Sinter strength prediction method and system based on visible light imaging of machine tail section
By using visible light imaging technology at the tail section of the sintering machine and establishing a return ore prediction model through neural network learning, the method based on visible light imaging at the tail section of the sintering machine solves the technical problems that are difficult to solve quickly in the existing technology, and realizes the rapid and accurate prediction of sinter intensity.
Patent Information
- Application Number
- CN202310839372.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-07-10
- Publication Date
- 2026-01-06
- Estimated Expiration
- 2043-07-10
AI Technical Summary
Existing technologies struggle to quickly predict the intensity of sinter, particularly in online prediction.
By using visible light imaging based on the tail section, the actual effective tail sintering cross section image of the current batch of trolleys is obtained. A return ore prediction model is established using neural network learning. By combining the difference between the return ore rate of sintered raw materials and the total return ore rate, the return ore rate of sintered clinker is predicted, thereby assessing the strength of sintered ore.
It enables rapid and accurate prediction of sinter strength, avoids further processing of undersize material, and improves prediction efficiency and accuracy.
Smart Images

Figure CN119294219B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of sintering technology, and in particular, to a method and system for predicting the strength of sintered ore based on visible light imaging of the tail section. Background Technology
[0002] With the rapid development of modern industry, steel production is becoming increasingly large-scale, and energy consumption is also increasing. Energy conservation and environmental protection indicators are becoming increasingly important factors to consider in the steel production process. In steel production, iron-containing raw materials need to be processed through a sintering system before entering the blast furnace for smelting. This involves mixing various powdered iron-containing raw materials with appropriate amounts of fuel (pulverized coal, coke powder) and flux, adding an appropriate amount of water, mixing and pelletizing them, and then placing them on a sintering trolley for roasting. This causes a series of physicochemical changes, forming easily smelted sintered ore. This process is called sintering.
[0003] The sintering process includes ignition sintering, crushing, cooling in an annular cooler, and screening. The oversize material after screening is the finished sintered ore, while the undersize material is returned to the sintering process. In existing technology, the sintering return rate is obtained by weighing the oversize and undersize materials. The undersize material is further processed into raw material undersize and clinker undersize, which are then weighed to obtain the clinker return rate. Finally, the sinter strength is assessed based on the clinker return rate. However, existing technology makes it difficult to quickly predict the sinter strength.
[0004] Therefore, it is necessary to propose a method and system for predicting the strength of sintered ore based on visible light imaging of the tail section to alleviate the above-mentioned shortcomings. Summary of the Invention
[0005] This invention provides a method and system for predicting the intensity of sintered ore based on visible light imaging of the tail section, which solves the existing technical problem of difficulty in predicting the intensity of sintered ore online.
[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:
[0007] A method for predicting the strength of sintered ore based on visible light imaging of the tail section includes the following steps: S10, acquiring visible light imaging of the actual effective tail section sintering cross-section of the current batch of trolleys, wherein the visible light imaging of the actual effective tail section sintering cross-section has a known correlation ratio with the true cross-sectional image of the current batch of trolleys; S20, acquiring the current sintered raw meal return rate of the current batch of trolleys based on the visible light imaging of the actual effective sintering cross-section; S30, acquiring the current actual total sintering return rate of the current batch of trolleys; S40, determining the current sintered clinker return rate based on the difference between the current actual total sintering return rate and the current sintered raw meal return rate; S50, predicting the current sintered ore strength based on the current sintered clinker return rate, wherein the higher the current sintered clinker return rate, the lower the current sintered ore strength.
[0008] Further, step S20 specifically includes: the visible light imaging of the actual effective tail sintering cross section has a visible light imaging black area and a visible light imaging bright area. The visible light imaging black area includes the visible light imaging base material section and the visible light sintering area. The visible light imaging bright area is located on the visible light sintering area. The visible light imaging base material section corresponds to the actual base material layer of the real cross-sectional image. The visible light sintering area corresponds to the actual sintering cross-sectional area of the real cross-sectional image. The visible light imaging bright area corresponds to the actual sintering critical area of the real cross-sectional image. The actual sintering critical area is located on the actual sintering cross-sectional area. Determine... The sintered material corresponding to the actual sintering critical region and the actual bottom material layer is the current sintering raw material region. The current raw material area ratio of the current sintering raw material region is calculated based on the area ratio of the current sintering raw material region to the actual sintering cross-sectional region. The current raw material area ratio and the current sintering operating parameters are input into the return ore prediction model to predict the current sintering raw material return rate of the current batch of trolleys. The historical sintering raw material area ratio and historical sintering operating parameters are used as the training input set, and the historical tail raw material return rate is used as the training output set to establish the return ore prediction model through neural network learning.
