A device and method for detecting mica content in machine-made sand based on multi-light source imaging

Abstract

The present invention discloses a device for detecting the mica content in manufactured sand based on multi-light source imaging. The device comprises: a darkroom, a vibrating feeder, a first light source, a second light source, an image acquisition device, and a processing terminal. The vibrating feeder, the first light source, the second light source, and the image acquisition device are respectively connected to the processing terminal. The vibrating feeder is disposed on one side of the darkroom and is used to receive and convey manufactured sand samples and control the uniform drop of the manufactured sand samples. The first light source and the second light source are both disposed on one side of the darkroom and below the vibrating feeder, providing illumination for the falling path of the manufactured sand samples. The image acquisition device is disposed between the first and second light sources and is used to capture images of the falling manufactured sand samples. The processing terminal is used to control the operating states of the vibrating feeder, the first light source, the second light source, and the image acquisition device, and to receive and process the captured images. The device is capable of quickly and accurately detecting the mica content in manufactured sand.

Description

Technical Field

[0001] The present invention relates to the technical field of material detection, and more particularly to a device and method for detecting the mica content in machine-made sand based on multi-light source imaging. Background Art

[0002] Currently, manufactured sand is a fine aggregate obtained by crushing, screening, shaping, and pulverizing various rock minerals. Made from rock minerals, tunnel slag, and pebbles and gravel, manufactured sand has become a green alternative to natural river sand. Mica is a natural mineral often associated with various types of rock, so it is present in a certain amount in manufactured sand. Mica is a harmful component in concrete. Exceeding a certain level of content can negatively impact the workability, mechanical properties, and durability of concrete. Therefore, a mica content indicator is a necessary control indicator. Existing standards in various fields use manual selection methods for testing mica content. For example, the standard "Construction Sand" (GB / T 14684-2011) stipulates that mica must be manually selected after magnification with a magnifying glass. This detection method is not only slow but also subject to significant human influence.

[0003] The prior art CN202311118650.1 discloses a detection device that utilizes the difference in bulk density between mica and other minerals, simplifies the mica detection process and equipment, and improves the detection efficiency. However, the bulk density of minerals in machine-made sand is not much different, so the detection accuracy is also affected; the prior art CN202010317865.6 combines the memory space occupied by the photo and the mica content-image memory size correspondence to obtain the mica content in concrete fine aggregate, and uses image processing software to distinguish mica, but the identification process is time-consuming and relatively complicated; the prior art CN201621162803.8 discloses a rapid detection method that utilizes the obvious color difference in the image to distinguish mica, but since quartz crystals will also produce color difference under full-spectrum light source illumination, there is a certain error in the result. At the same time, since the mica content is calculated by pixel comparison, there is a difference from the mass fraction result in the existing standard.

[0004] In summary, the current coarse aggregate particle morphology detection methods and devices still have the following problems:

[0005] (1) The standard method is simple and the detection efficiency is low: At present, the detection method of mica content is mostly manual selection, which is slow and greatly affected by human factors. It is not suitable for the rapid evaluation of mass-produced machine-made sand;

[0006] (2) The detection performance is diverse and the results have a great impact: using the characteristics of bulk density and morphology to quickly detect the content of mica is a feasible method, but since these properties of mica are not significantly different from those of other minerals, the improvement of detection accuracy is not significant;

[0007] (3) Image analysis methods are complex and have not been widely used: The mica content detection method that combines optical scattering characteristics with image analysis is a feasible technology, but there are differences between current research and the evaluation methods specified in the standards, and there are many interference factors in the image analysis process, so it has not been widely used.

[0008] Therefore, how to quickly and accurately detect the mica content in machine-made sand is a problem that those skilled in the art urgently need to solve. Summary of the Invention

[0009] In view of this, the present invention provides a device and method for detecting the mica content in manufactured sand based on multi-light source imaging. By taking advantage of the obvious optical scattering phenomenon of mica and combining it with image analysis, the mica content in the manufactured sand can be quickly and accurately detected, thereby achieving precise control of the quality of the manufactured sand.

