combustion efficiency impact feature set;

[0008] Real-time acquisition of combined pulverized coal injection ratio data participating in combustion in a blast furnace, wherein the combined pulverized coal injection ratio data includes pulverized coal types and their proportions;

[0009] Based on the combined pulverized coal injection ratio data, the pulverized coal combustion efficiency impact analysis models corresponding to each pulverized coal type are retrieved from the pulverized coal model database;

[0010] The pulverized coal combustion efficiency impact feature set is input into the pulverized coal combustion efficiency impact analysis model corresponding to each pulverized coal type to obtain the real-time combustion efficiency impact score of each pulverized coal type;

[0011] Based on the preset combustion efficiency impact optimization strategy, according to the combined pulverized coal injection ratio data and the real-time combustion efficiency impact score of each pulverized coal type, the proportion of each pulverized coal type in the combined pulverized coal is dynamically adjusted to obtain the combined pulverized coal injection optimization ratio data;

[0012] According to the combined pulverized coal injection optimization ratio data, blast furnace coal injection combustion supply is carried out.

[0013] Furthermore, the pulverized coal combustion efficiency influencing feature set includes blast furnace internal temperature distribution characteristics, gas composition characteristics, pressure and flow characteristics, pulverized coal characteristic parameters, external environment characteristics and historical data analysis.

[0014] Furthermore, the method for obtaining blast furnace combustion condition monitoring data and surrounding environment condition monitoring data includes:

[0015] Deploy sensors on the blast furnace, including temperature sensors, pressure sensors, gas concentration sensors and flow sensors; deploy a meteorological station in the surrounding environment of the blast furnace;

[0016] Collect data from each sensor node in real time and transmit the data to the central processing unit;

[0017] Preprocess the collected data, including data cleaning, denoising, and outlier detection;

[0018] Store the collected data.

[0019] Furthermore, the method for constructing the pulverized coal model database comprises:

[0020] Collect the combustion experimental data of various types of pulverized coal in blast furnaces and the historical data of blast furnace operation;

[0021] Preprocess the collected data, including noise removal, missing value filling, and data standardization;

[0022] Extracting features related to pulverized coal combustion efficiency from the collected data to obtain a pulverized coal feature set;

[0023] For each type of pulverized coal, a pulverized coal combustion efficiency impact analysis model is trained using its corresponding pulverized coal feature set and historical data of blast furnace operation;

[0024] The trained pulverized coal combustion efficiency impact analysis model is integrated into the pulverized coal model database.

[0025] Furthermore, the calculation formula for dynamically adjusting the proportion of each type of coal powder in the combined coal powder is:

[0026]

[0027] Among them, pi Indicates the proportion of the i-th type of coal powder in the current coal injection ratio, s i represents the real-time combustion efficiency impact score of the i-th coal powder type, and α is the adjustment coefficient used to adjust the score s i Pair ratio i The intensity of the impact, p i ′ Indicates the ratio adjusted according to the real-time combustion efficiency impact score.

[0028] Furthermore, the combustion efficiency impact optimization strategy includes:

[0029] According to the real-time combustion efficiency impact score of each type of pulverized coal, dynamically adjust its weight in the combined pulverized coal, and calculate the optimal combined pulverized coal ratio;

[0030] Adjust the combustion temperature and oxygen supply in the blast furnace according to the real-time temperature data in the blast furnace and the combustion characteristics of pulverized coal;

[0031] Optimize the mixing sequence of pulverized coal according to the combustion speed and combustion characteristics of different pulverized coal types;

[0032] Establish a real-time monitoring system for blast furnace coal powder combustion efficiency to monitor and record the parameters during the combustion process in real time.

[0033] Further, according to the combined pulverized coal injection optimization ratio data, a method for blast furnace coal injection combustion supply is performed, comprising:

[0034] Transmit the combined pulverized coal injection optimized ratio data to the blast furnace coal injection control system;

[0035] After receiving the optimized ratio data, the blast furnace coal injection system adjusts the distribution ratio in the pulverized coal distributor according to the optimized ratio data:

[0036] Adjust the number, position and intensity of the spray guns;

[0037] During the coal injection process, the combustion conditions in the blast furnace are monitored in real time.

[0038] On the other hand, the present application also provides a blast furnace coal powder combustion efficiency optimization system based on deep learning, the system comprising:

[0039] Data acquisition module, real-time acquisition of blast furnace combustion status monitoring data and surrounding environment status monitoring data;

[0040] The feature extraction module uses the pre-trained pulverized coal combustion efficiency impact feature extraction model to extract features from the blast furnace combustion condition monitoring data and the surrounding environment condition monitoring data to obtain the pulverized coal combustion efficiency impact feature set;

[0041] A coal injection ratio data acquisition module is used to acquire the combined coal powder injection ratio data participating in the combustion in the blast furnace in real time, wherein the combined coal powder injection ratio data includes the coal powder type and its proportion;

[0042] A data retrieval module, based on the combined pulverized coal injection ratio data, retrieves the pulverized coal combustion efficiency impact analysis models corresponding to each pulverized coal type from the pulverized coal model database; the pulverized coal model database stores pulverized coal combustion efficiency impact analysis models corresponding to all pulverized coal types;

