An intelligent detection method and system for temperature measurement and sampling gun position based on image

Abstract

The present invention provides an image-based temperature measurement and sampling gun lowering position intelligent detection method and system, the method comprising: acquiring a target image, the target image being a steel liquid surface image; acquiring slag seam profile information in the steel liquid surface according to the acquired target image, the profile information comprising an inner profile and an outer profile of the slag seam; acquiring the slag seam width according to the slag seam profile information; adapting a preset temperature measurement and sampling gun lowering position, an area of ​​interest around the gun lowering position and a minimum gun lowering area to the acquired slag seam width, and selecting a gun lowering position that meets the gun lowering condition in the steel liquid surface for temperature measurement and sampling; the present invention detects the distribution of slag on the steel liquid surface of a ladle through an image, calculates all slag seam widths in a preset gun lowering area, selects a gun lowering position that meets the gun lowering condition through a predetermined strategy, and performs temperature measurement and sampling, thereby improving the intelligence level of the temperature measurement and sampling operation of a manipulator.

Description

Technical Field

[0001] The invention relates to the field of metallurgy, and in particular to an image-based temperature measurement sampling gun position intelligent detection method and system. Background Art

[0002] In the field of metallurgy, improving the automation level of steelmaking can enhance the safety and reliability of the entire equipment operation, and plays a vital role in ensuring the quality of molten steel and improving the labor productivity of steelmaking. As the basis for the process operation of the steelmaking process, it is necessary to measure the temperature and take samples of the molten steel after steelmaking. In the prior art, temperature measurement and sampling are usually performed by a manipulator.

[0003] However, in the actual application of temperature measurement and sampling in the ladle refining furnace, the manipulator usually uses a fixed path to complete the operation. However, in the steelmaking process, since there is usually slag on the surface of the molten steel, when the manipulator uses a fixed path to measure temperature and take samples, the gun tip may be damaged by colliding with the slag, resulting in failure to meet the requirements of temperature measurement and sampling. In the existing technology, there is no detection method to adjust the gun lowering position according to the slag seam width. In summary, a new detection method is needed to detect the distribution of slag in the gun lowering point area and accurately locate the slag seam area suitable for gun lowering. Summary of the invention

[0004] In view of the above-mentioned shortcomings of the prior art, the present invention provides an image-based temperature measurement and sampling gun position intelligent detection method and system to solve the above-mentioned technical problems.

[0005] The present invention provides an intelligent detection method for the position of a gun under temperature measurement and sampling based on an image, comprising:

[0006] Acquiring a target image, wherein the target image is a steel liquid surface image;

[0007] Acquire the contour information of the slag seam in the molten steel surface according to the acquired target image, wherein the contour information includes the inner contour and the outer contour of the slag seam;

[0008] According to the slag seam profile information, obtaining the slag seam width;

[0009] The preset temperature measurement and sampling gun lowering position, the area of ​​interest around the gun lowering position and the minimum area of ​​the gun lowering are adapted to the obtained slag seam width, and the gun lowering position that meets the gun lowering conditions is selected in the steel liquid surface for temperature measurement and sampling.

[0010] Optionally, the region of interest of the target image is obtained, and then the grayscale histogram of the region of interest of the target image is obtained, and the slag seam contour information is obtained according to a preset grayscale threshold.

[0011] Optionally, the grayscale threshold includes a low tail value and a high tail value,

[0012] When the gray value in the area is lower than the low tail value, the area is determined to be a slag area;

[0013] When the gray value in the area is higher than the high tail value, the area is determined to be a molten steel area;

[0014] When the gray value in the area is between the low tail value and the high tail value, it is determined that the area is a mixed area of ​​​​both slag and molten steel on the molten steel surface.

[0015] Optionally, the mixed zone is subjected to dynamic threshold binarization processing to obtain a binarized image, and the slag area and the slag seam area in the mixed zone are obtained based on the binarized image.

[0016] Optionally, edge search is performed on the slag seam area to obtain the inner contour and outer contour of the slag seam area, and the distance between the inner contour and the outer contour is used as the slag seam width.

[0017] Optionally, the preset temperature measurement sampling gun position, the area of ​​interest around the gun position and the minimum area of ​​the gun are adapted to the acquired slag seam width, and the temperature measurement sampling is performed according to a preset gun lowering strategy, wherein the preset gun lowering strategy includes a nearest point strategy and / or a most suitable point strategy, wherein:

[0018] The nearest point strategy includes selecting the minimum area that satisfies the gun placement in the neighborhood around the preset temperature measurement sampling gun placement position as the gun placement position;

[0019] The most suitable point strategy includes selecting the area with the largest slag seam width in the preset temperature measurement sampling gun lowering position area of ​​interest as the gun lowering position.