[0009] Furthermore, the ideal sintering visible light image of the current batch of trolleys is obtained. The ideal sintering visible light image includes the theoretical material layer, which corresponds to the actual bottom material layer. The ideal sintering visible light image and the actual effective tail sintering cross-section visible light image are fused together, and the visible light imaging bottom material range is determined according to the theoretical material layer.
[0010] Furthermore, it also includes the following steps: historical sintering operating parameters, including historical sintering air volume parameters, historical trolley speed parameters, and historical sintering material layer thickness parameters.
[0011] Furthermore, the method also includes the following steps: before step S50, if the current sintering raw material return rate is greater than the current actual total sintering return rate, the visible light image of the actual effective tail sintering section of the previous batch of trolleys is updated to the visible light image of the actual effective tail sintering section of the current batch of trolleys.
[0012] Further, step S10 specifically includes: acquiring the initial actual sintering cross-section visible light imaging image of each target sintering trolley corresponding to the current batch of trolleys; filtering out the distortion of the initial actual sintering cross-section visible light imaging image; performing image processing on the filtered initial actual sintering cross-section visible light imaging image; performing secondary processing imaging by overlapping and averaging the image of the processed initial actual sintering cross-section visible light imaging image to obtain the effective actual sintering cross-section visible light imaging of the current batch of trolleys.
[0013] Further, step S30 specifically includes: obtaining the current actual total return rate of sintering for the current batch of trolleys based on the weighed mass of sintered material on the screen and the mass of sintered material under the screen of the current batch of trolleys.
[0014] This invention also provides a sintering return rate prediction system based on visible light imaging of the tail section, including a sintering machine, a sintering trolley, a visible light imaging acquisition device, and a processing device. The sintering trolley is movably arranged along the head wheel of the sintering machine toward the tail wheel. The end of the sintering machine near the head wheel is sequentially provided with a feeding area, an ignition furnace area, and a holding furnace area. The visible light imaging acquisition device is located on the outside of the tail wheel of the sintering machine and is used to acquire visible light images of the actual effective tail sintering cross section of the current batch of sintering trolleys. The processing device is used to execute the steps of the above-mentioned sintering ore intensity prediction method based on visible light imaging of the tail section.
[0015] The present invention has the following beneficial effects:
[0016] This invention provides a method and system for predicting sinter strength based on visible light imaging of the tail section of the sintering machine. Based on research into sintering technology, it acquires a visible light image of the actual effective tail section of the sintering machine from the tail wheel position in a timely manner. The visible light image of the actual effective tail section has a known correlation ratio with the actual cross-sectional image of the current batch of trolleys. Based on the visible light image of the actual effective tail section, the current raw sinter return rate of the current batch of trolleys is obtained. The current actual total return rate of the current batch of sintering is obtained based on the weighing results. The current clinker return rate is determined based on the difference between the current actual total return rate and the current raw sinter return rate. This ultimately achieves rapid acquisition of the current clinker return rate of the current batch of trolleys, thus facilitating the prediction of the current sinter strength based on the current clinker return rate.
[0017] In addition to the objectives, features, and advantages described above, the present invention has other objectives, features, and advantages. The invention will now be described in further detail with reference to the figures. Attached Figure Description
[0018] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:
[0019] Figure 1 This is a process flow diagram of the existing sintering system;
[0020] Figure 2 This is a schematic diagram of the formation of existing sintered ore, in which, Figure 2 a is a diagram of the existing sinter formation process. Figure 2 b is a cross-sectional view of the existing sinter formation. Figure 2 c is the completed cross-sectional view of the existing sintered ore;
[0021] Figure 3This is a flowchart of the sinter intensity prediction method based on visible light imaging of the tail section of the present invention;
[0022] Figure 4 A schematic diagram of the visible light imaging of the actual effective tail section sintering cross-section in one embodiment of the present invention;
[0023] Figure 5 This invention presents a partial structural schematic diagram of a sintering return rate prediction system based on visible light imaging of the tail section. Detailed Implementation
[0024] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
[0025] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.
