A method for inspecting axial deviation of a shaft hole of a component

Abstract

The application discloses a kind of part shaft hole shaft deviation inspection methods, it is related to detection technical field, and inspection method is:S1, the part to be inspected is placed on positioning assembly, and the part to be inspected is positioned and fixed by positioning assembly, wherein positioning assembly bottom is equipped with servo motor driven linear module, and the position of part positioning hole is photographed by industrial camera, the distance that positioning pin needs to adjust is automatically calculated, and linear module drives positioning pin to complete position self-adapting correction;S2, image acquisition is carried out based on camera, and the image data of the part to be inspected is obtained.The linear module driven by servo motor is cooperated with industrial camera, the position of positioning pin is automatically corrected, the error of artificial or fixed positioning is eliminated, the accurate reference for subsequent inspection is laid, whether qualified or not is quickly distinguished, when unqualified, the problem can be traced back, the direction for process adjustment is provided, the accurate quality control is assisted, and the circulation of unqualified products is reduced.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of detection, in particular to a part shaft hole shaft deviation inspection method. BACKGROUND

[0002] In the field of mechanical manufacturing, the shaft hole matching precision of parts directly determines the assembly quality and operation reliability of equipment, and the shaft hole deviation is one of the core defects affecting the matching precision, so efficient and accurate inspection of the shaft hole deviation of parts is very important. The current mainstream part shaft hole deviation inspection method generally has the problem of insufficient precision in the positioning link. The traditional positioning assembly mostly adopts fixed-size positioning pins or manual adjustment structures. When facing different specifications and batches of parts, the positioning parts need to be repeatedly disassembled, replaced and calibrated by manual operation, which is not only tedious and time-consuming, but also prone to positioning deviation due to manual operation errors, thereby affecting the accuracy of the subsequent inspection results, and it is difficult to cope with the positioning problems caused by the machining errors or surface state differences of the part positioning holes. To solve the above problems, a part shaft hole shaft deviation inspection method is provided. SUMMARY

[0003] To solve the above technical problems, a part shaft hole shaft deviation inspection method is provided, which solves the above problems.

[0004] To achieve the above purpose, the technical scheme adopted by the application is as follows: a part shaft hole shaft deviation inspection method, the inspection method is:

[0005] S1, placing the part to be inspected on the positioning assembly, positioning and fixing the part to be inspected through the positioning assembly, wherein the bottom of the positioning assembly is provided with a linear module driven by a servo motor, an industrial camera is used to shoot the position of the positioning hole of the part, the distance that the positioning pin needs to be adjusted is automatically calculated, and the linear module drives the positioning pin to complete the position self-adaptive correction;

[0006] S2, image acquisition is performed based on the camera, image data of the part to be inspected is obtained, and a data set is constructed after the image data is preprocessed;

[0007] S3, the data set is obtained, a hologram of the hole shaft region of the part is generated based on the holographic technology, feature parameters are extracted by analyzing the interference fringes of the hologram, and the extracted feature parameters include the center coordinates of the hole, the axis coordinates of the shaft, the diameter of the hole and the diameter of the shaft;

[0008] S4, the offset of the hole shaft is calculated according to the center coordinates of the hole and the axis coordinates of the shaft; the calculated offset is compared with the preset offset threshold value, if the offset is less than or equal to the threshold value, it is determined that the part hole shaft deviation is qualified; if the offset is greater than the threshold value, it is determined that the part hole shaft deviation is unqualified.

