Phosphor copper ball production polishing detection model construction method and system

Abstract

The invention belongs to the field of industrial modules, and provides a phosphor copper ball production polishing detection model construction method and system, and the method comprises the steps: collecting an optical image and a spectral image of the top of a polishing barrel; performing spatial alignment on the optical image and the spectral image, determining a first position of the phosphor copper ball in the spectral image, and calculating a corresponding second position of the phosphor copper ball in the optical image; judging the geometric integrity of the phosphor copper ball based on a roundness threshold value; calculating the roughness index of the surface of the phosphor copper ball at the second position by adopting a gray-level co-occurrence matrix analysis method so as to evaluate whether the polishing is uniform or not; calculating the smoothness uniformity of the phosphor copper ball by adopting a brightness histogram analysis method, and judging whether the phosphor copper ball meets a polishing standard or not; and when the finish degree of the phosphor copper ball is lower than a preset threshold value, adjusting polishing parameters and continuing polishing, otherwise, stopping polishing and outputting a detection result.

Description

Technical Field

[0001] The invention belongs to the field of industrial modules, and in particular relates to a method and system for constructing a production polishing detection model for phosphor bronze balls. Background Art

[0002] Phosphor copper balls are spherical metal particles widely used in the fields of electronics, welding and precision manufacturing. Referring to the production line disclosed in Chinese Patent Publication No. CN118417893A, its production process usually includes raw material processing, spheroidization, polishing and quality inspection. Polishing is a key step to improve the surface finish of phosphor copper balls, reduce the oxide layer and improve the conductivity, which directly affects the final quality of the product. However, in the traditional phosphor copper ball polishing process, there is a lack of effective polishing detection means, resulting in low polishing efficiency, unstable quality, and a large dependence on manual labor, which is difficult to meet the needs of modern industry for automation and efficient production.

[0003] In the existing phosphor bronze ball production process, a fixed time long polishing method is usually adopted, that is, without real-time detection of the polishing state of the phosphor bronze balls, a longer polishing time is set to ensure that all phosphor bronze balls can achieve qualified finish. However, in order to achieve a good polishing effect, the fixed time polishing method often sets a relatively long polishing time, thereby reducing the overall production efficiency and increasing unnecessary energy and material consumption.

[0004] Manual inspection is still the quality control method currently adopted by some phosphor bronze ball manufacturers, but it is difficult to adapt to the needs of large-scale continuous production.

[0005] In addition, existing machine vision inspection technology faces major challenges in the polishing process of phosphor bronze balls. Since the phosphor bronze balls are in a high-density stacking state in the polishing barrel, and chemical substances such as abrasive sand, brightener, and activator are added during the polishing process, these substances will form a covering layer or liquid film, which seriously affects the imaging quality of the phosphor bronze ball surface by the optical inspection system. For example, during the polishing process, the brightener and activator will form a layer of liquid film on the surface of the phosphor bronze ball, which will produce strong mirror reflection during optical imaging, making it difficult for traditional industrial cameras to clearly capture the true surface state of the phosphor bronze ball, resulting in misjudgment or failure to identify effective targets. The abrasive sand particles form a randomly distributed covering layer on the surface of the phosphor bronze ball, making the proportion of the phosphor bronze ball in the picture too small, making it difficult to detect. The lighting environment inside the polishing barrel is complex, and the scattering and reflection characteristics of the light source will cause the captured image to have a large brightness unevenness problem, making it difficult for the image detection algorithm based on grayscale features to distinguish the surface of the phosphor bronze ball from the background, affecting the detection accuracy. Summary of the invention

[0006] In order to solve the problems in the prior art, the present invention provides a method for constructing a production polishing detection model for phosphor bronze balls, comprising the following steps: Step S10, data acquisition, using an industrial camera to obtain an optical image of the phosphor bronze ball on the top of the polishing barrel, and using a short-wave infrared hyperspectral camera to obtain a spectral image of the top of the polishing barrel; Step S20, spatially aligning the optical image and the spectral image so that the two are analyzed in the same coordinate system; determining the first position of the phosphor bronze ball in the spectral image by a target detection algorithm, and calculating the corresponding second position of the phosphor bronze ball in the optical image based on the coordinate mapping model of the optical image, to ensure the consistency of the same phosphor bronze ball in the two data channels; Step S30, using an ellipse fitting algorithm to calculate the roundness of the phosphor bronze ball at the second position, and judging the geometric integrity of the phosphor bronze ball based on a roundness threshold, and when the roundness of the phosphor bronze ball does not meet the standard, adjusting the polishing parameters and continuing the grinding; Step S40, using the grayscale co-occurrence matrix analysis method to calculate the roughness index of the surface of the phosphor bronze ball at the second position to evaluate whether the polishing is uniform; using the brightness histogram analysis method to calculate the smoothness uniformity of the phosphor bronze ball to determine whether it meets the polishing standard; when the smoothness of the phosphor bronze ball is lower than the preset threshold, adjust the polishing parameters and continue polishing, otherwise stop polishing and output the detection result.

