Converter mouth splashing identification method

Abstract

The invention relates to a converter mouth splashing identification method, and belongs to the technical field of steelmaking methods. According to the technical scheme, a high-definition camera is used for obtaining video data, image preprocessing is conducted, the form and contour of a furnace mouth slag overflowing area in a first frame image of the video are detected, a mask image with the same size as the slag overflowing area is established, masks are applied to the whole video, a brightness threshold value is set, and the number of pixels, exceeding the brightness threshold value, of the slag overflowing area is calculated; and rating the slag overflow state according to the number of pixels. The method has the beneficial effects that the slag overflow video is acquired by utilizing the high-definition camera at the converter mouth, and the slag overflow grade of the converter mouth is acquired by calculating the number of pixels in the slag overflow area at the converter mouth, so that reliable data are provided for operators to adjust process parameters, and the quality of the converter mouth is improved. According to the slag overflow time and the slag overflow amount, the cause of the slag overflow phenomenon is analyzed and predicted, so that the process control is optimized, and the smelting quality is improved.

Description

Technical Field

[0001] The present invention relates to a method for identifying splashing at the converter mouth, belonging to the technical field of steelmaking methods. Background Art

[0002] In the iron and steel industry, the production and processing of steel plates is an important link. With the continuous advancement of industrial automation, in order to prevent the steel plates in the heat treatment furnace from colliding, traditional workshops often increase the distance between steel plates to improve production efficiency, and the method of manually measuring the size of steel plates gradually fails to meet the requirements of high-efficiency and precise production. Manual measurement is easily affected by subjective factors, such as the fatigue of measurement personnel, differences in operation skills, etc., resulting in large measurement errors. Moreover, manual measurement is slow, which will become a bottleneck in production efficiency on a large-scale steel plate production line.

[0003] Computer vision technology has made great progress in recent years. High-speed and high-resolution industrial cameras have emerged continuously, which can clearly capture the images of steel plates. Summary of the Invention

[0004] The object of the present invention is to provide a method for identifying splashing at the converter mouth. By using a high-definition camera at the converter mouth to obtain the slag overflow video, and calculating the number of pixels in the slag overflow area at the furnace mouth, the slag overflow level at the furnace mouth is obtained, so as to provide reliable data for operators to adjust process parameters, analyze the reasons for the slag overflow phenomenon based on the slag overflow time and the amount of slag overflow, and predict it, so as to optimize process control, improve smelting quality, and effectively solve the above problems existing in the background art.

[0005] The technical solution of the present invention is: a method for identifying splashing at the converter mouth, comprising the following steps: S1: Obtain video data by using a high-definition camera, and enter step S2; S2: Perform image preprocessing, and enter step S3; S3: Detect the shape and contour of the slag overflow area at the furnace mouth in the first frame image of the video, and enter step S4; S4: Establish a mask image with the same size as the slag overflow area, and enter step S5; S5: Apply the mask to the entire video, and enter step S6; S6: Set the brightness threshold, calculate the number of pixels in the slag overflow area that exceed the brightness threshold, and enter step S7; S7: Rate the slag overflow state according to the number of pixels.

[0006] In the above step S1, the high-definition camera is of the RGB-D type.

[0007] In step S2, the image preprocessing includes image normalization, grayscale conversion, and binarization, which are implemented through the normalize(), cvtColor(), and threshold() functions of the OpenCV library respectively.

[0008] In step S3, detect the shape and contour of the slag overflow area at the furnace mouth in the first frame image of the video, including selecting the coordinates of the irregular slag overflow area.

[0009] In step S4, mark the selected slag overflow area as the target area with 1, and mark the remaining areas with 0.

[0010] In step S5, apply the mask to the entire video, including paying attention to the target area in each frame image of the video.

[0011] In step S6, iterate the slag overflow image at the furnace mouth and select a specific threshold.

[0012] In step S7, set different threshold construction interval ranges.

[0013] The beneficial effects of the present invention are as follows: By using a high-definition camera at the converter furnace mouth to obtain the slag overflow video, and calculating the number of pixels in the slag overflow area at the furnace mouth to obtain the slag overflow level at the furnace mouth, reliable data is provided for operators to adjust process parameters, analyze the causes of the slag overflow phenomenon based on the slag overflow time and the amount of slag overflow, and predict it, so as to optimize process control and improve smelting quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is the flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0015] In order to make the objectives, technical solutions, and advantages of the invention implementation cases clearer, the technical solutions in the invention implementation cases will be clearly and completely described below in conjunction with the accompanying drawings in the implementation cases. Obviously, the described implementation cases are a small part of the implementation cases of the present invention, rather than all the implementation cases. Based on the implementation cases of the present invention, all other implementation cases obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0016] A converter furnace mouth splash identification method includes the following steps: S1: Obtain video data using a high-definition camera and enter step S2; S2: Image preprocessing and enter step S3; S3: Detect the shape and contour of the slag overflow area at the furnace mouth in the first frame image of the video and enter step S4; S4: Create a mask image with the same size as the slag overflow area, and proceed to step S5; S5: Apply the mask to the entire video, and proceed to step S6; S6: Set the brightness threshold, calculate the number of pixels in the slag overflow area that exceed the brightness threshold, and proceed to step S7; S7: Rate the slag overflow status based on the number of pixels.

[0017] In step S1, the high-definition camera is of the RGB-D type.

[0018] In step S2, the image preprocessing includes image normalization, grayscale conversion, and binarization, which are respectively implemented through the normalize(), cvtColor(), and threshold() functions of the OpenCV library.