[0009] Preferably, the adaptive correction step in S1 is:

[0010] The part to be inspected is placed on the positioning assembly workbench, the rough positioning mark is roughly aligned, and the industrial camera is triggered to take a panoramic image of the part;

[0011] The image is uploaded, focused and recognized, the positioning hole area on the part is identified, the edge of the collected image is detected, the actual contour of the positioning hole is extracted, the geometric center coordinates of the positioning hole are calculated, and the position of the coordinates in the image coordinate system is recorded;

[0012] The standard CAD data of the part is called, the theoretical center coordinates of the positioning hole are obtained, and the deviation value between the actual coordinates and the theoretical coordinates is automatically calculated;

[0013] When the deviation value exceeds the allowed range of positioning accuracy, the automatic correction program is started, pulse signals are sent to the servo motor to drive the X and Y axes of the linear module to move along the planned path, and when the positioning pin moves to the theoretical coordinate position, the motor stops moving, and the preliminary correction is completed;

[0014] The industrial camera takes another image of the positioning hole, and detects the alignment state of the positioning pin after correction with the positioning hole;

[0015] If there is still a small deviation, send a fine-tuning instruction to drive the positioning pin at low speed to meet the positioning accuracy requirement;

[0016] After correction, the locking device of the positioning assembly locks the position of the positioning pin to fix it.

[0017] Preferably, the deviation value is obtained by calculating the X and Y axis directions, and then the deviation value is obtained; wherein the X axis direction deviation calculation formula is: ; wherein is the actual center X coordinate of the positioning hole obtained by image recognition, is the theoretical center X coordinate of the positioning hole in the standard CAD data, and ΔX is the X axis direction deviation;

[0018] The Y axis direction deviation calculation formula is: , wherein is the actual center Y coordinate of the positioning hole obtained by image recognition, is the theoretical center Y coordinate of the positioning hole in the standard CAD data, and ΔY is the Y axis direction deviation;

[0019] The comprehensive deviation distance calculation formula is: , wherein D is the straight line distance deviation between the actual center and the theoretical center, and whether it exceeds the allowed range of accuracy is judged.

[0020] Preferably, the data preprocessing in S2 includes image denoising, contrast enhancement, geometric correction, image segmentation and data standardization.

[0021] Preferably, the hologram generating step in S3 is:

[0022] The Mach-Zehnder interference optical path is adopted to divide the laser output by a helium-neon laser into object light and reference light, wherein the object light irradiates the hole axis region of the part to be inspected, carries geometric information after reflection and transmission on the hole axis surface, and propagates to the holographic plate; the reference light directly irradiates the holographic plate to generate interference with the object light on the plate to generate a hologram of the hole axis region after exposure;

[0023] An industrial camera is used to shoot the holographic plate to convert the optical hologram into a digital image; a gray scale correction algorithm is used to eliminate the gray scale deviation caused by the uneven response of the camera sensor; and Fourier transform is performed on the digital hologram.

[0024] Preferably, in S3, the interference fringe analysis is performed by using an adaptive threshold segmentation method to separate the fringes from the background, and a skeleton extraction algorithm is used to extract the center line of each interference fringe to obtain a continuous fringe center line network, wherein the edges of the hole and the axis correspond to specific fringe bending characteristics; the circular edge of the hole causes the optical path difference of the object light to change periodically, forming annular interference fringes with the hole as the center, and the fringe density decreases with the increase of the distance from the hole center; the cylindrical surface of the axis corresponds to parallel and uniform interference fringes, and the diameter change of the axis will cause the change of the fringe spacing; curvature fitting is performed on the annular fringes to determine the center position of each annular fringe; straight line fitting is performed on the parallel fringes to obtain the inclination angle and spacing of the fringes.

[0025] Preferably, in S3, the hole axis feature parameter acquisition is performed by selecting 3 annular interference fringes with different radii, fitting the center of each fringe, taking the average coordinates of the 3 centers as the actual center coordinates of the hole to eliminate the single-point deviation caused by fringe noise; the spacing Δd of the adjacent two annular fringes is measured, and according to the relationship between the fringe spacing and the optical path difference of the object light, Δd = λ / (2sinθ), wherein θ is the object light incidence angle and λ is the wavelength of the laser, the distance from the edge of the hole to the center, i.e. the radius of the hole, is calculated in combination with the position of the hole radius corresponding to the fringe, and the diameter radius;

[0026] 3 groups of parallel interference fringes corresponding to the axis are selected, sampling points are taken from each group of fringes, and the straight line equation of each fringe is fitted; the bisector of the adjacent two parallel fringes is calculated, and the intersection point of the 3 bisectors is the axis center coordinate of the axis;

[0027] The spacing Δs of the parallel interference fringes corresponding to the axis is measured, and according to the imaging principle of the cylindrical surface of the axis, the fringe spacing Δs and the diameter of the axis satisfy the relationship: , n is the air refractive index, and α is the reference light incidence angle. The diameter of the axis is calculated by substituting the known parameters.

