Method and device for identifying particle size of biomass

Abstract

The application relates to the technical field of biomass particle size identification, in particular to a biomass particle size identification method and device, wherein the method comprises the following steps: acquiring geometric characteristic parameters of biomass according to a material image of the biomass, so as to determine the sphericity and the length-width ratio of the biomass; determining the category of the biomass according to the sphericity and the length-width ratio, obtaining the corresponding burnout time according to the category, and determining the range where the burnout time is located; in response to the case that the range where the burnout time is located is a first range, determining a diameter correction value of the biomass according to the length-width ratio and the sphericity, identifying the particle size distribution of the biomass according to the diameter correction value, and obtaining a biomass particle evaluation result. Therefore, the problems that, in the related art, the measurement results lack comparability and universality due to the fact that different equivalent diameters are used to define biomass particles, and the image analysis method is restricted in industrial scene popularization and application are solved.

Description

Technical Field

[0001] This application relates to the field of biomass particle size identification technology, and in particular to a method and apparatus for identifying the particle size of biomass. Background Technology

[0002] Biomass co-firing power generation is one of the main technological routes for the clean power generation transformation of coal-fired boilers. In industrial practice, biomass particles have diverse shapes and large differences in three-dimensional data, possessing unique packing characteristics, combustion rates, and heat and mass transfer efficiencies. Establishing an accurate and rapid biomass particle size measurement system and evaluation method can help improve the utilization efficiency of biomass fuel, thereby promoting the green transformation of coal-fired boilers.

[0003] Among related technologies, the main particle screening methods currently include the following: 1. Particles are classified by using standard sieves with different apertures, and the mass fraction of each particle size is counted to determine the particle size distribution. However, this method requires manual operation, is time-consuming, has large errors, and has not yet been widely used in industrial online detection.

[0004] 2. Based on the principles of light scattering and diffraction, biomass particles are sprayed into the test area, and the particle size distribution is calculated from the intensity distribution of scattered light. However, this method is greatly affected by particle uniformity and the test environment, and is not suitable for use in production.

[0005] 3. By using industrial cameras to acquire images of biomass particles, and obtaining the particle size, distribution, and morphology through edge recognition, feature extraction, and statistical algorithms, this image analysis method has a high degree of automation and strong industrial scalability. It has been tested for online monitoring on some biomass fuel production lines.

[0006] However, among related technologies, although image analysis is highly automated and has the potential to identify irregular particle sizes, its large-scale industrial application is limited by the highly diverse morphology of biomass particles and the large differences in length, width, and thickness. To address this issue, different studies often use different equivalent diameter definitions, which leads to a lack of comparability and universality in measurement results. This inconsistency in criteria has become a major obstacle to the promotion and application of image analysis in industrial scenarios. Summary of the Invention

[0007] This application provides a method and apparatus for identifying the particle size of biomass, in order to solve the problems in related technologies, such as the lack of comparability and universality of measurement results due to the use of different equivalent diameters to define biomass particles, which in turn restricts the promotion and application of image analysis methods in industrial scenarios.

[0008] The first aspect of this application provides a method for identifying the particle size of biomass, comprising the following steps: obtaining geometric feature parameters of the biomass based on a material image of the biomass to determine the sphericity and aspect ratio of the biomass; determining the category of the biomass based on the sphericity and aspect ratio, and obtaining the corresponding burnout time based on the category, and determining the range of the burnout time; in response to the range being a first range, determining a diameter correction value of the biomass based on the aspect ratio and the sphericity, so as to identify the particle size distribution of the biomass based on the diameter correction value, and to obtain a biomass particle size evaluation result.

[0009] Using the aforementioned technical means, this embodiment of the application can extract the geometric feature parameters of biomass particles through image recognition technology, and use the surface area-to-volume ratio diameter D32 (also known as the SAUTER diameter) as the equivalent particle size. During the calculation process, the D32 diameter is corrected by aspect ratio and sphericity. Compared with the traditional equivalent sphere diameter, the corrected D32 diameter can more accurately capture the influence of the shortest dimension of biomass particles on the heat and mass transfer process, thereby enhancing the guiding significance of the image recognition system's recognition results for actual production.

[0010] Optionally, in one embodiment of this application, the method further includes: in response to the condition that the range is a first range, using the volume equivalent diameter as a standard sample to identify the particle size distribution of the biomass; and in response to the condition that the range is a first range, using the surface area equivalent diameter as a standard sample to identify the particle size distribution of the biomass.

[0011] Through the above-mentioned technical means, the embodiments of this application can classify biomass particles into different morphological types based on the classification and evaluation method of sphericity and aspect ratio, and associate them with burnout characteristics. This allows for the construction of a unified equivalent particle size evaluation system that combines the surface area-volume ratio diameter and the equivalent diameter of the sphere, thereby obtaining the particle size distribution results of biomass particles. This enables rapid, accurate, and unified particle size identification and evaluation of biomass particles from different sources and morphologies, improving the feasibility of combustion characteristic prediction and industrial applications.

