Real-time detection control method and system for blast furnace tap hole state

Abstract

The invention belongs to the technical field of blast furnace ironmaking, and provides a blast furnace taphole state real-time detection control method and system, and the method comprises the steps: collecting the image information of a taphole in real time by using a high-speed camera; the obtained image is preprocessed through an image recognition algorithm, the circumscribed rectangle area of the contour of the molten iron splashing area is obtained, and the splashing amplitude area is obtained by calculating the circumscribed rectangle area; analyzing and comparing the splashing amplitude area with a preset threshold area to obtain a splashing abnormal signal; the splashing abnormal signal is processed to obtain a tap hole abnormal state value, and the tap hole abnormal state value and a tap hole state abnormal threshold value are compared and analyzed to generate an alarm signal; on the basis of analysis of the alarm signal, influence parameters influencing the opening state are obtained, and regulation and control parameters are obtained by processing the influence parameters; and controlling the tapping hole state in real time by using the regulation and control parameters.

Description

Technical Field

[0001] The present invention belongs to the technical field of blast furnace ironmaking, and specifically relates to a method and system for real-time detection and control of the state of the blast furnace taphole. Background Art

[0002] In the process of smelting waste gas and slag in iron and steel enterprises, the taphole is a crucial link; the smooth discharge of molten iron directly affects the production efficiency and product quality of the blast furnace; however, currently, during the taphole opening process, the problem of molten iron splashing is often faced; molten iron splashing not only poses a threat to the safety of operators, but also causes waste of molten iron, damage to equipment, and interruption of the production process.

[0003] The existing blast furnace taphole opening operations mainly rely on the experience of operators and some simple detection means, such as observing the state of molten iron flowing out, measuring the depth of the taphole, etc.; these methods are difficult to accurately and real-time detect the change in the splashing amplitude of molten iron, and cannot timely and effectively adjust the operation parameters of blast furnace ironmaking to control the splashing amplitude of molten iron.

[0004] Therefore, the present invention provides a method and system for real-time detection and control of the state of the blast furnace taphole. Summary of the Invention

[0005] In order to make up for the deficiencies of the prior art and solve at least one of the technical problems proposed in the background art.

[0006] The technical solution adopted by the present invention to solve its technical problems is as follows:

[0007] In a first aspect, the present invention provides a method for real-time detection and control of the state of the blast furnace taphole, including the following steps:

[0008] S1: Use a high-speed camera to collect image information of the taphole in real time;

[0009] S2: Through an image recognition algorithm, preprocess the obtained image to obtain the splashing amplitude area;

[0010] S3: Analyze the splashing amplitude area to obtain a splashing abnormal signal; process the splashing abnormal signal to obtain the abnormal state value of the taphole;

[0011] S4: Compare and analyze the abnormal state value of the taphole with the abnormal threshold of the taphole state to generate an alarm signal;

[0012] S5: Based on the analysis of the alarm signal, obtain the influencing parameters that affect the opening state, and obtain the control parameters through the processing of the influencing parameters;

[0013] S6: Use the control parameters to perform real-time control on the state of the taphole.

[0014] In a second aspect, the present invention provides a real-time detection and control system for the state of a blast furnace taphole, including the following modules:

[0015] Real-time image acquisition module: Use a high-speed camera to collect image information of the taphole in real time;

[0016] Image recognition and processing module: Use image recognition algorithms to calculate and monitor the splash amplitude of molten iron; after completing image segmentation to obtain the molten iron splash area, further extract the contour of the molten iron splash area; obtain the splash amplitude area by calculating the area of the circumscribed rectangle of the contour of the molten iron splash area;

