Method and system for adjusting rotating speed of ball mill

Abstract

The invention provides a ball mill rotating speed adjusting method and system. The method comprises the steps that a motion state image of a steel ball in a ball mill roller is obtained; standardizing the motion state image of the steel ball to obtain a standard image; performing graying processing on the standard image to obtain a grayscale image; performing binarization processing on the grayscale image to obtain a binarized image; and extracting a characteristic value in the binarized image so as to adjust the rotating speed of the roller of the ball mill according to the characteristic value. The method comprises the following steps: acquiring a motion state image of a steel ball in a ball mill roller in real time, processing the motion state image of the steel ball, judging motion state information of the steel ball in the ball mill roller by utilizing an image recognition algorithm, and then adjusting the rotating speed of the ball mill roller according to the motion state information of the steel ball in the ball mill roller. The problem that it is difficult to control the ball mill to obtain ideal roller rotating speed is solved.

Description

Technical Field

[0001] The present application relates to the technical field of ball mills, and specifically includes a method and system for adjusting the rotation speed of a ball mill. Background Art

[0002] A ball mill is a mechanical device that uses a rotating cylinder to cause the internal grinding media (such as steel balls) to impact and rub the material, thereby achieving material crushing. The ball mill is mainly composed of a feeding device, a supporting device, a rotating part, a discharging device and a transmission device. Among them, the rotating part includes the cylinder and the grinding media, which is the core component of the ball mill. When the material to be ground enters the ball mill from the feeding end, it is usually fed continuously and evenly through a screw conveyor or a bucket elevator. The ball mill is equipped with grinding media, usually steel balls, cast iron balls or spheres made of other hard materials. These spheres rise and fall as the cylinder rotates, causing impact and friction on the material. When the ball mill is started, the cylinder inside it begins to rotate. The speed of the cylinder can be adjusted according to the properties of the material and the grinding requirements, generally between tens of revolutions per minute and hundreds of revolutions per minute. As the cylinder rotates, the material falls freely under the action of gravity, meets the rising grinding media and is impacted and crushed. In this process, the material particles gradually become smaller until they reach the required particle size.

[0003] Among them, the grinding efficiency of the ball mill is an important indicator of the operation of the equipment. The key factor affecting the grinding efficiency is the movement state of the steel balls in the drum, which is affected by the material filling rate and the drum speed. Therefore, when the material filling rate is constant, the movement form of the steel balls in the ball mill is mainly affected by the drum speed.

[0004] Therefore, in the prior art, the drum speed can be obtained through industrial tests or calculated through empirical formulas. Although industrial tests are highly reliable, they are labor-intensive and time-consuming. Although empirical formula calculation is a simple and effective method, the theoretical basis of various empirical formulas is different, and the calculation results vary greatly. In addition, the correction coefficient of the empirical formula is not adaptable and universal to changes in material conditions and working environments, and has great limitations. In practice, production enterprises often use manual adjustment methods to make the ball mill run at the ideal drum speed. The disadvantage is that it is highly dependent on the experience of production personnel and cannot achieve intelligent identification and automatic adjustment of the ball mill's operating status. Summary of the invention

[0005] The present application provides a ball mill speed adjustment method and system to solve the problem of difficulty in controlling the ball mill to obtain an ideal drum speed.

[0006] In a first aspect, the present application provides a method for adjusting the rotation speed of a ball mill, comprising:

[0007] Obtain the motion state image of the steel balls in the ball mill drum;

[0008] Standardizing the steel ball motion state image to obtain a standard image;

[0009] Performing grayscale processing on the standard image to obtain a grayscale image;

[0010] Performing binarization processing on the grayscale image to obtain a binarized image;

[0011] Extracting feature values ​​from the binary image to adjust the rotation speed of the ball mill drum according to the feature values.

[0012] Optionally, obtaining the image of the motion state of the steel balls in the drum of the ball mill includes:

[0013] Taking a real-time image of the inside of the ball mill drum;

[0014] Calling the determination condition corresponding to the real-time image;

[0015] If the real-time image meets the determination condition, generating the steel ball motion state image;

[0016] If the real-time image does not meet the determination condition, the real-time image inside the ball mill drum is re-photographed.