[0012] Optionally, in one embodiment of this application, obtaining the geometric feature parameters of the biomass based on the biomass image includes: acquiring an initial biomass image; performing image preprocessing on the initial biomass image to obtain a biomass image that meets preset image conditions; and inputting the biomass image into a pre-constructed recognition model to output the geometric feature parameters.

[0013] Optionally, in one embodiment of this application, the formula for calculating the aspect ratio is: , in,L i This indicates the aspect ratio of the particle. a imax Indicates the maximum major axis. b imax Indicates the maximum minor axis; The formula for calculating the sphericity is: , in, C i Indicates the sphericity of the particles. A S This represents the surface area of ​​a sphere with the same volume as a biomass pellet. S i This indicates the surface area of ​​the particle.

[0014] Through the above-mentioned technical means, the embodiments of this application can quantitatively distinguish the shape type of each biomass particle by solving the aspect ratio of each biomass particle, and quantitatively determine the regularity of the particle morphology by solving the sphericity of each biomass particle.

[0015] Optionally, in one embodiment of this application, the formula for calculating the diameter correction value is: , in, d i This indicates the method for calculating the corresponding equivalent diameter.

[0016] Through the aforementioned technical means, the embodiments of this application can be solved based on the correction of the D32 diameter of biomass particles. By introducing morphological factor correction terms such as sphericity and aspect ratio, the original errors caused by deviations such as non-spherical particle shape can be effectively offset. This can not only improve the authenticity and reliability of particle size data, but also strengthen its correlation accuracy with core performance such as combustion efficiency and molding energy consumption. This provides precise support for process optimization, combustion equipment adaptation, fuel ratio adjustment and energy consumption control. At the same time, it can unify the particle size evaluation standards of biomass particles from different sources and in different forms, improve the comparability between batches and raw materials, and help to make the entire process of biomass processing and utilization more efficient, refined and standardized.

[0017] A second aspect of this application provides a biomass particle size identification device, comprising: a first determining module, configured to acquire geometric feature parameters of the biomass based on a material image of the biomass, to determine the sphericity and aspect ratio of the biomass; a second determining module, configured to determine the category of the biomass based on the sphericity and aspect ratio, and obtain the corresponding burnout time based on the category, and determine the range of the burnout time; and a first identifying module, configured to, in response to the condition that the range is a first range, determine a diameter correction value of the biomass based on the aspect ratio and the sphericity, to identify the particle size distribution of the biomass based on the diameter correction value, so as to obtain a biomass particle size evaluation result.

[0018] Using the aforementioned technical means, this embodiment of the application can extract the geometric feature parameters of biomass particles through image recognition technology, and use the surface area-to-volume ratio diameter D32 (also known as the SAUTER diameter) as the equivalent particle size. During the calculation process, the D32 diameter is corrected by aspect ratio and sphericity. Compared with the traditional equivalent sphere diameter, the corrected D32 diameter can more accurately capture the influence of the shortest dimension of biomass particles on the heat and mass transfer process, thereby enhancing the guiding significance of the image recognition system's recognition results for actual production.

[0019] Optionally, in one embodiment of this application, it further includes: a second identification module, configured to identify the particle size distribution of the biomass using the volume equivalent diameter as a standard sample when the range is a first range; and a third identification module, configured to identify the particle size distribution of the biomass using the surface area equivalent diameter as a standard sample when the range is a first range.

[0020] Through the above-mentioned technical means, the embodiments of this application can classify biomass particles into different morphological types based on the classification and evaluation method of sphericity and aspect ratio, and associate them with burnout characteristics. This allows for the construction of a unified equivalent particle size evaluation system that combines the surface area-volume ratio diameter and the equivalent diameter of the sphere, thereby obtaining the particle size distribution results of biomass particles. This enables rapid, accurate, and unified particle size identification and evaluation of biomass particles from different sources and morphologies, improving the feasibility of combustion characteristic prediction and industrial applications.

[0021] Optionally, in one embodiment of this application, the first determining module includes: a collection unit for collecting an initial material image of the biomass; a processing unit for performing image preprocessing on the initial material image to obtain a material image that meets preset image conditions; and an output unit for inputting the material image into a pre-constructed recognition model to output the geometric feature parameters.

[0022] Optionally, in one embodiment of this application, the formula for calculating the aspect ratio is: , in, L i This indicates the aspect ratio of the particle. a imax Indicates the maximum major axis. b imax Indicates the maximum minor axis; The formula for calculating the sphericity is: , in, C i Indicates the sphericity of the particles. A S This represents the surface area of ​​a sphere with the same volume as a biomass pellet. S i This indicates the surface area of ​​the particle.

