Fly ash quality identification method, system and medium
By obtaining multiple images of the fly ash sample on a glass slide at different focal lengths and performing fusion processing and ratio calculation, the accuracy problem of fly ash quality identification in the existing technology is solved and higher identification accuracy is achieved.
Patent Information
- Application Number
- CN202510964542.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-14
- Publication Date
- 2025-09-26
AI Technical Summary
In the existing technology, fly ash quality identification has problems such as strong subjectivity in manual counting, difficulty in identifying vitreous bodies, and difficulty in distinguishing stacked particles, resulting in low identification accuracy.
By obtaining multiple images of fly ash samples on a glass slide at different focal lengths and performing fusion processing, the sum of particle pixels in different roundness ranges is extracted, and the ratio is calculated to determine the quality information of the fly ash and reduce manual intervention.
The accuracy of fly ash quality identification is improved, the subjectivity of manual counting is reduced, and the objectivity and reliability of the identification results are improved.
Smart Images
Figure CN120702931A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical fields of image processing and quality identification, and in particular to a fly ash quality identification method, system and medium. Background Art
[0002] Fly ash, a mineral admixture for concrete, is a spherical, finely divided material that exhibits "balling effect," "micro-filling effect," and "pozzolanic reaction" in concrete mixtures, improving various concrete properties. However, the market is currently plagued by the practice of finely grinding tertiary ash, as well as inferior materials like coal cinders, stone, and slag, to pass off inferior products as genuine products. This creates difficulties in the concrete mixing, pouring, and curing processes, negatively impacting the concrete's appearance, strength, and durability.
[0003] To regulate the use of fly ash, the government has issued numerous standards and specifications, defining certain physical and chemical properties. However, these standards involve numerous parameters, require lengthy testing cycles, and some conventional test parameters for inferior fly ash are very similar to those for standard fly ash, making it difficult to accurately identify inferior fly ash. Consequently, inferior fly ash is often used in concrete as if it were standard quality fly ash.
[0004] In the existing scheme, when identifying the quality of fly ash, screening + visual counting of the vitreous body ratio under a microscope is usually used to achieve initial screening of the fly ash quality at the construction site. However, there are problems such as strong subjectivity in manual counting, difficulty in identifying vitreous bodies, and difficulty in distinguishing stacked particles, resulting in low accuracy in quality identification. Summary of the Invention
[0005] The embodiments of the present application provide a fly ash quality identification method, system and medium, which can extract multiple pictures of a fly ash sample on a glass slide at different focal lengths and use the multiple pictures to identify quality information without the need for manual counting, thereby improving the accuracy of fly ash quality identification.
[0006] A first aspect of an embodiment of the present application provides a method for identifying fly ash quality, the method comprising: Obtain a glass slide fly ash sample made of fly ash to be tested; Obtain k focal length images of the fly ash sample on the glass slide at different focal lengths; The k focal length images are fused to obtain the fly ash particle image; Extracting a first pixel sum of particle pixels in a first roundness interval from the fly ash particle image, and extracting a second pixel sum of particle pixels in a second roundness interval from the fly ash particle image, wherein the first roundness interval is a roundness interval greater than a first roundness threshold, the second roundness interval is a roundness interval greater than a second roundness threshold, and the first roundness threshold is greater than the second roundness threshold; The quality information of the fly ash to be detected is determined by using the first pixel sum, the second pixel sum, and the pixel sum in the fly ash particle image.
[0007] In one possible implementation, obtaining a glass slide fly ash sample made of fly ash to be tested includes: Mix the fly ash to be tested with pure water to prepare a sample mixture; extracting the sample mixture after dispersing the sample mixture; The extracted mixed solution was loaded onto the center of a glass slide to prepare a glass slide fly ash sample.
[0008] In one possible implementation, obtaining k focal length images of the glass slide fly ash sample at different focal lengths includes: The fly ash sample on a glass slide is placed under a microscope of a particle morphology recognition and analysis system to adjust the focus. The image is captured and processed as the particle clarity increases from small to large within the pixel field of view to obtain k focal length images.
[0009] In one possible implementation, determining the quality information of the fly ash to be tested by using the first pixel sum, the second pixel sum, and the pixel sum in the fly ash particle image includes: Calculating a ratio between the first pixel sum and the second pixel sum to obtain a first ratio; calculating a ratio between the first total pixel value and the total pixel value in the fly ash particle image to obtain a second ratio; The quality information of the fly ash to be detected is determined according to the first ratio and the second ratio.