[0028] Preferably, the offset calculation in S4 is to convert the hole center and shaft axis coordinates to the same coordinate system by unifying the coordinate reference, decompose each shaft offset component, calculate the horizontal and vertical offset, determine the offset degree and position relationship in each direction, calculate the comprehensive offset according to the matching scene, review the results, calculate the offset direction angle according to the demand, and store the data obtained.

[0029] Preferably, the comparison in S4 is to retrieve the matching threshold from the system database based on the part model, assembly scene and design requirements; compare the comprehensive offset with the threshold, when the offset is less than or equal to the threshold, it is determined to be qualified, the state is marked and the value is recorded for traceability; when the offset is greater than the threshold, it is determined to be unqualified, and an abnormal prompt is triggered; for the qualified parts with offset close to the threshold, mark them for attention, and track the deviation trend in subsequent batch inspection.

[0030] Compared with the prior art, the beneficial effects of the present application are:

[0031] The present application automatically corrects the position of the positioning pin by cooperating the linear module driven by the servo motor with the industrial camera, eliminates the error of manual or fixed positioning, lays a precise reference for subsequent inspection, adopts holographic technology for feature extraction, analyzes the interference fringes to obtain the hole shaft parameters, and the precision reaches sub-micron level, far exceeding the traditional method, accurately captures the subtle geometric features, adapts to the inspection requirements of precision parts, compares the offset with the threshold, the standard is clear and quantifiable, and the threshold can be flexibly adjusted according to the part scene, so that the qualified and unqualified can be quickly distinguished, the problem can be traced back when unqualified, the direction for process adjustment is provided, the precise quality control is assisted, and the circulation of unqualified products is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 The present application is a test step flow chart. DETAILED DESCRIPTION

[0033] The following description is used to disclose the present application so that those skilled in the art can implement the present application. The preferred embodiments in the following description are only as examples, and other obvious variants can be thought of by those skilled in the art.

[0034] Referring to Figure 1 As shown in the figure, a part shaft hole axis deviation inspection method, the inspection method is:

[0035] S1, place the part to be inspected on the positioning assembly, position and fix the part to be inspected through the positioning assembly, wherein the bottom of the positioning assembly is provided with a linear module driven by a servo motor, the position of the positioning hole of the part is shot by an industrial camera, the distance that the positioning pin needs to be adjusted is automatically calculated, and the linear module drives the positioning pin to complete the position self-adaptive correction;

[0036] S2, image acquisition based on camera, obtain the image data of the parts to be inspected, and construct a data set after preprocessing the image data;

[0037] S3, obtain the data set, generate a hologram of the hole-shaft region of the part based on holographic technology, analyze the interference fringes of the hologram, and extract feature parameters, including the center coordinates of the hole, the axis coordinates of the shaft, the diameter of the hole, and the diameter of the shaft;

[0038] S4, calculate the offset of the hole-shaft according to the center coordinates of the hole and the axis coordinates of the shaft; compare the calculated offset with the preset offset threshold value, if the offset is less than or equal to the threshold value, determine that the hole-shaft of the part is acceptable; if the offset is greater than the threshold value, determine that the hole-shaft of the part is unqualified.

