Sintering return mine rate prediction method and system based on tail section visible light imaging

Abstract

The invention discloses a sintering return mine rate prediction method and system based on tail section visible light imaging, and the method comprises the following steps: obtaining an actual effective tail sintering section visible light image of a current batch of trolleys, the actual effective tail sintering section visible light image and a real section image of the current batch of trolleys having a known correlation ratio; according to the area ratio of the current sintering raw material area to the real sintering cross section area, the current raw material area proportion of the current sintering raw material area is obtained through calculation; and inputting the current raw material area proportion and the current sintering working condition parameters into a return mine prediction model to predict the current sintering return mine rate of the current batch of trolleys. According to the sintering return ore rate prediction method based on tail section visible light imaging, the sintering return ore rate is obtained in real time, and the technical problems that in the prior art, the sintering return ore rate needs to be obtained after screening and weighing, the sintering working condition cannot be adjusted in time according to the sintering return ore rate, and the sintering efficiency is low are solved.

Description

Technical Field

[0001] The invention relates to the technical field of sintering, and in particular to a method and system for predicting a sintering return rate based on visible light imaging of a tail section of a machine. Background Art

[0002] With the rapid development of modern industry, the scale of steel production is getting larger and larger, and energy consumption is also increasing. Energy conservation and environmental protection indicators are becoming more and more important factors to consider in the steel production process. In steel production, iron-containing raw ore needs to be processed by the sintering system before entering the blast furnace for smelting. That is, various powdered iron-containing raw materials are mixed with appropriate amounts of fuel (coal powder, coke powder) and flux, and appropriate amounts of water. After mixing and balling, they are placed on the sintering trolley for roasting, so that a series of physical and chemical changes occur, forming sintered ore that is easy to smelt. This process is called sintering.

[0003] The sintering process includes ignition sintering, crushing, cooling with an annular cooler, and screening, wherein the screened material after screening is the sintered finished ore, and the screened material after screening is the sintered return ore. In the prior art, the sintering return rate is obtained by weighing the weight of the screened material and the screened material. Since the sintering machine has a long working time in the annular cooler cooling, the sintering return rate cannot be predicted in time after the sintering machine completes sintering, resulting in a serious lag in obtaining the sintering return rate, and the sintering conditions cannot be adjusted in time according to the sintering return rate, resulting in low sintering efficiency.

[0004] In view of this, it is necessary to propose a sintering return rate prediction method and system based on visible light imaging of the tail section to alleviate the above defects. Summary of the invention

[0005] The present invention provides a method and system for predicting sintering return rate based on visible light imaging of the tail section, which solves the existing technical problems of being unable to obtain the sintering return rate in time and unable to guide sintering in time.

[0006] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0007] A method for predicting sintering return rate based on visible light imaging of the tail section of a machine comprises the following steps:

[0008] S10, obtaining the actual effective tail sintering section visible light imaging of the current batch of trolleys, the actual effective tail sintering section visible light imaging and the real cross-sectional image of the current batch of trolleys have a known correlation ratio, the actual effective tail sintering section visible light imaging has a visible light imaging black area and a visible light imaging bright area, the visible light imaging black area includes a visible light base material layer and a visible light sintering area, the visible light imaging bright area is on the visible light sintering area, the visible light imaging base material layer corresponds to the real base material layer of the real cross-sectional image, the visible light sintering area corresponds to the real sintering cross-sectional area of ​​the real cross-sectional image, the visible light imaging bright area corresponds to the real sintering critical area of ​​the real cross-sectional image, and the real The actual sintering critical area is on the actual sintering cross-sectional area; S20, determine that the sintering material corresponding to the actual sintering critical area and the actual base material layer is the current sintering raw material area, and calculate the current raw material area ratio of the current sintering raw material area according to the area ratio of the current sintering raw material area and the actual sintering cross-sectional area; S30, input the current raw material area ratio and the current sintering operating condition parameters into the return ore prediction model to predict the current sintering return ore rate of the current batch of trolleys, wherein the historical sintering raw material area ratio and the historical sintering operating condition parameters are used as the training input set, and the historical machine tail raw material return rate is used as the training output set to establish a return ore prediction model through neural network learning.

[0009] Furthermore, the current clinker area ratio is obtained according to the current raw material area ratio, and the sum of the current raw material area ratio and the current clinker area ratio is 1.

