Ore particle granularity detection device and method based on flexible vibration disc

Abstract

The invention provides an ore particle granularity detection device and method based on a flexible vibration disk, and the device comprises the flexible vibration disk which is used for vibrating an ore material at a certain frequency and amplitude, so that the ore material is uniformly distributed and is in a proper posture; the image acquisition device is used for continuously shooting the ore materials on the flexible vibration disc to obtain ore images; the image processing device is used for carrying out preprocessing, segmentation, feature extraction and particle size analysis on the ore image and outputting the ore particle size distribution condition and an accumulative distribution curve; and the result output device is used for displaying the ore image and the granularity analysis result. According to the invention, while material accumulation is prevented, real-time, accurate and efficient detection of attitude distribution of ore materials is realized, and the method has the advantages of low cost of detection equipment, easy maintenance, strong interference resistance, high accuracy and stability of detection results, and the like.

Description

Technical Field

[0001] The invention relates to the field of particle size detection, in particular to a method and system for detecting the particle size composition of an irregularly shaped ore particle group by combining a flexible vibrating disk device with machine vision technology. Background Art

[0002] Ore particle size is a key evaluation indicator to measure the degree of ore crushing, and it is also the main influencing factor affecting the sorting effect of the mineral processing re-selection link. The traditional ore (3-50m) particle size detection often uses the screening method, which has cumbersome measurement steps and long lag time. At present, machine vision technology has been applied to a certain extent in the field of ore particle size detection. By using machine vision technology, non-contact, high-precision and high-efficiency detection of ore particle size can be achieved. Machine vision technology usually uses image sensors to obtain image information of a certain projection surface of ore particles, and extracts the particle size information of the ore by processing and analyzing the image. However, in the actual application process of the particle size detection method based on vision technology, it is impossible to avoid the accumulation, occlusion and bad posture (sideways or upright) of the material to be tested, resulting in large losses and errors in its particle size detection results. According to the shape characteristics of ore particles of different shapes, the present invention proposes a method for classifying ore particles suitable for machine vision recognition, and statistically analyzes the posture distribution of particles of different shapes after vibration through experiments, and predicts the posture of the ore in the recognition results; we use a flexible vibration disk device to effectively disperse the ore particle group, and based on this, study the influence of different vibration intensities and vibration frequencies on the dispersion of ore particles, and set an evaluation index for the position dispersion effect of ore particles to determine whether effective dispersion is achieved after vibration in the present invention. Among them, in order to eliminate the influence of particles in bad postures in the ore particle group on the particle size detection results, we divide all ores into four categories based on the shape characteristics of the ore, using the degree of unidirectional extension (elongation) and bidirectional extension (flatness) of the ore as the division index, and experimentally and statistically analyze the posture distribution probability of ore particles of different shapes, so as to correct the particle size of ore particles in bad postures. Finally, we propose an ore material dispersion detection system based on a flexible vibration disk that integrates posture information. Summary of the invention

[0003] The purpose of the present invention is to provide a device and method for detecting the particle size of ore based on a flexible vibration disk in view of the deficiencies in the prior art. The system can prevent material accumulation while realizing real-time, accurate and efficient detection of the posture distribution of ore materials. The system has the advantages of low cost of detection equipment, easy maintenance, strong anti-interference, high accuracy and stability of detection results, etc.

[0004] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: an ore particle size detection device based on a flexible vibrating disk, comprising: Flexible vibrating plate, used to vibrate the ore material at a certain frequency and amplitude to achieve uniform distribution and appropriate posture; The working principle of the flexible vibration plate is to use the principle of resonance and interference of coherent waves to achieve the process of moving materials in a certain direction to form an arrangement; the flexible vibration plate uses a voice coil motor as a power source, and controls the voice coil motor through a flexible vibration plate controller to control the vibration frequency of the loading plate to reach near the natural frequency of the material, causing the material to resonate and put the material in an active (easy to move) state.

