WO2023227113A1

WO2023227113A1 - Real-time slag amount measurement method and system for automatic slag dumping of converter

Info

Publication number: WO2023227113A1
Application number: PCT/CN2023/096563
Authority: WO
Inventors: 张宇军; 于艳; 蒋晓放
Original assignee: 宝山钢铁股份有限公司
Priority date: 2022-05-27
Filing date: 2023-05-26
Publication date: 2023-11-30
Also published as: CN117165733A

Abstract

Disclosed in the present invention are a real-time slag amount measurement method and system for automatic slag dumping of a converter. The method comprises the following steps: S1, obtaining the real-time thickness of a slag layer at any horizontal position of a slag dumping region; S2, collecting a real-time planar image of the slag layer in a thickness vertical direction, and multiplying the thickness of the slag layer by the area of the slag layer in a planar region within a time interval, so as to obtain the slag volume of a micro-layer; and S3, multiplying the slag volume of the micro-layer by the density of the slag layer and a conversion coefficient, so as to obtain the slag amount of the micro-layer, and continuing to accumulate the real-time slag amount of the micro-layer, so as to obtain the total slag amount which has been dumped into a slag tank. In the present invention, the dumped slag weight can be measured, calculated and fed back in real time in a quick, timely and accurate manner.

Description

A method and system for real-time measurement of slag amount for automatic converter slag pouring

Technical field

The present invention relates to steelmaking technology, and more specifically, to a method and system for real-time measurement of slag amount for automatic slag pouring in a converter.

Background technique

In the field of steelmaking technology, intelligent converter technology is constantly developing. Among them, the essence of converter steelmaking is slag refining, or slag making. Generally speaking, there are three slag making processes, namely single slag method, double slag method and double slag leaving slag method.

Among them, the single slag method is a process that creates slag once during the blowing process. There is no slag pouring or stripping during the process. This process is simple to operate, but the dephosphorization effect is relatively poor. It is only used to smelt sulfur and phosphorus in steel. Carbon steel and low alloy steel with low content control requirements. The double slag method is a process in which about 50%-65% of the weight of the slag is poured out during the blowing process, and then the slag is added to re-make the slag. This process has good dephosphorization and desulfurization effects. The phosphorus content in the molten iron is high and the blowing process is high. When carbon steel and molten iron have high silicon content to prevent splashing, or when blowing low manganese steel to prevent manganese return, the double slag method can be used. Finally, the double slag retention method refers to leaving the part of the terminal slag with high alkalinity, high temperature, and high FeO content in the furnace in order to accelerate the formation of the initial slag of the next furnace and blow it during the blowing process. It is a process in which part of the slag is poured out to regenerate new slag during the smelting process. This process has high desulfurization and dephosphorization efficiency and is used in the smelting process of steel types that require higher quality of molten steel.

In the above-mentioned double slag method and double slag slag retention method, both require a slag pouring operation midway, that is, a certain amount of slag is poured out during blowing. In the actual production process on site, the total amount of slag pouring can generally be determined by real-time weighing of the slag weight. The amount of slag poured is determined by weighing the weight change of the slag truck before and after loading slag. However, slag truck weighing has the following two shortcomings:

1) Adding new slag truck weighing equipment requires major modifications to the production site, which requires a long construction period and high costs;

2) There is a time lag in the real-time weighing of the slag truck. Since the slag pouring speed is very fast, the weight gain data of the slag truck can only be given after the slag has fallen into the slag tank (the part of the slag truck used to receive the slag) (i.e. The amount of slag poured into the converter), therefore, this time lag has a greater impact on the accuracy of the real-time weight change of the slag truck. Especially in the later stage of slag dumping and the slag dumping process of agglomerated slag, the weight gain data of the slag truck will have serious measurement deviations.

The existing publication number CN103397134A discloses a method for calculating the residue amount based on the tilt angle. This method uses an auxiliary gun to measure the height of the molten steel liquid level, and then calculates the difference between the total volume of the melt in the furnace and the total volume of the remaining melt based on the size of the ladle, the furnace lining erosion status data, and the tilting angle, which is the turning point. The amount of slag left in the furnace can be calculated by multiplying the volume of slag remaining in the furnace by the density of the molten slag.