[0020] Optionally, the preset gun lowering strategy also includes, when the nearest point strategy fails to find a position that meets the conditions, using the most suitable point strategy to determine the gun lowering position and perform temperature measurement sampling.

[0021] The present invention also provides an image-based temperature measurement and sampling gun position intelligent detection system, comprising:

[0022] An image acquisition module, used for acquiring a target image, wherein the target image is a steel liquid surface image;

[0023] An image processing module is used to obtain the contour information of the slag seam in the molten steel surface according to the collected target image, wherein the contour information includes the inner contour and the outer contour of the slag seam; and obtain the width of the slag seam according to the slag seam contour information;

[0024] The temperature measurement and sampling module is used to adapt the preset temperature measurement and sampling gun lowering position, the area of ​​interest around the gun lowering position and the minimum area of ​​the gun lowering to the acquired slag seam width, and select the gun lowering position that meets the gun lowering conditions in the steel liquid surface for temperature measurement and sampling.

[0025] Optionally, an image acquisition protection module is also included, which includes a cooling unit for reducing the working environment temperature of the image acquisition system and a protective cover for heat insulation, radiation protection and dust prevention.

[0026] Optionally, it also includes an installation module and an alarm module for alarming when the gun lowering position detection fails; the installation module includes a mounting bracket and a temperature measuring and sampling manipulator, and the image acquisition module is fixed to the mobile end of the temperature measuring and sampling manipulator through the mounting bracket.

[0027] Beneficial effects of the present invention: The image-based temperature measurement and sampling gun lowering position intelligent detection method and system of the present invention detects the distribution of slag on the steel liquid surface of the ladle through images, calculates all slag seam widths in the preset gun lowering area, and selects the gun lowering position that meets the gun lowering conditions through a predetermined strategy to perform temperature measurement and sampling, thereby improving the intelligence level of the temperature measurement and sampling operation of the robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a flow chart of an intelligent detection method for the temperature measurement and sampling gun position based on an image in an embodiment of the present invention.

[0029] Figure 2 It is a structural schematic diagram of an image-based temperature measurement and sampling gun position intelligent detection system in an embodiment of the present invention.

[0030] Figure 3 It is a target detection image and a schematic diagram of an area of ​​interest of an image-based temperature measurement sampling and gun position intelligent detection system in an embodiment of the present invention.

[0031] Figure 4 It is a grayscale histogram of the region of interest of the temperature measurement sampling and gun position intelligent detection system based on image in the embodiment of the present invention.

[0032] Figure 5 It is an inner and outer contour diagram of a binary image of a region of interest in the image-based temperature measurement and sampling gun position intelligent detection system in an embodiment of the present invention.

[0033] Figure 6 It is a schematic diagram of the minimum distance between the point to be measured and the inner and outer contours of the image-based temperature measurement and sampling gun position intelligent detection system in an embodiment of the present invention.

[0034] Figure 7It is a schematic diagram of the gun lowering point calculated according to the closest point strategy by the image-based temperature measurement sampling gun lowering position intelligent detection system in an embodiment of the present invention.

[0035] Figure 8 It is a schematic diagram of the gun lowering point calculated according to the most suitable point strategy of the image-based temperature measurement sampling gun lowering position intelligent detection system in an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0037] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0038] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0039] like Figure 1 As shown, the image-based temperature measurement sampling gun position intelligent detection method in this embodiment includes:

[0040] Acquire a target image, which is a steel liquid surface image;

[0041] According to the acquired target image, the contour information of the slag seam in the molten steel surface is obtained, and the contour information includes the inner contour and the outer contour of the slag seam;

[0042] According to the slag seam profile information, obtaining the slag seam width;

[0043] The preset temperature measurement and sampling gun lowering position, the area of ​​interest around the gun lowering position and the minimum area of ​​the gun lowering are adapted to the obtained slag seam width, and the gun lowering position that meets the gun lowering conditions is selected in the steel liquid surface for temperature measurement and sampling.

[0044] In this embodiment, the temperature measurement sampling gun lowering position, the area of ​​interest around the gun lowering position and the minimum area for gun lowering are pre-set in the image, and the minimum area for gun lowering is used as the gun lowering condition. The gun lowering condition in this embodiment means that when the gun tip is inserted into the molten steel surface, there is no slag in the vicinity around the molten steel surface contacted by the gun tip. Optionally, the default value of the minimum area size in this embodiment is 10X10cm.

