Planetary gearbox installation error detection method, device and equipment and storage medium

Abstract

The invention provides a planetary gearbox installation error detection method, device and equipment and a storage medium, and the method comprises the steps: collecting a target image of a planetary gearbox through an image sensor, carrying out the edge detection of the target image, and extracting gear contour coordinate points, according to the gear contour coordinate points, the center of a sun gear and the center of each planet gear are calculated through least square fitting; according to the center of the sun gear and the center of each planet gear, calculating an actual included angle between the centers of the adjacent planet gears, and comparing the actual included angle with a theoretical included angle to obtain an eccentric angle; calculating tangential eccentricity and longitudinal eccentricity according to the circle center of the sun gear, the circle center of each planet gear and the eccentric angle; the total eccentricity is calculated according to the tangential eccentricity and the longitudinal eccentricity, and the eccentric angle, the tangential eccentricity, the longitudinal eccentricity and the total eccentricity serve as installation error detection results. According to the invention, rapid and non-contact planetary gearbox installation error detection is realized, and a plurality of key parameters such as an eccentric angle and an eccentric amount can be quantified at the same time.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, device, and storage medium for detecting installation errors in planetary gearboxes. Background Technology

[0002] Planetary gear transmission systems are widely used in automotive transmissions, wind turbine gearboxes, and other equipment. Their installation accuracy directly affects transmission smoothness and service life. Installation errors in planetary gearboxes mainly include eccentricity angle errors and eccentricity errors in the planetary gears. These errors can lead to uneven gear meshing, increased vibration and noise, and accelerated tooth surface wear. Therefore, accurate detection of installation errors in planetary gearboxes is of great significance.

[0003] Currently, the detection methods for planetary gearbox installation errors mainly rely on contact-based testing equipment such as coordinate measuring machines (CMMs) or dedicated planetary gear testing instruments. These methods typically use contact probes to measure the position and orientation of the planetary gears point by point, and assess installation errors through multiple measurements and data processing. Although contact-based testing methods offer high accuracy, the process is time-consuming due to the need for multiple contact measurements, probe movements, and data acquisition. The testing time for a single gearbox often takes tens of minutes or even longer, resulting in extremely low efficiency. This makes it unsuitable for the high-volume, fast-paced production demands of modern manufacturing, severely hindering the improvement of production efficiency. Summary of the Invention

[0004] The main objective of this invention is to solve the technical problems of slow detection speed and low efficiency in existing planetary gearbox installation error detection methods; This invention provides a method for detecting installation errors in planetary gearboxes, the method comprising: Calculate the oil film pressure and oil film thickness in the gear meshing area based on the operating parameters of the gear transmission system. Calculate the meshing stiffness and meshing damping of the gear pair based on the oil film pressure and oil film thickness. Based on the meshing stiffness and meshing damping, a dynamic model of the bending-torsional coupling vibration of the gear transmission system is established and calculated and analyzed to obtain the vibration analysis results of the gear transmission system.

[0005] The present invention also provides a planetary gearbox installation error detection device, the planetary gearbox installation error detection device comprising: The oil film calculation module is used to calculate the oil film pressure and oil film thickness in the gear meshing area based on the operating parameters of the gear transmission system. The stiffness and resistance calculation module is used to calculate the meshing stiffness and meshing damping of the gear pair based on the oil film pressure and oil film thickness. The vibration analysis module is used to establish and solve the bending-torsional coupling vibration dynamic model of the gear transmission system based on the meshing stiffness and meshing damping, and obtain the vibration analysis results of the gear transmission system.

[0006] The present invention also provides a planetary gearbox installation error detection device, comprising: a memory and at least one processor, wherein the memory stores instructions, and the memory and the at least one processor are interconnected by a circuit; the at least one processor invokes the instructions in the memory to cause the planetary gearbox installation error detection device to perform the steps of the planetary gearbox installation error detection method described above.

[0007] The present invention also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the steps of the planetary gearbox installation error detection method described above.

[0008] The aforementioned method, apparatus, equipment, and storage medium for detecting installation errors in planetary gearboxes acquire a target image of the planetary gearbox using an image sensor. Edge detection is performed on the target image to extract gear contour coordinate points. Based on these coordinate points, the center of the sun gear and the centers of each planet gear are calculated using the least squares method. The actual angle between the centers of adjacent planet gears is calculated based on the sun gear center and the centers of each planet gear. This actual angle is compared with the theoretical angle to obtain the eccentricity angle. The tangential eccentricity and longitudinal eccentricity are calculated based on the sun gear center, the centers of each planet gear, and the eccentricity angle. The total eccentricity is calculated based on the tangential and longitudinal eccentricities, and the eccentricity angle, tangential eccentricity, longitudinal eccentricity, and total eccentricity are used as the installation error detection results. This invention achieves rapid, non-contact detection of planetary gearbox installation errors and can simultaneously quantify multiple key parameters such as eccentricity angle and eccentricity.

[0009] Beneficial effects: By acquiring target images of the planetary gearbox through an image sensor and extracting gear contour coordinates through edge detection, the center of the sun gear and the centers of each planet gear are calculated using the least squares method. Then, based on the center positions, the deviation between the actual and theoretical angles between the centers of adjacent planet gears is calculated to obtain the eccentricity angle. Combining the center coordinates and the eccentricity angle, the tangential eccentricity, longitudinal eccentricity, and total eccentricity are calculated, thus realizing a non-contact detection method based on image processing. This avoids the cumbersome process of multiple contact measurements, probe movement, and data acquisition required by traditional contact detection equipment, significantly shortening the detection time and improving detection efficiency. At the same time, this invention can obtain complete information about the planetary gearbox with a single image acquisition and simultaneously obtain multiple key parameters such as eccentricity angle, tangential eccentricity, longitudinal eccentricity, and total eccentricity through calculation, providing comprehensive data support for the installation quality assessment of the planetary gearbox.

[0010] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0011] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0012] Figure 1 This is a schematic diagram of the first embodiment of the planetary gearbox installation error detection method in this invention; Figure 2 This is a schematic diagram of a second embodiment of the planetary gearbox installation error detection method in this invention; Figure 3 This is a schematic diagram of one embodiment of the planetary gearbox installation error detection device according to the present invention; Figure 4 This is a schematic diagram of one embodiment of the planetary gearbox installation error detection device according to the present invention; Figure 5 This is a schematic diagram of the planetary gearbox in an embodiment of the present invention; Figure 6 This is a schematic diagram illustrating the geometric relationship between the center of the sun gear and the centers of each planet gear in an embodiment of the present invention; Figure 7 This is a schematic diagram illustrating the effect of binarizing the target image in an embodiment of the present invention. Detailed Implementation To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0013] The terms "comprising" and "having," and any variations thereof, used in the embodiments of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0014] To facilitate understanding of this embodiment, a method for detecting installation errors in a planetary gearbox, as disclosed in this embodiment of the invention, will first be described in detail. For example... Figure 1 As shown, this method includes the following steps: 101. Acquire a target image of the planetary gearbox using an image sensor, perform edge detection on the target image, extract gear contour coordinate points, and calculate the center of the sun gear and the centers of each planet gear of the planetary gearbox using the least squares method based on the gear contour coordinate points. In this embodiment, the step of acquiring a target image of the planetary gearbox using an image sensor, performing edge detection on the target image, and extracting gear contour coordinate points includes: acquiring a target image of the planetary gearbox using an image sensor, performing sub-pixel edge detection on the target image to obtain edge pixels; and performing contour tracking on the edge pixels to obtain the contour coordinate points of each gear.