[0007] The present invention also provides a phosphor bronze ball production polishing detection model construction system, comprising the following modules: A data acquisition module is used to obtain an optical image of the phosphor bronze ball on the top of the polishing barrel using an industrial camera, and to obtain a spectral image of the top of the polishing barrel using a short-wave infrared hyperspectral camera; The calibration module is used to align the optical image and the spectral image in space so that the two can be analyzed in the same coordinate system; the first position of the phosphor bronze ball in the spectral image is determined by the target detection algorithm, and the corresponding second position of the phosphor bronze ball in the optical image is calculated based on the coordinate mapping model of the optical image to ensure the consistency of the same phosphor bronze ball in the two data channels; a first judgment module, configured to calculate the roundness of the phosphor bronze ball at the second position by using an ellipse fitting algorithm, and judge the geometric integrity of the phosphor bronze ball based on a roundness threshold, and when the roundness of the phosphor bronze ball does not meet the standard, adjust the polishing parameters and continue grinding; The second judgment module is used to calculate the roughness index of the surface of the phosphor bronze ball at the second position by using the grayscale co-occurrence matrix analysis method to evaluate whether the polishing is uniform; calculate the smoothness uniformity of the phosphor bronze ball by using the brightness histogram analysis method to determine whether it meets the polishing standard; when the smoothness of the phosphor bronze ball is lower than the preset threshold, adjust the polishing parameters and continue polishing, otherwise stop polishing and output the detection result.

[0008] The present invention overcomes the problems of low detection accuracy, uncontrollable polishing time and low manual detection efficiency in the existing polishing process by constructing a phosphor copper ball polishing detection model based on the fusion of spectral images and optical images, and has the following beneficial effects: The position of the phosphor bronze ball is identified through spectral images and mapped to optical images to achieve precise positioning, avoid detection errors caused by coverage of abrasive sand, brighteners, and activators, and improve detection stability and robustness. By calculating the roundness, roughness, and finish of the phosphor bronze ball in real time, the polishing parameters are adjusted dynamically to avoid unnecessary long-term polishing, improve the automation level of the production line, and reduce energy and material waste. Computer vision and intelligent algorithms are used instead of manual inspection to reduce human misjudgment, improve the stability and consistency of detection standards, ensure that the polishing quality of the phosphor bronze ball meets high-precision requirements, and reduce the company's labor cost investment. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0010] Figure 1 This is the phosphor bronze ball production line targeted by the present invention; Figure 2 It is the polishing device targeted by the present invention; Figure 3 It is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0011] Below, the invention is preferably described in conjunction with the accompanying drawings and specific implementation methods.

[0012] like Figure 1 As shown, this embodiment describes a further optimization model of the phosphor bronze ball production line based on Chinese patent CN118417893A.

[0013] The process flow of producing copper balls is: discharge tray → ball stacking → conveying → collecting → polishing → cleaning → drying → weighing → packaging → coding → palletizing.

[0014] Among them, automatic punt machine: The ball-making process is: unloading plate (disc coil) → straightening machine → cutting → ball-making; Among them, automatic polishing production line: The polishing process is: ball machine discharges balls → lifting conveyor → collecting barrel → guide trough → grinding machine (2 units) → spray pipe → discharge.

[0015] Among them, automatic cleaning machine line: The cleaning process is: feeding → high-pressure spraying → fan blowing water → drying → conveyor belt feeding → discharging.

[0016] Among them, automatic packaging production line: Discharging of cleaning machine → lifting conveyor → automatic weighing → conveying → sealing → conveying → coding → conveying → strapping → conveying → stacking.

[0017] like Figure 2 Shown is a diagram of a polishing mechanism, in which phosphor bronze balls are polished in a polishing barrel. During the polishing process, abrasive sand, brightener, activator, etc. are used.

[0018] In one embodiment, reference Figure 3 The present invention provides a method for constructing a polishing detection model for phosphor bronze balls. The method collects optical images and spectral data of phosphor bronze balls in a polishing barrel, performs data fusion and analysis, and constructs a detection model that can accurately identify the polishing state of phosphor bronze balls. The method also adjusts the polishing parameters in combination with an intelligent optimization algorithm to ensure the polishing uniformity and quality consistency of the phosphor bronze ball surface, thereby improving the detection accuracy and production efficiency.

[0019] In the present invention, the phosphor bronze ball is a spherical metal particle made of phosphor bronze material, and its production process includes multiple links such as raw material processing, molding, polishing and surface quality inspection. Polishing refers to removing the oxide layer, burrs and microscopic unevenness on the surface of the phosphor bronze ball by mechanical grinding, chemical treatment or other methods to improve its smoothness and surface uniformity to meet specific use requirements.

[0020] Polishing inspection refers to the real-time monitoring of the surface morphology, smoothness, roundness and defects of the phosphor bronze balls through optical imaging, spectral analysis or other inspection technologies during the polishing process of the phosphor bronze balls, and the analysis of the inspection results to determine whether the phosphor bronze balls meet the polishing standards.

[0021] Based on the collected data of phosphor copper ball polishing process, the present invention uses computer vision, deep learning, spectral analysis, statistical analysis and other technologies to establish a mathematical model, optimize the detection algorithm, and combine the feedback control strategy to achieve dynamic evaluation and intelligent regulation of the polishing quality of phosphor copper balls. Specifically, the present invention includes the following steps: Step S10, data acquisition, using an industrial camera to obtain an optical image of the phosphor bronze ball on the top of the polishing barrel, and using a short-wave infrared hyperspectral camera to obtain a spectral image of the top of the polishing barrel.