[0005] An image acquisition device is used to continuously photograph the ore material on the flexible vibration plate to obtain an ore image; Image processing device, used for preprocessing, segmenting, feature extraction and particle size analysis of ore images, and outputting ore particle size distribution and cumulative distribution curve; Result output device, used to display ore images and particle size analysis results.

[0006] Preferably, the flexible vibration plate comprises: A loading tray for carrying ore materials, the surface of which is covered with a layer of anti-fouling material; A voice coil motor for driving the tray to vibrate. Four voice coil motors (equivalent to four vibration points) are distributed at the four inner corners of the flexible vibration plate. The voice coil motor includes a magnet and a coil. When an alternating current is passed through the coil, the coil generates a force under the action of the magnet, causing the vibration plate to vibrate. A controller is used to control the frequency, amplitude and phase of the coil current, thereby controlling the frequency, strength and direction of the vibration of the flexible plate.

[0007] Preferably, the image acquisition device comprises an industrial camera, and the industrial camera comprises: a lens for imaging the ore material on the flexible vibrating plate, having adjustable focal length, aperture and viewing angle to accommodate different shooting distances, lighting conditions and shooting ranges; An interface used to transmit electrical signals to a computer. It supports high-speed, high-stability data transmission protocols such as USB3.0, GigE, etc. to ensure the real-time and integrity of the image.

[0008] Preferably, the image processing device comprises a computer host and a display.

[0009] A detection method using the above-mentioned ore particle size detection device based on a flexible vibrating disk comprises the following steps: Step 1: Vibration Dispersion The ore particles are placed on the flexible vibration plate, and the vibration plate is vibrated by driving the voice coil motor. The ore to be tested will be dispersed during the vibration process. Step 2: Image capture An industrial camera is used to capture an original image of the ore material on the flexible vibrating plate and transmit the image to a computer in an image processing device; Step 3: Image Preprocessing The original image is gray-scale converted, noise removed and binarized; the original color image is converted into a gray-scale image to better identify the boundaries and textures of ore particles; the image is filtered using a bilateral filtering algorithm to filter out noise while retaining the edges of ore particles; the image is binarized using a method combining integral images and local thresholds to extract the target ore area, and the algorithm has the characteristics of light adaptability and high efficiency; the binary image is optimized using morphological operations to smooth the edges of ore particles and remove noise in the image; Step 4: Image Segmentation The watershed algorithm, the algorithm based on concave point detection and the ore texture recognition model algorithm based on SVM are used on the pre-processed images to effectively determine the image edges of individual ore particles and accurately divide the materials in the image into individual particles. Step 5: Dispersion Assessment The segmented particle group image is calibrated, and the centroid coordinates of each particle are obtained by particle outer contour detection. The Euclidean distance between the particle position and the average position of all particles in the particle group is calculated as the original data, and its coefficient of variation (CV), that is, the standard deviation of the original data, is calculated. The average of the original data to evaluate the overall dispersion of the particle group; if the obtained coefficient of variation is less than 30%, the vibration dispersion step is started again and the above process is repeated; Step 6: Granularity Calculation According to the segmentation result of each ore particle, the minimum circumscribed rectangle of its projection is obtained, and the two sides of the minimum circumscribed matrix are extracted as l and b respectively; the geometric mean diameter of the particles is calculated as the detection particle size D of the ore, and the calculation formula is as follows: .

[0010] Step 7: Posture distribution and granularity correction Image recognition is used to obtain the three-axis diameters l, b, and h of each ore particle. On this basis, the elongation and flatness of the particle are calculated, and used as the basis for morphological classification. Then, the detected particle size is multiplied by the probability of occurrence of bad postures in each shape and the correction coefficient to obtain the final posture distribution result of the particle group; the posture distribution result of the particle group will help to correct the particle size recognition result.

