Coating roller rotating speed detection method and system based on machine vision

Abstract

The embodiment of the invention discloses a coating roller rotating speed detection method and system based on machine vision. In the method, a visual mark is arranged in the edge area of the bottom surface of a coating roller; acquiring a coating roller bottom surface image containing the visual mark in real time through image acquisition equipment; identifying and positioning the position coordinates of the visual mark in the bottom surface image of the coating roller, and recording the corresponding acquisition time; the rotation angle of the coating roller is calculated according to the position coordinates, collected at the two adjacent time points, of the visual marks; and calculating the rotating speed of the coating roller based on the rotating angle and the time difference between the two adjacent time points. Therefore, according to the scheme provided by the embodiment of the invention, no speed metering equipment is additionally arranged on the coating roller, the non-contact real-time detection of the speed of the coating roller is realized, the detection precision and the intelligent degree of the cold rolling unit are improved, and the labor intensity of workers is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of cold rolling intelligent control, and particularly relates to a roll coating speed detection method and system based on machine vision. BACKGROUND

[0002] In the prior art, a roll coater device is usually arranged in a cold rolling mill set. The roll coater device is used to uniformly cover the surface of a strip steel with coating liquid of different components to change the performance of the strip steel. The thickness of the coating layer has a great influence on the performance of the strip steel. Some roll coaters are not provided with a motor drive and are driven to rotate by the friction between the strip steel and the roll coater when the strip steel moves. When the temperature decreases in winter, the roll coater and the surface coating liquid will expand due to thermal expansion and contraction, which will cause the gap between the roll coater and the strip steel to become larger, and thus the friction between the strip steel and the roll coater will be reduced, and the speed of the roll coater will be reduced, thereby affecting the thickness of the coating layer. Therefore, the speed of the roll coater can be used to indirectly determine whether the gap between the strip steel and the roll coater is normal. However, the roll coater is not provided with a motor drive, and thus the current speed of the roll coater cannot be directly measured, and manual visual inspection is required. This method relies heavily on manual experience and cannot timely detect the reduction of the speed of the roll coater, and is low in efficiency.

[0003] Therefore, how to realize non-contact real-time detection of the speed of the roll coater and improve the detection accuracy is a problem to be solved by those skilled in the art. SUMMARY

[0004] The embodiment of the present application provides a roll coating speed detection method and system based on machine vision, which can realize non-contact real-time detection of the speed of the roll coater, improve the detection accuracy, and reduce manual consumption.

[0005] The first aspect of the present application provides a roll coating speed detection method based on machine vision, comprising: A visual mark is arranged at the edge region of the bottom surface of the roll coater. An image acquisition device is used to acquire a roll coater bottom surface image containing the visual mark in real time. The position coordinates of the visual mark in the roll coater bottom surface image are recognized and located, and the corresponding acquisition time is recorded. The rotation angle of the roll coater is calculated according to the position coordinates of the visual mark acquired at two adjacent time points. The rotation speed of the roll coater is calculated based on the rotation angle and the time difference between the two adjacent time points.

[0006] Optionally, the visual mark is a color mark with high contrast, which is arranged at the outermost region of the bottom surface of the roll coater.

[0007] Optionally, the image acquisition device is a face array camera, which is installed in front of the bottom surface of the roll coater.

[0008] Optionally, the position coordinates of the visual mark in the image are recognized and located, comprising: detecting the position of the visual marker in the image by a preset image classification algorithm; The preset image classification algorithm comprises a classification model trained by a neural network based on sample images of the visual marker.

[0009] Optionally, the calculation of the rotation angle of the coating roller comprises: calibrating the center position coordinates of the coating roller in the bottom surface image of the coating roller; calculating a first included angle and a second included angle of the first connecting line and the second connecting line with the center position coordinates, respectively, according to the position coordinates of the visual marker at the two adjacent time points; calculating the rotation angle according to the first included angle and the second included angle.