[0023] Through the above-mentioned technical means, the embodiments of this application can quantitatively distinguish the shape type of each biomass particle by solving the aspect ratio of each biomass particle, and quantitatively determine the regularity of the particle morphology by solving the sphericity of each biomass particle.

[0024] Optionally, in one embodiment of this application, the formula for calculating the diameter correction value is: , in, d i This indicates the method for calculating the corresponding equivalent diameter.

[0025] Through the aforementioned technical means, the embodiments of this application can be solved based on the correction of the D32 diameter of biomass particles. By introducing morphological factor correction terms such as sphericity and aspect ratio, the original errors caused by deviations such as non-spherical particle shape can be effectively offset. This can not only improve the authenticity and reliability of particle size data, but also strengthen its correlation accuracy with core performance such as combustion efficiency and molding energy consumption. This provides precise support for process optimization, combustion equipment adaptation, fuel ratio adjustment and energy consumption control. At the same time, it can unify the particle size evaluation standards of biomass particles from different sources and in different forms, improve the comparability between batches and raw materials, and help to make the entire process of biomass processing and utilization more efficient, refined and standardized.

[0026] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the biomass particle size identification method as described in the above embodiments.

[0027] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described biomass particle size identification method.

[0028] A fifth aspect of this application provides a computer program product that stores a computer program that, when executed by a processor, implements the above-described biomass particle size identification method.

[0029] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0030] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a biomass particle size identification method provided according to an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a biomass particle size identification device according to an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0031] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0032] Currently, methods for measuring biomass particle size are showing a gradual development trend. Early methods mainly relied on traditional image analysis. Some researchers proposed a method for measuring the particle size distribution of biomass powder (CN111272616A), which uses a scanner to acquire two-dimensional images of biomass powder and uses software to extract the particle projection area and geometric parameters to achieve statistical analysis of particle size distribution. This type of method is simple in structure, but the testing speed is slow, the accuracy is poor, and it is mainly used for offline measurement. To address this problem, based on the need for online measurement and identification, some researchers have proposed a biomass fuel particle size identification system based on collision sound characteristics (CN115683959A), which collects biological... The sound signal of biomass particles falling and hitting the measuring plate is used to infer the biomass particle size based on the sound signal and spectral characteristics, thus achieving quasi-online particle size identification. Meanwhile, in order to further solve the problem of rapid and accurate identification of biomass particle size, some researchers have developed a deep learning holographic online metering method for the blending ratio of coal and biomass (CN112749507A). This scheme uses digital holograms to obtain the amplitude / phase map of the mixed particles, combines it with a convolutional neural network to identify the particle type, and predicts the blending ratio based on this, providing data basis for adjusting the amount of raw materials fed into the furnace.

[0033] While existing biomass pellet size measurement technology has made some progress through various new technical means, its application faces challenges. Due to the diverse morphology of biomass pellets, the dimensional data obtained by any technical means require secondary calculation of the equivalent particle size. Existing particle size evaluation methods are difficult to directly assess the combustion characteristics of pellets. Furthermore, the diverse sources and shapes of biomass raw materials, with potential significant size differences between batches, make it impossible to reasonably assess the combustion characteristics of biomass. This directly restricts the adjustment of biomass raw material ratios and furnace feed rates in actual industrial production. At the same time, the significant differences in burnout time between pellets of different sizes can lead to inaccurate burnout time predictions due to unreasonable criteria, making it difficult to coordinate combustion optimization with tail emission control.

[0034] The reason for this is that biomass pellets come from a wide range of sources, are diverse in type, and have great variations in morphology. In the existing research, researchers either characterize the particle size of biomass pellets based on the projected equivalent circle diameter or simple geometric parameters, or they have not detailed how to calculate the equivalent particle size of biomass pellets. As a result, a universal method for judging the combustion characteristics of biomass pellets cannot be formed. This mismatch between morphology and criteria is the fundamental problem that makes it difficult to promote the current technology.

[0035] Therefore, this application proposes a new method and apparatus for identifying the particle size of biomass. It obtains the geometric feature parameters of biomass particles through image recognition technology, and establishes an equivalent particle size evaluation system by combining the surface area-volume ratio diameter and the equivalent diameter of a sphere. This forms a biomass particle size identification and evaluation system with industrial application potential, thereby overcoming the technical defects in existing biomass particle size measurement methods, such as the lack of a clear method for determining the equivalent particle size and its theoretical basis, the difficulty in accurately reflecting the burnout characteristics of biomass particles, and the restriction on their promotion and application in industrial scenarios.

