A condensed pool coal water boundary line video image recognition device and method

Abstract

The application discloses a kind of concentrated pool coal-water interface video image recognition device and method, comprising: sequentially connected concentrated pool fixed module, mobile module, image acquisition module and image processing module;The mobile module uses movable guide rail, under the guidance of the concentrated pool fixed module, the video information in the concentrated pool is collected by the image acquisition module, and based on image processing module, the video information is analyzed and processed, the number of coal particles is obtained, and then the coal-water interface is identified.The application has the characteristics of non-contact and intelligence by image processing method, with the help of the relatively mature image processing technology and data transmission technology, the dependence on hardware such as sensor is lower, and it is easy to upgrade and transform.

Description

Technical Field

[0001] This invention belongs to the field of coal slime deposition thickness measurement technology in thickeners, and specifically relates to a video image recognition device and method for the coal-water boundary line in thickeners. Background Technology

[0002] Coal slime water treatment is a crucial step in the entire coal washing and beneficiation process, affecting the quality of the circulating water and influencing the production efficiency and product quality of the coal preparation plant. Thickening is currently the mainstream method for coal slime water treatment, using the appropriate addition of chemicals to rapidly settle the large number of water-insoluble particles and extremely fine coal slime particles in the coal slime water. Accurately measuring the settling level of water-insoluble particles in the coal slime water is essential to ensure the safe operation of the thickener and improve washing efficiency. Therefore, developing a device that intelligently identifies the coal-water boundary in the thickener tank and calculates its thickness is of great significance.

[0003] Currently, the main traditional detection methods are as follows:

[0004] (1) Manual measurement method

[0005] The manual measurement method involves using a manual probe to measure or detect the motor current or torque to reflect the thickener's operating condition, and then determining the coal-moisture boundary by comparing the measured data with empirical values ​​obtained through manual detection. This method results in low coal slime processing efficiency, high reagent consumption, difficulty in controlling product quality, and is highly subjective, relying heavily on human experience. Furthermore, it is susceptible to fluctuations in grid voltage, leading to significant current variations and unstable thickener operation, which negatively impacts the results and frequently causes errors. Sometimes, misjudgments can even cause coal slime rake accidents, preventing production from meeting requirements.

[0006] (2) Mechanical Measurement Method

[0007] The mechanical measurement principle involves setting a fixed concentration value in the controller. A servo motor drives the concentration detector up and down until the concentration sensor reading equals the set value, thus determining the water-coal boundary. At this point, the thickness of the coal slime is the thickness of the thickener minus the servo motor's movement. When the concentration changes, the controller readjusts the concentration sensor's position until the sensor reading equals the set value. While mechanical detection can measure coal slime thickness, it suffers from complex operation and difficult installation.

[0008] (3) Acoustic wave measurement method

[0009] The ultrasonic measurement method primarily utilizes the reliable principle of ultrasonic echo detection to determine the distance between the sensor probe and the coal-moisture interface, as well as the distance to the ground. It also provides a precise and comprehensive measurement of the coal slime layer thickness. However, practical experience has shown that the speed of sound is easily affected by factors such as sound velocity error, air density, humidity, and temperature, leading to measurement accuracy errors. Therefore, obtaining highly accurate coal slime thickness values ​​using ultrasonic measurement methods is not easily achievable.

[0010] (4) Isotope detection methods

[0011] Isotope detection works on the principle that gamma rays attenuate differently when passing through materials of varying densities. In the interface analyzer, a source emits gamma rays that strike the bottom of the coal slurry. The gamma rays penetrate the slurry and are detected by the detector. The detector adjusts its depth within the slurry based on the attenuation of the rays, ensuring the intensity of the received rays equals a set value, thus determining the coal-water boundary. Because this method uses radiation, it poses certain safety risks.

[0012] The aforementioned studies have implemented various methods for obtaining coal-water boundaries, but each has its own problems. Manual measurement methods are highly subjective and rely solely on personal experience, leading to instability. Mechanical measurement methods are complex to operate and difficult to install. Acoustic measurement methods are affected by too many factors and are inaccurate. Isotope detection methods pose certain safety risks. Therefore, there is an urgent need to find a new method for the safe, accurate, and convenient identification of coal-water boundaries. Summary of the Invention

[0013] The purpose of this invention is to provide a video image recognition device and method for the coal-water boundary line in a thickener, so as to solve the problems existing in the prior art.

[0014] To achieve the above objectives, the present invention provides a video image recognition device for the coal-water boundary line in a thickener, comprising: a thickener fixing module, a moving module, an image acquisition module, and an image processing module connected in sequence;

[0015] The mobile module uses a movable guide rail, which drives the image acquisition module to acquire video information inside the thickening tank under the guidance of the fixed module of the thickening tank. The video information is then analyzed and processed by the image processing module to obtain the number of coal particles and thus identify the coal moisture boundary.

