A method and system for optimizing the roasting control of a belt roaster

Abstract

The application provides a belt roaster optimization roasting control method and system, relates to the technical field of sintering and pelletizing, and comprises the following steps: obtaining a regenerative air improvement entering mode and a mixed burning blast furnace gas mode of a belt roaster; selecting a roasting temperature index set of the belt roaster; counting production data information of the belt roaster; constructing a belt roaster production database; obtaining a pellet compressive strength prediction model; verifying the pellet compressive strength prediction model to obtain a model verification error value; iteratively optimizing the pellet compressive strength prediction model; and performing roasting control on the belt roaster. The technical problem of the prior art that the fuel of the belt roaster combustion system is single (only coke oven gas is burned), the combustion chamber temperature and the roasting temperature of the roaster material layer are uneven, and the roasting temperature is set unreasonably, thereby causing nitrogen in the roasting flue gas to form thermal NOx under high-temperature oxidation conditions and causing high flue gas NOx concentration is solved.

Description

Technical Field

[0001] This disclosure relates to the fields of sintering and pelletizing technology, specifically to an optimized roasting control method and system for a belt roaster. Background Technology

[0002] Pellet production refers to the process of rolling fine-grained iron concentrate into pellets, screening out qualified green pellets, and then roasting and solidifying them at high temperatures to obtain an iron-containing furnace charge that meets the requirements for blast furnace smelting. With advancements in materials prepared by belt roaster trolleys, coupled with advantages such as large capacity, low energy consumption, and environmental friendliness, belt roaster pellet production technology has developed rapidly since 2019. Qualified green pellets (8-16mm) undergo five stages sequentially on the belt roaster: drying, preheating, roasting, homogenization, and cooling. The belt roaster has 26 symmetrically distributed combustion chambers on both sides of the preheating and roasting sections. The combustion of coke oven gas in these chambers provides the necessary heat for the roaster; this is the main source of NOx generation in the belt roaster.

[0003] The main reasons for the high NOx levels in belt roasters are:

[0004] (1) Single fuel. Currently, the fuel used in domestic belt roasters is coke oven gas (which is a high-calorific-value gas). The theoretical combustion temperature reaches 2400K. The combustion chamber temperature of the high-temperature roasting section of the belt roaster also reaches about 2400K. Nitrogen in the roasting flue gas undergoes high-temperature oxidation to form thermal NOx, resulting in a high NOx concentration in the flue gas (about 400mg / m3).

[0005] (2) Uneven combustion chamber temperature and roasting temperature of the calciner bed. The reheat air in the combustion chamber enters from the top of the combustion chamber, affecting the flame shape and causing the flame to be too close to the bottom of the combustion chamber, resulting in local high temperature at the bottom of the combustion chamber and increasing NOx generation. In addition, after the hot air flow from the combustion chamber enters the belt calciner hood, under the condition of exhaust roasting, most of the air flow is concentrated on the trolley bed near the combustion chamber outlet, resulting in uneven transverse roasting of the trolley bed of the belt calciner, which affects the compressive strength of the pellets. In order to improve the compressive strength of the pellets, the roasting temperature needs to be increased, which further increases the amount of NOx generated in the combustion chamber.

[0006] (3) The roasting temperature setting is unreasonable. At present, the roasting parameters of belt roasters in China are adjusted based on experience. In order to improve the compressive strength of pellets, it is necessary to increase the roasting temperature of the belt roaster. However, this will lead to an increase in NOx in the roasting flue gas and an increase in energy consumption. This adjustment method is seriously outdated and has only one means. The reason is that the factors affecting the compressive strength of pellets are not only roasting temperature, but also temperature gradient, physical and chemical properties of raw materials, production capacity and green pellet quality.

[0007] Currently, existing belt roaster combustion systems suffer from several technical problems, including the use of a single fuel (only coke oven gas), uneven combustion chamber temperature and roasting temperature of the roasting material layer, and unreasonable roasting temperature settings. These issues lead to high-temperature oxidation of nitrogen in the roasting flue gas, forming thermal NOx and resulting in high NOx concentrations in the flue gas. Summary of the Invention

[0008] This disclosure provides an optimized roasting control method and system for a belt roaster, which addresses the technical problems in existing belt roaster combustion systems, such as the use of a single fuel (only coke oven gas), uneven combustion chamber temperature and roasting temperature of the roasting material layer, and unreasonable roasting temperature settings, which lead to the formation of thermal NOx in the roasting flue gas under high-temperature oxidation conditions, resulting in high NOx concentration in the flue gas.