[0015] Specifically, after the planetary gearbox is assembled, an image acquisition device can be used to photograph the planetary gearbox and obtain a target image of the planetary gearbox, such as... Figure 5 As shown, the planetary gearbox mainly consists of a sun gear S at the center, three planet gears P evenly distributed around the sun gear, and an outermost internal gear ring. The image acquisition device can be an industrial camera, digital camera, or other device with image acquisition capabilities. To ensure the accuracy of subsequent inspection, when acquiring the target image, it is necessary to ensure that the optical axis of the image acquisition device is perpendicular to the axis of the planetary gearbox and maintain an appropriate shooting distance so that the visible parts of the sun gear, each planet gear, and the internal gear ring are fully included in the target image. Furthermore, sufficient and uniform lighting conditions are required to avoid image quality degradation due to uneven illumination.

[0016] After acquiring the target image, edge detection processing is required to extract the contour information of each gear. Traditional edge detection methods, such as the Sobel operator and the Canny operator, can detect edge positions, but their detection accuracy is usually only at the pixel level. Considering the high accuracy requirements for planetary gearbox installation error detection, this embodiment uses sub-pixel edge detection technology to process the target image.

[0017] Subpixel edge detection is an edge detection technique that achieves subpixel-level positioning accuracy. Its basic principle is to obtain a more precise edge location by interpolating and fitting the grayscale distribution of pixels near the edge, building upon pixel-level edge detection. In practice, the target image can first be preprocessed, including grayscale conversion and noise filtering. Grayscale conversion converts a color image to grayscale, simplifying subsequent processing; noise filtering can employ methods such as Gaussian filtering and median filtering to remove noise interference from the image.

[0018] After preprocessing, subpixel edge detection algorithms, such as the gray-scale moment method, the Zernike moment method, or curve fitting method, can be used to detect the edges of the gear in the target image. Taking the gray-scale moment method as an example, this method determines the subpixel position of the edge by calculating the first and zeroth moments of the gray-scale values ​​of pixels near the edge. Through subpixel edge detection, the edge pixels distributed in the target image can be obtained. These edge pixels correspond to the positional information of features such as gear tooth profiles and inner hole edges. Its positioning accuracy can reach the subpixel level, typically achieving an accuracy of a few tenths of a pixel.

[0019] After obtaining the edge pixels, contour tracking is required to form a continuous gear contour. Contour tracking is a common technique in image processing, aiming to connect edge pixels belonging to the same contour in a certain order to form a complete contour curve. In this embodiment, a neighborhood search-based contour tracking algorithm can be used. The specific steps include: first, selecting a starting point among the edge pixels; then, searching for the next edge pixel within the neighborhood of that starting point and using it as the next point of the contour; repeating the above search process until returning to the starting point or no next edge pixel can be found, thus completing the tracking of a complete contour. For all edge pixels in the target image, repeating the above contour tracking process can extract multiple contour curves.

[0020] In the target image of the planetary gearbox, these contour curves correspond to the inner and outer contours of the sun gear, the inner and outer contours of each planet gear, and the contour of the internal gear ring, respectively. Through contour tracking processing, the contour coordinate points of each gear can be obtained. These contour coordinate points are arranged in a continuous sequence according to the contours. Each coordinate point contains its x-coordinate and y-coordinate information in the image coordinate system, which can be represented in the form (xi, yi), where i is the coordinate point number. These contour coordinate points provide the basic data for subsequent circle center fitting calculations.

[0021] Specifically, after obtaining the contour coordinates of each gear, the center of the sun gear and the centers of each planet gear in the planetary gearbox need to be calculated using the least squares method based on these contour coordinates. Since the target image contains the contour information of the sun gear, multiple planet gears, and the internal gear ring, it is necessary to first classify the contour coordinates and extract the contour coordinates belonging to different gears.

[0022] In practice, contour coordinate points can be classified based on their spatial relationships and geometric features. For example, the center position and area enclosed by each contour can be calculated. Based on the distance between the contour centers and the differences in contour area, the contours can be divided into sun gear contours, planet gear contours, and internal gear contours. Generally, the sun gear is located in the central region of the image, the planet gears are distributed around the sun gear, and the internal gear is located on the outermost layer. In this way, the contour coordinate points belonging to the sun gear and the contour coordinate points belonging to each planet gear can be extracted separately.

[0023] After completing the contour classification, the least squares method can be used to perform circle fitting on the contour coordinate points of each gear to calculate the center coordinates of each gear. The least squares method is a commonly used curve fitting method. Its basic idea is to determine the parameters of the fitted curve by minimizing the sum of squared deviations between the fitted curve and the actual data points. For circle fitting problems, the least squares method can calculate the center position and radius of the circle that best fits a set of discrete contour coordinate points.

[0024] Specifically, for the contour coordinates of the sun gear, the coordinates of its center can be obtained by processing them using a least-squares circle fitting algorithm. For the contour coordinates of each planet gear, the coordinates of its center can be obtained by performing least-squares circle fitting on each planet gear. In practical applications, least-squares circle fitting can be implemented using algebraic fitting or geometric fitting methods. Both methods can solve for the optimal center position through iterative calculations. Through the above fitting calculations, the precise positional information of the sun gear center and the centers of each planet gear can be obtained. These center coordinates provide crucial data for subsequent installation error calculations.

[0025] 102. Based on the center of the sun gear and the centers of each planet gear, calculate the actual angle between the centers of adjacent planet gears, and compare the actual angle with the theoretical angle to obtain the eccentricity angle; In this embodiment, after obtaining the coordinate information of the center of the sun gear and the centers of each planet gear, it is necessary to calculate the actual included angle between the centers of adjacent planet gears based on the positions of these centers, and compare the actual included angle with the theoretical included angle to obtain the eccentricity angle.