[0010] Furthermore, the ideal sintering visible light imaging of the current batch of trolleys is obtained, and the ideal sintering visible light imaging includes a theoretical paving layer, and the theoretical paving layer corresponds to the real base material layer; the ideal sintering visible light imaging and the actual effective tail sintering section visible light imaging are integrated, and the visible light imaging base material interval is determined according to the theoretical paving layer.

[0011] Furthermore, the method also includes the step of issuing a warning message if the current clinker area ratio is less than a preset clinker threshold.

[0012] Furthermore, the historical sintering condition parameters include historical sintering air volume parameters, historical trolley speed parameters and historical sintering material layer thickness parameters.

[0013] Furthermore, step S10 specifically includes:

[0014] The initial actual sintering cross-section visible light imaging image of each target sintering trolley corresponding to the current batch of trolleys is obtained; the distorted initial actual sintering cross-section visible light imaging image is filtered out; the initial actual sintering cross-section visible light imaging image after the distortion is filtered out is image processed; the initial actual sintering cross-section visible light imaging image after image processing is overlapped and averaged for secondary processing to obtain the effective actual sintering cross-section visible light imaging model of the current batch of trolleys.

[0015] Further, all sintering trolleys passing through the sintering machine within the target time period are determined to be current batch trolleys.

[0016] The present invention also provides a sintering return rate prediction system based on visible light imaging of the tail section of the sintering machine, 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 toward the sintering machine tail wheel. The sintering machine is provided with a distribution area, an ignition furnace area and a holding furnace area in sequence at one end close to the sintering machine head wheel of the sintering machine; the visible light imaging acquisition device is arranged on the outer side of the sintering machine tail wheel of the sintering machine, and the visible light imaging acquisition device is used to obtain the actual effective visible light imaging of the tail sintering section of the current batch of trolleys; the processing device is used to execute the steps of the above-mentioned sintering return rate prediction method based on visible light imaging of the tail section of the sintering machine.

[0017] The present invention has the following beneficial effects:

[0018] The sintering return rate prediction method and system based on tail section visible light imaging provided by the present invention are based on the research on sintering technology, and timely obtain the actual effective tail section visible light imaging from the tail wheel position of the sintering machine. The actual effective tail section visible light imaging has a known correlation ratio with the real section image of the current batch of trolleys. The visible light bottom material layer, the visible light sintering area and the visible light imaging bright area are obtained through the visible light imaging technology, and finally the current sintering raw material area and the real sintering section area of ​​the current batch of sintering trolleys are obtained. domain, and realizes obtaining the current raw material area ratio from the position of the sintering machine tail wheel, and finally obtaining the sintering return rate based on the return prediction model, the current raw material area ratio and the current sintering condition parameters. The sintering return rate can be predicted when the sintering machine passes through the sintering machine tail wheel. The sintering return rate prediction method based on visible light imaging of the tail section provided by the present invention obtains the sintering return rate in real time, avoiding the existing need to obtain the sintering return rate through screening and weighing, resulting in the inability to adjust the sintering condition according to the sintering return rate in time, and the technical problem of low sintering efficiency.

[0019] In addition to the above-described objects, features and advantages, the present invention has other objects, features and advantages. The present invention will be further described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings constituting a part of this application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0021] Figure 1 It is the process flow chart of the existing sintering system;

[0022] Figure 2This is a schematic diagram of the existing sinter formation, where: Figure 2 a is the existing sinter formation process diagram, Figure 2 b is the existing sinter formation cross-section diagram, Figure 2 c is the completed cross-section of the existing sintered ore;

[0023] Figure 3 It is a flow chart of the sintering return rate prediction method based on visible light imaging of the tail section of the present invention;

[0024] Figure 4 A schematic diagram of visible light imaging of an actual effective tail sintering section in one embodiment of the present invention;

[0025] Figure 5 A partial structural schematic diagram of a sintering return rate prediction system based on visible light imaging of a tail section of the present invention. DETAILED DESCRIPTION