[0010] In order to achieve the above object, the present invention adopts the following technical solutions:

[0011] A device for detecting mica content in machine-made sand based on multi-light source imaging, comprising: a dark box, a vibration feeding device, a first light source, a second light source, an image acquisition device, and a processing terminal;

[0012] The vibration feeding device, the first light source, the second light source and the image acquisition device are respectively connected to the processing terminal;

[0013] The vibrating feeding device is arranged on one side of the dark box, and is used to receive and convey the machine-made sand sample and control the machine-made sand sample to fall at a uniform speed;

[0014] The first light source and the second light source are both arranged on one side of the dark box and below the vibrating feeding device, and are used to provide irradiation light for the falling path of the machine-made sand sample;

[0015] The image acquisition device is disposed between the first light source and the second light source, and is used to acquire an image of the falling machine-made sand sample;

[0016] The processing terminal is used to control the operating states of the vibration feeding device, the first light source, the second light source and the image acquisition device, and receive and process the acquired images.

[0017] Preferably, it also includes a weighing device;

[0018] The weighing device is connected to the processing terminal;

[0019] The weighing device is arranged in the dark box and is located directly below the outlet of the vibrating feeding device. It is used to receive the falling machine-made sand sample for mass measurement and transmit the mass information to the processing terminal.

[0020] Preferably, the angle between the light source axis of the first light source and the light source axis of the second light source is set to a preset angle;

[0021] The illumination range of the first light source and the second light source covers the acquisition range of the image acquisition device.

[0022] Preferably, the first light source and the second light source are both single-wavelength light sources, and the wavelength is 650nm±10nm.

[0023] Preferably, the vibrating feeding device is movably connected to one side of the dark box, and the inclination angle of the vibrating feeding device can be adjusted through the processing terminal.

[0024] Preferably, a round hole screen, a negative pressure dust collector and a screen bottom are sequentially arranged at the bottom of the vibrating feeding device;

[0025] The circular hole sieve is provided with a sieve with a sieve hole size of a preset value, for screening the machine-made sand samples, and retaining the machine-made sand samples with a size larger than the preset value;

[0026] The sieve bottom is used to receive machine-made sand samples with a size smaller than the preset value;

[0027] The negative pressure dust collector is arranged on the bottom of the sieve and is used to remove machine-made sand samples whose size is smaller than the preset value.

[0028] A method for detecting mica content in machine-made sand based on multi-light source imaging, comprising:

[0029] Obtain a machine-made sand sample to be tested and place it on a vibrating feeding device, while simultaneously turning on a first light source and a second light source;

[0030] Turning on the vibration feeding device, and controlling the machine-made sand sample to fall at a uniform speed by the vibration feeding device;

[0031] The image acquisition device automatically acquires sample images of the machine-made sand samples that fall within the acquisition range;

[0032] The weighing device receives the falling machine-made sand sample and obtains the total mass of the sample;

[0033] The processing terminal receives and obtains the initial mica content of the manufactured sand sample based on the sample image and the total mass of the sample;

[0034] The same group of samples is tested repeatedly for a preset number of times, and the average value of the initial mica contents obtained for the preset number of times is taken as the final mica content of the group of machine-made sand samples.

[0035] Preferably, the processing terminal is used to adjust the inclination angle of the vibration feeding device and the feeding speed of the machine-made sand sample to ensure that the image acquisition device captures non-overlapping and clear images of the machine-made sand sample.

[0036] Preferably, obtaining the initial mica content of the machine-made sand sample specifically includes:

[0037] The processing terminal performs binarization processing on all the sample images, identifies areas with grayscale values ​​less than a threshold as mica particles, and obtains a plurality of mica identification images;

[0038] Obtaining mica particle width and mica particle projected area based on the mica identification map;

[0039] Obtaining the mica mass of each mica particle based on the width of the mica particle and the projected area of ​​the mica particle;

[0040] The mica mass of the corresponding sample image is obtained based on the mica mass of all mica particles;

[0041] The sample mica mass is obtained based on the mica mass of all sample images;

[0042] The initial mica content is obtained based on the mica mass of the sample and the total mass of the sample.