[0026] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.
[0027] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.
[0028] The sintering system mainly includes several pieces of equipment such as a sintering trolley, a mixer, a main exhaust fan, and an annular cooler. See the sintering system process flow diagram. Figure 1As shown: Various raw materials are proportioned in the batching room to form a mixture. This mixture is then fed into a mixer for homogenization and pelletizing. It is then evenly distributed onto the sintering trolley by a roller feeder and a nine-roller distributor to form a sintering mixture layer. The ignition fan and ignition blower start the ignition furnace, igniting the uppermost layer of the sintering mixture on the sintering trolley. The ignited combustion zone moves downwards, and the mixture passing through it is roasted into sintered ore. This is the sintering process. After sintering, the resulting sintered ore is crushed by a single-roller crusher and cooled in an annular cooler. Finally, it is screened and granulated before being sent to the blast furnace or finished ore bin. The screened undersize includes raw meal undersize and clinker undersize, which are transported on a return ore conveyor belt. The materials are all small, dark brown particles or powders, and current technology makes it difficult to distinguish the proportions of clinker and raw meal return ore.
[0029] Please refer to Figure 2 ( Figure 2 a, Figure 2 b and Figure 2 c) During the sintering process, the ignited combustion zone moves from top to bottom, and its movement speed is the vertical sintering speed. The sintering trolley moves from the head to the tail (tail wheel) of the sintering machine, and its speed is the machine speed. When the combustion zone reaches the bottom of the mixture on the sintering trolley, the position of the sintering trolley relative to the head (or tail wheel) of the sintering machine is the sintering endpoint. Figure 2 As shown in Figure a, as the sintering trolley moves, the combustion zone gradually moves downward, and the mixture passing through the combustion zone is roasted into sintered ore; as... Figure 2 As shown in b, during the sintering process, the materials inside the sintering trolley can be divided into four layers from bottom to top: the bottom layer, the mixed layer, the combustion zone layer, and the sintered ore layer. For example... Figure 2 As shown in Figure c, when the combustion zone moves to the bottom material layer, all the material in the sintering trolley has been roasted into sinter. This position is the sintering endpoint, typically indicated by the bellows number. Optionally, the combustion zone has a certain thickness. The sintering endpoint can be understood as the bottom of the combustion zone just touching the bottom material layer. Controlling the sintering endpoint at the second-to-last or last bellows position prevents the generation of raw material, resulting in high fuel utilization and high sintering efficiency. Optionally, if the bottom of the combustion zone does not touch the bottom material layer when reaching the last bellows position, raw material is generated between the bottom of the combustion zone and the bottom material layer.
[0030] Please refer to Figure 1 and Figure 2Through research on sintering technology, the formation process of sintered ore is a gradual downward movement of the sintering combustion zone. The combustion temperature of the sintering combustion zone is 1250℃ (sintering material temperature). The sintering mixture contains various components such as fuel, flux, and iron ore. After the sintering material surface is ignited at the ignition furnace at the head of the sintering machine, a combustion zone with a thickness of about 20 to 30 mm is formed. The various mixtures in the combustion zone are roasted at high temperature to form sintered ore. After the combustion zone gradually moves down to the bottom of the sintering trolley and a bottom material layer is laid, the combustion zone will no longer move down. The fuel in the area traversed by the combustion zone has been completely burned. During the gradual downward movement of the combustion zone, the sintering trolley also moves towards the tail wheel of the sintering machine, and the sintering trolley moves to the tail of the sintering machine. Sintered ore return (total sintered ore return) includes raw meal return (raw meal undersize) and clinker return (clinker undersize). Raw meal return occurs when a portion of the mixture fails to enter the sintering process on the sintering trolley, resulting in unburned sinter. During sintering and cooling, this unburned mixture becomes powdery, and most of this powdery material is screened out (e.g., particle size <3mm), thus constituting raw meal return. Clinker return occurs when some sinter is broken into powder due to friction and impact during the feeding process between the sintering machine and screening, and is also screened out. The primary cause of raw meal return is incomplete sintering of the mixture, while the primary cause of clinker return is insufficient sinter strength. Different methods are used in sintering production to control raw meal return and clinker return.