[0036] The following description, with reference to the accompanying drawings, describes a method and apparatus for biomass particle size identification according to embodiments of this application. Addressing the problem mentioned in the background section of the related technologies where different equivalent diameters are used to define biomass particles, resulting in a lack of comparability and universality in measurement results, thus hindering the promotion and application of image analysis methods in industrial scenarios, this application provides a biomass particle size identification method. In this method, operations such as grayscale conversion, filtering, and contrast equalization are used to ensure clear particle boundaries and avoid identification errors; the minimum dimensional average value is obtained through measured samples to compensate for the deficiencies of two-dimensional images; and a unified criterion based on D32 is established, combined with sphericity and aspect ratio for correction, making the results more consistent with the biomass combustion process. Therefore, this solves the problem in the related technologies where the use of different equivalent diameters to define biomass particles leads to a lack of comparability and universality in measurement results, thus hindering the promotion and application of image analysis methods in industrial scenarios.

[0037] Specifically, Figure 1 This is a schematic flowchart of a biomass particle size identification method provided in an embodiment of this application.

[0038] like Figure 1 As shown, the biomass particle size identification method includes the following steps: In step S101, the geometric feature parameters of the biomass are obtained based on the biomass image to determine the sphericity and aspect ratio of the biomass.

[0039] Biomass refers to various organic substances produced through photosynthesis using the atmosphere, water, and land. In other words, all living, growing organic matter is collectively called biomass, which includes, but is not limited to, biomass raw materials and biomass pellet fuel. Biomass raw materials include various plants, crop straw, and forestry waste. For example, a pile of corn stalks naturally displays yellow and brown colors, and the stalks vary in shape, including long stalks and broken leaves. Biomass pellet fuel is pellet fuel made by compressing biomass raw materials.

[0040] Optionally, in one embodiment of this application, obtaining the geometric feature parameters of biomass based on the biomass image includes: acquiring an initial biomass image; performing image preprocessing on the initial biomass image to obtain a biomass image that meets preset image conditions; and inputting the biomass image into a pre-constructed recognition model to output the geometric feature parameters.

[0041] Specifically, in this embodiment of the application, acquiring an initial material image of biomass includes: First, a sample of biomass particles to be tested within a certain weight range needs to be weighed. The sample includes common woody and herbaceous biomass. Then, a representative sample can be obtained by mixing the samples using a rotary sampler or the quartering method. It should be ensured that impurities and out-of-range particles are removed. The biomass sample can then be evenly spread on a horizontal support platform. The support platform can be set as a diffuse reflective surface, and a length scale can be determined. The thickness of the spread layer can be controlled to be less than 5 mm. A scraper is used to ensure that the particles do not overlap, so that the smallest dimension of the particles is approximately perpendicular to the support platform. The sample batch and environmental conditions are recorded for result reproduction.

[0042] Next, images of the biomass are collected. Specifically, images can be acquired using an industrial camera under uniform lighting conditions. The biomass particles to be tested are randomly grouped, with at least 3 images taken for each group of samples, and the entire group of tests is repeated at least 3 times. The distance between the camera and the support plate and the field of view can be set according to the sample coverage area. The images are transmitted to the computer via 485 bus / USB / Ethernet, and the files are saved in a lossless or low-compression format (e.g., PNG, lossless JPEG).

[0043] In this embodiment of the application, the pixel-to-actual length conversion can also be completed based on the calibration diagram of the bearing plate ruler to obtain the pixel size coefficient k1 for imaging calibration. In this way, the length corresponding to each pixel point during the current test can be calculated. For example, if there are 8 pixels within a 1cm ruler length, then the pixel size coefficient is 1 / 8.

[0044] The raw images often contain uneven lighting and reflective particles. If used directly, they can lead to blurred particle boundaries and inaccurate identification. Therefore, preprocessing operations such as grayscale conversion, filtering, and contrast equalization can be used to clean up the images and make the particles and background more distinct. Even after image preprocessing, if some overlap occurs between particles, edge detection and connected component labeling should be used to find the approximate range of the particles. Watershed segmentation and distance transformation can be used to further separate the adhering particles. Based on this, a neural network algorithm can be used to identify the size characteristics of the biomass.

[0045] Furthermore, the material image is input into a pre-built recognition model to output geometric feature parameters, including: Before testing, excessively large or small biomass particles can be removed from the test sample. Specific standards can be selected according to testing requirements. Then, using image recognition algorithms, based on the size of each pixel and the number of pixels corresponding to the measurement object, the projection surface of each particle (since only a two-dimensional image of the projection surface can be extracted, essentially the shape seen from above, referred to here as the projection surface) is measured as follows: Within each individual particle, mutually perpendicular line segments are established, with the longer line segment considered the major axis. a i The shorter line segment is considered the minor axis. b i Each time the rotation is 10 degrees, a set of data is retained. A total of 180 degrees are rotated, and the maximum combination of major and minor axes is obtained from this combination, denoted as . a imax , b imax Furthermore, the perimeter can also be obtained based on image recognition algorithms. P i .