[0011] Preferably, the dispersion evaluation in the fifth step includes: performing position identification and coordinate statistics on the ore particles after vibration dispersion, and calculating the coordinate position of each ore particle. The average coordinate position of all particles The Euclidean distance , to get the degree to which each particle is away from the center position, the formula is as follows:

[0012] Count and calculate all particles , and calculate its average , and the standard deviation , the formula is as follows:

[0013] By calculating the ratio of the standard deviation to the mean, the coefficient of variation (CV) is obtained as an evaluation index of the position dispersion of the ore particle group. The calculation formula is as follows:

[0014] The coefficient of variation CV can reflect the overall dispersion of the particle group. The larger its value, the more uniform the dispersion between the particles. It is used as an evaluation index of the dispersion of the ore particle group after vibration. Experiments show that when the coefficient of variation is above 30%, the accumulation and obstruction of the ore particles will not have a significant impact on the particle size identification results.

[0015] Preferably, the posture distribution and particle size correction in the seventh step are specifically as follows: classify and count the ore particles according to the shape characteristics of the ore, predict the posture distribution of the ore according to the proportion of different shapes, and correct the particle size of some particles in the ore particles that are in a bad posture; obtain the distribution of the ore particles in shape through visual recognition based on the acquired ore particle images; the morphological classification is based on the following: the three-axis diameter of the ore particle size: height h, width b and length l; set the flatness m and elongation n of the particles, and the formula is as follows:

[0016] According to the flatness m and elongation n of the particles, the shapes of the particles are divided into four categories: block, flake, long flake and columnar, as shown in the following table:

[0017] Through repeated experiments, the proportion of bad posture distribution (sideways, upright) of the above four different shapes of ore particles after vibration and the particle size correction coefficient are as follows:

[0018] According to the proportion of each shape of the identified ore particle group to be tested, multiply it by the proportion of bad postures and the corresponding correction coefficient to obtain the corrected ore particle size result. The calculation formula is as follows: .

[0019] Beneficial effects: The present invention can prevent material accumulation while achieving real-time, accurate and efficient detection of the posture distribution of ore materials. It has the advantages of low cost of detection equipment, easy maintenance, strong anti-interference, high accuracy and stability of detection results, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a structural schematic diagram of an ore particle size detection device based on a flexible vibrating disk of the present invention; Figure 2 It is a flow chart of the ore particle size detection method based on the flexible vibrating plate of the present invention; Figure 3-5 is an example diagram of the ore particle dispersion process and dispersion value in the process of the present invention; wherein Figure 3 This is an example diagram when vibration starts. Figure 4 This is an example diagram of vibration dispersion. Figure 5 This is an example diagram after vibration dispersion is completed; Figure 6-8 is a particle size composition diagram of the particle size recognition result of the present invention, a comparison between the uncorrected recognition result and the manual screening result; wherein Figure 6 As a result of the present invention, Figure 7 For uncorrected results, Figure 8 This is the result of manual screening.

[0021] Explanation of the reference numerals: 1 is a flexible vibration disk, 2 is an image acquisition device, 3 is an image processing device, and 4 is a result output device. DETAILED DESCRIPTION

[0022] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0023] like Figure 1As shown, a device for detecting ore particle size based on a flexible vibrating plate comprises: The flexible vibration plate 1 is used to vibrate the ore material at a certain frequency and amplitude to achieve uniform distribution and a suitable posture; the flexible vibration plate 1 includes: A loading tray for carrying ore materials, the surface of which is covered with a layer of anti-fouling material; A voice coil motor for driving the tray to vibrate. Four voice coil motors (equivalent to four vibration points) are distributed at the four inner corners of the flexible vibration plate. The voice coil motor includes a magnet and a coil. When an alternating current is passed through the coil, the coil generates a force under the action of the magnet, causing the vibration plate to vibrate. A controller is used to control the frequency, amplitude and phase of the coil current, thereby controlling the frequency, strength and direction of the vibration of the flexible plate.