[0043] The combustion efficiency impact analysis module inputs the coal powder combustion efficiency impact feature set into the coal powder combustion efficiency impact analysis model corresponding to each coal powder type, and obtains the real-time combustion efficiency impact score of each coal powder type; the higher the real-time combustion efficiency impact score, the greater the impact on the combustion efficiency corresponding to the coal powder type is under real-time conditions, and the lower the combustion efficiency is;

[0044] The combustion efficiency optimization decision module dynamically adjusts the proportion of each type of coal in the combined pulverized coal based on the pre-set combustion efficiency impact optimization strategy and the combined pulverized coal injection ratio data and the real-time combustion efficiency impact score of each type of coal to obtain the combined pulverized coal injection optimization ratio data;

[0045] The blast furnace coal injection combustion supply control module performs blast furnace coal injection combustion supply according to the combined coal powder injection optimization ratio data.

[0046] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0047] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0048] Compared with the prior art, the present invention has the following beneficial effects: the method can obtain the combustion status and surrounding environment data of the blast furnace in real time, and immediately analyze and process them; the system can quickly respond to changes in the blast furnace state, and dynamically adjust the coal injection ratio based on real-time data, greatly improving the efficiency and accuracy of combustion efficiency optimization;

[0049] By extracting and analyzing the features of real-time data through pre-trained deep learning models, decisions can be made based on data, reducing the impact of human intervention and subjective judgment. The data-driven approach makes decisions more objective and scientific, which helps to improve the accuracy of blast furnace combustion efficiency optimization.

[0050] Integrating artificial intelligence technology, this method realizes the intelligent and automated optimization of blast furnace coal powder combustion efficiency; it can automatically complete tasks such as data acquisition, feature extraction, model analysis, optimization decision-making and combustion supply control, reducing the complexity and cost of manual operations;

[0051] For different types of pulverized coal and blast furnace conditions, this method can train different deep learning models and perform personalized optimization adjustments, so that the system can better adapt to different production scenarios and needs, improving the flexibility and adaptability of the system;

[0052] By real-time analysis and dynamic adjustment of the coal injection ratio, this method can optimize the combustion process of blast furnace coal powder and improve combustion efficiency; at the same time, due to the timely adjustment of combustion parameters, it also helps to improve the stability of the blast furnace and product quality, and reduce fluctuations and uncertainties in the production process;

[0053] Improved combustion efficiency means that the blast furnace can use energy more effectively during the production process, thereby reducing energy consumption and production costs;

[0054] In summary, this deep learning-based blast furnace coal powder combustion efficiency optimization method can not only significantly improve the blast furnace coal powder combustion efficiency, but also enhance the economic benefits and environmental protection performance of the entire steel production, providing more reliable and efficient technical support for modern steel production. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a flow chart of the present invention;

[0056] Figure 2 This is the structural diagram of the blast furnace pulverized coal combustion efficiency optimization system based on deep learning. DETAILED DESCRIPTION

[0057] In the description of the present application, those skilled in the art should know that the present application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, the present application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0058] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0059] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0060] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0061] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0062] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0063] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0064] The present application is described below in conjunction with the drawings in the present application.

[0065] Embodiment 1: Figure 1 As shown, the blast furnace coal powder combustion efficiency optimization method based on deep learning of the present invention specifically includes the following steps:

[0066] S1. Obtain real-time monitoring data of blast furnace combustion status and surrounding environment status;

[0067] The method for obtaining blast furnace combustion condition monitoring data and surrounding environment condition monitoring data includes:

[0068] Various sensors are deployed at key locations of the blast furnace and its surrounding environment, including temperature sensors, pressure sensors, gas concentration sensors, and flow sensors; weather stations are deployed around the blast furnace; sensors monitor key parameters such as temperature, pressure, gas composition, and flow rate inside the blast furnace in real time, and weather stations monitor external environment factors such as wind speed, wind direction, humidity, etc. that may affect blast furnace combustion in real time;

[0069] Collect data from each sensor node in real time and transmit the data to the central processing unit;

[0070] Preprocess the collected data, including data cleaning, denoising, and outlier detection, to ensure that the data input into the subsequent model is accurate and usable; the signal also needs to be filtered to eliminate unnecessary interference;

[0071] Store the collected data for subsequent analysis and historical record query;

[0072] When deploying the sensor network, it is necessary to fully consider the complex environment and harsh conditions of the blast furnace, select sensors that are resistant to high temperatures, corrosion, and vibration, and arrange them reasonably to ensure the comprehensiveness and accuracy of the monitoring data;

[0073] During real-time data transmission, it is necessary to ensure the security and integrity of the data to prevent data tampering or loss.