[0022] Optical image acquisition refers to the use of industrial cameras to obtain visible light images of phosphor bronze balls on the top of the polishing barrel to record the geometric features, contour morphology and surface texture information of the phosphor bronze balls. Industrial cameras are high-resolution imaging devices used for precise measurement and detection. Compared with ordinary cameras, they have higher imaging quality, faster frame rates and stronger environmental adaptability. The imaging area of ​​the industrial camera is set at the top of the polishing barrel, so that it can capture the phosphor bronze balls in the upper layer during the polishing process, and combined with external light source compensation technology to ensure uniform lighting and reduce ambient light interference to improve imaging quality.

[0023] Spectral image acquisition refers to the use of a short-wave infrared hyperspectral camera to obtain a spectral image of the phosphor bronze ball on the top of the polishing barrel to capture the reflectivity information of the phosphor bronze ball at different wavelengths, thereby analyzing its surface state. The short-wave infrared hyperspectral camera is a detection device that can simultaneously image in multiple wavelength channels. Its principle is based on spectral decomposition technology, which performs multi-band acquisition of the reflected light of the target object to obtain richer material property information than visible light imaging. During the polishing process of the phosphor bronze ball, the presence of brighteners and activators may cause changes in the surface reflection characteristics. The use of short-wave infrared imaging can effectively distinguish between the smooth surface and the area covered by brighteners, activators, etc.

[0024] Step S20, spatially aligning the optical image and the spectral image so that the two are analyzed in the same coordinate system; determining the first position of the phosphor bronze sphere in the spectral image through the target detection algorithm, and calculating the corresponding second position of the phosphor bronze sphere in the optical image based on the coordinate mapping model of the optical image, to ensure the consistency of the same phosphor bronze sphere in the two data channels.

[0025] During the polishing process of phosphor bronze balls, most of the image surface is covered by the liquid film produced by the abrasive sand, brightener and activator due to the use of abrasive sand, brightener and activator. The liquid film formed by the brightener produces strong specular reflection, making it difficult for ordinary image processing algorithms to distinguish whether the target is the phosphor bronze ball or the liquid film.

[0026] Due to the above factors, it is difficult for ordinary optical images to directly identify the position of the phosphor bronze ball, which makes the traditional edge detection or target detection-based algorithms unstable in complex polishing environments.

[0027] The spectral characteristics of phosphor bronze balls are clearly different from those of abrasive sand, brighteners, and activators. In the short-wave infrared (SWIR) band, the spectral reflectivity of phosphor bronze materials is quite different from that of abrasive sand, brighteners, and activators, allowing the spectral camera to clearly distinguish the phosphor bronze balls from the background.

[0028] Abrasive sand usually exhibits low infrared reflectivity, and its particle morphology leads to enhanced scattering, forming high-contrast areas in the spectral image, which is clearly different from the smooth surface of the phosphor bronze ball. Brighteners may cause high reflection in the visible light range, but usually appear as relatively uniform low-reflection areas in the short-wave infrared band, so they do not interfere with the positioning of the phosphor bronze ball in the spectral image. Due to the different chemical composition of the deposited layer of the activator, the absorption characteristics at specific infrared wavelengths are significantly different from those of the phosphor bronze material, allowing the spectral camera to identify the location of the phosphor bronze ball through multi-band imaging.

[0029] However, due to the low grayscale contrast of spectral data, the boundary contour of the phosphor bronze ball is difficult to accurately segment in the spectral image, and roundness detection requires high-precision boundary data for ellipse fitting and shape analysis, so spectral images are not suitable for roundness detection. At the same time, since spectral images are analyzed based on the spectral characteristics of material components, the reflectivity of light at different wavelengths may be affected by the residues of abrasive sand, brighteners, and activators, resulting in misjudgment of finish evaluation.

[0030] Based on the respective advantages of optical images and spectral images, the auxiliary positioning of spectral images for optical images can be achieved through the following steps: First, the position of the phosphor bronze ball is detected in the spectral image. The target detection algorithm based on spectral features is used to accurately identify the position of the phosphor bronze ball in the spectral image and determine its first position, that is, the coordinate point of the phosphor bronze ball in the spectral image. Through the deep learning target detection model (such as YOLO or Faster R-CNN), the unique spectral features of the phosphor bronze ball are extracted from the multi-band data, and a classification model is established, so that the detection system can eliminate the interference of abrasive sand, brightener and activator.

[0031] Based on the coordinate mapping model, the first position of the spectral image is mapped to the second position of the optical image. Due to the different imaging angles and resolutions of the optical camera and the spectral camera, the coordinate position of the same phosphor bronze sphere in the two images may deviate, so it is necessary to establish a spectral-optical coordinate mapping model.

[0032] In the present invention, the relative positions of the optical camera and the spectral camera are fixed, that is, the two cameras will not physically move during the entire phosphor bronze ball polishing detection process. Therefore, a fixed spatial mapping relationship can be established based on the camera coordinate system, so that the optical image and the spectral image can be analyzed in the same coordinate system, thereby improving the stability and consistency of the detection.