[0045] Optionally, in this embodiment, the manipulator is a six-axis manipulator, and the image acquisition system can be installed on the flange at the end of the six-axis manipulator. By teaching the manipulator to the ladle detection position and recording the original path of the action, when the manipulator moves to the ladle detection position, a new ladle steel liquid surface image is collected as the target image for detection.

[0046] In this embodiment, the region of interest of the steel liquid surface image is subjected to a dynamic threshold binarization operation, and then the connected domain detection is performed on the binarized image, and the detection result is subjected to region-based morphological processing to obtain the inner and outer contours of the slag seam; the distance between the inner and outer contours of the slag seam is the slag seam width. The nearest point strategy refers to calculating the minimum area that satisfies the gun lowering condition for a point in the neighborhood around the gun lowering position. For a steel liquid surface that is in a state of slight change, this strategy satisfies the gun lowering condition; the most suitable point strategy refers to calculating the area with the largest slag seam width in the region of interest around the gun lowering position as the gun lowering position, and even when the steel liquid surface is in dynamic change, the slag seam width in this area still satisfies the gun lowering condition.

[0047] In this embodiment, the grayscale histogram analysis is performed on the region of interest of the steel liquid surface image, and the low tail and high tail of the grayscale histogram statistics are limited. When the grayscale values ​​in the region are all lower than the low tail value, it is considered that the region is all steel slag, and the region is determined to be a steel slag area. When the grayscale values ​​in the region are all higher than the high tail value, it is considered that the region is all molten steel, and the region is determined to be a steel liquid area. When the grayscale value in the region is between the low tail value and the high tail value, the steel liquid surface contains both steel slag and molten steel, and the region is determined to be a mixed area of ​​the steel liquid surface containing both steel slag and molten steel. The region is subjected to dynamic threshold binarization operation through the grayscale histogram to obtain a binary image. The binary image is then subjected to connected domain analysis, and the obtained black region is the steel slag region, and the obtained white region is the steel slag seam region. By performing edge search on the steel slag seam region, the inner contour and outer contour of the region are obtained, and the distance between the inner contour and the outer contour is defined as the steel slag seam width.

[0048] In this embodiment, the gun lowering strategy can be pre-formulated, and one of the nearest point strategy or the most suitable point strategy can be selected for temperature measurement sampling. It can also include that when the nearest point strategy fails to find a position that meets the conditions, the most suitable point strategy is used to determine the gun lowering position and perform temperature measurement sampling. For example, the nearest point strategy is used to find all the slag seam widths in the neighborhood around the gun lowering position, and the position that meets the minimum area condition for gun lowering is calculated. When the nearest point strategy fails to find a position that meets the conditions, the most suitable point strategy is used to find the positions of all the slag seam areas that meet the conditions in the area of ​​interest and the slag seam widths corresponding to the positions. The position with the maximum width value is the most suitable gun lowering point.

[0049] Accordingly, this embodiment also provides an image-based temperature measurement and sampling gun position intelligent detection system, comprising:

[0050] An image acquisition module is used to acquire a target image, where the target image is a steel liquid surface image;

[0051] The image processing module is used to obtain the slag seam profile information in the molten steel surface according to the acquired target image, and the profile information includes the inner profile and the outer profile of the slag seam; obtain the slag seam width according to the slag seam profile information, and adapt the preset temperature measurement sampling gun position, the area of ​​interest around the gun position, and the minimum area of ​​the gun to the obtained slag seam width;

[0052] The temperature measurement and sampling module is used to select the gun lowering position that meets the gun lowering conditions in the steel liquid surface for temperature measurement and sampling.

[0053] In this embodiment, the image acquisition module may include image acquisition components such as industrial cameras, industrial lenses, and filters. The image acquisition module is fixed to the mobile end of the temperature measurement sampling manipulator through the mounting bracket to collect the target image. The image processing module can use the industrial computer in the technology to obtain the contour information of the slag seam in the steel liquid surface according to the collected target image. The contour information includes the inner contour and outer contour of the slag seam; according to the slag seam contour information, the slag seam width is obtained. The temperature measurement sampling module acts as an actuator to perform the front-end work of temperature measurement sampling.

[0054] In this embodiment, it also includes an image acquisition protection module, an installation module and an alarm module, wherein the image acquisition protection module includes a cooling unit for reducing the working environment temperature of the image acquisition system and a protective cover for heat insulation, radiation protection and dust prevention. The cooling unit can use air cooling to reduce the working environment temperature of the image acquisition module. The installation module includes a mounting bracket and a temperature measurement and sampling manipulator. The alarm module can use devices with warning functions such as sound and light alarm lights to alarm when the detection of the gun lowering position fails.