[0031] Please refer to Figure 3 , Figure 4 and Figure 5 This invention provides a method for predicting the strength of sintered ore based on visible light imaging of the tail section, comprising the following steps: S10, acquiring visible light imaging of the actual effective tail section sintering cross-section of the current batch of trolleys, wherein the visible light imaging of the actual effective tail section sintering cross-section has a known correlation ratio with the true cross-sectional image of the current batch of trolleys; S20, acquiring the current sintered raw material return rate of the current batch of trolleys based on the visible light imaging of the actual effective sintering cross-section; S30, acquiring the current actual total sintering return rate of the current batch of trolleys; S40, determining the current sintered clinker return rate based on the difference between the current actual total sintering return rate and the current sintered raw material return rate; S50, predicting the current sintered ore strength based on the current sintered clinker return rate, wherein the higher the current sintered clinker return rate, the lower the current sintered ore strength.
[0032] The present invention provides a method for predicting the strength of sintered ore based on visible light imaging of the tail section. Based on research into sintering technology, this method acquires a visible light image of the actual effective tail section sintering cross-section from the tail wheel position of the sintering machine in a timely manner. The visible light image of the actual effective tail section sintering cross-section has a known correlation ratio with the actual cross-sectional image of the current batch of trolleys. Based on the visible light image of the actual effective tail section sintering cross-section, the current raw ore return rate of the current batch of trolleys is obtained. The current actual total ore return rate of the current batch of trolleys is obtained based on the weighing results. The current clinker return rate is determined based on the difference between the current actual total ore return rate and the current raw ore return rate. This method ultimately achieves rapid acquisition of the current clinker return rate of the current batch of trolleys, thus facilitating the prediction of the current sintered ore strength based on the current clinker return rate.
[0033] Understandably, the current sinter strength is predicted based on the current clinker return rate. The higher the current clinker return rate, the lower the current sinter strength, and vice versa. The sinter strength prediction method based on visible light imaging of the tail section provided by this invention obtains the sinter return rate in real time, avoiding the existing method that requires further processing of the undersize material, dividing it into raw material undersize material and clinker undersize material, weighing them, and then obtaining the clinker return rate to assess the sinter strength. This method has the technical problem of not being able to quickly assess the sinter strength.
[0034] Further, step S20 specifically includes: the visible light imaging of the actual effective tail sintering cross section has a visible light imaging black area and a visible light imaging bright area. The visible light imaging black area includes a visible light imaging base material section and a visible light sintering area. The visible light imaging bright area is located on the visible light sintering area. The visible light imaging base material section corresponds to the actual base material layer of the actual cross-sectional image. The visible light sintering area corresponds to the actual sintering cross-sectional area of the actual cross-sectional image. The visible light imaging bright area corresponds to the actual sintering critical area of the actual cross-sectional image. The actual sintering critical area is located in the actual sintering cross-sectional area. The process involves determining the sintering material corresponding to the actual sintering critical region and the actual bottom material layer as the current sintering raw material region, calculating the current raw material area ratio of the current sintering raw material region based on the area ratio of the current sintering raw material region to the actual sintering cross-sectional region, and inputting the current raw material area ratio and current sintering operating condition parameters into the return ore prediction model to predict the current sintering raw material return rate of the current batch of trolleys. The historical sintering raw material area ratio and historical sintering operating condition parameters are used as the training input set, and the historical tail section raw material return rate is used as the training output set to establish the return ore prediction model through neural network learning. By acquiring visible light images of the actual effective sintering cross-section at the tail wheel of the sintering machine in real time, and recognizing the known correlation ratio between these images and the actual cross-sectional images of the current batch of sintering trolleys, visible light imaging technology is used to obtain the visible light imaging base material area, visible light sintering area, and visible light imaging bright area. Ultimately, the current sintering raw material area and the actual sintering cross-sectional area of the current batch of sintering trolleys are obtained. This achieves the acquisition of the current raw material area ratio from the tail wheel position of the sintering machine. Finally, based on the return ore prediction model, the current raw material area ratio, and the current sintering operating parameters, the current sintering raw material return rate is obtained. This allows for the prediction of the current sintering raw material return rate as the sintering machine passes the tail wheel, avoiding the technical problem of requiring further processing, separation, and weighing after screening to obtain the current sintering raw material return rate.
