Quality detection system for gravel crushing granularity size

Abstract

The invention discloses a gravel crushing granularity size quality detection system, and relates to the technical field of gravel detection, the system can efficiently and accurately obtain multi-angle image data of gravel particles through a multi-angle image acquisition module and a three-dimensional reconstruction module, and the detection accuracy is improved. And a high-precision three-dimensional particle model is generated through an image splicing and three-dimensional reconstruction technology. By analyzing the triangular mesh vertex vector of the three-dimensional model, the equivalent particle size and the uniformity index of the particles are calculated, and automatic evaluation of the gravel particle quality is achieved. According to the method, the quality and the uniformity of the gravel particles can be accurately evaluated, accurate data support is provided for quality control in the production process, a crushing process adjustment early warning is generated in time according to the size and the uniformity of the gravel particles, and accurate quality detection data is provided for a production line. According to the technology, the detection precision is remarkably improved, a traditional manual screening mode is replaced, personal errors are reduced, and the production efficiency and the automation degree are improved.

Description

Technical Field

[0001] The invention relates to the technical field of sand and gravel detection, in particular to a quality detection system for the size of crushed sand and gravel particles. Background Art

[0002] Crushed stone refers to small pieces of broken rock, also known as sand and gravel, which are irregular in size, shape, and texture. They are usually obtained by crushing large pieces of rock. Rocks are composed of one or several minerals and natural glass, and are solid aggregates with stable shapes. Among them, rocks composed of one mineral are called monomineral rocks, such as marble composed of calcite, quartzite composed of quartz, etc. At present, sand and gravel crushing technology is widely used in industries such as construction, mining, metallurgy and road construction, especially in the deep processing of sand and gravel resources. It plays a vital role. With the improvement of the quality requirements for sand and gravel particles, how to accurately and quickly detect the particle size, uniformity and crushing effect of crushed stone has become a major challenge in the sand and gravel production process. At the same time, in traditional quality inspection methods, particle size usually relies on manual screening or two-dimensional image analysis based on a single angle, which is not only time-consuming but also has low accuracy. Therefore, how to use advanced image processing technology to conduct a comprehensive and detailed evaluation of the particle size of sand and gravel particles has become the focus of current technical research.

[0003] Although existing particle size detection systems currently use visual sensors or simple image recognition methods to screen and analyze sand and gravel particles, these methods often show low accuracy and stability when the particle morphology is complex and the particle size varies greatly. Traditional two-dimensional images can only capture the projection information of particles from one angle, and it is difficult to fully reflect the true three-dimensional morphology of the particles, especially when the particles overlap, are obscured, or there are complex textures on the surface of the object, the detection effect is greatly reduced. In addition, these technologies usually ignore the morphological factors of the particles and cannot perform accurate volume measurement and reconstruction of three-dimensional models, resulting in large errors and uncertainties in the assessment of particle size.

[0004] Therefore, there is an urgent need for a technical solution that can accurately analyze sand and gravel particles from multiple angles and dimensions to improve detection accuracy and adapt to the needs of different production scenarios. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a quality detection system for the particle size of crushed sand and gravel to solve the problems mentioned in the background technology.

[0007] To achieve the above objectives, the present invention provides a quality detection system for the size of sand and gravel crushing particles, comprising: Multi-angle acquisition module, image preprocessing module, image stitching and 3D reconstruction module, particle quality detection module and screen status assessment module; The multi-angle acquisition module is installed above a conveyor belt, and the conveyor belt is used to transport sand and gravel to be tested. The multi-angle acquisition module continuously shoots the sand and gravel particles on the conveyor belt according to the conveying speed of the conveyor belt and the camera frame rate to obtain a multi-angle sand and gravel particle image data set, and transmits the multi-angle sand and gravel particle image data set to the image preprocessing module; The image preprocessing module is used to preprocess the multi-angle sand and gravel particle image data set, and the preprocessing includes blur detection and elimination, depth analysis and denoising, and outputs a standard sand and gravel particle image set; The image stitching and three-dimensional reconstruction module is used to extract feature point descriptors of all images in the standard sand and gravel particle image set, and then match the feature point descriptors to obtain feature point matching values, and then judge the matching situation based on the feature point matching value output result; based on the feature point descriptors, register the multi-angle sand and gravel particle images to generate a sparse point cloud model, and expand the sparse point cloud model into a triangular mesh structure to restore the three-dimensional particle model of the sand and gravel particles; The particle quality detection module is used to obtain the triangular mesh vertex vectors of the triangular mesh structure, calculate the equivalent particle size of the sand and gravel particles according to the triangular mesh vertex vectors, calculate the uniformity index of the sand and gravel particles based on the equivalent particle size, and perform a preliminary comparison and evaluation between a preset crushing standard threshold and the uniformity index; The screen status assessment module includes an optical sensor, which is arranged at the entrance and exit of the screen. The screen status assessment module is used to count the screening data of sand and gravel particles, and calculate the pass rate of the screen based on the screening data, and perform a secondary comparative assessment on the set pass threshold and the pass rate to obtain the damage condition of the screen.

[0008] Preferably, the multi-angle acquisition module includes an acquisition setting unit, a data processing unit and an image data transmission unit; The acquisition setting unit includes a conveyor belt speed sensor and a plurality of camera groups, which are respectively installed directly above the conveyor belt and on both sides of the conveyor belt. The conveyor belt speed sensor is used to obtain the transmission speed of the conveyor belt; The data processing unit is used to calculate the camera frame rate of the camera group, and emit an auxiliary wireframe through a laser calibrator to lock the sand and gravel particle area. The camera group continuously shoots at the camera frame rate F through frame synchronization technology to capture multi-angle image data of the same sand and gravel particle on the conveyor belt, and records the number of the sand and gravel particle and the shooting timestamp to obtain a multi-angle sand and gravel particle image data set; The image data transmission unit is used to transmit the multi-angle sand and gravel particle image data set collected by the camera group to the image preprocessing module.