[0074] In this step, by deploying various types of sensors at key locations of the blast furnace body and its surrounding environment, and setting up meteorological stations to monitor external environmental factors, the comprehensiveness and accuracy of the data are ensured; a solid foundation is provided for the subsequent optimization of combustion efficiency; the sensor network collects data in real time and transmits the data to the central processing unit through a high-speed data transmission network, ensuring the real-time nature of the data; real-time data can reflect the current combustion status and environmental changes of the blast furnace, thereby allowing the system to adjust the combustion parameters in a timely manner; preprocessing the collected data significantly improves the data quality; ensuring that the data input into the subsequent model is accurate, reliable and available, thereby improving the accuracy and effectiveness of the model analysis; storing the collected data not only facilitates subsequent analysis and historical record inquiries, but also provides long-term monitoring of the blast furnace combustion process. and optimization; through the comparison and analysis of historical data, the changing patterns and influencing factors of blast furnace combustion efficiency can be further revealed; when deploying the sensor network, the complex environment and harsh conditions of the blast furnace are fully considered, and high temperature resistant, corrosion resistant and vibration resistant sensors are selected, and a reasonable layout is carried out; the reliability and stability of the sensors in the extreme environment of the blast furnace are ensured, thereby ensuring the continuity and accuracy of the monitoring data; in the process of real-time data transmission, necessary security measures are taken to ensure the security and integrity of the data; data is prevented from being tampered with or lost during transmission, ensuring the authenticity and credibility of the data; this step provides strong data support for the optimization of blast furnace pulverized coal combustion efficiency by comprehensively, real-time and accurately acquiring blast furnace combustion condition monitoring data and surrounding environmental condition monitoring data.

[0075] S2. Using the pre-trained pulverized coal combustion efficiency impact feature extraction model, feature extraction is performed on the blast furnace combustion condition monitoring data and the surrounding environment condition monitoring data to obtain a pulverized coal combustion efficiency impact feature set;

[0076] Input the blast furnace combustion status monitoring data and the surrounding environment status monitoring data into the pre-trained feature extraction model; the model automatically extracts key features from the data to form a feature set that affects the pulverized coal combustion efficiency;

[0077] Regularly validate and test the feature extraction model to ensure that it remains stable and reliable on new data;

[0078] Analyzing the influence of each feature in the feature set on combustion efficiency helps to understand the complexity of the combustion process and key influencing factors, and provides guidance for the subsequent optimization strategy formulation;

[0079] Effectively integrate data features from different sensors and sources to form a more comprehensive and accurate set of features affecting pulverized coal combustion efficiency;

[0080] The pulverized coal combustion efficiency impact feature set includes:

[0081] Temperature distribution characteristics inside the blast furnace: Temperature data at different heights and areas of the blast furnace, including the top temperature, the body temperature and the hearth temperature, which reflect the heat transfer and energy conversion efficiency during the pulverized coal combustion process; temperature differences, including the radial temperature difference of the body and the temperature difference between the hearth and the body, which indicate problems of uneven combustion and heat loss;

[0082] Gas composition characteristics: The gas composition at the blast furnace outlet. The changes in the composition reflect the completeness of the coal powder combustion and the progress of the chemical reaction. The oxygen supply in the blast furnace tuyere area has a direct impact on the coal powder combustion efficiency.

[0083] Pressure and flow characteristics: pressure data at different locations in the blast furnace. Pressure changes will affect the injection and combustion effects of pulverized coal. The gas flow and wind speed in the tuyere area have an important influence on the mixing of pulverized coal and oxygen and the combustion rate.

[0084] Pulverized coal characteristic parameters: The particle size distribution, moisture content and volatile content of pulverized coal affect the combustion performance and efficiency of pulverized coal; the real-time injection rate and injection volume of pulverized coal are closely related to the distribution and combustion state of pulverized coal in the blast furnace;

[0085] External environmental characteristics: External environmental factors will affect the heat dissipation and ventilation conditions of the blast furnace, and thus affect the pulverized coal combustion efficiency; the stability and quality fluctuations of raw material supply will indirectly affect the pulverized coal combustion efficiency by affecting the overall operation status of the blast furnace;

[0086] Historical data analysis: Trend features extracted from historical data that indicate potential changes in combustion efficiency; the impact of different stages in the blast furnace operation cycle on pulverized coal combustion efficiency.

[0087] In this step, through the pre-trained pulverized coal combustion efficiency influencing feature extraction model, key features can be automatically extracted from the complex blast furnace combustion condition monitoring data and the surrounding environment condition monitoring data to form a pulverized coal combustion efficiency influencing feature set, which can quickly respond to the real-time changes in the blast furnace combustion state; the extracted feature set comprehensively covers various factors affecting the pulverized coal combustion efficiency. The comprehensive consideration of these features makes the subsequent optimization strategy formulation more accurate and can propose effective improvement measures for specific problems; the feature extraction model is regularly verified and tested to ensure that its performance on new data remains stable and reliable; so that the model can adapt to blast furnace combustion conditions pulverized coal combustion efficiency, and provides a richer information basis for the formulation of optimization strategies. This step provides strong support for the optimization of pulverized coal combustion efficiency and the overall efficiency and economic benefits of steel production.