[0017] Optionally, after the step of calling the determination condition corresponding to the real-time image, the method further includes:

[0018] Detecting sampling parameters of the real-time image, wherein the sampling parameters include contrast, brightness, restored color, and resolution;

[0019] Parsing parameter intervals in the determination conditions, the parameter intervals including a contrast interval, a brightness interval, a restored color interval, and a resolution interval;

[0020] If all items in the sampling parameters are within the corresponding parameter interval, it is determined that the real-time image meets the determination condition;

[0021] If any one of the sampling parameters is not within the corresponding parameter interval, it is determined that the real-time image does not meet the determination condition.

[0022] Optionally, standardizing the steel ball motion state image to obtain a standard image includes:

[0023] Obtaining the center point coordinates of the steel ball motion state image;

[0024] Obtaining a movement equation for moving the center point coordinates to the origin coordinates;

[0025] According to the movement equation, the steel ball motion state image is moved to obtain a first image;

[0026] The first image is divided into a first quadrant, a second quadrant, a third quadrant and a fourth quadrant at an origin to obtain the standard image.

[0027] Optionally, performing grayscale processing on the standard image to obtain a grayscale image includes:

[0028] Acquire RGB color features in the standard image;

[0029] A grayscale image is generated according to the RGB color features.

[0030] Optionally, performing binarization processing on the grayscale image to obtain a binarized image includes:

[0031] Set the image binarization threshold;

[0032] Traversing each pixel in the grayscale image to obtain the grayscale value corresponding to the pixel;

[0033] The grayscale values ​​of the pixels whose grayscale values ​​are greater than the image binarization threshold are set to 255, and the grayscale values ​​of the pixels whose grayscale values ​​are greater than the image binarization threshold are set to 0, so as to obtain a binary image.

[0034] Optionally, extracting the feature value in the binary image includes:

[0035] Dividing a first quadrant in the binary image into a first region and a second region;

[0036] Obtaining a pixel value of each pixel point in the first area to obtain a plurality of first pixel values;

[0037] Obtaining a pixel value of each pixel point in the second area to obtain a plurality of second pixel values;

[0038] Performing a summation calculation on the first pixel value to obtain a first eigenvalue;

[0039] A summation calculation is performed on the second pixel value to obtain a second eigenvalue.

[0040] Optionally, adjusting the rotation speed of the ball mill drum according to the characteristic value includes:

[0041] If the first characteristic value and the second characteristic value are within a first preset range, controlling the rotation speed of the ball mill drum to increase;

[0042] If the first characteristic value is within the second preset range and the second characteristic value is within the first preset range, the rotation speed of the ball mill drum is controlled to remain unchanged;

[0043] If the first characteristic value is within the first preset range and the second characteristic value is within the third preset range, the rotation speed of the ball mill drum is controlled to decrease.

[0044] In a second aspect, the present application provides a ball mill speed adjustment system, which is applied to the ball mill speed adjustment method described in the first aspect, and includes: a camera and a controller; the camera is arranged at one end of the ball mill drum; the camera is arranged on the central axis of the ball mill drum; the camera is connected to the controller;

[0045] The camera is configured to: obtain an image of the motion state of the steel balls in the drum of the ball mill;

[0046] The controller is configured to:

[0047] Standardizing the steel ball motion state image to obtain a standard image;

[0048] Performing grayscale processing on the standard image to obtain a grayscale image;

[0049] Performing binarization processing on the grayscale image to obtain a binarized image;

[0050] Extracting feature values ​​from the binary image to adjust the rotation speed of the ball mill drum according to the feature values.

[0051] Optionally, an auxiliary light source is further included, wherein the auxiliary light source is arranged at one end of the ball mill drum away from the camera, and the auxiliary light source is arranged on the central axis of the ball mill drum.