[0009] Preferably, the image preprocessing module includes a blur detection and removal unit, a depth analysis unit and a denoising processing unit; The blur detection and elimination unit is used to receive the collected multi-angle sandstone image data, calculate the clarity index corresponding to each sandstone image in the multi-angle sandstone image data by using the Laplace gradient method, and compare the clarity index with the set blur threshold: When the clarity index is greater than the blur threshold, it is determined to be the first sandstone image and retained, and the first sandstone image is a clear sandstone image; when the clarity index is less than or equal to the blur threshold, it is determined to be the second sandstone image and removed, and the second sandstone image is a blurred sandstone image; The depth analysis unit is used to analyze the first sandstone image by using a bullet screen deep learning algorithm, determine the distance from the pixel of the first sandstone image to the camera, and generate a depth map and a depth value corresponding to the coordinates of each pixel point; The denoising processing unit is used to refine and denoise the boundaries of the first sand and gravel image through a convolutional neural network CNN to optimize image clarity, and after denoising, summarize the remaining sand and gravel images to output a standard sand and gravel particle image set.

[0010] Preferably, the image stitching and three-dimensional reconstruction module includes a feature point extraction unit and a feature point matching unit; The feature point extraction unit is used to perform Gaussian blurring of different scales on all images in the standard sand and gravel particle image set, generate a multi-layer pyramid to detect features of different sizes, then perform differential calculation on the pyramid to calculate image differences between adjacent scales, extract extreme points as preliminary feature points, determine the precise position and main direction of the feature points, assign rotation invariance, calculate the gradient direction histogram within the neighborhood of the feature points, and form a feature point descriptor; The feature point matching unit is used to perform feature point matching on the feature point descriptor in combination with the depth value to obtain a feature point matching value, and to make a judgment based on an output result of the feature point matching value to determine an overlapping area of ​​multi-angle sand and gravel images in a standard sand and gravel particle image set, and to align the two images by matching feature points to generate a two-dimensional sand and gravel image; Wherein, the judgment is made based on the output result of the feature point matching value as follows; When the feature point matching value = 1, the two feature points are matching points; When the feature point matching value = 0, the two feature points are not matching points.

[0011] Preferably, the image stitching and three-dimensional reconstruction module further includes a point cloud registration and stitching unit; The point cloud registration and stitching unit is used to randomly select a subset from all matching points using the RANSAC algorithm, fit the transformation matrix model, and then calculate the matching point error e from all matching points to the transformation matrix model, and compare the matching point error e with the error threshold eth to determine the accuracy of the matching point, and repeat multiple iterations to select the transformation matrix model with the upper limit of the inner point as the matching point, and remove the wrong matching point; the specific judgment is as follows; When the matching point error is less than the error threshold, the point pair is considered to be matched successfully and marked as an inlier; When the matching point error ≥ the error threshold, the point pair is considered to have failed to match and the matching point is removed.

[0012] Preferably, the image stitching and three-dimensional reconstruction module further includes a matching point elimination unit, and the point cloud registration and stitching unit performs point cloud registration and stitching by applying an ICP algorithm to form a sparse point cloud model of complete sand and gravel particles, and then performs a neighbor search on the sparse point cloud model to construct a triangular mesh connection of the points, optimize the triangular mesh to complete the boundary, generate a closed surface, and restore the three-dimensional particle model of the sand and gravel particles; The triangular mesh determines the position coordinates of each vertex in the three-dimensional space through three vertex vectors.

[0013] Preferably, the particle quality detection module includes a particle size analysis unit, a uniformity analysis unit and a crushing effect evaluation unit; the particle size analysis unit extracts the vertex coordinates of each triangular mesh from the three-dimensional particle model and generates three vertex vectors of each triangular mesh; Based on the sum of the vertex vectors of all triangular meshes, the closed three-dimensional volume defined by the triangular meshes is calculated, the closed three-dimensional volume is the volume of the sand and gravel particles, and the equivalent particle size of the sand and gravel particles is calculated and output.

[0014] Preferably, the uniformity analysis unit calculates the equivalent particle size for all three-dimensional particle models, and calculates the average value and variance of all the equivalent particle sizes to determine the uniformity index of the sand and gravel particles and analyze the sand and gravel particle crushing process.

[0015] Preferably, the crushing effect evaluation unit sets the crushing standard threshold based on the sand and gravel crushing standard, performs a preliminary comparative evaluation with the uniformity index, analyzes the uniformity of the sand and gravel particles, and determines the crushing process adjustment. The specific evaluation contents are as follows; When the uniformity index is greater than the crushing standard threshold, it indicates that the sand and gravel particle size distribution is uneven, and an early warning for crushing process adjustment is generated; When the uniformity index is ≤ the crushing standard threshold, it means that the sand and gravel particle size distribution is uniform and no adjustment is required.