[0017] Image analysis module: Analyze and compare the splash amplitude area with a preset threshold area. If the splash amplitude area is greater than the preset threshold area, it indicates that there is a splash phenomenon at the taphole, and a splash anomaly signal is generated; mark the time period when the splash anomaly signal appears as the splash anomaly period, divide the splash anomaly period into several time analysis nodes, obtain the splash amplitude area at each time analysis node, sum and take the average value to obtain the average splash amplitude area within the splash anomaly period, perform a difference process on the average splash amplitude area and the preset threshold area, and then perform a ratio process with the preset threshold area; perform a product process on the splash amplitude area anomaly ratio and the splash anomaly duration ratio to obtain the taphole abnormal state value;

[0018] Real-time alarm module: Compare and analyze the taphole abnormal state value with the taphole state abnormal threshold. If the taphole abnormal state value is greater than the taphole state abnormal threshold, it indicates that the taphole state is abnormal, and an alarm signal is generated;

[0019] Control preprocessing module: Based on the alarm signal, obtain the change curve of the operating parameters over time to obtain the operating parameter curve, calculate the correlation between the splash change curve and the operating parameter curve, and use the formula to calculate the correlation value; then determine the influencing parameters affecting the opening state by analyzing the correlation value; then determine the influencing parameters affecting the opening state by analyzing the correlation value; if the correlation value is greater than or equal to the correlation threshold, it indicates that the operating parameter is an influencing parameter; obtain the variance index based on the influencing parameter; if the variance index value is less than the variance index threshold, it indicates that the operating parameter corresponding to the variance has a linear relationship with the splash amplitude and is a control parameter;

[0020] Control module: Based on the control parameter, use the formula: to obtain the control range T of the control parameter; where H is the slope ratio and C is the splash amplitude area exceeding the splash threshold when the taphole abnormal alarm occurs; calculate the value of the control range T of the control parameter; adjust the operating parameters of the blast furnace according to the value of the control range T of the control parameter until the taphole state returns to normal.

[0021] The beneficial effects of the present invention are as follows: During the smelting of waste gas and slag in iron and steel enterprises, by real-time monitoring the state of the taphole, abnormal situations of molten iron splashing can be detected in a timely manner and an alarm can be issued, enabling operators to take protective measures in advance, effectively reducing the harm of molten iron splashing to operators and equipment, and reducing the probability of safety accidents. By using advanced image recognition algorithms and data processing methods, the splashing amplitude of molten iron is accurately calculated to achieve precise monitoring of the splashing amplitude. By adjusting the operating parameters of the blast furnace, precise control of the splashing amplitude of molten iron is achieved, reducing the waste of molten iron and thus improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The present invention will be further described below with reference to the accompanying drawings.

[0023] Figure 1 is a flowchart of the steps of a method for real-time detection and control of the state of the taphole of a blast furnace provided by the present invention;

[0024] Figure 2 is a system module diagram of a system for real-time detection and control of the state of the taphole of a blast furnace provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] In order to make the technical means, creative features, achieved purposes and functions of the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.

[0026] Embodiment 1

[0027] As Figure 1 shown, a method for real-time detection and control of the state of the taphole of a blast furnace according to an embodiment of the present invention includes the following steps:

[0028] S1: Use a high-speed camera to collect image information of the taphole in real time; wherein, the high-speed camera continuously captures taphole images at a fixed frame rate to ensure real-time monitoring of the taphole state;

[0029] S2: Analyze the images captured by the high-speed camera through an image recognition algorithm to accurately calculate the splashing amplitude area of the molten iron; analyze and compare the splashing amplitude area with a preset threshold area to obtain a splashing abnormal signal;

[0030] Based on the images captured by the high-speed camera, preprocess the obtained images;

[0031] Specifically, use an image recognition algorithm to calculate and monitor the splashing amplitude of the molten iron; after completing image segmentation to obtain the molten iron splashing area, further extract the contour of the molten iron splashing area; obtain the splashing amplitude area by calculating the area of the circumscribed rectangle of the contour of the molten iron splashing area;

[0032] First, the image is grayscale processed, and each pixel is represented by a grayscale value. Then, the grayscale histogram of the image is calculated to find the threshold between the two peaks in the histogram.