[0039] The whole process of the application improves efficiency, servo motor automatically corrects positioning, automatically collects and analyzes, reduces manual intervention, shortens single inspection time by more than 50%, reduces labor cost; higher precision, holographic technology combined with image preprocessing, parameter measurement reaches micron level, quantitative judgment standard, avoids subjective error of manual work, reduces misjudgment rate; simplified operation, modularized process, personnel do not need complex technology, and data is automatically stored, which is convenient for tracing and reviewing, reduces training and recording cost; strong adaptability, can be connected with production line to realize production and inspection at the same time, can be adapted to multiple types of parts by adjusting parameters, meets batch and flexible production demand, is an inspection scheme suitable for intelligent manufacturing.

[0040] The adaptive correction step in S1 is:

[0041] Place the part to be inspected on the positioning assembly workbench, roughly align the coarse positioning mark, trigger the industrial camera to shoot the panoramic image of the part;

[0042] Upload the image, focus and identify the positioning hole region on the part, perform edge detection on the collected image, extract the actual contour of the positioning hole, calculate the geometric center coordinates of the positioning hole, and record the position of the coordinates in the image coordinate system;

[0043] Retrieve the standard CAD data of the part, obtain the theoretical center coordinates of the positioning hole, and automatically calculate the deviation value between the actual coordinates and the theoretical coordinates;

[0044] When the deviation value exceeds the allowed range of positioning accuracy, start the automatic correction program, send a pulse signal to the servo motor, drive the X and Y axes of the linear module to move along the planned path, and when the positioning pin moves to the theoretical coordinate position, the motor stops moving, completing the preliminary correction;

[0045] The industrial camera shoots the positioning hole image again, detects the alignment state of the corrected positioning pin and the positioning hole;

[0046] If there is still a slight deviation, send a fine-tuning instruction to drive the positioning pin at a low speed to achieve the positioning accuracy requirement;

[0047] After correction, the locking device of the positioning assembly locks the position of the positioning pin for fixation.

[0048] The process of the present application first takes a panoramic picture through an industrial camera, extracts the actual contour and geometric center of the positioning hole through edge detection, and then compares the standard CAD theoretical coordinates to calculate the deviation, ensuring accurate deviation identification; when the deviation exceeds the limit, the servo motor drives the linear module to move along the planned path, and after correction, the second shooting detection is performed, and slight deviation can be fine-tuned at a low speed, finally realizing positioning accuracy and providing accurate reference for image acquisition, parameter extraction and qualification determination, avoiding misjudgment caused by initial positioning deviation in subsequent inspection; reducing labor costs and operation threshold, from preliminary alignment triggering shooting to image analysis, deviation calculation, automatic correction and locking, there is no need for manual measurement of deviation and adjustment of positioning pin; even if fine-tuning is needed, the system automatically sends instructions, and the operator only needs to place the parts and preliminarily align the marks, reducing the manual intervention link, reducing the requirement for personnel technical level, and avoiding the problems of manual operation error and low efficiency; the correction process forms a closed loop of shooting recognition-deviation calculation-driving correction-second detection-fine-tuning-locking, each link has data support and result verification to ensure that the positioning deviation is fully corrected; after correction, the locking device locks the positioning pin to prevent displacement of the parts in subsequent inspection, ensuring stable positioning state and further improving the reliability and consistency of the overall inspection process.

[0049] The deviation value is calculated in the X-axis and Y-axis directions, and then the deviation value is obtained; the deviation calculation formula in the X-axis direction is: ; wherein is the actual center X coordinate of the positioning hole obtained by image recognition, is the theoretical center X coordinate of the positioning hole in the standard CAD data, and ΔX is the deviation in the X-axis direction.

[0050] The deviation calculation formula in the Y-axis direction is: , wherein is the actual center Y coordinate of the positioning hole obtained by image recognition, is the theoretical center Y coordinate of the positioning hole in the standard CAD data, and ΔY is the deviation in the Y-axis direction.

[0051] The comprehensive deviation distance calculation formula is: , wherein D is the straight line distance deviation between the actual center and the theoretical center, and whether it exceeds the allowable range of accuracy is judged.