The existing publication number CN107502698A is an automated steelmaking method suitable for slag-less smelting. It discloses a slag dumping and slag retention calculation model. Among them, the slag retention model is based on the slag truck weighing technology and calculates the slag truck collection early and real-time in real time. The difference in weight is the weight of the poured slag, thereby realizing the slag remaining smelting model control method.

However, among the above two patented technologies, the accuracy of slag quantity control and slag retention control is not high. The reasons are on the one hand due to the complex on-site conditions and the influence of the slag pouring operating environment, and on the other hand because of the weighing of the slag truck. Due to the low accuracy of control technology. Judging from the results of the survey of existing technologies at home and abroad, foreign steel companies, such as Nippon Steel and Posco, have not disclosed methods for real-time online measurement of slag thickness in converters, while conventional image recognition technology can only use plane The image fuzzy calculation of the slag amount has a large error; so far, there are no public reports that can accurately measure the slag amount of the converter.

Contents of the invention

In view of the above-mentioned defects in the prior art, the purpose of the present invention is to provide a real-time measurement method and system for the slag amount of automatic converter slag pouring, which can measure, calculate and feedback the poured slag weight in a timely and accurate manner. The method of the present invention can obtain the amount of slag to be poured out in the slag pouring path, which can effectively improve the accuracy of slag measurement.

In order to achieve the above objects, the present invention adopts the following technical solutions:

A first aspect of the present invention provides a real-time measurement method of slag amount for automatic slag pouring in a converter, which includes the following steps:

S1. Obtain the real-time thickness of the slag layer at any horizontal position in the slag dumping area;

S2. Collect real-time planar images of the slag layer in the direction perpendicular to the thickness (i.e., vertical direction), multiply the thickness of the slag layer by the area of the slag layer in the plane area within the time interval, and obtain the microlayer ( That is, the slag volume of the slag layer);

S3. Multiply the slag volume of the micro-layer by the density and conversion coefficient of the slag layer to obtain the slag amount of the micro-layer. Continuously add up the real-time slag amount of the micro-layer to obtain the total slag amount that has been poured into the slag tank.

In the present invention, the slag dumping area is the area occupied by steel slag in the slag dumping path (ie, between the ladle ladle mouth and the slag truck mouth).

Time interval = 1000/camera frame rate, unit: milliseconds. Only the camera frame rate is taken into account when determining the time interval. For example, when the actual frame rate of the camera is 50FPS (frames per second), the time interval is 1000/50=20 milliseconds.

The density of the microlayer/slag layer was determined using a steel slag densitometer. For example, when smelting low carbon steel, the density of the slag layer is between 2.1-3.6g/ ^cm3 .

The conversion coefficient of the microlayer/slag layer is the ratio of the actual slag weight to the measured slag weight, which is determined using the actual slag weight-corrected slag volume real-time measurement method (i.e., the slag volume calculation model). It is usually between 0.01-15.0 and is dimensionless.

Preferably, in step S1, by arranging a laser profile sensor at the same horizontal position on both sides of the slag dumping area, the front and rear waveform curves of the slag dumping area are measured in real time (the steel slag is on the selected horizontal plane front and rear contour lines), and obtain the real-time thickness of the horizontal position slag layer based on the distance difference in the thickness direction of the front and back waveform curves (specifically, the average distance between the two contour lines is used as the real-time thickness of the horizontal position slag layer ).

Preferably, the distance between the laser profile sensor and the slag dumping area is between 1000mm and 8000mm, and the laser sampling frequency is greater than 100Hz, preferably between greater than 100Hz-100kHz. The higher the sampling frequency, the better the obtained slag has been poured. The more accurate the total slag content of the tank is, the frequency used is usually below 100kHz due to the limitations of the instrument itself. The ranging repeatability accuracy is less than 50μm, which is determined by the conditions of the laser profile sensor itself.

Preferably, in step S2, a free fall model and/or a fall motion model with an initial velocity is used, and real-time plane images are collected by a high-speed camera to obtain the area of the slag layer, and the thickness of the slag layer is compared with the time interval. Multiply the areas of the slag layers in the inner plane area to obtain the slag volume of the microlayer;

The frame rate of the high-speed camera is greater than 30FPS.

