Low-turbine shaft nut tightening method and related device

Abstract

The invention provides a low-turbine shaft nut tightening method and a related device. According to the method, a camera is used for collecting nut-shaft head end face image data, and the image data are transmitted to a nut tightening angle real-time measurement module by means of a visual processing technology. The module comprises a feature extraction sub-module, an error fusion sub-module and an included angle calculation sub-module, a nut and shaft head locking groove boundary equation is extracted in sequence, a center line equation is screened based on a theoretical circle center value, and then the minimum angle difference of the nut and the shaft head locking groove is obtained. According to the minimum angle difference, the nut is automatically tightened through the tightening shaft to complete assembling, and meanwhile result visualization is achieved. The problems of invisibility, difficulty in alignment, low efficiency and the like in the assembly process are solved, automatic visual detection and automatic assembly in an invisible space are achieved, workers can conveniently check the assembly condition in real time, assembly automation integration is promoted, and the method has important significance in the field of low-turbine shaft nut assembly.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of aero-engines, in particular to a low-vortex shaft nut tightening method and related device. BACKGROUND

[0002] As one of the core parts in an aero-engine, a low-vortex shaft plays a key role in connecting a low-pressure compressor unit and a low-pressure turbine unit and bearing high-pressure core units, and is a main bearing component of the aero-engine in high-speed rotation. In the complex working environment of the aero-engine, the low-vortex shaft not only needs to bear the huge stress generated by high-speed rotation, but also needs to cope with complex load conditions such as vibration under adverse aerodynamic conditions. To ensure the stable connection between the low-pressure compressor rotor and the low-vortex shaft, the traditional method is to pre-tighten the nut at the shaft head section with a large torque during assembly, and to use a mechanical anti-loosening structure, that is, to process a plurality of grooves on the end faces of the shaft head and the low-vortex nut, and to use a locking ring to position and ensure mechanical high-reliability anti-loosening. This technology is widely used in the field of aero-engine manufacturing and is one of the important measures to ensure the safe and stable operation of the engine.

[0003] However, in actual application, the front section of the low-vortex shaft is located at the rear end of the low-pressure compressor of the aero-engine, and the assembly space is closed and narrow, which makes the tightening process of the low-vortex nut invisible to the human eye. The operator can only rely on repeated "tightening-exit-try-on locking ring" operations to adjust the nut position until the grooves are aligned and the locking ring assembly is completed. This process not only consumes time and effort, but also further prolongs the assembly cycle due to the large size of the tooling structure and the cumbersome lifting, which seriously affects the assembly efficiency. In addition, this reciprocating tightening adjustment method also causes the lack of stable process execution characteristics of the nut pre-tightening force loading, which brings difficulties to the accurate control of the pre-tightening force.

[0004] In view of the above problems, the existing technology attempts to introduce automation to improve the tightening efficiency of the low-vortex nut. For example, by marking on the shaft to approximately estimate the nut position, or using naked eye observation, endoscope exploration and other methods to assist assembly. However, these methods all need to interrupt the operation during tightening to make a judgment, and cannot realize the accurate alignment of the nut and the shaft head groove and automatic tightening in place. Although the introduction of automation technology improves the assembly efficiency to some extent, it still cannot fundamentally solve the problems of invisibility and difficult alignment in the assembly process.

[0005] In summary, in the assembly process of low-vortex shaft and low-vortex nut, although attempts have been made to improve efficiency through automation, there are still problems such as invisible assembly, difficult alignment, low efficiency, and unstable pre-tightening force control. These problems not only limit the further improvement of the assembly quality of aero-engine, but also increase the production cost and cycle. Therefore, it is particularly important to develop an image processing method that can measure the nut tightening angle in real time, realize automatic tightening to the right position, and visualize the assembly process. This method will effectively solve the bottleneck problem in the prior art and promote the intelligent and efficient development of aero-engine assembly technology. SUMMARY

[0006] In view of the problems of invisible assembly, difficult alignment, and low efficiency in the assembly operation, the present application provides a low-vortex shaft nut tightening method and related device. The method uses a camera to collect nut-shaft head end face image data, and uses visual processing technology to transmit the image to a nut tightening angle real-time measurement module. The module outputs the minimum angle difference between the nut and the shaft head locking groove. According to the minimum angle difference, the assembly is completed by automatically tightening the shaft, and the result is visualized, which facilitates real-time viewing by workers and facilitates assembly automation integration.

