Pellet roll screen gap monitoring and adjustment system

Abstract

The application discloses a kind of pellet roller screen gap monitoring and adjusting system, including high-definition camera, control terminal and roller screen, the gap adjuster is equipped on the roller screen, the gap adjuster, high-definition camera are connected with control terminal, high-definition camera is sent to control terminal after real-time acquisition roller screen image, this control terminal obtains real-time roller screen gap and the situation of material accumulation using pattern recognition algorithm: when gap is greater than the threshold value set, signal is sent to gap adjuster and roller screen gap is reduced in real time, so that it meets screening requirement;When finding material accumulation, signal is sent to gap adjuster and roller screen gap is adjusted to maximum, and material accumulation is discharged into next process.The application uses intelligent vision technology to detect roller screen gap on-line in real time;Through video recognition and gap control, on-line cleaning of roller screen material accumulation is realized, and on-line closed-loop adjustment of roller screen gap is realized.

Description

Technical Field

[0001] This invention relates to the field of roller screen gap control technology, and specifically to a pellet roller screen gap monitoring and adjustment system. Background Technology

[0002] In the pelleting industry, roller screens are used to screen green pellets of different sizes. Therefore, the accuracy of the roller screen gap determines the screening ratio and quality. During long-term production, the roller screen gap will lose accuracy due to wear and tear, or there may be material accumulation problems. Therefore, the detection and automatic adjustment of the roller screen gap plays a very important role in improving the quality of pellets. However, in the current pelleting industry, it is not possible to detect the roller screen gap in real time and form an online closed-loop adjustment, and it is not possible to clean the accumulated material on the roller screen in a timely manner. Summary of the Invention

[0003] The purpose of this invention is to propose a pellet roller screen gap monitoring and adjustment system, which uses a high-definition camera on the raw material conveyor belt to collect real-time images of the roller screen to obtain gap and material accumulation, thereby achieving online closed-loop adjustment.

[0004] To achieve the above objectives, this application proposes a pellet roller screen gap monitoring and adjustment system, including a high-definition camera, a control terminal, and a roller screen. The roller screen is equipped with a gap adjuster. Both the gap adjuster and the high-definition camera are connected to the control terminal. The high-definition camera acquires images of the roller screen in real time and sends them to the control terminal. The control terminal uses a pattern recognition algorithm to obtain the real-time roller screen gap and material accumulation status: when the gap is greater than a set threshold, a signal is sent to the gap adjuster to reduce the roller screen gap in real time to meet the screening requirements; when material accumulation is detected, a signal is sent to the gap adjuster to adjust the roller screen gap to the maximum, allowing the accumulated material to be discharged and proceed to the next process.

[0005] Furthermore, the high-definition camera is installed on the raw material conveyor belt to capture images of the tilting motion of the roller screen.

[0006] Furthermore, the control terminal is equipped with a display screen for displaying the real-time gap of the roller screen and whether there is material accumulation.

[0007] Furthermore, the control terminal uses a pattern recognition algorithm in Python+OpenCV image processing to obtain the gap of the roller screen.

[0008] Furthermore, the pattern recognition algorithm specifically includes:

[0009] First, the cvtColor technology is used to perform grayscale processing on the roller screen image;

[0010] Gaussian Blur is applied to the grayscale image of the roller screen. When smoothing the pixels in the neighborhood of the roller screen image, pixels at different positions are assigned different weights.

[0011] The gradient of each pixel in the smoothed roller screen image is obtained using the Sobel convolution operator;

[0012] Compare the current pixel along the gradient direction. If the pixel is larger than the pixels on both sides, keep it; otherwise, set it to 0.

[0013] Set two thresholds, minVal and maxVal: edge points greater than maxVal are retained, edge points less than minVal are discarded, and edge points between minVal and maxVal are determined to be connected to the true boundary. If they are connected, they are retained; otherwise, they are discarded. The resulting binarized roller screen image is then obtained.

[0014] Furthermore, when the roller screen is unloaded, after the contour positioning and pixel determination, the width corresponding to all pixels in the gap is obtained and the average value is calculated. The average value is the current size of the gap. If the current size is greater than the set threshold, it needs to be adjusted.