[0009] In view of the above problems, this application provides an optimized roasting control method and system for a belt roaster.

[0010] According to a first aspect of this disclosure, an optimized roasting control method for a belt roaster is provided. The method includes: obtaining an improved regenerative air inlet method and a blast furnace gas blending method for the belt roaster; selecting a set of roasting temperature indices for the belt roaster; statistically analyzing production data information of the belt roaster based on the set of roasting temperature indices; constructing a production database for the belt roaster based on the production data information; performing linear regression analysis on the set of roasting temperature indices and the production database for the belt roaster to obtain a pellet compressive strength prediction model; validating the pellet compressive strength prediction model to obtain a model validation error value; iteratively optimizing the pellet compressive strength prediction model based on the model validation error value; and controlling the roasting of the belt roaster based on the improved regenerative air inlet method, the blast furnace gas blending method, and the pellet compressive strength prediction model.

[0011] According to a second aspect of this disclosure, an optimized roasting control system for a belt roaster is provided. The system includes: an information acquisition module for obtaining the improved regenerative air entry method and blast furnace gas blending method of the belt roaster; a temperature index set acquisition module for selecting a roasting temperature index set for the belt roaster; a production information statistics module for statistically analyzing production data information of the belt roaster based on the roasting temperature index set; and a production database construction module for constructing a production database for the belt roaster based on the production data information; and a pellet compressive strength prediction model. The system comprises the following modules: a pellet compressive strength prediction model acquisition module, which performs linear regression analysis on the roasting temperature index set and the belt roaster production database to obtain a pellet compressive strength prediction model; a model verification module, which verifies the pellet compressive strength prediction model and obtains the model verification error value; a model optimization module, which iteratively optimizes the pellet compressive strength prediction model based on the model verification error value; and a roasting control module, which controls the roasting of the belt roaster based on the improved regenerative air entry method, the blast furnace gas blending method, and the pellet compressive strength prediction model.

[0012] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0013] At least one processor; and

[0014] A memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0016] According to the optimized roasting control method for a belt roaster adopted in this disclosure, the following steps are taken: an improved regenerative air intake method and a blast furnace gas co-firing method for the belt roaster are obtained; a set of roasting temperature indices for the belt roaster is selected; based on the set of roasting temperature indices, production data information of the belt roaster is statistically analyzed; a production database for the belt roaster is constructed based on the production data information; linear regression analysis is performed on the set of roasting temperature indices and the production database for the belt roaster to obtain a pellet compressive strength prediction model; the pellet compressive strength prediction model is verified to obtain a model verification error value; based on the model verification error value, the pellet compressive strength prediction model is iteratively optimized; and roasting control of the belt roaster is performed based on the improved regenerative air intake method, the blast furnace gas co-firing method, and the pellet compressive strength prediction model. This disclosure achieves the technical effect of controlling NOx production from the source by co-firing blast furnace gas, changing the way regenerative air enters the combustion chamber of the belt roaster, and establishing an optimization model for the roasting parameters of the belt roaster, thereby further improving the environmental friendliness of the belt roaster.

[0017] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0019] Figure 1 This application provides a schematic flowchart of an optimized roasting control method for a belt roaster;

[0020] Figure 2 This application provides a schematic diagram of the original combustion chamber regenerative air entry method in an optimized roasting control method for a belt roaster;

[0021] Figure 3 This application provides a schematic diagram of the modified combustion chamber regenerative air entry method in the optimized roasting control method of a belt roaster;

[0022] Figure 4 This application provides a schematic diagram of the cross-sectional structure of the burner co-firing blast furnace gas in the optimized roasting control method of the belt roaster;

[0023] Figure 5This application provides a schematic diagram of the overall structure of the burner co-firing blast furnace gas burner in the optimized roasting control method of the belt roaster;

[0024] Figure 6 This application provides a schematic diagram of an optimized roasting control system for a belt roaster;

[0025] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure.