[0007] To achieve the above-mentioned purpose, the present application provides the following technical solutions: a low-vortex shaft nut tightening method, which transmits the pictures of the nut locking groove and the shaft head locking groove on the low-vortex shaft to a nut tightening angle real-time measurement module to obtain the minimum angle difference between the nut locking groove and the shaft head locking groove. According to the minimum angle difference, the nut on the low-vortex shaft is tightened. The nut tightening angle real-time measurement module includes a feature extraction module, an error fusion module, and an included angle calculation module. The feature extraction module is used to extract the boundary equation of the nut locking groove and the shaft head locking groove respectively. The error fusion module is used to filter the corresponding nut locking groove and shaft head locking groove center line equation based on the theoretical circle center value and the boundary equation. The included angle calculation module is used to obtain the minimum angle difference between the nut locking groove and the shaft head locking groove according to the theoretical circle center and the locking groove center line equation.

[0008] Further, the pictures of the nut locking groove and the shaft head locking groove are pictures of the entire region of the locking groove. After smoothing, gray scale distribution optimization, binarization, and denoising, the pictures of the nut locking groove and the shaft head locking groove are input into the nut tightening angle real-time measurement module.

[0009] Further, the feature extraction module comprises a target positioning module, a locking groove preliminary feature extraction module, and a locking groove boundary equation optimization module, wherein: the target positioning module uses an image contour search algorithm to perform region segmentation on the input image, divides the image into different contour regions, calculates the pixel area features of each contour region, sorts the areas, and compares them with a preset area threshold to screen out contour regions meeting the requirements, thereby realizing nut-shaft head target region positioning; the locking groove preliminary feature extraction module extracts the minimum circumscribed rectangle of the target region contour using a blank mask, obtains the rectangular short side parameters representing the distribution characteristics of the locking groove by analyzing the rectangular vertex coordinates, takes the midpoint of the short side as a reference point, iterates the contour point set, calculates the distance between each contour point and the midpoint of the short side, and screens the locking groove boundary feature points according to a preset distance threshold; in the locking groove boundary equation optimization module, the least square straight line fitting is performed on the locking groove boundary feature points, the perpendicular distance of the locking groove boundary feature points to the fitted straight line is calculated, the perpendicular distance distribution variance is counted, the feature points exceeding three times the variance and a preset threshold of the number of pixel points are removed, and the remaining feature point set is subjected to least square straight line fitting again to obtain the optimized locking groove boundary equation.

[0010] Further, the error fusion module comprises an observation equation set construction module, an error analysis module, and a centerline equation screening module, wherein: the observation equation set construction module calculates the centerline equation using each pair of locking groove boundary straight line equations, and jointly constructs an observation equation set; the error analysis module uses the least square method to solve the observation equation set to obtain the theoretical center coordinates, and then calculates the distance error between the locking groove centerline and the theoretical center; in the centerline equation screening module, all centerline equations are iterated, centerline equations greater than the distance error are removed, and the remaining centerline equations are used to reconstruct the observation equation set.

[0011] Further, the included angle calculation module comprises an angle calculation module, an alignment condition module, and an image visualization module, wherein: in the angle calculation module, the theoretical center is taken as the coordinate axis origin of angle calculation, the coordinate horizontal axis is set as the reference axis, one locking groove centerline equation is randomly selected, the angle of the locking groove in the constructed coordinate system is calculated, and the angle is taken as the basic angle; in the alignment condition module, the basic angle, the nut and shaft head distribution law, and the slot angle between the nut and shaft head locking grooves are used to obtain the nut locking groove angle set and the shaft head locking groove angle set, and the nut-shaft head locking groove angle difference set is obtained by screening according to the boundary conditions, and the minimum angle difference is searched; in the image visualization module, the nut locking groove angle set and the shaft head locking groove angle set are used to construct a visual theoretical model, the image data is adjusted and corrected using the theoretical center, and finally the corrected image and the original image are fused to generate a visual image.

[0012] Further, in the alignment condition module: The nut locking groove angle set is represented as: ; The set of shaft head locking groove angle is represented as: ; The set of nut-shaft head locking groove angle difference is represented as:

[0013] wherein, is the corresponding inter-slot angle of the nut, ; is the corresponding inter-slot angle of the shaft head, ; is the theoretical locking groove angle difference; m is the number of nut locking grooves; n is the number of shaft head locking grooves; The boundary condition is .