[0024] The image acquisition device 2 is used to continuously photograph the ore material on the flexible vibration plate to obtain the ore image; The image acquisition device 2 comprises an industrial camera, and the industrial camera comprises: a lens for imaging the ore material on the flexible vibrating plate, having adjustable focal length, aperture and viewing angle to accommodate different shooting distances, lighting conditions and shooting ranges; An interface used to transmit electrical signals to a computer. It supports high-speed, high-stability data transmission protocols such as USB3.0, GigE, etc. to ensure the real-time and integrity of the image.

[0025] Image processing device 3, used for preprocessing, segmenting, feature extraction and particle size analysis of ore images, and outputting ore particle size distribution and cumulative distribution curve; The image processing device 3 includes a computer host and a display.

[0026] The result output device 4 is used to display the ore image and the particle size analysis result.

[0027] like Figure 2 As shown, a detection method using the above-mentioned ore particle size detection device based on a flexible vibration disk comprises the following steps: Step 1: Vibration Dispersion The ore particles are placed on the flexible vibration plate, and the vibration plate is vibrated by driving the voice coil motor. The ore to be tested will be dispersed during the vibration process. Step 2: Image capture An industrial camera is used to capture an original image of the ore material on the flexible vibrating plate and transmit the image to a computer in an image processing device; Step 3: Image Preprocessing The original image is gray-scale converted, noise removed and binarized; the original color image is converted into a gray-scale image to better identify the boundaries and textures of ore particles; the image is filtered using a bilateral filtering algorithm to filter out noise while retaining the edges of ore particles; the image is binarized using a method combining integral images and local thresholds to extract the target ore area, and the algorithm has the characteristics of light adaptability and high efficiency; the binary image is optimized using morphological operations to smooth the edges of ore particles and remove noise in the image; Step 4: Image Segmentation The watershed algorithm, the algorithm based on concave point detection and the ore texture recognition model algorithm based on SVM are used on the pre-processed images to effectively determine the image edges of individual ore particles and accurately divide the materials in the image into individual particles. Step 5: Dispersion Assessment The segmented particle group image is calibrated, and the centroid coordinates of each particle are obtained by particle outer contour detection. The Euclidean distance between the particle position and the average position of all particles in the particle group is calculated as the original data, and its coefficient of variation (CV), that is, the standard deviation of the original data, is calculated. The average of the original data to evaluate the overall dispersion of the particle group; if the obtained coefficient of variation is less than 30%, the vibration dispersion step is started again and the above process is repeated; the vibration dispersion and dispersion evaluation results are as follows Figure 3-5 As shown; The dispersion evaluation specifically includes: identifying the position and coordinate statistics of the ore particles after vibration dispersion, and calculating the coordinate position of each ore particle. The average coordinate position of all particles The Euclidean distance , to get the degree to which each particle is away from the center position, the formula is as follows:

[0028] Count and calculate all particles , and calculate its average , and the standard deviation , the formula is as follows:

[0029] By calculating the ratio of the standard deviation to the mean, the coefficient of variation (CV) is obtained as an evaluation index of the position dispersion of the ore particle group. The calculation formula is as follows:

[0030] The coefficient of variation CV can reflect the overall dispersion of the particle group. The larger its value is, the more uniform the dispersion between the particles is. It is used as an evaluation index of the dispersion of the ore particle group after vibration. Through experiments, it is known that when the coefficient of variation is above 30%, the accumulation and shielding of ore particles will not have a significant impact on the particle size identification results. Step 6: Granularity Calculation According to the segmentation result of each ore particle, the minimum circumscribed rectangle of its projection is obtained, and the two sides of the minimum circumscribed matrix are extracted as l and b respectively; the geometric mean diameter of the particles is calculated as the detection particle size D of the ore, and the calculation formula is as follows: ; The measured particle size data is classified according to the particle size. In this example, three particle sizes, 0-8mm, 8-16mm and 16-25mm, are used as classification. After the particle size results are counted, the particle size composition of each particle size is calculated as follows: Number percentage = (number of particles of this particle size / total number of particles of all particle sizes) × 100%; Step 7: Posture distribution and granularity correction Image recognition is used to obtain the three-axis diameters l, b, and h of each ore particle. On this basis, the elongation and flatness of the particle are calculated and used as the basis for morphological classification. The detected particle size is then multiplied by the probability of occurrence of bad postures in each shape and the correction coefficient to obtain the final posture distribution result of the particle group. The posture distribution result of the particle group will help to correct the particle size recognition result. In this example, columnar limestone particles are selected as a demonstration.