[0088] S3, real-time acquisition of combined pulverized coal injection ratio data participating in combustion in the blast furnace, wherein the combined pulverized coal injection ratio data includes pulverized coal type and its proportion;

[0089] The method for obtaining the combined pulverized coal injection ratio data participating in combustion in a blast furnace comprises:

[0090] Real-time monitoring and recording of the injection volume of pulverized coal and the mixing ratio of different types of pulverized coal;

[0091] Combined pulverized coal is a mixture of different types of pulverized coal, each of which has different combustion characteristics; therefore, when collecting data, it is necessary to clearly identify the type and identification of each pulverized coal;

[0092] The proportion of pulverized coal refers to the percentage of each type of pulverized coal in the pulverized coal combustion in the blast furnace; this proportion directly determines the overall combustion characteristics of the mixed pulverized coal and has an important impact on the combustion efficiency and stability of the blast furnace;

[0093] Since the blast furnace combustion process is a dynamic process, the combined pulverized coal injection ratio data also needs to be updated in real time; data acquisition is required to quickly respond to changes in the blast furnace operating status and provide the latest data to the optimization algorithm in a timely manner;

[0094] Before using the data in the optimization algorithm, the collected data is preprocessed, including data cleaning and data normalization;

[0095] The processed data is stored securely and reliably for subsequent analysis and query.

[0096] In this step, by real-time monitoring and recording the injection volume of coal powder and the mixing ratio of different types of coal powder, the real-time nature of the data can be ensured; the type and identification of each type of coal powder and the percentage of each type of coal powder in the mixed coal powder are clarified, and the accuracy of the data is ensured; since the combined coal powder is a mixture of multiple different types of coal powder, and each type of coal powder has different combustion characteristics, by real-time acquisition and analysis of these data, the proportion of coal powder can be flexibly adjusted to adapt to changes in the blast furnace combustion process; it is helpful to improve the combustion efficiency and stability of the blast furnace; before the real-time acquired data is used in the optimization algorithm, necessary data preprocessing is performed to ensure the quality of the data; then, these high-quality data are input into the optimization algorithm to achieve data-based optimization decisions; the processed data is stored safely and reliably, which not only ensures the integrity of the data, but also facilitates subsequent analysis and query; Step S3 lays a solid foundation for the optimization of blast furnace coal powder combustion efficiency by providing real-time, accurate, flexible and high-quality data support, which helps to improve the combustion efficiency and stability of the blast furnace, reduce production costs, and improve product quality, thereby achieving sustainable development of steel production.

[0097] S4. Based on the combined pulverized coal injection ratio data, the pulverized coal combustion efficiency impact analysis models corresponding to each pulverized coal type are retrieved from the pulverized coal model database; the pulverized coal model database stores pulverized coal combustion efficiency impact analysis models corresponding to all pulverized coal types;

[0098] The method for constructing the pulverized coal model database comprises:

[0099] Collect combustion experimental data of various types of pulverized coal in blast furnaces and historical data of blast furnace operation;

[0100] Preprocess the collected data, including removing noise, filling missing values, and standardizing data; ensure the accuracy and consistency of the data to provide a reliable basis for subsequent modeling;

[0101] Extract features related to pulverized coal combustion efficiency from the original data to obtain a pulverized coal feature set, which includes the pulverized coal's physical and chemical properties, combustion conditions, and blast furnace operating conditions; use feature selection technology to screen out the feature set that has the greatest impact on combustion efficiency;

[0102] For each type of pulverized coal, a pulverized coal combustion efficiency impact analysis model is trained using its corresponding pulverized coal feature set and historical data of blast furnace operation;

[0103] Integrate the trained coal powder combustion efficiency impact analysis model into the coal powder model database; the database should support efficient data retrieval and model calling functions to quickly obtain the required model during the real-time optimization process; with the continuous accumulation of new data and the continuous advancement of technology, the model should be regularly updated and tuned to improve its prediction accuracy and adaptability.

[0104] In this step, by collecting combustion experimental data of various types of coal powder in blast furnaces and historical data of blast furnace operation, and after strict preprocessing and feature selection, the accuracy and consistency of the model training data are ensured; this enables the trained coal powder combustion efficiency impact analysis model to more accurately reflect the changing law of coal powder combustion efficiency, thereby improving the accuracy of combustion efficiency evaluation; the coal powder model database supports real-time calling of the combustion efficiency impact analysis model corresponding to each coal powder type, and dynamically evaluates the combustion efficiency impact of each coal powder type based on the real-time blast furnace combustion status and combined coal powder injection ratio data; so that the blast furnace coal powder combustion process can be based on actual The system can adjust the situation in time to achieve higher combustion efficiency and more stable operation status; the pulverized coal model database contains the combustion efficiency impact analysis models corresponding to all pulverized coal types, so that the system can easily cope with the switching and combination of different pulverized coal types; when the blast furnace needs to use a new type of pulverized coal or adjust the pulverized coal ratio, the system can quickly retrieve the corresponding model from the database for evaluation and optimization, enhancing the flexibility and adaptability of the system; with the continuous accumulation of new data and the continuous advancement of technology, the pulverized coal model database supports regular updating and tuning of the model, which means that the system can continuously absorb new knowledge and experience to improve the prediction accuracy and adaptability of the model.