[0014] The application also provides a low-vortex shaft nut tightening system for implementing the low-vortex shaft nut tightening method, comprising: A tightening angle calculation module is configured to transmit the nut locking groove and the shaft head locking groove pictures on the low-vortex shaft to a nut tightening angle real-time measurement module respectively to obtain the minimum angle difference between the nut locking groove and the shaft head locking groove. A nut tightening module is configured to transmit the minimum angle difference to a motion control system, and the motion control system tightens the nut on the low-vortex shaft according to the minimum angle difference. The nut tightening angle real-time measurement module comprises a feature extraction module, an error fusion module, and an included angle calculation module. The feature extraction module is configured to extract the boundary equation of the nut locking groove and the shaft head locking groove respectively. The error fusion module is configured to filter the corresponding locking groove center line equation based on the theoretical circle center value and the boundary equation. The included angle calculation module is configured to obtain the minimum angle difference between the nut locking groove and the shaft head locking groove according to the theoretical circle center and the locking groove center line equation.

[0015] The application also provides a terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the low-vortex shaft nut tightening method.

[0016] The application also provides a computer readable storage medium storing a computer program, wherein the computer program is executable on a processor to implement the steps of the low-vortex shaft nut tightening method.

[0017] The application also provides a computer program product comprising a computer program, wherein the computer program is executable on a processor to implement the steps of the low-vortex shaft nut tightening method.

[0018] Compared with the prior art, the application has at least the following beneficial effects: The application provides a low vortex shaft nut tightening method, which realizes visual automatic detection of invisible space by means of image processing technology, collecting nut-shaft head end surface images and transmitting the images to a nut tightening angle real-time measurement module. Through the collaborative operation of feature extraction, error fusion and included angle calculation modules, the minimum angle difference between the nut and the shaft head locking groove is accurately obtained, and the technical blank of automatic detection in this field is filled. Further, the nut is tightened according to the obtained minimum angle difference, and the operation of invisible and difficult-to-align components in traditional manual assembly is converted into automatic operation, effectively overcoming the assembly problem and laying a foundation for assembly automation. Further, the application can realize result visualization, facilitate staff to view the assembly situation in real time, find problems in time and adjust, guarantee assembly quality and promote the integrated development of assembly automation.

[0019] The low vortex shaft nut tightening system provided by the application runs the low vortex shaft nut tightening method, efficiently transmits image data through the tightening angle calculation module and obtains the minimum angle difference, thereby providing accurate data support for subsequent assembly. The nut tightening module transmits the angle difference to the motion control system to realize automatic nut tightening, thereby greatly improving the assembly efficiency. The sub-modules in the nut tightening angle real-time measurement module have clear division of labor, the feature extraction module extracts the boundary equation, the error fusion module screens the center line equation, and the included angle calculation module obtains the minimum angle difference. The modules are closely matched, ensuring the accuracy and efficiency of the assembly process and effectively promoting the intelligent and automatic development of low vortex shaft nut assembly. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 The specific flowchart of the visual algorithm is shown in the figure. Figure 2 The feature extraction flowchart of the nut-shaft head is shown in the figure. Figure 3 The nut-shaft head locking groove alignment schematic diagram is shown in the figure. Figure 4 The locking groove boundary extraction calculation schematic diagram is shown in the figure. Figure 5 The observation equation construction schematic diagram is shown in the figure. Figure 6 The distance error calculation schematic diagram is shown in the figure. Figure 7 The locking groove angle calculation schematic diagram is shown in the figure.

[0021] Figure 8 The locking groove alignment condition module is shown in the figure.

[0022] Figure 9 The tightening result determination schematic diagram is shown in the figure.

[0023] Figure 10 The tightening result determination structural diagram is shown in the figure.

[0024] In the drawing: 1, nut groove; 2, shaft head groove; 3, end groove outer contour; 4, circumscribed rectangle; 5, locking groove; 6, theoretical center; 7, reference axis; 8, nut; 9, shaft head; 10, locking sleeve. DETAILED DESCRIPTION

[0025] The present application will be further described below in combination with the drawing and specific implementation steps. The existing transmission low vortex nut assembly method has narrow assembly space, poor visual conditions, and relies on repeated trial assembly by manual operation. The process of tightening, checking whether the nut and shaft head grooves are aligned, and checking the nut and shaft head grooves is repeated several times to achieve the tightening requirement, and experienced workers are required to operate to achieve the tightening requirement. The present application solves the problems of invisibility and difficult alignment in the original assembly process by real-time acquisition of nut-shaft head images and processing and calculation of the angle difference between the nut-shaft head locking grooves, i.e., the angle to be tightened. The present application can achieve one-time tightening and avoid repeated operations, thereby improving efficiency. The present application uses the OpenCV vision library to implement the following steps, and the relevant vision processing technology refers to similar function functions. The above is an explanation of the present application and not a limitation.

