Intelligent control system for blast furnace ironmaking pellet roasting

Abstract

The invention discloses a blast furnace ironmaking pellet roasting intelligent management and control system, and relates to the technical field of intelligent management and control, the system comprises the following components: a field data acquisition layer, a data transmission and storage layer, a cloud service platform layer, an intelligent analysis and optimization control layer and a user interaction interface layer. Various parameters in the pellet roasting process can be precisely controlled, errors and delay in traditional manual operation are effectively avoided through precise control, the production efficiency and the product quality are remarkably improved, the system can automatically recognize abnormal modes and potential risks in the production process, the technological parameters are automatically adjusted, and the production efficiency is improved. And the stability and reliability of the production process are improved, so that the rejection rate and the production of unqualified products are reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management and control technology, and in particular to an intelligent management and control system for blast furnace ironmaking pellet roasting. Background Art

[0002] In the traditional blast furnace ironmaking pellet roasting process, production control mainly relies on manual operation and on-site monitoring. This method has many shortcomings. First, manual monitoring is difficult to achieve all-weather, all-round real-time monitoring of the production site, which can easily lead to omissions and delayed processing of key data, thereby affecting production efficiency and product quality. Secondly, due to the complexity of the blast furnace ironmaking pellet roasting process, which involves a variety of physical and chemical reactions and high temperature and high pressure environments, manual judgment and control are often difficult to be accurate, and are prone to operational errors and untimely regulation, increasing safety hazards and accident risks in the production process.

[0003] In addition, most traditional management and control systems are deployed locally, with limited data storage and analysis capabilities, and are unable to fully utilize big data and advanced cloud computing technologies for deep mining and intelligent analysis. This limits the system's ability to monitor the production process in real time, predict and warn, and optimize and adjust, making it difficult to cope with the increasingly complex and changing production environment and market demands. Therefore, it is particularly important to develop an intelligent management and control system for blast furnace ironmaking pellet roasting. Summary of the invention

[0004] The purpose of the present invention is to make up for the deficiencies of the prior art and provide an intelligent control system for blast furnace ironmaking pellet roasting, which improves the automation level of the pellet roasting process through intelligent means, realizes precise control and optimized management, and thus improves the production quality and production efficiency of pellet ore.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent management and control system for blast furnace ironmaking pellet roasting, comprising a field data acquisition layer, a data transmission and storage layer, a cloud service platform layer, an intelligent analysis and optimization control layer, and a user interaction interface layer;

[0006] The on-site data collection layer deploys multiple sensors such as high-definition cameras, temperature sensors, pressure sensors, and gas analyzers to collect video images, temperature, pressure, and key parameter data of gas composition during pellet roasting in real time;

[0007] The data transmission and storage layer uses industrial Ethernet to safely and efficiently transmit the data collected on-site to the cloud server. The cloud server adopts a distributed storage architecture to ensure the reliability and scalability of the data.

[0008] The cloud service platform layer builds an intelligent management and control platform based on cloud computing, including a real-time monitoring module, a data analysis module, a report generation module, a fault diagnosis module, and an equipment maintenance management module. Users can access the platform through the Internet to view real-time videos and data reports of the production site, receive and process alarm information, and perform remote operations and fault diagnosis;

[0009] The intelligent analysis and optimization control layer uses big data analysis and machine learning algorithms to conduct in-depth mining of the collected data, identify abnormal patterns and potential risks in the production process, automatically adjust process parameters, optimize the roasting process, and achieve precise control. At the same time, it predicts future production trends based on historical data, providing a scientific basis for production planning and decision-making;

[0010] The user interaction interface layer is designed with an intuitive and easy-to-use user interface, supports multi-terminal access, and provides rich visual charts and operation interfaces, so that users can grasp the production status anytime and anywhere and perform remote management and control.

