A device and method for measuring boiler coal powder particles based on X-ray imaging

Abstract

The present invention discloses a boiler coal powder particle measurement device and method based on X-ray imaging, and relates to the technical field of boiler coal powder measurement. The device includes: an X-ray imaging acquisition module, which is used to acquire the X-ray array image of the boiler; an image processing module, which is used to process the X-ray array image, and the processing includes denoising, enhancement and feature extraction; a three-dimensional modeling module, which is used to analyze the processed X-ray array image in sequence according to the array sorting through a ray projection algorithm, and reconstruct it into a three-dimensional graphic, and separately model the coal powder particles whose edge contour information exceeds the threshold. The present invention acquires the coal powder data inside the boiler through X-ray imaging, then three-dimensionalizes it, and then displays it through a VR interactive module to interact with the user, providing a very realistic visual presentation effect, and visualizes and interacts with the measurement results of the coal powder particles.

Description

Technical Field

[0001] The invention relates to the technical field of boiler coal powder measurement, and in particular to a boiler coal powder particle measurement device and method based on X-ray imaging. Background Art

[0002] During boiler operation, the characteristics of pulverized coal particles (such as particle size distribution, concentration, combustion state, etc.) have a critical impact on combustion efficiency, energy consumption and pollutant emissions. Traditional boiler pulverized coal particle measurement methods have significant deficiencies in data visualization and interactive experience, making it difficult for operators to deeply, comprehensively and accurately grasp the actual state of pulverized coal inside the boiler, which to a certain extent limits the optimization and efficient management of boiler operation. With the rapid development of X-ray imaging technology and VR technology, the organic combination of the two and their application in the field of boiler pulverized coal particle measurement has shown great potential and broad prospects. However, there is currently no mature and complete technical solution that can fully meet this demand. Summary of the invention

[0003] The object of the present invention is to provide a device and method for measuring the particle size of boiler coal powder based on X-ray imaging to solve the problems raised in the above background technology.

[0004] To achieve the above object, the present invention provides the following technical solution: a boiler coal powder particle measurement device based on X-ray imaging, comprising:

[0005] An X-ray imaging acquisition module, which is used to acquire an X-ray array image of a boiler pulverized coal bin discharge port and / or a boiler furnace;

[0006] An image processing module, which is used to process the X-ray array image, wherein the processing includes denoising, enhancement, feature extraction and feature analysis;

[0007] The feature extraction includes measuring and identifying the coal powder particles in the X-ray array image and extracting the edge contour information thereof;

[0008] The feature analysis is used to analyze the edge profile information of the coal powder, obtain the particle size data of the coal powder, and generate a distribution curve report based on the particle size data of the coal powder;

[0009] A three-dimensional modeling module is used to analyze the processed X-ray array images in sequence according to the array order through a ray casting algorithm, reconstruct them into three-dimensional graphics, and separately model the coal powder particles whose edge contour information exceeds a threshold;

[0010] A VR interactive module is used to import three-dimensional graphics into a VR device, render the three-dimensional graphics in the VR device through a rendering engine, and perform enhanced rendering of the separately modeled coal powder particles;

[0011] Wherein, the VR interaction module also includes:

[0012] A data analysis and display unit, which is used to display the coal powder particle size data and the distribution curve report;

[0013] The interactive data collection unit is used to collect data when the user interacts with the three-dimensional graphics when using the VR device, as well as other data performed by the user.

[0014] Preferably, the X-ray imaging acquisition module includes a plurality of X-ray sources and a detector array adapted thereto;

[0015] The X-ray source adjusts the energy range, intensity level and emission angle of the X-rays according to the operating conditions of the boiler and specific measurement requirements;

[0016] The detector array is used to capture the attenuation signal after the X-ray penetrates the discharge port of the boiler coal powder bin and / or the coal powder particle flow in the boiler furnace, and convert it into digital image data.

[0017] Preferably, the image processing module includes:

[0018] A denoising processing unit, which is used to perform denoising processing on the X-ray array image through a filtering algorithm;

[0019] An enhancement processing unit, which is used to enhance the contrast of the X-ray array image after denoising by using a histogram equalization algorithm based on local contrast enhancement;

[0020] The feature extraction unit is used to identify the coal powder particles in the X-ray array image through an edge detection algorithm and extract the edge contour information of the coal powder particles.