[0035] Understandably, visible light imaging technology is existing technology, and the actual effective tail section of the sintering machine is divided into dark and bright areas under visible light. In this invention, the visible light imaging dark area above the bright area represents fully sintered ore (sintered cooled ore), and the visible light imaging dark area below the bright area represents sintered raw material and sintered base material. The area corresponding to the sintered raw material can be obtained by determining the mapping relationship between the actual base material layer and the visible light imaging of the actual effective tail section of the sintering machine. Specifically, if the visible light imaging of the actual effective tail section of the sintering machine is completely black, the sintering endpoint is before the tail section. If the current area is completely black, it indicates that the sintering endpoint is too far forward, and the sintering area of the sintering machine is not being fully utilized. In this case, reducing the gas injection volume corresponds to a slower vertical combustion speed, which can adjust the sintering endpoint to move backward until a bright line appears on the tail section of the sintering machine.
[0036] In this invention, the actual sintering critical region and the actual sintering cross-sectional region above the actual sintering critical region are the sintered clinker region.
[0037] Understandably, because the sintering operating parameters of each sintering plant differ within a certain sintering cycle (e.g., different raw material conditions, gas conditions, and equipment models and specifications), it is impossible to quantitatively provide a linear relationship between the current critical sintering temperature range and the current sintering cross-sectional area range applicable to all sintering plants. This invention establishes a return ore prediction model to establish the correspondence between the current raw material area ratio, the current sintering operating parameters, and the current sintering raw material return rate. Based on visible light imaging of the actual effective tail section sintering cross-section, it can accurately predict the current sintering raw material return rate of the current batch of sintering trolleys. Understandably, the current batch of sintering trolleys can be one sintering trolley or multiple sintering trolleys.
[0038] Furthermore, in order to accurately obtain the area mapped by the actual bottom material layer in the visible light imaging of the actual effective tail sintering cross section, and thus improve the accuracy of the sintering return rate prediction, the ideal sintering visible light imaging of the current batch of trolleys is obtained. The ideal sintering visible light imaging includes a theoretical bottom material layer, which corresponds to the actual bottom material layer. The ideal sintering visible light imaging and the actual effective tail sintering cross section visible light imaging are fused together, and the bottom material interval of the visible light imaging is determined according to the theoretical bottom material layer.
[0039] Understandably, please refer to Figure 4Visible light imaging technology is an existing technology. Analysis shows that the actual effective visible light imaging of the tail section typically includes a visible light imaging black area and a visible light imaging bright area. The visible light imaging black area includes the visible light imaging base material section and the visible light sintering area. The visible light imaging base material section maps to the actual base material layer of the current batch of trolleys. The sintering material in the area between the visible light imaging bright area and the visible light imaging base material section is the sintering raw material (the actual combustion zone has not burned to the base material section position before reaching the sintering endpoint). The sintering material in the visible light imaging bright area and the sintering material above the visible light imaging bright area is the sintered clinker. It can be understood that the visible light imaging bright area is the combustion area. In this invention, the current raw material area ratio of the current sintering raw material area is calculated based on the area ratio of the current sintering raw material area to the actual sintering cross-sectional area. The current sintering cross-sectional area is composed of the cross-sectional area of the current sintering raw material area, the cross-sectional area of the current sintered clinker, and the base material section.
[0040] Furthermore, in order to quickly and accurately obtain the visible light imaging base material zone, based on the study of sintering, the ideal sintering visible light image of the current batch of trolleys is obtained. The ideal sintering visible light image includes the theoretical base material layer. The ideal sintering visible light image and the actual effective tail sintering cross-section visible light image are fused together, and the base material zone is determined based on the theoretical base material layer.
