Method and device for identifying molten steel at tail end of long nozzle

Abstract

The invention discloses a method and a device for identifying molten steel at the tail end of a long nozzle, which are used for identifying the molten steel so as to judge the starting time of an automatic control program of the liquid level of an intermediate tank: in the production process, shooting and uploading an image at the position of the long nozzle above the intermediate tank in real time, detecting whether the long nozzle exists in the image by using a deep learning target detection algorithm, and after it is detected that the long nozzle exists in the image, a molten steel area is extracted from the tail end of the long nozzle in the image through the image processing technology, whether the molten steel flows out normally or not is recognized, and when it is recognized that the molten steel flows out normally, an intermediate tank liquid level automatic control program is started. The method not only can automatically judge and start the automatic control of the liquid level of the intermediate tank, but also can reduce the working intensity of operators.

Description

Technical Field

[0001] The invention belongs to the field of steelmaking and continuous casting in the metallurgical industry, and specifically relates to a method and a device for identifying molten steel at the end of a long shroud. Background Art

[0002] The intermediate tank acts as a buffer device between the ladle and the crystallizer, which plays a role in regulating the flow of molten steel and maintaining a stable liquid level. Since multiple furnaces of molten steel are usually continuously cast during the production process, the ladle needs to be frequently replaced and the ladle needs to be re-cast. When the ladle is cast, the turntable turns the ladle to the casting position, and the robot puts the long nozzle on the sliding nozzle of the ladle, opens the sliding nozzle, and flows the molten steel into the intermediate tank. If no molten steel flows out, the long nozzle needs to be removed and oxygen needs to be burned. When the ladle is almost finished, it is manually or by the slag detection system to determine whether the molten steel has reached the slag layer. If slag is found, the sliding nozzle is closed, and then the long nozzle is removed to change the ladle.

[0003] In continuous casting production, more and more tundish liquid level automatic control technology is used for production. The existing tundish liquid level automatic control system cannot automatically adjust the working state of the liquid level control system according to the actual production situation due to the lack of external information acquisition. In the actual production process, the tundish liquid level must first meet the set value range requirements manually before entering the tundish liquid level automatic control. Not only can it not automatically determine to start the tundish liquid level automatic control, but the work intensity of the workers is also high. Summary of the invention

[0004] The purpose of the present invention is to provide a method for identifying molten steel at the end of a long shroud, and a device for identifying molten steel at the end of a long shroud based on the above-mentioned molten steel identification method. This method can not only automatically determine and start automatic control of the liquid level in the intermediate tank, but also reduce the workload of operators.

[0005] The technical solution adopted by the present invention is: A method for identifying molten steel at the end of a shroud is used to identify the molten steel and thus determine the timing for starting an automatic control program for the liquid level of an intermediate tank: during the production process, an image of the shroud position above the intermediate tank is photographed and uploaded in real time, and a deep learning target detection algorithm is used to detect whether there is a shroud in the image. After the shroud is detected in the image, the image processing technology is used to extract the molten steel area at the end of the shroud in the image and identify whether the molten steel is flowing out normally. When it is identified that the molten steel is flowing out normally, the automatic control program for the liquid level of the intermediate tank is started.

[0006] Furthermore, a set of programs for capturing images at the shroud position above the tundish, detecting the shroud, extracting the molten steel area, and identifying the molten steel is set as a recognition program. After the automatic control program of the tundish liquid level is turned on, the recognition program is stopped and the ladle pouring stage is entered. After that, the large ladle is lowered to a low position and the shroud is extended into the tundish until the ladle changing stage is entered, at which time the recognition program is started again.

[0007] Furthermore, a method for identifying molten steel using image processing technology is: first extracting a ROI area at the end of a long water nozzle in the image for subsequent molten steel identification, and then performing grayscale processing, binarization processing, morphological opening operation, and connected domain processing on the ROI area in turn, thereby extracting the molten steel area, and finally identifying whether the molten steel flows out normally based on the shape and size of the molten steel area.

[0008] Furthermore, a model building method for a deep learning target detection algorithm for detecting whether there is a long shroud in an image is as follows: first, a number of original images are taken at the long shroud position above the intermediate tank under different working conditions, and then a data set is produced after preprocessing the images, and then a neural network is trained with the goal of detecting the long shroud, and then the optimal model is saved.

