An intelligent control method and system for the thermal parameters of a grate-kiln

Abstract

The present invention belongs to the field of intelligent control technology and discloses a chain grate-rotary kiln thermal parameter intelligent control method and system. Based on the coupling relationship between thermal parameters of pellet production equipment, data mining and correlation analysis methods are used to analyze the correlation between the chain grate-rotary kiln hot air circulation system, and a related mathematical model is constructed to realize the visualization of the chain grate-rotary kiln thermal parameter adjustment, and adjust the various parameters in the chain grate-rotary kiln thermal system to adapt to changes in raw materials. Based on the characteristics of the chain grate-rotary kiln-ring cooler trinity, the present invention adopts a technology that combines correlation analysis with mathematical modeling to ensure the rationality of the results and reduce the difficulty of model solution, increase the transparency of the production process, reduce the control difficulty caused by information lag, and can optimize the thermal parameters of the three main machines online, effectively reducing power consumption and energy consumption, and improving production efficiency.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent control technology, and in particular relates to an intelligent control method and system for thermal parameters of a chain grate-rotary kiln. Background Art

[0002] In recent years, with the rapid growth of my country's economy, the steel industry, a pillar industry, has experienced rapid development. This has led to a significant increase in the raw materials required for ironmaking. Modern enterprises are also increasingly demanding higher quality steel. The quality and efficiency of steel products have become crucial for the survival of steel companies. To transform lean ore into rich ore to meet the requirements of blast furnace production, pelletizing, a high-quality method for converting lean ore into rich ore, has been widely adopted worldwide and has become an increasingly important method for producing blast furnace raw materials. Pelletizing processes primarily include shaft furnaces, belt roasters, and grate-rotary kilns. Grate-rotary kilns are particularly popular due to their strong raw material adaptability, high production capacity, stable product quality, and diverse fuel options.

[0003] The chain grate-rotary kiln process can be regarded as a continuously flowing series production structure. The temperature spatial distribution of the process equipment during the production process is complex and mutually influential. If the green balls are not dried well, the preheated balls will have low strength, the powder rate will increase, and they will easily form rings in the rotary kiln, which is not conducive to production. Moreover, the pellet roasting process of this process is a very complex physical and chemical process. It has the characteristics of dynamics, large hysteresis and complex mechanisms. In addition, the process parameters of this process are numerous, and the three main machines are a series whole. As a result, the relationship between the process parameters of the three main machines in the production process is complex and mutually influential. There is almost a strong coupling or weak correlation between the various parameters. As a result, the chain grate-rotary kiln-annular cooler process cannot effectively infer the changing laws of the various process parameters during adjustment and control, making it impossible to achieve the expected value during adjustment. Therefore, the control and adjustment of its thermal system is one of the most important links in the entire pellet production process.

[0004] Currently, most manufacturers still rely on manual operation, requiring workers to rely on experience and experience, which leads to great uncertainty. This situation makes the output and quality of finished pellets completely dependent on the state of the pelletizing process. Therefore, a chain grate-rotary kiln thermal parameter optimization control method is proposed to effectively solve the manual control problem.

[0005] Through the above analysis, the problems and defects of the existing technology are: the control and adjustment method of the existing chain grate-rotary kiln thermal system is manual operation, which requires workers to rely on experience to operate, with great uncertainty, making the output and quality of the finished balls unstable. Summary of the Invention

[0006] In view of the problems existing in the prior art, the present invention provides a method and system for intelligent control of thermal parameters of a chain grate-rotary kiln.

[0007] The present invention is achieved in this way: a chain grate-rotary kiln thermal parameter intelligent control method includes:

[0008] Based on the coupling relationship between the thermal parameters of pellet production equipment, data mining and correlation analysis methods are used to analyze the correlation between the chain grate and rotary kiln hot air circulation system, and a related mathematical model is constructed to realize the visualization of the chain grate and rotary kiln thermal parameter adjustment. The various parameters in the chain grate and rotary kiln thermal system are adjusted to adapt to the changes in raw materials.