[0016] Optionally, the image processing module is connected to both the image acquisition module and the movable guide rail, and is used to analyze and process the video information acquired by the image acquisition module, and, in conjunction with the operating data of the movable guide rail, identify the coal-water boundary.

[0017] Optionally, the movable guide rail is rotated by a motor, and the motor operation data is uploaded to the image processing module via a counter wheel.

[0018] Optionally, the image acquisition module uses an underwater camera to move along the mobile guide rail to acquire video information from the concentration tank.

[0019] This invention also provides a video image recognition method for the coal-water boundary line in a thickener, comprising the following steps:

[0020] The video information in the concentration tank is acquired, and the video information is processed frame by frame to obtain image information;

[0021] The image information is analyzed and processed to obtain the number of coal particles, and the coal moisture boundary is identified based on the number of coal particles.

[0022] Optionally, the process of analyzing and processing the image information includes: performing Gaussian smoothing on the image information and then grayscale processing; performing adaptive thresholding on the grayscale image to obtain a black and white image of the particles; performing noise reduction processing on the black and white image of the particles, retrieving the outermost contour, extracting the coordinates of the circumscribed rectangle of the contour, and drawing the circumscribed rectangle to obtain the number of coal particles.

[0023] Optionally, the process of identifying the coal-water boundary includes: based on the grayscale image, pre-setting the grayscale values ​​within the circumscribed rectangular area; counting the frequency of each pixel and assigning a value of 0 to the frequency of white pixels; using the grayscale value with the highest frequency in the statistical results as the brightness of the current image frame; when the brightness of two consecutive image frames is 0, the current position of the underwater camera is the location of the coal-water boundary.

[0024] The technical effects of this invention are as follows:

[0025] The coal-water boundary video image recognition device for thickeners designed in this invention analyzes images captured by a camera using image processing methods, identifies the coal-water boundary, records the corresponding movable guide rail data, and finally calculates the coal slime layer thickness. This invention, through image processing, features non-contact and intelligent operation. Leveraging well-developed image processing and data transmission technologies, it has low dependence on hardware such as sensors and is easy to upgrade and modify.

[0026] The identification device proposed in this invention is safe and simple to install, easy to operate, and has clear judgment criteria within the image processing module, reducing the instability of detection.

[0027] The coal slime sedimentation conditions may vary in different locations. This invention allows the recognition device to adapt well to new working environments by modifying the image threshold, exhibiting good adaptability and anti-interference capabilities. Attached Figure Description

[0028] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0029] Figure 1 This is a schematic diagram of the structure of the video image recognition device for the coal-water boundary in the thickener in an embodiment of the present invention;

[0030] Figure 2 This is a flowchart of the video image processing of the coal-water boundary in the thickener in an embodiment of the present invention. Detailed Implementation

[0031] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0032] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0033] Example 1

[0034] like Figure 1 As shown, this embodiment provides a video image recognition device for the coal-water boundary line in a thickener, including: an image acquisition module, a moving module, an image processing module, and a thickener fixing module; the moving module moves using a movable guide rail; the image processing module processes the image using a software program. The software program is connected to the image acquisition module and the movable guide rail respectively, and calculates the number of coal particles in the current image and identifies the coal-water boundary line by using image processing technology, outputting the result; the image acquisition module is connected to the movable guide rail; the movable guide rail is connected to the thickener fixing module; the thickener fixing module is set on the side and top of the thickener.

[0035] The image acquisition module is an underwater camera; the underwater camera supports formats above 1080P.

[0036] The image acquisition module is connected to a movable guide rail, which moves up and down in the same area under the guidance of a fixed device.

[0037] The movable guide rail rotates via a motor; the movable guide rail can return motor operation data to the software program via a counter wheel.

[0038] The software program is connected to the movable guide rail and the image acquisition module; the software program can analyze and process the image information collected by the image acquisition module, and calculate the output result by combining the data returned by the movable guide rail; the software program can display video information, output data, etc. on the software interface.

[0039] This embodiment also provides a video image recognition method for the coal-water boundary line in a thickener, and the recognition process is as follows:

[0040] S1: The image acquisition module moves on the movable guide rail to acquire the video stream;

[0041] S2: The software program extracts image frames from the video stream, processes the images, and calculates the number of coal particles.

[0042] like Figure 2 As shown, as a preferred embodiment, the specific steps are as follows:

[0043] S21: Process the video stream transmitted by the image acquisition module frame by frame. First, use the cv2.GaussianBlue() function to perform Gaussian smoothing on the image using a 3*3 convolution kernel. Then, use the cv2.cvtColor() function to convert the color image to grayscale and proceed to step S622.

[0044] S22: The grayscale image is subjected to adaptive thresholding using the cv2.adaptiveThreshold() function. The adaptive window size is 71 minus a constant value of 2. The threshold is the average value of the pixels in the window. The grayscale value is set to 255 if it is less than the threshold and 0 if it is greater than the threshold, thus obtaining a black and white image of the particles. Proceed to step S623.