[0105] S5. Input the pulverized coal combustion efficiency impact feature set into the pulverized coal combustion efficiency impact analysis model corresponding to each pulverized coal type, and obtain the real-time combustion efficiency impact score of each pulverized coal type; the higher the real-time combustion efficiency impact score, the greater the degree of impact on the combustion efficiency corresponding to the pulverized coal type under real-time conditions, and the lower the combustion efficiency;

[0106] Input the coal powder combustion efficiency influencing feature set into the model corresponding to each coal powder type;

[0107] After receiving the input feature set, each pulverized coal combustion efficiency impact analysis model will calculate according to its internal algorithm and parameters to obtain the real-time combustion efficiency impact score of each pulverized coal type under the current blast furnace combustion status and environmental conditions;

[0108] The real-time combustion efficiency impact score reflects the degree to which the combustion efficiency of a specific coal powder type is affected under current conditions;

[0109] The higher the score, the more the combustion efficiency of the pulverized coal type is affected under the current conditions, that is, the lower the combustion efficiency;

[0110] Record the real-time combustion efficiency impact score of each coal powder type for subsequent analysis and optimization; feedback the results to the system to ensure that the score can be used for the next optimization decision.

[0111] In this step, by inputting the coal powder combustion efficiency impact feature set into the model corresponding to each coal powder type in real time, the real-time combustion efficiency impact score of each coal powder type under the current blast furnace combustion status and environmental conditions can be immediately obtained; so that the blast furnace operator can quickly respond to changes in the combustion state and take adjustment measures in time to improve the combustion efficiency; each coal powder combustion efficiency impact analysis model can fully consider the complex factors in the blast furnace combustion process, so as to more accurately evaluate the combustion efficiency impact of each coal powder type; the real-time combustion efficiency impact score not only reflects the combustion efficiency status of each coal powder type under the current conditions, but also provides a basis for dynamically adjusting the combined coal powder injection ratio; according to the scoring results, the system can automatically adjust the coal powder ratio to optimize the overall combustion efficiency, which helps to improve the stability and production efficiency of the blast furnace; by real-time evaluation and adjustment of coal powder combustion efficiency, it can significantly reduce energy consumption and emissions in the blast furnace smelting process, improve energy utilization and environmental protection level; at the same time, the improvement of combustion efficiency also helps to increase the output and quality of steel products, thereby enhancing the market competitiveness of enterprises.

[0112] S6. Based on the preset combustion efficiency impact optimization strategy, according to the combined pulverized coal injection ratio data and the real-time combustion efficiency impact score of each pulverized coal type, dynamically adjust the proportion of each pulverized coal type in the combined pulverized coal to obtain the combined pulverized coal injection optimization ratio data;

[0113] Integrate the real-time combustion efficiency impact scores of each pulverized coal type and the combined pulverized coal injection ratio data, and through the analysis of these data, identify which pulverized coal types have lower combustion efficiency under current conditions and which pulverized coal types have relatively higher combustion efficiency;

[0114] Based on the integrated and analyzed data, the proportion of each type of pulverized coal in the combined pulverized coal is dynamically adjusted according to the pre-set optimization strategy; this adjustment process involves complex calculations and optimization algorithms to ensure that the pulverized coal combustion efficiency is maximized while maintaining the stable operation of the blast furnace; the calculation formula for dynamically adjusting the proportion of each type of pulverized coal in the combined pulverized coal is:

[0115]

[0116] Among them, p i Indicates the proportion of the i-th type of coal powder in the current coal injection ratio, s i represents the real-time combustion efficiency impact score of the i-th coal powder type, and α is the adjustment coefficient used to adjust the score s i Pair ratioi The intensity of the impact, p i ′ It indicates the ratio adjusted according to the real-time combustion efficiency impact score;

[0117] For coal powder types with higher real-time combustion efficiency impact scores, reduce their proportion in the combined coal powder to reduce their adverse effects on the overall combustion efficiency; correspondingly, for coal powder types with lower real-time combustion efficiency impact scores, increase their proportion in the combined coal powder to improve the overall combustion efficiency;

[0118] The combustion efficiency impact optimization strategy includes:

[0119] Proportion optimization adjustment: According to the real-time combustion efficiency impact score of each type of pulverized coal, dynamically adjust its weight in the combined pulverized coal; for pulverized coal types with low real-time combustion efficiency impact scores, appropriately reduce their proportions; on the contrary, for pulverized coal types with high impact scores, consider increasing their proportions or replacing them with pulverized coal types with higher efficiency; use optimization algorithms to calculate the best combined pulverized coal ratio to maximize the overall combustion efficiency;

[0120] Optimization of combustion conditions: According to the real-time temperature data in the blast furnace and the combustion characteristics of pulverized coal, the combustion temperature in the blast furnace is adjusted to optimize the combustion efficiency of the pulverized coal; the oxygen supply in the blast furnace is adjusted to ensure that the pulverized coal burns in an environment with sufficient oxygen, thereby improving the combustion efficiency;

[0121] Optimization of pulverized coal mixing strategy: Consider the combustion speed and combustion characteristics of different types of pulverized coal and optimize the pulverized coal mixing sequence; try various pulverized coal mixing ratios while keeping the total coal injection amount unchanged to find the combination that is most conducive to improving combustion efficiency;

[0122] Real-time monitoring feedback: Establish a real-time monitoring system for blast furnace coal powder combustion efficiency to monitor and record key parameters in the combustion process in real time; timely evaluate changes in coal powder combustion efficiency based on real-time monitoring data, and adjust the optimization strategy for combustion efficiency based on the evaluation results.