[0010] Optionally, the calculation of the rotation speed of the coating roller based on the rotation angle and the time difference between the two adjacent time points comprises: calculating the motion arc length of the visual marker within the adjacent collection time according to the rotation angle and the radius of the coating roller; calculating the linear speed of the coating roller according to the motion arc length and the time difference; calculating the rotation speed of the coating roller according to the linear speed and the radius of the coating roller.

[0011] Optionally, it further comprises: establishing a corresponding relationship between the rotation speed of the coating roller and the coating thickness; judging whether the current coating thickness is qualified according to the real-time detected rotation speed of the coating roller; when the rotation speed of the coating roller is abnormal, an alarm signal is sent and a process parameter adjustment is prompted.

[0012] The second aspect of the present application provides a coating roller rotation speed detection system based on machine vision, comprising: a marking unit for setting a visual marker on the edge area of the bottom surface of the coating roller; an image acquisition unit for acquiring the bottom surface image of the coating roller containing the visual marker in real time through an image acquisition device; a processing unit for identifying and positioning the position coordinates of the visual marker in the bottom surface image of the coating roller and recording the corresponding collection time; a calculation unit for calculating the rotation angle of the coating roller according to the position coordinates of the visual marker collected at the two adjacent time points; and calculating the rotation speed of the coating roller based on the rotation angle and the time difference between the two adjacent time points.

[0013] The third aspect of the present application provides a coating roller rotation speed detection device based on machine vision, comprising: one or more processors; a memory having one or more programs stored thereon; The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method for detecting the rotating speed of a coating roller based on machine vision as claimed in any one of the above.

[0014] The fourth aspect of the present application provides a computer storage medium for storing a program, which, when executed, is used to implement the method for detecting the rotating speed of a coating roller based on machine vision as claimed in any one of the above.

[0015] The embodiment of the present application discloses a method and system for detecting the rotating speed of a coating roller based on machine vision. In the method, a visual mark is arranged at the edge area of the bottom surface of the coating roller; an image acquisition device is used to acquire the image of the bottom surface of the coating roller containing the visual mark in real time; the position coordinates of the visual mark in the image of the bottom surface of the coating roller are identified and located, and the corresponding acquisition time is recorded; the rotating angle of the coating roller is calculated according to the position coordinates of the visual mark acquired at two adjacent time points; and the rotating speed of the coating roller is calculated based on the rotating angle and the time difference between the two adjacent time points. As can be seen, by using the scheme provided by the embodiment of the present application, the speed measuring device can be not installed on the coating roller, the speed of the coating roller can be detected in real time in a non-contact manner, the detection accuracy and the intelligent degree of the cold rolling mill are improved, and the work intensity of the workers is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0017] Figure 1 A flowchart of a method for detecting the rotating speed of a coating roller based on machine vision provided by the embodiment of the present application; Figure 2 A structure diagram of a system for detecting the rotating speed of a coating roller based on machine vision provided by the embodiment of the present application; Figure 3 A structure diagram of a device for detecting the rotating speed of a coating roller based on machine vision provided by the embodiment of the present application. DETAILED DESCRIPTION

[0018] The embodiment of the present application provides a method and system for detecting the rotating speed of a coating roller based on machine vision, which is used to detect the speed of the coating roller in a non-contact manner in real time, improve the detection accuracy and the intelligent degree of the cold rolling mill, and reduce the work intensity of the workers.

[0019] Reference Figure 1Fig. 1 is a flowchart of a machine vision-based coating roller rotational speed detection method according to an embodiment of the present application. The machine vision-based coating roller rotational speed detection method according to an embodiment of the present application can be implemented, for example, by the following steps S101-S105.

[0020] S101: A visual mark is arranged at an edge region of a bottom surface of a coating roller.

[0021] In an embodiment of the present application, the visual mark is a color mark with high contrast, which is arranged at an outermost region of the bottom surface of the coating roller.

[0022] S102: An image acquisition device is used to acquire a coating roller bottom surface image containing the visual mark in real time.

[0023] In an embodiment of the present application, the image acquisition device is a face array camera, which is installed in front of the bottom surface of the coating roller. The face array camera is a high-speed acquisition face array camera, which is used to acquire the coating roller bottom surface image.