[0011] Furthermore, the field data acquisition layer selects a suitable installation position to ensure that the camera can cover the key area of ​​the pellet roasting, adjusts the focal length, angle and resolution of the camera to obtain a clear video image, starts the camera, and performs image acquisition at a fixed frame rate. The temperature sensor is installed at an appropriate position of the pellet roasting equipment, and a suitable temperature sensor type is selected. The temperature measurement principle of the thermocouple is: T = a × (V measured -V reference )+T reference , where a is the sensitivity coefficient of the thermocouple, V measured is the measured voltage, V reference is the reference voltage, V reference The temperature measurement formula of the thermal resistor is: R=R0×(1+α×T), where R is the measurement resistor, R0 is the reference resistor, α is the resistance temperature coefficient, and T is the temperature. The sensor converts the temperature into an electrical signal and transmits it to the data acquisition system.

[0012] Furthermore, the on-site data acquisition layer installs a pressure sensor at the pressure monitoring point of the pellet roasting equipment, determines the range and accuracy of the pressure sensor to meet the measurement requirements, and the pressure measurement formula is: P=F / A, where P is pressure, F is force, and A is the force area. The sensor outputs an electrical signal proportional to the pressure, which is received by the data acquisition system. A gas analyzer is installed at the gas sampling point to ensure that representative gas samples can be accurately extracted. The gas analyzer determines the concentration of the gas components through chemical analysis and physical detection methods, and the analysis results are transmitted to the data acquisition system in the form of digital signals.

[0013] Furthermore, the data transmission and storage layer evaluates the on-site environment and data transmission requirements, and determines to use industrial Ethernet and wireless communication technology. For industrial Ethernet, the bandwidth calculation formula is: bandwidth (B) = sampling frequency (f s )×number of quantization bits (n)×number of channels (m), install Ethernet switches, routers and wireless access point devices, establish a connection with the cloud server, ensure secure authentication and encrypted transmission, package and send the collected data according to the set protocol and format, data transmission rate formula: transmission rate (R) = data volume (D) / transmission time (t), the cloud server receives the data from the field, unpacks and verifies it, performs preliminary processing and classification of the data, adopts a distributed storage architecture, and distributes and stores the data on multiple storage nodes. The storage capacity calculation formula is: total storage capacity (C) = single node storage capacity (c)×number of nodes (N), establish a data copy and backup mechanism to ensure data reliability.

[0014] Furthermore, the cloud service platform layer selects a suitable cloud computing service provider, determines the configuration and storage capacity of the server according to the expected user access volume and data processing volume, and the storage capacity calculation formula is: storage capacity = average data volume × retention time × redundancy coefficient, where the redundancy coefficient is usually greater than 1 to cope with emergencies, configures a virtual network to ensure the security and stability of data transmission, establishes a stable connection with the on-site data acquisition equipment, sets the data acquisition frequency, and the acquisition frequency formula is: acquisition frequency = 1 / acquisition interval time. The collected real-time data and video images are encoded and compressed to reduce the transmission bandwidth requirement. The compression ratio formula is: compression ratio = original data size / compressed data size. The data and video are displayed in real time on the platform interface. The data analysis module is constructed using dynamic charts and real-time image refresh steps, collects and organizes historical data, establishes a data warehouse, and applies data analysis algorithms. The linear regression equation is: y = β0 + β1x1 + β2x2 + … + ∈, where β is the regression coefficient and ∈ is the error term. Generate analysis reports and visualization results. According to user needs and business rules, define the format and content of the report, extract relevant data from the database, calculate and summarize, and calculate the average value: where x i is the data point, n is the number of data points, and the report is generated according to the preset template, and supports export and printing.

[0015] Furthermore, the cloud service platform layer defines common fault types and corresponding characteristic indicators, monitors data in real time, and triggers an alarm when the indicator exceeds the normal range. The threshold judgment formula is: data value>upper threshold and data value<lower threshold. The fault diagnosis algorithm is used for analysis to locate the source of the fault and establish an equipment information database, including equipment model, installation time, and maintenance records. The next maintenance time is calculated based on the equipment operating time and maintenance cycle. The next maintenance time = current time + maintenance cycle. A maintenance work order is generated and the maintenance progress is tracked. Network access rights are configured to allow users to log in to the platform through the Internet. Encryption technology is used, and the encryption strength evaluation formula is: encryption strength = key length × algorithm complexity. User identity authentication and authorization mechanisms are set to ensure that only legitimate users can perform corresponding operations.