[0123] In this step, by real-time evaluation and adjustment of the pulverized coal ratio, it is possible to quickly respond to changes in the combustion process, reduce the proportion of pulverized coal types with low combustion efficiency, and increase the proportion of pulverized coal types with high combustion efficiency, thereby significantly improving the overall pulverized coal combustion efficiency; it helps to reduce the energy consumption and production costs of blast furnaces and improve the economic benefits of steel production lines; the dynamic adjustment of pulverized coal ratio not only focuses on combustion efficiency, but also comprehensively considers the stable operation of the blast furnace and product quality; by optimizing the mixing order and proportion of pulverized coal, it can reduce furnace condition fluctuations caused by uneven combustion of pulverized coal, maintain the stable operation of the blast furnace, and reduce the production process The failure rate and downtime in the blast furnace are reduced; the improvement of combustion efficiency directly affects the smelting effect of the blast furnace, and optimizing the coal powder ratio can improve the heat distribution and chemical reaction conditions in the blast furnace, thereby increasing the output and quality of molten iron; by improving the combustion efficiency of coal powder, the emission of unburned coal powder and energy waste are reduced; at the same time, optimizing combustion conditions and coal powder mixing strategies also help to reduce the generation and emission of harmful gases; this step achieves a comprehensive improvement in combustion efficiency, blast furnace stability, product quality and output by dynamically adjusting the proportion of each type of coal powder in the combined coal powder, thereby promoting the intelligent and green development of the steel production industry.

[0124] S7, according to the combined pulverized coal injection optimization ratio data, the blast furnace coal injection combustion supply;

[0125] The method for blast furnace coal injection combustion supply according to the combined coal powder injection optimization ratio data includes:

[0126] The optimized ratio data of combined pulverized coal injection is transmitted to the blast furnace pulverized coal injection control system; during the transmission process, data verification is performed to ensure the accuracy and completeness of the optimized ratio data to avoid abnormal operation of the blast furnace caused by erroneous data;

[0127] The blast furnace coal injection system includes coal powder preparation, coal powder transportation, coal powder distribution and injection. After receiving the optimized ratio data, the coal injection equipment is adjusted accordingly:

[0128] According to the optimized ratio data, adjust the distribution ratio in the pulverized coal distributor to ensure that various pulverized coals are mixed in the predetermined ratio;

[0129] Adjust the number, position and injection intensity of the injection guns to adapt to the new pulverized coal ratio, ensure that the pulverized coal is evenly distributed in the blast furnace, and improve combustion efficiency;

[0130] During the coal injection process, real-time monitoring of the combustion conditions in the blast furnace, including temperature distribution, gas composition, coal powder combustion rate and other parameters;

[0131] If it is found that the combustion efficiency does not meet expectations, or the blast furnace operation is unstable, the control system should promptly analyze the reasons and consider whether it is necessary to fine-tune the optimized ratio data;

[0132] At the same time, the monitoring system will also record various data during the coal injection process to provide data support for subsequent optimization work.

[0133] In this step, by acquiring and applying the optimized ratio data based on deep learning in real time, the combustion process of pulverized coal in the blast furnace can be controlled more accurately, ensuring that various types of pulverized coal are mixed in the optimal proportion, thereby improving the combustion efficiency of pulverized coal; it not only helps to improve the thermal efficiency of the blast furnace, but also reduces energy waste and reduces production costs; the optimized ratio data can fully consider the current combustion status of the blast furnace and the surrounding environmental conditions, so as to dynamically adjust the pulverized coal ratio to meet the actual needs of blast furnace operation; it helps to reduce fluctuations and unstable factors in blast furnace operation and improve the continuity and stability of the production process; the optimization of pulverized coal combustion efficiency directly affects the quality of molten iron smelted by the blast furnace; by improving the combustion efficiency, To ensure the stability of the temperature, atmosphere and other conditions in the blast furnace, which is conducive to the removal of impurities in the molten iron and the improvement of its purity, thereby producing higher quality products; through real-time monitoring and recording of various data during the coal injection process, it provides rich data support for subsequent optimization work; it is used to analyze the laws and characteristics of blast furnace operation, provide a basis for formulating more scientific and reasonable combustion strategies, and promote blast furnace production to develop in a more efficient and environmentally friendly direction; the beneficial effect of this step is that through the application of optimized ratio data, precise control and intelligent management of blast furnace coal injection combustion supply are achieved, combustion efficiency is improved, the stability of blast furnace operation is enhanced, product quality is improved, and the intelligent upgrade of blast furnace production is promoted.