[0009] Furthermore, the specific steps of the chain grate-rotary kiln thermal parameter intelligent control method include:

[0010] Step 1: Treat the three main machines—the grate, rotary kiln, and annular cooler—as a series-connected process. Based on the corresponding relationships between the various parameters in the grate-rotary kiln hot air circulation system, the required thermal parameters are collected online. Temperature sampling points (using high-temperature probes) are set at the smoke hoods and wind boxes of each section of the grate, rotary kiln, and annular cooler. Simultaneously, burner fuel parameters and other important parameters are collected in real time in the central control room every two minutes.

[0011] Step 2: Preprocess the collected data, use relevant data analysis software to mine useful data and test their normality. Normality test is a common statistical analysis method to determine whether the population from which the sample is derived obeys a normal distribution. The normal distribution of the population is the basis and premise of regression analysis.

[0012] Step 3: After normality verification, use relevant data processing software to analyze the correlation between the two sets of thermal parameter variables to determine whether an effective mathematical model can be constructed between the variables. Correlation analysis is the analysis of two or more potentially related variable elements to determine whether the two variables are correlated and the degree of correlation between them. The correlation coefficient is a measure of correlation and is defined as the product of the covariance and standard deviation of the two variables. Its value range is [-1, 1]. The closer the absolute value of the correlation coefficient is to 1, the stronger the correlation between the two variables.

[0013] Step 4: Use the multivariate linear regression analysis method to construct a mathematical model between the thermal parameters of the chain grate and rotary kiln, clarify the influence rules of the changes between each parameter, and provide a specific intelligent control method for on-site production based on the mathematical model.

[0014] Furthermore, the thermal parameters required for online collection in step 1 include:

[0015] Through data mining methods, sampling points for temperature data are set at the smoke hoods and bellows of each section of the chain grate, rotary kiln and ring cooler to obtain the bellows temperature of the chain grate blower drying section, the smoke hood temperature of the exhaust drying section, the smoke hood temperature of the first preheating section, the smoke hood temperature of the second preheating section, the kiln head temperature and the kiln tail temperature of the rotary kiln, the smoke hood temperature of the first ring cooler, the smoke hood temperature of the second ring cooler, and the smoke hood temperature of the third ring cooler. At the same time, the real-time fuel consumption in the rotary kiln is collected.

[0016] Furthermore, the step three analyzes the correlation between the two groups of thermal parameter variables, specifically including:

[0017] Data analysis software is used to conduct correlation analysis on the collected relevant data, and the correlation between thermal parameters is used to determine whether the regression equation is statistically significant.

[0018] Furthermore, the step 4 uses a multiple regression analysis method to construct a mathematical model between process parameters, including:

[0019] Firstly, the rotary kiln temperature regression model was constructed with the kiln tail temperature and kiln head temperature as dependent variables, and the blast furnace gas nozzle quantity, coke oven gas nozzle quantity and combustion fan flow rate as independent variables.

[0020] Then, regression models of corresponding parameters in the hot air circulation systems of the three main engines were constructed respectively;

[0021] Finally, when the blast furnace gas nozzle quantity, coke oven gas nozzle quantity and combustion air flow rate in the rotary kiln need to be adjusted, the specific change values of the thermal parameters of each section of the grate-rotary kiln can be accurately inferred based on the regression model.

[0022] Furthermore, the fourth step provides a specific intelligent control method for on-site production based on the mathematical model, including:

[0023] The mathematical model is applied to pellet production control, and the changing rules of various thermal parameters during the adjustment of the chain grate-rotary kiln thermal system are obtained.