[0016] Preferably, the screen state assessment module includes a screening rate analysis unit and a screen state assessment unit; The screening rate analysis unit installs optical sensors at the outlet and inlet of the screen. When it is preliminarily evaluated that the sand and gravel particle size distribution is uniform, the optical sensors are started to count the number of screened particles and the number of incoming particles in real time, and the number of screened particles and the number of incoming particles are given to calculate the pass rate of the screen. The screen state evaluation unit sets the pass threshold by the user according to the production process requirements, and performs a secondary comparative evaluation with the pass rate to analyze the damage of the screen. The specific evaluation content is as follows; When the pass rate is greater than the pass threshold, it indicates that the sieve screening effect is normal and no generation operation is required; When the pass rate is greater than twice the pass threshold, it indicates that the pass rate R of the sieve screening effect is abnormal, and the sieve is judged to be damaged. At this time, the first sieve warning is generated, prompting the replacement of the sieve; When the pass rate is ≤ the pass threshold and the time is > 5 seconds, it indicates that the screening effect of the screen is abnormal and the screen surface is judged to be blocked. At this time, a second screen warning is generated to prompt the screen surface to be cleaned.

[0017] The present invention has the following beneficial effects: (1) The system can efficiently and accurately obtain multi-angle image data of sand and gravel particles through the multi-angle image acquisition module and the three-dimensional reconstruction module, and generate a high-precision three-dimensional particle model through image stitching and three-dimensional reconstruction technology. By analyzing the vertex vectors of the triangular mesh of the three-dimensional model, the equivalent particle size and uniformity index of the particles are calculated, and the automatic evaluation of the quality of sand and gravel particles is realized. The system can generate early warnings for crushing process adjustments in a timely manner based on the size and uniformity of sand and gravel particles, and provide accurate quality inspection data for the production line. This technology significantly improves the detection accuracy, replaces the traditional manual screening method, reduces human errors, and improves production efficiency and automation.

[0018] (2) The system uses a screen status assessment module and an optical sensor to monitor the screening process of sand and gravel particles in real time and automatically calculate the screen pass rate. By setting a reasonable screen pass rate threshold F2, the system can automatically perform a secondary assessment when the screen is damaged or blocked and generate relevant warnings. Specifically, when the screen pass rate exceeds twice the threshold, the system will trigger the first screen warning, indicating that the screen may be damaged and needs to be replaced; when the pass rate is lower than the threshold and the time exceeds 5 seconds, the system will generate a second screen warning, indicating that the screen surface is blocked and needs to be cleaned. This warning mechanism can effectively reduce production stagnation caused by screen damage or blockage, ensure the continuity and screening efficiency of the screening process, avoid material waste, and improve the stability of the production line.

[0019] (3) The system uses the particle size analysis unit and uniformity analysis unit in the particle quality detection module to calculate the equivalent particle size of the particles and evaluate the uniformity of the particles based on the real-time acquisition of sand and gravel particle size data, thereby obtaining a uniformity index. If the uniformity index exceeds the preset crushing standard threshold, the system will automatically trigger a crushing process adjustment warning to remind the operator to adjust the crushing process parameters, thereby improving the uniformity of the particles and avoiding low production efficiency caused by uneven particle size distribution. Through this intelligent evaluation and adjustment mechanism, the system can effectively optimize the sand and gravel crushing process, reduce particles that do not meet the specifications, improve crushing efficiency, save energy, reduce waste, and ultimately improve the economic benefits of production. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and other objects, features and advantages of the present application will become more apparent through a more detailed description of exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0021] Figure 1 It is a structural schematic diagram of a quality detection system shown in an embodiment of the present application. DETAILED DESCRIPTION

[0023] 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.

[0024] Example 1 See also Figure 1The present invention provides a quality detection system for the size of crushed sand and gravel particles. To achieve the above purpose, the present invention is implemented through the following technical solutions: including a multi-angle acquisition module, an image preprocessing module, an image stitching and three-dimensional reconstruction module, a particle quality detection module and a screen state evaluation module; The multi-angle acquisition module installs a camera group on the conveyor belt, calculates the camera frame rate F in combination with the conveyor belt speed Vb, and continuously shoots the sand and gravel particles on the conveyor belt through a trigger according to the camera frame rate F to obtain a multi-angle sand and gravel particle image data set. At the same time, a quality inspection system is constructed to transmit the multi-angle sand and gravel particle image data set to the quality inspection system; The image preprocessing module preprocesses the multi-angle sand and gravel particle image data set in the quality inspection system. The preprocessing includes blur detection and elimination, depth analysis and denoising, and outputs a standard sand and gravel particle image set. The image stitching and 3D reconstruction module extracts the feature point descriptors f(pi) of all images in the standard sand and gravel particle image set, matches the feature point pi, obtains the feature point matching value Match(pi, pj), and then judges the matching situation based on the output result of the feature point matching value Match(pi, pj); At the same time, the multi-angle sand and gravel particle images are registered through the feature point descriptor f(pi) to generate a sparse point cloud model, and the sparse point cloud model is expanded into a triangular mesh structure to restore the three-dimensional particle model of the sand and gravel particles; The particle quality detection module calculates the equivalent particle size Deq of the sand and gravel particles through the triangular mesh vertex vectors of the three-dimensional particle model, and calculates the uniformity index CV of the sand and gravel particles based on the equivalent particle size Deq, and then performs a preliminary comparative evaluation between the preset crushing standard threshold F1 and the uniformity index CV; The screen status assessment module installs optical sensors at the entrance and exit of the screen to count the screening data of sand and gravel particles, calculates the pass rate R of the screen based on the screening data, and sets the pass threshold F2 to conduct a secondary comparative assessment with the pass rate R to analyze the damage of the screen.