[0033] The specific formula is: G(t) = W1(t)(u1(t) - ut) 2 + W2(t)(u2(t) - ut) 2 The between-class variance G is calculated; where u1 is the average grayscale of the foreground, u2 is the average grayscale of the background, ut is the average grayscale of the image, and W1(t) and W2(t) are the proportions of the foreground and background pixel numbers to the total pixel number respectively; the threshold t is a variable that can be used as a threshold, and all possible between-class variances G are calculated. The t that makes the between-class variance G maximum is the threshold t.

[0034] Based on the threshold t, the binary image is processed, and the grayscale value of each pixel in the image is compared with the threshold; if the grayscale value of the pixel in the image is greater than or equal to the threshold t, it is the hot metal part; if the grayscale value of the pixel in the image is less than the threshold t, it is the non-hot metal part.

[0035] For the segmented binary image, starting from the upper left corner of the image, scan the image row by row and column by column to find the edge points of the hot metal splash area; when encountering a point where the pixel value changes from the background value to the splash area value or from the splash area value to the background value, record it as an edge point.

[0036] Starting from a found edge point, follow along the edge points in a certain direction until returning to the starting point to form a closed contour.

[0037] Determine the coordinate range of the contour, record the maximum value Xmax and minimum value Xmin of the abscissa; the maximum value Ymax and minimum value Ymin of the ordinate; the width W of the circumscribed rectangle = Xmax - Xmin, and the height H of the circumscribed rectangle = Ymax - Ymin.

[0038] Calculate the area C of the circumscribed rectangle of the hot metal splash area contour according to the formula C = W × H; that is the splash amplitude area.

[0039] S3: Analyze and compare the splash amplitude area with the preset threshold area; it should be noted that the preset threshold area is a value with reference value obtained by technicians in this industry based on historical production experience.

[0040] If the splash amplitude area is less than or equal to the preset threshold area, it indicates that there is no splash phenomenon at the taphole and no treatment is required.

[0041] If the splash amplitude area is greater than the preset threshold area, it indicates that there is a splash phenomenon at the taphole, and a splash anomaly signal is generated.

[0042] Obtain the occurrence duration t of the splashing abnormal signal within the total production cycle duration T; and perform a ratio process with the total production cycle duration T, as shown in the formula: Obtain the splashing abnormal duration ratio A;

[0043] Mark the time period when the splashing abnormal signal appears as the splashing abnormal period, divide the splashing abnormal period into several time analysis nodes, obtain the splashing amplitude area at each time analysis node, sum and take the average value to obtain the average splashing amplitude area within the splashing abnormal period. After performing a difference process on the average splashing amplitude area and the preset threshold area, and then performing a ratio process with the preset threshold area, as shown in the formula: As shown, obtain the splashing amplitude area abnormal ratio F, where SN represents the splashing amplitude area at the Nth time analysis node, N represents the number serial number of the time analysis node, and S represents the preset threshold area;

[0044] Perform a multiplication process on the splashing amplitude area abnormal ratio F and the splashing abnormal duration ratio A to obtain the abnormal state value of the taphole;

[0045] S4: Compare and analyze the abnormal state value of the taphole with the abnormal threshold of the taphole state; it should be noted that the abnormal threshold of the taphole state is a reference value obtained by technicians in this industry based on historical production experience;

[0046] If the abnormal state value of the taphole is less than or equal to the abnormal threshold of the taphole state, it indicates that the taphole state is normal, and the splashing phenomenon belongs to an accidental situation, without any treatment;

[0047] If the abnormal state value of the taphole is greater than the abnormal threshold of the taphole state, it indicates that the taphole state is abnormal, and then generate an alarm signal;

[0048] In the steps of this embodiment, the molten iron splashing images are continuously captured by a high-speed camera at a fixed frame rate, and each frame of image is processed in real time according to the above image processing and abnormal calculation process of the taphole state; compare the calculated abnormal state value of the taphole with the preset abnormal threshold of the taphole state to judge the state of the taphole and generate an alarm signal; remind the operator to pay attention to the state of the taphole in real time; compared with the existing technical state, it gets rid of the need for the operator to rely on technical experience to judge the state of the taphole, and at the same time realizes the real-time detection of the taphole state, improving the production efficiency;