[0043] It can be seen from the above technical solution that, compared with the prior art, the present invention discloses a device and method for detecting the mica content in machine-made sand based on multi-light source imaging, which has the following beneficial effects:

[0044] 1. The detection method is simple and intelligent: The present invention uses image analysis to directly detect the mica content of the finished machine-made sand product, with high detection efficiency, truly meeting the demand for rapid detection of mica content.

[0045] 2. Accurate detection parameters and high accuracy of results: The strong optical scattering characteristics of machine-made sand mica under multiple light sources are used for evaluation, which is significantly different from other minerals, and the detection results are highly accurate.

[0046] 3. Efficient testing and accurate test results: The volume and mass of sand particles are automatically calculated, and the mica content is evaluated by mass fraction. The test results are highly correlated with the existing evaluation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0048] Figure 1 This is a structural schematic diagram of a device for detecting mica content in manufactured sand based on multi-light source imaging provided by the present invention.

[0049] Figure 2 A schematic structural diagram of another preferred device for detecting mica content in manufactured sand based on multi-light source imaging provided by the present invention.

[0050] Figure 3 This is a schematic structural diagram of the vibration feeding device provided by the present invention.

[0051] Figure 4 This is a flow chart of a method for detecting mica content in manufactured sand based on multi-light source imaging provided by the present invention.

[0052] Figure 5 Flowchart of the method for obtaining the initial mica content of the machine-made sand sample provided by the present invention.

[0053] Figure 6 This is a schematic diagram of the two-dimensional morphology of mica particles provided by the present invention.

[0054] Explanation of the accompanying drawings: 1-dark box; 2-vibrating feeding device; 21-round hole sieve; 22-negative pressure dust collector; 23-sieve bottom; 3-first light source; 4-second light source; 5-image acquisition device; 6-processing terminal; 7-weighing device. DETAILED DESCRIPTION

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0056] Example 1

[0057] like Figure 1 As shown, the embodiment of the present invention discloses a device for detecting the mica content in machine-made sand based on multi-light source imaging, comprising: a dark box 1, a vibrating feeding device 2, a first light source 3, a second light source 4, an image acquisition device 5, and a processing terminal 6;

[0058] The vibration feeding device 2, the first light source 3, the second light source 4 and the image acquisition device 5 are respectively connected to the processing terminal 6;

[0059] The vibrating feeding device 2 is arranged on one side of the dark box 1, and is used to receive and convey the machine-made sand sample and control the machine-made sand sample to fall at a uniform speed;

[0060] The first light source 3 and the second light source 4 are both arranged on one side of the dark box 1 and located below the vibrating feeding device 2, and are used to provide irradiation light for the falling path of the machine-made sand sample;

[0061] The image acquisition device 5 is arranged between the first light source 3 and the second light source 4, and is used to acquire images of the falling machine-made sand sample;

[0062] The processing terminal 6 is used to control the operating states of the vibration feeding device 2, the first light source 3, the second light source 4 and the image acquisition device 5, and receive and process the acquired images.

[0063] Preferably, the dark box 1 is used to provide a closed light-shielding environment, which can create a closed light-shielding environment. Under ideal conditions, no light can pass through, thereby preventing external light from affecting the detection process.

[0064] Example 2

[0065] like Figure 2 As shown, the embodiment of the present invention discloses a device for detecting the mica content in machine-made sand based on multi-light source imaging, comprising: a dark box 1, a vibrating feeding device 2, a first light source 3, a second light source 4, an image acquisition device 5, and a processing terminal 6;

[0066] The vibration feeding device 2, the first light source 3, the second light source 4 and the image acquisition device 5 are respectively connected to the processing terminal 6;

[0067] The vibrating feeding device 2 is arranged on one side of the dark box 1, and is used to receive and convey the machine-made sand sample and control the machine-made sand sample to fall at a uniform speed;

[0068] The first light source 3 and the second light source 4 are both arranged on one side of the dark box 1 and located below the vibrating feeding device 2, and are used to provide irradiation light for the falling path of the machine-made sand sample;

[0069] The image acquisition device 5 is arranged between the first light source 3 and the second light source 4, and is used to acquire images of the falling machine-made sand sample;

[0070] The processing terminal 6 is used to control the operating states of the vibration feeding device 2, the first light source 3, the second light source 4 and the image acquisition device 5, and receive and process the acquired images.