[0021] Preferably, the contrast enhancement of the denoised X-ray array image by using a histogram equalization algorithm based on local contrast enhancement includes:

[0022] The grayscale distribution of the local area of ​​the X-ray array image is analyzed, and based on the analysis results, the overall grayscale range of the X-ray array image is stretched and adjusted to enhance the contrast between the coal powder particles and the background and between the coal powder particles in different combustion states and different particle sizes.

[0023] Preferably, the feature extraction unit further includes:

[0024] Set edge contour threshold;

[0025] Detecting the edge contour information of the extracted coal powder particles and analyzing whether the edge contour of the coal powder particles exceeds a threshold;

[0026] If it exceeds, the edge contour information of the coal powder particle is marked;

[0027] If it does not exceed the limit, continue to detect the edge contour information of other coal powder particles.

[0028] Preferably, the 3D modeling module is also used to extract edge contour information of coal powder particles after the 3D graphics are reconstructed, and to separately model the coal powder particles exceeding the threshold through their edge contour information, and restore them to their original positions in the 3D graphics.

[0029] Preferably, the three-dimensional modeling module further includes:

[0030] A model evaluation and adjustment unit is used to compare and analyze with a pre-established coal powder particle model library and big data to evaluate whether there is a bias / error in the three-dimensional graph;

[0031] If there is a deviation / error, the parameters of the reconstruction algorithm are adjusted to reconstruct the three-dimensional graphics;

[0032] If there is no deviation / error, the three-dimensional graphics will be output directly.

[0033] Preferably, the rendering effects of the VR interactive module include lighting effects, shadow effects, and material textures.

[0034] The present invention also provides a method for measuring boiler coal powder particles based on X-ray imaging, comprising:

[0035] Acquire an X-ray array image of the boiler;

[0036] Processing the X-ray array image, wherein the processing includes denoising, enhancement and feature extraction;

[0037] The feature extraction includes measuring and identifying the coal powder particles in the X-ray array image and extracting the edge contour information thereof;

[0038] Through the ray casting algorithm, the processed X-ray array images are analyzed in sequence according to the array order and reconstructed into a three-dimensional graph, and the coal powder particles whose edge contour information exceeds the threshold are individually modeled;

[0039] The three-dimensional graphics are imported into the VR device, the three-dimensional graphics in the VR device are rendered through the rendering engine, and the individually modeled coal powder particles are enhanced for rendering.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The present invention obtains image data of boiler coal powder particles through an X-ray imaging acquisition module, and then processes the X-ray image data to ensure high accuracy and high reliability of the measurement data. Then, a highly restored three-dimensional model can be accurately constructed based on the two-dimensional image through the three-dimensional modeling module, and some larger coal powder particles are modeled separately. The three-dimensional model is then imported into the VR interactive module for users to interact. This not only provides a very realistic visual presentation effect, visualizes and makes interactive the measurement results of the coal powder particles, and displays the coal powder particle size data and distribution curve report, but also can collect user interaction data in real time and comprehensively, and obtain user feedback data on the distribution of coal powder particles, which is conducive to the subsequent strengthening of boiler operation management and improving the coal powder combustion efficiency of the boiler. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of the structure of a boiler coal powder particle measurement device based on X-ray imaging provided by an embodiment of the present invention;

[0043] Figure 2 A flow chart of the steps of a method for measuring boiler coal powder particles based on X-ray imaging is provided in an embodiment of the present invention.