[0134] Embodiment 2: Figure 2 As shown, the blast furnace coal powder combustion efficiency optimization system based on deep learning of the present invention specifically includes the following modules;

[0135] Data acquisition module, real-time acquisition of blast furnace combustion status monitoring data and surrounding environment status monitoring data;

[0136] The feature extraction module uses the pre-trained pulverized coal combustion efficiency impact feature extraction model to extract features from the blast furnace combustion condition monitoring data and the surrounding environment condition monitoring data to obtain the pulverized coal combustion efficiency impact feature set;

[0137] A coal injection ratio data acquisition module is used to acquire the combined coal powder injection ratio data participating in the combustion in the blast furnace in real time, wherein the combined coal powder injection ratio data includes the coal powder type and its proportion;

[0138] A data retrieval module, based on the combined pulverized coal injection ratio data, retrieves the pulverized coal combustion efficiency impact analysis models corresponding to each pulverized coal type from the pulverized coal model database; the pulverized coal model database stores pulverized coal combustion efficiency impact analysis models corresponding to all pulverized coal types;

[0139] The combustion efficiency impact analysis module inputs the coal powder combustion efficiency impact feature set into the coal powder combustion efficiency impact analysis model corresponding to each coal powder type, and obtains the real-time combustion efficiency impact score of each coal powder type; the higher the real-time combustion efficiency impact score, the greater the impact on the combustion efficiency corresponding to the coal powder type is under real-time conditions, and the lower the combustion efficiency is;

[0140] The combustion efficiency optimization decision module dynamically adjusts the proportion of each type of coal in the combined pulverized coal based on the pre-set combustion efficiency impact optimization strategy and the combined pulverized coal injection ratio data and the real-time combustion efficiency impact score of each type of coal to obtain the combined pulverized coal injection optimization ratio data;

[0141] The blast furnace coal injection combustion supply control module performs blast furnace coal injection combustion supply according to the combined coal powder injection optimization ratio data.

[0142] The system can obtain the combustion status and environmental data of the blast furnace in real time, and immediately extract and analyze features, so that the combustion parameters can be adjusted in time during the combustion process; ensuring that the system can quickly respond to changes in the combustion status of the blast furnace, avoiding the lag of evaluation and adjustment after the combustion process is completed in the traditional method;

[0143] By processing real-time data through deep learning models, the coal injection ratio can be dynamically adjusted according to the current combustion conditions and coal powder ratio; this overcomes the limitations of traditional methods that rely on fixed experience and formulas for adjustment, and improves the accuracy and flexibility of combustion efficiency optimization;

[0144] The system integrates artificial intelligence technology, which can automatically extract useful information from large amounts of data and conduct complex analysis and decision-making; it enables the system to learn and optimize autonomously, reduces dependence on manual experience, and improves the system's automation and intelligence levels;

[0145] By real-time analysis and dynamic adjustment of the coal injection ratio, the combustion process of blast furnace pulverized coal can be optimized and the combustion efficiency can be improved; this not only helps to reduce the energy consumption and cost of the blast furnace, but also helps to improve the stability of the blast furnace and the product quality;

[0146] The system can be customized and expanded according to specific blast furnace production conditions and needs; it can also be integrated with other blast furnace control systems to achieve more comprehensive blast furnace production optimization; the system makes decisions based on real-time data, reducing the impact of human intervention and subjective judgment; making decisions more objective and scientific, and helping to improve the accuracy and reliability of decisions;

[0147] In summary, this system can not only significantly improve the combustion efficiency of pulverized coal in blast furnaces, but also enhance the economic benefits and environmental performance of the entire steel production, providing more reliable and efficient technical support for modern steel production.

[0148] The various variations and specific embodiments of the deep learning-based blast furnace coal powder combustion efficiency optimization method in the aforementioned embodiment 1 are also applicable to the deep learning-based blast furnace coal powder combustion efficiency optimization system in this embodiment. Through the aforementioned detailed description of the deep learning-based blast furnace coal powder combustion efficiency optimization method, those skilled in the art can clearly know the implementation method of the deep learning-based blast furnace coal powder combustion efficiency optimization system in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0149] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0150] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for optimizing blast furnace coal powder combustion efficiency based on deep learning, characterized in that: The method comprises: Obtain real-time monitoring data of blast furnace combustion conditions and surrounding environment conditions; Using the pre-trained pulverized coal combustion efficiency impact feature extraction model, feature extraction is performed on the blast furnace combustion condition monitoring data and the surrounding environment condition monitoring data to obtain the pulverized coal combustion efficiency impact feature set; Real-time acquisition of combined pulverized coal injection ratio data participating in combustion in a blast furnace, wherein the combined pulverized coal injection ratio data includes pulverized coal types and their proportions; Based on the combined pulverized coal injection ratio data, the pulverized coal combustion efficiency impact analysis models corresponding to each pulverized coal type are retrieved from the pulverized coal model database; The pulverized coal combustion efficiency impact feature set is input into the pulverized coal combustion efficiency impact analysis model corresponding to each pulverized coal type to obtain the real-time combustion efficiency impact score of each pulverized coal type; Based on the preset combustion efficiency impact optimization strategy, according to the combined pulverized coal injection ratio data and the real-time combustion efficiency impact score of each pulverized coal type, the proportion of each pulverized coal type in the combined pulverized coal is dynamically adjusted to obtain the combined pulverized coal injection optimization ratio data; According to the combined pulverized coal injection optimization ratio data, blast furnace coal injection combustion supply is carried out.

2. The method for optimizing blast furnace coal powder combustion efficiency based on deep learning according to claim 1, characterized in that: The pulverized coal combustion efficiency influencing feature set includes blast furnace internal temperature distribution characteristics, gas composition characteristics, pressure and flow characteristics, pulverized coal characteristic parameters, external environment characteristics and historical data analysis.