[0026] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0029] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0030] The sintering system mainly includes sintering trolley, mixer, main exhaust fan, ring cooler and other equipment. Figure 1As shown in the figure: various raw materials are proportioned in the batching room to form a mixture. After the mixture enters the mixer for mixing and balling, it is evenly spread on the sintering trolley through the round roller feeder and the nine-roller distributor to form a sintering mixture layer. The ignition fan and the ignition fan start the ignition furnace, and the sintering mixture on the top layer of the sintering trolley is ignited in the ignition furnace. The ignited combustion zone begins to move from top to bottom, and the mixture passing through the combustion zone is roasted into sintered ore. This is the sintering process. The sintered ore obtained after sintering is crushed by a single roller crusher and then cooled in an annular cooler. Finally, it is sent to the blast furnace or the finished ore bin after screening and granulation. Among them, the oxygen required for the sintering process is provided by the main exhaust fan. There are multiple vertically arranged bellows under the sintering trolley. Under the bellows is a horizontally placed large flue (or flue). The large flue is connected to the main exhaust fan. The negative pressure wind generated by the main exhaust fan through the large flue and the bellows passes through the trolley to provide combustion-supporting air for the sintering process. Among them, the screened undersize includes raw meal undersize and clinker undersize. The raw meal undersize and clinker undersize are transported on the return ore belt. The materials are all small black-brown particles or powdery materials. It is difficult to distinguish the proportion of clinker return ore and raw meal return ore in time at the tail of the sintering machine with the existing technology.

[0031] 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 the moving speed of the combustion zone is the vertical sintering speed; the sintering trolley moves from the head to the tail (sintering machine tail wheel) of the sintering machine, and the moving speed of the sintering trolley is the sintering machine speed; when the combustion zone moves to the bottom of the sintering trolley mixture, the corresponding position of the sintering trolley relative to the sintering machine head (or sintering machine tail wheel) is the sintering end point. Figure 2 As shown in a, with the movement of the sintering trolley, the combustion zone gradually moves downward, and the mixed material passing through the combustion zone is roasted into sintered ore; Figure 2 As shown in b, during the sintering process, the materials in the sintering trolley can be divided into a bottom material layer, a mixed material layer, a combustion zone layer, and a sintered ore layer from bottom to top. Figure 2 As shown in c, when the combustion zone moves to the bed material layer, the materials in the sintering trolley have all been roasted into sintered ore. At this time, the corresponding position is the sintering end position, which is generally represented by the bellows number. Optionally, the combustion zone layer has a certain thickness, and the sintering end position can be understood as the bottom of the combustion zone just touching the bed material layer. When the sintering end position is controlled at the second to last bellows or the first to last bellows, no raw meal will be produced, the fuel utilization rate is high, and the sintering efficiency is high. Optionally, if the bottom of the combustion zone does not touch the bed material layer when reaching the first to last bellows, raw meal is produced between the bottom of the combustion zone and the bed material layer.

[0032] Please refer to Figure 1 and Figure 2Through the study of sintering technology, it is found that the formation process of sintered ore is the process of the sintering combustion zone gradually moving downward. The combustion temperature of the sintering combustion zone is 1250℃ (sintering material temperature). The sintering mixture is mixed with various components such as fuel, flux, iron ore, etc. 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 30mm is formed. The various mixed materials 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 to lay the bottom material layer, the combustion zone will no longer move down, and the fuel in the combustion zone has been burned. Among them, during the gradual downward movement of the combustion zone, the sintering machine trolley is also moving towards the direction of the sintering machine tail wheel, and the sintering machine trolley moves to the tail of the sintering machine.

[0033] Through the study of sintering technology, during the sintering process, the sintering mixture is spread on the sintering trolley and roasted into sintered ore on the sintering trolley. As the sintering machine trolley moves to the tail of the machine, the sintered ore on the sintering trolley will slide from the tail of the sintering machine to the single-roll crusher in units of trolleys. The crushed sintered ore enters the ring cooler (or cooling equipment such as belt cooler) for cooling. The cooled sintered ore enters the screening link, and the powdered material under the screen will be sent back to the batching link and re-enter the sintering machine. This part of the material under the screen and sent back to the batching link is the returned ore; the more returned ore, the more unfavorable it is for sintering production. For example, if the sintering machine outlet material is 100% and the returned ore is 20%, then the sintered product is only 80% of the sintering outlet material. If the returned ore is 5%, the product has the sintering outlet material. 95%, the lower the return rate, the higher the utilization rate of the sintering machine; there are raw material return and clinker return in the sintering return. Raw material return means that part of the mixed material on the sintering trolley has not entered the sintering process, and the mixed material has not been roasted into sintered ore. It will become powder in the sintering cooling and other links. Most of these powder materials will be screened out in the screening link (for example, particle size <3mm), which is raw material return; clinker return means that some sintered ores are broken into powder due to friction, falling in the feeding link and other factors in the process from the sintering machine to the screening, and will also be screened out in the screening link; the main reason for the formation of raw material return is that the mixed material has not completed the sintering process, and the main reason for the formation of clinker return is that the strength of the sintered ore is not enough. To control the return of raw material and the return of clinker, different means are used in sintering production.