[0019] In step S3, detect the shape and contour of the slag overflow area at the furnace mouth in the first frame image of the video, including selecting the coordinates of the irregular slag overflow area.

[0020] In step S4, mark the selected slag overflow area as the target area with 1, and mark the remaining areas with 0.

[0021] In step S5, applying the mask to the entire video includes paying attention to the target area in each frame of the video.

[0022] In step S6, iterate through the slag overflow image at the furnace mouth and select a specific threshold.

[0023] In step S7, set different thresholds to construct an interval range.

[0024] In practical applications, the present invention uses a high-definition camera to obtain video data; performs image preprocessing; detects the shape and contour of the slag overflow area at the furnace mouth in the first frame image of the video; creates a mask image with the same size as the slag overflow area; applies the mask to the entire video; sets the brightness threshold, calculates the number of pixels in the slag overflow area that exceed the brightness threshold; and rates the slag overflow status based on the number of pixels. On the basis of ensuring production safety, the present invention can provide key data support for operators by conducting in-depth analysis of the slag overflow time and slag overflow volume, enabling them to take corresponding measures in a timely and accurate manner, optimize and adjust the process parameters, thereby effectively improving production efficiency and promoting the scientific and refined management of the production process. Embodiment

[0025] A converter furnace mouth slag overflow recognition method provided by an embodiment of the present invention includes the following steps: S1: Use a high-definition camera to obtain video data, and proceed to step S2; S2: Perform image preprocessing, and proceed to step S3; S3: Detect the shape and contour of the slag overflow area in the first frame image of the video, and proceed to step S4; S4: Create a mask image with the same size as the slag overflow area, and proceed to step S5; S5: Apply the mask to the entire video, and proceed to step S6; S6: Set the brightness threshold, calculate the number of pixels in the slag overflow area that exceed the brightness threshold, and proceed to step S7; S7: Rate the slag overflow status based on the number of pixels; The present invention uses an RGB-D camera to capture packet number data, and divides the slag overflow level by the number of pixels. Analyze the reasons for the slag overflow phenomenon based on the time and amount of slag overflow, and make predictions for it. Thus, optimize the process control and improve the smelting quality.

[0026] Specifically, the high-definition camera in step S1 is of the RGB-D type, and the function to read the camera is cv2.VideoCapture().

[0027] The image preprocessing in step S2 includes image normalization, grayscale conversion, and binarization, which are respectively implemented through the normalize(), cvtColor(), and threshold() functions of the OpenCV library.

[0028] In step S3, detecting the shape and contour of the slag overflow area in the first frame image of the video includes selecting the coordinates of the irregular slag overflow area.

[0029] It should be noted that the selection of the coordinates of the slag overflow area is drawn by using mouse interaction, and the extracted coordinates are saved in a list.

[0030] In step S4, creating a mask image with the same size as the slag overflow area includes marking the selected slag overflow area as the target area with 1 and the remaining areas with 0.

[0031] It should be noted that the creation of the mask is through the bitwise_and() function in the OpenCV library. This function is used to perform a bitwise AND operation. Take two input images as parameters and perform a bitwise AND operation on their corresponding pixels.

[0032] In step S5, applying the mask to the entire video includes focusing on the target area of each frame image in the video.

[0033] In step S6, setting the brightness threshold and calculating the number of pixels in the slag overflow area that exceed the brightness threshold includes iterating over the slag overflow image at the furnace mouth and selecting a specific threshold.

[0034] In step S7, the overflow slag state is rated according to the number of pixels, including setting different threshold construction ranges and setting corresponding thresholds according to different furnace mouths.

Claims

1. A method for identifying the splashing at the converter mouth, characterized in that It includes the following steps: S1: Obtain video data using a high-definition camera and proceed to step S2; S2: Perform image preprocessing and proceed to step S3; S3: Detect the shape and contour of the slag overflow area at the furnace mouth in the first-frame image of the video and proceed to step S4; S4: Establish a mask image with the same size as the slag overflow area and proceed to step S5; S5: Apply the mask to the entire video and proceed to step S6; S6: Set a brightness threshold, calculate the number of pixels in the slag overflow area that exceed the brightness threshold, and proceed to step S7; S7: Rate the slag overflow status based on the number of pixels.

2. The method for identifying the splash at the converter mouth according to claim 1, wherein: In step S1, the high-definition camera is of the RGB-D type.

3. A converter mouth splashing recognition method according to claim 1, characterized in that: In step S2, the image preprocessing includes image normalization, grayscale conversion, and binarization, which are respectively implemented through the normalize(), cvtColor(), and threshold() functions of the OpenCV library.

4. A converter mouth splashing recognition method according to claim 1, characterized in that: In step S3, detecting the shape and contour of the slag overflow area at the furnace mouth in the first-frame image of the video includes selecting the coordinates of the irregular slag overflow area.

5. A converter mouth splashing recognition method according to claim 1, characterized in that: In step S4, the selected slag overflow area is marked as the target area with 1, and the remaining areas are marked as 0.

6. The converter mouth splash identification method according to claim 1, characterized in that: In step S5, applying the mask to the entire video includes paying attention to the target area in each frame of the video.

7. A converter mouth splashing recognition method according to claim 1, characterized in that: In step S6, iterate the furnace mouth slag overflow image and select a specific threshold.

8. A converter mouth splashing recognition method according to claim 1, characterized in that: In step S7, set different thresholds to construct an interval range.

Images