[0049] Embodiment 2

[0050] S5: Based on the alarm signal, obtain the operating parameters of blast furnace ironmaking during the time period when the abnormal state of the taphole occurs; the operating parameters include, but are not limited to, top pressure, internal furnace pressure, hot blast pressure, hot metal temperature, top temperature, internal furnace temperature, and gas flow rate; at the same time, obtain the curve of the change of the splash amplitude area over time during the abnormal state time period of the taphole to obtain the splash change curve, where the horizontal axis is time and the vertical axis is area; obtain the curve of the change of any operating parameter over time to obtain the operating parameter curve, and calculate the correlation between the splash change curve and the operating parameter curve to determine the correlation value; then judge the influencing parameters affecting the opening state by analyzing the correlation value.

[0051] Based on any operating parameter, obtain the curve of the change of the operating parameter over time; preprocess the obtained curve of the change of the operating parameter over time to ensure that the time axis data points of the two curves are exactly corresponding, that is, for each time point, there is a corresponding splash amplitude area value and operating parameter value; make the two curves comparable in time.

[0052] Divide the total production cycle duration T into several i production nodes, and according to the splash change curve and the operating parameter curve, obtain the operating parameters and splash amplitude areas at different production nodes to form an operating data group and a splash data group; among them, the operating data group is (X1, X2, X3......Xi), and the splash data group is (Y1, Y2, Y3......Yi).

[0053] Use the Pearson correlation coefficient to process the operating data group and the splash data group. Specifically: through the formula Calculate to obtain the correlation value; where Xi is the operating parameter at the i-th production node in the operating data group, and Yi is the splash amplitude area at the i-th production node in the splash data group.

[0054] It should be noted that the value range of the correlation value is between -1 and 1, and the closer the absolute value is to 1, the stronger the correlation.

[0055] Using the Pearson correlation coefficient calculation, there is no need to analyze the correlation of two curves with different dimensions in the same coordinate system. Just ensure that the time axis data points of the two curves are exactly corresponding, and the correlation of the two curves can be analyzed quickly and accurately.

[0056] Based on all operating parameter data, calculate its Pearson correlation coefficient to obtain the correlation value; compare and analyze the absolute value of the correlation value with the correlation threshold.

[0057] It should be noted that the correlation threshold is a reference value obtained by technicians in this industry based on historical production experience.

[0058] If the correlation value is greater than or equal to the correlation threshold, it indicates that the operating parameter is an influencing parameter;

[0059] If the correlation value is less than the correlation threshold, it indicates that the operating parameter is a non-influencing parameter;

[0060] Based on any influencing parameter, divide the data of the splash change curve and the operating parameter curve at the same time node into several equal parts to form several equal-spacing segments; respectively obtain the maximum value Xmax and minimum value Xmin of the abscissa values and the maximum value Ymax and minimum value Ymin of the ordinate values of the splash change curve and the operating parameter curve in several equal-spacing segments; calculate the slope of the splash change curve and the operating parameter curve in each equal-spacing segment; as the formula:

[0061] Respectively obtain the slope Kp of the splash change curve and the slope Ky of the operating parameter curve; perform a ratio process on the slope Kp of the splash change curve and the slope Ky of the operating parameter curve; obtain the slope ratio H, as the formula: Calculate the mean of the sum of all slope ratios, as the formula: Where, N represents the number of all slope ratios; then, calculate the variance of the slope ratio H to obtain the variance index; as the formula: Where, N is the number of all slope ratios calculated;

[0062] Compare the variance index of any splash change curve and the operating parameter curve with the variance index threshold;

[0063] It should be noted that the variance index threshold is a value with reference value obtained by technicians in this industry based on historical production experience;