[0009] A device for identifying molten steel at the end of a long shroud is used to identify molten steel and thus determine the timing of starting an automatic control program for the liquid level of an intermediate tank, comprising an industrial camera and a controller; the industrial camera is used to photograph the position of the long shroud above the intermediate tank and upload the photograph to the controller; the controller adopts the control strategy of the method for identifying molten steel at the end of the long shroud, controls the operation of the industrial camera according to the control strategy, and is electrically connected to a control module of the automatic control program for the liquid level of the intermediate tank, and uploads the detection result of whether the long shroud exists and the recognition result of whether the molten steel flows out normally to the control module, and the control module starts the automatic control program for the liquid level of the intermediate tank when it is recognized that the molten steel flows out normally.

[0010] Furthermore, the industrial camera is installed at the base of the turntable and is equipped with high temperature protection measures.

[0011] The beneficial effects of the present invention are: This method uses a deep learning target detection algorithm to detect the long shroud, and can quickly and accurately detect the long shroud; because the molten steel flows into the tundish through the long shroud, that is, the position of the molten steel is below the long shroud, this method first detects whether there is a long shroud, and then extracts the molten steel area at the end of the long shroud in the image, which can quickly and accurately locate the range of the molten steel, thereby reducing the interference of other highlighted targets in the background and achieving accurate segmentation of the molten steel; this method can automatically obtain the status of the long shroud and the molten steel, and determine the timing of starting the automatic control program of the tundish liquid level by identifying the molten steel, without the need for manual intervention throughout the process, and can automatically determine the start of the automatic control of the tundish liquid level and reduce the workload of the operator. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a schematic diagram of the process of the method for identifying molten steel at the end of a long nozzle and the corresponding image in an embodiment of the present invention.

[0013] Figure 2 It is a schematic diagram of the process of model establishment and use of the deep learning target detection algorithm in the present invention.

[0014] Figure 3 It is a schematic diagram of the process of identifying molten steel in the ROI area and the corresponding image in the present invention. DETAILED DESCRIPTION

[0015] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0016] Embodiment 1 This embodiment provides a method for identifying molten steel at the end of a long shroud, which is used to identify molten steel and thus determine the start time of the automatic control program of the liquid level in the intermediate tank: during the production process, such as Figure 1 As shown, an image of the long shroud position above the intermediate tank is photographed and uploaded in real time, and a deep learning target detection algorithm is used to detect whether there is a long shroud in the image. After the long shroud is detected in the image, the molten steel area is extracted at the end of the long shroud in the image by using image processing technology and whether the molten steel flows out normally. When it is identified that the molten steel flows out normally, the automatic control program of the liquid level of the intermediate tank is started. This method uses a deep learning target detection algorithm to detect the long shroud, which can quickly and accurately detect the long shroud; since the molten steel flows into the intermediate tank through the long shroud, that is, the position of the molten steel is below the long shroud, this method adopts the method of first detecting whether there is a long shroud and then extracting the molten steel area at the end of the long shroud in the image, which can quickly and accurately locate the range of the molten steel, thereby reducing the interference of other bright targets in the background and realizing accurate segmentation of the molten steel; this method can automatically know the state of the long shroud and the molten steel, and judge the start time of the automatic control program of the liquid level of the intermediate tank by identifying the molten steel, without manual intervention throughout the process, which can not only automatically judge and start the automatic control of the liquid level of the intermediate tank, but also reduce the work intensity of the operator.

[0017] Suppose a set of programs for shooting images at the long nozzle position above the tundish, detecting the long nozzle, extracting the molten steel area, and identifying the molten steel is a recognition program. Regarding the start and stop timing of the recognition program, in this embodiment: after the automatic control program of the liquid level of the tundish is turned on, the recognition program is stopped and the ladle pouring stage is entered. After that, the large ladle is lowered to a low position and the long nozzle is extended into the tundish until the ladle changing stage is entered, and the recognition program is started again; the recognition program works in the production process, and it is stopped after the automatic control program of the liquid level of the tundish is turned on and started in the ladle changing stage. It is only started to identify the molten steel at key nodes to avoid disorderly consumption.

[0018] The model building method of the deep learning target detection algorithm for detecting whether there is a long water outlet in the image is: Figure 2 As shown, several original images are first taken at the position of the long shroud above the tundish under different working conditions, and then the images are preprocessed to produce a data set. Then, a neural network is trained with the goal of detecting the long shroud, and then the optimal model is saved.