[0010] In one possible implementation, fusing k focal length images to obtain a fly ash particle image includes: Encode k focal length pictures to obtain k encoded images; Extract weight values from k encoded images to obtain k fusion weights; The k fusion weights and the corresponding coded images are used to perform depth of field fusion processing to obtain the fly ash particle image.
[0011] A second aspect of an embodiment of the present application provides a fly ash quality identification system, the system comprising: An acquisition unit is used to acquire a glass slide fly ash sample made of fly ash to be tested; and acquire k focal length images of the glass slide fly ash sample at different focal lengths; A fusion unit is used to fuse k focal length images to obtain a fly ash particle image; an extraction unit, configured to extract a first pixel sum of particle pixels in a first roundness interval from the fly ash particle image, and to extract a second pixel sum of particle pixels in a second roundness interval from the fly ash particle image, wherein the first roundness interval is a roundness interval greater than a first roundness threshold, and the second roundness interval is a roundness interval greater than a second roundness threshold, wherein the first roundness threshold is greater than the second roundness threshold; The determination unit is configured to determine the quality information of the fly ash to be detected by using the first pixel sum, the second pixel sum, and the pixel sum in the fly ash particle image.
[0012] In one possible implementation, in obtaining the fly ash sample on a glass slide made of fly ash to be tested, the obtaining unit is specifically configured to: Mix the fly ash to be tested with pure water to prepare a sample mixture; extracting the sample mixture after dispersing the sample mixture; The extracted mixed solution was loaded onto the center of a glass slide to prepare a glass slide fly ash sample.
[0013] In a possible implementation, in acquiring k focal length images of the glass slide fly ash sample at different focal lengths, the acquiring unit is specifically configured to: The fly ash sample on a glass slide is placed under a microscope of a particle morphology recognition and analysis system to adjust the focus. The image is captured and processed as the particle clarity increases from small to large within the pixel field of view to obtain k focal length images.
[0014] In one possible implementation, the determining unit is specifically configured to: Calculating a ratio between the first pixel sum and the second pixel sum to obtain a first ratio; calculating a ratio between the first total pixel value and the total pixel value in the fly ash particle image to obtain a second ratio; The quality information of the fly ash to be detected is determined according to the first ratio and the second ratio.
[0015] In one possible implementation, the fusion unit is specifically configured to: Encode k focal length pictures to obtain k encoded images; Extract weight values from k encoded images to obtain k fusion weights; The k fusion weights and the corresponding coded images are used to perform depth of field fusion processing to obtain the fly ash particle image.
[0016] A third aspect of an embodiment of the present application provides a terminal, comprising a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions and execute the step instructions in the first aspect of the embodiment of the present application.
[0017] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, wherein the above-mentioned computer-readable storage medium stores a computer program for electronic data exchange, wherein the above-mentioned computer program enables a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application.
[0018] A fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to perform some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package.
[0019] The implementation of the embodiments of the present application has the following beneficial effects: By obtaining a glass slide fly ash sample made of fly ash to be tested, k focal length images of the glass slide fly ash sample at different focal lengths are obtained, and the k focal length images are fused to obtain a fly ash particle image, a first pixel sum of particle pixels in a first roundness interval is extracted from the fly ash particle image, and a second pixel sum of particle pixels in a second roundness interval is extracted from the fly ash particle image, the first roundness interval is a roundness interval greater than a first roundness threshold, the second roundness interval is a roundness interval greater than a second roundness threshold, and the first roundness threshold is greater than the second roundness threshold. The first pixel sum, the second pixel sum, and the pixel sum in the fly ash particle image are used to determine the quality information of the fly ash to be tested. Therefore, multiple images of the glass slide fly ash sample at different focal lengths can be extracted and then the multiple images can be used to identify the quality information without manual counting, thereby improving the accuracy of fly ash quality identification. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the embodiments of the present application 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 only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0021] Figure 1 A schematic flow chart of a method for identifying fly ash quality is provided for an embodiment of the present application; Figure 2 A microscopic image of a fly ash sample on a glass slide is provided for the embodiment of the present application; Figure 3 Another microscopic image of a glass slide fly ash sample is provided for the present application examples; Figure 4 Another microscopic image of a glass slide fly ash sample is provided for the present application examples; Figure 5 A structural schematic diagram of a fly ash quality identification device is provided for an embodiment of the present application. DETAILED DESCRIPTION
[0022] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.