[0024] Another object of the present invention is to provide a chain grate-rotary kiln thermal parameter intelligent control system, the chain grate-rotary kiln thermal parameter intelligent control system comprising:

[0025] The data acquisition module is used to collect the required thermal parameters online based on the corresponding relationship between the various parameters in the chain grate-rotary kiln hot air circulation system;

[0026] Data preprocessing module, used to preprocess the collected data and test their normality;

[0027] The correlation analysis module is used to analyze the correlation between two groups of thermal parameter variables and determine whether an effective mathematical model can be constructed between the variables;

[0028] The model building module is used to build a mathematical model between process parameters using multiple regression analysis, and provide specific intelligent control methods for on-site production based on the mathematical model.

[0029] In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

[0030] First, in view of the technical problems existing in the above-mentioned prior art and the difficulty of solving these problems, this paper closely combines the technical solutions to be protected by the present invention and the results and data during the research and development process, and analyzes in detail and in depth how the technical solutions of the present invention solve the technical problems and some creative technical effects brought about by solving the problems. The specific description is as follows:

[0031] 1. Based on the trinity of the chain grate, rotary kiln, and annular cooler, namely, the presence of gas-phase and solid-phase heat exchange between each stage of the chain grate, rotary kiln, and annular cooler process, and the mutual influence of thermal parameters among the three, the proposed optimization control method is scientific and effective, combining correlation analysis with mathematical modeling. The mathematical model fully considers the influence of on-site rotary kiln fuel combustion and hot air exchange between the various main units, while ignoring factors with less influence on the pellet temperature field. This ensures the rationality of the results and reduces the difficulty of solving the model.

[0032] 2. The mathematical model used in the present invention is established based on the actual operating parameters on site. Its solution process fully considers the coupling relationship between the thermal parameters of each device, which not only makes the production process intuitive and transparent, but also makes the calculation results closer to actual production. The model has strong real-time and adaptability, which will be very helpful for the operator to grasp the working conditions.

[0033] 3. The chain grate-rotary kiln thermal parameter optimization control model established by the present invention is used to guide the adjustment and control of the production process of a large-scale pelletizing plant. Combined with the recent production results on site, it is shown that the accuracy of the model is basically above 95%, realizing the visualization of the adjustment of the pelletizing thermal parameters and the transparency of the thermal parameter change process.

[0034] 4. By using the present invention to guide the chain grate-rotary kiln production process online, the transparency of the production process is increased, the control difficulty caused by information lag is reduced, and the thermal operation of the three main machines can be optimized online, effectively reducing power consumption and energy consumption and improving production efficiency.

[0035] Second, considering the technical solution as a whole or from the perspective of the product, the technical effects and advantages of the technical solution to be protected by the present invention are described in detail as follows:

[0036] Based on the coupling relationship between thermal parameters of pellet production equipment, the present invention adopts data mining and correlation analysis methods to deeply study the correlation between the chain grate and rotary kiln hot air circulation system, and constructs a relevant mathematical model to realize the visualization of the chain grate and rotary kiln thermal parameter adjustment, forming a set of chain grate and rotary kiln thermal parameter intelligent control system, so as to timely and effectively adjust various parameters in the chain grate and rotary kiln thermal system to adapt to changes in raw materials and optimize the production process.

[0037] Third, as auxiliary evidence of the invention's creativity, it is also reflected in the following important aspects:

[0038] (1) The expected benefits and commercial value of the technical solution of the present invention after transformation are:

[0039] After a pelletizing plant was transformed according to the technical solution of the present invention, the pellet production was significantly improved. Under the premise of unchanged raw material consumption, the output of finished pellets increased from 1.7 million tons / year to 1.8 million tons / year, and the annual revenue is expected to increase by 13.704 million yuan.