[0064] If the variance index value is greater than or equal to the variance index threshold, it indicates that the operating parameter corresponding to this variance has a non-linear relationship with the splash amplitude and is a non-regulation parameter;

[0065] If the variance index value is less than the variance index threshold, it indicates that the operating parameter corresponding to this variance has a linear relationship with the splash amplitude and is a regulation parameter;

[0066] S6: When the abnormal tapping hole alarm occurs, obtain any regulation parameter; the formula is: Obtain the regulation range T of the regulation parameter; where, H is the slope ratio, and C is the splash amplitude area exceeding the splash threshold when the abnormal tapping hole alarm occurs;

[0067] Calculate the value of the regulation range T of the regulation parameter; regulate the operating parameters of the blast furnace according to the value of the regulation range T of the regulation parameter until the tapping hole state returns to normal;

[0068] Embodiment 3

[0069] As shown Figure 2 in the figure, a real-time detection and control system for the state of the blast furnace taphole according to an embodiment of the present invention includes the following modules:

[0070] Real-time image acquisition module: Use a high-speed camera to collect image information of the taphole in real time;

[0071] Image recognition and processing module: Use image recognition algorithms to calculate and monitor the splash amplitude of the molten iron; After completing image segmentation to obtain the molten iron splash area, further extract the contour of the molten iron splash area; Obtain the splash amplitude area by calculating the area of the circumscribed rectangle of the contour of the molten iron splash area;

[0072] Image analysis module: Analyze and compare the splash amplitude area with a preset threshold area. If the splash amplitude area is greater than the preset threshold area, it indicates that there is a splash phenomenon at the taphole, and a splash abnormal signal is generated; Mark the time period when the splash abnormal signal appears as the splash abnormal period, divide the splash abnormal period into several time analysis nodes, obtain the splash amplitude area at each time analysis node, sum and take the average to obtain the average splash amplitude area within the splash abnormal period, perform difference processing on the average splash amplitude area and the preset threshold area, and then perform ratio processing with the preset threshold area; Multiply the splash amplitude area abnormal ratio by the splash abnormal duration ratio to obtain the abnormal state value of the taphole;

[0073] Real-time alarm module: Compare and analyze the abnormal state value of the taphole with the abnormal threshold of the taphole state. If the abnormal state value of the taphole is greater than the abnormal threshold of the taphole state, it indicates that the taphole state is abnormal, and an alarm signal is generated;

[0074] Control preprocessing module: Based on the alarm signal, obtain the change curve of the operating parameters over time to obtain the operating parameter curve, calculate the correlation between the splash change curve and the operating parameter curve, and use the formula to calculate the correlation value; Then judge the influencing parameters affecting the opening state by analyzing the correlation value; Then judge the influencing parameters affecting the opening state by analyzing the correlation value; If the correlation value is greater than or equal to the correlation threshold, it indicates that the operating parameter is the influencing parameter; Obtain the variance index based on the influencing parameter; If the variance index value is less than the variance index threshold, it indicates that the operating parameter corresponding to the variance has a linear relationship with the splash amplitude and is the regulation parameter;

[0075] Control module: Based on the regulation parameter, use the formula: to obtain the regulation range T of the regulation parameter; where H is the slope ratio and C is the splash amplitude area exceeding the splash threshold when the taphole abnormal alarm occurs; Calculate the value of the regulation range T of the regulation parameter; Regulate the operating parameters of the blast furnace according to the value of the regulation range T of the regulation parameter until the taphole state returns to normal;

[0076] The basic principles, main features and advantages of the present invention have been shown and described above. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A real-time detection and control method for the state of the blast furnace taphole, characterized in that: Including: S1: Using a high-speed camera to collect the image information of the taphole in real time; S2: Through an image recognition algorithm, preprocessing the obtained image to obtain the splashing amplitude area; S3: Analyzing the splashing amplitude area to obtain a splashing abnormal signal; processing the splashing abnormal signal to obtain the abnormal state value of the taphole; S4: Comparing and analyzing the abnormal state value of the taphole with the abnormal threshold of the taphole state to generate an alarm signal; S5: Based on the analysis of the alarm signal, obtaining the influencing parameters affecting the opening state, and obtaining the control parameters through the processing of the influencing parameters; S6: Using the control parameters to control the taphole state in real time.