Preferably, the calculation of the area of the slag layer specifically includes the following steps:

S21. Obtain the real-time video stream of the slag layer in the vertical direction of thickness (Z direction in Figure 3) through the high-speed camera;

S22. Intercept the image of the slag flow area in the video stream;

S23. Binarize the image of the slag flow area, in which the pixel gray value of the background is 0 and the pixel gray value of the slag flow area is 1;

S24. Accumulate the pixel gray values in the slag flow area, and the obtained sum is the representation value of the area of the real-time micro-slag layer.

The slag flow area is a specific area selected in the slag dumping area.

Preferably, when the ladle is nearly horizontally inverted (the axis of the ladle deviates from the vertical direction at an angle of 0 to 10 degrees), the free fall model is used; when the ladle is tilted or inverted at a larger angle (the axis of the ladle deviates from the vertical direction) When the angle is greater than 10 degrees, preferably less than 20 degrees), the falling body motion model with initial velocity is used, The initial velocity is 0.01 to 0.3 meters/second, which is related to the inclination angle of the ladle. The greater the inclination angle, the greater the value of the initial velocity. When the tilt angle of the ladle is greater than 10 degrees, the initial velocity of the falling steel slag needs to take into account the influence of the static pressure of the molten steel in the ladle, so a falling motion model with initial velocity is used. When the tilt angle of the ladle is within 10 degrees, it is believed that the falling speed of the steel slag in the vertical direction is only affected by its own weight, so a free fall model is used.

Preferably, in step S3, the total slag amount is calculated by the following formula:

Another aspect of the present invention provides a real-time slag amount measurement system for automatic converter slag pouring, which includes:

converter;

A converter tipping driving device, which is connected to the converter and used to drive the converter to tilt and perform the slag dumping operation;

A converter inclination angle measuring device used to measure the inclination angle of the converter (the angle at which the axis of the converter deviates from the vertical direction);

A thickness gauge, used to measure the real-time thickness of the slag layer at any horizontal position in the slag dumping area when the converter performs the slag dumping operation;

An image collector used to collect the real-time video stream of the slag dumping area in the thickness vertical direction (vertical direction);

An image processing module to process the video stream into a planar image;

A storage module to store the video stream and the plane image;

An image recognition and calculation module, used to perform slag flow area image recognition on the plane image;

Control server system, which communicates with the converter, the converter tipping drive device, the converter inclination angle measuring device, the thickness gauge, the image collector, the image processing module, the storage module and the image The identification and calculation module is connected through network communication, and uses the free fall model or the falling motion model with initial velocity to multiply the thickness of the slag layer by the area of the slag layer in the plane area within the time interval to obtain The slag volume of the micro-layer is then multiplied by the density and conversion coefficient of the slag layer to obtain the slag amount of the micro-layer. The real-time slag amount of the micro-layer is continuously accumulated to obtain the total amount of slag that has been poured into the slag tank. Amount of slag;

The real-time measurement method of the slag amount of the converter's automatic slag pouring is realized through the real-time measurement system of the slag amount of the converter's automatic slag pouring.

Preferably, the thickness gauge uses two laser profile sensors, and the laser profile sensors are respectively located on Both sides of the slag dumping area are at the same level.

The distance between the laser profile sensor and the slag dumping area is 1000mm to 8000mm, the laser sampling frequency is greater than 100Hz, preferably greater than 100Hz-100kHz, and the ranging repeatability is less than 50μm;

The laser profile sensor is equipped with an air-cooled or water-cooled high-temperature protective cover and an air blowing smoke and dust removal device.

Preferably, the image collector uses a high-speed camera;

The frame rate of the high-speed camera is greater than 30FPS.

The invention provides a method and system for real-time measurement of slag amount for automatic converter slag pouring, which adopts a three-dimensional recognition technology that combines machine vision recognition of the two-dimensional slag image area and laser measurement of the third-dimensional thickness. During the slag pouring process, The amount of slag poured out of the converter can be obtained through the information of the slag dumping area, which effectively solves the time lag problem of slag truck weighing and the measurement problem of fast flowing slag thickness. It is operable, effective and practical in the actual implementation of converter automatic slag pouring technology, and can effectively improve the accuracy and control precision of intelligent identification technology.