[0045] S23: Denoise the black and white image of the particles. First, obtain a 20*20 cross-shaped kernel and a 7*7 rectangular kernel using the cv2.getStructuringElement() function. Then, perform an opening operation using the former kernel using the cv2.morphologyEx() function. After that, perform a dilation operation using the latter kernel using the cv2.dilate() function. Proceed to step S624.

[0046] S24: Using the cv2.findContours() function, only the outermost contour is retrieved, and only the inflection point information of the contour is retained in the contours parameter. Then, the cv2.boundingRect() function is used to obtain the smallest bounding upright rectangle of each contour in contours, and the matrix is ​​numbered and stored in the form of the top left corner coordinates of the rectangle, the width of the rectangle, and the height of the rectangle (x, y, w, h). The accurate coordinates of each vertex of the rectangle are obtained through mathematical operations. Proceed to step S625;

[0047] S25: Output the last rectangle number as the number of particles, and retain the matrix coordinate information.

[0048] S3: The software program determines whether it is a water-coal boundary line by further processing the results;

[0049] As a preferred embodiment, the specific steps are as follows:

[0050] S31: Based on the grayscale image obtained in S621, using the rectangular coordinates retained in S625, the grayscale value within the rectangular area is set to 255 using the cv2.fillPoly() function to eliminate the influence of particles, and then proceed to step S632.

[0051] S32: The frequency of each pixel is counted using the calcHist() function, and then the white hist

[255] is assigned a value of 0, indicating that the white pixel in the image appears 0 times. This operation is approximately equivalent to deleting the particles from the image and keeping only the background. The gray value that appears most frequently in the statistical results is taken as the brightness of the frame, and the process proceeds to step S633;

[0052] S33: When the brightness of two consecutive frames is 0, it is determined that the coal seam has been reached. At this time, the position of the image acquisition module is the water-coal boundary line.

[0053] S4: The result is yes. The software program calculates the thickness value based on the data returned by the movable guide rail and displays the number of particles and the thickness value on the software interface.

[0054] S5: If the result is negative, repeat S1 to S3.

[0055] The coal-water boundary video image recognition device for the thickener designed in this embodiment analyzes the images captured by the camera using image processing methods, identifies the coal-water boundary, records the corresponding movable guide rail data, and finally calculates the coal slime layer thickness. This image processing method is non-contact and intelligent. Utilizing mature image processing and data transmission technologies, it has low dependence on hardware such as sensors and is easy to upgrade. Furthermore, the device is safe, simple to install, and easy to operate. The image processing software program has clear judgment criteria, reducing detection instability. The coal slime sedimentation conditions may vary in different locations; by modifying the image threshold, it can adapt well to new working environments, exhibiting good adaptability and anti-interference capabilities.

[0056] The above description is merely a preferred embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A video image recognition device for the coal-water boundary line in a thickener, characterized in that, include: The concentrator is connected in sequence to a fixed module, a moving module, an image acquisition module, and an image processing module. The mobile module uses a movable guide rail, which drives the image acquisition module to acquire video information in the thickening tank under the guidance of the fixed module of the thickening tank. The video information is then analyzed and processed by the image processing module to obtain the number of coal particles and identify the coal moisture boundary. The method for recognizing the coal-moisture boundary in a thickener based on a video image recognition device includes the following steps: The video information in the concentration tank is acquired, and the video information is processed frame by frame to obtain image information; The image information is analyzed and processed to obtain the number of coal particles, and the coal moisture boundary is identified based on the number of coal particles. The process of analyzing and processing the image information includes: performing Gaussian smoothing on the image information and then grayscale processing; performing adaptive threshold processing on the grayscale image to obtain a black and white image of the particles; performing noise reduction processing on the black and white image of the particles; retrieving the outermost contour of the particles; extracting the coordinates of the circumscribed rectangle of the contour; drawing the circumscribed rectangle; and thus obtaining the number of coal particles. The process of identifying the coal-water boundary includes: based on the grayscale image, preset the grayscale values ​​within the circumscribed rectangular area; count the frequency of each pixel and assign a value of 0 to the frequency of white pixels; take the grayscale value with the highest frequency in the statistical results as the brightness of the current image frame; when the brightness of two consecutive image frames is 0, the current position of the underwater camera is the location of the coal-water boundary.

2. The video image recognition device for the coal-water boundary line in the thickener according to claim 1, characterized in that, The image processing module is connected to the image acquisition module and the movable guide rail respectively, and is used to analyze and process the video information acquired by the image acquisition module, and identify the coal moisture boundary by combining the operating data of the movable guide rail.

3. The video image recognition device for the coal-water boundary line in the thickener according to claim 2, characterized in that, The movable guide rail rotates via a motor, and the motor's operating data is uploaded to the image processing module via a counter wheel.

4. The video image recognition device for the coal-water boundary line in the thickener according to claim 2, characterized in that, The image acquisition module uses an underwater camera that moves along the movable guide rail to acquire video information.

Images