Device and method for monitoring product quality based on machine vision and medium

Abstract

The invention provides a device and method for monitoring product quality based on machine vision and a medium, and the device comprises an image collection device which is disposed in a blanking pipeline, and is used for obtaining a real-time image of powder in a powder blanking process, and transmitting the real-time image to a processor; the transparent cover plate is located at an observation opening in the particle pipeline; the light source is used for providing shooting lighting for the image acquisition equipment; and the processor is used for analyzing the real-time image so as to determine the corundum particle size value of the powder, and controlling the discharging bin to stop working so as to control the powder to stop discharging to the finished product bin under the condition that the corundum particle size value is greater than a preset particle size alarm value. Through the device, real-time accurate detection of powder can be realized, errors and hysteresis of a manual detection result are overcome, and the product quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of machine vision, and in particular to a device, method and medium for monitoring product quality based on machine vision. Background Art

[0002] Machine vision is to use machines to replace human eyes for measurement and judgment. The machine vision system converts the captured target into an image signal through machine vision products (i.e., image capture devices, divided into CMOS and CCD), transmits it to a dedicated image processing system, obtains the morphological information of the captured target, and converts it into a digital signal based on pixel distribution, brightness, color and other information. The image system performs various operations on these signals to extract the characteristics of the target, and then controls the operation of the equipment on site based on the judgment results.

[0003] In the field of corundum products, downstream customers have strict requirements on the particle size of the product, and the pass rate of the finished product must be greater than 90%. Among them, no mixing, no large particles, and uniform product particle size are key factors in product quality. In traditional technology, samples are usually taken at the feed port by human eyes to observe the product particle size. Samples are taken every two hours, and the screen is replaced when large particles are found. However, this quality monitoring process has the disadvantage of delayed detection results. When the screen is damaged, large particles of products flow into the packaging warehouse, and the quality pass rate is low. Summary of the invention

[0004] In view of the problems existing in the prior art, the embodiments of the present invention provide a device, method and medium for monitoring product quality based on machine vision, so as to solve or partially solve the technical problem that the quality of corundum products cannot be guaranteed in the prior art.

[0005] A first aspect of the present invention provides a device for monitoring product quality based on machine vision, the device comprising:

[0006] An image acquisition device is installed in the feeding pipe, and is used to obtain a real-time image of the powder material during the feeding process of the powder material and transmit it to the processor;

[0007] Transparent cover, observation port located at the particle pipe;

[0008] A light source, used to provide lighting for the image acquisition device;

[0009] The processor is used to analyze the real-time image to determine the corundum particle size value of the powder, and when the corundum particle size value is greater than a preset particle size alarm value, control the unloading bin to stop working so as to control the powder to stop unloading into the finished product bin.

[0010] In the above solution, the distance between the image acquisition device and the transparent cover is 150 mm to 250 mm.

[0011] In the above solution, the distance between the image acquisition device and the transparent cover is 200 mm.

[0012] In the above scheme, the image acquisition device is a global camera with a pixel of not less than 1200w, and its lens is a focal length lens of 12mm.

[0013] In the above solution, the transparent cover plate is an acrylic plate.

[0014] In the above solution, the device also includes a light source controller connected to the light source, which is used to adjust the brightness of the light source according to environmental parameters and shooting requirements.

[0015] In the above solution, the light source is a hole surface light source with a size of 300*200.

[0016] In the above scheme, the preset particle size alarm value is 3mm.

[0017] A second aspect of the present invention provides a method for monitoring product quality based on machine vision, the method comprising:

[0018] During the powder material feeding process, a real-time image of the powder material is obtained by an image acquisition device, wherein the image acquisition device is installed in the feeding pipeline;

[0019] Based on the BLOB analysis function, the smallest circle that can completely surround the BLOB is determined according to the real-time image, and the diameter of the smallest circle is mapped to the pixel points of the real-time image to determine the corundum particle size value of the powder according to the occupied number of the pixel points;

[0020] When the corundum particle size value is greater than the preset particle size alarm value, the unloading bin is controlled to stop working so as to control the powder to stop unloading into the finished product bin.

[0021] According to a third aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods described in the first aspect are implemented.

[0022] The present invention provides a device, method and medium for monitoring product quality based on machine vision. The device includes an image acquisition device installed in a feeding pipe, and the image acquisition device is used to obtain a real-time image of the powder during the feeding process and transmit it to a processor; a transparent cover plate is located at an observation port at a particle pipe; a light source is used to provide shooting lighting for the image acquisition device; and a processor is used to analyze the real-time image to determine the corundum particle size value of the powder, and when the corundum particle size value is greater than a preset particle size alarm value, control the feeding bin to stop working to control the powder to stop feeding into the finished product bin. The device can realize real-time and accurate detection of powder, overcome the error and hysteresis of manual detection results, and improve product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0024] Figure 1 A schematic diagram of the structure of a device for monitoring product quality based on machine vision according to an embodiment of the present invention is shown;

[0025] Figure 2 A specific schematic diagram of a device for monitoring product quality based on machine vision according to an embodiment of the present invention is shown;

[0026] Figure 3 A flow chart of a method for monitoring product quality based on machine vision according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0027] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0028] In one embodiment, Figure 1 As shown, a device for monitoring product quality based on machine vision is provided, the device includes an image acquisition device 1, a transparent cover plate 2, a light source 3 and a processor 4; wherein,

[0029] The image acquisition device 1 is installed in the feeding pipe. The image acquisition device is used to obtain the real-time image of the powder material and transmit it to the processor during the powder material feeding process.