[0052] The present application can The deviation in the X-axis direction and the deviation in the Y-axis direction are calculated respectively, so that the specific deviation in the horizontal direction or the vertical direction can be directly located, the corresponding shaft of the linear module can be driven by the servo motor for targeted adjustment, and the problems of low correction efficiency and repeated debugging caused by traditional overall deviation fuzzy adjustment can be avoided; the shaft deviation calculation also reduces the possibility that a single comprehensive deviation calculation may cover up the case that the deviation of one axis exceeds the limit, so that the deviation analysis is more detailed; the comprehensive deviation quantification is more comprehensive, and the precision determination is more reliable; the comprehensive deviation between the actual center and the theoretical center is calculated through the straight-line distance formula, so that the spatial deviation state of the positioning hole can be completely reflected; even when the single-axis deviation of the X-axis and the Y-axis does not exceed the limit, the comprehensive deviation may still exceed the limit due to the superposition of the deviations of the two axes; this calculation method can avoid the loophole that the single-axis deviation meets the standard and is determined to be qualified, ensures that the positioning accuracy completely meets the inspection requirements, and provides more reliable reference for subsequent image acquisition and parameter extraction; the determination standard is objective and unified, and subjective errors are reduced; whether the shaft deviation or the comprehensive deviation is calculated, the calculation is based on the actual coordinates and the theoretical coordinates through a fixed formula, without manual estimation or experience-based judgment; when different operators or different batches of parts are inspected, the deviation calculation logic and the determination basis are completely consistent, so that the deviation determination difference caused by subjective operation is completely eliminated, and the uniformity of the positioning correction standard and the reliability of the inspection result are ensured.

[0053] The data preprocessing in the S2 step includes image denoising processing, contrast enhancement, geometric correction, image segmentation and data standardization processing.

[0054] The hologram generation step in the S3 step is:

[0055] A Mach-Zehnder interference optical path is adopted, and the laser output by the helium-neon laser is divided into object light and reference light; the object light irradiates the hole shaft region of the part to be inspected, carries geometric information after reflection and transmission on the hole shaft surface, and propagates to the holographic plate; the reference light directly irradiates the holographic plate to generate interference with the object light on the plate, and a hologram of the hole shaft region is generated after exposure;

[0056] An industrial camera is used to shoot the holographic plate, and the optical hologram is converted into a digital image; a gray scale correction algorithm is used to eliminate the gray scale deviation caused by uneven response of the camera sensor; and Fourier transform is performed on the digital hologram.

[0057] A Mach-Zehnder interference optical path is adopted, and the laser is divided into object light and reference light; when the object light irradiates the hole shaft region, it carries three-dimensional geometric information of the surface topography, the hole size and the axis position of the hole shaft, and then interferes with the reference light on the holographic plate to form an image; this method is different from the traditional two-dimensional image which only records plane information, and can completely retain the spatial structure details of the hole shaft, so that even a small hole deviation or axis deviation can be reflected through the distribution difference of the interference fringes, and provide comprehensive data support for subsequent extraction of the center coordinates and the diameter of the key parameters;

[0058] The optical holography is digitized to improve the processing convenience and precision. The optical hologram is converted into a digital image through an industrial camera, breaking the limitation of traditional optical hologram relying on physical dry plate and difficult to subsequent analysis, and facilitating accurate processing through computer algorithm. The gray scale correction algorithm can eliminate the gray scale deviation caused by uneven response of camera sensor, avoid image brightness imbalance caused by hardware difference, and ensure that the gray scale distribution of digital hologram truly reflects the interference fringe characteristics, providing high-quality digital image source for subsequent Fourier transform.