[0040] (2) The technical solution of the present invention fills the technical gap in the industry at home and abroad:

[0041] The present invention is based on the production data of the chain grate-rotary kiln thermal system in the pelletizing process, uses data analysis software to analyze the chain grate-rotary kiln hot air circulation system, judges whether the regression equation has statistical significance based on the correlation between the thermal parameters, and then obtains the change law between the various thermal parameters when the chain grate-rotary kiln thermal system is adjusted according to the regression equation, thereby realizing the visualization of the thermal parameter adjustment and the transparency of the thermal parameter change process, maintaining the parameter stability of the chain grate-rotary kiln-annular cooler thermal system when adjusting, and ensuring the stability of pellet production. It provides a new chain grate-rotary kiln partial thermal parameter intelligent control method and system for steel enterprises in pelletizing production, filling the technical gap of the intelligent regulation of some chain grate-rotary kiln thermal parameters.

[0042] (3) Whether the technical solution of the present invention solves the technical problems that people have been eager to solve but have not been able to solve successfully:

[0043] The thermal system of the iron ore pelletizing chain grate-rotary kiln process has the characteristics of complex control objects, long and lagging adjustment process, and mutual coupling between various thermal parameters. As a result, the process cannot effectively infer the changing trends of various thermal parameters during adjustment and control, resulting in the adjustment failing to achieve the expected results. To address these technical difficulties, the present invention proposes a novel chain grate-rotary kiln partial thermal parameter intelligent control method and system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1This is a flow chart of a method for intelligently controlling thermal parameters of a grate-rotary kiln provided by an embodiment of the present invention;

[0045] Figure 2 This is a common structural diagram of the hot air circulation system of three main hosts provided by an embodiment of the present invention;

[0046] Figure 3 It is a structural diagram of the chain grate-rotary kiln thermal parameter intelligent control system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0048] In order to enable those skilled in the art to fully understand how to implement the present invention, this section provides an explanatory embodiment that expands on the technical solutions of the claims.

[0049] like Figure 1 As shown, the chain grate-rotary kiln thermal parameter intelligent control method provided by the embodiment of the present invention includes:

[0050] S101: The chain grate, rotary kiln, and ring cooler are considered as a series process. Based on the corresponding relationship between the parameters in the chain grate-rotary kiln hot air circulation system, the required thermal parameters are collected online.

[0051] S102, preprocessing the collected data to test their normality;

[0052] S103, after normality verification, analyze the correlation between the two groups of thermal parameter variables to determine whether an effective mathematical model can be constructed between the variables;

[0053] S104, using multiple regression analysis to construct a mathematical model between process parameters, and providing a specific intelligent control method for on-site production based on the mathematical model.

[0054] Suppose a pelletizing plant needs to adjust the thermal parameters of the three main engines to meet new production conditions. Under the guidance of a mathematical model, the thermal parameters can be adjusted. If the temperature at the tail of the rotary kiln is to be increased by 50°C, the specific adjustments required for the coke oven gas flow rate, blast furnace gas flow rate, and combustion air flow rate can be calculated based on the regression equation. The adjustment of the fuel amount will cause the thermal parameters of the entire chain grate-rotary kiln to change. Therefore, the adjusted fuel amount is input into the regression equation to calculate the changed temperature at the head of the rotary kiln. Then, the new temperatures at the head and tail of the rotary kiln can be used to deduce the changed flue gas temperature of the first stage of the ring cooler and the temperature of the second stage of the chain grate preheating hood, respectively, according to the regression equation. Under the guidance of the regression equation, the flue gas temperature of the first stage of the ring cooler and the temperature of the second stage of the chain grate preheating hood can be used to calculate the adjusted hood temperatures of the second stage of the ring cooler and the exhaust drying section of the chain grate, respectively. Similarly, all the air temperature values of each section of the three main engines after the fuel parameter adjustment can be calculated. This is a new method for intelligent control of the thermal parameters of the chain grate-rotary kiln.

[0055] The mathematical model of the three main engines needs to be combined with the site. For example, the types of fuel used in different pelletizing plants will be different, so when constructing the regression model, changes must be made based on the actual production on site.