[0026] Specifically, in a standard planetary gearbox design, the planet gears are typically evenly distributed around the sun gear. For a planet gear set with Z planet gears... 行 In a planetary gearbox, the theoretical angle between the center of two adjacent planetary gears and the center of the sun gear should be 2π / Z. 行Taking a common three-planetary gear structure as an example, the theoretical included angle is 120 degrees. However, in the actual assembly process, due to assembly errors, the actual installation position of each planetary gear often deviates from the theoretical position, resulting in a deviation between the actual included angle and the theoretical included angle between adjacent planetary gears. This deviation is called the eccentricity angle. To calculate the actual angle between the centers of adjacent planetary gears, the law of cosines can be used, such as... Figure 6 As shown, for the i-th planetary gear Pi and the (i+1)-th planetary gear, a triangle can be constructed consisting of the center of the sun gear, the center of the i-th planetary gear, and the center of the (i+1)-th planetary gear. ε in the diagram represents the eccentricity angle. Specifically, for the i-th planetary gear and the (i+1)-th planetary gear, a triangle can be constructed consisting of the center of the sun gear, the center of the i-th planetary gear, and the center of the (i+1)-th planetary gear. Given the coordinates of the three vertices in this triangle, the lengths of the three sides can be calculated, and then the actual included angle between the centers of adjacent planetary gears can be determined using the law of cosines.

[0027] According to the law of cosines, the angle between the centers of adjacent planetary gears can be calculated using the following formula: ; Where ε is the eccentricity angle, i.e. the deviation between the actual included angle and the theoretical included angle; Ai represents the distance from the center of the i-th planetary gear to the center of the sun gear; Ai+1 represents the distance from the center of the (i+1)-th planetary gear to the center of the sun gear; Bi represents the distance between the centers of the i-th planetary gear and the (i+1)-th planetary gear. , Let x and y be the x and y coordinates of the center of the i-th planetary gear, respectively. , These are the x and y coordinates of the center of the (i+1)th planetary gear, respectively. , These are the x-coordinate and y-coordinate of the center of the sun wheel, respectively.

[0028] 103. Calculate the tangential eccentricity and longitudinal eccentricity based on the center of the sun gear, the centers of each planet gear, and the eccentricity angle. In this embodiment, calculating the tangential eccentricity and longitudinal eccentricity based on the center of the sun gear, the centers of each planet gear, and the eccentricity angle includes: calculating the tangential eccentricity based on the theoretical center distance from the center of the planet gear to the center of the sun gear and the eccentricity angle; and calculating the longitudinal eccentricity based on the theoretical center distance and the actual distance between the center of the sun gear and the centers of each planet gear.

[0029] Specifically, after obtaining the eccentricity angle, it is necessary to further calculate the tangential eccentricity and longitudinal eccentricity to comprehensively evaluate the installation error of the planetary gears. The tangential eccentricity reflects the positional deviation of the planetary gears in the tangential direction, while the longitudinal eccentricity reflects the positional deviation of the planetary gears in the longitudinal direction. These two parameters together describe the degree of deviation between the actual and theoretical installation positions of the planetary gears.

[0030] First, calculate the tangential eccentricity. Tangential eccentricity is the positional offset of the planetary gears in the tangential direction caused by the eccentricity angle. Ideally, the planetary gears should be evenly distributed around the sun gear, and the distance from the center of each planetary gear to the center of the sun gear should equal the theoretical center distance. This theoretical center distance can be calculated based on the basic parameters of the sun gear and planetary gears. Specifically, the theoretical center distance equals the product of the module and number of teeth of the sun gear plus the product of the module and number of teeth of the planetary gears, divided by two. When there is an angular deviation in the actual installation position of the planetary gears, i.e., when the eccentricity angle is not zero, a positional offset will occur in the tangential direction.

[0031] Based on geometric relationships, the tangential eccentricity can be obtained by multiplying the theoretical center distance by the sine of the eccentricity angle. The formula for calculating the tangential eccentricity is: ; in, For tangential eccentricity; The module of the sun gear; The number of teeth on the sun gear; The module of the planetary gear; ε represents the number of teeth on the planetary gears; ε is the eccentricity angle. The above formula represents the theoretical center distance from the center of the planetary gear to the center of the sun gear. This formula can be used to calculate the tangential eccentricity of each planetary gear, which reflects the degree to which the planetary gear deviates from its theoretical position along the circumferential tangential direction.

[0032] Next, we calculate the longitudinal eccentricity. Longitudinal eccentricity is the difference between the actual distance from the center of the planetary gear to the center of the sun gear and the theoretical center distance, reflecting the positional deviation of the planetary gear in the longitudinal direction. To calculate the longitudinal eccentricity, we first need to calculate the actual distance from the center of the planetary gear to the center of the sun gear. This actual distance can be directly calculated from the coordinates of the sun gear center and the planetary gear center; specifically, it can be calculated using the formula for the distance between two points.

[0033] For the i-th planetary gear, the actual distance from its center to the center of the sun gear is the square root of the difference between the x-coordinate of the i-th planetary gear center and the x-coordinate of the sun gear center, plus the square root of the difference between the y-coordinate of the i-th planetary gear center and the y-coordinate of the sun gear center. After obtaining the actual distance, subtracting the actual distance from the theoretical center distance yields the longitudinal eccentricity. The formula for calculating longitudinal eccentricity is: ; in, This represents the radial eccentricity; the meanings of the other symbols are the same as in the formula for tangential eccentricity and the angle between the centers of adjacent planetary gears. The expression within the square root calculates the actual distance from the center of the planetary gear to the center of the sun gear. Subtracting this actual distance from the theoretical center distance gives the radial eccentricity. If the radial eccentricity is positive, it means the actual distance is less than the theoretical center distance, and the planetary gears are offset towards the sun gear; if the radial eccentricity is negative, it means the actual distance is greater than the theoretical center distance, and the planetary gears are offset outwards. It should be noted that tangential eccentricity and radial eccentricity describe the installation error of the planetary gears from different directions. Tangential eccentricity is mainly caused by angular deviation and reflects the positional offset of the planetary gears in the circumferential direction; radial eccentricity reflects the deviation in distance between the planetary gears and the sun gear. In practical applications, these two parameters can be analyzed independently or comprehensively evaluated to assess the overall installation quality of the planetary gearbox. By calculating the tangential and radial eccentricities of each planetary gear separately, the installation error of each planetary gear can be accurately located.

[0034] 104. Calculate the total eccentricity based on the tangential eccentricity and the longitudinal eccentricity, and use the eccentricity angle, tangential eccentricity, longitudinal eccentricity and total eccentricity as the installation error detection results of the planetary gearbox.