[0025] In this embodiment, the multi-angle acquisition module of the system calculates the camera frame rate F by installing a camera group on the conveyor belt and combining the speed Vb of the conveyor belt, and continuously shoots the sand and gravel particles from multiple angles under the control of the trigger to obtain a detailed particle image data set. Then, the image is processed by the image preprocessing module, including blur detection, depth analysis and denoising, and a standardized particle image set is output to ensure the quality and accuracy of the image data. Next, the image stitching and three-dimensional reconstruction module generates a sparse point cloud model by extracting feature points in the image, matching and registering, and further expands it into a triangular mesh structure to restore the three-dimensional form of the sand and gravel particles. On this basis, the particle quality detection module calculates the equivalent particle size Deq using the triangular mesh vertex vector of the three-dimensional particle model, and evaluates its crushing effect according to the particle uniformity index CV. When the particle uniformity index CV is higher than the set threshold, the system will generate a crushing process adjustment warning, prompting the operator to optimize the crushing process to ensure the uniformity of the particle size and the crushing efficiency. At the same time, the screen state evaluation module combines the optical sensor to monitor the screening situation in real time, calculates the pass rate R of the screen, and then evaluates the working state of the screen. When the pass rate is lower than the set threshold, the system will automatically trigger a screen damage or blockage warning, prompting the operator to perform screen maintenance or replacement. Through the collaborative work of these modules, the quality inspection system of the present invention not only greatly improves the accuracy and automation of sand and gravel particle detection, but also optimizes the crushing process in real time and improves the overall efficiency of the production line. Specifically, it can accurately evaluate the quality and screening effect of particles, reduce production stoppages caused by uneven particle size or screen problems, optimize production processes, reduce energy consumption and material waste, and ultimately improve the stability and production efficiency of the sand and gravel crushing process.

[0026] Example 2 This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the multi-angle acquisition module includes an acquisition setting unit and an image data transmission unit; The acquisition setting unit installs a camera group just above and on both sides of the sand and gravel conveyor belt, and then uses the conveyor belt speed sensor to obtain the conveyor belt speed Vb to calculate the camera frame rate F. The algorithm formula of the camera frame rate F is: , where Dmin represents the minimum diameter of the sand and gravel particles, and S represents the safety multiple. At the same time, the laser calibrator is used to emit an auxiliary wireframe to lock the sand and gravel particle area. The camera uses frame synchronization technology to continuously shoot at a camera frame rate F to capture multi-angle image data of the same sand and gravel particles on the conveyor belt. The camera's automatic recording function records the sand and gravel particle number and the shooting timestamp to obtain a multi-angle sand and gravel particle image data set; The image data transmission unit constructs a quality inspection system, directly connects the camera group and the quality inspection system through a line, and transmits the multi-angle sand and gravel particle image data set collected by the camera group to the quality inspection system.

[0027] In this embodiment, the multi-angle acquisition module of the system realizes efficient, multi-angle real-time image acquisition and transmission of sand and gravel particles through the close cooperation of the acquisition setting unit and the image data transmission unit. The specific implementation method is that the acquisition setting unit installs multiple camera groups just above and on both sides of the sand and gravel conveyor belt, combines the conveyor belt speed sensor to obtain the conveyor belt speed Vb in real time, and calculates the camera frame rate F based on the speed. The particle area is locked by the camera frame synchronization technology and the laser calibrator auxiliary wireframe to ensure that the camera can continuously shoot the sand and gravel particle images on the conveyor belt at the correct frame rate F, and automatically record the number and timestamp of each particle, and capture the multi-angle sand and gravel particle image data set. These image data will be directly transmitted to the quality inspection system through the image data transmission unit, realizing the fast and stable transmission of data. Through this design, this module can efficiently and accurately collect multi-angle image data of sand and gravel particles, providing a high-quality image data foundation for subsequent particle quality analysis, three-dimensional reconstruction and screen status evaluation.

[0028] Example 3 This embodiment is explained in Example 2. Please refer to Figure 1 ,Specifically: the image preprocessing module includes a blur detection and removal unit, a depth analysis unit and a ,denoising processing unit; The blur detection and elimination unit receives the multi-angle sand and gravel image data collected in the quality inspection system in real time, calculates the clarity index L of the sand and gravel image in the multi-angle sand and gravel image data by using the Laplace gradient method, and sets the blur threshold Lmin to perform blur detection and elimination evaluation. The specific evaluation content is as follows; When the clarity index is greater than the blur threshold, it is determined to be the first sandstone image and retained, and the first sandstone image is a clear sandstone image; when the clarity index is less than or equal to the blur threshold, it is determined to be the second sandstone image and removed, and the second sandstone image is a blurred sandstone image; The depth analysis unit is used to analyze the first sandstone image by using a bullet screen deep learning algorithm, determine the distance from the pixel of the first sandstone image to the camera, and generate a depth map and a depth value corresponding to the coordinates of each pixel point; The specific algorithm formula of the clarity index L is: ;in, represents partial derivative, I(x, y) represents the pixel value of the image at the pixel coordinate (x, y), x represents the horizontal axis direction, and y represents the vertical axis direction; After removing the blurred image, the depth analysis unit uses the bullet screen deep learning algorithm to analyze the distance from the pixel of each sandstone image in the multi-angle sandstone image data to the camera, and generates a depth map D (x, y) and the depth value Z (x, y) corresponding to each pixel point coordinate (x, y); The denoising unit introduces the convolutional neural network (CNN) to refine and denoise the boundaries of each sand and gravel image in the multi-angle sand and gravel image data to optimize the image clarity. After denoising, the remaining sand and gravel images are summarized and a standard sand and gravel particle image set is output.