[0023] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.
[0024] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments.
[0025] To better understand the fly ash quality identification method provided in the embodiments of this application, the following briefly describes methods for obtaining fly ash quality information in existing solutions. In existing solutions, initial screening of fly ash quality at construction sites is typically achieved through screening combined with visual counting of the vitreous fraction using a microscope. However, manual counting is highly subjective, vitreous fractions are difficult to identify, and stacked particles are difficult to distinguish, resulting in low accuracy in quality identification.
[0026] In order to solve the above-mentioned technical problems, an embodiment of the present application provides a fly ash quality identification method, which can extract multiple pictures of a fly ash sample on a glass slide at different focal lengths and use these multiple pictures to identify quality information without the need for manual counting, thereby improving the accuracy of fly ash quality identification.
[0027] See also Figure 1 , Figure 1 The present invention provides a flow chart of a fly ash quality identification method. Figure 1 As shown, the method includes: 101. Obtain a glass slide fly ash sample made of the fly ash to be tested.
[0028] Specifically, a method for obtaining a glass slide fly ash sample made of fly ash to be tested includes: A1. Mix the fly ash to be tested with purified water to prepare a sample mixture; A2. Dispersing the sample mixture and then extracting the mixture; A3. Load the extracted mixed solution onto the center of a glass slide to prepare a glass slide fly ash sample.
[0029] A certain mass of fly ash to be tested and purified water can be mixed, for example, 0.2 grams of fly ash to be tested and 20 grams of purified water. Alternatively, 2 grams of fly ash to be tested and 200 grams of purified water can be used, or 1 gram of fly ash to be tested and 100 grams of purified water can be used.
[0030] The method for dispersing the sample mixture can be to disperse the sample mixture for 2 minutes using an ultrasonic disperser, or to stir the sample mixture for 2.5 minutes using a glass rod to fully disperse the sample mixture.
[0031] After the stirring stops, use a rubber-tipped dropper to take a tube of mixed liquid at 1 / 2 liquid level (from the liquid surface) within 5 to 10 seconds, and drop one drop on the center of the slide within 1 to 3 seconds, then cover it with a cover glass and press gently to further disperse the fly ash sample suspension, thereby making a slide fly ash sample.
[0032] 102. Obtain k focal length images of the fly ash sample on the glass slide at different focal lengths.
[0033] Specifically, a method for obtaining k focal length images of the fly ash sample on a glass slide at different focal lengths may include placing the fly ash sample on a glass slide under a microscope in a particle morphology recognition and analysis system, adjusting the focal length, and capturing and processing the images as the particle definition increases from small to large within the pixel field of view, thereby obtaining k focal length images. Here, k may be 6. This is for illustrative purposes only and is not intended to be limiting.
[0034] Specifically, place the prepared fly ash sample on a glass slide under a microscope in a particle morphology recognition and analysis system. First, observe with a 10x objective lens. Adjust the movable ruler clamp and focus knob to obtain a clear image. Select a field of view where the fly ash is relatively evenly dispersed and has a sufficient number of particles. Ideally, select a field of view where at least 80% of the fly ash particles are present and evenly dispersed. Then, rotate the objective lens to a 40x objective lens and obtain a clear image using the 40x objective lens by adjusting the movable ruler clamp and focus knob.
[0035] Select a field of view with even dispersion and sufficient particles, and adjust the fine focus screw to make the smallest and largest visible particles in the field of view clear, so as to determine the adjustment range of the fine focus screw. Re-fine-tune the fine focus screw to the clear position of the smallest particles, so that the particle targets gradually become clear from small to large. Take 6 photos with different focal lengths during the process of gradually becoming clear from small to large. Make sure to take a photo when most small particles and most large particles are clear, and take 4 microscopic photos with different focal lengths in between. During the photo shooting process, the particle morphology recognition and analysis system automatically detects the image clarity, contrast, uniform lighting, number of particles, and particle overlap. Unqualified photos will be given a specific unqualified prompt and prompted to retake.
[0036] 103. The k focal length images are fused to obtain a fly ash particle image.
[0037] Specifically, a method for fusing k focal length images to obtain a fly ash particle image includes: K focal length images are encoded to obtain k encoded images; weight values are extracted from the k encoded images to obtain k fusion weights; the k fusion weights and the corresponding encoded images are used to perform depth of field fusion processing to obtain a fly ash particle image.