[0019] The method of using image processing technology to identify molten steel is: Figure 3 As shown, the ROI area is first extracted at the end of the long nozzle in the image for subsequent molten steel recognition, and then the ROI area is processed by grayscale, binarization, morphological opening, and connected domain processing in sequence to extract the molten steel area. Finally, whether the molten steel flows out normally is identified based on the shape and size of the molten steel area.

[0020] Embodiment 2 The present embodiment provides a device for identifying molten steel at the end of a long shroud, which is used to identify molten steel and thus determine the timing for starting an automatic control program for the liquid level in an intermediate tank: it comprises an industrial camera and a controller; the industrial camera is used to photograph the position of the long shroud above the intermediate tank and upload the photograph to the controller; the controller adopts the control strategy of the method for identifying molten steel at the end of the long shroud in the first embodiment, and controls the operation of the industrial camera according to the control strategy, and is electrically connected to a control module (generally a PLC controller) of the automatic control program for the liquid level in the intermediate tank, and uploads the detection result of whether there is a long shroud and the recognition result of whether the molten steel is flowing out normally to the control module, and the control module starts the automatic control program for the liquid level in the intermediate tank when it is recognized that the molten steel is flowing out normally.

[0021] In order to prevent high temperature from harming the camera, the industrial camera is installed on the base of the turntable and is equipped with high temperature protection measures.

[0022] The embodiments described above are part of the embodiments of the present application, rather than all of the embodiments. The detailed description of the embodiments of the present application is not intended to limit the scope of the present application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

Claims

1. A method for identifying molten steel at the end of a long nozzle, characterized in that: Used to identify molten steel and thus determine when to start the automatic control program for the liquid level in the intermediate tank: During the production process, an image of the shroud position above the intermediate tank is captured and uploaded in real time. A deep learning target detection algorithm is used to detect whether there is a shroud in the image. After the shroud is detected in the image, image processing technology is used to extract the molten steel area at the end of the shroud in the image and identify whether the molten steel is flowing out normally. When it is identified that the molten steel is flowing out normally, the automatic control program for the liquid level in the intermediate tank is started.

2. The method for identifying molten steel at the end of a shroud as claimed in claim 1, characterized in that: A set of programs for capturing images at the shroud position above the tundish, detecting the shroud, extracting the molten steel area, and identifying the molten steel is assumed to be the identification program. After the automatic control program of the tundish liquid level is turned on, the identification program is stopped and the ladle pouring stage is entered. After that, the large ladle is lowered to a low position and the shroud is extended into the tundish until the ladle changing stage is entered, at which time the identification program is started again.

3. The method for identifying molten steel at the end of a shroud as claimed in claim 1, characterized in that: The method of identifying molten steel using image processing technology is: first extract the ROI area at the end of the long nozzle in the image for subsequent molten steel identification, then perform grayscale processing, binarization processing, morphological opening operation, and connected domain processing on the ROI area in turn, so as to extract the molten steel area, and finally identify whether the molten steel flows out normally according to the shape and size of the molten steel area.

4. The method for identifying molten steel at the end of a shroud as claimed in claim 1, characterized in that: The model building method of the deep learning target detection algorithm for detecting whether there is a long shroud in an image is: first, take a number of original images at the long shroud position above the tundish under different working conditions, then pre-process the images to create a data set, then train the neural network with the goal of detecting the long shroud, and then save the optimal model.

5. A device for identifying molten steel at the end of a long shroud, characterized in that: The method is used for identifying molten steel and thus determining when to start an automatic control program for the liquid level of an intermediate tank, and comprises an industrial camera and a controller; the industrial camera is used for photographing the position of the long shroud above the intermediate tank and uploading the photograph to the controller; the controller adopts the control strategy of the method for identifying molten steel at the end of the long shroud as described in any one of claims 1 to 4, and controls the operation of the industrial camera according to the control strategy, and is electrically connected to a control module of the automatic control program for the liquid level of the intermediate tank, and uploads the detection result of whether the long shroud exists and the identification result of whether the molten steel flows out normally to the control module, and the control module starts the automatic control program for the liquid level of the intermediate tank when it is identified that the molten steel flows out normally.

6. The device for identifying molten steel at the end of a shroud as claimed in claim 5, characterized in that: The industrial camera is installed at the base of the turntable and is equipped with high temperature protection measures.

Images