[0029] In this embodiment, the image preprocessing module of the system significantly improves the quality and reliability of the sand and gravel particle image data through the collaborative work of submodules including blur detection and removal unit, depth analysis unit and denoising processing unit, ensuring the accuracy of subsequent image stitching and three-dimensional reconstruction process. The specific implementation method is that the blur detection and removal unit first uses the Laplace gradient method to calculate the clarity index L of the sand and gravel image, and sets the blur threshold Lmin to evaluate the clarity of each image in real time. When the clarity index L of the image is greater than the threshold, the image is retained; if L is less than or equal to the threshold, it is determined to be a blurry image and removed, reducing the interference of the blurry image on the subsequent analysis results. Through this preprocessing step, low-quality image data can be effectively removed, thereby improving the overall quality of the image data set. Next, the depth analysis unit analyzes the distance between the sand and gravel particles and the camera in each image through a deep learning algorithm, generates an accurate depth map D (x, y) and the depth value Z (x, y) of each pixel point, and provides spatial position information for subsequent three-dimensional reconstruction and particle size analysis. This depth analysis process ensures the three-dimensional sense and realism of the image data, making the spatial distribution and morphological characteristics of the particles more accurate. Finally, the denoising unit uses the convolutional neural network (CNN) to refine the image boundaries and denoise it, further optimizing the image clarity and removing background noise and irrelevant information. After denoising, the system will obtain a set of standardized, clear and accurate sand and gravel particle images, providing high-quality input data for subsequent image stitching, 3D reconstruction and particle quality detection.

[0030] Example 4 This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: the image stitching and 3D reconstruction module includes a feature point extraction and ,matching unit and a registration and stitching unit; The feature point extraction and matching unit includes a feature point extraction unit and a feature point matching unit; The feature point extraction unit performs Gaussian blurring of different scales on all images in the standard sand and gravel particle image set to generate a multi-layer pyramid to detect features of different sizes, then performs differential calculation on the pyramid to calculate the image difference between adjacent scales, extracts extreme points as preliminary feature points, determines the precise position and main direction of the feature points, assigns rotation invariance, calculates the gradient direction histogram within the neighborhood of the feature points, and forms a feature point descriptor f(pi), where the feature point descriptor f(pi) = {position, scale, direction, descriptor}; The feature point matching unit performs feature point matching through the feature point descriptors f(pi) of all the sand and gravel images in the standard sand and gravel particle image set and combines the depth value Z(x, y) to obtain the feature point matching value Match(pi, pj), and judges the matching situation based on the output result of the feature point matching value Match(pi, pj), finds the overlapping area of ​​the multi-angle sand and gravel images in the standard sand and gravel particle image set, aligns the two images by matching the feature points, and generates a two-dimensional sand and gravel image; The judgment formula of feature point matching value Match (pi, pj) is: ; In the formula, otherwise means otherwise, which means when the above conditions are not met, if means the condition, f(pj) means the descriptor of feature point pj, z(x, y) pi Indicates the depth value of feature point pi, z (x, y) pj represents the depth value of feature point pj, Represents the depth value weight factor, which is used to balance the influence of feature descriptor similarity and depth difference. When it is larger, the depth difference is more important for matching; When it is small, it mainly depends on the similarity of the descriptors. represents the matching threshold; The specific judgment is as follows; When the feature point matching value Match (pi, pj) = 1, it means that the i-th feature point pi and the j-th feature point pj are matching points; When the feature point matching value Match(pi,pj)=0, it means that the i-th feature point pi and the j-th feature point pj are not matching points.

[0031] The registration and splicing unit includes a matching point elimination unit and a point cloud registration and splicing unit; The point cloud registration and stitching unit randomly selects a subset from the matching points by using the RANSAC algorithm, fits the transformation matrix model, and then calculates the matching point error e from all matching points to the transformation matrix model. It compares the matching point error e with the error threshold eth to determine the accuracy of the matching point, and repeats multiple iterations to select the transformation matrix model with the upper limit of the internal point as the matching point, and removes the wrong matching points. The specific algorithm formula of matching point error e is: , where H represents the transformation matrix; The specific judgment is as follows; When the matching point error e < error threshold eth, the point pair is considered to be matched successfully, and (pi, pj) is an interior point; When the matching point error e≥error threshold eth, the point pair is considered to have failed to match, and the matching point (pi, pj) is removed; The error threshold eth obtains the typical matching error range through experiments, and then selects a threshold that can distinguish between correct matches and incorrect matches, and then is initially set by relevant staff.

[0032] The point cloud registration and stitching unit applies the ICP algorithm to perform point cloud registration and stitching to form a sparse point cloud model of complete sand and gravel particles, then performs a neighbor search on the sparse point cloud model, builds a triangular mesh connection of the points, optimizes the triangular mesh to complete the boundary, generates a closed surface, and restores the three-dimensional particle model of the sand and gravel particles; A triangular mesh is constructed by three vertex vectors Determine the position coordinates (x v ,y v , z v ), represents the three vertices of a triangle and defines the position of the triangle in three-dimensional space.

[0033] In this embodiment, the feature point extraction and matching unit of the system extracts feature points in the sand and gravel particle image through Gaussian blur and differential pyramid algorithm, and generates a rotation-invariant descriptor f(pi) for each feature point. This process ensures that the feature points have strong robustness and can effectively identify the same particles under different viewing angles. Next, the feature point matching unit combines the depth information of the image and accurately matches the feature points of the same particle in different images by comparing the depth value and the feature point descriptor, thereby finding the overlapping areas between the images. This matching process uses the feature point matching value Match(pi, pj) to judge the correctness of the match, ensuring the high quality and low error of the matching points.