[0034] Please refer to Figure 3 , Figure 4 and Figure 5The present invention provides a method for predicting the sintering return rate based on visible light imaging of the tail section, comprising the following steps: S10, obtaining the actual effective tail sintering section visible light imaging of the current batch of trolleys, the actual effective tail sintering section visible light imaging and the real cross-sectional image of the current batch of trolleys have a known correlation ratio, the actual effective tail sintering section visible light imaging has a visible light imaging black area and a visible light imaging bright area, the visible light imaging black area includes a visible light base material layer and a visible light sintering area, the visible light imaging bright area is on the visible light sintering area, the visible light imaging base material layer corresponds to the real base material layer of the real cross-sectional image, the visible light sintering area corresponds to the real sintering cross-sectional area of ​​the real cross-sectional image, and the visible light imaging bright area is The real sintering critical area of ​​the real cross-sectional image should be located on the real sintering cross-sectional area; S20, determining the sintering material corresponding to the real sintering critical area and the real base material layer as the current sintering raw material area, and obtaining the current raw material area ratio of the current sintering raw material area according to the area ratio of the current sintering raw material area and the real sintering cross-sectional area; S30, inputting the current raw material area ratio and the current sintering operating condition parameters into the return ore prediction model to predict the current sintering return ore rate of the current batch of trolleys, wherein the historical sintering raw material area ratio and the historical sintering operating condition parameters are used as the training input set, and the historical machine tail raw material return rate is used as the training output set, and the return ore prediction model is established through neural network learning.

[0035] The sintering return rate prediction method based on tail section visible light imaging provided by the present invention is based on the research on sintering technology, and timely obtains the actual effective tail section visible light imaging from the tail wheel position of the sintering machine. The actual effective tail section visible light imaging has a known correlation ratio with the real cross-sectional image of the current batch of trolleys. The visible light base material layer, the visible light sintering area and the visible light imaging bright area are obtained by the visible light imaging technology, and finally the current sintering raw material area and the real sintering cross-sectional area of ​​the current batch of sintering trolleys are obtained. The method realizes obtaining the current raw material area ratio from the position of the tail wheel of the sintering machine, and finally obtaining the sintering return rate based on the return prediction model, the current raw material area ratio and the current sintering condition parameters. The sintering return rate can be predicted when the sintering machine passes through the tail wheel of the sintering machine. The sintering return rate prediction method based on visible light imaging of the tail section provided by the present invention obtains the sintering return rate in real time, avoiding the existing technical problem of obtaining the sintering return rate after screening and weighing, resulting in the inability to adjust the sintering condition according to the sintering return rate in time and low sintering efficiency.

[0036] It can be understood that visible light imaging technology belongs to the prior art, and the actual effective tail sintering section is divided into a black area and a bright area under visible light technology. In the present invention, the visible light imaging black area above the visible light imaging bright area is a completely sintered ore (sintered cooling ore), and the visible light imaging black area below the visible light imaging bright area is a sintered raw material and a sintered base material, wherein the area corresponding to the sintered raw material can be finally obtained by determining the mapping relationship between the real base material layer and the actual effective tail sintering section visible light imaging. Specifically, if the actual effective tail sintering section visible light imaging is completely black, the sintering end point is before the tail section; if it is currently a completely black area, it means that the sintering end point is too far forward and the sintering area of ​​the sintering machine is not fully utilized. At this time, the gas injection amount is reduced, and the corresponding vertical combustion speed is slowed down. The sintering end point can be adjusted to move backward until a bright line appears in the tail section of the sintering machine.

[0037] In the present invention, the real sintering critical region and the real sintering cross-sectional region above the real sintering critical region are the sintering clinker region.

[0038] It is understandable that, due to the different sintering parameters of each sintering plant in a certain sintering cycle (e.g., different raw material conditions, gas conditions, equipment models and specifications), it is impossible to quantitatively give a linear relationship between the current sintering completion interval and the current sintering section entire section interval that is suitable for all sintering plants. The present invention establishes a return ore prediction model, establishes the corresponding relationship between the current raw material area ratio, the current sintering parameters and the current sintering return ore rate, and can accurately predict the current sintering return ore rate of the current batch of trolleys based on the visible light imaging of the actual effective tail sintering section. It is understandable that the current batch of trolleys can be one sintering trolley or multiple sintering trolleys.

[0039] Furthermore, the current clinker area ratio is obtained according to the current raw material area ratio, and the sum of the current raw material area ratio and the current clinker area ratio is 1.