[0030] The transparent cover plate 2 is located at the observation port of the particle pipeline.

[0031] Light source 3 is used to provide shooting lighting for the image acquisition device.

[0032] Processor 4 is used to analyze the real-time image to determine the corundum particle size value of the powder, and when the corundum particle size value is greater than the preset particle size alarm value, control the unloading bin to stop working so as to control the powder to stop unloading to the finished product bin.

[0033] In this embodiment, the powder refers to the corundum particles produced in the production process of the corundum product. Figure 2The schematic diagram of the device for monitoring product quality based on machine vision is shown in FIG. A section of the feeding pipe after the finished product is screened can be selected for opening, and then an image acquisition device can be installed at this position. In order to ensure the quality of the image, the image acquisition device can use a high-speed camera to capture the flowing powder during the feeding process. Figure 2 As shown, the device may further include a bracket, on which a power supply for powering the image acquisition device may be installed. The power supply may also be used to power the light source. The processor may be a computer, which is used to monitor based on real-time images. Specifically, the real-time image may be analyzed to determine the corundum particle size value of the powder, and when the corundum particle size value is greater than a preset particle size alarm value, the unloading bin is controlled to stop working to control the powder to stop unloading to the finished product bin.

[0034] In a specific embodiment, the image acquisition device may use a global camera with a pixel of not less than 1200w, and the lens thereof may have a focal length of 12mm.

[0035] In order to cooperate with the camera shooting, the cover of the original observation port at the particle pipeline can be replaced with a transparent cover. In one embodiment, the transparent cover can be an acrylic plate. Further, in order to ensure the sealing of the scene and the light transmittance of the detection position, the distance between the image acquisition device and the transparent cover is 150mm to 250mm.

[0036] In one embodiment, the distance between the image acquisition device and the transparent cover is 200 mm.

[0037] In one embodiment, according to the actual field of view of the on-site inspection port, a 300*200 hole surface light source can be selected as the light source of the device for monitoring product quality based on machine vision. Furthermore, a light source controller can also be provided. The light source controller is connected to the light source and is used to adjust the brightness of the light source according to environmental parameters and shooting requirements.

[0038] In one embodiment, the device for monitoring product quality based on machine vision has the function of retaining abnormal images, which is convenient for subsequent quality management and tracing. The abnormal image refers to an image in which the corundum particle size value is detected to be greater than the preset particle size alarm value.

[0039] In one embodiment, the preset particle size alarm value can be set to a corresponding value according to different corundum types. In a specific embodiment, the preset particle size alarm value can be set to 3mm. That is, when the processor detects that the corundum particle size value of the powder is greater than 3mm, the alarm function will be activated, and the feeding bin will be controlled to stop working to control the powder to stop feeding into the finished product bin, thereby preventing large particles of powder from falling into the finished product bin.

[0040] Based on the same inventive concept as the above-mentioned embodiment, the present invention also provides a method for monitoring product quality based on machine vision, such as Figure 3 As shown, the method mainly includes the following steps:

[0041] S310, during the powder material feeding process, a real-time image of the powder material is obtained by an image acquisition device, wherein the image acquisition device is installed in the feeding pipeline.

[0042] S311, based on the BLOB analysis function, the smallest circle that can completely surround the BLOB is determined according to the real-time image, and the diameter of the smallest circle is mapped to the pixel points of the real-time image to determine the corundum particle size value of the powder according to the occupied number of pixel points.

[0043] S312, when the corundum particle size value is greater than the preset particle size alarm value, the feeding bin is controlled to stop working to control the powder material to stop feeding into the finished product bin.

[0044] The image acquisition device is used to obtain real-time images of powders during the powder feeding process. The image acquisition device can use a high-speed camera plus a 12mm focal length lens to achieve high-speed capture of flowing powders. Therefore, the real-time image of the powder captured can more clearly present the real-time status of the particles during the falling process. Using the BLOB analysis function, find the smallest circle that can completely surround the BLOB. The diameter of the smallest circle is the minimum circumscribed circle diameter. Specifically, analyze the boundary points of the BLOB and find the two boundary points with the farthest distance. The distance between them is the minimum circumscribed circle diameter. Suppose the boundary point coordinate set of the BLOB is {(x1,y 1, ),(x1,y2),……,(x i ,y i )} can be obtained by the distance d between all points i,j , find the largest d i,j , the calculation formula is:

[0045]

[0046] Multiple d i,jThe maximum value in is the minimum circumscribed circle diameter. Then the minimum circumscribed circle diameter is mapped to the pixel points of the real-time image of the powder, and the actual corundum particle size value can be calculated by calculating the number of occupied pixels. When the actual corundum particle size value is greater than the preset particle size alarm value, such as when the actual corundum particle size value is greater than 3mm, the alarm function can be activated, and the relay can be used to control the unloading bin to stop working to control the powder to stop unloading to the finished product bin, so as to facilitate timely inspection of the equipment and replacement of the screen. Among them, BLOB in computer vision refers to a connected area in the image, and BLOB analysis is to extract and mark the connected domain of the binary image after foreground / background separation. Each marked Blob represents a foreground target, and then some relevant features of the BLOB can be calculated. Its advantage is that information about related areas can be obtained through BLOB extraction.