[0026] As shown in Figure 1 , the present application provides a low vortex shaft nut tightening method, comprising the following steps: 1) Nut assembly end face image acquisition, real-time capture of nut-shaft head images by high-precision camera, including all areas of the nut and shaft head locking grooves.

[0027] 2) Image preprocessing for nut assembly image acquisition, which includes the following sub-steps: (2.1) Gaussian filter algorithm is used to smooth the original image, eliminate noise interference caused by uneven illumination and surface texture, and set the filter kernel size and standard deviation parameters to construct a frequency domain suppression model; (2.2) Apply histogram equalization technique to optimize the gray scale distribution of the filtered image, and strengthen the boundary contrast of the locking groove and the background area; (2.3) Determine the best segmentation threshold value by dynamic threshold iteration algorithm, and process the image into 0 (black) and 255 (white) binary image; (2.4) Finally, use the erosion and expansion algorithm to eliminate discrete noise points and enhance the continuous geometric features of the locking groove.

[0028] 3) Nut and shaft head image feature extraction, the flow is shown in Figure 2 , comprising the following steps: This section will take the nut locking groove feature extraction as an example, introduce how to extract the locking groove feature of nut and shaft head based on image processing technology. The extraction method of shaft head locking groove is similar to that of nut locking groove, the specific process is described as follows. Through detailed analysis of the extraction process of nut locking groove, the same processing idea and method can be provided for the extraction of shaft head locking groove.

[0029] (3.1) First, the image contour finding algorithm is used for region segmentation of the image; (3.2) Calculate the pixel area feature of each contour region, sort the area, and realize the accurate positioning of the nut-shaft head target region by comparing the area sorting with the area threshold, and screen the contour regions that meet the requirements; (3.3) Create a blank mask and extract the minimum bounding rectangle of the contour, and obtain the rectangular short side parameters representing the distribution characteristics of the locking groove through vertex coordinate analysis; specific Reference Figure 4 , the outer contour of the locking groove 3 is obtained by combining the rectangle finding function, and the length of the four sides of the rectangle is calculated according to the vertex coordinates of the rectangle, and the length of the two short sides of the rectangle is obtained by sorting the length of the four sides.

[0030] (3.4) Take the midpoint of the short side as the reference point, traverse the contour point set and calculate the distance between each contour point and the midpoint of the short side, and select the locking groove boundary feature points according to the preset distance threshold; Reference Figure 4 , point z is the midpoint of the short side of the rectangle, points O i1 and O i2 are any two points on the locking groove, by traversing the contour points, setting the threshold value as half of the length of the locking groove, the points on the contour that meet the locking groove, such as point O i1 to point z, are less than the threshold value, and are reserved as data for subsequent calculation of the locking groove, and points O i2 to point z are greater than the threshold value and are removed, and all contour points on the contour are filtered by traversing the contour points in this aspect.

[0031] (3.5) Least square straight line fitting is performed on the discrete point set of the locking groove boundary, and the perpendicular distance of each discrete point to the fitted straight line is calculated, the variance of the perpendicular distance distribution is calculated, and three times the variance is set as the judgment standard of the effectiveness of the discrete points, that is, the discrete points with a distance deviation of more than 3 times the standard deviation are removed; when the number of discrete points in a certain line segment region is less than the preset threshold, it is considered that the line segment lacks statistical significance, and the pixel point set of the line segment is directly removed, and is not regarded as an effective representation object of the groove-edge structure. The pixel point set that passes through the double screening (variance constraint + point number constraint) is re-performed least square straight line fitting to obtain the optimized locking groove boundary equation of the nut.

[0032] 4) Measurement error fusion, get the theoretical center value and the center line equation of the locking groove that meets the conditions, including the following steps: (4.1) Since the middle vector of the locking groove pattern passes through the center of the circle, the middle line equation is calculated according to the locking groove boundary straight line equation of each pair, and all the middle line equations are constructed into an observation equation set: ; Reference Figure 5 , according to the distribution law of the locking groove, the middle line of all locking grooves passes through the theoretical center 6, so the calculated middle line equation is combined to form an observation equation set, and the solution of the observation equation set is the coordinate value of the theoretical center 6.