[0038] Among them, a general image coding processing method can be used for coding processing to obtain k coded images, and then the corresponding fusion weights can be extracted. The fusion weights can be extracted according to the focal length corresponding to the coded image. Different focal lengths correspond to different fusion weights. Finally, a general depth of field fusion processing method is used to fuse the k coded images to obtain a fly ash particle image. The fly ash particle image can be specifically referred to in the subsequent embodiments. Figure 2 、 Figure 3 、 Figure 4 As shown in the picture.
[0039] 104. Extract a first pixel sum of particle pixels in a first roundness interval from the fly ash particle image, and extract a second pixel sum of particle pixels in a second roundness interval from the fly ash particle image, wherein the first roundness interval is a roundness interval greater than a first roundness threshold, the second roundness interval is a roundness interval greater than a second roundness threshold, and the first roundness threshold is greater than the second roundness threshold.
[0040] The first roundness threshold may be 0.8, and the second roundness threshold may be 0.5.
[0041] 105. Determine quality information of the fly ash to be tested by using the first pixel sum, the second pixel sum, and the pixel sum in the fly ash particle image.
[0042] Specifically, a method for determining quality information of fly ash to be detected by using the first pixel sum, the second pixel sum, and the pixel sum in the fly ash particle image includes: C1. Calculate the ratio between the first pixel sum and the second pixel sum to obtain a first ratio; C2. Calculate the ratio of the first total pixel value to the total pixel value in the fly ash particle image to obtain a second ratio; C3. Determine the quality information of the fly ash to be tested according to the first ratio and the second ratio.
[0043] Among them, when the first ratio (roundness ratio, SR), i.e. SR>0.8 / SR>0.5, is higher than 10%, and the second ratio (area ratio) is not less than 85%, it is considered high-quality fly ash; When the first ratio (roundness ratio, SR) is 5% to 10% and the value of SR>0.8 / SR>0.5 is between 5% and 10%, and the second ratio (area ratio) is not less than 50%, it is ordinary fly ash; When the first ratio (roundness ratio, SR) SR>0.8 / SR>0.5 is less than 5%, or the second ratio (area ratio) is less than 50%, it is low-quality fly ash.
[0044] In a specific implementation, another fly ash quality identification method is provided. The ash sample is high-quality fly ash, and the microscopic image of the fly ash sample on the glass slide is as follows: Figure 2 As shown, the specific steps are: a1. Take 0.2g of fly ash sample and mix thoroughly with 20g of pure water to prepare a sample mixture.
[0045] b1. Use a glass rod to stir for 2.5 minutes to fully disperse the sample mixture.
[0046] c1 After stirring stops, use a rubber-tipped dropper to take a tube of mixed liquid at 1 / 2 liquid level (from the liquid surface) within 5 to 10 seconds, and drop one drop on the center of the slide within 1 to 3 seconds, then cover it with a cover glass and press gently to further disperse the fly ash sample suspension.
[0047] d1. Place the prepared fly ash sample on a glass slide under a microscope in a particle morphology recognition and analysis system. Observe first with a 10x objective lens. Adjust the movable ruler clamp and focus knob to obtain a clear image. Select a field of view where the fly ash is relatively evenly dispersed and there are a sufficient number of particles. A field of view where at least 80% of the fly ash particles are present and relatively evenly dispersed is optimal. Then, adjust the objective lens to a 40x lens and obtain a clear image using the 40x objective lens by adjusting the movable ruler clamp and focus knob.
[0048] e1. Select a field of view with evenly dispersed particles and sufficient particles. Adjust the fine focus knob so that the smallest and largest visible particles within the field of view are clear, respectively, to determine the adjustment range of the fine focus knob. Re-adjust the fine focus knob to the position where the smallest particles are clear, so that the particles gradually become clearer from small to large. During this process, take six photos at different focal lengths. Ensure that a photo is taken when most small particles and a photo is taken when most large particles are clear. Take four microscopic photos at different focal lengths in between. During the photo shooting process, the particle morphology recognition and analysis system automatically detects image clarity, contrast, uniform lighting, number of particles, and particle overlap. Unqualified photos will be given a specific unqualified prompt and prompted to retake.
[0049] f1. After the image is taken, it is automatically transmitted to the particle shape recognition and analysis system. The system automatically performs depth-of-field fusion on the six images taken at different focal lengths, producing a clear image of the fly ash particles with a clear majority of particles. The particle shape recognition and analysis system also pre-processes the image to eliminate the effects of uneven lighting and background fluorescence, making the fly ash particle signal more uniform. A smoothing filter is used to reduce image noise and improve subsequent recognition accuracy. The system automatically identifies all particle pixels in the image by using the difference in pixel grayscale value or color between the fly ash particles and the surrounding area (background).