Description of the drawings

Figure 1 is a schematic flow chart of the real-time measurement method of slag amount for automatic converter slag pouring according to the present invention;

Figure 2 is a schematic diagram of the layout of the laser profile sensor in the real-time measurement method of slag amount for automatic converter slag pouring according to the present invention;

Figure 3 is a photo of the automatic slag pouring process of the converter according to the present invention.

Detailed ways

In order to better understand the above technical solutions of the present invention, the technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and examples.

As shown in Figure 1, the present invention provides a real-time measurement method of slag amount for automatic slag pouring in a converter, including the following steps:

S2. Collect real-time plane images of the slag layer in the vertical direction of thickness (Z direction in Figure 3), multiply the thickness of the slag layer by the area of the slag layer in the plane micro-region within a small time interval, and obtain the slag volume of the micro-layer;

As shown in FIG. 2 , in the above step S1, when the ladle 100 pours slag into the slag tank 200, by pouring A laser profile sensor 1, 2 is arranged at the same horizontal position on both sides of the slag area to measure the front and rear waveform curves/contours of the slag dumping area in real time. The horizontal position is obtained based on the distance difference between the two front and rear waveform curves in the thickness direction. The real-time thickness of the slag layer.

Specifically, the above step S1 can be implemented as follows: obtaining the real-time thickness curve of the slag layer at any horizontal position in the slag dumping area (curves 1 and 2 in Figure 1). The width direction of the slag layer is marked as the X direction, and the thickness direction of the slag layer is marked as the Y direction (refer to Figure 3 for the area (the number of micro areas is between 10 and 1000), and the real-time thickness is the average of the thickness of multiple micro areas.

The horizontal distance between laser profile sensors 1 and 2 and the central axis of the slag dumping area is 1000mm to 8000mm, the laser sampling frequency is greater than 100Hz, and the ranging repeatability is less than 50μm. The thickness direction in the present invention is the connection direction of the two laser profile sensors.

As shown in Figure 2, in the above step S2, a high-speed camera is used to collect real-time plane images, and the area of the slag layer is obtained through a free fall model or a fall motion model with an initial velocity, and the thickness of the slag layer is compared with the plane within the time interval. The area of the slag layer in the region is multiplied to obtain the slag volume of the microlayer. The frame rate of the high-speed camera is greater than 30FPS.

The calculation of the area of the slag layer specifically includes the following steps:

S21. Obtain the real-time video stream of the slag layer in the vertical direction of thickness (Z direction in Figure 3) through a high-speed camera;

S22. Intercept the image of the slag flow area in the video stream (such as the dotted box area in Figure 3. The range of this area is adjustable. The area height is the distance the slag flow drops within the unit time interval. The height of the selected area is usually between 1mm and 20mm. The width of the area is greater than the maximum width of the slag flow distribution. Among them, unit time interval = 1000/actual frame rate of the camera);

S23. Binarize the image of the slag flow area (remove the background and leave only the slag flow. In addition, dynamic thresholding, gradient sharpening, morphological transformation, edge detection and other algorithms can also be used to process the image), The pixel gray value of the background is 0, and the pixel gray value of the slag flow area is 1;

S24. Accumulate the pixel grayscale values in the slag flow area, and the obtained sum is the representation value of the area of the real-time microlayer/slag layer.

The total slag amount can be calculated by multiplying and accumulating the representative value of the area of the microlayer/slag layer and the measured value of the slag thickness of the layer, and then multiplying it by the conversion coefficient and the slag density.

In addition, the conversion coefficient of the slag volume calculation model is corrected by the actual slag weight. The conversion coefficient is the difference between the actual slag weight and the measured The ratio of measuring slag weight, the value range is between 0.01 and 15.0, dimensionless. Specifically, the conversion coefficient can be specifically determined as follows in actual operation: use the real-time slag volume measurement method and system of the present invention to measure the weight of steel slag produced during, for example, 100 times of smelting, and obtain the actual slag weight of these 100 times of steel slag, The ratio of the average value of the actual slag weight to the average value of the measured slag weight is used as the conversion factor used to obtain the amount of slag dumped.