[0031] The posture distribution and particle size correction are as follows: classify and count the ore particles according to the shape characteristics of the ore, predict the posture distribution of the ore according to the proportion of different shapes, and correct the particle size of some particles in the ore particles that are in a bad posture; obtain the distribution of the ore particles in shape through visual recognition based on the acquired ore particle images; the morphological classification is based on the following: the three-axis diameter of the ore particle size: height h, width b and length l; set the flatness m and elongation n of the particles, and the formula is as follows:

[0032] According to the flatness m and elongation n of the particles, the shapes of the particles are divided into four categories: block, flake, long flake and columnar, as shown in the following table:

[0033] Through repeated experiments, the proportion of bad posture distribution (sideways, upright) of the above four different shapes of ore particles after vibration and the particle size correction coefficient are as follows: According to the proportion of each shape of the identified ore particle group to be tested, multiply it by the proportion of bad postures and the corresponding correction coefficient to obtain the corrected ore particle size result. The calculation formula is as follows: .

[0034] Step 8: Result verification The accuracy of the present invention is evaluated by comparing the test results of the particle size detection method of the present invention, the general machine vision particle size detection method and the manual screening method on the particle group to be tested composed of ore particles. The results are shown in the following table: In addition, the particle size composition statistics obtained by the above three methods are as follows Figure 6 , Figure 7 and Figure 8 shown.

[0035] The applicant declares that the above is only a specific implementation of the present invention, but the protection scope of the present invention is not limited thereto. The technicians in the technical field should understand that any changes or substitutions that can be easily thought of by the technicians in the technical field within the technical scope disclosed by the present invention are within the protection scope and disclosure scope of the present invention.

Claims

1. A device for detecting ore particle size based on a flexible vibrating disk, characterized in that: include: Flexible vibrating plate, used to vibrate the ore material at a certain frequency and amplitude to achieve uniform distribution and appropriate posture; The flexible vibration plate comprises: A loading tray for carrying ore materials, the surface of which is covered with a layer of anti-fouling material; A voice coil motor for driving the tray to vibrate. Four voice coil motors are distributed at four inner corners of the flexible vibration plate. The voice coil motor includes a magnet and a coil. When an alternating current is passed through the coil, the coil generates a force under the action of the magnet, causing the vibration plate to vibrate. a controller for controlling the frequency, amplitude and phase of the coil current, thereby controlling the frequency, intensity and direction of vibration of the flexible plate; An image acquisition device is used to continuously photograph the ore material on the flexible vibration plate to obtain an ore image; The image acquisition device comprises an industrial camera, and the industrial camera comprises: a lens for imaging the ore material on the flexible vibrating plate, having adjustable focal length, aperture and viewing angle; An interface for transmitting electrical signals to a computer, which supports high-speed, high-stability data transmission protocols; Image processing device, used for preprocessing, segmenting, feature extraction and particle size analysis of ore images, and outputting ore particle size distribution and cumulative distribution curve; The image processing device comprises a computer host and a display; Result output device, used to display ore images and particle size analysis results.