[0055] In this embodiment, a communication module is also included for data transmission between the image acquisition module and the image processing module. The communication module can adopt a wired communication module, for example, communicating through the TCP / IP network protocol. Optionally, the communication module can be installed at the end of the temperature measurement sampling robot. After the robot moves to the detection position, the image captured by the image acquisition module is transmitted to the image processing module for detection, and the detection result is sent to the robot.

[0056] In this embodiment, the system control process includes:

[0057] S11, after receiving the temperature measurement and sampling command, the system controls the manipulator to move to the temperature measurement and sampling detection position;

[0058] S12, after the manipulator moves to the detection position, a feedback signal is given to the image processing module, and the image processing module triggers the image acquisition module to acquire the ladle liquid surface image and use it as the target image;

[0059] S13, pre-setting the closest point and / or the most suitable point strategy in the image processing module, and setting different priorities for the two strategies respectively, and executing them through the temperature measurement sampling module in descending order of priority.

[0060] In this embodiment, the region of interest around the gun lowering position, the gun lowering position for temperature measurement sampling in the image, and the minimum area for gun lowering are pre-set, such as Figure 3 As shown in the figure, the minimum area of ​​the gun is taken as the gun lowering condition. The gun lowering condition means that when the gun head is inserted into the molten steel surface, there is no slag in the vicinity of the molten steel surface contacted by the gun head.

[0061] In this embodiment, a grayscale histogram analysis is performed on the region of interest of the molten steel surface image, and the low tail and high tail of the grayscale histogram statistics are restricted. When the grayscale values ​​in the region are all lower than the low tail value of 1, it is considered that the region is all slag, and when the grayscale values ​​in the region are all higher than the high tail value of 3, it is considered that the region is all molten steel. When the grayscale value in the region is between the low tail value and the high tail value, the molten steel surface contains both slag and molten steel. The region is subjected to dynamic threshold binarization operation through the grayscale histogram, and a binary image is obtained using the dynamic threshold of 2. In this embodiment, a connected domain analysis is performed on the binary image, and the obtained black area is the slag area, and the obtained white area is the slag seam area, such as Figure 4 shown.

[0062] In this embodiment, the edge search is performed on the slag seam area to obtain the inner contour and outer contour of the area, such as Figure 5 As shown, due to the limitation of black and white colors of the picture, different colors can be used to distinguish them in practical applications. For example, the red outline is the outer outline of the slag seam, the blue outline is the inner outline of the slag seam, and the distance between the inner outline and the outer outline is defined as the slag seam width.

[0063] Specifically, we first need to find the points of the slag seam. The search method is as follows:

[0064] like Figure 6 As shown, point A is the point to be measured, 61 is the region of interest, 62 is the outer contour, and 63 and 64 are the inner contours. Point A to be measured is selected in the region of interest around the lower gun position, and the relationship between point A to be measured and the outer contour (62) and the inner contour (63 and 64) is judged to determine whether point A to be measured is in the slag seam. The judgment rule is: if point A to be measured is both inside the outer contour (62) and outside the inner contour (63 and 64), then point A to be measured is a point in the slag seam. The minimum distance between point A to be measured in the slag seam and the outer contour (62) and the inner contour (63 and 64) is calculated, which is defined as the slag seam width of the point to be measured.

[0065] In this embodiment, if Figure 7 As shown in the figure, the nearest point strategy is used to find all the slag seam widths in the neighborhood around the gun position, and the position that meets the minimum area condition for the gun position is calculated. The circle mark is the preset gun position, and the size of the neighborhood around the gun position can be preset. The minimum distance between each point in the slag seam and the inner and outer contours in the neighborhood around the gun position is calculated, and the distance of each point is compared to find the maximum value of all distances, as shown by the cross mark. When the maximum value is greater than the minimum gun area, it means that there is a gun point that meets the nearest point strategy in the neighborhood around the preset gun area.

[0066] In this embodiment, the most suitable strategy is used to find all the slag seam widths in the area of ​​interest of the gun position, and calculate the position that meets the minimum area condition of the gun position. The method is the same as the closest point strategy. The only difference is that the closest point strategy only traverses the points in the neighborhood around the gun position as the test points, while the most suitable point strategy uses all the points in the area of ​​interest of the gun position as the test points. The calculation results are as follows: Figure 8 The cross in the figure is the position of the next shot calculated by the most suitable point strategy.

[0067] After intelligent detection based on the two strategies, the position of the gun lowering point is calculated and the coordinates are sent to the robot. If the calculation fails, an alarm is triggered.

[0068] Then, the robot moves to the new gun placement point to perform temperature measurement and sampling operations.