[0026] Figure labeling: Information acquisition module 11, Temperature index set acquisition module 12, Production information statistics module 13, Production database construction module 14, Pellet compressive strength prediction model acquisition module 15, Model verification module 16, Model optimization module 17, Roasting control module 18, Combustion chamber regenerator duct 1, Combustion chamber 2, Burner 3, Blast furnace gas channel 4, Swirl air combustion-supporting air channel 5, Coke oven gas channel 6, Central air channel 7, Electronic equipment 800, Processor 801, Memory 802, Bus architecture 803. Detailed Implementation

[0027] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0028] To address the technical problems in existing belt roaster combustion systems, such as the use of a single fuel (only coke oven gas), uneven combustion chamber temperature and roasting temperature of the roasting bed, and unreasonable roasting temperature settings, which lead to the formation of thermal NOx from nitrogen in the roasting flue gas under high-temperature oxidation conditions and resulting in high NOx concentrations, the inventors of this disclosure, through creative work, have developed an optimized roasting control method for belt roasters: This method involves obtaining an improved regenerative air inlet method and a co-firing method using blast furnace gas; selecting a set of roasting temperature indices for the belt roaster; and based on this set of roasting temperature indices... The production data of the belt roaster is collected; a production database for the belt roaster is constructed based on the production data; linear regression analysis is performed on the roasting temperature index set and the production database of the belt roaster to obtain a predictive model for the compressive strength of pellets; the predictive model for the compressive strength of pellets is verified to obtain the model verification error value; based on the model verification error value, the predictive model for the compressive strength of pellets is iteratively optimized; and roasting control of the belt roaster is performed based on the improved regenerative air entry method, the blending method of blast furnace gas, and the predictive model for the compressive strength of pellets.

[0029] Example 1

[0030] Figure 1 An optimized roasting control method for a belt roaster is provided in the embodiments of this application, such as... Figure 1 As shown, the method includes:

[0031] Step S100: Obtain the improved regenerative air entry method and blast furnace gas co-firing method for the belt roaster;

[0032] In this embodiment, step S100, which involves obtaining an improved regenerative air intake method for the belt roaster, further includes:

[0033] Step S110: Change the regenerative air intake from the top to the symmetrical intake from the middle of the combustion chamber.

[0034] In this embodiment, step S110 further includes:

[0035] Step S111: The symmetrical entry of the combustion chamber in the middle is achieved by arranging the combustion chamber reheat air duct, combustion chamber, and burner according to a preset modification method.

[0036] In the method of obtaining blast furnace gas by the belt roaster, step S100 in this application embodiment further includes:

[0037] Step S120: Modify the burner to co-fire blast furnace gas.

[0038] In this embodiment, step S120 further includes:

[0039] Step S121: Central air duct, wherein the central air duct is located at the center of the modified burner;

[0040] Step S122: Arrange the coke oven gas channel, the swirl combustion air channel, and the blast furnace gas channel in sequence from the inside to the outside of the central air channel.

[0041] Specifically, this involves improving the reheat air intake method of the belt roaster, that is, changing the reheat air intake method of the belt roaster, such as... Figure 2 , Figure 3 As shown, top entry type (see) Figure 2 ) was changed to a symmetrical entry system in the center of the combustion chamber (see Figure 3 The symmetrical entry design in the center of the combustion chamber is achieved by arranging the combustion chamber reheat air duct 1, combustion chamber 2, and burner 3 according to a preset modification method, such as... Figure 3As shown, the regenerating air duct 1 of the combustion chamber branches off 3m from the top of the combustion chamber, with the two ducts angled downwards at 45°. When it reaches the top of combustion chamber 2, the regenerating air duct changes to a 90° downward angle. When it reaches the center line of combustion chamber 2, the regenerating air duct changes to a 0° angle entering combustion chamber 2. By changing the regenerating air entry method of the belt roaster, the influence of regenerating air on the flame shape is reduced, the flame is prevented from getting too close to the bottom of the combustion chamber, and the local high-temperature area of ​​the combustion chamber is reduced.