[0033] Since the positions of the optical camera and the spectral camera are fixed, a one-time calibration can be performed when the system is installed to establish the coordinate transformation relationship between the two cameras to ensure that the images collected by both can be mapped to a unified coordinate system. The specific construction method of the spectral-optical coordinate mapping model is as follows: First, the camera intrinsic calibration is performed using a chessboard or calibration plate to calibrate the intrinsic parameter matrices of the optical camera and spectral camera, including focal length, principal point coordinates, and lens distortion coefficient.

[0034] Use a checkerboard or calibration plate to calibrate the optical camera and spectral camera respectively to obtain the camera's intrinsic parameter matrix and lens distortion coefficient.

[0035] The internal parameter matrix is ​​defined as follows:

[0036] in: Indicates: horizontal and vertical focal length (unit: pixel); Represents the coordinates of the principal point (optical center).

[0037] The lens distortion parameters are

[0038] Among them, k1, k2, k3, k4 are radial distortion coefficients; is the tangential distortion coefficient.

[0039] During the calibration process, you can collect multiple checkerboard images at different angles, and then use OpenCV's cv2.calibrateCamera() to calculate the camera intrinsic parameter matrix for the collected images. and distortion coefficient .

[0040] Then the camera extrinsic calibration is performed to determine the relative position relationship between the optical camera and the spectral camera (i.e., the rotation matrix R and the translation vector T), which are used to describe the coordinate transformation of the two cameras.

[0041] The relationship between the rotation matrix and the translation vector is as follows:

[0042] in: R represents the rotation matrix; T represents the translation vector; represents the coordinates of a point in an optical image, Represents the coordinates of a point in a spectral image.

[0043] During the specific calibration, a calibration plate is used to take multiple sets of images in the overlapping fields of view of the optical camera and the spectral camera, and then the corresponding relationship between the checkerboard corner points of the cameras is calculated. The PnP algorithm is used to solve the external parameters. cv2.solvePnP() is used to calculate the external parameter matrix: Calculate the homography matrix between the cameras. Since the cameras are fixed, the projection transformation matrix of the two can be obtained through a one-time calibration and stored for subsequent image transformation. In the formula, object points represent the 3D coordinates of the points calibrated on the calibration board; image points represent the pixel coordinates corresponding to the projection of object points in the camera image.

[0044] The camera calibration results can then be used directly for image alignment without the need for dynamic alignment every time a test is performed. The calculated rotation matrix and translation vector are used to transform the pixels in the spectral image into the coordinate system of the optical image to ensure that the spatial positions of the two match.

[0045] First calculate the 3D coordinates of each pixel in the spectral image Assume that the point in the spectral image In the pixel coordinate system, we have:

[0046] in: is the inverse matrix of the intrinsic parameter matrix of the spectral camera; 3D point in the spectral camera coordinate system; Project the points in the spectral image to the optical camera coordinate system, and transform to the optical camera coordinate system:

[0047] Then reproject it to the optical image:

[0048] in, is the optical image obtained by reprojection; Get the transformed optical image coordinates.

[0049] Then, through homography transformation, the corresponding position of each pixel in the spectral image in the optical image is calculated using the projection transformation matrix and remapped.

[0050] Specifically, the homography matrix H is calculated first:

[0051] in: is the internal reference of the optical camera; is the plane normal vector; is the distance from the plane to the camera for Transformation matrix.

[0052] Then perform projection transformation

[0053] in: is the pixel coordinate of the spectral image; is the mapping coordinate in the optical image; Represents the perspective scaling factor.

[0054] Then cv2.warpPerspective() is used to perform perspective transformation and reproject the spectral image into the optical image coordinate system.

[0055] Through the aligned image coordinates, the phosphor bronze sphere information in the spectral image is annotated on the optical image to assist in subsequent geometric detection.

[0056] Through the second position provided by the spectral image, the optical image is cropped in the region, and fine-grained detection is performed only on the positions where phosphor bronze spheres may exist, thus avoiding the computational overhead caused by global search.

[0057] This step uses spectral images to assist in positioning the optical image, overcoming the detection difficulties caused by the coverage of abrasive sand, brighteners and activators, and improving the accuracy of phosphor bronze ball polishing detection. By constructing a spectral-optical coordinate mapping model, the consistency of the same phosphor bronze ball in the two data channels is ensured, making the subsequent polishing state analysis more accurate. This method can effectively improve the stability of the phosphor bronze ball polishing detection system and provide important data support for optimizing the polishing process and improving product quality.

[0058] Step S30, using an ellipse fitting algorithm to calculate the roundness of the phosphor bronze ball at the second position, and judging the geometric integrity of the phosphor bronze ball based on a roundness threshold; when the roundness of the phosphor bronze ball does not meet the standard, adjusting the polishing parameters and continuing grinding.

[0059] During the polishing process, the roundness of the phosphor bronze ball gradually increases. When its roundness approaches the standard value, the surface microstructure tends to be smooth, making it difficult for the abrasive sand, brightener and activator attached to the surface of the phosphor bronze ball to remain attached. Instead, they naturally slide off or are thrown out by the high-speed rotating polishing barrel.

[0060] Since the surface tension of the phosphor bronze ball after polishing is low, the residual grinding media cannot effectively adhere, so that the phosphor bronze ball in the optical image presents a standard circular area, that is, the boundary of the phosphor bronze ball becomes clearly visible and forms a clear contrast with the background.