2. A detection method using the ore particle size detection device based on a flexible vibrating disk as described in claim 1, characterized in that: The following steps are involved: Step 1: Vibration Dispersion The ore particles are placed on the flexible vibration plate, and the vibration plate is vibrated by driving the voice coil motor. The ore to be tested will be dispersed during the vibration process. Step 2: Image capture An industrial camera is used to capture an original image of the ore material on the flexible vibrating plate and transmit the image to a computer in an image processing device; Step 3: Image Preprocessing The original image is gray-scale converted, noise removed and binarized; the original color image is converted into a gray-scale image to better identify the boundaries and textures of ore particles; the image is filtered using a bilateral filtering algorithm to filter out noise while retaining the edges of ore particles; the image is binarized using a method combining integral images and local thresholds to extract the target ore area, and the algorithm has the characteristics of light adaptability and high efficiency; the binary image is optimized using morphological operations to smooth the edges of ore particles and remove noise in the image; Step 4: Image Segmentation The watershed algorithm, the algorithm based on concave point detection and the ore texture recognition model algorithm based on SVM are used on the pre-processed images to effectively determine the image edges of individual ore particles and accurately divide the materials in the image into individual particles. Step 5: Dispersion Assessment The segmented particle group image is calibrated, and the centroid coordinates of each particle are obtained by particle outer contour detection. The Euclidean distance between the particle position and the average position of all particles in the particle group is calculated as the original data, and its coefficient of variation CV, that is, the standard deviation of the original data, is calculated. The average of the original data to evaluate the overall dispersion of the particle group; if the obtained coefficient of variation is less than 30%, the vibration dispersion step is started again and the above process is repeated; Step 6: Granularity Calculation According to the segmentation result of each ore particle, the minimum circumscribed rectangle of its projection is obtained, and the two sides of the minimum circumscribed matrix are extracted as l and b respectively; the geometric mean diameter of the particles is calculated as the detection particle size D of the ore, and the calculation formula is as follows: ； Step 7: Posture distribution and granularity correction Image recognition is used to obtain the three-axis diameters l, b, and h of each ore particle. On this basis, the elongation and flatness of the particle are calculated, and used as the basis for morphological classification. Then, the detected particle size is multiplied by the probability of occurrence of bad postures in each shape and the correction coefficient to obtain the final posture distribution result of the particle group; the posture distribution result of the particle group will help to correct the particle size recognition result.

3. The detection method of the ore particle size detection device based on the flexible vibration disk according to claim 2 is characterized in that: The dispersion evaluation in the fifth step includes: performing position identification and coordinate statistics on the ore particles after vibration dispersion, and calculating the coordinate position of each ore particle. The average coordinate position of all particles The Euclidean distance , to get the degree to which each particle is away from the center position, the formula is as follows: ； Count and calculate all particles , and calculate the average , and the standard deviation , the formula is as follows: ； By calculating the ratio of the standard deviation to the mean, the coefficient of variation is obtained as an evaluation index of the position dispersion of the ore particle group. The calculation formula is as follows: ； The coefficient of variation CV reflects the overall dispersion of the particle group. The larger its value, the more uniform the dispersion between the particles. It is used as an evaluation index for the dispersion of the ore particle group after vibration. When the coefficient of variation is above 30%, the accumulation and obstruction of the ore particles will not have a significant impact on the particle size identification results.

4. The detection method of the ore particle size detection device based on the flexible vibration disk according to claim 3 is characterized in that: The posture distribution and particle size correction in the seventh step are specifically as follows: classifying and counting the ore particles according to the shape characteristics of the ore, predicting the posture distribution of the ore according to the proportion of different shapes, so as to correct the particle size of some particles in the ore particles that are in bad postures; obtaining the distribution of the ore particles in shape through visual recognition based on the acquired ore particle images; The morphological classification is based on the following: the three-axis diameters of the ore particle size: height h, width b and length l; the flatness m and elongation n of the particle are set, and the formula is as follows: ； According to the flatness m and elongation n of the particles, the shapes of the particles are divided into four categories: block, flake, long flake and columnar, as shown in the following table: ； The distribution ratios of the four different shapes of ore particles after vibration and the particle size correction coefficients are as follows: ； According to the proportion of each shape of the identified ore particle group to be tested, multiply it by the proportion of bad postures and the corresponding correction coefficient to obtain the corrected ore particle size result. The calculation formula is as follows: 。

Images