[0042] Furthermore, to obtain the method of co-firing blast furnace gas in the belt roaster, the combustion chamber burners are modified to co-fire blast furnace gas. The central air duct is located at the center of the modified burner 3. The coke oven gas duct 6, the swirl combustion air duct 5, and the blast furnace gas duct are arranged sequentially from the inside to the outside, according to the arrangement of 4 and the central air duct 7. Figure 4 , Figure 5 As shown, at the very center of burner 3 is the central air channel 7, with a channel diameter of 20mm. Its main purpose is to cool the burner and reduce the temperature at the center of the flame, controlling the temperature at the highest point of the flame. Next to it is the coke oven gas channel 6, with a channel gap of 40mm, which provides coke oven gas fuel to the burner. The combustion of the coke oven gas provides heat for the belt roaster to roast the pellets. Next to it is the swirl combustion air channel 5, with a channel gap of 25mm. Its main purpose is to provide primary combustion air and also to cool the burner. Because the burner head is equipped with a swirl component (a small steel plate at a certain angle to the radial velocity of the combustion air, changing the direction of the combustion air and giving it a certain axial velocity), it also accelerates the mixing of fuel gas, primary air, and regenerated air, improving combustion efficiency. Next to it is the blast furnace gas channel 4, with a channel gap of 20mm. Its main purpose is to control the temperature at the highest point of the combustion chamber by co-firing low-calorific-value gas, reducing the amount of N2 oxidation in the roasting air, and controlling the NOx production in the roasting flue gas of the belt roaster.

[0043] Step S200: Select the set of roasting temperature indicators for the belt roaster;

[0044] Specifically, the set of roasting temperature indicators includes the physicochemical properties of raw materials, green pellet moisture content, green pellet drop strength, green pellet compressive strength, belt roaster bed thickness, hood temperature, wind box temperature, wind box pressure, coke oven gas flow rate, pellet compressive strength, and high-pressure roller mill operating parameters. By selecting the set of roasting temperature indicators for the belt roaster, a solid foundation is laid for the subsequent statistical analysis of production data information of the belt roaster.

[0045] Step S300: Based on the set of roasting temperature indicators, statistically analyze the production data information of the belt roaster;

[0046] Specifically, based on the set of roasting temperature indicators, indicators related to the compressive strength of pellets are selected for table compilation and statistics. The data corresponding to each indicator in the set of roasting temperature indicators are statistically analyzed, which is the production data information of the belt roaster.

[0047] Step S400: Based on the production data information, construct a production database for the belt roaster;

[0048] Specifically, based on the production data of the belt roaster, a belt roaster production database is constructed. The belt roaster production database includes all production data information, providing data support for the subsequent construction of a pellet compressive strength prediction model.

[0049] Step S500: Perform linear regression analysis on the set of roasting temperature indices and the production database of the belt roaster to obtain a predictive model for the compressive strength of pellets;

[0050] In this embodiment, step S500 of obtaining the pellet compressive strength prediction model further includes:

[0051] Step S510: Use the compressive strength index of pellets in the roasting temperature index set as the dependent variable;

[0052] Step S520: Use the remaining temperature indices in the set of roasting temperature indices as independent variables;

[0053] Step S530: Based on the dependent variable and the independent variable, perform model fitting to obtain the predictive model of the compressive strength of the pellet.

[0054] Specifically, linear regression analysis was performed on the set of roasting temperature indicators and the production database of the belt roaster to obtain a predictive model for the compressive strength of pellets. The predictive model for the compressive strength of pellets is a functional model that analyzes and predicts the compressive strength of pellets and the remaining temperature indicators in the set of roasting temperature indicators. Specifically, the linear regression analysis on the set of roasting temperature indicators and the production database of the belt roaster, as well as the construction of the predictive model for the compressive strength of pellets, were all completed using the professional statistical analysis software SPSS.