[0071] Preferably, it further comprises a weighing device 7;

[0072] The weighing device 7 is connected to the processing terminal 6;

[0073] The weighing device 7 is arranged in the dark box 1 and is located directly below the outlet of the vibrating feeding device 2. It is used to receive the falling machine-made sand sample for mass measurement and transmit the mass information to the processing terminal 6.

[0074] Preferably, the weighing device 7 of this embodiment adopts a weighing tray, which can measure the mass of the machine-made sand sample in real time with an accuracy of 0.01g.

[0075] Preferably, the angle between the light source axis of the first light source 3 and the light source axis of the second light source 4 is set to a preset angle. The use of synchronized multi-light sources for illumination can effectively avoid the generation of shadows and thus affect the detection results. At the same time, an increase in the incident angle will significantly reduce the scattering intensity of light. Therefore, the angle between the two light sources should not be too large. In this embodiment, the angle between the light source axis of the first light source 3 and the light source axis of the second light source 4 is set to 60°.

[0076] Preferably, the illumination range of the first light source 3 and the second light source 4 covers the acquisition range of the image acquisition device 5 .

[0077] Preferably, the first light source 3 and the second light source 4 are both single-wavelength light sources, and the wavelength is 650nm±10nm.

[0078] Preferably, the first light source 3 and the second light source 4 of this embodiment both use single-wavelength LED light sources with wavelengths of 650nm±10nm, and use a light source with a wavelength of 650nm with obvious scattering of mica minerals for irradiation. At this time, the quartz scattering intensity is low to reduce the reflection of the quartz crystal affecting the detection results.

[0079] Preferably, the image acquisition device 5 of this embodiment adopts a dynamic particle image acquisition device, which quickly acquires and records the sample image after the first light source 3 and the second light source 4 irradiate the falling machine-made sand sample. The acquired sample image is a grayscale image.

[0080] Preferably, the vibrating feeding device 2 is movably connected to one side of the dark box 1, and the inclination angle of the vibrating feeding device 2 can be adjusted through the processing terminal 5, thereby adjusting the feeding speed of the machine-made sand sample. At the same time, it can ensure that the image acquisition device 5 captures non-overlapping and clear images of the machine-made sand samples, further ensuring the accuracy of the detection results.

[0081] Preferably, the adjustable range of the tilt angle θ of the vibrating feeding device 2 in this embodiment is: 0° to 15°.

[0082] Preferably, Figure 3 As shown, the bottom of the vibrating feeding device 2 is provided with a round hole screen 21, a negative pressure dust collector 22 and a screen bottom 23 in sequence;

[0083] The circular hole sieve 21 is provided with a sieve with a preset sieve hole size, which is used to screen the machine-made sand samples and retain the machine-made sand samples with a size larger than the preset value to prevent dust and other impurities from affecting the final test results;

[0084] The sieve bottom 23 is used to receive machine-made sand samples with a size smaller than a preset value;

[0085] The negative pressure dust collector 22 is arranged on the sieve bottom 23 and is used to remove machine-made sand samples whose size is smaller than a preset value.

[0086] Preferably, the preset value in this embodiment is set to 0.3 mm.

[0087] Example 3

[0088] like Figure 4 As shown, a method for detecting mica content in machine-made sand based on multi-light source imaging includes:

[0089] Obtain a machine-made sand sample to be tested and place it on a vibrating feeding device, while simultaneously turning on a first light source and a second light source;

[0090] Turn on the vibration feeding device and control the machine-made sand sample to fall at a uniform speed through the vibration feeding device;

[0091] The image acquisition device automatically acquires sample images of the machine-made sand samples that fall within the acquisition range;

[0092] The weighing device receives the falling machine-made sand sample and obtains the total mass of the sample;

[0093] The processing terminal receives and obtains the initial mica content of the manufactured sand sample based on the sample image and the total mass of the sample;

[0094] The same group of samples was tested repeatedly for a preset number of times, and the average value of the initial mica contents obtained for the preset number of times was taken as the final mica content of the group of machine-made sand samples.