[0046] Since image testing can only identify two-dimensional cross-sections and cannot measure the smallest dimension, 30-50 samples should be randomly selected from the raw material for actual measurement, and the arithmetic mean should be taken as the particle height. c i This allows us to determine the third dimension of biomass particles.

[0047] The geometric feature parameters may include the surface area and volume of the biomass particles. In this embodiment, the surface area of ​​each particle can be calculated based on the projected area and the minimum dimension.

[0048] Calculate the volume of each particle:

[0049] The diameter of each particle at equal volume:

[0050] Diameter of each particle with equal surface area:

[0051] This allows us to obtain the size data for each particle.

[0052] Through the aforementioned technical means, the embodiments of this application can achieve efficient and automated acquisition of biomass geometric characteristic parameters through systematic image acquisition, preprocessing, and intelligent recognition. This not only overcomes the problems of low efficiency and strong subjectivity of traditional manual measurement methods, but also ensures the standardization and consistency of data sources through standardized image preprocessing. Furthermore, advanced recognition models can be used to achieve accurate quantification and feature extraction of complex and irregular biomass morphology, thereby significantly improving the accuracy and efficiency of biomass characteristic analysis. This provides a reliable data foundation and decision support for subsequent classification, quality assessment, process optimization, and resource utilization, and promotes the intelligent development of related fields.

[0053] Furthermore, after obtaining the size data corresponding to each particle, it is also necessary to determine the criteria for the particles, specifically the aspect ratio and sphericity of the particles.

[0054] Optionally, in one embodiment of this application, the formula for calculating the aspect ratio is:

[0055] in, L i This indicates the aspect ratio of the particle. a imax Indicates the maximum major axis. b imax Indicates the maximum minor axis.

[0056] The formula for calculating sphericity is:

[0057] in, C i Indicates the sphericity of the particles. A S This represents the surface area of ​​a sphere with the same volume as a biomass pellet. S i This indicates the surface area of ​​the particle.

[0058] In the processing, application, and performance research of particulate materials (such as biomass pellets, powder materials, and industrial pellets), aspect ratio (the ratio of particle length to width) and sphericity (the degree to which the actual shape of the particle closely resembles an ideal sphere) are core geometric characteristic parameters, and their role is involved throughout the entire process of particle processing, equipment design, performance control, and application effect optimization.

[0059] The aspect ratio can directly reflect the "shape regularity" and "anisotropy" of particles. Sphericity is usually defined as "the ratio of the actual surface area of ​​a particle to the surface area of ​​an ideal sphere of the same volume", with a value of 0 to 1. The closer it is to 1, the closer it is to a sphere.

[0060] Through the above-mentioned technical means, the embodiments of this application can quantitatively distinguish the shape type of each biomass particle by solving the aspect ratio of each biomass particle, and quantitatively determine the regularity of the particle morphology by solving the sphericity of each biomass particle.

[0061] In step S102, the biomass category is determined based on sphericity and aspect ratio, and the corresponding burnout time is obtained based on the category, thus determining the range of burnout time.

[0062] Specifically, in this application embodiment, two data points, sphericity and aspect ratio, can be introduced to classify and evaluate the morphology of biomass particles, and the classification criteria are shown in Table 1:

[0063] As one possible approach, embodiments of this application can be based on the sphericity classification and evaluation results of cases 1-9 in Table 1, respectively, using the volume equivalent diameter D... V Surface area equivalent diameter D A Spherical biomass pellets of the corresponding diameter were prepared as standard samples, and burnout time tests were conducted to obtain the standard burnout time t. V and t A Then, 2-3 groups of raw materials were selected from each particle size group (each biomass pellet group classified according to case 1-case 9) for experimental testing to obtain the burnout time t under different sphericity. i .

[0064] As another possible approach, embodiments of this application can also be based on the aspect ratio classification evaluation results of cases 1-9 in Table 1, respectively, using the volume equivalent diameter D... V Surface area equivalent diameter D A Spherical biomass pellets of the corresponding diameter were prepared as standard samples, and burnout time tests were conducted to obtain the standard burnout time t. V and t A Then, 2-3 groups of raw materials were taken from each particle size group (each biomass pellet group classified according to case 1-case 9) for experimental testing to obtain the burnout time t under different sphericity. i .

[0065] In step S103, in response to the condition that the range is the first range, the diameter correction value of the biomass is determined according to the aspect ratio and sphericity, so as to identify the particle size distribution of the biomass according to the diameter correction value, so as to obtain the biomass particle evaluation result.

[0066] The first range can be understood as the error range between the burn-out time of the standard sample and the burn-out time of the actual particles. In the embodiments of this application, the burn-out time error range can be set to not exceed ±10% of the overall burn-out time.