[0052] It can be seen from the above technical solutions that the present application provides a method and system for adjusting the speed of a ball mill, the method comprising: obtaining a motion state image of a steel ball in a ball mill drum; standardizing the motion state image of the steel ball to obtain a standard image; graying the standard image to obtain a gray image; binarizing the gray image to obtain a binarized image; extracting feature values ​​from the binarized image to adjust the speed of the ball mill drum according to the feature values. The motion state image of the steel ball in the ball mill drum is obtained in real time, and after processing the motion state image of the steel ball, an image recognition algorithm is used to determine the motion state information of the steel ball in the ball mill drum, and then the speed of the ball mill drum is adjusted according to the motion state information of the steel ball in the ball mill drum, so as to solve the problem of difficulty in controlling the ball mill to obtain an ideal drum speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0054] Figure 1 A flow chart of a ball mill speed adjustment method provided in an embodiment of the present application;

[0055] Figure 2 A schematic diagram of the falling motion of a steel ball provided in an embodiment of the present application;

[0056] Figure 3 A schematic diagram of the falling motion of a steel ball provided in an embodiment of the present application;

[0057] Figure 4 A schematic diagram of the circular motion of a steel ball provided in an embodiment of the present application;

[0058] Figure 5 A schematic diagram of a standard image provided in an embodiment of the present application;

[0059] Figure 6 A schematic diagram of the first region and the second region images provided in an embodiment of the present application;

[0060] Figure 7 Schematic diagram of the ball mill speed adjustment system provided in an embodiment of the present application.

[0061] Reference numerals:

[0062] Among them, 1-controller; 2-ball mill drum; 3-camera; 4-auxiliary light source. DETAILED DESCRIPTION

[0063] The following embodiments are described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following embodiments do not represent all implementations consistent with the present application. They are only examples of systems and methods consistent with some aspects of the present application as detailed in the claims.

[0064] A ball mill is a mechanical device that uses a rotating cylinder to cause the internal grinding media (such as steel balls) to impact and rub the material, thereby achieving material crushing. The ball mill is mainly composed of a feeding device, a supporting device, a rotating part, a discharging device and a transmission device. Among them, the rotating part includes the cylinder and the grinding media, which is the core component of the ball mill. When the material to be ground enters the ball mill from the feeding end, it is usually fed continuously and evenly through a screw conveyor or a bucket elevator. The ball mill is equipped with grinding media, usually steel balls, cast iron balls or spheres made of other hard materials. These spheres rise and fall as the cylinder rotates, causing impact and friction on the material. When the ball mill is started, the cylinder inside it begins to rotate. The speed of the cylinder can be adjusted according to the properties of the material and the grinding requirements, generally between tens of revolutions per minute and hundreds of revolutions per minute. As the cylinder rotates, the material falls freely under the action of gravity, meets the rising grinding media and is impacted and crushed. In this process, the material particles gradually become smaller until they reach the required particle size.

[0065] Among them, the grinding efficiency of the ball mill is an important indicator of the operation of the equipment. The key factor affecting the grinding efficiency is the movement state of the steel balls in the drum, which is affected by the material filling rate and the drum speed. Therefore, when the material filling rate is constant, the movement form of the steel balls in the ball mill is mainly affected by the drum speed.

[0066] When the rolling speed is low, the steel ball performs a falling motion in the drum, and its motion form is as follows: Figure 2 As shown in the figure, at this time, the grinding efficiency of the ball mill is low. As the drum speed increases, when the speed value reaches a certain moderate range, the steel balls will fall in the drum, and its movement form is as follows: Figure 3 As shown in the figure, at this time, the grinding efficiency of the ball mill is relatively high. As the drum speed continues to increase, when the speed value exceeds the drum speed range required by the previous motion form, the steel balls and logistics will perform uniform circular motion in the drum due to the centrifugal force, and its motion form is as follows: Figure 4 As shown, at this time, the grinding efficiency of the ball mill is low.

[0067] In actual production, in order to obtain higher grinding efficiency, it is necessary to adjust the drum speed of the ball mill to the ideal drum speed so that the steel balls in the drum can be thrown down. However, the logistics filling rate in the drum is not constant due to different working conditions, so the ideal drum speed of the ball mill also changes due to different working conditions. Among them, the ideal drum speed can be obtained through industrial time experiments or calculated through empirical formulas. Although industrial experiments have high reliability, they are labor-intensive and time-consuming. Although empirical formula calculation is a simple and effective method, the theoretical basis of various empirical formulas is different, and the calculation results vary greatly. In addition, the correction coefficient of the empirical formula is not adaptable and universal to changes in material conditions and working environment, and has great limitations. In practice, production enterprises often use manual adjustment methods to make the ball mill run at the ideal drum speed. The disadvantage is that it is highly dependent on the experience of production personnel and cannot achieve intelligent identification and automatic adjustment of the operating status of the ball mill.

