V-shaped notch test bar forming and grinding in-situ detection system and detection method based on white light interference and microscopic vision

Abstract

The invention discloses a V-shaped notch test bar forming and grinding in-situ detection system based on white light interference and microscopic vision, which comprises a system base, a white light interference testing device is arranged on the system base, and high-precision limiting detection devices are arranged on the two sides of the white light interference testing device. The high-precision limiting detection device is also fixedly arranged on the system base, and a test wheel fixing device is arranged on the system base. The invention belongs to the technical field of test bar grinding machining, specifically adopts double positions to collect macroscopic and microscopic morphology of grinding wheels and test bars at different angles, and is compact in structure and suitable for in-situ measurement; establishing a mapping relation between the grinding wheel surface microstructure parameters and the test bar notch bottom surface roughness; the method does not need separate multiple times of monitoring, can realize nondestructive detection, has high data acquisition efficiency, and the established model can directly predict the second surface roughness of the test bar.

Description

Technical Field

[0001] The invention belongs to the technical field of test bar grinding, and in particular relates to an on-site detection system and method for V-notch test bar forming grinding based on white light interference and microscopic vision. Background Art

[0002] The relationship between the size, shape, and surface topography of test bars and grinding wheels during grinding is complex and intimate, and studying this relationship has a critical impact on subsequent fatigue testing. Conventional testing of test bars and grinding wheels during grinding involves machining, downtime, offline testing, and re-clamping. To increase efficiency and reduce errors, we developed an in-situ testing system for notched test bar profile grinding. This system collects macroscopic and microscopic topographical data from the grinding wheel and test bar notch bottoms, and trains a machine learning network model on this data set. The resulting network is used to determine parameters related to the microscopic surface topography of the test bar notch bottom.

[0003] The existing grinding inspection process involves machining, disassembly, offline dimensional and shape measurement, and re-clamping. This traditional process presents several challenges. The process is complex, and repeated disassembly and assembly are labor-intensive. Since the subsequent development of a roughness prediction model for the notch bottom of a V-notch test bar requires surface topography data collection, offline inspection efficiency is low. Repeated disassembly and assembly can lead to loss of datums and introduce errors. Furthermore, research using white light interferometry to in-situ inspect the surface topography of test bars and grinding wheels is lacking. Summary of the Invention

[0004] The technical problems to be solved by the present invention are:

[0005] The traditional inspection process of test bar grinding is complicated and has large errors, and there is a lack of research on the use of white light interferometry to inspect the test bar and grinding wheel surface in situ.

[0006] In order to solve the above technical problems, the technical solution proposed in the present invention is: an in-situ detection system for V-notch test bar forming grinding based on white light interferometry and microscopic vision, including a system base, a white light interferometry test device is installed on the system base, high-precision limit detection devices are installed on both sides of the white light interferometry test device, and the high-precision limit detection devices are also fixed on the system base. A test wheel fixing device is provided on the system base, and the test wheel fixing device is perpendicular to the surface where the white light interferometry test device is located.

[0007] The white light interferometer testing device includes a lifting platform, on which a ball screw transmission group is fixedly installed. The ball screw transmission group is driven by a stepping motor. A white light interferometer is installed on the ball screw transmission group through an adapter thread connection, and an annular piezoelectric positioning platform is installed on the white light interferometer.

[0008] The high-precision limit detection device includes a fixture and a dimension measuring instrument. The fixture is fixed on the system base through a vertical bracket, and the dimension measuring instrument is installed on the fixture.

[0009] The clamps and vertical supports are respectively provided with two groups, and a backlight is installed on a group of clamps away from the size measuring instrument.

[0010] The detection method of the in-situ detection system for V-notch test bar profile grinding based on white light interferometry and microscopic vision includes the following steps:

[0011] S1: Stop the cylindrical grinding machine to cool down, wipe off the stains on the base and then place the detection system base;

[0012] S2: Install the white light interferometer and dimension measuring instrument of the detection system, ensuring that the instruments are aligned with the test wheel and test bar in the horizontal and vertical directions. Adjust the lifting platform for rough positioning, and locate the intersection of the line connecting the dimension measuring instrument and the back projection light and the ray starting from the white light interferometer lens at the top grinding area on the left side of the grinding wheel to ensure that the area measured by the system is the same grinding area.

[0013] S3: Power on, turn on the system and rear projection light source, and connect to the industrial control computer. Observe the displayed image and adjust the height of the vertical bracket until the industrial camera of the size detector can capture a clear image. Adjust the rear projection light brightness or system exposure according to the inspection working environment until a V-shaped image outline appears in the camera's field of view, and fine-tune until the outline is clear.

[0014] S4: Adjust the lifting platform to roughly position the white light interferometer light source, adjust the stepper motor to drive the ball screw transmission group to move the white light interferometer in the horizontal direction, and move it step by step until a clearer image is observed in the field of view. Reduce the adjustment step and move it further until some annular envelope interference fringes appear in the image in the field of view;

[0015] S5: When a few annular envelope-shaped interference fringes appear in the field of view, the motion control is switched to the annular piezoelectric positioning stage, which performs precise movement, performing step-by-step tomographic scanning with nanometer-level displacement, and recording the current height and displacement data. The camera moves step by step with a fixed step size until the annular envelope-shaped interference fringes disappear from the camera's field of view, and the current height is recorded again.