[0044] Figure numerals: 11, X-ray imaging acquisition module; 12, image processing module; 13, three-dimensional modeling module; 14, VR interaction module. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] See also Figure 1The present invention provides a boiler coal powder particle measurement device based on X-ray imaging, including an X-ray imaging acquisition module 11, an image processing module 12, a three-dimensional modeling module 13 and a VR interactive module 14. During the device installation stage, the X-ray source and detector array of the X-ray imaging acquisition module 11 are accurately installed at a predetermined measurement position in the boiler furnace. The predetermined measurement position needs to ensure that it can fully and accurately cover the area to be monitored and is not disturbed by factors such as vibration and high-temperature airflow during the operation of the boiler. Then, the high-speed data transmission line between the image processing module 12, the three-dimensional modeling module 13 and the VR interactive module 14 is connected to ensure that the data can be transmitted stably and quickly. The transmission line can be made of optical fiber material to reduce signal attenuation and interference. Then, the VR device is installed and debugged to ensure that it is connected to the VR interactive module normally, and the VR device is calibrated and initialized, including setting the correct resolution, field of view, positioning accuracy and other parameters.

[0047] Specifically, the X-ray imaging acquisition module 11 is used to acquire an X-ray array image of a boiler pulverized coal bin discharge port and / or a boiler furnace;

[0048] An image processing module 12, which is used to process the X-ray array image, including denoising, enhancement, feature extraction and feature analysis;

[0049] Among them, feature extraction includes measuring and identifying coal powder particles in the X-ray array image and extracting their edge contour information;

[0050] The feature analysis is used to analyze the edge profile information of the coal powder, obtain the coal powder particle size data, and generate a distribution curve report based on the coal powder particle size data for subsequent guidance to improve the boiler combustion efficiency;

[0051] A three-dimensional modeling module 13 is used to analyze the processed X-ray array images in sequence according to the array order through a ray casting algorithm and reconstruct them into a three-dimensional graphic;

[0052] A VR interactive module 14 is used to import the three-dimensional graphics into the VR device, render the three-dimensional graphics in the VR device through a rendering engine, and enhance the rendering of the separately modeled coal powder particles to make them more prominent;

[0053] The VR interaction module 14 further includes:

[0054] A data analysis and display unit, which is used to display the coal powder particle size data and the distribution curve report;

[0055] The interactive data collection unit is used to collect data when the user interacts with the three-dimensional graphics when using the VR device, as well as other data performed by the user.

[0056] In one embodiment, the X-ray imaging acquisition module 11 includes a plurality of X-ray sources and a detector array adapted thereto;

[0057] The X-ray source can precisely adjust the X-ray energy range (e.g. flexible setting between 30-150keV), intensity level and emission angle according to the boiler's operating conditions such as load, air volume, combustion temperature, etc., as well as specific measurement requirements;

[0058] The detector array is used to capture the attenuation signal of X-rays penetrating the discharge port of the boiler pulverized coal bin and / or the pulverized coal particle flow in the boiler furnace through the detector elements, and convert it into digital image data, with fast response characteristics and low noise performance.

[0059] Specifically, during the operation of the boiler, the working parameters of the X-ray acquisition module 11 are finely adjusted according to the specific type of the boiler (such as power station boiler, industrial boiler, etc.), real-time operating parameters (such as current load level, air intake, coal powder supply rate, etc.) and pre-set measurement requirements. For example, for a large power station boiler in the high-load stable operation stage, the energy of the X-ray source is set to 120keV, the intensity is adjusted to 10mA, and the emission angle is optimized according to the furnace structure and the key measurement area; the detector array collects the attenuation image data of the X-ray penetrating the boiler coal powder bin discharge port and / or the coal powder particles in the boiler furnace at a high rate of 20 frames per second, and transmits it to the image processing module in real time through a high-speed data transmission line. During the acquisition process, the working status of the X-ray source and the detector array is continuously monitored to ensure the stability and continuity of data acquisition.

[0060] In an optional embodiment, the image processing module 12 includes:

[0061] A denoising processing unit, which is used to perform denoising processing on the X-ray array image through a filtering algorithm;

[0062] An enhancement processing unit, which is used to enhance the contrast of the X-ray array image after denoising by using a histogram equalization algorithm based on local contrast enhancement;

[0063] The feature extraction unit is used to identify the coal powder particles in the X-ray array image through an edge detection algorithm and extract the edge contour information of the coal powder particles.