[0035] In this embodiment, calculating the total eccentricity based on the tangential eccentricity and the longitudinal eccentricity includes: squaring the tangential eccentricity and the longitudinal eccentricity respectively to obtain the squared value of the tangential eccentricity and the squared value of the longitudinal eccentricity; summing the squared value of the tangential eccentricity and the squared value of the longitudinal eccentricity to obtain the summation result; and taking the square root of the summation result to obtain the total eccentricity.

[0036] Specifically, after calculating the tangential and radial eccentricities separately, it is necessary to further calculate the total eccentricity to comprehensively evaluate the overall installation error of the planetary gears. Since the tangential and radial eccentricities reflect the positional deviations of the planetary gears in two mutually perpendicular directions, the total eccentricity can be calculated using a vector synthesis method, that is, by using the Pythagorean theorem to combine the tangential and radial eccentricities into a comprehensive eccentricity index.

[0037] The calculation of total eccentricity follows the basic principle of vector composition. In a Cartesian coordinate system, tangential eccentricity can be considered as a component along the tangent direction, and radial eccentricity can be considered as a component along the radial direction; these two directions are perpendicular to each other. According to the principle of vector composition, the length of the composite vector of two perpendicular components is equal to the square root of the sum of the squares of their components. Therefore, the calculation of total eccentricity requires first squaring both the tangential and radial eccentricities, then adding the two squared values, and finally taking the square root of the sum.

[0038] First, the tangential eccentricity is squared to obtain its squared value. This squared value reflects the contribution of the tangential eccentricity to the total eccentricity. Similarly, the radial eccentricity is squared to obtain its squared value. By squaring, the influence of the sign of the eccentricity can be eliminated, ensuring that deviations in different directions can participate in subsequent calculations as positive values.

[0039] Next, the squared values ​​of the tangential and radial eccentricities are summed to obtain the summation result. This summation result represents the combined effect of the deviations in both the tangential and radial directions. Because a sum of squares is used, larger deviations will have a more significant impact on the total eccentricity, which aligns with the practical engineering need to pay more attention to larger errors.

[0040] Finally, the total eccentricity is obtained by taking the square root of the summation result. The formula for calculating the total eccentricity is: ; The magnitude of the total eccentricity comprehensively reflects the positional deviation of the planetary gears in both the tangential and radial directions. The total eccentricity calculated by this formula is a scalar value; the larger the value, the farther the actual installation position of the planetary gears deviates from the theoretical position, and the greater the installation error. After calculating the total eccentricity, the four parameters—eccentricity angle, tangential eccentricity, radial eccentricity, and total eccentricity—can be used together as the output of the planetary gearbox's installation error detection result. Specifically, the eccentricity angle reflects the deviation in the angular distribution of the planetary gears; the tangential eccentricity reflects the tangential positional offset caused by the angular deviation; the radial eccentricity reflects the deviation in the distance between the planetary gears and the sun gear; and the total eccentricity comprehensively reflects the overall positional deviation of the planetary gears. These four parameters comprehensively describe the installation error status of the planetary gearbox from different perspectives.

[0041] In practical applications, these test results can be used to evaluate the installation quality of planetary gearboxes. For example, various parameters can be compared with preset allowable error ranges to determine whether the installation error is within acceptable limits. If the total eccentricity of a planetary gear exceeds the allowable value, it indicates a significant deviation in the installation of that planetary gear, requiring adjustment or reinstallation. By detecting and analyzing the installation error of each planetary gear, installation problems can be identified promptly, providing a basis for assembly quality control and preventing issues such as poor gear meshing, increased vibration and noise, and reduced service life caused by installation errors.

[0042] Furthermore, this embodiment achieves non-contact detection of planetary gearbox installation errors through image acquisition and digital image processing technology. Compared with traditional contact detection methods, it has advantages such as fast detection speed, high efficiency, and no need for multiple contact measurements. The entire detection process only requires acquiring one target image. Through image processing steps such as edge detection, contour extraction, and circle center fitting, various installation error parameters can be quickly calculated, meeting the needs of modern manufacturing for high-efficiency and high-precision detection. This provides an effective technical means for the mass production and quality control of planetary gearboxes.

[0043] In this embodiment, the target image of the planetary gearbox is acquired using an image sensor, and edge detection is performed to extract the coordinate points of the gear contour. The center of the sun gear and the centers of each planet gear are calculated using the least squares method. Then, the deviation between the actual and theoretical angles between the centers of adjacent planet gears is calculated based on the center positions to obtain the eccentricity angle. The tangential eccentricity, longitudinal eccentricity, and total eccentricity are calculated by combining the center coordinates and the eccentricity angle. This achieves a non-contact detection method based on image processing, avoiding the cumbersome process of multiple contact measurements, probe movement, and data acquisition required by traditional contact detection equipment. This significantly shortens the detection time and improves the detection efficiency. At the same time, this invention can obtain complete information about the planetary gearbox with a single image acquisition and simultaneously obtain multiple key parameters such as eccentricity angle, tangential eccentricity, longitudinal eccentricity, and total eccentricity through calculation, providing comprehensive data support for the installation quality assessment of the planetary gearbox.

[0044] Please see Figure 2 Another embodiment of the planetary gearbox installation error detection method in this application includes: 201. Acquire a target image of the planetary gearbox using an image sensor, perform edge detection on the target image, and extract the gear contour coordinate points; In this embodiment, the planetary gearbox is first imaged using an image acquisition device to obtain a target image of the planetary gearbox. When acquiring the target image, it is essential to ensure that the optical axis of the image acquisition device is perpendicular to the axis of the planetary gearbox, and to maintain an appropriate shooting distance and sufficient, uniform lighting conditions. After acquiring the target image, edge detection processing is performed to extract the contour information of each gear.

[0045] This embodiment employs subpixel edge detection technology to process the target image. Specifically, the target image is first converted to grayscale, transforming a color image into a grayscale image. Then, Gaussian filtering or median filtering is used to filter noise and remove interference. After preprocessing, Canny or Sobel operators are used for pixel-level edge detection to initially locate the edge positions. Based on pixel-level edge detection, subpixel edge detection algorithms, such as grayscale moment methods, Zernike moment methods, or curve fitting methods, are further employed to precisely locate the edge positions, achieving subpixel-level edge localization accuracy.

[0046] Subpixel edge detection identifies the distributed edge pixels in the target image. These edge pixels correspond to the positional information of features such as gear tooth profiles and inner hole edges. After obtaining the edge pixels, contour tracking is performed on these discretely distributed edge pixels to connect edge pixels belonging to the same contour in a certain order, forming a complete contour curve. Contour tracking can be implemented using a neighborhood search-based algorithm, starting from a starting point and searching for the next edge pixel within its neighborhood, connecting them sequentially until a closed contour is formed or no further edge pixels can be found. Through contour tracking, the contour coordinates of each gear can be extracted, and these coordinates are arranged in a continuous sequence according to the contour.