[0056] The structure of the hot air circulation system of the three main engines is as follows Figure 2 As shown in the figure, the correlation analysis of the thermal parameters of the three main engines and the establishment of the mathematical model are all studied in accordance with the traditional chain grate-rotary kiln-ring cooler hot air circulation method.

[0057] When the accuracy of the mathematical model between the thermal parameters is high, they can be combined into a mathematical model between two new variables, and the accuracy of the new model can also meet production requirements.

[0058] The mathematical modeling principle for the relationship between grate and rotary kiln thermal parameters is as follows: First, regression models for the rotary kiln temperature are constructed, using the kiln tail and head temperatures as dependent variables, and the blast furnace gas nozzle volume, coke oven gas nozzle volume, and combustion air fan flow rate as independent variables. Next, regression models are constructed for the three main hot air circulation systems, such as the independent variable rotary kiln tail temperature and the dependent variable grate preheating stage 2 hood temperature, the independent variable rotary kiln head temperature and the dependent variable ring cooler stage 1 flue gas temperature, and the independent variable grate preheating stage 2 hood temperature and the dependent variable grate exhaust drying stage hood temperature. Finally, when the blast furnace gas nozzle volume, coke oven gas nozzle volume, and combustion air flow rate within the rotary kiln require adjustment, the regression model accurately predicts the specific changes in the thermal parameters of each grate-rotary kiln section.

[0059] In order to prove the creativity and technical value of the technical solution of the present invention, this section provides application examples of the claimed technical solution on specific products or related technologies.

[0060] The core of the main product and application of the present invention is the chain grate-rotary kiln thermal parameter intelligent control system, the structure of the system is as follows: Figure 3 As shown in the figure, it mainly includes three modules: system database module, data preprocessing module, thermal parameter control guidance model and instruction sending module. Among them, the system database module is mainly responsible for online and offline collection of production data and manual setting of process parameters. The data preprocessing module is responsible for eliminating abnormal data and data normality test. The main task of the manual parameter control guidance model module is to analyze the correlation between the thermal parameters of the three main machines, construct a mathematical model between the thermal parameters of the three main machines, and guide workers to adjust the thermal parameters.

[0061] If a pelletizing plant uses a chain grate-rotary kiln process, and all process parameters are recorded in a corresponding control system, the plant can be optimized by implementing an intelligent control system for the thermal parameters of the chain grate-rotary kiln. This system continuously collects and analyzes on-site production data, continuously improving the accuracy of the thermal parameter control guidance model to adapt to various raw material conditions in the pelletizing process. The display effect of this system on a computer is equivalent to a software interface. When a small section of the thermal parameters in the on-site chain grate-rotary kiln process needs to be adjusted, simply enter the adjusted thermal parameters into the system to obtain the corresponding fuel parameters, chain grate thermal parameters, rotary kiln thermal parameters, and ring cooler thermal parameters. Optimization is then repeated until the adjusted thermal parameters are optimal.

[0062] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware portion can be implemented using dedicated logic; the software portion can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. Those skilled in the art will appreciate that the above-mentioned devices and methods can be implemented using computer-executable instructions and / or contained in processor control code, for example, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The devices and modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, or can be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0063] The embodiments of the present invention have achieved some positive results during the development or use process, and indeed have great advantages over the existing technology. The following content describes them in conjunction with data, charts, etc. from the experimental process.

[0064] The specific implementation process of the present invention mainly includes: collecting host operation data, normality testing of relevant data, correlation analysis between variables, building a regression model, and testing the rationality of the regression model. The collection of production data is related to the level of on-site automation and is mainly achieved by accessing the server database, accessing the on-site operating unit PLC, accessing the database of the host computer monitoring software, etc., which will not be described here. Taking the pellet production process of a certain steel enterprise as an example, we now introduce a specific implementation method for normality testing, correlation analysis, regression model establishment and verification of the data in combination with some of the collected production data, as shown in the following example.