[0068] In order to solve the problem of difficulty in controlling the ball mill to obtain an ideal drum speed, the present application embodiment provides a ball mill speed adjustment method, see Figure 1 , including:

[0069] S100: Acquire a motion state image of the steel balls in the drum of the ball mill.

[0070] Wherein, obtaining the motion state image of the steel balls in the drum of the ball mill includes shooting the real-time image in the drum of the ball mill.

[0071] Specifically, by setting up a camera, real-time images of the ball mill drum are captured at certain intervals. For example, the camera is set at the opening of the ball mill drum and the camera is started every 1 minute to obtain images of the movement status of the steel balls. After obtaining the images of the movement of the steel balls, it is necessary to determine whether the real-time images captured by the camera meet the requirements.

[0072] Therefore, the judgment conditions corresponding to the real-time image can be called.

[0073] If the real-time image meets the judgment conditions, a steel ball motion state image is generated.

[0074] If the real-time image does not meet the judgment condition, the real-time image inside the ball mill drum is re-photographed.

[0075] The determination conditions corresponding to calling the real-time image specifically include:

[0076] Detect the sampling parameters of real-time images, including contrast, brightness, restored color, and resolution.

[0077] The parameter interval is parsed in the judgment condition, and the parameter interval includes a contrast ratio interval, a brightness interval, a restored color interval, and a resolution interval.

[0078] If all items in the sampling parameters are within the corresponding parameter range, it is determined that the real-time image meets the determination condition.

[0079] If any item of the sampling parameters is not within the corresponding parameter range, it is determined that the real-time image does not meet the determination condition.

[0080] For example, when the real-time image is completely black, its contrast, brightness, color restoration, resolution and other parameters do not meet the judgment conditions, which means that the real-time image is unqualified and it is necessary to re-take the real-time image inside the ball mill drum. When the parameters of the real-time image meet the judgment conditions, it means that the real-time image is qualified and can continue to be processed.

[0081] S200: Standardizing the steel ball motion state image to obtain a standard image.

[0082] After obtaining the steel ball motion state image, it is also necessary to perform standardization on the steel ball motion state image to facilitate processing and analysis. The standardization of the steel ball motion state image to obtain a standard image specifically includes:

[0083] S210: Obtain the center point coordinates of the steel ball motion state image.

[0084] S220: Obtain a movement equation for moving the center point coordinates to the origin coordinates.

[0085] S230: According to the movement equation, the steel ball motion state image is moved to obtain a first image.

[0086] S240: Divide the first image into a first quadrant, a second quadrant, a third quadrant, and a fourth quadrant at the origin to obtain a standard image.

[0087] Among them, since the cross-section of the drum is circular, in the process of shooting the steel ball motion state image, the circular area is the effective information area. Therefore, in order to facilitate image processing, it is necessary to obtain the coordinates of the center point of the steel ball motion state image, and then move the center point coordinates to the origin. After obtaining the movement equation, the circular area can be moved as a whole according to the movement equation, so that the circular area in the steel ball motion state image is moved to the center point. For example, the center point coordinates of the steel ball motion state image are (4, 5), and the origin coordinates are (0, 0), then the movement equation is (x-4, y-5); then the X coordinates of the pixels in the circular area are reduced by 4, and the Y coordinates are reduced by 5, so that the image is translated as a whole. After obtaining the first image, as shown in Figure 5 As shown, the first image is divided into four regions, namely the first quadrant, the second quadrant, the third quadrant and the fourth quadrant, to obtain a standard image.

[0088] S300: grayscale processing is performed on the standard image to obtain a grayscale image.

[0089] Among them, simplifying image information is one of the main purposes of grayscale processing. Grayscale images only contain brightness information. Compared with the color information of the three channels of red, green, and blue in standard images, grayscale images are more simplified, reducing the amount of data that needs to be processed. It can reduce the demand for computation and storage space and improve processing speed. Secondly, removing redundant information is also an important reason for grayscale. In the process of graphic recognition, when color information is not key information, it is necessary to pay attention to the contour and structure information of the image. Grayscale can remove the interference of color information, highlight the contour and details of the image, and thus better perform feature extraction and recognition. In addition, improving computational efficiency is another important reason for grayscale. Compared with color images, grayscale images have smaller computational complexity and faster processing speed. For large-scale image recognition tasks, grayscale can improve the efficiency of the algorithm and reduce computing time and resource consumption.