[0024] S103: The position coordinates of the visual mark in the coating roller bottom surface image are identified and located, and the corresponding acquisition time is recorded.

[0025] In an embodiment of the present application, the position of the visual mark in the image is detected by a preset image classification algorithm. The preset image classification algorithm includes a classification model obtained by neural network training based on a sample image of the visual mark.

[0026] S104: The rotational angle of the coating roller is calculated according to the position coordinates of the visual mark acquired at two adjacent time points.

[0027] In an embodiment of the present application, the center position coordinates of the coating roller are calibrated in the coating roller bottom surface image. The first and second angles of the first and second lines respectively connecting the center position coordinates and the position coordinates of the visual mark at two adjacent time points are calculated. The rotational angle is calculated according to the first and second angles.

[0028] Specifically, the angle change of the position coordinates of the visual mark acquired at two adjacent time points is calculated. The first and second angles of the visual mark position coordinates relative to the center of the coating roller are calculated by a trigonometric function. The rotational angle is determined according to the first and second angles. S105: The rotational speed of the coating roller is calculated based on the rotational angle and the time difference between the two adjacent time points.

[0029] In an embodiment of the present application, the movement arc length of the visual mark within the adjacent acquisition time is calculated according to the rotational angle and the radius of the coating roller. The linear speed of the coating roller is calculated according to the movement arc length and the time difference. The rotational speed of the coating roller is calculated according to the linear speed and the radius of the coating roller.

[0030] In an implementation form of the embodiment of the application, a correspondence between the coating roller speed and the coating thickness is established; whether the current coating thickness is qualified is determined according to the real-time detected coating roller speed; when the coating roller speed is abnormal, an alarm signal is sent and the process parameters are prompted to be adjusted.

[0031] Specifically, when the real-time detected coating roller speed is out of or lower than the preset threshold range, it indicates that the gap between the strip steel and the coating roller is abnormal, and the thickness of the current coating is unqualified, at this time, an alarm signal is sent and the process parameters are prompted to be adjusted.

[0032] The embodiment of the application discloses a coating roller speed detection method and system based on machine vision. In the method, a visual mark is arranged at the edge area of the bottom surface of the coating roller; the bottom surface image of the coating roller containing the visual mark is acquired in real time through an image acquisition device; the position coordinates of the visual mark in the bottom surface image of the coating roller are identified and located, and the corresponding acquisition time is recorded; the rotation angle of the coating roller is calculated according to the position coordinates of the visual mark acquired at two adjacent time points; and the rotation speed of the coating roller is calculated based on the rotation angle and the time difference between the two adjacent time points. As can be seen, by using the scheme provided in the embodiment of the application, the speed metering device does not need to be installed on the coating roller, the non-contact real-time detection of the coating roller speed is realized, the detection accuracy and the intelligent degree of the cold rolling mill are improved, and the work intensity of the workers is reduced.

[0033] Based on the method provided in the above embodiment, the embodiment of the application further provides a coating roller speed detection system based on machine vision, which will be introduced below in combination with the drawings.

[0034] Referring to Figure 2 The figure is a structural schematic diagram of a coating roller speed detection system based on machine vision provided in the embodiment of the application.

[0035] The coating roller speed detection system based on machine vision 200 provided in the embodiment of the application comprises a marking unit 201, an image acquisition unit 202, a processing unit 203 and a calculation unit 204.

[0036] The marking unit 201 is configured to arrange a visual mark at the edge area of the bottom surface of the coating roller. The image acquisition unit 202 is configured to acquire the bottom surface image of the coating roller containing the visual mark in real time through an image acquisition device. The processing unit 203 is configured to identify and locate the position coordinates of the visual mark in the bottom surface image of the coating roller, and record the corresponding acquisition time. The calculation unit 204 is configured to calculate the rotation angle of the coating roller according to the position coordinates of the visual mark acquired at two adjacent time points, and calculate the rotation speed of the coating roller based on the rotation angle and the time difference between the two adjacent time points.

[0037] In a possible implementation, the visual mark is a color mark with high contrast, and is arranged at the outermost region of the bottom surface of the coating roller.