[0059] In the S3 step, the interference fringe analysis separates the fringes from the background by using the adaptive threshold segmentation method, extracts the center line of each interference fringe by using the skeleton extraction algorithm, and obtains a continuous fringe center line network, in which the edges of the hole and the shaft correspond to specific fringe bending characteristics. The circular edge of the hole causes the optical path difference of the object light to change periodically, forming a ring-shaped interference fringe centered on the hole, and the fringe density decreases with the increase of the distance from the hole center. The cylindrical surface of the shaft corresponds to parallel and uniform interference fringes, and the diameter change of the shaft will cause the change of the fringe spacing. The curvature fitting is performed on the ring-shaped fringes to determine the center position of each ring-shaped fringe. The straight line fitting is performed on the parallel fringes to obtain the inclination angle and spacing of the fringes.

[0060] The adaptive threshold segmentation method is used in the present application, which can dynamically adjust the segmentation threshold according to the gray scale difference between the interference fringes and the background, avoid the problem that the fixed threshold is difficult to adapt to different regions, efficiently separate the fringes from the complex background, ensure that the subsequent analysis only focuses on the effective fringe information, exclude the interference of background noise on feature recognition, and improve the accuracy of fringe analysis.

[0061] In the S3 step, the hole shaft feature parameter acquisition selects 3 ring-shaped interference fringes with different radii, fits the center of each fringe, takes the average coordinates of the 3 centers as the actual center coordinates of the hole, and eliminates the single-point deviation caused by fringe noise. The spacing Δd of the adjacent two ring-shaped fringes is measured, the relationship between the fringe spacing and the optical path difference of the object light is Δd = λ / (2sinθ), where θ is the incidence angle of the object light and λ is the wavelength of the laser, the distance from the edge of the hole to the center is calculated according to the position of the hole radius corresponding to the fringe, that is, the radius of the hole, and the diameter radius;

[0062] Three groups of parallel interference fringes corresponding to the shaft are selected, and the straight line equation of each fringe is obtained by fitting the sampling points of each group of fringes. The perpendicular bisectors of the adjacent two parallel fringes are calculated, and the intersection point of the three perpendicular bisectors is the axis coordinate of the shaft.

[0063] The spacing Δs of the parallel interference fringes corresponding to the shaft is measured, and according to the imaging principle of the cylindrical surface of the shaft, the relationship between the fringe spacing Δs and the diameter D of the shaft satisfies the relationship: ​, n is the air refractive index, and a is the reference light incidence angle, and the diameter of the shaft is calculated by substituting the known parameters.

[0064] When the application obtains the coordinates of the center of the hole, three annular fringes with different radii are selected to fit the center of the circle, and then the average coordinates are obtained, which effectively offsets the deviation of the center of the circle caused by noise and local interference anomalies of a single fringe, and avoids accidental errors of single-point fitting; when the application obtains the coordinates of the center of the shaft, the intersection of the midlines of the three groups of parallel fringes is determined, and the geometric logic of three lines intersecting at a point is used to reduce the influence of fitting deviation of a single group of fringes on the positioning of the center of the shaft, so that the core coordinate parameters of the hole and the shaft are closer to the actual values.

[0065] In the S4 step, the offset calculation converts the coordinates of the center of the hole and the center of the shaft to the same coordinate system, decomposes the offset components of each shaft, calculates the horizontal and vertical offset, determines the offset degree and position relationship in each direction, calculates the comprehensive offset according to the matching scene, reviews the results, calculates the offset direction angle according to the requirements, and stores the data obtained.

[0066] The application converts the coordinates of the center of the hole and the center of the shaft to the same coordinate system, completely solves the misplacement problem of offset calculation caused by the fact that the coordinates of the hole and the shaft belong to different dimensions, avoids the miscomputation of the offset caused by the difference in coordinate systems in the early image acquisition and parameter extraction link, and ensures that the decomposition of the horizontal and vertical offset components and the calculation of the comprehensive offset are based on the same spatial dimension, thereby ensuring the data comparability and calculation accuracy from the source.