[0015] Furthermore, when the roller screen is working, after the contour positioning and pixel are determined, if the material does not undergo effective displacement within a certain period of time, it is considered that the material is stuck and accumulated on the roller screen, and the roller screen needs to be opened to release the material.

[0016] Furthermore, the gradients G_X and G_Y along the horizontal x and vertical y directions are obtained using the following operators:

[0017] K_{GX}=[-101;-202;-101],K_{GY}={-1-2-1;000;121}

[0018] The gradient magnitude G of each pixel is obtained from the gradients G_X and G_Y.

[0019] Compared with the prior art, the above technical solution adopted in this invention has the following advantages: This invention uses intelligent vision technology to perform online real-time detection of the roller screen gap; through video recognition and gap control, it realizes online cleaning of accumulated material on the roller screen and online closed-loop adjustment of the roller screen gap. Attached Figure Description

[0020] Figure 1 Schematic diagram of the pellet roller screen gap monitoring and adjustment system;

[0021] Figure 2 An illustration of Gaussian factor selection when different weights are assigned to pixels at different locations within the neighborhood. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application; that is, the described embodiments are only a part of the embodiments of this application, and not all of them. The components of the embodiments of this application described and shown in the accompanying drawings can typically be arranged and designed in various different configurations.

[0023] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0024] Example 1

[0025] like Figure 1 As shown, this embodiment provides a pellet roller screen gap monitoring and adjustment system, including:

[0026] A high-definition camera is installed on the raw material conveyor belt to capture images of the moving inclined roller screen in real time and send them to the control terminal.

[0027] The control terminal may include a human-machine interface, a server, a power supply system, etc. It uses a pattern recognition algorithm to obtain the real-time roller screen gap and material accumulation status: when the gap is greater than the set threshold, it sends a signal to the gap adjuster to reduce the roller screen gap in real time to meet the screening requirements; when material accumulation is detected, it sends a signal to the gap adjuster to adjust the roller screen gap to the maximum and release the accumulated material to enter the next process.

[0028] The roller screen is equipped with a gap adjuster, which is used to receive signals from the control terminal.

[0029] Preferably, the control terminal is equipped with a display screen for displaying the real-time gap of the roller screen and whether there is material accumulation.

[0030] It should be noted that this invention uses a pattern recognition algorithm in Python + OpenCV image processing to identify the gaps in the roller screen. The steps are as follows:

[0031] S1. First, use cvtColor technology to convert the roller screen image to grayscale;

[0032] Specifically, since the goal of pattern recognition algorithms is edge and contour extraction, and color information is not used as a recognition target, grayscale is performed first, which can easily reduce the amount of computation and improve recognition accuracy and speed. It uses cvtColor technology for grayscale processing.

[0033] S2. Apply Gaussian Blur to the grayscale image of the roller screen. When smoothing the pixels in the neighborhood of the roller screen image, pixels at different positions are assigned different weights.

[0034] Specifically, since edge detection is easily affected by noise in the roller screen image, noise reduction processing is required. When Gaussian Blur smooths the pixels in the image's neighborhood, pixels at different positions within the neighborhood are assigned different weights. The selection of the Gaussian factor, such as... Figure 2 As shown;

[0035] The Gaussian function smooths the image while preserving more of the overall grayscale distribution characteristics of the roller screen image.

[0036] S3. The gradient of each pixel in the smoothed roller screen image is obtained using the Sobel convolution operator;

[0037] Specifically, the location with the strongest grayscale intensity change in the roller screen image refers to the gradient direction. The gradient of each pixel in the smoothed roller screen image can be obtained by the Sobel convolution operator, using the following operators to calculate the gradients G_X and G_Y along the horizontal x and vertical y directions:

[0038] K_{GX}=[-101;-202;-101],K_{GY}={-1-2-1;000;121}

[0039] The gradient magnitude G of each pixel can be obtained from G_X and G_Y, and each pixel is represented by G. For boundaries with drastic changes, the larger the G value, the white the corresponding color.

[0040] S4. Compare the current pixel along the gradient direction. If the pixel is larger than the pixels on both sides, keep it; otherwise, set it to 0.

[0041] Specifically, this step sharpens the blurred boundaries by eliminating a large portion of pixels that are not edges.