[0061] This phenomenon can be used to further improve the detection accuracy, that is, when the outline of the phosphor bronze ball in the image presents a complete, unbroken standard circular area, it can be judged that its polishing is close to completion.

[0062] Since the specific position of the phosphor bronze ball has been located in the previous step, this step calculates the roundness of the phosphor bronze ball based on the ellipse fitting algorithm. The ellipse fitting algorithm refers to calculating the ellipse parameters and evaluating the fitting error on the detected phosphor bronze ball contour point set through the least squares method or the ellipse least squares fitting method to determine whether the geometric shape of the phosphor bronze ball is close to the ideal circle.

[0063] Specifically, the contour points of the phosphor bronze sphere are first extracted through edge detection methods (such as the Canny algorithm), and then the major axis, minor axis, center point coordinates and rotation angle of the phosphor bronze sphere are calculated based on the ellipse fitting algorithm, and the roundness calculation formula is used to determine whether the shape of the phosphor bronze sphere meets the standard.

[0064] The roundness threshold refers to a preset value used to evaluate whether the phosphor bronze ball has reached the standard shape. Its value is usually set based on experimental data and corresponds to the quality requirements of the target product.

[0065] When the calculated roundness is lower than the preset threshold, it means that there is still slight deformation on the surface of the phosphor bronze ball, which may be caused by uneven polishing, uneven distribution of grinding media, or insufficient polishing time.

[0066] At this time, the system automatically adjusts the polishing parameters, such as increasing the grinding time, increasing the rotation speed of the polishing barrel, or optimizing the ratio of grinding sand, brightener, and activator to further improve the geometry of the phosphor bronze ball.

[0067] In this step, the roundness is calculated by the ellipse fitting algorithm, and the morphological changes of the phosphor bronze ball can be monitored in real time during the polishing process, and the polishing parameters can be dynamically adjusted according to the detection results to improve the polishing accuracy. Due to the natural sliding of the grinding medium on the surface of the phosphor bronze ball, when the phosphor bronze ball reaches the standard roundness, the system can automatically identify and stop polishing, avoiding unnecessary resource consumption and improving production efficiency. At the same time, by performing standardized analysis on the phosphor bronze ball area in the optical image, it can ensure that the subsequent finish detection and surface defect identification are more accurate.

[0068] Step S40, using the grayscale co-occurrence matrix analysis method to calculate the roughness index of the surface of the phosphor bronze ball at the second position to evaluate whether the polishing is uniform; using the brightness histogram analysis method to calculate the smoothness uniformity of the phosphor bronze ball to determine whether it meets the polishing standard; when the smoothness of the phosphor bronze ball is lower than the preset threshold, adjust the polishing parameters and continue polishing, otherwise stop polishing and output the detection result.

[0069] The gray-level co-occurrence matrix analysis method is to extract the texture features of the surface of the phosphor bronze ball by calculating the spatial relationship between the gray-level pixels of the image, and use this to measure whether the polishing is uniform.

[0070] Specifically, the optical image of the phosphor bronze ball is first normalized in grayscale, a fixed pixel window is set, and the grayscale co-occurrence matrix between adjacent pixels is calculated in different directions (0°, 45°, 90°, 135°). The surface roughness is quantified by extracting features such as contrast, energy, homogeneity, and entropy.

[0071] Specifically, since optical images may contain pixel values ​​in different brightness ranges, the image needs to be grayscale normalized to ensure consistent image contrast under different lighting conditions.

[0072] Convert optical images to grayscale

[0073] in: are the red, green, and blue channels of the image is the converted grayscale image.

[0074] Then perform grayscale normalization

[0075] in: and are the minimum and maximum grayscale values ​​of the original image respectively; and is the normalized grayscale range (0-255) Represents a normalized grayscale image.

[0076] Set the window size to (such as 5×5 or 7×7), slide the window across the entire image, and calculate the gray-level co-occurrence matrix for each window.

[0077] Gray Level Co-occurrence Matrix Determined by:

[0078] in, is the grayscale (such as 0-255); is the image pixel coordinate; Represents the relative position (direction) between pixels, where: 0° horizontal direction 45° oblique 90° vertical direction 135° oblique The gray-level co-occurrence matrix is ​​a Dimensional matrix ( is the number of gray levels, such as 256), where each element Represents grayscale arrive The frequency of symbiotic relationships.

[0079] Contrast A measure of the intensity of grayscale differences, reflecting the presence of rough or uneven areas on the surface:

[0080] energy A measure of uniformity, the higher the energy value, the more regular the surface texture:

[0081] Uniformity A measure of the smoothness of the distribution of adjacent gray levels, with surfaces that are more uniform being smoother:

[0082] entropy Measures the amount of information, reflecting the randomness and complexity of the texture:

[0083] Among them, the contrast value reflects the change in surface height. The larger the value, the higher the surface roughness. The energy and uniformity indicators reflect the consistency of the surface texture. The higher the value, the more uniform the polishing.

[0084] When the calculated roughness is higher than the preset threshold, it indicates that there is still slight uneven wear or grinding residue on the surface of the phosphor bronze ball. At this time, the polishing parameters are adjusted to optimize the grinding process.