[0047] 202. The coarse center coordinates of all the gear profile coordinate points are calculated using the superposition averaging method; In this embodiment, after extracting the contour coordinates of each gear, it is necessary to first calculate the coarse center coordinates of the entire planetary gear train. This coarse center serves as a reference for subsequent processing, used to classify and filter the contour coordinates of different gears. The coarse center is calculated using the superposition averaging method, which is simple and efficient, and can quickly obtain the geometric center position of the contour coordinates.

[0048] The basic principle of the superposition averaging method is to sum the coordinate values ​​of all profile coordinate points in both the horizontal and vertical directions, and then divide by the total number of profile coordinate points to obtain the average position of all coordinate points. Since the profile coordinate points of the sun gear, planet gears, and internal gear ring in a planetary gearbox roughly exhibit a spatial distribution characteristic centered on a certain point, the rough center obtained by the superposition averaging method can reflect the geometric center position of the entire planetary gear train quite well.

[0049] Specifically, the formula for calculating the rough coordinates of the circle's center is as follows: ; in, The x-coordinate is the approximate center of the circle; The ordinate is the approximate center of the circle; Let x be the x-coordinate of the i-th contour point; Let be the ordinate of the i-th contour coordinate point; n is the total number of contour coordinate points. In the above formula, the numerator is the sum of all contour coordinate points along the x-axis or y-axis, and the denominator is the total number of contour coordinate points. The average value, which is the coordinate of the approximate center, can be obtained by division. While the coarse center coordinates calculated using the superposition averaging method are less accurate than the precise center coordinates obtained by subsequent least-squares fitting, they are simple and fast to calculate, providing a valid reference benchmark for subsequent contour classification and sun gear data extraction. In practical applications, the coarse center is usually located near the geometric center of the planetary gear train. The distance information from each contour coordinate point to this coarse center can then be used to classify and filter the contour coordinate points, thereby extracting the contour data of the sun gear, planet gears, and internal gear ring separately.

[0050] 203. Based on the distance between the gear contour coordinate points and the rough center coordinates, a threshold is set, the inner hole contour coordinate points of the sun gear are extracted, and the sun gear center coordinates are obtained by fitting the inner hole contour coordinate points of the sun gear using the least squares method. In this embodiment, the step of setting a threshold based on the distance between the gear contour coordinate points and the coarse center coordinates, extracting the sun gear inner bore contour coordinate points, and using the least squares method to fit the sun gear inner bore contour coordinate points to obtain the sun gear center coordinates includes: calculating the distance value from each contour coordinate point to the coarse center based on the gear contour coordinate points and the coarse center coordinates; setting a threshold based on the minimum distance value among the distance values, and extracting contour coordinate points with distance values ​​less than the threshold as sun gear inner bore contour coordinate points; and using the least squares method to perform circle fitting on the sun gear inner bore contour coordinate points to obtain the sun gear center coordinates.

[0051] In this embodiment, after obtaining the rough center coordinates, the contour coordinate points need to be classified and filtered according to their distances from the rough center, thereby extracting the contour coordinate points belonging to the inner bore of the sun gear. Since the sun gear is located at the center of the planetary gearbox, its inner bore is closest to the rough center, while the outer contour of the sun gear, the contours of the planet gears, and the internal gear ring are successively farther from the rough center. Therefore, by setting a distance threshold, the contour coordinate points closer to the rough center can be extracted as the contour data of the inner bore of the sun gear.

[0052] First, the distance from each contour coordinate point to the coarse center needs to be calculated. For each contour coordinate point, the distance to the coarse center can be calculated using the distance formula between two points, based on its coordinates and the coordinates of the coarse center. To facilitate subsequent threshold filtering, a modified distance value is introduced. Specifically, the formula for calculating this distance value is: ; in, This is the corrected distance value for the i-th contour coordinate point; , These are the x and y coordinates of the i-th contour coordinate point, respectively; , Here, x and y are the x and y coordinates of the approximate center, respectively; 'a' is the correction parameter. The expression within the square root calculates the Euclidean distance from the contour coordinate point to the approximate center, and subtracts the correction parameter 'a' to obtain the corrected distance value. This correction parameter 'a' can be set according to the geometry of the sun gear, and is usually set to the theoretical value of the outer radius of the sun gear, i.e., a = ( ) / 2, where The module of the sun gear. This represents the number of teeth on the sun gear. By introducing a correction parameter 'a', the correction distance value can be adjusted. It better reflects the positional relationship of the contour coordinate points relative to the sun gear. After calculating the corrected distance values ​​for all contour coordinate points, the minimum distance value can be identified. The contour coordinate point corresponding to this minimum distance value is typically located at the edge of the sun gear's inner bore. Based on the minimum distance value, a threshold can be set to filter the contour coordinate points within the sun gear's inner bore. Specifically, the threshold can be set to a multiple of the minimum distance value. Based on practical experience and geometric relationships, the threshold can be set to 1.2 times the minimum distance value. After setting the threshold, all contour coordinate points can be traversed, and those with a correction distance value less than the threshold can be extracted and used as the contour coordinate points of the sun gear's inner hole. This filtering process can be represented by the following conditions: ; in, Indicates the coordinate points of the inner bore of the sun gear; These are the contour coordinates to be filtered; the conditions within the curly braces indicate when the distance value is adjusted. When the distance is less than 1.2 times the minimum distance value, the contour coordinate point is determined to be the contour coordinate point of the sun gear inner hole. Through the above screening process, the contour coordinate point of the sun gear inner hole can be effectively separated from all contour coordinate points. It should be noted that in practical applications, the coordinates of the outer contour of the sun gear can also be extracted simultaneously. Specifically, a second threshold can be set to extract the contour coordinates of the sun gear's outer contour where the corrected distance value falls between 1.2 times and 1.8 times the minimum distance value. in, This represents the coordinates of the outer contour of the sun gear. By setting different distance threshold ranges, the inner and outer contours of the sun gear can be extracted separately, providing a data basis for subsequent accurate center fitting. After extracting the coordinate points of the sun gear's inner bore contour, a least-squares circle fitting method needs to be applied to these coordinate points to obtain the precise center coordinates of the sun gear. Least-squares circle fitting is a commonly used data fitting method. Its basic idea is to determine the center coordinates and radius of the fitted circle by minimizing the sum of squared deviations between the fitted circle and the actual data points. For a given set of sun gear inner bore contour coordinate points, the least-squares method can solve an optimization problem to calculate the center position of the circle that best fits these coordinate points.