[0065] Example 1

[0066] A host computer accessing the server database and the on-site operation unit PLC was set up on site to collect data. The main equipment parameters and their variable names of the chain grate-rotary kiln process of a domestic pelletizing plant were collected, as shown in Table 1.

[0067] Table 1 Main sampling parameters of a chain grate-rotary kiln process

[0068] Process parameters variable name Process parameters variable name Air box temperature of grate drying section / ℃ QT_PT_0717 Rotary kiln tail temperature / ℃ QT_TE_0811 Chain grate exhaust drying section hood temperature / ℃ QT_PT_0714 Rotary kiln head temperature / ℃ QT_TE_0812 Chain grate preheating hood temperature / ℃ QT_PT_0710 <![CDATA[BF gas nozzle volume / m 3 ·h -1 > QT_FT_102 Chain grate preheating second stage smoke hood temperature / ℃ QT_PT_0703 <![CDATA[Coke oven gas nozzle volume / m 3 ·h -1 > QT_FT_101 Annular cooler first stage hood temperature / ℃ QT_TE_0862 <![CDATA[Rotary kiln combustion-supporting air flow rate / m 3 ·h -1 > QT_FT_0812 Annular cooler second stage hood temperature / ℃ QT_TE_0863 Annular cooler three-stage hood temperature / ℃ QT_TE_0864

[0069] Then, the data were tested for normality using statistical analysis software, and the results are shown in Table 2.

[0070] Table 2 Normality test of data

[0071]

[0072]

[0073] The results of the Kolmogorov-Smirnov calculation in Table 2 show that, given a large sample size and stable data, the blast furnace gas volume, coke oven gas volume, and combustion air flow rate within the rotary kiln all showed high significance, reaching 0.200. Furthermore, the temperatures of the three main units—the grate, rotary kiln, and annular cooler—were also highly significant. The temperature of the grate exhaust drying section and the flue gas temperature of the three annular coolers showed the lowest significance, at 0.150 and 0.120, respectively, but the significance was still greater than 0.05. Therefore, all collected process parameter data conformed to a normal distribution, exhibited good statistical significance, and could be used to construct a regression model.

[0074] According to the hot air circulation path in the chain grate-rotary kiln hot air circulation system, the analysis software was used to perform correlation analysis on the corresponding parameter data in the hot air circulation system. The results are shown in Table 3.

[0075] Table 3 Correlation analysis among variables

[0076]

[0077] Note: **, at the <0.01 level (two-tailed), the correlation is highly significant; *, at the <0.05 level (two-tailed), the correlation is significant.

[0078] As can be seen from the above table, the correlations between the parameter variables of the chain grate-rotary kiln-annular cooler hot air circulation system are highly significant, and the correlation coefficients are large, basically above 0.9. Therefore, there is a strong positive correlation between the above sample variables, and a linear regression model with smaller errors can be established.

[0079] The blast furnace gas volume, coke oven gas volume, and combustion fan flow rate were set as variables X1, X2, and X3. Other thermal parameters included the temperatures of the grate drying section, exhaust drying section, and preheating sections 1 and 2 as G1, G2, G3, and G4; the kiln tail and kiln head temperatures as K5 and K6, respectively; and the flue gas temperatures of the first, second, and third stages of the ring cooler as R7, R8, and R9. A multivariate linear regression model was constructed for the grate-rotary kiln thermal parameters, and the results are shown in Table 4.