[0064] Specifically, the denoising processing unit performs deep denoising processing on the original image data transmitted from the X-ray camera acquisition module through an adaptive noise filtering algorithm. The algorithm can dynamically adjust the filtering parameters according to the noise characteristics of different areas of the image. For example, the filter window size and weight coefficient are automatically increased in areas with more serious noise, and a smaller filter window is used in areas with rich image details and less noise. In this way, while effectively removing various types of interference caused by X-ray scattering, electronic noise, etc., key detail information such as the edge and texture of the image is retained to the greatest extent.

[0065] Optionally, the adaptive noise filtering algorithm used by the denoising processing unit can be one or more of an adaptive median filtering algorithm, an adaptive Wiener filtering algorithm and a wavelet threshold denoising algorithm. The median filtering algorithm is a nonlinear signal processing method based on the theory of sorting statistics. It replaces the grayscale value of a point in the image with the median of the grayscale values ​​of each pixel in the neighborhood of the point. On this basis, the adaptive median filtering algorithm dynamically changes the size of the filtering window according to the statistical characteristics of the local area of ​​the image. The Wiener filter is a linear filtering method based on the minimum mean square error criterion. It estimates the statistical characteristics of the image and noise and seeks an optimal filter so that the mean square error between the filtered image and the original noise-free image is minimized. The adaptive Wiener filtering algorithm dynamically adjusts the parameters of the filter according to statistical information such as the variance of the local area of ​​the image. Wavelet transform is a time-frequency analysis method that can decompose image signals into wavelet coefficients of different scales and directions. The wavelet threshold denoising algorithm considers that the wavelet coefficients of an image are mainly composed of a signal coefficient and a noise coefficient. The noise coefficient usually has a smaller amplitude and is more evenly distributed on different scales, while the signal coefficient has a larger amplitude and has a stronger correlation in certain scales and directions. Therefore, a threshold can be set, and the wavelet coefficients less than the threshold are regarded as noise coefficients and set to zero, and then the image is reconstructed by inverse wavelet transform, so as to achieve the purpose of denoising. The adaptive wavelet threshold denoising algorithm dynamically adjusts the size of the threshold according to the statistical characteristics of the image wavelet coefficients. Which algorithm or combination of algorithms to use is selected according to the actual situation and is not specifically limited in this embodiment.

[0066] The enhancement processing unit can use a histogram equalization algorithm based on local contrast enhancement to perform contrast enhancement operations on the denoised image. The algorithm analyzes and adjusts the grayscale distribution of the local area of ​​the image, and reasonably stretches the overall grayscale range of the image, so that the contrast between the coal powder particles and the background and between the coal powder particles in different combustion states and different particle sizes is significantly enhanced, laying a solid foundation for subsequent feature extraction and precise analysis.

[0067] Next, the feature extraction unit can accurately extract the edge contour information of the coal powder particles through an edge detection algorithm based on a multi-scale morphological gradient. The algorithm can accurately identify the boundaries of the coal powder particles in a complex image background and provide high-quality two-dimensional image basic data for the three-dimensional modeling module 13.

[0068] Specifically, when the feature extraction unit performs the feature extraction operation, the following steps are included:

[0069] Step S1231, setting edge contour threshold;

[0070] Step S1232, detecting the edge contour information of the extracted coal powder particles, analyzing whether the edge contour of the coal powder particles exceeds the threshold value, if it exceeds the threshold value, continuing to execute step S1233, otherwise jumping to step S1234;

[0071] Step S1233, marking the edge contour information of the coal powder particles;

[0072] Step S1234, continue to detect the edge contour information of other coal powder particles.

[0073] In an optional embodiment, the three-dimensional modeling module 13 is also used to extract edge contour information of coal powder particles after the three-dimensional graphics are reconstructed, and to separately model the coal powder particles that exceed the threshold through their edge contour information, and restore them to their original positions in the three-dimensional graphics.

[0074] Specifically, the 3D modeling module 13 uses a ray casting algorithm based on volume rendering, combined with multi-dimensional information such as edge contours, gray value distribution, and spatial position relationship of coal powder particles in the processed X-ray 2D image sequence, to construct 3D model data.