[0090] Therefore, since the standard image has a large amount of information, when performing image recognition, the standard image needs to be grayed out to improve the recognition speed. Therefore, the steps of graying out the standard image to obtain a gray image include:

[0091] S310: RGB color features in the standard image.

[0092] S320: Generate a grayscale image according to the RGB color features.

[0093] Among them, the RGB color feature is composed of the three components R, G, and B in the standard image. The maximum method, average method, and weighted average method can be used to generate grayscale graphics based on the RGB color feature. Among them, the maximum value is to take the maximum value of the three components of R, G, and B. The formula is R=G=B=max(R,G,B). The average method is to take the average value of the three components of R, G, and B. The formula is R=G=B=(R+G+B) / 3. The weighted average method is to weight the three components. Since the human eye is more sensitive to green and the least sensitive to blue, the three components of R, G, and B can be weighted. The formula is Gray(i, j)=0.299×R(i, j)+0.578×G(i, j)+0.114×B(i, j), where i represents the position of the pixel in the row of the image, and j represents the position of the pixel in the column of the image. Through the RGB color feature, the standard image can be converted into a grayscale image.

[0094] S400: performing binarization processing on the grayscale image to obtain a binarized image.

[0095] The specific steps of binarizing the grayscale image include:

[0096] Set the image binarization threshold.

[0097] Traverse each pixel in the grayscale image to obtain the grayscale value corresponding to the pixel.

[0098] The grayscale values ​​of pixels whose grayscale values ​​are greater than the image binarization threshold are set to 255, and the grayscale values ​​of pixels whose grayscale values ​​are greater than the image binarization threshold are set to 0 to obtain a binary image.

[0099] Among them, the binarization threshold can be determined by experiment during the debugging process to determine an optimal binarization threshold, so as to remove the interference structure in the image by binarizing the grayscale image. It can be understood that if the grayscale value of the pixel point whose grayscale value is greater than the image binarization threshold is set to 255, the pixel point will become black, and if the grayscale value of the pixel point whose grayscale value is less than the image binarization threshold is set to 0, the pixel point will become white.

[0100] S500: extracting feature values ​​from the binary image to adjust the rotation speed of the ball mill drum according to the feature values.

[0101] The specific steps of extracting the feature value in the binary image include:

[0102] S510: Divide the first quadrant in the binary image into a first region and a second region.

[0103] S520: Obtain a pixel value of each pixel point in the first area to obtain a plurality of first pixel values.

[0104] S530: Obtain the pixel value of each pixel point in the second area to obtain a plurality of second pixel values.

[0105] S540: Perform a summation calculation on the first pixel value to obtain a first eigenvalue.

[0106] S550: Perform a summation calculation on the second pixel value to obtain a second eigenvalue.

[0107] Among them, when the steel balls are falling in the drum, fewer steel balls will pass through the first quadrant, when the steel balls are falling, more steel balls will pass through the first area of ​​the first quadrant, and when the steel balls are in circular motion, more steel balls will pass through the second area of ​​the first quadrant. Therefore, Figure 6As shown, the area where A is located in the first quadrant is the first area, and the area where B is located is the second area. The first pixel value and the second pixel value are obtained by acquiring the pixel values ​​of the pixel points in the first area and the second area, respectively. For example, the pixel values ​​of the pixel points in the first area and the second area are traversed respectively. When the pixel value of the pixel point in the first area is 255, the first pixel value is recorded as 1, and when the pixel value of the pixel point in the second area is 255, the second pixel value is recorded as 1. The first pixel value and the second pixel value can respectively represent the number of steel balls in the first area and the second area, and then the first pixel values ​​in the first area are summed to obtain the first eigenvalue, and the second pixel values ​​in the second area are summed to obtain the second eigenvalue. Then, the movement of the steel balls in the drum can be judged by the first eigenvalue and the second eigenvalue.

[0108] The method of judging the movement of the steel ball in the drum by using the first characteristic value and the second characteristic value specifically includes:

[0109] If the first characteristic value and the second characteristic value are within the first preset range, the rotation speed of the ball mill drum is controlled to increase.