[0069] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. An intelligent detection method for the position of the temperature sampling gun based on an image. It is characterized in that include: Acquiring a target image, wherein the target image is a steel liquid surface image; Acquire the contour information of the slag seam in the molten steel surface according to the acquired target image, wherein the contour information includes the inner contour and the outer contour of the slag seam; According to the slag seam profile information, obtaining the slag seam width; The preset temperature measurement sampling gun lowering position, the area of ​​interest around the gun lowering position and the minimum gun lowering area are adapted to the obtained slag seam width, and the gun lowering position that meets the gun lowering conditions is selected in the steel liquid surface for temperature measurement sampling; Acquire the region of interest of the target image, and then acquire the grayscale histogram of the region of interest of the target image, and acquire the slag seam contour information according to a preset grayscale threshold; Perform edge search on the slag seam area, obtain the inner contour and outer contour of the slag seam area, and use the distance between the inner contour and the outer contour as the slag seam width; The preset temperature measurement sampling gun position, the area of ​​interest around the gun position and the minimum gun area are adapted to the acquired slag seam width, and the temperature measurement sampling is performed according to the preset gun lowering strategy, which includes the nearest point strategy and / or the most suitable point strategy, wherein: The nearest point strategy includes selecting the minimum area that satisfies the gun placement in the neighborhood around the preset temperature measurement sampling gun placement position as the gun placement position; The most suitable point strategy includes selecting the area with the largest slag seam width in the preset temperature measurement sampling gun lowering position area of ​​interest as the gun lowering position.

2. According to the image-based temperature measurement sampling gun position intelligent detection method of claim 1, It is characterized in that The grayscale threshold includes a low tail value and a high tail value, When the gray value in the area is lower than the low tail value, the area is determined to be a slag area; When the gray value in the area is higher than the high tail value, the area is determined to be a molten steel area; When the gray value in the area is between the low tail value and the high tail value, it is determined that the area is a mixed area of ​​​​both slag and molten steel on the molten steel surface.

3. The method for intelligent detection of the temperature sampling gun position based on image according to claim 2, It is characterized in that The mixed zone is subjected to dynamic threshold binarization processing to obtain a binarized image, and the slag area and the slag seam area in the mixed zone are obtained based on the binarized image.

4. The method for intelligent detection of the position of the temperature sampling gun based on an image according to claim 1, It is characterized in that The preset gun lowering strategy also includes, when the nearest point strategy fails to find a position that meets the conditions, using the most suitable point strategy to determine the gun lowering position and perform temperature measurement sampling.

5. An intelligent detection system for temperature measurement and sampling gun position based on images, It is characterized in that include An image acquisition module, used for acquiring a target image, wherein the target image is a steel liquid surface image; An image processing module is used to obtain the contour information of the slag seam in the molten steel surface according to the collected target image, wherein the contour information includes the inner contour and the outer contour of the slag seam; obtain the slag seam width according to the slag seam contour information, and adapt the preset temperature measurement sampling gun position, the area of ​​interest around the gun position, and the minimum area of ​​the gun to the obtained slag seam width; The temperature measurement and sampling module is used to select the gun lowering position that meets the gun lowering conditions in the steel liquid surface for temperature measurement and sampling; Acquire the region of interest of the target image, and then acquire the grayscale histogram of the region of interest of the target image, and acquire the slag seam contour information according to a preset grayscale threshold; Perform edge search on the slag seam area, obtain the inner contour and outer contour of the slag seam area, and use the distance between the inner contour and the outer contour as the slag seam width; The preset temperature measurement sampling gun position, the area of ​​interest around the gun position and the minimum gun area are adapted to the acquired slag seam width, and the temperature measurement sampling is performed according to the preset gun lowering strategy, which includes the nearest point strategy and / or the most suitable point strategy, wherein: The nearest point strategy includes selecting the minimum area that satisfies the gun placement in the neighborhood around the preset temperature measurement sampling gun placement position as the gun placement position; The most suitable point strategy includes selecting the area with the largest slag seam width in the preset temperature measurement sampling gun lowering position area of ​​interest as the gun lowering position.

6. The image-based temperature measurement and sampling gun position intelligent detection system according to claim 5, It is characterized in that It also includes an image acquisition protection module, which includes a cooling unit for reducing the working environment temperature of the image acquisition system and a protective cover for heat insulation, radiation protection and dust prevention.

7. The image-based temperature measurement and sampling gun position intelligent detection system according to claim 6, It is characterized in that It also includes an installation module and an alarm module for alarming when the gun position detection fails; the installation module includes a mounting bracket and a temperature measurement and sampling manipulator, and the image acquisition module is fixed to the temperature measurement and sampling manipulator through the mounting bracket.

Images