[0075] Understandably, during the 3D graphics reconstruction process, it is necessary to consider the physical properties of coal powder particles (such as density, shape, fluidity, etc.), the changing rules during the combustion process (such as particle shrinkage, expansion, surface morphology changes, etc.), and the complex flow field environment inside the boiler, and optimize the model in many aspects. For example, a surface smoothing algorithm based on a physical model is used to finely smooth the particle surface to make it more in line with the actual situation; multi-resolution modeling technology is used to dynamically adjust the model's detail level according to the user's viewing angle, improving rendering efficiency while ensuring visual effects.

[0076] When reconstructing three-dimensional graphics, it is detected whether the reconstructed two-dimensional data includes coal powder particle data that exceeds the threshold. If so, the coal powder particles exceeding the threshold are modeled separately so that they can be used to interact with users in subsequent VR devices. For others that do not exceed the threshold, they can be integrated into an integrated model and used as the internal background model of the current boiler.

[0077] In an optional embodiment, the three-dimensional modeling module 13 includes:

[0078] The model evaluation and adjustment unit is used to provide model verification and adaptive adjustment functions. It comprehensively evaluates the accuracy and reliability of the three-dimensional model by comparing and analyzing the pre-established high-precision coal powder particle standard model library and a large amount of actual physical experimental data. If deviations or errors are detected in the model, the system can automatically adjust the key parameters of the reconstruction algorithm (such as ray projection step size, sampling density, color mapping function, etc.) or promptly prompt the user to make manual corrections to ensure that the final generated three-dimensional model can truly and accurately reflect the actual state and change process of the coal powder particles in the boiler.

[0079] Specifically, the workflow of the model evaluation and adjustment unit includes the following steps:

[0080] Step S1311, compare and analyze with the pre-established coal powder particle model library and big data to evaluate whether there is a deviation / error in the three-dimensional graph. If there is a deviation / error, execute step S1312; otherwise, jump to execute step S1313;

[0081] Step S1312, adjusting the parameters of the reconstruction algorithm to reconstruct the three-dimensional graphics;

[0082] Step S1313, directly output three-dimensional graphics.

[0083] In an optional embodiment, the VR interactive module 14 is composed of a VR device interface unit, a high-performance image rendering engine, an interactive data acquisition unit, and a data analysis and display unit. The VR device interface unit is used to establish a high-speed and stable connection with various mainstream VR head-mounted displays, handles, space locators and other devices to achieve real-time and lossless transmission of data;

[0084] The image rendering engine is used to render the three-dimensional graphic data generated by the three-dimensional modeling module 13 in real time, and according to the characteristics of the VR device (such as resolution, field of view, display refresh rate, etc.) and the personalized viewing angle requirements of the user, add realistic lighting effects (including simulation and setting of various light source types such as ambient light, point light source, spotlight, etc.), delicate shadow effects (using shadow mapping technology or ray tracing shadow algorithm to generate high-precision shadows), and highly realistic material textures (such as setting corresponding texture mapping according to different combustion stages, hardness, roughness, etc. of coal powder particles), and carefully create a highly immersive visual effect of the internal environment of the boiler;

[0085] The interactive data acquisition unit is used to collect various operation data of users in the VR environment in real time, including the translation, rotation, button triggering and other action information of the handle, the user's head and body position and posture change data fed back by the spatial locator, and the user's voice command information, etc. At the same time, based on the advanced interactive logic algorithm, the three-dimensional image is dynamically displayed and interactively feedback is performed in real time according to the user's interactive operation. For example, when the user scales the three-dimensional coal powder particle model through the handle operation, the system can dynamically adjust the display size of the model according to the scaling ratio and update the model's detail level accordingly; when the user focuses on the coal powder particles in a specific area, the system automatically displays the detailed information of the coal powder particles in the area (such as particle size distribution histogram, concentration value, combustion state evaluation results, etc.); when the user issues a voice command to query a parameter or perform an operation, the system quickly performs voice recognition and command analysis, and makes corresponding responses and feedback. Through the above functions, users are provided with a highly immersive and interactive experience, allowing users to deeply explore the state and characteristics of the coal powder particles inside the boiler as if they were personally there;

[0086] A data analysis and display unit is used to display the coal powder particle size data and the distribution curve report.