[0085] The brightness histogram analysis method refers to judging the uniformity of the smoothness of the phosphor bronze ball by statistically analyzing the distribution of brightness values ​​of different pixels on the surface of the phosphor bronze ball.

[0086] Specifically, the brightness distribution of the phosphor bronze ball area in the optical image is first statistically analyzed, and the standard deviation, kurtosis, and skewness of the brightness histogram are calculated to evaluate whether the surface finish is uniform.

[0087] Among them, the standard deviation of the brightness histogram reflects the degree of discreteness of the brightness distribution. A lower value indicates that the surface finish is uniform. The kurtosis indicates the concentration of the image brightness. The higher the value, the better the polishing uniformity. The skewness is used to judge the symmetry of the brightness distribution. If the skewness is close to zero, it means that the surface finish is uniform.

[0088] If the finish is lower than the preset threshold, it means that there are still local rough areas or grinding residues on the surface of the phosphor bronze ball, and polishing needs to be continued.

[0089] When the test results show that the surface roughness of the phosphor bronze ball is high or the finish is low, the system automatically adjusts the polishing parameters, including: Adjust the fineness of the abrasive sand. If the surface roughness is high, increase the proportion of fine abrasive sand to improve surface smoothness.

[0090] Optimize the ratio of brightener to activator. If the finish is uneven, adjust the concentration of brightener to improve the uniformity of surface light reflection.

[0091] Extend the polishing time. If the finish does not meet the standard, increase the polishing time appropriately to ensure that the surface of all phosphor bronze balls evenly meets the polishing requirements.

[0092] Optimize the polishing barrel rotation speed. If the finish is still low, adjust the polishing barrel rotation mode to make the phosphor bronze balls roll more evenly in the barrel to improve grinding uniformity.

[0093] When the test results show that the roughness of the phosphor bronze ball is lower than the preset threshold and the finish uniformity is higher than the set standard, the system determines that the polishing of the phosphor bronze ball is completed and records its test results.

[0094] In this step, the surface roughness of the phosphor bronze ball is calculated through the grayscale co-occurrence matrix, and the uniformity of the finish is analyzed by combining the brightness histogram. A high-precision polishing detection system is constructed, and the polishing parameters are adjusted through intelligent feedback to ensure that the surface quality of the phosphor bronze ball is uniform, optimize the polishing production process, and improve the overall production efficiency and quality stability.

[0095] In another embodiment, the present invention further provides a phosphor bronze ball production polishing detection model construction system, comprising: A data acquisition module is used to obtain an optical image of the phosphor bronze ball on the top of the polishing barrel using an industrial camera, and to obtain a spectral image of the top of the polishing barrel using a short-wave infrared hyperspectral camera; The calibration module is used to align the optical image and the spectral image in space so that the two can be analyzed in the same coordinate system; the first position of the phosphor bronze ball in the spectral image is determined by the target detection algorithm, and the corresponding second position of the phosphor bronze ball in the optical image is calculated based on the coordinate mapping model of the optical image to ensure the consistency of the same phosphor bronze ball in the two data channels; a first judgment module, configured to calculate the roundness of the phosphor bronze ball at the second position by using an ellipse fitting algorithm, and judge the geometric integrity of the phosphor bronze ball based on a roundness threshold, and when the roundness of the phosphor bronze ball does not meet the standard, adjust the polishing parameters and continue grinding; The second judgment module is used to calculate the roughness index of the surface of the phosphor bronze ball at the second position by using the grayscale co-occurrence matrix analysis method to evaluate whether the polishing is uniform; calculate the smoothness uniformity of the phosphor bronze ball by using the brightness histogram analysis method to determine whether it meets the polishing standard; when the smoothness of the phosphor bronze ball is lower than the preset threshold, adjust the polishing parameters and continue polishing, otherwise stop polishing and output the detection result.

[0096] In a further embodiment, spatial alignment of the optical image and the spectral image is achieved by the following modules: The intrinsic parameter calibration module is used to perform camera intrinsic parameter calibration. It uses a chessboard or calibration plate to calibrate the intrinsic parameter matrices of the optical camera and spectral camera, including focal length, principal point coordinates, and lens distortion coefficient. The external parameter calibration module is used to perform camera external parameter calibration to determine the relative position relationship between the optical camera and the spectral camera, that is, the rotation matrix and translation vector, which are used to describe the coordinate transformation of the two cameras and calculate the homography matrix between the cameras; The spatial position matching module is used to convert the pixel points in the spectral image into the coordinate system of the optical image using the calculated rotation matrix and translation vector to ensure that the spatial positions of the two match; The remapping module is used to calculate the corresponding position of each pixel in the spectral image in the optical image by using the projection transformation matrix through homography transformation and perform remapping.

[0097] In a further embodiment, the gray level co-occurrence matrix analysis method is used to calculate the roughness index of the phosphor bronze ball surface through the following modules: The image preprocessing module is used to perform grayscale normalization on the optical image of the phosphor bronze ball, set a fixed pixel window, calculate the grayscale co-occurrence matrix between adjacent pixels in different directions, and quantify the surface roughness by extracting contrast, energy, uniformity, and entropy features; the grinding judgment module is used to adjust the polishing parameters and continue grinding when the calculated roughness is higher than the preset threshold, indicating that there is still slight uneven wear or grinding residue on the surface of the phosphor bronze ball.