[0034] On the basis of feature point matching, the registration and stitching unit selects internal points from the matching points through the RANSAC algorithm, and fits the transformation matrix model to further eliminate erroneous matching points. Through multiple iterations, the system can accurately calculate the transformation relationship of the matching points, and synthesize the sand and gravel particle information in multiple images into a complete sparse point cloud model through point cloud registration and stitching technology. Then, based on the ICP algorithm, the registration effect of the point cloud is further optimized, the triangular mesh connection of the points is performed, the boundaries are completed, and a closed surface is generated to successfully restore the three-dimensional shape of the particles. This process generates a high-precision three-dimensional particle model for each sand and gravel particle through precise image stitching and three-dimensional reconstruction, which significantly improves the accuracy of particle size measurement and quality inspection. At the same time, the results of the three-dimensional reconstruction provide more accurate particle distribution information for the evaluation of the screen state, thereby improving the accuracy of the evaluation of the screening effect.

[0035] Example 5 This embodiment is explained in Example 4. Please refer to Figure 1 ,Specifically: the particle quality detection module includes a particle size analysis unit, a ,uniformity analysis unit and a crushing effect evaluation unit; The particle size analysis unit extracts the vertex coordinates (x, y, z) of each triangular mesh from the three-dimensional particle model and calculates three vertex vectors for each triangular mesh. The specific algorithm is as follows: ; Based on the sum of the vertex vectors of all triangular meshes, the closed three-dimensional volume defined by the triangular meshes is calculated to obtain the volume V of the sand and gravel particles, and given the volume V of the sand and gravel particles, the equivalent particle size Deq of the sand and gravel particles is calculated and output; The equivalent particle size Deq is calculated by the following algorithm formula: ;in ; Where N is the total number of triangular meshes, and π is the circumference of a circle, which is 3.14. represents the dot product of the vertex vector and the normal vector, and represents the projection of the triangle volume. represents the cross product of two vertex vectors, representing the normal vector of the triangle; By deriving the equivalent diameter from the volume, a standardized size index can be used to represent the particle size, even if the particles are irregular in shape.

[0036] The uniformity analysis unit calculates the equivalent particle size Deq for all three-dimensional particle models, and calculates the average value and variance of all equivalent particle sizes Deq to obtain the uniformity index CV of the sand and gravel particles, and analyzes the crushing process of the sand and gravel particles; The uniformity index CV is calculated and output by the following algorithm formula; ; In the formula, Deq n represents the equivalent diameter of the nth particle, Represents the average value of equivalent diameter.

[0037] The crushing effect evaluation unit sets the crushing standard threshold F1 based on the sand and gravel crushing standard, makes a preliminary comparative evaluation with the uniformity index CV, analyzes the uniformity of the sand and gravel particles, and determines the adjustment of the crushing process. The specific evaluation contents are as follows; When the uniformity index CV> the crushing standard threshold F1, it means that the sand and gravel particle size distribution is uneven, and an early warning for crushing process adjustment is generated at this time; When the uniformity index CV ≤ the crushing standard threshold F1, it means that the sand and gravel particle size distribution is uniform and no adjustment is required.

[0038] In this embodiment, the particle size analysis unit of the system extracts the vertex coordinates (x, y, z) of the triangular mesh from the three-dimensional particle model, calculates the vertex vector of each triangular mesh, and then uses the volume derivation formula of the triangular mesh to calculate the volume V of the sand and gravel particles. Through these volume data, the equivalent particle size Deq of the sand and gravel particles is further derived. The equivalent particle size provides a standardized size indicator that can accurately describe the size of the sand and gravel particles even if the shape is irregular. This analysis provides basic data for further quality detection of particles and ensures high-precision measurement of particle size.

[0039] Secondly, the uniformity analysis unit calculates the mean and variance of the equivalent particle size Deq of all sand and gravel particles to obtain the uniformity index CV. The uniformity index CV reflects the distribution of particle size and helps analyze whether the sand and gravel particles are uniform during the crushing process. A lower CV value indicates that the particle size distribution is more uniform, while a higher CV value means that the particle distribution is uneven, which may indicate a problem in the crushing process. Finally, the crushing effect evaluation unit sets the crushing standard threshold F1 and combines it with the uniformity index CV for evaluation. When the CV value exceeds the threshold F1, the system will generate a crushing process adjustment warning, indicating that the particle size distribution is uneven and the crushing process may need to be adjusted; when the CV value is less than or equal to F1, it indicates that the particle size distribution is uniform and the system does not need to be adjusted. This module not only helps monitor the uniformity of sand and gravel particles, but also provides real-time feedback on the effectiveness of the crushing process, adjusts the production process in a timely manner, and ensures the stability of the quality of sand and gravel products.

[0040] Example 6 This embodiment is explained in Example 5. Please refer to Figure 1 ,Specifically: the sieve state evaluation module includes a screening rate analysis unit and a sieve state evaluation unit; The screening rate analysis unit installs optical sensors at the outlet and inlet of the sieve. When the initial assessment shows that the sand and gravel particle size distribution is uniform, the optical sensors are started to count the number of sieved particles Npass and the number of incoming particles Ntotal in real time, and the number of sieved particles Npass and the number of incoming particles Ntotal are given to calculate the pass rate R of the sieve. The specific algorithm formula of the pass rate R is: ; The screen status evaluation unit allows the user to set the pass threshold F2 according to the production process requirements, and then conducts a secondary comparative evaluation with the pass rate R to analyze the damage of the screen. The specific evaluation contents are as follows; When the pass rate R> the pass threshold F2, it means that the sieve screening effect is normal and no generation operation is required; When the pass rate R> twice the pass threshold F2, it means that the pass rate R of the sieve screening effect is abnormal, and the sieve is judged to be damaged. At this time, the first sieve warning is generated to prompt the replacement of the sieve; When the pass rate R ≤ the pass threshold F2, and the time is greater than 5 seconds, it indicates that the screening effect of the screen is abnormal, and the screen surface is judged to be blocked. At this time, a second screen warning is generated, prompting the screen surface to be cleaned.