[0016] Furthermore, the intelligent analysis and optimization control layer obtains data in the production process from various data sources, including data collected by sensors and production records, integrates and formats the data to make it have a unified format and structure, cleans up missing values, and fills them with mean and median. The mean filling formula is: where x i is the non-missing value, n is the number of non-missing values, remove the noise data, and use the data smoothing method and moving average method: Where k is the window size, representative features are extracted from the original data, and the feature selection algorithm is used. Information gain: Select features that have an important impact on the model and choose a suitable machine learning algorithm, support vector machine (SVM). For SVM, its decision function is: f(x) = sign(∑ i＝1 α i y i K(x i ,x)+b), where α i is the Lagrange multiplier, y i is the category label, and K is the kernel function.

[0017] Furthermore, the intelligent analysis and optimization control layer inputs real-time data into the trained model to calculate the anomaly score. The anomaly score formula is Where x is the data point, μ is the mean, and σ is the standard deviation. The score is used to determine whether it is an abnormal mode. The direction and amplitude of the adjustment are determined based on the output of the model and the preset adjustment rules. The formula for adjusting the temperature is: NewTemperature=CurrentTemperature+ΔT, where ΔT is the adjustment amount. The adjusted production indicators are continuously monitored, and the optimization effect indicators and quality improvement rate are calculated: Based on historical data, the ARIMA model is established as a time series forecasting model. The expression of the ARIMA model is: φ(B)Φ(B)yt =θ(B)θ(B)∈ t , where B is the lag operator, which helps decision makers formulate production plans and decision strategies. The production planning formula is ProductionQuantity=DemandForecast×SafetyFactor, where DemandForecast is the demand forecast and SafetyFactor is the safety factor.

[0018] Furthermore, the user interaction interface layer communicates with users and relevant stakeholders to understand their needs for interface functions and operations, collects type and resolution information of multiple terminals, divides the interface area, determines the position and size of different functional areas for information display and operation control, selects appropriate visualization chart types, including but not limited to bar charts, line charts and pie charts, where for bar charts, the column height H is proportional to the data value D: H=k×D, where k is the proportionality coefficient, designs the color, font, and coordinate axis elements of the chart to enhance readability, determines the position, shape and size of the operation button, and designs the operation process to make it simple and intuitive.

[0019] Furthermore, the user interaction interface layer adjusts the layout and size of interface elements according to the screen size and resolution of different terminals, and dynamically adjusts the element width according to the screen width W: ElementWidth = W × proportion, where proportion is the set ratio, optimizes the interface loading speed, reduces the amount of data requests, and the loading time T is related to the data volume Q and the network speed V: T = Q / V. Invite users to test, collect their feedback, and improve and optimize the interface based on the feedback.

[0020] Compared with the existing technology, an intelligent control system for blast furnace ironmaking pellet roasting has the following beneficial effects:

[0021] 1. The intelligent control system for blast furnace ironmaking pellet roasting of the present invention can accurately control various parameters in the pellet roasting process through real-time monitoring and data analysis. This precise control effectively avoids errors and delays in traditional manual operations, significantly improves production efficiency and product quality. The system can automatically identify abnormal patterns and potential risks in the production process, and automatically adjust process parameters, the stability and reliability of the production process, thereby reducing the scrap rate and the generation of unqualified products.

[0022] 2. The intelligent management and control system realizes comprehensive automated monitoring and management of the pellet roasting process, greatly reducing the need for manual intervention. The traditional blast furnace ironmaking pellet roasting process requires a large amount of manpower for real-time monitoring and operation, which is not only costly but also has high safety risks. By introducing intelligent means, the system can automatically complete data collection, processing, analysis and control, significantly reducing labor costs. At the same time, the system can also monitor the safety status of the production site in real time, promptly discover and deal with potential safety hazards, and enhance the safety of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 An operation flow chart of an intelligent management and control system for blast furnace ironmaking pellet roasting. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Embodiment 1

[0027] This embodiment aims to comprehensively optimize the blast furnace ironmaking pellet roasting process by introducing an intelligent management and control system, significantly improve production efficiency, reduce energy consumption, and stabilize the production process.