[0095] Example 4

[0096] A method for detecting mica content in machine-made sand based on multi-light source imaging, comprising:

[0097] Obtain a machine-made sand sample to be tested and place it on a vibrating feeding device, and turn on the first light source and the second light source at the same time.

[0098] Preferably, a machine-made sand sample of preset quality is obtained from the machine-made sand production line in real time, the obtained machine-made sand sample is dried at 105° C. and then cooled to room temperature, and the pretreated machine-made sand sample is placed in a vibrating feeding device.

[0099] Preferably, the first light source and the second light source illuminate the falling machine-made sand sample at different angles. In this embodiment, the angle between the light source axis of the first light source and the light source axis of the second light source is 60°, which can avoid the generation of shadows and thus affect the accuracy of the final detection results.

[0100] Turn on the vibration feeding device and control the machine-made sand sample to fall at a uniform speed through the vibration feeding device.

[0101] Preferably, the processing terminal calculates and adjusts the inclination angle of the vibrating feeding device and the falling speed of the machine-made sand sample to ensure that the image acquisition device captures clear and non-overlapping images of the machine-made sand sample.

[0102] The image acquisition device automatically acquires sample images of the machine-made sand samples that fall within the acquisition range.

[0103] Preferably, the illumination range of the first light source and the second light source completely covers the acquisition range of the image acquisition device, and the sample image acquired by the image acquisition device is a grayscale image.

[0104] The weighing device receives the falling machine-made sand sample and obtains the total mass of the sample.

[0105] The processing terminal receives and obtains the initial mica content of the manufactured sand sample based on the sample image and the total mass of the sample.

[0106] Preferably, Figure 5 As shown, the initial mica content of the machine-made sand sample is obtained, specifically including:

[0107] The processing terminal performs binarization on all sample images, identifies areas with grayscale values ​​less than a threshold as mica particles, and obtains multiple mica identification images;

[0108] Obtaining the width and projected area of ​​mica particles based on the mica identification diagram;

[0109] The mica mass of each mica particle is obtained based on the mica particle width and the mica particle projected area;

[0110] The mica mass of the corresponding sample image is obtained based on the mica mass of all mica particles;

[0111] The sample mica mass is obtained based on the mica mass of all sample images;

[0112] The initial mica content was obtained based on the sample mica mass and the total sample mass.

[0113] Preferably, in this embodiment, regions with grayscale values ​​less than 40 are identified as mica particles, and regions with grayscale values ​​greater than or equal to 40 are not identified.

[0114] Preferably, Figure 6 As shown, by performing image processing on the mica identification image, the circumscribed rectangle of the mica particle is obtained, and the width w, the centroid P, and the projected area S of the mica particle are obtained based on the circumscribed rectangle; the mica mass Ga of each mica particle is obtained based on the obtained parameters:

[0115]

[0116] Where ρ represents the density of mica particles. ρ can be found according to the type of mica, or directly taken as ρ = 2.8 kg / m 3 .

[0117] Alternatively, the approximate volume V of the mica particle can be obtained by rotating half of the projected area S around the axis of the centroid P. The mica mass Ga of each mica particle can be obtained based on the approximate volume V and the density ρ of the mica particle:

[0118] Ga=ρV

[0119] The centroid P is obtained by connecting the diagonals of the circumscribed rectangle.

[0120] Preferably, the geometric dimensions of the aggregate can be obtained through image processing, and an approximate calculation method for the aggregate volume is proposed in combination with Gurukin's theorem. The calculation result converts the two-dimensional image of the mica particle into the three-dimensional volume of the mica particle, which is more accurate than the commonly used sphere approximation calculation method. Therefore, the obtained mica quality is more accurate and convenient to establish a connection with the evaluation method in the existing standard.