[0041] In this embodiment, the screening rate analysis unit of the system installs optical sensors at the entrance and exit of the screen to count the number of particles Npass passing through the screen and the number of particles Ntotal entering the screen in real time, and calculates the pass rate R of the screen by the ratio of the two. Specifically, when the system preliminarily evaluates that the size distribution of the sand and gravel particles is uniform, the optical sensor is started to collect real-time data of the particles passing through the screen. The calculation formula of the pass rate R is, which can directly reflect the screening efficiency of the screen under the current operating conditions. This analysis provides timely and accurate feedback for the screen state. Secondly, the screen state evaluation unit sets a pass rate threshold F2 according to the production process requirements set by the user, and performs a secondary comparative evaluation on the actual calculated pass rate R. According to the relationship between the pass rate and the threshold, the system can accurately judge the working state of the screen: when the pass rate R is greater than the threshold F2, it means that the screening effect of the screen is normal and no operation is required. When the pass rate R exceeds twice the threshold F2, it means that the screening effect of the screen is abnormal, and there may be a situation where the screen is damaged. At this time, the system will generate a first screen warning to remind the operator to replace the screen. When the pass rate R is less than or equal to the threshold F2 and the time exceeds 5 seconds, it means that the screen surface may be blocked and the screening effect is seriously reduced. At this time, the system will generate a second screen warning to remind the operator to clean the screen. Through these refined evaluation and warning mechanisms, this module can not only monitor the screening effect of the screen in real time, but also effectively predict and discover potential problems of screen damage or blockage in advance, thereby providing accurate guidance for screen maintenance and replacement during the production process.

[0042] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A quality detection system for the size of crushed sand and gravel particles, characterized in that: include: Multi-angle acquisition module, image preprocessing module, image stitching and 3D reconstruction module, particle quality detection module and screen status assessment module; The multi-angle acquisition module is installed above a conveyor belt, and the conveyor belt is used to transport sand and gravel to be tested. The multi-angle acquisition module continuously shoots the sand and gravel particles on the conveyor belt according to the conveying speed of the conveyor belt and the camera frame rate to obtain a multi-angle sand and gravel particle image data set, and transmits the multi-angle sand and gravel particle image data set to the image preprocessing module; The image preprocessing module is used to preprocess the multi-angle sand and gravel particle image data set, and the preprocessing includes blur detection and elimination, depth analysis and denoising, and outputs a standard sand and gravel particle image set; The image stitching and three-dimensional reconstruction module is used to extract feature point descriptors of all images in the standard sand and gravel particle image set, then match the feature point descriptors to obtain feature point matching values, and then judge the matching situation based on the feature point matching value output result; Based on the feature point descriptors, register the multi-angle sand and gravel particle images to generate a sparse point cloud model, and expand the sparse point cloud model into a triangular mesh structure to restore the three-dimensional particle model of the sand and gravel particles; The particle quality detection module is used to obtain the triangular mesh vertex vectors of the triangular mesh structure, calculate the equivalent particle size of the sand and gravel particles according to the triangular mesh vertex vectors, calculate the uniformity index of the sand and gravel particles based on the equivalent particle size, and perform a preliminary comparison and evaluation between a preset crushing standard threshold and the uniformity index; The screen status assessment module includes an optical sensor, which is arranged at the entrance and exit of the screen. The screen status assessment module is used to count the screening data of sand and gravel particles, and calculate the pass rate of the screen based on the screening data, and perform a secondary comparative assessment on the set pass threshold and the pass rate to obtain the damage condition of the screen.

2. A quality detection system for crushed sand and gravel particles according to claim 1, characterized in that: The multi-angle acquisition module includes an acquisition setting unit, a data processing unit and an image data transmission unit; The acquisition setting unit includes a conveyor belt speed sensor and a plurality of camera groups, which are respectively installed directly above the conveyor belt and on both sides of the conveyor belt. The conveyor belt speed sensor is used to obtain the transmission speed of the conveyor belt; The data processing unit is used to calculate the camera frame rate of the camera group, and emit an auxiliary wireframe through a laser calibrator to lock the sand and gravel particle area. The camera group continuously shoots at the camera frame rate F through frame synchronization technology to capture multi-angle image data of the same sand and gravel particle on the conveyor belt, and records the number of the sand and gravel particle and the shooting timestamp to obtain a multi-angle sand and gravel particle image data set; The image data transmission unit is used to transmit the multi-angle sand and gravel particle image data set collected by the camera group to the image preprocessing module.

3. A quality detection system for crushed sand and gravel particles according to claim 1, characterized in that: The image preprocessing module includes a blur detection and removal unit, a depth analysis unit and a denoising processing unit; The blur detection and elimination unit is used to receive the collected multi-angle sandstone image data, calculate the clarity index corresponding to each sandstone image in the multi-angle sandstone image data by using the Laplace gradient method, and compare the clarity index with the set blur threshold: When the clarity index is greater than the blur threshold, it is determined to be the first sandstone image and retained, and the first sandstone image is a clear sandstone image; when the clarity index is less than or equal to the blur threshold, it is determined to be the second sandstone image and removed, and the second sandstone image is a blurred sandstone image; The depth analysis unit is used to analyze the first sandstone image by using a bullet screen deep learning algorithm, determine the distance from the pixel of the first sandstone image to the camera, and generate a depth map and a depth value corresponding to the coordinates of each pixel point; The denoising processing unit is used to refine and denoise the boundaries of the first sand and gravel image through a convolutional neural network CNN to optimize image clarity, and after denoising, summarize the remaining sand and gravel images to output a standard sand and gravel particle image set.