[0028] High-definition cameras are installed in the key areas of the feed port, combustion zone, and discharge port of the pellet roasting equipment, and are equipped with infrared night vision function and intelligent tracking technology to ensure that clear video images can be obtained under different lighting conditions. Thermocouples and thermal resistors with high stability and fast response characteristics are selected and installed in different positions of the roasting furnace to monitor the temperature distribution in the furnace in real time to ensure that the measurement accuracy reaches ±0.5°C. High-precision pressure sensors are installed at the air inlet, air outlet and key process nodes of the roasting furnace. The measuring range and accuracy are customized according to actual needs to ensure that the pressure changes in the furnace can be accurately reflected. An online multi-component gas analyzer is introduced to continuously extract representative gas samples to monitor and analyze the key gas components of oxygen, carbon dioxide, and carbon monoxide in the roasting process in real time, providing a basis for optimizing combustion control.

[0029] The bandwidth of the existing industrial Ethernet is upgraded, and fiber-optic communication technology is adopted to ensure that the data transmission rate reaches the GB / s level and reduce data transmission delays. Wireless access points are added in the roasting workshop to achieve Wi-Fi and 5G dual-mode coverage to ensure the stability and flexibility of data transmission. High-performance cloud servers are selected and a distributed storage architecture is adopted to ensure reliable storage and fast access to massive data. At the same time, a data backup and recovery mechanism is established to ensure data security.

[0030] Develop a real-time monitoring module that integrates video monitoring, data display, and alarm reminder functions to achieve second-level data updates and all-round monitoring of the production site. Introduce deep learning algorithms and machine learning models to conduct in-depth mining of production process data, identify potential production fluctuations and risk points, and build a time series prediction model, expressed as: φ(B)Φ(B)y t =θ(B)θ(B)∈ t , where: B is the lag operator, indicating the delay operation, φ(B) and Φ(B) are the coefficient polynomials of the autoregressive (AR) part, usually expressed as φ(B) = 1-φ1B-φ2B 2 -…-φ p B p , Φ(B)=1-Φ1B-Φ2B 2 -…-Φ P B P (For the seasonal AR part, θ(B) and θ(B) are the coefficient polynomials of the moving average (MA) part, usually expressed as: θ(B) = 1-θ1B-θ2B 2 -…-θ q B q , Θ(B)=1-Θ1B-Θ2B 2 -…-Θ Q B Q (For the seasonal MA part), y t is the observed value of the time series at time t, ∈ t is a white noise sequence, usually assumed to have a mean of 0 and a variance of σ 2 It can predict future production trends based on historical data, provide a scientific basis for production planning, realize automatic generation and customized services of daily, weekly and monthly reports, support users to customize report content and format as needed, and improve the flexibility and practicality of data reports.

[0031] Based on the deep learning algorithm, a multi-factor comprehensive prediction model is constructed, considering multiple parameters such as temperature, pressure, and gas composition, accurately predicting the roasting effect and production efficiency, and developing an adaptive control system. According to real-time data and prediction results, the process parameters are automatically adjusted to achieve refined control of the production process. Genetic algorithms and particle swarm optimization algorithms are used. The genetic algorithm formula is as follows: Fitness function: defined according to the specific problem, used to evaluate the quality of individuals. Crossover probability: used to control the probability of occurrence of crossover operations, usually expressed as P co Mutation probability: used to control the probability of occurrence of mutation operation, usually expressed as P rn , the particle swarm optimization algorithm formula is: Speed ​​formula: v i (t+1)=wv i (t)+c1r1(p iBest -x i (t))+c2r2(g Best -x i (t)) where v i (t) is the velocity of particle i at the tth iteration, w is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers, p iBest is the historical optimal position of particle i, g Best is the global optimal position, x i (t) is the position of particle i at the tth iteration, and the position update formula is: i (t+1)=x i (t)+v i (t+1), globally optimize the production process, find the optimal combination of process parameters, and further improve production efficiency.