[0053] Specifically, least squares circle fitting can be achieved using either algebraic fitting or geometric fitting. Algebraic fitting expresses the equation of the circle in algebraic form and solves for the center and radius parameters using linear least squares. Geometric fitting directly minimizes the sum of squared geometric distances from all data points to the fitted circle and solves for the optimal parameters using an iterative optimization algorithm. Both methods can obtain precise center coordinates of the sun gear's inner bore. These precise center coordinates offer higher positioning accuracy compared to a coarse center coordinate, more accurately reflecting the actual center position of the sun gear.

[0054] 204. Perform binarization processing on the target image to extract the contour coordinates and midpoint coordinates of the white area around the inner hole of the planetary gear; In this embodiment, after obtaining the coordinates of the sun gear's center, it is necessary to further extract the contour information of each planetary gear to facilitate accurate fitting of the planetary gear centers. To extract the planetary gear contour data, this embodiment employs image binarization processing technology to process the target image. Binarization is a commonly used image segmentation technique. Its basic principle is to divide the pixels in the image into two categories—black pixels and white pixels—based on a grayscale threshold, thereby simplifying the image and extracting features.

[0055] Specifically, when binarizing a target image, the first step is to determine a suitable grayscale threshold. This threshold can be set manually based on experience or determined using an automatic threshold selection algorithm, such as the Otsu method or the maximum entropy method. After determining the threshold, each pixel in the target image is iterated through, and pixels with grayscale values ​​greater than the threshold are set to white, while pixels with grayscale values ​​less than or equal to the threshold are set to black, thus obtaining the binarized image.

[0056] In the target image of a planetary gearbox, the gears themselves typically exhibit a darker grayscale value, while the inner bore of the gears and the blank areas between the planet gears and the sun gear exhibit a brighter grayscale value. Therefore, by appropriately setting the binarization threshold, the gear area can be displayed as black in the binarized image, while the blank areas between the inner bore and the planet gears are displayed as white. This clear black-and-white binarized image facilitates subsequent region segmentation and contour extraction.

[0057] After obtaining the binarized image, it is necessary to segment and label the white regions in the image, such as... Figure 7 As shown, after binarization, the gear area appears black, while the blank area between the inner bore and the planetary gears appears white. A connected white area is formed around the inner bore of each planetary gear, consisting of the inner bore of the planetary gear, the gap between the planetary gear and the sun gear, and the gap between the planetary gear and the internal gear ring. Connected component analysis can identify and label each individual white area in the image. Connected component analysis can be implemented using seed filling algorithms or label-based connected component detection algorithms, effectively distinguishing different white areas.

[0058] For each identified white region, the coordinates of its edge contour points need to be extracted. These coordinates are located at the boundary between the white and black regions and can be obtained using a boundary tracking algorithm. By extracting the coordinates of the edge contour points of each white region, the shape information of the blank area surrounding the inner bore of the planetary gear can be obtained. In addition to extracting the contour coordinates, it is also necessary to calculate the midpoint coordinates of each white region. The midpoint coordinates can be obtained by averaging the coordinates of all pixels within the white region, or by using a superposition averaging method on the contour coordinates of the white region's edges. These midpoint coordinates can approximate the initial position of the planetary gear's center. These midpoint coordinates provide initial values ​​for subsequent fitting of the planetary gear's center using constrained least squares, helping to improve the convergence speed and accuracy of the fitting calculation.

[0059] 205. Based on the midpoint coordinates, the sun gear center coordinates, and the contour coordinates, the constrained least squares method is used to fit and obtain the center coordinates of each planetary gear; In this embodiment, the step of fitting the coordinates of the center of each planetary gear using constrained least squares method based on the midpoint coordinates, the coordinates of the sun gear center, and the contour coordinates includes: calculating the theoretical center distance from the center of the planetary gear to the center of the sun gear based on the module and number of teeth of the sun gear and the module and number of teeth of the planetary gear; calculating the radius of the inner hole of the planetary gear based on the contour coordinates of the white area; using the midpoint coordinates as the initial value, setting the distance from the center of the planetary gear to the center of the sun gear equal to the theoretical center distance as the first constraint condition, and setting the distance from the center of the planetary gear to the inner hole contour point equal to the inner hole radius of the planetary gear as the second constraint condition, and fitting the coordinates of the center of each planetary gear using constrained least squares method.

[0060] Specifically, after extracting the contour coordinates and midpoint coordinates of each white area, the center position of the planetary gear needs to be accurately fitted. Since the mounting position of the planetary gear is geometrically constrained by the gear meshing relationship, the ordinary least squares method cannot be simply used for center fitting. Instead, constrained least squares should be used to incorporate the geometric constraints of the gear meshing into the fitting calculation process, thereby improving the fitting accuracy and reliability.

[0061] First, the theoretical center distance between the centers of the planet gears and the sun gear needs to be calculated. This theoretical center distance is a geometric quantity determined by the fundamental parameters of the sun gear and planet gears. In standard gear transmissions, the center distance between the planet gears and the sun gear is equal to the sum of their pitch circle radii. For the module... Number of teeth The gear has a pitch circle radius of . Therefore, the theoretical center distance from the center of the planetary gear to the center of the sun gear can be calculated as follows: ; in, The module of the sun gear; The number of teeth on the sun gear; The module of the planetary gear; Let be the number of teeth on the planetary gear. This theoretical center distance is the geometric relationship that the planetary gear and the sun gear should satisfy when they are properly meshed, and it will serve as the first constraint condition in the constrained least squares fitting process.

[0062] Next, the radius of the planetary gear's inner bore needs to be calculated. This radius can be calculated based on the coordinates of the edge contour points of the white area. Specifically, for a given white area, the coordinates of its edge contour points contain the boundary information of the planetary gear's inner bore. Multiple distance values ​​can be obtained by calculating the distances from these edge contour coordinate points to the midpoint of the white area. Among these distance values, the set of smaller and relatively stable values ​​corresponds to the distance from the boundary of the planetary gear's inner bore to the midpoint. Statistical analysis can be performed on these distance values, such as calculating the average or median, to obtain the radius of the planetary gear's inner bore. This radius value reflects the actual size of the planetary gear's inner bore and will serve as the second constraint condition in the constrained least squares fitting process.

[0063] After determining the theoretical center distance and the inner radius of the planetary gear, a constrained least squares optimization problem can be established. Constrained least squares is an optimization method that introduces constraints into the traditional least squares method. Its goal is to minimize the deviation between the fitted circle and the actual data points while satisfying the constraints. For the fitting problem of the planetary gear center, two constraints need to be satisfied simultaneously.