[0087] Specifically, the distribution curve report can be produced by Python, and the example steps are as follows:

[0088] Step S1421, in the data analysis part of the system, the particle characteristic data such as particle size data is stored in a suitable data structure, including a list in Python or a NumPy array. For example, all measured coal powder particle sizes are stored in a list called particle_sizes.

[0089] Step S1422, use the loop and conditional judgment statements of the programming language to implement data grouping statistics. For example, set the particle size interval to [0-10μm, 10-20μm, 20-30μm, ...], and count the number of particles in each interval by looping through the particle_sizes list. A dictionary can be used to store the number of particles in each interval, where the key is the particle size interval and the value is the number of particles in the interval.

[0090] Step S1423, using a data visualization library to draw a curve;

[0091] First, the midpoint of the particle size interval is used as the horizontal axis (for example, for the 10-20 μm interval, the horizontal axis is 15 μm), and the proportion of particles corresponding to each interval (number of particles / total number of particles) is used as the vertical axis;

[0092] Use Matplotlib's plot function to draw a line graph or use the hist function to draw a histogram, such as plt.plot(x_axis,y_axis), where x_axis is a list of midpoints of the particle size range and y_axis is a list of particle number percentages;

[0093] Finally, the drawn curve graph is displayed through plt.show().

[0094] It can be understood that by importing three-dimensional graphics through the VR interactive module 14, an intuitive, immersive and interactive display of the state of coal powder particles in the boiler is achieved. Users can comprehensively, deeply and accurately observe key information such as the three-dimensional distribution and particle size changes of coal powder particles in the VR environment, which is conducive to the user's in-depth understanding and judgment of the internal state of the boiler, and provides technical support for the subsequent operation and management of the boiler.

[0095] In this embodiment, the present invention obtains image data of boiler pulverized coal particles through an X-ray imaging acquisition module 11, and then processes the X-ray image data to ensure high accuracy and high reliability of the measurement data. Then, the three-dimensional modeling module 13 can accurately construct a highly restored three-dimensional model based on the two-dimensional image, and separately model some larger pulverized coal particles. The three-dimensional model is then imported into the VR interactive module 14 for users to interact. This not only provides a very realistic visual presentation effect, visualizes and makes interactive the measurement results of the pulverized coal particles, and displays the pulverized coal particle size data and distribution curve report, but also can collect user interaction data in real time and comprehensively, and obtain user feedback data on the distribution of pulverized coal particles, which is conducive to the subsequent strengthening of boiler operation management and improving the pulverized coal combustion efficiency of the boiler.

[0096] Based on the above embodiments, Figure 2 As shown, the present invention also provides a boiler coal powder particle measurement method based on X-ray imaging, which is applied to the boiler coal powder particle measurement device based on X-ray imaging of the above embodiment. The method includes:

[0097] S210, acquiring an X-ray array image of a discharge port of a boiler pulverized coal bin and / or a boiler furnace.

[0098] Specifically, S210 includes:

[0099] Provide a plurality of X-ray sources and detector arrays adapted thereto;

[0100] The X-ray source adjusts the energy range, intensity level and emission angle of the X-rays according to the operating conditions of the boiler and specific measurement requirements;

[0101] The detector array is used to capture the attenuation signal after the X-ray penetrates the discharge port of the boiler coal powder bin and / or the coal powder particle flow in the boiler furnace, and convert it into digital image data.

[0102] S220, processing the X-ray array image, including denoising, enhancement, feature extraction and feature analysis.

[0103] Among them, feature extraction includes measuring and identifying coal powder particles in the X-ray array image and extracting their edge contour information;

[0104] The feature analysis is used to analyze the edge profile information of the coal powder, obtain the particle size data of the coal powder particles, and generate a distribution curve report based on the particle size data of the coal powder particles.

[0105] Specifically, S220 includes:

[0106] Step S221, performing denoising processing on the X-ray array image by using a filtering algorithm;

[0107] Step S222, performing contrast enhancement on the denoised X-ray array image using a histogram equalization algorithm based on local contrast enhancement;

[0108] Step S223, identifying the coal powder particles in the X-ray array image by using an edge detection algorithm, and extracting edge contour information of the coal powder particles;

[0109] Step S224: Analyze the edge profile information of the coal powder to obtain the particle size data of the coal powder, and generate a distribution curve report based on the particle size data of the coal powder.