[0055] Specifically, based on the calcination temperature index set and the belt calciner production database, sufficient sample data were selected and imported into the professional statistical analysis software SPSS. Specifically, SPSS (Statistical Product and...) ServiceSolutions, a statistical analysis software called "Statistical Products and Services Solutions," uses a graphical menu-driven interface. After importing sample data into SPSS, users select Analysis → Regression → Linearity to access the main analysis dialog box. The user selects the pellet compressive strength index as the dependent variable (y) and the remaining temperature indices in the roasting temperature index set as independent variables (X1, X2, X3, etc.). In the statistical selection, users choose "Estimated Value," "Model Fit," and "Partial Correlation and Partial Correlation." In the "Save" dialog box, users select "Unstandardized" and then choose the "Step" method to obtain various models. The statistically significant pellet compressive strength prediction model is selected. After conducting experiments, the following prediction example is obtained: Pellet compressive strength = a * bed thickness + b * highest bellows temperature + c * highest hood temperature + d * drying section air temperature + e * extraction section air temperature, where a, b, c, d, and e refer to the independent variable coefficients in the model. Obtaining the pellet compressive strength prediction model lays the foundation for subsequently obtaining suitable roasting temperature values.

[0056] Step S600: Validate the pellet compressive strength prediction model and obtain the model validation error value;

[0057] Specifically, the model for predicting the compressive strength of iron ore pellets is validated to obtain the model validation error value. Simply put, the difference between the actual compressive strength of iron ore pellets and the predicted value is compared. Based on the difference between the actual compressive strength of iron ore pellets and the predicted value, the error value is obtained. By obtaining the model validation error value, it can be determined whether the model can be used.

[0058] Step S700: Based on the model verification error value, iteratively optimize the pellet compressive strength prediction model;

[0059] Specifically, based on the model validation error value, the prediction model for the compressive strength of pellets is iteratively optimized. Specifically, after verification, the data error is within ±0.3%, the error rate is within 0 to 2%, and the fitting is good. It can be used to predict the compressive strength of pellets. It is worth noting that the data error and error rate here are obtained through experimental verification. If the data error and error rate are large and exceed expectations, the model needs to be iteratively optimized until the error value meets expectations.

[0060] Step S800: The belt roaster is roasted based on the improved regenerative air entry method, the blending method of blast furnace gas, and the pellet compressive strength prediction model.

[0061] Specifically, based on the improved entry method of reheated air, the method of co-firing blast furnace gas, and the prediction model of pellet compressive strength, the appropriate roasting temperature can be derived by inputting the pellet compressive strength, material layer thickness, maximum wind box temperature, maximum hood temperature, blast temperature of the drying section, and blast temperature of the extraction section, thereby controlling the roasting process.

[0062] Furthermore, in the embodiment of this application, step S900, which involves obtaining a predictive model for the compressive strength of pellets, further includes:

[0063] Step S910: When adding variable factor indicators, store the variable factor indicators in the belt roaster production database to obtain the belt roaster updated production database;

[0064] Step S920: Based on the production database updated by the belt roaster, the prediction model for the compressive strength of the pellets is fitted and updated.

[0065] Specifically, to improve the model's adaptability, if variable factors increase, the increased variable factor indicators need to be added to the belt roaster production database to obtain an updated belt roaster production database. Based on the updated belt roaster production database, the pellet compressive strength prediction model is remodeled and analyzed. For example, if the type of raw material changes, the characteristic indicators of this raw material need to be added to the production database. Linear regression analysis is then performed on the belt roaster production database to fit and update the pellet compressive strength prediction model, so that the appropriate roasting temperature can be deduced from the pellet compressive strength prediction model.

[0066] Based on the above analysis, this disclosure provides an optimized roasting control method for a belt roaster, comprising: obtaining an improved regenerative air intake method and a blast furnace gas co-firing method for the belt roaster; selecting a set of roasting temperature indices for the belt roaster; statistically analyzing the production data information of the belt roaster based on the set of roasting temperature indices; constructing a production database for the belt roaster based on the production data information; performing linear regression analysis on the set of roasting temperature indices and the production database for the belt roaster to obtain a pellet compressive strength prediction model; validating the pellet compressive strength prediction model to obtain a model validation error value; iteratively optimizing the pellet compressive strength prediction model based on the model validation error value; and controlling the roasting of the belt roaster based on the improved regenerative air intake method, the blast furnace gas co-firing method, and the pellet compressive strength prediction model. This application embodiment achieves the technical effect of controlling NOx generation in the belt roaster from the source by co-firing blast furnace gas, changing the way regenerative air enters the combustion chamber of the belt roaster, and establishing an optimization model for the roasting parameters of the belt roaster. It also controls the roasting temperature based on actual production data, thereby further improving the environmental friendliness of the belt roaster.