[0121] Preferably, the mica mass of the sample GA is obtained by summing the mica masses of the mica particles in all the sample images; the mica mass of the sample GA is obtained by summing the mica mass of the sample GA and the total mass of the sample G. 总 Get the initial mica content Q':

[0122]

[0123] Among them, G 总 The total mass of the manufactured sand sample measured by a weighing device.

[0124] The same group of samples was tested repeatedly for a preset number of times, and the average value of the initial mica contents obtained for the preset number of times was taken as the final mica content of the group of machine-made sand samples.

[0125] Preferably, the preset number of times in this embodiment is set to 2, and two initial mica contents are obtained by repeating the above steps twice for the same group of machine-made sand samples, and the average value of the two initial mica contents is taken as the final mica content of the reorganized machine-made sand samples.

[0126] Preferably, the method further comprises: grading the machine-made sand sample based on the final mica content:

[0127] The final mica content is ≤1.0%, which is Grade I;

[0128] 1.0%<final mica content≤2.0%, which is Grade II.

[0129] Preferably, the present invention uses image analysis to directly perform real-time detection of the mica content of the sample during the production of machine-made sand. The detection efficiency is high, and the rapid detection of the mica content of the machine-made sand is achieved. The mica content of the machine-made sand can be obtained in real time during the production process, and then corresponding processing can be performed according to the mica content.

[0130] Example 5

[0131] The mica content detection device and method of the invented machine-made sand based on multi-light source imaging were verified by obtaining 150g of basalt machine-made sand samples and granite machine-made sand samples respectively. The representative data detection results of basalt machine-made sand and granite machine-made sand obtained by the device and method of the present invention are shown in Table 1:

[0132] Table 1 Mica content test results of two machine-made sand samples

[0133] Lithology quantity Mica types Density (ρ) Width (w) Projected area (S) Mass (G) basalt 3 muscovite 2.8 0.45 0.18 0.18 granite 12 biotite 2.7 0.33 0.28 0.20

[0134] The mass of all mica particles in all sample images collected is added together to obtain the mica mass of the basalt machine-made sand sample: G 玄 =0.42g and granite machine-made sand sample mica mass: G 花 =2.65g, in this example, the mica content of the sample is calculated only once as the final sample mica content, and the mica content Q of the basalt machine-made sand sample is calculated according to the above formula 玄 and the mica content Q of granite machine-made sand samples 花 :

[0135]

[0136] The results show that the mica content of basalt artificial sand reaches level I, and that of granite artificial sand reaches level II.

[0137] To compare the accuracy of the test results, a petrographic analysis of two types of manufactured sand was conducted: basalt is primarily composed of plagioclase, pyroxene phenocrysts, magnetite, and a small amount of muscovite; granite is primarily composed of plagioclase, hornblende, quartz, and orthoclase. Manual sorting and calculation revealed a mica content of 0.4% for the basalt and 1.9% for the granite. The results demonstrate that this patented method accurately detects the content of different types of mica in manufactured sand, with results close to those obtained by manual testing, demonstrating high reliability.

[0138] It can be seen from the above technical solution that, compared with the prior art, the present invention discloses a device and method for detecting the mica content in machine-made sand based on multi-light source imaging, which has the following beneficial effects:

[0139] 1. The detection method is simple and intelligent: The present invention uses image analysis to directly detect the mica content of the finished machine-made sand product, with high detection efficiency, truly meeting the demand for rapid detection of mica content.

[0140] 2. Accurate detection parameters and high accuracy of results: The strong optical scattering characteristics of machine-made sand mica under multiple light sources are used for evaluation, which is significantly different from other minerals, and the detection results are highly accurate.

[0141] 3. Efficient testing and accurate test results: The volume and mass of sand particles are automatically calculated, and the mica content is evaluated by mass fraction. The test results are highly correlated with the existing evaluation system.