[0032] Adopting modern UI / UX design concepts, an intuitive and easy-to-use user interface is designed with a reasonable interface layout, clear information display, and easy operation. It provides 3D visualization display function of real-time data and production status. Users can intuitively understand the temperature distribution and gas flow in the furnace through the three-dimensional model. Mobile APP or mini-programs are developed to support access from smartphones and tablets, making it convenient for managers to check production conditions, receive alarm information and perform remote operations anytime and anywhere. A user feedback mechanism is established to regularly collect user opinions and suggestions to continuously optimize system functions and user experience.

[0033] In summary, this embodiment successfully constructs an intelligent management and control system for blast furnace ironmaking pellet roasting, realizes intelligent, automated and refined control of the production process, significantly improves production efficiency, reduces energy consumption, and lays a solid foundation for the sustainable development of the enterprise.

[0034] Embodiment 2

[0035] This embodiment aims to comprehensively improve user experience and production efficiency by building a remote monitoring and fault diagnosis system with a responsive user interface and an integrated cloud platform, and ensure visualization, controllability and intelligence of the production process.

[0036] Design a responsive user interface to ensure a good user experience on different types of terminals. Automatically adjust the layout and size of interface elements according to the screen size and resolution of the terminal to ensure clear display of information and ease of operation. The interface design follows the principle of simplicity and clarity, using intuitive icons and clear text descriptions to reduce the user's cognitive burden. Improve the readability and attractiveness of information through reasonable color matching and layout design. Establish a user feedback collection mechanism, regularly invite users to participate in interface design satisfaction surveys, collect user opinions and suggestions on interface layout, function settings, and ease of operation. Based on user feedback, continuously optimize the interface design, enhance user experience, optimize interface loading speed, reduce data request volume and response time, improve the overall performance of the system, and ensure a smooth experience for users during operation.

[0037] The cloud platform provides remote operation functions. Users can access the system through the Internet at any time and any place to adjust process parameters, view equipment status, and receive and process alarm information. These operation functions are transmitted through a secure network channel to ensure data integrity and security. Strict user permissions and identity authentication mechanisms are set to ensure that only legitimate users can perform corresponding remote operations. Different operation permissions are assigned according to the user's role and responsibilities. Assume that the user set is U = {u1,u2,…,u n}, the set of operation permissions is P = {p1, p2, ..., p m}, we can use an n×m matrix A to represent user permissions, where a ij =1 indicates user u i Has operation permission j , a ij =0 means user u i No operation permission j , prevent unauthorized access and operation, and display the data and video images of the production site in real time on the cloud platform interface. Through dynamic charts and real-time image refresh technology, users can grasp the production status at any time, discover problems in time and deal with them.

[0038] Through the fault diagnosis module of the cloud platform, the operating status and key parameters of the equipment are monitored in real time. When potential faults or abnormal modes are found, the system can automatically trigger the early warning mechanism and notify relevant personnel to handle them through text messages and emails. Using machine learning algorithms and fault diagnosis models, the collected data is deeply mined and analyzed, the source and cause of the fault can be quickly located, and detailed fault diagnosis reports and solution suggestions can be provided to help users quickly resume production. An equipment information database is established to record the equipment model, installation time and maintenance record details. Through data analysis functions, the maintenance cycle and replacement time of the equipment are predicted, and maintenance plans are formulated in advance to reduce production interruptions caused by equipment failures. According to the equipment maintenance plan and actual fault conditions, maintenance work orders are generated and assigned to relevant personnel for processing, and maintenance progress and results are tracked to ensure that the equipment can be maintained and repaired in a timely manner.

[0039] In summary, this embodiment, by constructing a responsive user interface and a cloud platform remote monitoring and fault diagnosis system, not only improves the user experience, but also realizes the intelligent management of the production process, improves production efficiency, reduces maintenance costs, and lays a solid foundation for the sustainable development of the enterprise.