[0110] Wherein, step S222 also includes:

[0111] The grayscale distribution of the local area of ​​the X-ray array image is analyzed, and based on the analysis results, the overall grayscale range of the X-ray array image is stretched and adjusted to enhance the contrast between the coal powder particles and the background and between the coal powder particles in different combustion states and different particle sizes.

[0112] Specifically, step S224 includes:

[0113] Step S2241, setting edge contour threshold;

[0114] Step S2242, detecting the edge contour information of the extracted coal powder particles, analyzing whether the edge contour of the coal powder particles exceeds the threshold, if it exceeds the threshold, continue to step S2243, otherwise jump to step S2244;

[0115] Step S2243, marking the edge contour information of the coal powder particles;

[0116] Step S2244, continue to detect the edge contour information of other coal powder particles.

[0117] S230, through the ray casting algorithm, the processed X-ray array image is analyzed in sequence according to the array sorting, and reconstructed into a three-dimensional graphic, and the coal powder particles whose edge contour information exceeds the threshold are individually modeled.

[0118] Among them, S230 also includes:

[0119] Step S231, compare and analyze with the pre-established coal powder particle model library and big data to evaluate whether the three-dimensional graph has bias / error. If yes, execute step S232, otherwise jump to step S233;

[0120] Step S232, adjusting the parameters of the reconstruction algorithm to reconstruct the three-dimensional graphics;

[0121] Step S233, directly output the three-dimensional image.

[0122] The S230 also includes:

[0123] After the three-dimensional graphics are reconstructed, the edge contour information of the coal powder particles is extracted, and the coal powder particles exceeding the threshold are individually modeled based on their edge contour information and restored to their original positions in the three-dimensional graphics.

[0124] S240, importing the three-dimensional graphics into the VR device, rendering the three-dimensional graphics in the VR device through a rendering engine, and performing enhanced rendering on the separately modeled coal powder particles.

[0125] In this embodiment, the present invention obtains image data of boiler coal powder particles through X-ray imaging, and then processes the X-ray image data to ensure high accuracy and high reliability of the measurement data, and then accurately constructs a highly restored three-dimensional model based on the two-dimensional image, and separately models some larger coal powder particles, and then imports the three-dimensional model into the VR device for users to interact, which not only provides a very realistic visual presentation effect, visualizes and makes the measurement results of the coal powder particles interactive, and displays the coal powder particle size data and distribution curve report, but also can collect user interaction data in real time and comprehensively, and can obtain user feedback data on the distribution of coal powder particles, which is conducive to the subsequent strengthening of boiler operation management and improving the coal powder combustion efficiency of the boiler.

[0126] It should be noted that the above examples are only specific embodiments of the present invention, and the present invention is obviously not limited to the above examples, and there are many similar variations. All variations directly derived or associated from the contents disclosed by the technicians in this field should fall within the protection scope of the present invention.

[0127] The above are only preferred embodiments of the present invention and are not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A boiler coal powder particle measurement device based on X-ray imaging, characterized in that: include: An X-ray imaging acquisition module, which is used to acquire an X-ray array image of a boiler pulverized coal bin discharge port and / or a boiler furnace; An image processing module, which is used to process the X-ray array image, wherein the processing includes denoising, enhancement, feature extraction and feature analysis; The feature extraction includes measuring and identifying the coal powder particles in the X-ray array image and extracting the edge contour information thereof; The feature analysis is used to analyze the edge profile information of the coal powder, obtain the particle size data of the coal powder, and generate a distribution curve report based on the particle size data of the coal powder; A three-dimensional modeling module is used to analyze the processed X-ray array images in sequence according to the array order through a ray casting algorithm, reconstruct them into three-dimensional graphics, and separately model the coal powder particles whose edge contour information exceeds a threshold; A VR interactive module is used to import three-dimensional graphics into a VR device, render the three-dimensional graphics in the VR device through a rendering engine, and perform enhanced rendering of the separately modeled coal powder particles; Wherein, the VR interaction module also includes: A data analysis and display unit, which is used to display the coal powder particle size data and the distribution curve report; An interactive data collection unit, which is used to collect data when a user uses a VR device to interact with a three-dimensional graphic, as well as other data performed by the user; The three-dimensional modeling module includes: A model evaluation and adjustment unit is used to compare and analyze with a pre-established coal powder particle model library and big data to evaluate whether there is a bias / error in the three-dimensional graph; If there is a deviation / error, the parameters of the reconstruction algorithm are adjusted to reconstruct the three-dimensional graphics; If there is no deviation / error, the three-dimensional graphics will be output directly.