[0067] In the S4 step, the comparison is based on the part model, assembly scene and design requirements to retrieve the matching threshold from the system database; when the comprehensive offset is ≤ the threshold, it is determined to be qualified, the state is marked and the value is recorded for tracing; when the offset is > the threshold, it is determined to be unqualified, and an abnormal prompt is triggered; for the qualified parts with offset close to the threshold, mark them for attention, and track the deviation trend in the subsequent batch inspection.

[0068] The above shows and describes the basic principles, main features and advantages of the application. Those skilled in the art should understand that the application is not limited to the above examples, and the above examples and descriptions in the specification are only the principles of the application. Without departing from the spirit and scope of the application, various changes and improvements can be made to the application, and these changes and improvements all fall within the scope of the claimed application. The scope of protection claimed by the application is defined by the appended claims and their equivalents.

Claims

1. A method for inspecting shaft offset of a component's shaft hole, characterized in that, The test method is: S1, the parts to be tested are placed on the positioning assembly, and the parts to be tested are positioned and fixed by the positioning assembly, wherein the bottom of the positioning assembly is provided with a linear module driven by a servo motor, the position of the positioning hole of the part is shot by an industrial camera, the distance that the positioning pin needs to be adjusted is automatically calculated, and the linear module drives the positioning pin to complete the self-adaptive correction of the position; S2, image acquisition is performed based on the camera, image data of the parts to be tested is obtained, and the data set is constructed after the image data is preprocessed; S3, the data set is obtained, a hologram of the hole shaft region of the part is generated based on holographic technology, feature parameters are extracted by analyzing the interference fringes of the hologram, and the extracted feature parameters include the center coordinates of the hole, the axis coordinates of the shaft, the diameter of the hole and the diameter of the shaft; S4, according to the center coordinates of the hole and the axis coordinates of the shaft, the offset of the hole shaft is calculated; compare the calculated offset with the preset offset threshold value, if the offset is less than or equal to the threshold value, it is determined that the hole shaft of the part is qualified; if the offset is greater than the threshold value, it is determined that the hole shaft of the part is unqualified.

2. A method of inspecting a shaft hole of a component shaft according to claim 1, characterized by, The adaptive correction step in S1 step is: Place the part to be tested on the workbench of the positioning assembly, roughly align the coarse positioning mark, and trigger the industrial camera to shoot a panoramic image of the part; Upload the image, focus and identify the positioning hole region on the part, perform edge detection on the collected image, extract the actual contour of the positioning hole, calculate the geometric center coordinates of the positioning hole, and record the position of the coordinates in the image coordinate system; Call the standard CAD data of the part to obtain the theoretical center coordinates of the positioning hole, and automatically calculate the deviation value of the actual coordinates and the theoretical coordinates; When the deviation value exceeds the allowed range of positioning accuracy, start the automatic correction program, send a pulse signal to the servo motor to drive the X and Y axes of the linear module to move along the planned path, and when the positioning pin moves to the theoretical coordinate position, the motor stops moving, and the preliminary correction is completed; The industrial camera shoots the positioning hole image again, and detects the alignment state of the positioning pin after correction and the positioning hole; If there is still a small deviation, send a fine tuning instruction to drive the positioning pin at a low speed to meet the positioning accuracy requirement; After the correction is completed, the locking device of the positioning assembly locks the position of the positioning pin.

3. A method of inspecting a shaft hole of a component shaft according to claim 2, characterized in that: The deviation value is calculated in the X and Y axis directions, and then the deviation value is obtained; The X-axis direction deviation calculation formula is: ; wherein is the X coordinate of the actual center of the positioning hole obtained through image recognition, is the X coordinate of the theoretical center of the positioning hole in the standard CAD data, and ΔX is the X-axis direction deviation. The Y-axis direction deviation calculation formula is: Wherein is the positioning hole actual center Y coordinate obtained by image recognition, is the positioning hole theoretical center Y coordinate in the standard CAD data, and ΔY is the Y-axis direction deviation. The comprehensive deviation distance calculation formula is: Wherein D is the linear distance deviation between the actual center and the theoretical center, and whether it exceeds the accuracy allowable range is judged.