[0064] The first constraint is that the distance from the center of the planetary gear to the center of the sun gear is equal to the theoretical center distance. This constraint can be expressed as: ; in, Let be the coordinates of the planetary gear center to be fitted; Here are the coordinates of the sun gear center; the expression within the square root calculates the actual distance from the planet gear center to the sun gear center, which should be close to the theoretical center distance. This constraint ensures that the fitted planet gear center positions conform to the geometry of gear meshing. The second constraint is that the distance from the planet gear center to the inner bore contour point is equal to the radius of the planet gear's inner bore. This constraint can be expressed as: ; in, These are the coordinate points of the outline of the white area's edge; Let be the radius of the planetary gear's inner bore. This constraint states that the distance from the planetary gear's center to any point on its inner bore boundary should approximate the inner bore radius; that is, the fitted circle's center should be located at the geometric center of the inner bore. This constraint allows for precise positioning of the circle's center using the shape information of the inner bore boundary.

[0065] After establishing the constraints, a constrained optimization algorithm can be used to solve the problem. In practice, the coordinates of the midpoint of the white area can be used. As initial values, an optimization objective function is constructed that includes the two constraints mentioned above. The optimization objective function typically includes a data fitting term and a constraint penalty term. The data fitting term measures the deviation between the fitted circle and the actual data points, while the constraint penalty term measures the degree to which the constraints are satisfied. By employing constraint optimization algorithms such as the Lagrange multiplier method, the penalty function method, or the projected gradient method, the planetary gear center coordinates that minimize the objective function can be found while satisfying the constraints.

[0066] For each white area, repeating the constrained least squares fitting process yields the precise center coordinates of each planetary gear. Typically, a planetary gearbox contains three planetary gears. These center coordinates, compared to those obtained using ordinary least squares fitting, better reflect the actual installation positions of the planetary gears because they fully utilize the geometric constraints of gear meshing and the shape information of the inner bore boundaries. The planetary gear center coordinates obtained through constrained least squares fitting provide high-precision positional data for subsequent installation error calculations.

[0067] 206. Based on the center of the sun gear and the centers of each planet gear, calculate the actual angle between the centers of adjacent planet gears, and compare the actual angle with the theoretical angle to obtain the eccentricity angle; 207. Calculate the tangential eccentricity and longitudinal eccentricity based on the center of the sun gear, the centers of each planet gear, and the eccentricity angle. 208. Calculate the total eccentricity based on the tangential eccentricity and the longitudinal eccentricity, and use the eccentricity angle, tangential eccentricity, longitudinal eccentricity and total eccentricity as the installation error detection results of the planetary gearbox.

[0068] In this embodiment, steps 206-208 are similar to steps 102-104 in the first embodiment, and will not be described again here.

[0069] In this embodiment, the target image of the planetary gearbox is acquired using an image sensor, and edge detection is performed to extract the coordinate points of the gear contour. The center of the sun gear and the centers of each planet gear are calculated using the least squares method. Then, the deviation between the actual and theoretical angles between the centers of adjacent planet gears is calculated based on the center positions to obtain the eccentricity angle. The tangential eccentricity, longitudinal eccentricity, and total eccentricity are calculated by combining the center coordinates and the eccentricity angle. This achieves a non-contact detection method based on image processing, avoiding the cumbersome process of multiple contact measurements, probe movement, and data acquisition required by traditional contact detection equipment. This significantly shortens the detection time and improves the detection efficiency. At the same time, this invention can obtain complete information about the planetary gearbox with a single image acquisition and simultaneously obtain multiple key parameters such as eccentricity angle, tangential eccentricity, longitudinal eccentricity, and total eccentricity through calculation, providing comprehensive data support for the installation quality assessment of the planetary gearbox.

[0070] The above describes the planetary gearbox installation error detection method in the embodiments of the present invention. The following describes the planetary gearbox installation error detection device in the embodiments of the present invention. Please refer to [link to relevant documentation] for details on this planetary gearbox installation error detection device. Figure 3 One embodiment of the planetary gearbox installation error detection device of the present invention includes: The center fitting module 301 is used to acquire a target image of the planetary gearbox through an image sensor, perform edge detection on the target image, extract gear contour coordinate points, and calculate the center of the sun gear and the center of each planet gear of the planetary gearbox by least squares fitting based on the gear contour coordinate points. Angle calculation module 302 is used to calculate the actual included angle between the centers of adjacent planetary gears based on the center of the sun gear and the centers of each planetary gear, and compare the actual included angle with the theoretical included angle to obtain the eccentric angle; The eccentricity calculation module 303 is used to calculate the tangential eccentricity and the longitudinal eccentricity based on the center of the sun gear, the centers of each planet gear, and the eccentricity angle. The result output module 304 is used to calculate the total eccentricity based on the tangential eccentricity and the longitudinal eccentricity, and to use the eccentricity angle, tangential eccentricity, longitudinal eccentricity and total eccentricity as the installation error detection result of the planetary gearbox.

[0071] In this embodiment of the invention, the planetary gearbox installation error detection device operates the aforementioned planetary gearbox installation error detection method. The device acquires a target image of the planetary gearbox using an image sensor and extracts gear contour coordinates through edge detection. It then uses the least squares method to fit and calculate the center of the sun gear and the centers of each planet gear. Based on the center positions, it calculates the deviation between the actual and theoretical angles between the centers of adjacent planet gears to obtain the eccentricity angle. Combining the center coordinates and the eccentricity angle, it calculates the tangential eccentricity, longitudinal eccentricity, and total eccentricity. This achieves a non-contact detection method based on image processing, avoiding the cumbersome process of multiple contact measurements, probe movement, and data acquisition required by traditional contact-based detection equipment. This significantly shortens the detection time and improves detection efficiency. Furthermore, this invention can acquire complete information about the planetary gearbox with a single image acquisition and simultaneously calculate multiple key parameters such as the eccentricity angle, tangential eccentricity, longitudinal eccentricity, and total eccentricity, providing comprehensive data support for evaluating the installation quality of the planetary gearbox.

[0072] above Figure 3 The planetary gearbox installation error detection device in this embodiment of the invention is described in detail from the perspective of unitized functional entities. The planetary gearbox installation error detection device in this embodiment of the invention is described in detail from the perspective of hardware processing.

[0073] Figure 4 This is a schematic diagram of a planetary gearbox installation error detection device 400 provided in an embodiment of the present invention. The planetary gearbox installation error detection device 400 can vary significantly due to different configurations or performance. It may include one or more central processing units (CPUs) 410 (e.g., one or more processors) and a memory 420, and one or more storage media 430 (e.g., one or more mass storage devices) storing application programs 433 or data 432. The memory 420 and storage media 430 can be temporary or persistent storage. The program stored in the storage media 430 may include one or more units (not shown in the diagram), each unit may include a series of instruction operations on the planetary gearbox installation error detection device 400. Furthermore, the processor 410 may be configured to communicate with the storage media 430 and execute the series of instruction operations in the storage media 430 on the planetary gearbox installation error detection device 400 to implement the steps of the planetary gearbox installation error detection method described above.