[0142] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0143] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A device for detecting mica content in machine-made sand based on multi-light source imaging, characterized in that: include: Dark box, vibrating feeding device, first light source, second light source, image acquisition equipment and processing terminal; The vibration feeding device, the first light source, the second light source and the image acquisition device are respectively connected to the processing terminal; The vibrating feeding device is arranged on one side of the dark box, and is used to receive and convey the machine-made sand sample and control the machine-made sand sample to fall at a uniform speed; The vibrating feeding device is movably connected to one side of the dark box, and the inclination angle of the vibrating feeding device can be adjusted through the processing terminal; The bottom of the vibrating feeding device is provided with a round hole screen, a negative pressure dust collector and a screen bottom in sequence; The circular hole sieve is provided with a sieve with a sieve hole size of a preset value, for screening the machine-made sand samples, and retaining the machine-made sand samples with a size larger than the preset value; The sieve bottom is used to receive machine-made sand samples with a size smaller than the preset value; The negative pressure dust collector is arranged on the bottom of the sieve, and is used to remove machine-made sand samples whose size is smaller than the preset value; The first light source and the second light source are both arranged on one side of the dark box and below the vibrating feeding device, and are used to provide irradiation light for the falling path of the machine-made sand sample; The angle between the light source axis of the first light source and the light source axis of the second light source is set to a preset angle; The image acquisition device is disposed between the first light source and the second light source, and is used to acquire an image of the falling machine-made sand sample; The processing terminal is used to control the operating states of the vibration feeding device, the first light source, the second light source and the image acquisition device, and receive and process the acquired images.

2. The device for detecting mica content in machine-made sand based on multi-light source imaging according to claim 1, characterized in that: Also included is a weighing device; The weighing device is connected to the processing terminal; The weighing device is arranged in the dark box and is located directly below the outlet of the vibrating feeding device. It is used to receive the falling machine-made sand sample for mass measurement and transmit the mass information to the processing terminal.

3. The device for detecting mica content in machine-made sand based on multi-light source imaging according to claim 1, characterized in that: The illumination range of the first light source and the second light source covers the acquisition range of the image acquisition device.

4. The device for detecting mica content in machine-made sand based on multi-light source imaging according to claim 1, characterized in that: The first light source and the second light source are both single-wavelength light sources, and the wavelength is 650nm±10nm.

5. A method for detecting mica content in machine-made sand based on multi-light source imaging, characterized in that: A device for detecting mica content in manufactured sand based on multi-light source imaging according to any one of claims 1 to 4, comprising: Obtain a machine-made sand sample to be tested and place it on a vibrating feeding device, while simultaneously turning on a first light source and a second light source; Turning on the vibration feeding device, and controlling the machine-made sand sample to fall at a uniform speed by the vibration feeding device; The image acquisition device automatically acquires sample images of the machine-made sand samples that fall within the acquisition range; The weighing device receives the falling machine-made sand sample and obtains the total mass of the sample; The processing terminal receives and obtains the initial mica content of the manufactured sand sample based on the sample image and the total mass of the sample; Obtaining the initial mica content of the machine-made sand sample specifically includes: The processing terminal performs binarization processing on all the sample images, identifies areas with grayscale values ​​less than a threshold as mica particles, and obtains a plurality of mica identification images; Obtaining mica particle width and mica particle projected area based on the mica identification map; Obtaining the mica mass of each mica particle based on the width of the mica particle and the projected area of ​​the mica particle; The mica mass of the corresponding sample image is obtained based on the mica mass of all mica particles; The sample mica mass is obtained based on the mica mass of all sample images; Obtaining the initial mica content based on the mica mass of the sample and the total mass of the sample; By performing image processing on the mica identification image, the circumscribed rectangle of the mica particle is obtained, and the width w and the projected area S of the mica particle are obtained based on the circumscribed rectangle. The mica mass Ga of each mica particle is obtained based on the obtained parameters: Where ρ represents the density of mica particles; The same group of samples is tested repeatedly for a preset number of times, and the average value of the initial mica contents obtained for the preset number of times is taken as the final mica content of the group of machine-made sand samples.

6. The method for detecting mica content in machine-made sand based on multi-light source imaging according to claim 5, characterized in that: The processing terminal is used to adjust the inclination angle of the vibrating feeding device and the feeding speed of the machine-made sand sample, so as to ensure that the image acquisition device captures clear and non-overlapping images of the machine-made sand sample.

Images