[0038] In a possible implementation, the image acquisition device is a face array camera, and is installed in front of the bottom surface of the coating roller.

[0039] In a possible implementation, the processing unit 203 has functions of: detecting the position of the visual mark in the image by using a preset image classification algorithm; The preset image classification algorithm includes a classification model trained by a neural network based on sample images of the visual mark.

[0040] In a possible implementation, the calculation unit 204 has functions of: calibrating the center position coordinates of the coating roller in the image of the bottom surface of the coating roller; calculating a first included angle and a second included angle between the center position coordinates and the position coordinates of the visual mark at two adjacent time points, respectively; calculating the rotation angle according to the first included angle and the second included angle.

[0041] In a possible implementation, the calculation unit 204 has functions of: calculating the motion arc length of the visual mark within the adjacent acquisition time according to the rotation angle and the radius of the coating roller; calculating the linear velocity of the coating roller according to the motion arc length and the time difference; calculating the rotation speed of the coating roller according to the linear velocity and the radius of the coating roller.

[0042] In a possible implementation, the system 200 further includes a prompting unit having functions of: establishing a corresponding relationship between the rotation speed of the coating roller and the coating thickness; judging whether the current coating thickness is qualified according to the real-time detected rotation speed of the coating roller; when the rotation speed of the coating roller is abnormal, issuing an alarm signal and prompting to adjust the process parameters.

[0043] Since the system 200 is a system corresponding to the machine vision-based coating roller rotation speed detection method provided in the above method embodiments, the specific implementation of each unit of the system 200 is the same as the same idea as the above method embodiments, and therefore, for the specific implementation of each unit of the system 200, reference can be made to the description of the machine vision-based coating roller rotation speed detection method in the above method embodiments, which will not be repeated here.

[0044] The embodiment of the present application also provides a machine vision-based coating roller rotation speed detection device, which comprises a processor and a memory. The memory is configured to store instructions. The processor is configured to execute the instructions in the memory to implement the machine vision-based coating roller rotating speed detection method mentioned in the above embodiments.

[0045] It should be noted that the hardware structure of the machine vision-based coating roller rotating speed detection device provided in the embodiments of the present application can be as shown in Figure 3 Figure 3 FIG. 1 is a structural schematic diagram of a machine vision-based coating roller rotating speed detection device provided in the embodiments of the present application.

[0046] Referring to FIG. 3, Figure 3 The device 300 includes a processor 310, a communication interface 320 and a memory 330. The number of processors 310 in the device 300 can be one or more, Figure 3 In the embodiment of the present application, the processor 310, the communication interface 320 and the memory 330 can be connected through a bus system or other means, wherein, Figure 3 In the embodiment of the present application, the processor 310, the communication interface 320 and the memory 330 are connected through the bus system 340.

[0047] The processor 310 can be a central processing unit (CPU), a network processor (NP) or a combination of CPU and NP. The processor 310 can further include a hardware chip. The hardware chip can be an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0048] ​The memory 330 can include a volatile memory (e.g., a random-access memory, RAM), and can also include a non-volatile memory (e.g., a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD)), or a combination thereof.

[0049] Optionally, the memory 330 stores an operating system and programs, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the programs can include various operation instructions for implementing various operations. The operating system can include various system programs for implementing various basic services and processing hardware-based tasks. The processor 310 can read the programs in the memory 330 to implement the machine vision-based coating roller speed detection method provided in the embodiments of the present application.

[0050] The bus system 340 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus system 340 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0051] The embodiments of the present application also provide a computer readable storage medium, including instructions, when running on a computer, causing the computer to execute the machine vision-based coating roller speed detection method mentioned in the above embodiments.

[0052] The embodiments of the present application also provide a computer program product including instructions, when running on a computer, causing the computer to execute the machine vision-based coating roller speed detection method mentioned in the above embodiments.