[0067] Example 2

[0068] Based on the same inventive concept as the optimized roasting control method for a belt roaster in the foregoing embodiments, such as Figure 6 As shown, this application also provides an optimized roasting control system for a belt roaster, the system comprising:

[0069] Information acquisition module 11, the information acquisition module 11 is used to obtain the improved regenerative air entry method and the blast furnace gas co-firing method of the belt roaster;

[0070] Temperature index set acquisition module 12, the temperature index set acquisition module 12 is used to select the roasting temperature index set of the belt roaster;

[0071] Production information statistics module 13 is used to collect production data information of the belt roaster based on the roasting temperature index set.

[0072] Production database construction module 14, which is used to construct a production database for the belt roaster based on the production data information;

[0073] The pellet compressive strength prediction model acquisition module 15 is used to perform linear regression analysis on the roasting temperature index set and the belt roaster production database to obtain the pellet compressive strength prediction model.

[0074] Model verification module 16 is used to verify the prediction model of the compressive strength of the pellet ore and obtain the model verification error value.

[0075] Model optimization module 17 is used to iteratively optimize the pellet compressive strength prediction model based on the model verification error value.

[0076] The roasting control module 18 is used to control the roasting of the belt roaster based on the improved regenerative air entry method, the blending of blast furnace gas and the pellet compressive strength prediction model.

[0077] Furthermore, the system also includes:

[0078] The regenerative air intake method improvement module is used to change the regenerative air intake method from top entry to symmetrical entry in the middle of the combustion chamber.

[0079] The symmetrical entry type in the middle of the combustion chamber is achieved by arranging the combustion chamber reheat air duct, combustion chamber, and burner according to a preset modification method.

[0080] Furthermore, the system also includes:

[0081] A module for obtaining blast furnace gas by co-firing is used to obtain blast furnace gas by modifying the burners.

[0082] Furthermore, the system also includes:

[0083] A central air duct setting module is used to set the central air duct at the center of the modified burner.

[0084] Other channels are arranged in sequence. The other channels are arranged in sequence to arrange the coke oven gas channel, the swirl combustion air channel, and the blast furnace gas channel in order from the inside to the outside of the central air channel.

[0085] Furthermore, the system also includes:

[0086] A dependent variable construction module, wherein the dependent variable construction module is used to take the compressive strength index of pellets in the roasting temperature index set as the dependent variable;

[0087] Independent variable construction module, the independent variable construction module is used to take the remaining temperature indexes in the roasting temperature index set as independent variables;

[0088] The model fitting module is used to perform model fitting based on the dependent variable and the independent variable to obtain the prediction model of the compressive strength of the pellet.

[0089] Furthermore, the system also includes:

[0090] The production database update module is used to store the variable factor index into the belt roaster production database when a variable factor index is added, thereby obtaining an updated production database for the belt roaster.

[0091] The model fitting and updating module is used to fit and update the pellet compressive strength prediction model based on the production database updated by the belt roaster.

[0092] The specific example of the optimized roasting control method for a belt calender in Embodiment 1 described above is also applicable to the optimized roasting control system for a belt calender in this embodiment. Through the foregoing detailed description of the optimized roasting control method for a belt calender, those skilled in the art can clearly understand the optimized roasting control system for a belt calender in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here. As for the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant details can be found in the method section.

[0093] Example 3

[0094] Figure 7 This is a schematic diagram based on the third embodiment of the present disclosure, as shown below. Figure 7 As shown, the electronic device 800 in this disclosure may include a processor 801 and a memory 802.

[0095] Memory 802 is used to store programs. Memory 802 may include volatile memory, such as random-access memory (RAM), such as static random-access memory (SRAM), double data rate synchronous dynamic random-access memory (DDR SDRAM), etc.; memory may also include non-volatile memory, such as flash memory. Memory 802 is used to store computer programs (such as application programs, functional modules, etc. that implement the above methods), computer instructions, etc. The computer programs, computer instructions, etc., can be partitioned and stored in one or more memories 802. Furthermore, the computer programs, computer instructions, data, etc., can be accessed by processor 801.