2. The real-time detection and control method for the state of the blast furnace taphole according to claim 1, characterized in that: The specific process of preprocessing the obtained image is as follows: Using an image recognition algorithm, calculating and monitoring the splashing amplitude of the molten iron; after completing image segmentation to obtain the molten iron splashing area, further extracting the contour of the molten iron splashing area; obtaining the splashing amplitude area by calculating the area of the circumscribed rectangle of the contour of the molten iron splashing area.

3. The real-time detection and control method for the state of the blast furnace taphole according to claim 1, characterized in that: The specific process of obtaining the splashing amplitude area is as follows: For the segmented binary image, starting from the upper left corner of the image, scanning the image row by row and column by column to find the edge points of the molten iron splashing area; when encountering a point where the pixel value changes from the background value to the splashing area value or from the splashing area value to the background value, record it as an edge point; starting from a found edge point, following a certain direction, sequentially tracking along the edge points until returning to the starting point to form a closed contour; calculating the area C of the circumscribed rectangle of the contour of the molten iron splashing area according to the formula C = W × H; that is the splashing amplitude area.

4. A real-time detection and control method and system for the state of opening the blast furnace taphole according to claim 1, characterized in that: The specific process of analyzing the splashing amplitude area to obtain a splashing abnormal signal is as follows: Analyzing and comparing the splashing amplitude area with the preset threshold area; if the splashing amplitude area is less than or equal to the preset threshold area, it indicates that there is no splashing phenomenon at the taphole, and no treatment is required; If the splashing amplitude area is greater than the preset threshold area, it indicates that there is a splashing phenomenon at the taphole, and a splashing abnormal signal is generated.

5. A real-time detection and control method for the state of the blast furnace taphole according to claim 1, characterized in that: The specific process of processing the splashing abnormal signal to obtain the abnormal state value of the taphole is as follows: Obtain the duration of the splashing abnormal signal during the total duration of the production cycle, and perform a ratio process with the total duration of the production cycle to obtain the splashing abnormal duration ratio. Mark the time period when the splashing abnormal signal appears as the splashing abnormal time period, divide the splashing abnormal time period into several time analysis nodes, obtain the splashing amplitude area at each time analysis node, sum and take the average value to obtain the average splashing amplitude area within the splashing abnormal time period. After performing a difference process between the average splashing amplitude area and the preset threshold area, and then performing a ratio process with the preset threshold area, as shown in the formula: As shown, obtain the splashing amplitude area abnormal ratio, and perform a product process on the splashing amplitude area abnormal ratio and the splashing abnormal duration ratio to obtain the abnormal state value of the taphole.

6. The real-time detection and control method for the state of the blast furnace taphole according to claim 1, characterized in that: The specific process of comparing and analyzing the abnormal state value of the taphole with the abnormal threshold of the taphole state to generate an alarm signal is as follows: Comparing and analyzing the abnormal state value of the taphole with the abnormal threshold of the taphole state; if the abnormal state value of the taphole is greater than the abnormal threshold of the taphole state, it indicates that the taphole state is abnormal, and an alarm signal is generated.

7. A real-time detection and control method for the state of the blast furnace taphole according to claim 1, characterized in that: The specific process of obtaining the influence parameters affecting the opening state is as follows: Based on the alarm signal, obtain the operation parameter curve and the splash change curve of blast furnace ironmaking during the time period when the abnormal state of the taphole opening occurs; According to the splash change curve and the operation parameter curve, obtain the operation parameters and the splash amplitude area at different production nodes, form an operation data group and a splash data group, and use the Pearson correlation coefficient to process the operation data group and the splash data group. Specifically: Through the formula calculate to obtain the correlation value. If the correlation value is greater than or equal to the correlation threshold, it indicates that the operation parameter is an influence parameter.