[0098] In a further embodiment, the brightness histogram analysis method is used to calculate the smoothness uniformity of the phosphor bronze ball using the following modules: The brightness distribution evaluation module is used to count the brightness distribution of the phosphor bronze ball area in the optical image and calculate the standard deviation, kurtosis and skewness of the brightness histogram to evaluate whether the surface finish is uniform; Brightness histogram evaluation module, used for the standard deviation of the brightness histogram to reflect the discreteness of the brightness distribution. The lower the value, the more uniform the surface finish. The kurtosis indicates the concentration of the image brightness. The higher the value, the better the polishing uniformity. The skewness is used to judge the symmetry of the brightness distribution. The lower the value, the more uniform the surface finish. The smoothness evaluation module is used to indicate that if the smoothness is lower than the preset threshold, it indicates that there are still local rough areas or grinding residues on the surface of the phosphor bronze ball, and polishing needs to be continued; The polishing judgment module is used to adjust the polishing parameters and continue polishing when the detection results show that the surface roughness of the phosphor bronze ball is high or the finish is low.

[0099] It should be noted that the explanation of the aforementioned embodiment of the method for constructing a polishing detection model for phosphor bronze balls is also applicable to the device of the embodiment of the present application and will not be repeated here.

[0100] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0101] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0102] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0103] The above is only a specific implementation method of the present application. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in this application, which should be included in the protection scope of this application. The scope of protection of this application shall be based on the protection scope of the claims. For some module structures that are not particularly clear in the present invention, the contents recorded in the prior art shall prevail. The prior art mentioned in the aforementioned background technology section and the specific embodiment section of the present invention can be used as a part of the present invention to understand the meaning of some technical features or parameters.

Claims

1. A method for constructing a production polishing detection model for phosphor bronze balls, characterized in that: The method comprises the following steps: Step S10, data acquisition, using an industrial camera to obtain an optical image of the phosphor bronze ball on the top of the polishing barrel, and using a short-wave infrared hyperspectral camera to obtain a spectral image of the top of the polishing barrel; Step S20, spatially aligning the optical image and the spectral image so that the two are analyzed in the same coordinate system; determining the first position of the phosphor bronze ball in the spectral image by a target detection algorithm, and calculating the corresponding second position of the phosphor bronze ball in the optical image based on the coordinate mapping model of the optical image, to ensure the consistency of the same phosphor bronze ball in the two data channels; Step S30, using an ellipse fitting algorithm to calculate the roundness of the phosphor bronze ball at the second position, and judging the geometric integrity of the phosphor bronze ball based on a roundness threshold, and when the roundness of the phosphor bronze ball does not meet the standard, adjusting the polishing parameters and continuing the grinding; Step S40, using the grayscale co-occurrence matrix analysis method to calculate the roughness index of the surface of the phosphor bronze ball at the second position to evaluate whether the polishing is uniform; using the brightness histogram analysis method to calculate the smoothness uniformity of the phosphor bronze ball to determine whether it meets the polishing standard; when the smoothness of the phosphor bronze ball is lower than the preset threshold, adjust the polishing parameters and continue polishing, otherwise stop polishing and output the detection result.

2. The method for constructing a phosphor bronze ball production polishing detection model according to claim 1, characterized in that: The positions of the industrial camera and the short-wave infrared hyperspectral camera are relatively fixed.

3. The method for constructing a phosphor bronze ball production polishing detection model according to claim 2, characterized in that: The spatial alignment of the optical image and the spectral image comprises: Perform camera internal parameter calibration, using a chessboard or calibration plate to calibrate the internal parameter matrices of the optical camera and spectral camera, including focal length, principal point coordinates, and lens distortion coefficients; Perform camera extrinsic calibration to determine the relative position relationship between the optical camera and the spectral camera, that is, the rotation matrix and translation vector, which are used to describe the coordinate transformation of the two cameras and calculate the homography matrix between the cameras; The calculated rotation matrix and translation vector are used to transform the pixels in the spectral image into the coordinate system of the optical image to ensure that the spatial positions of the two match. Then, through homography transformation, the corresponding position of each pixel in the spectral image in the optical image is calculated using the projection transformation matrix and remapped.

4. The method for constructing a phosphor bronze ball production polishing detection model according to claim 1, characterized in that: The gray level co-occurrence matrix analysis method is used to calculate the roughness index of the phosphor bronze ball surface, including: The optical image of the phosphor bronze ball is grayscale normalized, a fixed pixel window is set, the grayscale co-occurrence matrix between adjacent pixels is calculated in different directions, and the surface roughness is quantified by extracting contrast, energy, uniformity, and entropy features; The contrast value reflects the change in surface height. The larger the value, the higher the surface roughness. The energy and uniformity indexes reflect the consistency of the surface texture, with higher values ​​indicating more uniform polishing; When the calculated roughness is higher than the preset threshold, it indicates that there is still slight uneven wear or grinding residue on the surface of the phosphor bronze ball. At this time, the polishing parameters are adjusted and grinding is continued.