[0040] Furthermore, in the present invention, 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 section, and thus improve the accuracy of the prediction of the sintering return rate, the ideal sintering visible light imaging of the current batch of trolleys is obtained, and the ideal sintering visible light imaging includes a theoretical paving layer, and the theoretical paving layer corresponds to the real bottom material layer; the ideal sintering visible light imaging and the actual effective tail sintering section visible light imaging are integrated, and the visible light imaging bottom material interval is determined according to the theoretical paving layer.

[0041] Understandably, please refer to Figure 4Visible light imaging belongs to the existing technology. Analysis shows that the actual effective tail sintering section visible light imaging usually includes visible light imaging black area and visible light imaging bright area. The visible light imaging black area includes the visible light base material layer and the visible light sintering area, wherein the visible light base material layer maps the real 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 base material layer is the sintering raw material (the actual combustion zone has not burned to the base material interval before reaching the sintering end point), the sintering material in the visible light imaging bright area and the sintering material above the visible light imaging bright area are sintering clinker.

[0042] It can be understood that the bright area of ​​the visible light imaging is the combustion area. In the present 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 and the real sintering cross-sectional area; wherein the cross-sectional interval of the current sintering raw material area, the cross-sectional interval of the current sintering clinker and the bottom material interval constitute the current sintering cross-sectional interval.

[0043] Furthermore, in order to quickly and accurately obtain the visible light base material layer, based on the research on sintering, the ideal sintering visible light imaging of the current batch of trolleys is obtained, and the ideal sintering visible light imaging includes the theoretical paving layer; the ideal sintering visible light imaging and the actual effective tail sintering section visible light imaging are integrated to determine the base material interval based on the theoretical paving layer.

[0044] Furthermore, in order to quickly and accurately obtain the current sintering raw material area, the cross-sectional area of ​​the base 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 base material.

[0045] Furthermore, if the current clinker area ratio is less than a preset clinker threshold, an early warning message is issued. It can be understood that the clinker threshold ranges from 75% to 95%.

[0046] Furthermore, the historical sintering operating condition parameters include historical sintering air volume parameters, historical trolley speed parameters, and historical sintering material layer thickness parameters.

[0047] Furthermore, in order to improve the prediction accuracy, step S10 specifically includes: obtaining 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 distorted initial actual sintering cross-section visible light imaging image; performing image processing on the initial actual sintering cross-section visible light imaging image after filtering out the distortion; overlapping and averaging the initial actual sintering cross-section visible light imaging image after image processing to obtain the effective actual sintering cross-section visible light imaging model of the current batch of trolleys.

[0048] Further, the sintering trolleys passing through the sintering machine within the target time period are determined as the current batch trolleys. Specifically, the current batch trolleys are determined according to actual needs.

[0049] More preferably, the target time period is determined based on the actual operation of each trolley in the environmental machine.

[0050] Please refer to Figure 5 The present 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 sintering machine head wheel toward the sintering machine tail wheel, and the sintering machine is provided with a distribution area, an ignition furnace area and a holding furnace area in sequence at one end close to the sintering machine head wheel; the visible light imaging acquisition device is arranged on the outer side of the sintering machine tail wheel of the sintering machine, and the visible light imaging acquisition device is used to obtain the actual effective tail sintering section visible light imaging of the current batch of trolleys; the processing device is used to execute the steps of the above-mentioned sintering return rate prediction method based on visible light imaging of the tail section.

[0051] It can be understood that a sensor is installed on the tail wheel of the sintering machine to track the inclination angle A of the trolley. When the inclination angle A of the trolley is reached, the visible light imaging camera takes a picture of the tail section of the sintering machine to obtain the actual effective visible light imaging of the tail sintering section. In this embodiment, the ideal visible light imaging of the sintering section at the target sintering end position is set when the trolley inclination angle A is set, and the ideal visible light imaging of the sintering of the current batch of trolleys is obtained. The ideal visible light imaging of sintering includes a theoretical paving layer; the ideal visible light imaging of sintering and the actual effective visible light imaging of the tail sintering section are integrated, and the bottom material interval is determined according to the theoretical paving layer. The ideal temperature distribution diagram of the ideal visible light imaging of the sintering section can be determined by theoretical calculation. Specifically, a typical large-scale sintering machine trolley is 2 meters long and 5.5 meters wide, and the travel speed of the sintering trolley is 2 meters / min. After the tail wheel trolley of the tail sintering machine is tilted to a certain angle, the materials on the entire trolley slide to the downstream process, and at the same time, the sintering section of the trolley adjacent to the sliding material trolley is exposed, and the system obtains visible light imaging of the tail section here.