3. The method for optimizing blast furnace coal powder combustion efficiency based on deep learning according to claim 1, characterized in that: The method for obtaining blast furnace combustion condition monitoring data and surrounding environment condition monitoring data includes: Deploy sensors on the blast furnace, including temperature sensors, pressure sensors, gas concentration sensors and flow sensors; deploy a meteorological station in the surrounding environment of the blast furnace; Collect data from each sensor node in real time and transmit the data to the central processing unit; Preprocess the collected data, including data cleaning, denoising, and outlier detection; Store the collected data.

4. The method for optimizing blast furnace coal powder combustion efficiency based on deep learning according to claim 1, characterized in that: The method for constructing the pulverized coal model database comprises: Collect the combustion experimental data of various types of pulverized coal in blast furnaces and the historical data of blast furnace operation; Preprocess the collected data, including noise removal, missing value filling, and data standardization; Extracting features related to pulverized coal combustion efficiency from the collected data to obtain a pulverized coal feature set; For each type of pulverized coal, a pulverized coal combustion efficiency impact analysis model is trained using its corresponding pulverized coal feature set and historical data of blast furnace operation; The trained pulverized coal combustion efficiency impact analysis model is integrated into the pulverized coal model database.

5. The method for optimizing blast furnace coal powder combustion efficiency based on deep learning according to claim 1, characterized in that: The calculation formula for dynamically adjusting the proportion of each type of coal powder in the combined coal powder is: Among them, p i Indicates the proportion of the i-th type of coal powder in the current coal injection ratio, s i represents the real-time combustion efficiency impact score of the i-th coal powder type, and α is the adjustment coefficient used to adjust the score s i Ratio p i The intensity of the impact, p i ′ Indicates the ratio adjusted according to the real-time combustion efficiency impact score.

6. The method for optimizing blast furnace coal powder combustion efficiency based on deep learning according to claim 1, characterized in that: The combustion efficiency impact optimization strategy includes: According to the real-time combustion efficiency impact score of each type of pulverized coal, dynamically adjust its weight in the combined pulverized coal, and calculate the optimal combined pulverized coal ratio; Adjust the combustion temperature and oxygen supply in the blast furnace according to the real-time temperature data in the blast furnace and the combustion characteristics of pulverized coal; Optimize the mixing sequence of pulverized coal according to the combustion speed and combustion characteristics of different pulverized coal types; Establish a real-time monitoring system for blast furnace coal powder combustion efficiency to monitor and record the parameters during the combustion process in real time.

7. The method for optimizing blast furnace coal powder combustion efficiency based on deep learning according to claim 1, characterized in that: The method for blast furnace coal injection combustion supply according to the combined coal powder injection optimization ratio data includes: Transmit the combined pulverized coal injection optimized ratio data to the blast furnace coal injection control system; After receiving the optimized ratio data, the blast furnace coal injection system adjusts the distribution ratio in the pulverized coal distributor according to the optimized ratio data: Adjust the number, position and intensity of the spray guns; During the coal injection process, the combustion conditions in the blast furnace are monitored in real time.

8. A blast furnace coal powder combustion efficiency optimization system based on deep learning, characterized in that: The system comprises: Data acquisition module, real-time acquisition of blast furnace combustion status monitoring data and surrounding environment status monitoring data; The feature extraction module uses the pre-trained pulverized coal combustion efficiency impact feature extraction model to extract features from the blast furnace combustion condition monitoring data and the surrounding environment condition monitoring data to obtain the pulverized coal combustion efficiency impact feature set; A coal injection ratio data acquisition module is used to acquire the combined coal powder injection ratio data participating in the combustion in the blast furnace in real time, wherein the combined coal powder injection ratio data includes the coal powder type and its proportion; A data retrieval module, based on the combined pulverized coal injection ratio data, retrieves the pulverized coal combustion efficiency impact analysis models corresponding to each pulverized coal type from the pulverized coal model database; the pulverized coal model database stores pulverized coal combustion efficiency impact analysis models corresponding to all pulverized coal types; The combustion efficiency impact analysis module inputs the coal powder combustion efficiency impact feature set into the coal powder combustion efficiency impact analysis model corresponding to each coal powder type, and obtains the real-time combustion efficiency impact score of each coal powder type; the higher the real-time combustion efficiency impact score, the greater the impact on the combustion efficiency corresponding to the coal powder type is under real-time conditions, and the lower the combustion efficiency is; The combustion efficiency optimization decision module dynamically adjusts the proportion of each type of coal in the combined pulverized coal based on the pre-set combustion efficiency impact optimization strategy and the combined pulverized coal injection ratio data and the real-time combustion efficiency impact score of each type of coal to obtain the combined pulverized coal injection optimization ratio data; The blast furnace coal injection combustion supply control module performs blast furnace coal injection combustion supply according to the combined coal powder injection optimization ratio data.

9. An electronic device for optimizing blast furnace coal powder combustion efficiency based on deep learning, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, characterized in that: When the computer program is executed by the processor, the steps in the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 7 are implemented.

Images