5. The method for constructing a production polishing detection model for phosphor bronze balls according to claim 1, characterized in that: The brightness histogram analysis method is used to calculate the finish uniformity of phosphor bronze balls, including: The brightness distribution of the phosphor bronze ball area in the optical image is counted, and the standard deviation, kurtosis and skewness of the brightness histogram are calculated to evaluate whether the surface finish is uniform; The standard deviation of the brightness histogram reflects the degree of dispersion of the brightness distribution. The lower the value, the more uniform the surface finish. The kurtosis indicates the concentration of the image brightness. The higher the value, the better the polishing uniformity. The skewness is used to judge the symmetry of the brightness distribution. The lower the value, the more uniform the surface finish. If the finish is lower than the preset threshold, it means that there are still local rough areas or grinding residues on the surface of the phosphor bronze ball, and polishing needs to be continued; When the test results show that the surface roughness of the phosphor bronze ball is high or the finish is low, the polishing parameters are adjusted to continue polishing.

6. A phosphor bronze ball production polishing detection model construction system, characterized in that: The system includes the following modules: A data acquisition module is used to obtain an optical image of the phosphor bronze ball on the top of the polishing barrel using an industrial camera, and to obtain a spectral image of the top of the polishing barrel using a short-wave infrared hyperspectral camera; The calibration module is used to align the optical image and the spectral image in space so that the two can be analyzed in the same coordinate system; the first position of the phosphor bronze ball in the spectral image is determined by the target detection algorithm, and the corresponding second position of the phosphor bronze ball in the optical image is calculated based on the coordinate mapping model of the optical image to ensure the consistency of the same phosphor bronze ball in the two data channels; a first judgment module, configured to calculate the roundness of the phosphor bronze ball at the second position by using an ellipse fitting algorithm, and judge the geometric integrity of the phosphor bronze ball based on a roundness threshold, and when the roundness of the phosphor bronze ball does not meet the standard, adjust the polishing parameters and continue grinding; The second judgment module is used to calculate the roughness index of the surface of the phosphor bronze ball at the second position by using the grayscale co-occurrence matrix analysis method to evaluate whether the polishing is uniform; calculate the smoothness uniformity of the phosphor bronze ball by using the brightness histogram analysis method to determine whether it meets the polishing standard; when the smoothness of the phosphor bronze ball is lower than the preset threshold, adjust the polishing parameters and continue polishing, otherwise stop polishing and output the detection result.

7. The phosphor bronze ball production polishing detection model construction system according to claim 6, characterized in that: The positions of the industrial camera and the short-wave infrared hyperspectral camera are relatively fixed.

8. The phosphor bronze ball production polishing detection model construction system according to claim 7, characterized in that: The spatial alignment of the optical image and the spectral image is achieved by the following modules: The intrinsic parameter calibration module is used to perform camera intrinsic parameter calibration. It uses a chessboard or calibration plate to calibrate the intrinsic parameter matrices of the optical camera and spectral camera, including focal length, principal point coordinates, and lens distortion coefficient. The external parameter calibration module is used to perform camera external parameter calibration to determine the relative position relationship between the optical camera and the spectral camera, that is, the rotation matrix and translation vector, which are used to describe the coordinate transformation of the two cameras and calculate the homography matrix between the cameras; The spatial position matching module is used to convert the pixel points in the spectral image into the coordinate system of the optical image using the calculated rotation matrix and translation vector to ensure that the spatial positions of the two match; The remapping module is used to calculate the corresponding position of each pixel in the spectral image in the optical image by using the projection transformation matrix through homography transformation and perform remapping.

9. The phosphor bronze ball production polishing detection model construction system according to claim 6, characterized in that: The gray level co-occurrence matrix analysis method is used to calculate the roughness index of the phosphor bronze ball surface through the following modules: The image preprocessing module is used to perform grayscale normalization on the optical image of the phosphor bronze ball, set a fixed pixel window, calculate the grayscale co-occurrence matrix between adjacent pixels in different directions, and quantify the surface roughness by extracting contrast, energy, uniformity, and entropy features; The grinding judgment module is used to adjust the polishing parameters and continue grinding when the calculated roughness is higher than the preset threshold, indicating that there is still slight uneven wear or grinding residue on the surface of the phosphor bronze ball.

10. The phosphor bronze ball production polishing detection model construction system according to claim 6, characterized in that: The brightness histogram analysis method is used to calculate the smoothness uniformity of phosphor bronze balls using the following modules: The brightness distribution evaluation module is used to count the brightness distribution of the phosphor bronze ball area in the optical image and calculate the standard deviation, kurtosis and skewness of the brightness histogram to evaluate whether the surface finish is uniform; Brightness histogram evaluation module, used for the standard deviation of the brightness histogram to reflect the discreteness of the brightness distribution. The lower the value, the more uniform the surface finish. The kurtosis indicates the concentration of the image brightness. The higher the value, the better the polishing uniformity. The skewness is used to judge the symmetry of the brightness distribution. The lower the value, the more uniform the surface finish. The smoothness evaluation module is used to indicate that if the smoothness is lower than the preset threshold, it indicates that there are still local rough areas or grinding residues on the surface of the phosphor bronze ball, and polishing needs to be continued; The polishing judgment module is used to adjust the polishing parameters and continue polishing when the detection results show that the surface roughness of the phosphor bronze ball is high or the finish is low.

Images