Continuing to refer to Figure 3, using image recognition technology can accomplish the following:

1) Obtain the slag width distribution size during the slag pouring process in real time. When the slag width is less than the set threshold, it is considered that the end point of slag pouring has been reached;

2) Based on the free fall model or the falling motion model with initial velocity, and through the real-time recognition results of high-speed cameras, the cumulative calculation of the slag amount is estimated, so as to meet the slag retention requirements for smelting.

When the ladle is nearly horizontally inverted (0 to 10 degrees), the free fall model is used to calculate the area of the slag layer; when the ladle is tilted or inverted at a large angle (greater than 10 degrees), the falling motion model with initial velocity is used to calculate the area of the slag layer. The area and initial velocity are 0.01 to 0.3 meters/second, which are related to the inclination angle of the ladle.

Therefore, the real-time values entering the slag amount image recognition area per unit time can be calculated and accumulated to obtain the final area of the slag layer.

In the free fall model, the velocity v of steel slag in the vertical direction changes with the falling time t as v=gt, g is the acceleration of gravity; the displacement h of the steel slag in the vertical direction changes with the falling time t as h=1 /2gt2.

Continuing to refer to Figure 3, depth Depth is the depth of the accumulation area calculated based on the time interval of the camera taking pictures, that is, the difference between the height value h1 entering the accumulation area and the height value h2 leaving the accumulation area, where V1 and V2 are respectively The slag velocity value entering and leaving the accumulation area; DT is the time interval value calculated based on the camera frame rate FPS (time interval = 1000/camera actual frame rate).

In step S3, the total slag amount is calculated by the following formula (1):

The invention also discloses a real-time measurement system for slag amount for automatic converter slag pouring, which includes:

converter;

The converter tipping driving device is connected to the converter to drive the converter to tilt and perform the slag dumping operation;

Converter inclination angle measuring device, used to measure the inclination angle of the converter;

Thickness gauge, used to measure the real-time thickness of the slag layer at any horizontal position in the slag dumping area when the converter performs slag dumping operation;

Image collector to collect real-time video stream of the dumped slag area in the vertical direction of thickness;

The image processing module processes the video stream into a flat image;

Storage module to store video streams and flat images;

The image recognition and calculation module is used to identify the slag flow area image on the plane image;

The control server system is connected to the converter, the converter tipping drive device, the converter inclination angle measuring device, the thickness gauge, the image collector, the image processing module, the storage module and the image recognition and calculation module through network communication, and through the free fall model or The falling body motion model with initial velocity multiplies the thickness of the slag layer by the area of the slag layer in the plane area within the time interval to obtain the slag volume of the micro-layer, and then multiplies the slag volume of the micro-layer with the density and conversion coefficient of the slag layer, Obtain the slag amount of the micro-layer, continuously accumulate the real-time slag amount of the micro-layer, and obtain the total slag amount that has been poured into the slag tank;

The real-time measurement method of the slag amount of the converter of the present invention for automatic slag pouring is realized by the real-time measurement system of the present invention for the automatic slag pouring of the converter.

The thickness gauge uses a laser profile sensor 1, two of which are located at the same horizontal position on both sides of the slag dumping area; the horizontal distance between the laser profile sensor and the central axis of the slag dumping area is 1000mm to 8000mm, and the laser sampling frequency is greater than 100Hz , the ranging repeatability is less than 50μm; the laser profile sensor is equipped with an air-cooled or water-cooled high-temperature protective cover and an air blowing smoke and dust removal device.

The image collector uses a high-speed camera; the frame rate of the high-speed camera is greater than 30FPS. The machine vision recognition of the two-dimensional slag image area is combined with the laser measurement of the third-dimensional thickness, and the implementation technology that combines high-speed communication network communication and three-dimensional recognition technology effectively solves the time lag problem of slag truck weighing. Moreover, the relative laser profile measurement technology on the same horizontal plane is used to effectively solve the problem of measuring the thickness of fast flowing slag.