[0096] The aforementioned computer programs and instructions can be stored in one or more partitions of memory 802. Furthermore, the aforementioned computer programs and instructions can be invoked by processor 801.

[0097] The processor 801 is configured to execute the computer program stored in the memory 802 to implement the various steps in the methods described in the above embodiments.

[0098] For details, please refer to the relevant descriptions in the preceding method embodiments.

[0099] The processor 801 and the memory 802 can be independent structures or integrated structures. When the processor 801 and the memory 802 are independent structures, the memory 802 and the processor 801 can be coupled together via bus 803.

[0100] The electronic device in this embodiment can execute the technical solution in the above method. Its specific implementation process and technical principle are the same, and will not be repeated here.

[0101] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0102] According to embodiments of this disclosure, this disclosure also provides a computer program product comprising: a computer program stored in a readable storage medium, at least one processor of an electronic device being able to read the computer program from the readable storage medium, and the at least one processor executing the computer program causing the electronic device to perform the scheme provided in any of the above embodiments.

[0103] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders.

[0104] This document does not impose any restrictions as long as the desired results of the disclosed technical solution can be achieved.

[0105] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An optimized roasting control method for a belt roaster, characterized in that, The method includes: Improved intake method of regenerated air and method of co-firing blast furnace gas in belt roaster; Select the set of roasting temperature indicators for the belt roaster; Based on the set of roasting temperature indicators, the production data information of the belt roaster is statistically analyzed. Based on the aforementioned production data information, a production database for the belt roaster is constructed. Linear regression analysis was performed on the set of roasting temperature indices and the production database of the belt roaster to obtain a predictive model for the compressive strength of pellets. The model for predicting the compressive strength of the pellets was validated, and the model validation error value was obtained. Based on the model verification error value, the prediction model for the compressive strength of the pellet ore is iteratively optimized. The roasting control of the belt roaster is based on the improved regenerative air entry method, the blending method of blast furnace gas, and the pellet compressive strength prediction model. The improved regenerative air intake method of the belt roaster is specifically changed from top intake to symmetrical intake in the middle of the combustion chamber. The specific method of co-firing blast furnace gas is as follows: by modifying the burners, co-firing blast furnace gas; The modified burner includes: a central air duct, which is located at the center of the modified burner; and a coke oven gas duct, a swirl combustion air duct, and a blast furnace gas duct arranged sequentially from the inside to the outside of the central air duct.

2. The method as described in claim 1, characterized in that, The symmetrical entry design in the center of the combustion chamber is achieved by arranging the combustion chamber reheat air duct, combustion chamber, and burner according to a preset modification method.

3. The method as described in claim 1, characterized in that, The model for predicting the compressive strength of pellets includes: The compressive strength index of pellets in the roasting temperature index set is used as the dependent variable; Use the remaining temperature indices in the set of roasting temperature indices as independent variables; Based on the dependent variable and the independent variable, a model is fitted to obtain the prediction model for the compressive strength of the pellet.

4. The method as described in claim 1, characterized in that, The method includes: When a variable factor index is added, the variable factor index is stored in the production database of the belt roaster to obtain the updated production database of the belt roaster. The production database of the belt roaster is updated to fit and update the prediction model for the compressive strength of the pellets.

5. An optimized roasting control system for a belt roaster, characterized in that, The system is used for optimizing the roasting control method of the belt roaster according to any one of claims 1 to 4, the system comprising: Information acquisition module, which is used to obtain the improved regenerative air entry method and the blending method of blast furnace gas in the belt roaster; A temperature index set acquisition module is used to select the roasting temperature index set of the belt roaster. The production information statistics module is used to collect production data information of the belt roaster based on the roasting temperature index set. A production database construction module is used to construct a production database for a belt roaster based on the production data information. A pellet compressive strength prediction model acquisition module is used to perform linear regression analysis on the roasting temperature index set and the belt roaster production database to obtain a pellet compressive strength prediction model. The model verification module is used to verify the prediction model of the compressive strength of the pellet ore and obtain the model verification error value. A model optimization module is used to iteratively optimize the pellet compressive strength prediction model based on the model verification error value. The roasting control module is used to control the roasting of the belt roaster based on the improved regenerative air entry method, the blending method of blast furnace gas, and the pellet compressive strength prediction model.

6. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

Images