[0050] g1. The particle morphology recognition and analysis system counts the total number of pixels of particles with a roundness of 0.8 or greater and the total number of pixels of particles with a roundness of 0.5 or greater, and divides these to obtain the roundness ratio criterion value SR>0.8 / SR>0.5. Particles with SR>0.8 are identified as glass microbeads, an effective component of fly ash, and the ratio of the total number of glass microbead pixels to the total number of pixels of all particles is used to obtain the area ratio criterion value.
[0051] The roundness ratio SR>0.8 / SR>0.5 of the fly ash sample is 21.5%; the area accounts for 91.3%, which meets the criteria for judging high-quality fly ash.
[0052] More preferably, the optimal magnification of the microscope in step d1 is 400 times.
[0053] Further preferably, in step e1, after taking the photo, the system automatically detects the image clarity, contrast, uniform lighting, number of particles, and particle overlap, and gives a specific unqualified prompt for unqualified photos without saving them.
[0054] More preferably, in step f1, the particle morphology recognition and analysis system automatically performs depth-of-field fusion on 4 to 6 images taken with different focal lengths to obtain an image of fly ash particles in which most particles are clear.
[0055] More preferably, in step f1, the particle morphology recognition and analysis system preprocesses the image to eliminate the effects of uneven lighting or background fluorescence, making the fly ash particle signal more uniform. A smoothing filter is used to reduce image noise, thereby improving subsequent recognition accuracy. The system automatically identifies all particle pixels in the image by utilizing the differences in pixel grayscale value or color between the fly ash particles and the surrounding area (background). It should be noted that the above steps can be performed automatically by the system.
[0056] In a specific implementation, another fly ash quality identification method is provided, such as Figure 3 As shown, the ash sample is normal fly ash, and the microscopic image of the fly ash sample on the glass slide is as follows Figure 3 As shown, the specific steps are: a2. Take 2g of fly ash sample and mix thoroughly with 200g of pure water to prepare a sample mixture.
[0057] b2. Use an ultrasonic disperser to disperse the sample mixture for 2 minutes.
[0058] c2. After stirring stops, use a rubber-tipped dropper to take a tube of mixed liquid at 1 / 2 liquid level (from the liquid surface) within 5 to 10 seconds, and drop one drop on the center of the slide within 1 to 3 seconds. Then cover it with a cover glass and press gently to further disperse the fly ash sample suspension.
[0059] d2. Place the prepared fly ash sample on the glass slide under a microscope in the particle morphology recognition and analysis system. Observe first with a 10x objective lens. Adjust the movable ruler clamp and focus knob to obtain a clear image. Select a field of view where the fly ash is relatively evenly dispersed and has a sufficient number of particles. A field of view where at least 80% of the fly ash particles are present and evenly dispersed is optimal. Then, adjust the objective lens to a 40x lens and obtain a clear image using the 40x objective lens by adjusting the movable ruler clamp and focus knob.
[0060] e2. Select a field of view with evenly dispersed particles and sufficient particles. Adjust the fine focus knob so that the smallest and largest visible particles within the field of view are clear, respectively, to determine the adjustment range of the fine focus knob. Re-adjust the fine focus knob to the position where the smallest particles are clear, so that the particles gradually become clearer from small to large. During this process, take six photos at different focal lengths. Ensure that a photo is taken when most small particles and most large particles are clear. Take four microscopic photos at different focal lengths in between. During the photo shooting process, the particle morphology recognition and analysis system automatically detects image clarity, contrast, uniform lighting, number of particles, and particle overlap. Unqualified photos will be given a specific unqualified prompt and prompted to retake.
[0061] f2. After the image is taken, it is automatically transmitted to the particle shape recognition and analysis system. The system automatically performs depth-of-field fusion on the six images taken at different focal lengths, producing a clear image of the fly ash particles with a clear majority of particles. The particle shape recognition and analysis system also pre-processes the image to eliminate the effects of uneven lighting and background fluorescence, making the fly ash particle signal more uniform. A smoothing filter is used to reduce image noise and improve subsequent recognition accuracy. The system automatically identifies all particle pixels in the image by using the difference in pixel grayscale value or color between the fly ash particles and the surrounding area (background).