8. A real-time detection and control method for the state of the blast furnace taphole according to claim 1, characterized in that: The specific process of obtaining the control parameters through the processing of the influencing parameters is as follows: Based on the influencing parameters, respectively obtaining the maximum and minimum values of the abscissa and the maximum and minimum values of the ordinate of the splashing change curve and the operating parameter curve in several equidistant segments; calculating the slope of the splashing change curve and the operating parameter curve in each equidistant segment to obtain the slope ratio; calculating the variance of the slope ratio to obtain the variance index. If the variance index value is less than the variance index threshold, it indicates that the operating parameter corresponding to the variance has a linear relationship with the splashing amplitude, and it is the control parameter.

9. A real-time detection and control method for the state of the blast furnace taphole according to claim 1, characterized in that: The specific process of real-time control of the taphole state using the control parameters is as follows: When a taphole abnormality alarm occurs, any one of the control parameters is obtained; the formula used is: The control range T of the control parameter is obtained; where H is the slope ratio and C is the splash amplitude area exceeding the splash threshold when the taphole abnormality alarm occurs; the value of the control range T of the control parameter is calculated; the operating parameters of the blast furnace are adjusted according to the value of the control range T of the control parameter until the taphole state returns to normal.

10. A real-time detection and control system for the state of the blast furnace taphole, characterized in that: Including the following modules: Real-time image acquisition module: Using a high-speed camera to collect the image information of the taphole in real time; Image recognition processing module: Using image recognition algorithms, calculate and monitor the splashing amplitude of hot metal; after completing image segmentation to obtain the hot metal splashing area, further extract the contour of the hot metal splashing area; obtain the splashing amplitude area by calculating the area of the circumscribed rectangle of the contour of the hot metal splashing area; Image analysis module: Analyze and compare the splashing amplitude area with a preset threshold area. If the splashing amplitude area is greater than the preset threshold area, it indicates that there is a splashing phenomenon at the taphole, and then generate a splashing anomaly signal; Mark the time period when the splashing anomaly signal appears as the splashing anomaly time period, divide the splashing anomaly time period into several time analysis nodes, obtain the splashing amplitude area at each time analysis node, sum and take the average to obtain the average splashing amplitude area within the splashing anomaly time period, perform a difference process on the average splashing amplitude area and the preset threshold area, and then perform a ratio process with the preset threshold area; Perform a multiplication process on the splashing amplitude area anomaly ratio and the splashing anomaly duration ratio to obtain the taphole opening anomaly status value; Real-time alarm module: Compare and analyze the taphole opening anomaly status value with the taphole opening status anomaly threshold. If the taphole opening anomaly status value is greater than the taphole opening status anomaly threshold, it indicates that the taphole opening status is abnormal, and then generate an alarm signal; Control preprocessing module: Based on the alarm signal, obtain the change curve of the operating parameters over time to get the operating parameter curve, calculate the correlation between the splashing change curve and the operating parameter curve, and obtain the correlation value through the formula Calculate to obtain the correlation value; then determine the influencing parameters affecting the opening state by analyzing the correlation value; then determine the influencing parameters affecting the opening state by analyzing the correlation value; if the correlation value is greater than or equal to the correlation threshold, it indicates that the operating parameter is an influencing parameter; obtain the variance index based on the influencing parameter; if the variance index value is less than the variance index threshold, it indicates that the operating parameter corresponding to the variance has a linear relationship with the splashing amplitude and is a control parameter; Control module: Based on the regulation parameters, the formula is: Obtain the regulation range T of the regulation parameters; where H is the slope ratio, and C is the splash amplitude area exceeding the splash threshold when the abnormal tapping hole alarm occurs; Calculate the regulation range T value of the regulation parameter; regulate the operating parameters of the blast furnace according to the regulation range T value of the regulation parameter until the taphole opening status returns to normal.

Images