Example 1

Two laser profile sensors are used, both with a sampling frequency of 120Hz, installed 5000mm away from the slag outlet, using a high-speed communication interface with a wavelength of 405nm;

Using a high-speed camera with a calibrated frame rate of 60fps, a black and white visible light camera with an infrared filter;

The molten steel in the converter weighs 250 tons, and the automatic slag pouring lasts for 85 seconds. The camera actually samples an image in about 20ms, and moves down 235 pixels in the image in 20ms, so the height of the selected slag flow area is 235 pixels. The width of the selected slag flow area is 1800 pixels. When calculating the slag thickness of the micro-layer, the width of the slag flow area is divided into 100 micro-areas, and the width of each micro-area is 18 pixels. The average value of the slag layer thickness in the 100 micro-areas is used as the slag thickness of the micro-layer. In this embodiment, the conversion factor is 1.1. Then the total volume of slag dumped is calculated as follows:

Calculate the weight of poured slag = total volume of poured slag × average density of slag = 8.304m ³ × 2.3 tons/m ³ = 19.1 tons,

The average density of slag in this embodiment is 2.3 tons/cubic meter, and the hit rate of slag dumping and slag retention is greater than 85%. Among them, the hit rate of slag dumping and slag retention is the proportion of the deviation between the measured slag weight and the actual slag weight within ±3 tons.

Example 2

The molten steel in the converter weighs 255 tons, and the automatic slag pouring takes a total of 79 seconds. The camera actually samples an image for about 20ms. If 20ms moves down 235 pixels in the image, the height of the selected slag flow area is 235 pixels. The width of the selected slag flow area is 1800 pixels. When calculating the slag thickness of the micro-layer, the width of the slag flow area is divided into 100 micro-areas, and the width of each micro-area is 18 pixels. The average value of the slag layer thickness in the 100 micro-areas is used as the slag thickness of the micro-layer. In this embodiment, the conversion factor is 1.1. Then the total volume of slag dumped is calculated as follows:

Calculate the weight of poured slag = total volume of poured slag × average density of slag = 8.043m ³ × 2.3 tons/m ³ = 18.5 tons.

The average density of slag in this embodiment is 2.3 tons/cubic meter, and the hit rate of slag dumping and slag retention is greater than 85%.

Example 3

The molten steel in the converter weighs 235 tons, and the automatic slag pouring lasts for 69 seconds. The camera actually samples an image in about 20ms, and moves down 235 pixels in the image in 20ms, so the height of the selected slag flow area is 235 pixels. The width of the selected slag flow area is 1800 pixels. When calculating the slag thickness of the micro-layer, the width of the slag flow area is divided into 100 micro-areas, and the width of each micro-area is 18 pixels. The average value of the slag layer thickness in the 100 micro-areas is used as the slag thickness of the micro-layer. In this embodiment, the conversion factor is 1.1. Then the total volume of slag dumped is calculated as follows:

Calculate the weight of poured slag = total volume of poured slag × average density of slag = 7.217m ³ × 2.3 tons/m ³ = 16.6 tons.

Those of ordinary skill in the art should realize that the above embodiments are only used to illustrate the present invention and are not used to limit the present invention. As long as they are within the scope of the essential spirit of the present invention, the above embodiments can be Changes and modifications will fall within the scope of the claims of the present invention.

Claims

A real-time measurement method of slag amount for automatic converter slag pouring, which is characterized by including the following steps:

S1. Obtain the real-time thickness of the slag layer at any horizontal position in the slag dumping area;

S2. Collect real-time planar images of the slag layer in the vertical direction of thickness, multiply the thickness of the slag layer by the area of the slag layer in the plane area within the time interval, and obtain the slag volume of the microlayer;