[0062] g2. The particle morphology recognition and analysis system calculates the total number of pixels of particles with a roundness of 0.8 or greater and the total number of pixels of particles with a roundness of 0.5 or greater, and divides these to obtain the roundness ratio criterion value SR>0.8 / SR>0.5. Particles with SR>0.8 are identified as glass microbeads, an effective component of fly ash, and the ratio of the total number of glass microbead pixels to the total number of pixels of all particles is used to determine the area ratio criterion value.
[0063] The roundness ratio SR>0.8 / SR>0.5 of the fly ash sample is 20.3%; the area accounts for 83.6%, which meets the judgment criteria of normal fly ash.
[0064] More preferably, the optimal magnification of the microscope in step d2 is 400 times.
[0065] Further preferably, in step e2, after taking the photo, the system automatically detects the image clarity, contrast, uniform lighting, number of particles, and particle overlap, and gives a specific unqualified prompt for unqualified photos without saving them.
[0066] More preferably, in step f2, the particle morphology recognition and analysis system automatically performs depth-of-field fusion on 4 to 6 images taken with different focal lengths to obtain an image of fly ash particles in which most particles are clear.
[0067] More preferably, in step f2, the particle morphology recognition and analysis system preprocesses the image to eliminate the effects of uneven lighting or background fluorescence, making the fly ash particle signal more uniform. A smoothing filter is used to reduce image noise, thereby improving subsequent recognition accuracy. The system automatically identifies all particle pixels in the image by utilizing the differences in pixel grayscale value or color between the fly ash particles and the surrounding area (background). It should be noted that the above steps can be performed automatically by the system.
[0068] In a specific implementation, another fly ash quality identification method is provided. The ash sample is low-quality fly ash, and the microscopic image of the fly ash sample on the glass slide is as follows: Figure 4 As shown, the specific steps are: a3. Take 1g of fly ash sample and mix it thoroughly with 100g of pure water to prepare a sample mixture.
[0069] b3. Use an ultrasonic disperser to disperse the sample mixture for 2 minutes.
[0070] c3. After stirring stops, use a rubber-tipped dropper to take a tube of mixed liquid at 1 / 2 liquid level (from the liquid surface) within 5 to 10 seconds, and drop one drop on the center of the slide within 1 to 3 seconds. Then cover it with a cover glass and press gently to further disperse the fly ash sample suspension.
[0071] D3. Place the prepared fly ash sample on the glass slide under a microscope in the particle morphology recognition and analysis system. Observe first with a 10x objective lens. Adjust the movable ruler clamp and focus knob to obtain a clear image. Select a field of view where the fly ash is relatively evenly dispersed and has a sufficient number of particles. A field of view where at least 80% of the fly ash particles are present and evenly dispersed is optimal. Then, adjust the objective lens to a 40x lens and obtain a clear image using the 40x objective lens by adjusting the movable ruler clamp and focus knob.
[0072] e3. Select a field of view with evenly dispersed particles and sufficient particles. Adjust the fine focus knob to make the smallest and largest visible particles within the field of view clear, respectively, to determine the adjustment range of the fine focus knob. Re-adjust the fine focus knob to the position where the smallest particles are clear, so that the particles gradually become clearer from small to large. During this process, take six photos at different focal lengths. Ensure that a photo is taken when most small particles and a photo is taken when most large particles are clear. Take four microscopic photos at different focal lengths in between. During the photo shooting process, the particle morphology recognition and analysis system automatically detects image clarity, contrast, uniform lighting, number of particles, and particle overlap. Unqualified photos will be given a specific failure notice and prompted to retake.
[0073] f3. After the image is taken, it is automatically transmitted to the particle shape recognition and analysis system. The system automatically performs depth-of-field fusion on the six images taken at different focal lengths, producing a clear image of the fly ash particles with a clear majority of particles. The particle shape recognition and analysis system also pre-processes the image to eliminate the effects of uneven lighting and background fluorescence, making the fly ash particle signal more uniform. A smoothing filter is used to reduce image noise and improve subsequent recognition accuracy. The system automatically identifies all particle pixels in the image by using the difference in pixel grayscale value or color between the fly ash particles and the surrounding area (background).