[0041] Furthermore, in order to quickly and accurately obtain the current sintering raw material area, the cross-sectional area of the bottom material of the current batch of trolleys is calculated in advance, and the area of the current sintering raw material area is obtained based on the difference between the area of the visible light imaging black area below the visible light imaging bright area and the cross-sectional area of the bottom material.
[0042] Furthermore, if the current clinker area ratio is less than a preset clinker threshold, an early warning message will be issued. Understandably, the clinker threshold ranges from 75% to 95%.
[0043] Furthermore, historical sintering operating parameters include historical sintering air volume parameters, historical trolley speed parameters, and historical sintering material layer thickness parameters.
[0044] Furthermore, before step S50, the method further includes: if the current sintering raw material return rate is greater than the current actual total sintering return rate, updating the visible light image of the actual effective tail section sintering cross-section of the previous batch of trolleys to the visible light image of the actual effective tail section sintering cross-section of the current batch of trolleys. In this invention, if the current sintering raw material return rate is greater than the current actual total sintering return rate, it indicates that there is an error in the visible light image of the actual effective tail section sintering cross-section. In this case, the visible light image of the actual effective tail section sintering cross-section of the previous batch of trolleys is updated to the visible light image of the actual effective tail section sintering cross-section of the current batch of trolleys for correction. The current sintering raw material return rate is estimated using the visible light image of the actual effective tail section sintering cross-section of the previous batch of trolleys.
[0045] Furthermore, to improve prediction accuracy, step S10 specifically includes: acquiring the initial actual sintering cross-section visible light imaging image of each target sintering trolley corresponding to the current batch of trolleys; filtering out the distortion of the initial actual sintering cross-section visible light imaging image; performing image processing on the filtered initial actual sintering cross-section visible light imaging image; performing secondary processing and imaging by overlapping and averaging the image of the processed initial actual sintering cross-section visible light imaging image to obtain the effective actual sintering cross-section visible light imaging of the current batch of trolleys.
[0046] Furthermore, if the current clinker area ratio is less than a preset clinker threshold, an early warning message will be issued. Understandably, the clinker threshold ranges from 75% to 95%.
[0047] Furthermore, the actual sintered return ore for the current batch of trolleys is obtained based on the weighed mass of the sintered material on the screen and the mass of the sintered material under the screen of the current batch of trolleys.
[0048] This invention also provides a sintering return rate prediction system based on visible light imaging of the tail section, including a sintering machine, a sintering trolley, a visible light imaging acquisition device, and a processing device. The sintering trolley is movably arranged along the head wheel of the sintering machine toward the tail wheel. The end of the sintering machine near the head wheel is sequentially provided with a feeding area, an ignition furnace area, and a holding furnace area. The visible light imaging acquisition device is located on the outside of the tail wheel of the sintering machine and is used to acquire visible light images of the actual effective tail sintering cross section of the current batch of sintering trolleys. The processing device is used to execute the steps of the above-mentioned sintering ore intensity prediction method based on visible light imaging of the tail section.
[0049] Understandably, a sensor is installed on the tail wheel of the sintering machine to track the trolley tilt angle A. When the trolley tilt angle A is reached, a visible light imaging camera takes a picture of the tail section of the sintering machine to obtain a visible light image of the actual effective tail section sintering cross-section. In this embodiment, a visible light image of the ideal sintering cross-section at the target sintering endpoint is obtained when the trolley tilt angle A is set. This ideal sintering visible light image includes the theoretical material layer. The ideal sintering visible light image and the actual effective tail section sintering visible light image are fused together, and the bottom material layer is determined based on the theoretical material layer. The ideal temperature distribution map of the ideal sintering cross-section visible light image can be determined by theoretical calculation.