[0033] (4.2) The observation equation set is solved by least squares to find the image center, and the theoretical center should be located on the middle line, but the calculation equation is an over-determined equation set, and the equation constructed in the equation cannot represent the position of the theoretical center line, resulting in the actual middle line not necessarily passing through the theoretical center obtained by solving the observation equation set, so there is a distance error between the theoretical center and the actual middle line; Reference Figure 6 , according to the observation equation to calculate the theoretical center 6, there is a middle line of the locking groove 5 that does not pass through the theoretical center 6, and the calculation error distance d i , used to screen the middle line equation with too large error.

[0034] (4.3) In order to improve the visual accuracy, set the radial distance error threshold of the theoretical center to each line segment equation to 5 pixels, traverse the radial distance deviation of each middle line and the theoretical center d i , and screen out the line segments that do not meet the conditions, and re-iterate to calculate the accurate value of the center that meets the error allowance.

[0035] 5) Nut-shaft head locking groove angle output and image visualization, including the following steps: (5.1) Taking the theoretical center as the angle calculation coordinate axis origin, taking the horizontal axis of the coordinate as the reference axis, and taking any locking groove center line equation, the relative angle of the locking groove in the coordinate system can be calculated. Because the nut and shaft head angle calculation uses the same image data and the same coordinate system, the relative angle can be used as the absolute angle directly when calculating the nut-shaft head locking groove angle and image visualization.

[0036] Reference Figure 7 , taking the theoretical center 6 as the coordinate axis origin and the horizontal axis as the reference axis 7, the relative angle of the locking groove 5 with respect to the reference axis 7 is calculated as the absolute angle of the locking groove (shaft head corresponding locking groove angle , nut corresponding locking groove angle ).

[0037] (5.2) ReferenceFigure 8 The angle of the locking groove corresponding to the shaft head obtained through the above calculations The angle of the locking groove corresponding to the nut Based on the distribution pattern of the nut and shaft locking groove, an alignment condition module is established to obtain the nut-shaft locking groove angle set, and the corresponding locking groove angle difference is calculated based on the nut-shaft locking groove angle set. 5.2.1 The alignment condition module is calculated as follows: Nut locking groove angle (first) i (slots) ; Shaft head locking groove angle (first) j (slots) ; Based on the distribution pattern of the nuts and shaft ends, the number of locking grooves for the nuts and shaft ends is m and n respectively; the corresponding groove angles are... and , means as follows:

[0038] 5.2.2 Using the shaft end locking groove as a reference, calculate the angle difference between all nuts and the theoretical locking groove of the shaft end. The set of angle differences between the nut and shaft head locking grooves is obtained:

[0039] Because of the distribution pattern of the nut-shaft locking grooves and the fact that the tightening process is unidirectional, a screening boundary condition is set for all locking grooves:

[0040] 5.2.3 Find the minimum angle difference in the set of nut-shaft locking groove angle differences. .

[0041] (5.3) A visualization theoretical model is established based on the set of nut-shaft locking groove angles, and the image data is corrected by combining the theoretical center. The image visualization result can be completed by merging it with the original image. 6) The processed minimum angle difference The data is uploaded to the motion control system (low vortex tightening equipment control system) for tightening operation. During the tightening process, the corresponding nut-shaft locking groove angle data is monitored in real time. After tightening is completed, the tightening result is judged. If it does not meet the assembly allowable error, the process returns to step (1) to calculate the tightening angle difference and tighten. Once the assembly allowable error is met, the tightening is completed. The angle change data collected throughout the process is uploaded to the upper management system to form a traceable quality data chain.

[0042] The application provides a low-vortex shaft nut tightening method, visual automatic detection of invisible space in an assembly process is realized through an image processing technology, assembly automation is assisted, and a technical blank of an automatic process in the field is filled. The method realizes real-time linkage of online visual detection and a tightening mechanism, converts a traditional manual assembly process into automatic assembly technology, effectively shortens an assembly cycle, and greatly improves part assembly efficiency. Meanwhile, a visual archive function is introduced, an assembly theoretical model is generated in real time, and assembly related parameters are output, thereby providing a digital basis for quality tracing. In addition, a narrow space visual guiding assembly technology system is provided, which can be extended and applied to centering of an aero-engine stator assembly, positioning of a combustion chamber nozzle and similar closed scenes, and promotes evolution of aero-engine manufacturing to an intelligent assembly stage.