[0080] Table 4 Multiple linear regression model

[0081] Model Regression equation <![CDATA[Coefficient of correlation R 2 > <![CDATA[Tail-end temperature K5 of rotary kiln]]> <![CDATA[K5=858.534+0.027X1+0.030X2+0.027X3]]> 0.975 <![CDATA[Kiln head temperature of rotary kiln K6]]> <![CDATA[K6=337.735+0.047X1+0.068X2+0.124X3]]> 0.988 <![CDATA[Temperature of the second preheating section hood of the grate cooler G4]]> <![CDATA[G4=-1846.105+2.239K5]]> 0.963 <![CDATA[Temperature of the hood in the induced draft drying section of the grate-kiln G2]]> <![CDATA[G2=23.562+0.315G4]]> 0.989 <![CDATA[Temperature of the first-stage hood of the ring cooler R7]]> <![CDATA[R7=-329.938+1.036K6]]> 0.953 <![CDATA[Temperature of the second-stage hood of the annular cooler R8]]> <![CDATA[R8=5.149E-5+0.707R7]]> 1.000 <![CDATA[Temperature of the third-stage hood of the annular cooler R9]]> <![CDATA[R9=10.769+0.255R8]]> 0.729 <![CDATA[Temperature of the first-stage preheating hood of the grate-kiln G3]]> <![CDATA[G3=98.343+0.775R8]]> 0.969 <![CDATA[Air box temperature G1 in the air blast drying section of the grate-kiln]]> <![CDATA[G1=18.285+0.715R9]]> 0.971

[0082] The above regression model was used to guide the regulation and control of the on-site process, and then the rationality of each regression equation was tested in combination with the recent production results on site. It was found that the error of the regression equation was basically below 10%.

[0083] Example 2

[0084] The above model guides on-site production and visualizes the adjustment of the thermal parameters of the three main engines. The ratio of the coke oven gas flow rate, blast furnace gas flow rate, and combustion air flow rate added to the rotary kiln on site is known to be 4:3:5. Under the guidance of the regression model, the thermal parameters are adjusted. To adjust the rotary kiln tail temperature from 1100°C to 1150°C, the coke oven gas flow rate, blast furnace gas flow rate, and combustion air flow rate need to be increased by 20.1%, 15.0%, and 25.1%, respectively. It can also be predicted that the rotary kiln head temperature will rise by approximately 162°C, while the temperature of the chain grate preheating stage 2 and the exhaust drying stage will increase by approximately 112°C and 35°C. Furthermore, the exhaust gas temperatures of the first, second, and third stages of the ring cooler will also increase by approximately 168°C, 119°C, and 30°C, respectively. The changes in the exhaust gas temperatures of the second and third stages of the ring cooler will cause the temperatures of the chain grate preheating stage 1 and the blast drying stage to increase by 92°C and 21°C, respectively.

[0085] Example 3

[0086] The above model guides on-site production and visualizes the adjustment of the thermal parameters of the three main engines. Given that the ratio of coke oven gas, blast furnace gas, and combustion air added to the rotary kiln is 4:3:5, the regression model guides the adjustment of thermal parameters. To adjust the second-stage preheating temperature of the grate from 900°C to 950°C, the kiln tail temperature needs to be increased by 22°C. Consequently, the coke oven gas flow, blast furnace gas flow, and combustion air flow must be increased by 8.8%, 6.6%, and 11.0%, respectively. Furthermore, it can be predicted that the kiln head temperature will rise by approximately 110°C, while the temperature of the grate exhaust drying section will rise by approximately 16°C. Furthermore, the exhaust gas temperatures of the first, second, and third stages of the annular cooler will rise by approximately 114°C, 81°C, and 18°C, respectively. The changes in the exhaust gas temperatures of the second and third stages of the annular cooler will cause the temperatures of the first and blast drying sections of the grate to rise by 63°C and 13°C, respectively.

[0087] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with this technical field within the technical scope disclosed by the present invention and within the spirit and principles of the present invention should be covered by the scope of protection of the present invention.