[0040] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An intelligent control system for blast furnace ironmaking pellet roasting, characterized in that: The system includes a field data acquisition layer, a data transmission and storage layer, a cloud service platform layer, an intelligent analysis and optimization control layer, and a user interaction interface layer; The on-site data collection layer deploys multiple sensors such as high-definition cameras, temperature sensors, pressure sensors, and gas analyzers to collect video images, temperature, pressure, and key parameter data of gas composition during pellet roasting in real time; The data transmission and storage layer uses industrial Ethernet to safely and efficiently transmit the data collected on-site to the cloud server. The cloud server adopts a distributed storage architecture to ensure the reliability and scalability of the data. The cloud service platform layer builds an intelligent management and control platform based on cloud computing, including a real-time monitoring module, a data analysis module, a report generation module, a fault diagnosis module, and an equipment maintenance management module. Users can access the platform through the Internet to view real-time videos and data reports of the production site, receive and process alarm information, and perform remote operations and fault diagnosis; The intelligent analysis and optimization control layer uses big data analysis and machine learning algorithms to conduct in-depth mining of the collected data, identify abnormal patterns and potential risks in the production process, automatically adjust process parameters, optimize the roasting process, and achieve precise control. At the same time, it predicts future production trends based on historical data, providing a scientific basis for production planning and decision-making; The user interaction interface layer is designed with an intuitive and easy-to-use user interface, supports multi-terminal access, and provides rich visual charts and operation interfaces, so that users can grasp the production status anytime and anywhere and perform remote management and control.

2. According to claim 1, a blast furnace ironmaking pellet roasting intelligent management and control system is characterized in that: The field data acquisition layer selects a suitable installation position, the camera can cover the key area of ​​pellet roasting, adjusts the focal length, angle and resolution of the camera to obtain a clear video image, starts the camera, and collects images at a fixed frame rate. The temperature sensor is installed at the location of the pellet roasting equipment, and the temperature sensor type is selected. The temperature measurement principle of the thermocouple is: T=a×(V measured -V reference )+T reference， Where a is the sensitivity coefficient of the thermocouple, V measured is the measured voltage, V reference is the reference voltage, T reference The temperature measurement formula of the thermal resistor is: R=R0×(1+α×T), where R is the measured resistance, R0 is the reference resistance, α is the resistance temperature coefficient, and T is the temperature. The sensor converts the temperature into an electrical signal and transmits it to the data acquisition system.

3. According to claim 2, a blast furnace ironmaking pellet roasting intelligent management and control system is characterized in that: The field data acquisition layer installs a pressure sensor at the pressure monitoring point of the pellet roasting equipment, determines the range and accuracy of the pressure sensor to meet the measurement requirements, and the pressure measurement formula is: P=F / A, where P is pressure, F is force, and A is the force area. The sensor outputs an electrical signal proportional to the pressure, which is received by the data acquisition system. The gas analyzer is installed at the gas sampling point, which can accurately extract representative gas samples. The gas analyzer determines the concentration of the gas components through chemical analysis and physical detection methods, and the analysis results are transmitted to the data acquisition system in the form of digital signals.

4. According to claim 1, a blast furnace ironmaking pellet roasting intelligent management and control system is characterized in that: The data transmission and storage layer evaluates the on-site environment and data transmission requirements and determines the use of industrial Ethernet and wireless communication technology. For industrial Ethernet, the bandwidth calculation formula is: Bandwidth (B) = Sampling frequency (f s ) × number of quantization bits (n) × number of channels (m), install Ethernet switches, routers and wireless access point devices, establish a connection with the cloud server, ensure secure authentication and encrypted transmission, package and send the collected data according to the set protocol and format, data transmission rate formula: transmission rate (R) = data volume (D) / transmission time (t), the cloud server receives the data from the field, unpacks and verifies it, performs preliminary processing and classification of the data, adopts a distributed storage architecture, and distributes and stores the data on multiple storage nodes. The storage capacity calculation formula is: total storage capacity (C) = single node storage capacity (c) × number of nodes (N), and establishes a data copy and backup mechanism.