S3. Multiply the slag volume of the micro-layer by the density and conversion coefficient of the slag layer to obtain the slag amount of the micro-layer. Continuously add up the real-time slag amount of the micro-layer to obtain the total slag amount that has been poured into the slag tank.
The real-time measurement method of the slag amount of the converter automatic slag dumping according to claim 1, characterized in that: in the step S1, a laser profile sensor is arranged at the same horizontal position on both sides of the slag dumping area to measure the slag amount in real time. The front and rear waveform curves of the slag dumping area are measured, and the real-time thickness of the horizontal slag layer is obtained based on the distance difference in the thickness direction of the front and rear waveform curves.
The real-time measurement method of slag amount for automatic converter slag dumping according to claim 2, characterized in that: the distance between the laser profile sensor and the slag dumping area is between 1000mm and 8000mm, the laser sampling frequency is greater than 100Hz, and the distance measurement Repeat accuracy is less than 50μm.
The real-time measurement method of the slag amount of the converter for automatic slag pouring according to claim 1, characterized in that: in the step S2, a high-speed camera is used to collect real-time plane images, and the images are obtained through a free fall model or a fall motion model with initial velocity. For the area of the slag layer, multiply the thickness of the slag layer by the area of the slag layer in the plane area within the time interval to obtain the slag volume of the microlayer;

The frame rate of the high-speed camera is greater than 30FPS.
The real-time measurement method of slag amount for automatic converter slag pouring according to claim 4, wherein the calculation of the area of the slag layer specifically includes the following steps:

S21. Obtain the real-time video stream of the slag layer in the vertical direction of thickness through the high-speed camera;

S22. Intercept the image of the slag flow area in the video stream;

S23. Binarize the image of the slag flow area, in which the pixel gray value of the background is 0, so The pixel gray value in the slag flow area is 1;

S24. Accumulate the pixel gray values in the slag flow area, and the obtained sum is the representation value of the area of the real-time micro-slag layer.
The real-time measurement method of slag amount for automatic converter slag pouring according to claim 5, characterized in that: when the inversion angle of the ladle is 0 to 10 degrees, the free fall model is used; when the inversion angle of the ladle is greater than 10 degrees , using the falling body motion model with an initial velocity of 0.01 to 0.3 meters/second.
The real-time measurement method of slag amount for automatic converter slag pouring according to claim 1, characterized in that in step S3, the total slag amount is calculated by the following formula:
A real-time measurement system for slag quantity for automatic converter slag pouring, which is characterized by including:

converter;

A converter tipping driving device, which is connected to the converter and used to drive the converter to tilt and perform the slag dumping operation;

A converter inclination angle measuring device used to measure the inclination angle of the converter;

A thickness gauge, used to measure the real-time thickness of the slag layer at any horizontal position in the slag dumping area when the converter performs the slag dumping operation;

An image collector used to collect real-time video streams of the slag layer in the vertical direction of thickness;

An image processing module to process the video stream into a planar image;

A storage module to store the video stream and the plane image;

An image recognition and calculation module, used to perform slag flow area image recognition on the plane image;

Control server system, which communicates with the converter, the converter tipping drive device, the converter inclination angle measuring device, the thickness gauge, the image collector, the image processing module, the storage module and the image The identification and calculation module is connected through network communication, and uses the free fall model or the falling motion model with initial velocity to multiply the thickness of the slag layer by the area of the slag layer in the plane area within the time interval to obtain The slag volume of the microlayer is then multiplied by the density and conversion coefficient of the slag layer to obtain the microlayer. The amount of slag continuously accumulates the real-time slag amount of the micro-layer to obtain the total amount of slag that has been poured into the slag tank;

The real-time measurement method of the slag amount of the converter automatically pouring slag according to one of claims 1 to 7 is realized by the real-time measurement system of the slag amount of the converter automatically pouring slag.
The real-time slag amount measurement system for automatic converter slag dumping according to claim 8, characterized in that: the thickness gauge adopts two laser profile sensors, which are respectively located at the same horizontal position on both sides of the slag dumping area;

The distance between the laser profile sensor and the slag dumping area is between 1000mm and 8000mm, the laser sampling frequency is greater than 100Hz, and the ranging repeatability is less than 50μm;

The laser profile sensor is equipped with an air-cooled or water-cooled high-temperature protective cover and an air blowing smoke and dust removal device.
The real-time slag amount measurement system for automatic converter slag pouring according to claim 8, characterized in that: the image acquisition device adopts a high-speed camera;

The frame rate of the high-speed camera is greater than 30FPS.