[0043] The working process of the application is as follows: (1) After collecting the original image, first, noise reduction processing is performed to eliminate noise caused by the light source to the workpiece image and improve the image contrast to make the features more obvious, then the image is read as a gray image, and the gray image is binarized, the binarization threshold is set to 200 (that is, the pixels with a pixel value greater than 200 are set to white, and vice versa, black), then the image is subjected to an erosion and expansion operation, because the main purpose is to eliminate non-target regions in the image, and most of the non-target regions are small noise regions, so the operation of first erosion and then expansion is required, wherein the erosion and expansion structure element is 3x3, through the above operation, the regions irrelevant to the nut and shaft head are removed, thereby reducing the workload and improving the efficiency of subsequent image processing.

[0044] (2) The contour of the preprocessed image is searched, the features of the nut and shaft head regions are segmented, the areas of the regions are calculated, the contours are numbered, the contour areas are sorted, the area threshold is set by manually observing the nut and shaft head contour area range, the regions with an area less than 3500 pixels and between 5500 pixels and 7000 pixels are screened, a blank mask is created, the boundary image of the nut-shaft head contour after screening is drawn on the mask, the minimum circumscribed rectangle frame of each contour is drawn, the lengths of the sides of the rectangle are calculated, and the lengths are sorted, the short side is searched and the midpoint of the short side is calculated, the distance between the contour point and the midpoint is traversed, the threshold is set to 1.5, and if the distance is less than the threshold, it is determined that it is the locking groove boundary. The initial least square straight line fitting is performed on the discrete point set of the locking groove contour, the perpendicular distance of each discrete point to the fitted straight line is calculated, and the variance distribution is counted; the discrete point rejection threshold is set based on three times the variance, and the abnormal contour points deviating from the fitted straight line by more than three times the standard deviation are screened out; then the contour point quantity threshold is set to 5, and the local line segment with a remaining point set quantity lower than the threshold is determined as an invalid representation section and is removed; finally, the effective contour point set screened through the variance constraint and the point number constraint is subjected to secondary least square straight line fitting, and the optimized locking groove boundary equation with statistical significance is obtained, thereby providing a high-precision geometric reference for angle calculation.

[0045] (3) Set the angle threshold value as 10°, form a pair (i.e. two edges of a locking groove) by fitting straight lines for the two edges of the locking groove, obtain the equation of the middle line segment of the two line segments, construct an observation equation set by using all the middle line equations, solve the center of the circle and output, and calculate the distance between the middle line equation and the center of the circle, set the distance threshold value as 5 pixels, screen out the line segments with too large distance, and iteratively and repeatedly solve the center of the circle.

[0046] (4) Finally, according to the solved center of the circle, construct an angle calculation coordinate system, respectively calculate the absolute angle value of the middle line equation of the nut and the shaft head locking groove relative to the horizontal axis of the coordinate system, and construct a nut-shaft head locking groove angle set; calculate the nut-shaft head angle difference for each angle in the set, and extract the minimum angle difference as the assembly phase reference angle. According to the size parameters of the nut and the shaft head, an alignment condition module is established, and the spatial position is corrected according to the angle and the center of the circle of the locking groove of the nut and the shaft head.

[0047] The original method adopts multiple tightening, and after the tightening is completed, the check-repeated test- until the tightening is successful (more than half an hour), the alignment method of the present application only needs artificial pre-tightening (the angle alignment does not need to be considered in the pre-tightening stage), and the pre-tightening is performed to the point that the artificial person cannot tighten the nut, and then the tightening device (the camera acquisition system provides the tightening angle basis for the tightening device by identifying the nut-shaft head) is installed, the whole installation time is not more than 3 minutes, the tightening process is shortened to 1 minute, and the single tightening can guarantee the tightening accuracy.

[0048] The following is a device embodiment of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the device embodiment, please refer to the method embodiment of the present application.

[0049] In another embodiment of the present application, a low vortex shaft nut tightening system is also provided, which runs the low vortex shaft nut tightening method, comprising: A tightening angle calculation module is used for transmitting the nut locking groove and the shaft head locking groove pictures on the low vortex shaft to the nut tightening angle real-time measurement module respectively, so as to obtain the minimum angle difference between the nut locking groove and the shaft head locking groove. A nut tightening module is used for transmitting the minimum angle difference to the motion control system, and the motion control system tightens the nut on the low vortex shaft according to the minimum angle difference. Figure 3 As shown in Reference Figure 9 , Figure 10By introducing a locking sleeve 10 as an auxiliary checking tool, the locking sleeve is composed of a circular body matched with the hollow structure inside the shaft head and a protruding groove, and the protruding part is accurately fitted with the aligned groove in the nut and the end face of the shaft head. After tightening is completed, the locking sleeve is inserted into the aligned locking groove of the nut and the shaft head, and if the locking sleeve can be smoothly clamped, it indicates that the angle alignment of the nut and the shaft head reaches the tightening requirement.