[0052] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for predicting sintering return rate based on visible light imaging of the tail section of a machine, characterized in that: The steps include: S10, obtaining the actual effective visible light imaging of the tail sintering section of the current batch of trolleys, wherein the actual effective visible light imaging of the tail sintering section has a known correlation ratio with the real cross-sectional image of the current batch of trolleys, and the actual effective visible light imaging of the tail sintering section has a visible light imaging black area and a visible light imaging bright area, wherein the visible light imaging black area includes a visible light base material layer and a visible light sintering area, wherein the visible light imaging bright area is located on the visible light sintering area, wherein the visible light imaging base material layer corresponds to the real base material layer of the real cross-sectional image, wherein the visible light sintering area corresponds to the real sintering cross-sectional area of ​​the real cross-sectional image, wherein the visible light imaging bright area corresponds to the real sintering critical area of ​​the real cross-sectional image, and wherein the real sintering critical area is located on the real sintering cross-sectional area; S20, determining that the sintering material corresponding to the actual sintering critical region and the actual base material layer is the current sintering raw material region, and obtaining the current raw material area ratio of the current sintering raw material region according to the area ratio of the current sintering raw material region and the actual sintering cross-sectional region; S30, inputting the current raw material area ratio and the current sintering condition parameters into the return ore prediction model to predict the current sintering return ore rate of the current batch of trolleys, wherein the historical sintering raw material area ratio and the historical sintering condition parameters are used as training input sets, and the historical machine tail raw material return rate is used as the training output set to establish the return ore prediction model through neural network learning.

2. The sintering return rate prediction method based on visible light imaging of the tail section of claim 1 is characterized in that: The current clinker area ratio is obtained according to the current raw material area ratio, and the sum of the current raw material area ratio and the current clinker area ratio is 1.

3. The method for predicting sintering return rate based on visible light imaging of the tail section of claim 1, characterized in that: Obtaining an ideal sintering visible light image of the current batch of trolleys, wherein the ideal sintering visible light image includes a theoretical paving layer, and the theoretical paving layer corresponds to the actual bottom paving layer; The ideal sintering visible light imaging and the actual effective tail sintering section visible light imaging are integrated, and the visible light imaging base material paving interval is determined according to the theoretical paving layer.

4. The method for predicting sintering return rate based on visible light imaging of the tail section of claim 2, wherein: Also includes the steps: If the current clinker area ratio is less than the preset clinker threshold, an early warning message is issued.

5. The method for predicting sintering return rate based on visible light imaging of the tail section of claim 1, characterized in that: The historical sintering condition parameters include historical sintering air volume parameters, historical trolley speed parameters and historical sintering material layer thickness parameters.

6. The method for predicting sintering return rate based on visible light imaging of the tail section of a machine according to any one of claims 1 to 3, characterized in that: Step S10 specifically includes: Acquire an initial actual sintering cross-section visible light imaging image of each target sintering trolley corresponding to the current batch of trolleys; Filtering out the distorted initial actual sintered cross-section visible light imaging image; Processing the initial actual sintered cross-section visible light imaging image after filtering out distortion; The initial actual sintering section visible light imaging image after image processing is overlapped and averaged for secondary processing imaging to obtain the actual effective tail sintering section visible light imaging of the current batch of trolleys.

7. The method for predicting sintering return rate based on visible light imaging of the tail section of a machine according to any one of claims 1 to 3, characterized in that: All sintering trolleys passing through the sintering machine within the target time period are determined to be the current batch trolleys.

8. A sintering return rate prediction system based on visible light imaging of the tail section, characterized in that: It comprises a sintering machine, a sintering trolley, a visible light imaging acquisition device and a processing device, wherein the sintering trolley is movably arranged along the sintering machine head wheel toward the sintering machine tail wheel, and the sintering machine is provided with a material distribution area, an ignition furnace area and a heat preservation furnace area in sequence at one end close to the sintering machine head wheel; The visible light imaging acquisition device is arranged on the outer side of the sintering machine tail wheel of the sintering machine, and the visible light imaging acquisition device is used to acquire the visible light imaging of the actual effective tail sintering section of the current batch of trolleys; The processing device is used to execute the steps of the sintering return rate prediction method based on visible light imaging of the tail section as described in any one of claims 1 to 7.

Images