[0047] In this embodiment, if the image acquisition device captures multiple real-time images, when the first real-time image is processed to calculate the corundum particle size value of the powder, the subsequent images captured will be automatically filtered out until the real-time image being processed is processed. At the same time, in this embodiment, abnormal images can be retained for subsequent quality management traceability. Among them, abnormal images refer to images in which the corundum particle size value is detected to be greater than the preset particle size alarm value.

[0048] In summary, the innovative points of the present invention are divided into two points:

[0049] 1. Improve the BLob algorithm. The improved algorithm optimizes the particle adhesion segmentation process when detecting the corundum particle size, uses adaptive threshold to enhance the contrast, can accurately identify edge information, effectively improves the accuracy and stability of particle size detection, and reduces the misjudgment rate.

[0050] 2. With functional innovation as the core, the device is equipped with a threshold alarm function, which can automatically save image records after the alarm is triggered, and supports remote monitoring by operators. The detection device adopts an integrated functional design, which realizes the automation, visualization and data management of particle size monitoring, effectively improving the convenience and reliability of production monitoring.

[0051] This method of monitoring product quality based on machine vision can change the original manual sampling inspection method every two hours, saving labor input costs. This solution can achieve real-time and accurate detection of powder materials, overcome the errors and lags of manual inspection results, and improve product quality.

[0052] Based on the same inventive concept, this embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any step of the method described above when executing the computer program.

[0053] Based on the same inventive concept, this embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the methods described above are implemented.

[0054] Through one or more embodiments of the present invention, the present invention has the following beneficial effects or advantages:

[0055] The present invention provides a device, method and medium for monitoring product quality based on machine vision. The device includes an image acquisition device installed in a feeding pipe, and the image acquisition device is used to obtain a real-time image of the powder during the feeding process and transmit it to a processor; a transparent cover plate is located at an observation port at a particle pipe; a light source is used to provide shooting lighting for the image acquisition device; and a processor is used to analyze the real-time image to determine the corundum particle size value of the powder, and when the corundum particle size value is greater than a preset particle size alarm value, control the feeding bin to stop working to control the powder to stop feeding into the finished product bin. The device can realize real-time and accurate detection of powder, overcome the error and hysteresis of manual detection results, and improve product quality.

[0056] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0057] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0058] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0059] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0060] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0061] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all functions of some or all components of a gateway, proxy electronic device, or system according to an embodiment of the present invention. The present invention may also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0062] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0063] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0064] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A device for monitoring product quality based on machine vision, characterized in that: The device comprises: An image acquisition device is installed in the feeding pipe, and is used to obtain a real-time image of the powder material during the feeding process of the powder material and transmit it to the processor; Transparent cover, observation port located at the particle pipe; A light source, used to provide lighting for the image acquisition device; The processor is used to analyze the real-time image to determine the corundum particle size value of the powder, and when the corundum particle size value is greater than a preset particle size alarm value, control the unloading bin to stop working so as to control the powder to stop unloading into the finished product bin.

2. The device according to claim 1, characterized in that The distance between the image acquisition device and the transparent cover plate is 150 mm to 250 mm.

3. The device according to claim 2, characterized in that The distance between the image acquisition device and the transparent cover is 200 mm.

4. The device according to claim 1, characterized in that The image acquisition device is a global camera with a pixel of not less than 1200w, and its lens has a focal length of 12mm.

5. The device according to claim 1, characterized in that The transparent cover plate is an acrylic plate.

6. The device according to claim 1, characterized in that The device also includes a light source controller connected to the light source, which is used to adjust the brightness of the light source according to environmental parameters and shooting requirements.

7. The device according to claim 1, characterized in that The light source is a 300*200 aperture surface light source.

8. The device according to claim 1, characterized in that The preset particle size alarm value is 3 mm.

9. A method for monitoring product quality based on machine vision, characterized in that: The method comprises: During the powder material feeding process, a real-time image of the powder material is obtained by an image acquisition device, wherein the image acquisition device is installed in the feeding pipeline; Based on the BLOB analysis function, the smallest circle that can completely surround the BLOB is determined according to the real-time image, and the diameter of the smallest circle is mapped to the pixel points of the real-time image to determine the corundum particle size value of the powder according to the occupied number of the pixel points; When the corundum particle size value is greater than the preset particle size alarm value, the unloading bin is controlled to stop working so as to control the powder to stop unloading into the finished product bin.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to claim 9 are implemented.

Images