[0053] The terms "first", "second", "third", "fourth", and the like in the description and in the claims of the present application, and in the above Description of Drawings if any, are used for distinguishing between similar objects talking about the embodiments and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of these terms herein is to be construed to cover the embodiments described herein and any equivalents or alternatives of those embodiments. The terms "comprise", "comprising", "comprises", "include", "including", and the like are to be construed open- ended, i.e., to mean "including, but not limited to", unless otherwise noted. One or more of the listed elements can be present or absent, but need not be present or be absent. The language "to, "at or "by" preceding the recitation of a step or element, material, substance, composition, or the like, throughout this disclosure, including the claims, does not embody a doing constraint or a limitation of action exclusivity as those terms are used in the preambles of method claims. The terms "about" and "substantially" are used to describe and account for small fluctuations, such as due to measurement or other experimental error, which can occur in measurements of a variable. Such terms encompass variations that can exist in the values that the variable is intended to represent as well as understandable adjustments for small fluctuations, and unless otherwise noted, the description is meant to encompass such variations.

[0054] While this application has been particularly shown and described with references to preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details can be made therein without departing from the spirit and scope of the application as defined by the appended claims.

Claims

1. A machine vision-based coating roll rotational speed detection method, characterized by, The method comprises: setting a visual mark on the edge area of the bottom surface of the coating roller; acquiring the image of the bottom surface of the coating roller containing the visual mark in real time through an image acquisition device; identifying and locating the position coordinates of the visual mark in the image of the bottom surface of the coating roller and recording the corresponding acquisition time; calculating the rotation angle of the coating roller according to the position coordinates of the visual mark acquired at adjacent two time points; calculating the rotation speed of the coating roller based on the rotation angle and the time difference between the adjacent two time points.

2. The method of claim 1, wherein, The visual mark is a color mark with high contrast, which is arranged on the outermost area of the bottom surface of the coating roller.

3. The method of claim 1, wherein, The image acquisition device is a face array camera, which is installed in front of the bottom surface of the coating roller.

4. The method of claim 1, wherein, The identification and location of the position coordinates of the visual mark in the image comprises: detecting the position of the visual mark in the image through a preset image classification algorithm; The preset image classification algorithm comprises a classification model trained by a neural network based on sample images of the visual mark.

5. The method of claim 1, wherein, The calculation of the rotation angle of the coating roller comprises: calibrating the center position coordinates of the coating roller in the image of the bottom surface of the coating roller; calculating the first and second included angles of the first and second lines respectively connecting the center position coordinates and the position coordinates of the visual mark at adjacent two time points; calculating the rotation angle according to the first and second included angles.

6. The method of claim 5, wherein, The calculation of the rotation speed of the coating roller based on the rotation angle and the time difference between the adjacent two time points comprises: calculating the motion arc length of the visual mark within the adjacent acquisition time according to the rotation angle and the radius of the coating roller; calculating the linear speed of the coating roller according to the motion arc length and the time difference; calculating the rotation speed of the coating roller according to the linear speed and the radius of the coating roller.

7. The method of claim 1, wherein, Further comprising: establishing the corresponding relationship between the rotation speed of the coating roller and the coating thickness; judging whether the current coating thickness is qualified according to the real-time detected rotation speed of the coating roller; when the rotation speed of the coating roller is abnormal, issuing an alarm signal and prompting to adjust the process parameters.

8. A machine vision-based coating roll rotational speed detection system, characterized by, The method comprises: a marking unit for setting a visual mark on the edge area of the bottom surface of the coating roller; an image acquisition unit for acquiring the image of the bottom surface of the coating roller containing the visual mark in real time through an image acquisition device; a processing unit for identifying and locating the position coordinates of the visual mark in the image of the bottom surface of the coating roller and recording the corresponding acquisition time; a calculation unit for calculating the rotation angle of the coating roller according to the position coordinates of the visual mark acquired at adjacent two time points; calculating the rotation speed of the coating roller based on the rotation angle and the time difference between the adjacent two time points.

9. A machine vision-based roll speed detection apparatus, characterized by, The device comprises a processor and a memory; The memory is used to store instructions; The processor is used to execute the instructions in the memory, and execute the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The instructions, when executed on a computer, cause the computer to execute the method of any one of claims 1-7.

Images