[0050] The nut tightening angle real-time measurement module includes a feature extraction module, an error fusion module and an included angle calculation module, the feature extraction module is used for extracting the boundary equation of the nut locking groove and the shaft head locking groove respectively, the error fusion module is used for screening the corresponding locking groove center line equation based on the theoretical circle center value and the boundary equation, and the included angle calculation module is used for obtaining the minimum angle difference between the nut locking groove and the shaft head locking groove according to the theoretical circle center and the locking groove center line equation.

[0051] The image processing system of the present application can output the angle required for rotation in the assembly process by calculating and analyzing the shooting pictures in the nut-shaft head assembly process, thereby saving the working time of manual operation and repeated trial and error in the assembly process, and realizing the automation of the assembly.

[0052] In another embodiment of the present application, a terminal device is also provided, which includes a processor and a memory, the memory is used for storing a computer program, the computer program includes program instructions, and the processor is used for executing the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to realize the corresponding method flow or corresponding function. The processor in the embodiment of the present application can realize the operation of a low vortex shaft nut tightening method.

[0053] In still another embodiment, the present application provides a storage medium, specifically a computer readable storage medium (Memory), which is a memory device in the terminal equipment, for storing programs and data. It should be understood that the computer readable storage medium herein can include the built-in storage medium in the terminal equipment, and of course can also include the expansion storage medium supported by the terminal equipment. The computer readable storage medium provides a storage space, which stores the operating system of the terminal. Moreover, one or more instructions adapted to be loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer readable storage medium herein can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory. The one or more instructions stored in the computer readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the low-winding nut tightening method in the above embodiment.

[0054] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer-usable program code.

[0055] The present application is described with reference to the flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device that implements the flowcharts and / or block diagrams. Figure 1 The function of one or more flows and / or blocks Figure 1 The device that implements the function specified in one or more flows and / or blocks.

[0056] These computer program instructions can also be stored in a computer readable storage medium that can direct the computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a manufactured product including instruction devices that implement the flowcharts and / or block diagrams. Figure 1 The function of one or more flows and / or blocks Figure 1the function specified in the one or more blocks.

[0057] These computer program instructions can also be loaded into computer or other programmable data processing devices, so that a series of operation steps are performed on the computer or other programmable data processing devices to generate computer-implemented processes, so that the instructions executed on the computer or other programmable devices provide processes for implementing the flowcharts Figure 1 one or more flows and / or blocks Figure 1 the steps of the function specified in the one or more blocks.

[0058] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, but not to limit it, although the above embodiments of the present application have been described in detail, those skilled in the art should understand: the specific embodiments of the present application can be modified or replaced by the same, without departing from the spirit and scope of the present application, any modification or equivalent replacement, which should be covered in the protection scope of the claims of the present application.

Claims

1. A method for tightening a low-profile worm gear nut, characterized in that, The images of the nut locking groove and shaft head locking groove on the low-pressure vortex shaft are transmitted to the real-time nut tightening angle measurement module to obtain the minimum angle difference between the nut locking groove and the shaft head locking groove. Tighten the nut on the low-profile worm shaft according to the minimum angle difference; The real-time nut tightening angle measurement module includes a feature extraction module, an error fusion module, and an angle calculation module. The feature extraction module is used to extract the boundary equations of the nut locking groove and the shaft head locking groove, respectively. The error fusion module is used to filter the corresponding centerline equations of the nut locking groove and the shaft head locking groove based on the theoretical center value and the boundary equations. The angle calculation module is used to obtain the minimum angle difference between the nut locking groove and the shaft head locking groove according to the theoretical center value and the centerline equation of the locking groove.

2. The method for tightening a low-profile worm gear nut according to claim 1, characterized in that, The images of the nut locking groove and the shaft locking groove are images of the entire area of ​​the locking groove; after smoothing, grayscale distribution optimization, binarization, and noise reduction of the images of the nut locking groove and the shaft locking groove, they are input into the real-time measurement module for the nut tightening angle.