5. According to claim 1, the intelligent control system for blast furnace ironmaking pellet roasting is characterized in that: The cloud service platform layer selects a suitable cloud computing service provider, determines the configuration and storage capacity of the server according to the expected user access volume and data processing volume, and the storage capacity calculation formula is: storage capacity = average data volume × retention time × redundancy coefficient, where the redundancy coefficient is usually greater than 1 to cope with emergencies, configures a virtual network, establishes a stable connection with the on-site data acquisition equipment, sets the data acquisition frequency, and the acquisition frequency formula is: acquisition frequency = 1 / acquisition interval time. The collected real-time data and video images are encoded and compressed to reduce the transmission bandwidth requirement. The compression ratio formula is: compression ratio = original data size / compressed data size. The data and video are displayed in real time on the platform interface, and dynamic charts and real-time image refresh steps are used to build a data analysis module, collect and organize historical data, establish a data warehouse, and apply data analysis algorithms. The linear regression equation is: y=β0+β1x1+β2x2+…+∈, where β is the regression coefficient and ∈ is the error term. Generate analysis reports and visualization results. According to user needs and business rules, define the format and content of the report, extract relevant data from the database, calculate and summarize, and calculate the average value: average value = , where x i is the data point, n is the number of data, and a report is generated according to the preset template.

6. The intelligent control system for blast furnace ironmaking pellet roasting according to claim 5, characterized in that: The cloud service platform layer defines common fault types and corresponding characteristic indicators, monitors data in real time, and triggers an alarm when the indicator exceeds the normal range. The threshold judgment formula is: data value>upper threshold and data value<lower threshold. The fault diagnosis algorithm is used for analysis to locate the source of the fault and establish an equipment information database, including equipment model, installation time, and maintenance records. The next maintenance time is calculated based on the equipment operation time and maintenance cycle. The next maintenance time = current time + maintenance cycle. A maintenance work order is generated and the maintenance progress is tracked. Network access rights are configured to allow users to log in to the platform through the Internet. Encryption technology is used. The encryption strength evaluation formula is: encryption strength = key length × algorithm complexity. User identity authentication and authorization mechanisms are set.

7. The intelligent control system for blast furnace ironmaking pellet roasting according to claim 1, characterized in that: The intelligent analysis and optimization control layer obtains data from various data sources in the production process, including data collected by sensors and production records, integrates and formats the data to make it have a unified format and structure, cleans up missing values, and fills them with mean and median. The mean filling formula is: Filling value = , where x i is the non-missing value, n is the number of non-missing values, remove the noise data, and use the data smoothing method, moving average method: smoothed value = , where k is the window size, extract representative features from the original data, use feature selection algorithm, information gain: , select the features that have an important impact on the model, select the appropriate machine learning algorithm, support vector machine (SVM), for SVM, its decision function is: , where α i is the Lagrange multiplier, y i is the category label, and K is the kernel function.

8. The intelligent control system for blast furnace ironmaking pellet roasting according to claim 7, characterized in that: The intelligent analysis and optimization control layer inputs real-time data into the trained model and calculates the anomaly score. The anomaly score formula , where x is the data point, μ is the mean, and σ is the standard deviation. The score is used to determine whether it is an abnormal mode. The direction and amplitude of the adjustment are determined based on the output of the model and the preset adjustment rules. The formula for adjusting the temperature is: NewTemperature=CurrentTemperature+∆T, where ∆T is the adjustment amount. The adjusted production indicators are continuously monitored, and the optimization effect indicators and quality improvement rate are calculated: , based on historical data, establish the time series forecasting model ARIMA model, the expression of ARIMA model: , where B is the lag operator, which helps decision makers formulate production plans and decision strategies. The production planning formula is ProductionQuantity=DemandForecast×SafetyFactor, where DemandForecast is the demand forecast and SafetyFactor is the safety factor.

9. The intelligent control system for blast furnace ironmaking pellet roasting according to claim 1, characterized in that: The user interaction interface layer communicates with users and relevant stakeholders to understand their needs for interface functions and operations, collects type and resolution information of multiple terminals, divides the interface area, determines the location and size of different functional areas for information display and operation control, and selects appropriate visualization chart types, including but not limited to bar charts, line charts and pie charts.

10. The intelligent control system for blast furnace ironmaking pellet roasting according to claim 9, characterized in that: The user interaction interface layer adjusts the layout and size of interface elements according to the screen sizes and resolutions of different terminals, invites users to conduct tests, collects their feedback, and improves and optimizes the interface based on the feedback.

Images