[0050] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A method for sinter strength prediction based on tailings cross-section visible light imaging, characterized by, The method comprises the following steps: S10, acquiring actual effective machine tail sintering section visible light imaging of the current batch of trolleys, the actual effective machine tail sintering section visible light imaging having a known correlation ratio with the real section image of the current batch of trolleys; S20, acquiring the current sintering green material return rate of the current batch of trolleys according to the actual effective machine tail sintering section visible light imaging; The actual effective machine tail sintering section visible light imaging has a visible light imaging dark area and a visible light imaging bright area, the visible light imaging dark area comprising a visible light imaging bottom material interval and a visible light sintering area, the visible light imaging bright area being on the visible light sintering area, the visible light imaging bottom material interval corresponding to a real bottom material layer of the real section image, the visible light sintering area corresponding to a real sintering section area of the real section image, the visible light imaging bright area corresponding to a real sintering critical area of the real section image, the real sintering critical area being on the real sintering section area; The sintered material corresponding between the real sintering critical area and the real bottom material layer is determined as a current sintering green material area, the current sintering green material area is calculated according to the area ratio of the current sintering green material area and the real sintering section area to obtain a current green material area ratio, the current green material area ratio and current sintering working condition parameters are input into a return material prediction model to predict the current sintering green material return rate of the current batch of trolleys, wherein historical sintering green material area ratios and historical sintering working condition parameters are taken as a training input set, and historical machine tail green material return rates are taken as a training output set to learn and establish the return material prediction model through a neural network; S30, acquiring a current sintering actual total return rate of the current batch of trolleys; S40, determining a current sintered material return rate according to the difference between the current sintering actual total return rate and the current sintering green material return rate; S50, predicting a current sintered ore strength according to the current sintered material return rate, the greater the current sintered material return rate is, the lower the current sintered ore strength is.
2. The sintered ore strength prediction method based on machine tail section visible light imaging according to claim 1, wherein ideal sintering visible light imaging of the current batch of trolleys is acquired, the ideal sintering visible light imaging comprising a theoretical bottom material layer, the theoretical bottom material layer corresponding to the real bottom material layer; the ideal sintering visible light imaging and the actual effective machine tail sintering section visible light imaging are fused, and the visible light imaging bottom material interval is determined according to the theoretical bottom material layer.
3. The sinter strength prediction method based on visible light imaging of the tail end section according to claim 1, characterized by, The method further comprises the following steps: The historical sintering working condition parameters comprise historical sintering air volume parameters, historical trolley speed parameters and historical sintering material layer thickness parameters.
4. The sinter strength prediction method based on visible light imaging of the tail end section according to claim 1, characterized by, The method further comprises the following steps: Before step S50, the method further comprises the following steps: If the current sintering green material return rate is greater than the current sintering actual total return rate, the actual effective machine tail sintering section visible light imaging of the previous batch of trolleys is updated to the actual effective machine tail sintering section visible light imaging of the current batch of trolleys.
5. The sintered ore strength prediction method based on machine tail section visible light imaging according to any one of claims 1 to 4, wherein The step S10 specifically comprises: obtaining an initial actual sintering section visible light imaging image of each target sintering trolley corresponding to the current batch trolley; filtering out the distorted initial actual sintering section visible light imaging image; image processing the filtered-out initial actual sintering section visible light imaging image; obtaining the actual effective tail section sintering visible light imaging of the current batch trolley by performing an overlapping and mean value secondary processing imaging on the image-processed initial actual sintering section visible light imaging image.
6. The sinter strength prediction method based on visible light imaging of the tail end section according to any one of claims 1 to 4, characterized in that, The step S30 specifically comprises: obtaining the current sintering actual total return ore rate of the current batch trolley according to the screened sintering material mass and the underscreened sintering material mass of the current batch trolley.
7. A sinter return ore rate prediction system based on tail section visible light imaging, characterized in that, comprising a sintering machine, a sintering trolley, a visible light imaging acquisition device and a processing device, the sintering trolley is movably arranged along the sintering machine head wheel towards the sintering machine tail wheel, and the sintering machine is sequentially provided with a distribution area, an ignition furnace area and a holding furnace area at one end close to the sintering machine head wheel; the visible light imaging acquisition device is arranged outside the sintering machine tail wheel of the sintering machine, and is used for obtaining the actual effective tail section sintering visible light imaging of the current batch sintering trolley; the processing device is used for executing the steps of the sinter ore strength prediction method based on the tail section visible light imaging according to any one of claims 1 to 6.
Citation Information
Patent Citations
Sintering end point control method and system
CN115493400A
Sintered ore quality online analysis method based on imaging technology
CN116256336A