4. The method of claim 1, wherein: The data preprocessing in S2 step includes image denoising, contrast enhancement, geometric correction, image segmentation and data standardization.

5. The method of claim 1, wherein, The hologram generation step in S3 step is: A Mach-Zehnder interference optical path is adopted, and the laser output by a helium-neon laser is divided into object light and reference light, wherein the object light irradiates the hole shaft region of the part to be tested, and carries geometric information after reflection and transmission on the surface of the hole shaft to a holographic dry plate; the reference light directly irradiates the holographic dry plate to produce interference with the object light on the dry plate, and a hologram of the hole shaft region is generated after exposure; An industrial camera is used to shoot the holographic dry plate, the optical hologram is converted into a digital image, the gray scale deviation caused by the uneven response of the camera sensor is eliminated by a gray scale correction algorithm, and the digital hologram is subjected to Fourier transform.

6. A method of inspecting a shaft hole of a component shaft according to claim 1, characterized by: In the S3 step, the interference fringes are separated from the background by using adaptive threshold segmentation method, and the center line of each interference fringe is extracted by skeleton extraction algorithm to obtain a continuous fringe center line network, in which the edges of the hole and the shaft correspond to specific fringe bending characteristics; The circular edge of the hole makes the optical path difference of the object light change periodically, forming a ring-shaped interference fringe centered on the hole, and the fringe density decreases with the increase of the distance from the hole center; the cylindrical surface of the shaft corresponds to parallel and uniform interference fringes, and the diameter change of the shaft will cause the change of the fringe spacing; The curvature fitting is performed on the ring-shaped fringes to determine the center position of each ring-shaped fringe; the straight line fitting is performed on the parallel fringes to obtain the inclination angle and spacing of the fringes.

7. The method of claim 1, wherein: In the S3 step, the characteristic parameters of the hole axis are obtained by selecting three different radius annular interference fringes, fitting the center of each fringe, taking the average coordinates of the three centers as the actual center coordinates of the hole to eliminate single point deviation caused by fringe noise; the distance Δd between the adjacent two annular fringes is measured, according to the relationship between the distance of the interference fringes and the optical path difference of the object light, Δd = λ / (2sinθ), wherein θ is the incidence angle of the object light, λ is the wavelength of the laser, and the distance from the edge of the hole to the center, that is, the radius of the hole, is calculated in combination with the position of the hole radius corresponding to the fringe, to obtain the diameter ; Three groups of parallel interference fringes corresponding to the shaft are selected, sampling points are taken from each group of fringes, and the straight line equation of each fringe is fitted; the bisector of the adjacent two parallel fringes is calculated, and the intersection point of the three bisectors is the coordinate of the shaft center; The pitch Δs of the parallel interference fringes corresponding to the measuring shaft is measured, according to the cylindrical surface imaging principle of the shaft, the pitch Δs of the fringes is related to the diameter D of the shaft The relationship is satisfied: , n is the air refractive index, and α is the reference light incidence angle. The diameter of the shaft is calculated by substituting the known parameters.

8. The method of claim 1, wherein: In the S4 step, the hole center and the shaft center coordinates are converted to the same coordinate system by using a unified coordinate reference, and the horizontal and vertical offset components are decomposed to determine the offset degree and position relationship in each direction, calculate the comprehensive offset according to the matching scene, review the results, calculate the offset direction angle according to the requirements, and organize and store the obtained data.

9. A method of inspecting a shaft hole of a component shaft according to claim 1, characterized by: In the S4 step, the matching threshold is called from the system database based on the part model, assembly scene and design requirements; the comprehensive offset is compared with the threshold, when the offset is less than or equal to the threshold, it is determined to be qualified, the state is marked and the value is recorded for tracing; when the offset is greater than the threshold, it is determined to be unqualified, and an abnormal prompt is triggered; For qualified parts with offset close to the threshold, mark them for attention, and track the deviation trend in subsequent batch inspection.

Images