[0074] g3. The particle morphology recognition and analysis system counts the total number of pixels of particles with a roundness of 0.8 or greater and the total number of pixels of particles with a roundness of 0.5 or greater, and divides these to obtain the roundness ratio criterion value SR>0.8 / SR>0.5. Particles with SR>0.8 are identified as glass microbeads, an effective component of fly ash, and the ratio of the total number of glass microbead pixels to the total number of pixels of all particles is used to obtain the area ratio criterion value.
[0075] The roundness ratio SR>0.8 / SR>0.5 of the fly ash sample is 4.3%; the area accounts for 1.2%, which meets the criteria for judging inferior fly ash.
[0076] More preferably, the optimal magnification of the microscope in step d3 is 400 times.
[0077] Further preferably, in step e3, after taking the photo, the system automatically detects the image clarity, contrast, uniform lighting, number of particles, and particle overlap, and gives a specific unqualified prompt for unqualified photos without saving them.
[0078] More preferably, in step f3, the particle morphology recognition and analysis system automatically performs depth-of-field fusion on 4 to 6 images taken with different focal lengths to obtain an image of fly ash particles in which most particles are clear.
[0079] More preferably, in step f3, the particle morphology recognition and analysis system preprocesses the image to eliminate the effects of uneven lighting or background fluorescence, making the fly ash particle signal more uniform. A smoothing filter is used to reduce image noise, thereby improving subsequent recognition accuracy. The system automatically identifies all particle pixels in the image by utilizing the differences in pixel grayscale value or color between the fly ash particles and the surrounding area (background). It should be noted that the above steps can be performed automatically by the system.
[0080] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that, in order to implement the above functions, the terminal includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of the various examples described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0081] The embodiment of the present application can divide the terminal into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical functional division. In actual implementation, there may be other division methods.
[0082] In line with the above, please see Figure 5 , Figure 5 The present invention provides a schematic diagram of a fly ash quality identification system. Figure 5 As shown, the system includes: An acquisition unit 501 is configured to acquire a glass slide fly ash sample made of fly ash to be tested; and acquire k focal length images of the glass slide fly ash sample at different focal lengths; A fusion unit 502 is used to fuse the k focal length images to obtain a fly ash particle image; an extraction unit 503 configured to extract, from the fly ash particle image, a first pixel sum of particle pixels in a first roundness interval, and to extract, from the fly ash particle image, a second pixel sum of particle pixels in a second roundness interval, wherein the first roundness interval is a roundness interval greater than a first roundness threshold, and the second roundness interval is a roundness interval greater than a second roundness threshold, wherein the first roundness threshold is greater than the second roundness threshold; The determining unit 504 is configured to determine the quality information of the fly ash to be detected by using the first pixel sum, the second pixel sum, and the pixel sum in the fly ash particle image.
[0083] In one possible implementation, in obtaining the fly ash sample on a glass slide made of fly ash to be tested, the obtaining unit 501 is specifically configured to: Mix the fly ash to be tested with pure water to prepare a sample mixture; extracting the sample mixture after dispersing the sample mixture; The extracted mixed solution was loaded onto the center of a glass slide to prepare a glass slide fly ash sample.
[0084] In a possible implementation, in acquiring k focal length images of the glass slide fly ash sample at different focal lengths, the acquiring unit 501 is specifically configured to: The fly ash sample on a glass slide is placed under a microscope of a particle morphology recognition and analysis system to adjust the focus. The image is captured and processed as the particle clarity increases from small to large within the pixel field of view to obtain k focal length images.
[0085] In a possible implementation, the determining unit 504 is specifically configured to: Calculating a ratio between the first pixel sum and the second pixel sum to obtain a first ratio; calculating a ratio between the first total pixel value and the total pixel value in the fly ash particle image to obtain a second ratio; The quality information of the fly ash to be detected is determined according to the first ratio and the second ratio.
[0086] In one possible implementation, the fusion unit 502 is specifically configured to: Encode k focal length pictures to obtain k encoded images; Extract weight values from k encoded images to obtain k fusion weights; The k fusion weights and the corresponding coded images are used to perform depth of field fusion processing to obtain the fly ash particle image.
[0087] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any fly ash quality identification method described in the above method embodiments.
[0088] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program enables a computer to execute part or all of the steps of any fly ash quality identification method recorded in the above method embodiments.
[0089] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.
[0090] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0091] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0092] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.
[0093] In addition, the functional units in the various embodiments of the application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software program modules.
[0094] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk, or optical disk, etc., various media that can store program code.
[0095] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.