[0067] Optionally, in one embodiment of this application, the method further includes: in response to the condition that the range is a first range, using the volume equivalent diameter as a standard sample to identify the particle size distribution of biomass; and in response to the condition that the range is a first range, using the surface area equivalent diameter as a standard sample to identify the particle size distribution of biomass.

[0068] Specifically, as an feasible approach, taking the sphericity classification evaluation results of cases 1-9 in Table 1 to distinguish particle size ranges as an example, t i With t V and t A By plotting a two-dimensional curve of burnout time and sphericity, t can be obtained. V With t A The smaller of the errors in burnout time and actual particle burnout time should be used as the method for calculating the equivalent diameter of particles within the current sphericity range. The burnout time error range should not exceed ±10% of the overall burnout time. The calculated equivalent diameter is:

[0069]

[0070] Where N1 and N2 are the sphericity ranges that satisfy the corresponding error requirements.

[0071] As another feasible approach, taking the particle size range distinguished based on the aspect ratio classification evaluation results of cases 1-9 in Table 1 as an example, t i With t V and t A By plotting a two-dimensional curve of burnout time and sphericity, t can be obtained. V With t A The smaller of the errors in burnout time and actual particle burnout time should be used as the method for calculating the equivalent diameter of particles within the current sphericity range. The burnout time error range should not exceed ±10% of the overall burnout time. The calculated equivalent diameter is:

[0072]

[0073] Among them, N3 and N4 are the aspect ratio ranges that meet the corresponding error requirements.

[0074] That is, the embodiments of this application distinguish particle size ranges using sphericity and aspect ratio respectively. The ultimate goal is that for a certain group of biomass particles, if sphericity is used for classification, D can be obtained. V Or D A To determine which is better, use sphericity for classification. If that doesn't work, use aspect ratio for classification. If that still doesn't work, then use a combination of sphericity and aspect ratio to classify D.V Or D A The correction is made to obtain the equivalent diameter that can accurately reflect the burnout time of the current biomass pellet pack.

[0075] Specifically, if determining the equivalent diameter using sphericity and aspect ratio separately for different particle size ranges within a certain particle size range fails to yield a reasonable equivalent diameter calculation method within the error range, then it is necessary to conduct 3-5 sets of repeated experiments for particles within that range, and establish a calculation equation with aspect ratio, sphericity, and equivalent diameter as variables. The equivalent diameter calculation method with smaller error should then be selected to correct the experimental parameters of sphericity and aspect ratio, resulting in the equivalent diameter:

[0076] or

[0077] Through the above-mentioned technical means, the embodiments of this application can classify biomass particles into different morphological types based on the classification and evaluation method of sphericity and aspect ratio, and associate them with burnout characteristics. This allows for the construction of a unified equivalent particle size evaluation system that combines the surface area-volume ratio diameter and the equivalent diameter of the sphere, thereby obtaining the particle size distribution results of biomass particles. This enables rapid, accurate, and unified particle size identification and evaluation of biomass particles from different sources and morphologies, improving the feasibility of combustion characteristic prediction and industrial applications.

[0078] Optionally, in one embodiment of this application, the formula for calculating the diameter correction value is: , In this embodiment of the application, after determining the corresponding equivalent diameter through the above process, a corrected solution method for calculating the D32 diameter for biomass particle size can be obtained, namely:

[0079] in, d i Each method is used to calculate the corresponding equivalent diameter.

[0080] Through the above-mentioned technical means, the embodiments of this application can be solved based on the correction of the D32 diameter of biomass particles. By introducing morphological factor correction terms such as sphericity and aspect ratio, the original errors caused by deviations such as non-spherical particle shape can be effectively offset. This can not only improve the authenticity and reliability of particle size data, but also strengthen its correlation accuracy with core performance such as combustion efficiency and molding energy consumption. This provides precise support for processing technology optimization, combustion equipment adaptation, fuel ratio adjustment and energy consumption control. At the same time, it can unify the particle size evaluation standards of biomass particles from different sources and in different forms, improve the comparability between batches and raw materials, and help to make the entire process of biomass processing and utilization more efficient, refined and standardized.

[0081] In summary, the key technical points of the embodiments of this application can be roughly summarized as follows: 1. Combining two-dimensional image recognition and minimum dimension compensation, the particle volume, surface area and equivalent diameter are calculated. Based on the equivalent diameter of the particle size determined by classification, the modified D32 diameter is used as a unified criterion for the equivalent diameter of the group.

[0082] 2. For the segmentation method of agglomerated biomass particles, a watershed segmentation and neural network are combined to achieve the separation of complex particles.

[0083] 3. Based on the classification and evaluation method of sphericity and aspect ratio, biomass pellets are divided into different morphological types and correlated with burnout characteristics.