4. A quality detection system for crushed sand and gravel particles according to claim 3, characterized in that: The image stitching and three-dimensional reconstruction module includes a feature point extraction unit and a feature point matching unit; The feature point extraction unit is used to perform Gaussian blurring of different scales on all images in the standard sand and gravel particle image set, generate a multi-layer pyramid to detect features of different sizes, then perform differential calculation on the pyramid to calculate image differences between adjacent scales, extract extreme points as preliminary feature points, determine the precise position and main direction of the feature points, assign rotation invariance, calculate the gradient direction histogram within the neighborhood of the feature points, and form a feature point descriptor; The feature point matching unit is used to perform feature point matching on the feature point descriptor in combination with the depth value to obtain a feature point matching value, and to make a judgment based on an output result of the feature point matching value to determine an overlapping area of ​​multi-angle sand and gravel images in a standard sand and gravel particle image set, and to align the two images by matching feature points to generate a two-dimensional sand and gravel image; Wherein, the judgment is made based on the output result of the feature point matching value as follows; When the feature point matching value = 1, the two feature points are matching points; When the feature point matching value = 0, the two feature points are not matching points.

5. The quality detection system for crushed sand and gravel particles according to claim 3 is characterized in that: The image stitching and three-dimensional reconstruction module also includes a point cloud registration and stitching unit; The point cloud registration and stitching unit is used to randomly select a subset from all matching points using the RANSAC algorithm, fit the transformation matrix model, and then calculate the matching point error e from all matching points to the transformation matrix model, and compare the matching point error e with the error threshold eth to determine the accuracy of the matching point, and repeat multiple iterations to select the transformation matrix model with the upper limit of the inner point as the matching point, and remove the wrong matching point; the specific judgment is as follows; When the matching point error is less than the error threshold, the point pair is considered to be matched successfully and marked as an inlier; When the matching point error ≥ the error threshold, the point pair is considered to have failed to match and the matching point is removed.

6. A quality detection system for crushed sand and gravel particles according to claim 5, characterized in that: The image stitching and three-dimensional reconstruction module also includes a matching point elimination unit. The point cloud registration and stitching unit performs point cloud registration and stitching by applying an ICP algorithm to form a sparse point cloud model of complete sand and gravel particles, and then performs a neighbor search on the sparse point cloud model to build a triangular mesh connection of the points, optimize the triangular mesh to complete the boundary, generate a closed surface, and restore the three-dimensional particle model of the sand and gravel particles. The triangular mesh determines the position coordinates of each vertex in the three-dimensional space through three vertex vectors.

7. The quality detection system for crushed sand and gravel particles according to claim 1 is characterized in that: The particle quality detection module includes a particle size analysis unit, a uniformity analysis unit and a crushing effect evaluation unit; the particle size analysis unit extracts the vertex coordinates of each triangular mesh from the three-dimensional particle model and generates three vertex vectors of each triangular mesh; Based on the sum of the vertex vectors of all triangular meshes, the closed three-dimensional volume defined by the triangular meshes is calculated, the closed three-dimensional volume is the volume of the sand and gravel particles, and the equivalent particle size of the sand and gravel particles is calculated and output.

8. The quality detection system for sand and stone crushing particle size according to claim 7 is characterized by: The uniformity analysis unit calculates the equivalent particle size for all three-dimensional particle models, and calculates the average value and variance of all the equivalent particle sizes to determine the uniformity index of the sand and gravel particles and analyze the sand and gravel particle crushing process.

9. A quality detection system for crushed sand and gravel particles according to claim 8, characterized in that: The crushing effect evaluation unit sets the crushing standard threshold based on the sand and gravel crushing standard, performs a preliminary comparative evaluation with the uniformity index, analyzes the uniformity of the sand and gravel particles, and determines the crushing process adjustment. The specific evaluation contents are as follows; When the uniformity index is greater than the crushing standard threshold, it indicates that the sand and gravel particle size distribution is uneven, and an early warning for crushing process adjustment is generated. When the uniformity index is ≤ the crushing standard threshold, it means that the sand and gravel particle size distribution is uniform and no adjustment is required.

10. The quality detection system for crushed sand and gravel particles according to claim 1, characterized in that: The screen state evaluation module includes a screening rate analysis unit and a screen state evaluation unit; The screening rate analysis unit installs optical sensors at the outlet and inlet of the screen. When it is preliminarily evaluated that the sand and gravel particle size distribution is uniform, the optical sensors are started to count the number of screened particles and the number of incoming particles in real time, and the number of screened particles and the number of incoming particles are given to calculate the pass rate of the screen. The screen state evaluation unit sets the pass threshold by the user according to the production process requirements, and performs a secondary comparative evaluation with the pass rate to analyze the damage of the screen. The specific evaluation content is as follows; When the pass rate is greater than the pass threshold, it indicates that the sieve screening effect is normal and no generation operation is required; When the pass rate is greater than twice the pass threshold, it indicates that the pass rate R of the sieve screening effect is abnormal, and the sieve is judged to be damaged. At this time, the first sieve warning is generated, prompting the replacement of the sieve; When the pass rate is ≤ the pass threshold and the time is > 5 seconds, it indicates that the screening effect of the screen is abnormal and the screen surface is judged to be blocked. At this time, a second screen warning is generated to prompt the screen surface to be cleaned.

Images