[0110] If the first characteristic value is within the second preset range and the second characteristic value is within the first preset range, the rotation speed of the ball mill drum is controlled to remain unchanged.

[0111] If the first characteristic value is within the first preset range and the second characteristic value is within the third preset range, the rotation speed of the ball mill drum is controlled to decrease.

[0112] Among them, the first preset range, the second preset range and the third preset range can be adjusted during the debugging process, the maximum value of the first preset range is less than the minimum value of the second preset range, and the maximum value of the second preset range is less than the minimum value of the third preset range. For example, the first preset range is 0-3, the second preset range is 10-20, and the third preset range is 50-60; that is, when the first eigenvalue and the second eigenvalue are both within the first preset range, it means that in the first quadrant, the number of steel balls is small, and the operating state reflected by the current image is that the steel balls are falling in the drum, and the drum speed needs to be increased. When the first eigenvalue is within the second preset range and the second eigenvalue is within the first preset range, it means that the number of steel balls in the first area is medium, and the number of steel balls in the second area is small. The operating state reflected by the current image is that the steel balls are falling in the drum, and the drum speed is an ideal speed. When the first eigenvalue is within the first preset range and the second eigenvalue is within the third preset range, it means that the number of steel balls in the first area is small, and the number of steel balls in the second area is large. The operating state reflected by the current image is that the steel balls are circularly moving in the drum, and the drum speed is high, and the speed needs to be reduced. By analyzing the characteristic values ​​of the first area and the second area, the drum speed can be determined, which is convenient and quick. At the same time, it can be understood that the area ratio of the first area and the second area can be adjusted to suit different usage scenarios.

[0113] In some embodiments, Figure 7 As shown, an embodiment of the present application also provides a ball mill speed adjustment system, which is applied to the ball mill speed adjustment method provided in the above embodiment, including: a camera 3, a controller 1; the camera 3 is arranged at one end of the ball mill drum 2; the camera 3 is arranged on the central axis of the ball mill drum 2; the camera 3 is connected to the controller 1.

[0114] The camera 3 is configured to obtain an image of the movement state of the steel balls in the ball mill drum 2 .

[0115] Controller 1 is configured as:

[0116] The steel ball motion state image is standardized to obtain a standard image.

[0117] Perform grayscale processing on the standard image to obtain a grayscale image.

[0118] Perform binarization on the grayscale image to obtain a binarized image.

[0119] The feature values ​​in the binary image are extracted to adjust the rotation speed of the ball mill drum according to the feature values.

[0120] In some embodiments, an auxiliary light source 4 is further included. The auxiliary light source 4 is disposed at one end of the ball mill drum 2 away from the camera 3 , and the auxiliary light source 4 is disposed on the central axis of the ball mill drum 2 .

[0121] It can be seen from the above technical solutions that the present application provides a method and system for adjusting the speed of a ball mill, the method comprising: obtaining a motion state image of a steel ball in a ball mill drum; standardizing the motion state image of a steel ball to obtain a standard image; graying the standard image to obtain a gray image; binarizing the gray image to obtain a binarized image; extracting feature values ​​from the binarized image to adjust the speed of the ball mill drum according to the feature values. By obtaining the motion state image of a steel ball in a ball mill drum in real time and processing the motion state image of a steel ball, an image recognition algorithm is used to determine the motion state information of the steel ball in the ball mill drum, and then the speed of the ball mill drum is adjusted according to the motion state information of the steel ball in the ball mill drum, so as to solve the problem of difficulty in controlling the ball mill to obtain an ideal drum speed.

[0122] Similar parts between the embodiments provided in this application can be referenced to each other. The specific implementation methods provided above are only a few examples under the general concept of this application and do not constitute a limitation on the protection scope of this application. For those skilled in the art, any other implementation methods expanded based on the scheme of this application without creative work belong to the protection scope of this application.

Claims

1. A method for adjusting the rotation speed of a ball mill, characterized in that: include: Obtain the motion state image of the steel balls in the ball mill drum; Standardizing the steel ball motion state image to obtain a standard image; Performing grayscale processing on the standard image to obtain a grayscale image; Performing binarization processing on the grayscale image to obtain a binarized image; Extracting feature values ​​from the binary image to adjust the rotation speed of the ball mill drum according to the feature values.