[0096] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application. At the same time, for those skilled in the art, according to the idea of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A method for identifying fly ash quality, characterized in that: The method comprises: Obtain a glass slide fly ash sample made of fly ash to be tested; Obtain k focal length images of the fly ash sample on the glass slide at different focal lengths; The k focal length images are fused to obtain the fly ash particle image; Extracting a first pixel sum of particle pixels in a first roundness interval from the fly ash particle image, and extracting a second pixel sum of particle pixels in a second roundness interval from the fly ash particle image, wherein the first roundness interval is a roundness interval greater than a first roundness threshold, the second roundness interval is a roundness interval greater than a second roundness threshold, and the first roundness threshold is greater than the second roundness threshold; The quality information of the fly ash to be detected is determined by using the first pixel sum, the second pixel sum, and the pixel sum in the fly ash particle image.
2. The fly ash quality identification method according to claim 1, characterized in that: The method of obtaining a glass slide fly ash sample made from fly ash to be tested comprises: Mix the fly ash to be tested with pure water to prepare a sample mixture; extracting the sample mixture after dispersing the sample mixture; The extracted mixed solution was loaded onto the center of a glass slide to prepare a glass slide fly ash sample.
3. The fly ash quality identification method according to claim 2, characterized in that: The step of obtaining k focal length images of the glass slide fly ash sample at different focal lengths comprises: The fly ash sample on a glass slide is placed under a microscope of a particle morphology recognition and analysis system to adjust the focus. The image is captured and processed as the particle clarity increases from small to large within the pixel field of view to obtain k focal length images.
4. The fly ash quality identification method according to any one of claims 1 to 3, characterized in that: The method of determining the quality information of the fly ash to be detected by using the total of the first pixels, the total of the second pixels, and the total of pixels in the fly ash particle image includes: Calculating a ratio between the first pixel sum and the second pixel sum to obtain a first ratio; calculating a ratio between the first total pixel value and the total pixel value in the fly ash particle image to obtain a second ratio; The quality information of the fly ash to be detected is determined according to the first ratio and the second ratio.
5. The fly ash quality identification method according to claim 4, characterized in that: The k focal length images are fused to obtain a fly ash particle image, including: Encode k focal length pictures to obtain k encoded images; Extract weight values from k encoded images to obtain k fusion weights; The k fusion weights and the corresponding coded images are used to perform depth of field fusion processing to obtain the fly ash particle image.
6. A fly ash quality identification system, characterized in that: The system comprises: An acquisition unit is used to acquire a glass slide fly ash sample made of fly ash to be tested; and acquire k focal length images of the glass slide fly ash sample at different focal lengths; A fusion unit is used to fuse k focal length images to obtain a fly ash particle image; an extraction unit, configured to extract a first pixel sum of particle pixels in a first roundness interval from the fly ash particle image, and to extract a second pixel sum of particle pixels in a second roundness interval from the fly ash particle image, wherein the first roundness interval is a roundness interval greater than a first roundness threshold, and the second roundness interval is a roundness interval greater than a second roundness threshold, wherein the first roundness threshold is greater than the second roundness threshold; The determination unit is configured to determine the quality information of the fly ash to be detected by using the first pixel sum, the second pixel sum, and the pixel sum in the fly ash particle image.
7. The fly ash quality identification system according to claim 6, characterized in that: In the aspect of obtaining the fly ash sample on a glass slide made of fly ash to be tested, the obtaining unit is specifically used for: Mix the fly ash to be tested with pure water to prepare a sample mixture; extracting the sample mixture after dispersing the sample mixture; The extracted mixed solution was loaded onto the center of a glass slide to prepare a glass slide fly ash sample.
8. The fly ash quality identification system according to claim 7, characterized in that: In the aspect of obtaining k focal length images of the glass slide fly ash sample at different focal lengths, the obtaining unit is specifically used for: The fly ash sample on a glass slide is placed under a microscope of a particle morphology recognition and analysis system to adjust the focus. The image is captured and processed as the particle clarity increases from small to large within the pixel field of view to obtain k focal length images.
9. The fly ash quality identification system according to any one of claims 6 to 8, characterized in that: The determining unit is specifically configured to: Calculating a ratio between the first pixel sum and the second pixel sum to obtain a first ratio; calculating a ratio between the first total pixel value and the total pixel value in the fly ash particle image to obtain a second ratio; The quality information of the fly ash to be detected is determined according to the first ratio and the second ratio.
10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor, the processor executes the fly ash quality identification method according to any one of claims 1 to 5.