[0074] The planetary gearbox installation error detection device 400 may also include one or more power supplies 440, one or more wired or wireless network interfaces 450, one or more input / output interfaces 460, and / or one or more operating systems 431, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 4 The illustrated planetary gearbox installation error detection device structure does not constitute a limitation on the planetary gearbox installation error detection device provided by the present invention. It may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0075] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when the instructions are executed on a computer, cause the computer to perform the steps of the planetary gearbox installation error detection method.

[0076] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system, device, or unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0077] If the integrated unit is implemented as 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 invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0078] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting installation errors in a planetary gearbox, characterized in that, The method for detecting installation errors in the planetary gearbox includes: The target image of the planetary gearbox is acquired by an image sensor, edge detection is performed on the target image, gear contour coordinate points are extracted, and the center of the sun gear and the center of each planet gear of the planetary gearbox are calculated by least squares fitting based on the gear contour coordinate points. Based on the center of the sun gear and the centers of each planet gear, calculate the actual angle between the centers of adjacent planet gears, and compare the actual angle with the theoretical angle to obtain the eccentricity angle; Calculate the tangential eccentricity and longitudinal eccentricity based on the center of the sun gear, the centers of each planet gear, and the eccentricity angle. The total eccentricity is calculated based on the tangential eccentricity and the longitudinal eccentricity, and the eccentricity angle, tangential eccentricity, longitudinal eccentricity, and total eccentricity are used as the installation error detection results of the planetary gearbox.

2. The method for detecting installation errors in a planetary gearbox according to claim 1, characterized in that, The step of acquiring a target image of the planetary gearbox using an image sensor, performing edge detection on the target image, and extracting gear contour coordinate points includes: The target image of the planetary gearbox is acquired by an image sensor, and sub-pixel edge detection is performed on the target image to obtain edge pixels; Contour tracking is performed on the edge pixels to obtain the contour coordinates of each gear.

3. The method for detecting installation errors in a planetary gearbox according to claim 1, characterized in that, The step of calculating the center of the sun gear and the centers of each planet gear in the planetary gearbox using the least squares fitting method based on the gear profile coordinate points includes: The coarse center coordinates of all the gear profile coordinate points are calculated using the superposition averaging method. Based on the distance between the gear profile coordinate points and the rough center coordinates, a threshold is set, the sun gear inner hole profile coordinate points are extracted, and the sun gear center coordinates are obtained by fitting the sun gear inner hole profile coordinate points using the least squares method. The target image is binarized to extract the contour coordinates and midpoint coordinates of the white area around the inner hole of the planetary gear; Based on the midpoint coordinates, the sun gear center coordinates, and the contour coordinates, the constrained least squares method is used to fit and obtain the center coordinates of each planetary gear.

4. The method for detecting installation errors in a planetary gearbox according to claim 3, characterized in that, The step of setting a threshold based on the distance between the gear profile coordinate points and the rough center coordinates, extracting the sun gear inner bore profile coordinate points, and using the least squares method to fit the sun gear inner bore profile coordinate points to obtain the sun gear center coordinates includes: Calculate the distance from each profile coordinate point to the rough circle center based on the gear profile coordinate points and the rough circle center coordinates; A threshold is set based on the minimum distance value among the distance values, and the contour coordinate points with distance values ​​less than the threshold are extracted as the contour coordinate points of the sun gear inner hole. The coordinates of the sun gear's inner bore contour are fitted using the least squares method to obtain the coordinates of the sun gear's center.

5. The method for detecting installation errors in a planetary gearbox according to claim 3, characterized in that, The process of obtaining the center coordinates of each planetary gear using constrained least squares fitting based on the midpoint coordinates, the center coordinates of the sun gear, and the contour coordinates includes: Calculate the theoretical center distance from the center of the planet gear to the center of the sun gear based on the module and number of teeth of the sun gear and the module and number of teeth of the planet gear; Calculate the radius of the planetary gear's inner hole based on the outline coordinates of the white area; Using the midpoint coordinates as initial values, the distance from the center of the planetary gear to the center of the sun gear is equal to the theoretical center distance as the first constraint condition, and the distance from the center of the planetary gear to the inner hole contour point is equal to the inner hole radius of the planetary gear as the second constraint condition. The constrained least squares method is used for fitting to obtain the coordinates of the center of each planetary gear.

6. The method for detecting installation errors in a planetary gearbox according to claim 1, characterized in that, The calculation of tangential and longitudinal eccentricities based on the center of the sun gear, the centers of each planet gear, and the eccentricity angle includes: The tangential eccentricity is calculated based on the theoretical center distance from the center of the planetary gear to the center of the sun gear and the eccentricity angle. The longitudinal eccentricity is calculated based on the theoretical center distance and the actual distance between the center of the sun gear and the centers of each planet gear.

7. The method for detecting installation errors in a planetary gearbox according to claim 1, characterized in that, The calculation of the total eccentricity based on the tangential eccentricity and the longitudinal eccentricity includes: The tangential eccentricity and the longitudinal eccentricity are squared respectively to obtain the squared value of the tangential eccentricity and the squared value of the longitudinal eccentricity; The square values ​​of the tangential eccentricity and the longitudinal eccentricity are summed to obtain a summation result, and the square root of the summation result is taken to obtain the total eccentricity.

8. A planetary gearbox installation error detection device, characterized in that, The planetary gearbox installation error detection device includes: The center fitting module is used to acquire the target image of the planetary gearbox through the image sensor, perform edge detection on the target image, extract the gear contour coordinate points, and calculate the center of the sun gear and the center of each planet gear of the planetary gearbox by least squares fitting based on the gear contour coordinate points. An angle calculation module is used to calculate the actual angle between the centers of adjacent planetary gears based on the center of the sun gear and the centers of each planet gear, and compare the actual angle with the theoretical angle to obtain the eccentric angle; The eccentricity calculation module is used to calculate the tangential eccentricity and longitudinal eccentricity based on the center of the sun gear, the centers of each planet gear, and the eccentricity angle. The result output module is used to calculate the total eccentricity based on the tangential eccentricity and the longitudinal eccentricity, and to use the eccentricity angle, tangential eccentricity, longitudinal eccentricity and total eccentricity as the installation error detection results of the planetary gearbox.

9. A planetary gearbox installation error detection device, characterized in that, The planetary gearbox installation error detection device includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor invokes the instructions in the memory to cause the planetary gearbox installation error detection device to perform the steps of the planetary gearbox installation error detection method as described in any one of claims 1-7.

10. A computer-readable storage medium storing instructions thereon, characterized in that, When the instruction is executed by the processor, it implements the steps of the planetary gearbox installation error detection method as described in any one of claims 1-7.

Images