[0084] The image recognition-based biomass particle size measurement and evaluation method proposed in this application involves laying samples flat on a horizontal platform and acquiring images using an industrial camera. After the images are transmitted to a computer via 485 communication, an image recognition algorithm based on a neural network method is used to extract geometric feature parameters such as the length and width of the biomass particles. Then, a unified equivalent particle size evaluation system is constructed by combining the surface area-volume ratio diameter and the equivalent diameter of a sphere to obtain the particle size distribution results of the biomass particles. This enables rapid, accurate, and unified particle size identification and evaluation of biomass particles from different sources and with different morphologies, improving the feasibility of combustion characteristic prediction and industrial applications.

[0085] Some technical points in the embodiments of this application can be replaced by other methods: (1) Image acquisition: In addition to industrial cameras, mobile phone high-definition cameras, scanners or microscope imaging devices can also be used, with the same principle.

[0086] (2) Image preprocessing: In addition to grayscale conversion and median filtering, Gaussian filtering, bilateral filtering, histogram equalization and other methods can also be used, all of which aim to enhance the particle boundaries.

[0087] (3) Particle segmentation: In addition to watershed and deep learning, segmentation methods such as region growing, k-means clustering, and contour fitting can also be used.

[0088] (4) Third dimension measurement: In addition to sampling and actual measurement, thickness information can also be obtained through laser scanning, structured light imaging, and binocular stereo cameras.

[0089] (5) Calculation of equivalent diameter: In addition to D32, D43, projected equivalent diameter, etc. can also be tried as alternative criteria. After experimental correction, the same goal can be achieved.

[0090] The biomass particle size identification method proposed in this application can ensure clear particle boundaries and avoid identification errors through operations such as grayscale conversion, filtering, and contrast equalization; it obtains the minimum dimensional average value through measured samples to compensate for the shortcomings of two-dimensional images; and it establishes a unified criterion based on D32, combined with sphericity and aspect ratio for correction, making the results more consistent with the biomass combustion process. Therefore, it solves the problems in related technologies where the use of different equivalent diameters to define biomass particles leads to a lack of comparability and universality in measurement results, thus restricting the promotion and application of image analysis methods in industrial scenarios.

[0091] In other words, the biomass particle size identification method proposed in this application can solve the problems of inconsistent criteria and incomparable results in existing studies by introducing the improved surface area-volume ratio diameter (D32) based on the actual morphological characteristics of the particles as the basic calculation method for the equivalent diameter; and by combining two-dimensional image recognition with third-dimensional sampling compensation, the volume and surface area estimation of the particles can be made closer to reality, improving the correlation between the particle size distribution results and the actual combustion characteristics; and for the problem of severe adhesion and overlap of biomass particles, watershed segmentation and neural network segmentation methods can be used to improve the identification accuracy under complex morphologies.

[0092] Next, refer to the appendix. Figure 2 This application describes a biomass particle size identification device according to embodiments thereof.

[0093] Figure 2 This is a block diagram of a biomass particle size identification device according to an embodiment of this application.

[0094] like Figure 2 As shown, the biomass particle size identification device 10 includes: a first determining module 100, a second determining module 200, and a first identifying module 300.

[0095] The first determining module 100 is used to obtain the geometric feature parameters of the biomass based on the biomass image, so as to determine the sphericity and aspect ratio of the biomass.

[0096] The second determining module 200 is used to determine the category of biomass based on sphericity and aspect ratio, and to obtain the corresponding burnout time based on the category, thereby determining the range of burnout time.

[0097] The first identification module 300 is used to determine the diameter correction value of biomass based on aspect ratio and sphericity when the range is a first range, so as to identify the particle size distribution of biomass based on the diameter correction value and obtain the biomass particle evaluation result.

[0098] Optionally, in one embodiment of this application, the biomass particle size identification device 10 further includes: a second identification module and a third identification module; wherein, the second identification module is used to identify the particle size distribution of biomass by using the volume equivalent diameter as a standard sample when the range is a first range; and the third identification module is used to identify the particle size distribution of biomass by using the surface area equivalent diameter as a standard sample when the range is a first range.

[0099] Optionally, in one embodiment of this application, the first determining module 100 includes: a collection unit, a processing unit, and an output unit; wherein, the collection unit is used to collect an initial material image of biomass; the processing unit is used to perform image preprocessing on the initial material image to obtain a material image that meets preset image conditions; and the output unit is used to input the material image into a pre-constructed recognition model to output geometric feature parameters.

[0100] Optionally, in one embodiment of this application, the formula for calculating the aspect ratio is: , in, L i This indicates the aspect ratio of the particle. a imax Indicates the maximum major axis. b imax Indicates the maximum minor axis; The formula for calculating sphericity is: , in, C i Indicates the sphericity of the particles. A S This represents the surface area of ​​a sphere with the same volume as a biomass pellet. S i This indicates the surface area of ​​the particle.