[0042] S5. Set two thresholds, minVal and maxVal: retain edge points greater than maxVal, discard edge points less than minVal, and determine whether edge points between minVal and maxVal are connected to the true boundary. If they are connected, retain them; otherwise, discard them. The binarized roller screen image output result is obtained.

[0043] S6. Contour localization and output results:

[0044] When the roller screen is unloaded, after the contour positioning and pixel determination, the width corresponding to all pixels in the gap is obtained and the average value is calculated. The average value is the current size of the gap. If the current size is greater than the set threshold, it needs to be adjusted.

[0045] When the roller screen is working, after the contour positioning and pixel are determined, if the material does not move effectively within a certain period of time (such as 5 minutes), it is considered that the material is stuck and accumulated on the roller screen, and the roller screen needs to be opened to release the material.

[0046] The foregoing description of specific exemplary embodiments of the invention is for illustrative and explanatory purposes. These descriptions are not intended to limit the invention to the precise forms disclosed, and it will be apparent that many changes and variations can be made in accordance with the foregoing teachings. The exemplary embodiments were chosen and described in order to explain the specific principles of the invention and its practical application, thereby enabling those skilled in the art to implement and utilize various different exemplary embodiments of the invention, as well as various different choices and variations. The scope of the invention is intended to be defined by the claims and their equivalents.

Claims

1. A pellet roller screen gap monitoring and adjustment system, characterized in that, The system includes a high-definition camera, a control terminal, and a roller screen. The roller screen is equipped with a gap adjuster. Both the gap adjuster and the high-definition camera are connected to the control terminal. The high-definition camera captures images of the roller screen in real time and sends them to the control terminal. The control terminal uses a pattern recognition algorithm to obtain the real-time roller screen gap and material accumulation status: when the gap is greater than a set threshold, it sends a signal to the gap adjuster to reduce the roller screen gap in real time to meet the screening requirements; when material accumulation is detected, it sends a signal to the gap adjuster to adjust the roller screen gap to the maximum, releasing the accumulated material for the next process. The pattern recognition algorithm specifically includes: First, the cvtColor technology is used to perform grayscale processing on the roller screen image; Gaussian Blur filtering was applied to the grayscale image of the roller screen. When smoothing pixels within the neighborhood of a roller screen image, pixels at different locations are assigned different weights. The gradient of each pixel in the smoothed roller screen image is obtained using the Sobel convolution operator; Compare the current pixel along the gradient direction. If the pixel is larger than the pixels on both sides, keep it; otherwise, set it to 0. Two thresholds, minVal and maxVal, are set: edge points greater than maxVal are retained, edge points less than minVal are discarded, and edge points between minVal and maxVal are determined to be connected to the true boundary. If they are connected, they are retained; otherwise, they are discarded. The binarized roller screen image output is obtained. When the roller screen is unloaded, after the contour positioning and pixel determination, the width corresponding to all pixels in the gap is obtained and the average value is calculated. The average value is the current size of the gap. If the current size is greater than the set threshold, it needs to be adjusted. When the roller screen is working, after the contour positioning and pixel are determined, if the material does not move effectively within a certain period of time, it is considered that the material is stuck and accumulated on the roller screen, and the roller screen needs to be opened to release the material. The gradients G_X and G_Y along the horizontal x and vertical y directions are obtained using the following operators: K_{GX} = [-1 0 1; -2 0 2; -1 0 1], K_{GY} = {-1 -2 -1; 0 0 0; 1 2 1} The gradient magnitude G of each pixel is obtained from the gradients G_X and G_Y.

2. The pellet roller screen gap monitoring and adjustment system according to claim 1, characterized in that, The high-definition camera is installed on the raw material conveyor belt to capture images of the tilting motion of the roller screen.

3. The pellet roller screen gap monitoring and adjustment system according to claim 1, characterized in that, The control terminal is equipped with a display screen to show the real-time gap of the roller screen and whether there is material accumulation.

4. The pellet roller screen gap monitoring and adjustment system according to claim 1, characterized in that, The control terminal uses a pattern recognition algorithm in image processing with Python and OpenCV to obtain the gap of the roller screen.

Images