Claims

1. A chain grate-rotary kiln thermal parameter intelligent control method, characterized in that: include: Based on the coupling relationship between the thermal parameters of pellet production equipment, data mining and correlation analysis methods are used to analyze the correlation between the chain grate and rotary kiln hot air circulation system. A related mathematical model is constructed to realize the visualization of the chain grate and rotary kiln thermal parameter adjustment. The various parameters in the chain grate and rotary kiln thermal system are adjusted to adapt to the changes in raw materials. The specific steps of the chain grate-rotary kiln thermal parameter intelligent control method include: Step 1: Treat the three main machines, the chain grate, rotary kiln, and ring cooler, as a series process. Based on the corresponding relationship between the various parameters in the chain grate-rotary kiln hot air circulation system, the required thermal parameters are collected online. Step 2: preprocess the collected data to test their normality; Step 3: After normality verification, the correlation between the two groups of thermal parameter variables is analyzed to determine whether an effective mathematical model can be constructed between the variables; Step 4: Use multiple regression analysis to build a mathematical model between process parameters, and provide specific intelligent control methods for on-site production based on the mathematical model; The thermal parameters required for online collection in step 1 include: Through data mining methods, sampling points for temperature data are set at the smoke hoods and bellows of each section of the chain grate, rotary kiln and ring cooler to obtain the bellows temperature of the chain grate blower drying section, the smoke hood temperature of the exhaust drying section, the smoke hood temperature of the first preheating section, the smoke hood temperature of the second preheating section, the kiln head temperature and the kiln tail temperature of the rotary kiln, the smoke hood temperature of the first ring cooler, the smoke hood temperature of the second ring cooler, and the smoke hood temperature of the third ring cooler. At the same time, the real-time fuel consumption in the rotary kiln is collected.

2. The chain grate-rotary kiln thermal parameter intelligent control method according to claim 1, characterized in that: The third step is to analyze the correlation between the two groups of thermal parameter variables, specifically including: Data analysis software is used to conduct correlation analysis on the collected relevant data, and the correlation between thermal parameters is used to determine whether the regression equation is statistically significant.

3. The chain grate-rotary kiln thermal parameter intelligent control method according to claim 1, characterized in that: The step 4 uses the multiple regression analysis method to construct a mathematical model between the process parameters, including: Firstly, the rotary kiln temperature regression model was constructed with the kiln tail temperature and kiln head temperature as dependent variables, and the blast furnace gas nozzle quantity, coke oven gas nozzle quantity and combustion fan flow rate as independent variables. Then, the corresponding regression models of the hot air circulation systems of the three main engines were constructed respectively; Finally, when the blast furnace gas nozzle quantity, coke oven gas nozzle quantity and combustion-supporting air flow rate in the rotary kiln need to be adjusted, the specific change values of the thermal parameters of each section of the chain grate-rotary kiln can be accurately estimated based on the regression model.

4. The chain grate-rotary kiln thermal parameter intelligent control method according to claim 1, characterized in that: The fourth step provides a specific intelligent control method for on-site production based on the mathematical model, including: The mathematical model is applied to pellet production control, and the changing rules of various thermal parameters during the adjustment of the chain grate-rotary kiln thermal system are obtained.

5. A chain grate-rotary kiln thermal parameter intelligent control system for implementing the chain grate-rotary kiln thermal parameter intelligent control method according to any one of claims 1 to 4, characterized in that: The chain grate-rotary kiln thermal parameter intelligent control system includes: The data acquisition module is used to collect the required thermal parameters online based on the corresponding relationship between the various parameters in the chain grate-rotary kiln hot air circulation system; The preprocessing module is used to preprocess the collected data and test their normality; The correlation analysis module is used to analyze the correlation between two groups of thermal parameter variables and determine whether an effective mathematical model can be constructed between the variables; The model building module is used to build a mathematical model between process parameters using multiple regression analysis, and provide specific intelligent control methods for on-site production based on the mathematical model.

6. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the chain grate-rotary kiln thermal parameter intelligent control method according to any one of claims 1 to 5.

7. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the chain grate-rotary kiln thermal parameter intelligent control method according to any one of claims 1 to 5.

8. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the steps of the chain grate-rotary kiln thermal parameter intelligent control method according to any one of claims 1 to 5.

Images