2. The boiler coal powder particle measurement device based on X-ray imaging according to claim 1 is characterized in that: The X-ray imaging acquisition module includes a plurality of X-ray sources and a detector array adapted thereto; The X-ray source adjusts the energy range, intensity level and emission angle of the X-rays according to the operating conditions of the boiler and specific measurement requirements; The detector array is used to capture the attenuation signal after the X-ray penetrates the discharge port of the boiler coal powder bin and / or the coal powder particle flow in the boiler furnace, and convert it into digital image data.

3. The boiler coal powder particle measurement device based on X-ray imaging according to claim 1 is characterized in that: The image processing module comprises: A denoising processing unit, which is used to perform denoising processing on the X-ray array image through a filtering algorithm; An enhancement processing unit, which is used to enhance the contrast of the X-ray array image after denoising by using a histogram equalization algorithm based on local contrast enhancement; The feature extraction unit is used to identify the coal powder particles in the X-ray array image through an edge detection algorithm and extract the edge contour information of the coal powder particles.

4. The boiler coal powder particle measurement device based on X-ray imaging according to claim 3 is characterized in that: The contrast of the X-ray array image after denoising is enhanced by using a histogram equalization algorithm based on local contrast enhancement, including: The grayscale distribution of the local area of ​​the X-ray array image is analyzed, and based on the analysis results, the overall grayscale range of the X-ray array image is stretched and adjusted to enhance the contrast between the coal powder particles and the background and between the coal powder particles in different combustion states and different particle sizes.

5. The boiler coal powder particle measurement device based on X-ray imaging according to claim 3 is characterized in that: The feature extraction unit also includes: Set edge contour threshold; Detecting the edge contour information of the extracted coal powder particles and analyzing whether the edge contour of the coal powder particles exceeds a threshold; If it exceeds, the edge contour information of the coal powder particle is marked; If it does not exceed the limit, continue to detect the edge contour information of other coal powder particles.

6. The boiler coal powder particle measurement device based on X-ray imaging according to claim 1, characterized in that: The separately modeling of the pulverized coal particles whose edge profile information exceeds a threshold value includes: After the three-dimensional graphics are reconstructed, the edge contour information of the coal powder particles is extracted, and the coal powder particles exceeding the threshold are individually modeled based on their edge contour information and restored to their original positions in the three-dimensional graphics.

7. The boiler coal powder particle measurement device based on X-ray imaging according to claim 1 is characterized in that: The rendering effects of the VR interactive module include lighting effects, shadow effects, and material textures.

8. A method for measuring boiler coal powder particles based on X-ray imaging, characterized in that: The following steps are involved: Acquire an X-ray array image of the boiler; Processing the X-ray array image, wherein the processing includes denoising, enhancement and feature extraction; The feature extraction includes measuring and identifying the coal powder particles in the X-ray array image and extracting the edge contour information thereof; Through the ray casting algorithm, the processed X-ray array images are analyzed in sequence according to the array order and reconstructed into a three-dimensional graph, and the coal powder particles whose edge contour information exceeds the threshold are individually modeled; Compare and analyze with the pre-established coal powder particle model library and big data to evaluate whether there is any deviation / error in the 3D graphics. If there is any deviation / error, adjust the parameters of the reconstruction algorithm and reconstruct the 3D graphics. If there is no deviation / error, directly output the 3D graphics; The three-dimensional graphics are imported into the VR device, the three-dimensional graphics in the VR device are rendered through the rendering engine, and the individually modeled coal powder particles are enhanced for rendering.

Images