[0101] Optionally, in one embodiment of this application, the formula for calculating the diameter correction value is: , in, d i This indicates the method for calculating the corresponding equivalent diameter.

[0102] It should be noted that the foregoing explanation of the embodiment of the biomass particle size identification method also applies to the biomass particle size identification device of this embodiment, and will not be repeated here.

[0103] The biomass particle size identification device proposed in this application can ensure clear particle boundaries and avoid identification errors through operations such as grayscale conversion, filtering, and contrast equalization; it obtains the minimum dimensional average value through actual measurement samples to compensate for the shortcomings of two-dimensional images; and it establishes a unified criterion based on D32, combined with sphericity and aspect ratio for correction, making the results more consistent with the biomass combustion process. Therefore, it solves the problems in related technologies where the use of different equivalent diameters to define biomass particles leads to a lack of comparability and universality in measurement results, thus restricting the promotion and application of image analysis methods in industrial scenarios.

[0104] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 301, the processor 302, and the computer program stored on the memory 301 and capable of running on the processor 302.

[0105] When the processor 302 executes the program, it implements the biomass particle size identification method provided in the above embodiments.

[0106] Furthermore, electronic devices also include: Communication interface 303 is used for communication between memory 301 and processor 302.

[0107] The memory 301 is used to store computer programs that can run on the processor 302.

[0108] The memory 301 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0109] If the memory 301, processor 302, and communication interface 303 are implemented independently, then the communication interface 303, memory 301, and processor 302 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0110] Optionally, in a specific implementation, if the memory 301, processor 302, and communication interface 303 are integrated on a single chip, then the memory 301, processor 302, and communication interface 303 can communicate with each other through an internal interface.

[0111] Processor 302 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0112] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described biomass particle size identification method.

[0113] This application also provides a computer program product storing a computer program that, when executed by a processor, implements the above-described biomass particle size identification method.

[0114] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0115] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0116] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0117] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0118] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0119] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0120] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0121] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for identifying the particle size of biomass, characterized in that, Includes the following steps: Geometric feature parameters of the biomass are obtained from the biomass image to determine the sphericity and aspect ratio of the biomass. The biomass category is determined based on the sphericity and aspect ratio, and the corresponding burnout time is obtained based on the category, thus determining the range of the burnout time. In response to the condition that the range is a first range, a diameter correction value for the biomass is determined based on the aspect ratio and the sphericity, so as to identify the particle size distribution of the biomass based on the diameter correction value, and to obtain a biomass particle evaluation result.

2. The method according to claim 1, characterized in that, Also includes: In response to the condition that the range is a first range, the particle size distribution of the biomass is identified using the volume equivalent diameter as a standard sample; In response to the condition that the range is a first range, the particle size distribution of the biomass is identified using the surface area equivalent diameter as a standard sample.

3. The method according to claim 1, characterized in that, The step of obtaining the geometric feature parameters of the biomass based on the biomass image includes: Acquire initial material images of the biomass; The initial material image is preprocessed to obtain a material image that meets preset image conditions; The material image is input into a pre-built recognition model to output the geometric feature parameters.

4. The method according to claim 1, characterized in that, in, The formula for calculating the aspect ratio is: ， in, L i This indicates the aspect ratio of the particle. a imax Indicates the maximum major axis. b imax Indicates the maximum minor axis; The formula for calculating the sphericity is: ， in, C i Indicates the sphericity of the particles. A S This represents the surface area of ​​a sphere with the same volume as a biomass pellet. S i This indicates the surface area of ​​the particle.

5. The method according to claim 4, characterized in that, The formula for calculating the diameter correction value is: ， in, d i This indicates the method for calculating the corresponding equivalent diameter.

6. A biomass particle size identification device, characterized in that, include: The first determining module is used to obtain the geometric feature parameters of the biomass based on the biomass image, so as to determine the sphericity and aspect ratio of the biomass; The second determining module is used to determine the category of biomass based on the sphericity and aspect ratio, obtain the corresponding burnout time based on the category, and determine the range of the burnout time. The first identification module is configured to, in response to the condition that the range is a first range, determine the diameter correction value of the biomass based on the aspect ratio and the sphericity, so as to identify the particle size distribution of the biomass based on the diameter correction value, and obtain the biomass particle evaluation result.

7. The apparatus according to claim 6, characterized in that, Also includes: The second identification module is used to identify the particle size distribution of the biomass by using the volume equivalent diameter as a standard sample when the range is the first range. The third identification module is used to identify the particle size distribution of the biomass by using the surface area equivalent diameter as a standard sample when the range is the first range.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the biomass particle size identification method as described in any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the biomass particle size identification method as described in any one of claims 1-5.

10. A computer program product, comprising a computer program, characterized in that, The computer program is executed to implement the biomass particle size identification method as described in any one of claims 1-5.

Images