3. The method for tightening a low-profile worm gear nut according to claim 1, characterized in that, The feature extraction module includes a target localization module, a preliminary feature extraction module for the locking groove, and a boundary equation optimization module for the locking groove. Specifically: the target localization module uses an image contour search algorithm to segment the input image into different contour regions, calculates the pixel area features of each contour region, sorts the areas, and compares them with a preset area threshold to select the contour regions that meet the requirements, thus achieving the localization of the nut-shaft head target region; the preliminary feature extraction module for the locking groove uses a blank mask to extract the minimum bounding rectangle of the target region contour, and analyzes the vertex coordinates of the rectangle... Obtain the parameters of the short side of the rectangle representing the distribution characteristics of the locking groove. Using the midpoint of the short side as the reference point, traverse the set of contour points and calculate the distance between each contour point and the midpoint of the short side. Filter the locking groove boundary feature points according to a preset distance threshold. In the locking groove boundary equation optimization module, perform least-squares line fitting on the locking groove boundary feature points and calculate the vertical distance from the locking groove boundary feature points to the fitted line, and statistically analyze the variance of the vertical distance distribution. Remove feature points with a variance exceeding three times or a preset threshold for the number of pixels. Re-fit the remaining feature point set with least-squares line fitting to obtain the optimized locking groove boundary equation.

4. The method for tightening a low-profile worm gear nut according to claim 1, characterized in that, The error fusion module includes an observation equation set construction module, an error analysis module, and a centerline equation screening module. Specifically: the observation equation set construction module calculates the centerline equation using the boundary line equations of each pair of locking grooves and jointly constructs the observation equation set; the error analysis module uses the least squares method to solve the observation equation set to obtain the theoretical center coordinates, and then calculates the distance error between the centerline of the locking groove and the theoretical center; the centerline equation screening module traverses all centerline equations, eliminates centerline equations with a distance error greater than the distance error, and reconstructs the observation equation set for the remaining centerline equations.

5. A method for tightening a low-profile worm gear nut according to claim 1, characterized in that, The angle calculation module includes an angle calculation module, an alignment condition module, and an image visualization module. Specifically: the angle calculation module uses the theoretical center of the circle as the origin of the coordinate axis for angle calculation, sets the horizontal axis as the reference axis, and calculates the angle of any locking groove centerline equation in the constructed coordinate system. This angle serves as the base angle. The alignment condition module uses the base angle, the distribution pattern of the nut and shaft head, and the groove angle between the nut and shaft head locking grooves to obtain the nut locking groove angle set and the shaft head locking groove angle set. It then filters the nut-shaft head locking groove angle difference set based on boundary conditions and finds and outputs the minimum angle difference. The image visualization module uses the nut locking groove angle set and the shaft head locking groove angle set to construct a visualization theoretical model. It uses the theoretical center of the circle to adjust and correct the image data, and finally merges the corrected image with the original image to generate a visualization image.

6. A method for tightening a low-profile worm gear nut according to claim 5, characterized in that, In the alignment conditions module: The set of nut locking groove angles is represented as follows: ; The set of shaft head locking groove angles is represented as follows: ; The set of angle differences between the nut and shaft locking grooves is represented as: in, This refers to the angle between the grooves corresponding to the nut. ; This refers to the angle between the grooves corresponding to the shaft head. ; This is the theoretical difference in locking groove angle; m The number of nut locking grooves; n The number of locking grooves on the shaft head; Boundary conditions are .

7. A low-profile worm gear nut tightening system, characterized in that, The method for tightening the low-profile worm gear nut according to any one of claims 1 to 6 includes: The tightening angle calculation module is used to transmit the images of the nut locking groove and the shaft head locking groove on the low-pressure worm shaft to the real-time nut tightening angle measurement module to obtain the minimum angle difference between the nut locking groove and the shaft head locking groove. The nut tightening module is used to transmit the minimum angle difference to the motion control system, which tightens the nut on the low-profile worm shaft according to the minimum angle difference. The real-time nut tightening angle measurement module includes a feature extraction module, an error fusion module, and an angle calculation module. The feature extraction module is used to extract the boundary equations of the nut locking groove and the shaft head locking groove respectively. The error fusion module is used to filter the corresponding locking groove centerline equation based on the theoretical center value and the boundary equation. The angle calculation module is used to obtain the minimum angle difference between the nut locking groove and the shaft head locking groove according to the theoretical center value and the locking groove centerline equation.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of a low-profile worm gear nut tightening method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of a low-profile worm gear nut tightening method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of a low-profile worm gear nut tightening method as described in any one of claims 1 to 6.

Images