2. The ball mill speed adjustment method according to claim 1, characterized in that: Obtaining the motion state image of the steel balls in the ball mill drum includes: Taking a real-time image of the inside of the ball mill drum; Calling the determination condition corresponding to the real-time image; If the real-time image meets the determination condition, generating the steel ball motion state image; If the real-time image does not meet the determination condition, the real-time image inside the ball mill drum is re-photographed.

3. The ball mill speed adjustment method according to claim 2, characterized in that: After the step of calling the determination condition corresponding to the real-time image, the method further includes: Detecting sampling parameters of the real-time image, wherein the sampling parameters include contrast, brightness, restored color, and resolution; Parsing parameter intervals in the determination conditions, the parameter intervals including a contrast interval, a brightness interval, a restored color interval, and a resolution interval; If all items in the sampling parameters are within the corresponding parameter interval, it is determined that the real-time image meets the determination condition; If any one of the sampling parameters is not within the corresponding parameter interval, it is determined that the real-time image does not meet the determination condition.

4. The ball mill speed adjustment method according to claim 1, characterized in that: The steel ball motion state image is standardized to obtain a standard image including: Obtaining the center point coordinates of the steel ball motion state image; Obtaining a movement equation for moving the center point coordinates to the origin coordinates; According to the movement equation, the steel ball motion state image is moved to obtain a first image; The first image is divided into a first quadrant, a second quadrant, a third quadrant and a fourth quadrant at an origin to obtain the standard image.

5. The ball mill speed adjustment method according to claim 1, characterized in that: Performing grayscale processing on the standard image to obtain a grayscale image includes: Acquire RGB color features in the standard image; A grayscale image is generated according to the RGB color features.

6. The method for adjusting the rotation speed of a ball mill according to claim 1, characterized in that: Performing binarization processing on the grayscale image to obtain a binarized image includes: Set the image binarization threshold; Traversing each pixel in the grayscale image to obtain the grayscale value corresponding to the pixel; The grayscale values ​​of the pixels whose grayscale values ​​are greater than the image binarization threshold are set to 255, and the grayscale values ​​of the pixels whose grayscale values ​​are greater than the image binarization threshold are set to 0, so as to obtain a binary image.

7. The method for adjusting the speed of a ball mill according to claim 1, characterized in that: Extracting the feature value in the binary image includes: Dividing a first quadrant in the binary image into a first region and a second region; Obtaining a pixel value of each pixel point in the first area to obtain a plurality of first pixel values; Obtaining a pixel value of each pixel point in the second area to obtain a plurality of second pixel values; Performing a summation calculation on the first pixel value to obtain a first eigenvalue; A summation calculation is performed on the second pixel value to obtain a second eigenvalue.

8. The method for adjusting the rotation speed of a ball mill according to claim 7, characterized in that: Adjusting the rotation speed of the ball mill drum according to the characteristic value includes: If the first characteristic value and the second characteristic value are within a first preset range, controlling the rotation speed of the ball mill drum to increase; If the first characteristic value is within the second preset range and the second characteristic value is within the first preset range, the rotation speed of the ball mill drum is controlled to remain unchanged; If the first characteristic value is within the first preset range and the second characteristic value is within the third preset range, the rotation speed of the ball mill drum is controlled to decrease.

9. A ball mill speed adjustment system, applied to the ball mill speed adjustment method according to any one of claims 1 to 8, characterized in that: include: A camera and a controller; the camera is arranged at one end of the ball mill drum; the camera is arranged on the central axis of the ball mill drum; The camera is connected to the controller; The camera is configured to: obtain an image of the motion state of the steel balls in the drum of the ball mill; The controller is configured to: Standardizing the steel ball motion state image to obtain a standard image; Performing grayscale processing on the standard image to obtain a grayscale image; Performing binarization processing on the grayscale image to obtain a binarized image; Extracting feature values ​​from the binary image to adjust the rotation speed of the ball mill drum according to the feature values.

10. The ball mill speed adjustment system according to claim 9, characterized in that: It also includes an auxiliary light source, which is arranged at one end of the ball mill drum away from the camera, and the auxiliary light source is arranged on the central axis of the ball mill drum.

Images