[0016] S6: After obtaining the upper and lower limits of the appearance and disappearance of the envelope-shaped interference fringes, the system automatically starts tomographic scanning, automatically moves step by step again at the upper and lower limits of the height and collects the current height image;

[0017] S7: Perform super depth of field image fusion to obtain high-resolution sequence images and three-dimensional point cloud data;

[0018] S8: Perform the same operations as S1-S7 above on the notch of the test V-shaped bar to obtain the microscopic morphology parameters of the test bar, calculate the microscopic morphology parameters such as surface roughness and the height of the exposed microscopic abrasive grains of the grinding wheel, and then prepare a data set. 75% of the data in the machine learning data set in the above steps is used as the training data set, and the remaining 25% is used as the validation data set;

[0019] S9: Apply machine learning algorithms including prediction models such as multi-layer perceptron to predict the roughness of the notch bottom of the test rod. Use MPL to establish a mapping relationship between the micromorphological parameters of the grinding wheel surface and the surface roughness of the notch bottom of the test rod. Then, evaluate the prediction model of MPL on the validation set.

[0020] The beneficial effects achieved by the present invention using the above structure are as follows:

[0021] A dual-camera system is used to collect the macro- and micro-morphologies of grinding wheels and test rods at different angles. The compact structure is suitable for on-site measurement. White light interferometry is used to detect and evaluate the micro-abrasive grains of the grinding wheel on-site, without the need for repeated disassembly for offline testing, reducing errors and avoiding loss of references. A mapping relationship between the micro-morphological parameters of the grinding wheel surface and the surface roughness of the bottom of the test rod notch is established. Non-destructive testing can be achieved without the need for multiple separate monitorings, with high data acquisition efficiency. The established model can directly predict the second surface roughness of the test rod. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a schematic diagram of the overall structure of the in-situ detection system for V-notch test bar profile grinding based on white light interferometry and microscopic vision proposed in the present invention;

[0023] Figure 2 This is a structural schematic diagram of another angle of the in-situ detection system for V-notch test bar profile grinding based on white light interferometry and microscopic vision proposed by the present invention;

[0024] Figure 3 for Figure 1 A partial enlarged view of part A;

[0025] Figure 4 for Figure 2 A partial enlarged view of part B;

[0026] Figure 5 This is a flow chart of the detection method of the in-situ detection system for V-notch test bar forming grinding based on white light interferometry and microscopic vision proposed by the present invention.

[0027] Among them, there are system base 1, test wheel fixing device 2, high-precision limit detection device 3, white light interference test device 4, lifting platform 5, ball screw transmission group 6, white light interferometer 7, annular piezoelectric positioning table 8, fixture 9, dimension measuring instrument 10, vertical bracket 11, and back projection light 12.

[0028] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0030] like Figure 1-4 As shown, the in-situ detection system for V-notch test bar forming grinding based on white light interference and microscopic vision proposed in the present invention includes a system base 1, a white light interference test device 4 is installed on the system base 1, and high-precision limit detection devices 3 are installed on both sides of the white light interference test device 4, and the high-precision limit detection device 3 is also fixed on the system base 1. A test wheel fixing device 2 is provided on the system base 1, and the test wheel fixing device 2 is perpendicular to the surface where the white light interference test device 4 is located. A grinding wheel is installed on the test wheel fixing device 2, and the grinding wheel test wheel fixing device 2 grinds the test bar. The lifting platform 5 can perform in-situ detection on the distribution state of abrasive particles in the grinding area of the grinding wheel and the exposed height, and can also perform in-situ detection on the surrounding morphology of the bottom of the V-shaped notch of the test bar.

[0031] The high-precision limit detection device 3 detects the shape parameters of the grinding area of the forming grinding wheel in situ to ensure the consistency of the arc radius of the grinding area of the grinding wheel and the soil size of the test rod notch. At the same time, the high-precision limit detection device 3 can also perform in-situ detection of the shape and size of the V-shaped notch of the test rod.

[0032] In order to perform white light interferometry detection more comprehensively, the white light interferometry testing device 4 includes a lifting platform 5, on which a ball screw transmission group 6 is fixedly installed. The ball screw transmission group 6 is driven by a stepping motor, and a white light interferometer 7 is installed on the ball screw transmission group 6 through an adapter thread connection. In order to perform more precise detection, an annular piezoelectric positioning platform 8 is installed on the white light interferometer 7.

[0033] In order to detect the macro shape and size of the grinding area on the top of the grinding wheel and adjust it according to test wheels of different specifications, the high-precision limit detection device 3 includes a clamp 9 and a dimension measuring instrument 10. The clamp 9 is fixed to the system base 1 through a vertical bracket 11. The dimension measuring instrument 10 is installed on the clamp 9. The clamp 9 is provided with a thread that can adjust the relative position between it and the vertical bracket 11 according to the use position.

[0034] The clamps 9 and the vertical brackets 11 are provided in two groups respectively. A backlight 12 is installed on a group of clamps 9 away from the size measuring instrument 10. The backlight 12 can provide a light source for the size measuring instrument 10 to fill in the light and obtain a perfect image.

[0035] When in use, the cylindrical grinding machine is stopped to cool down, and the base is wiped clean of stains before placing the device; install the white light interferometer 7 and the dimension measuring instrument 10 of the detection system, and ensure that the instrument is on the same plane as the test wheel and test rod to be tested in the horizontal and vertical directions. Adjust the lifting platform 5 for rough positioning, and position the intersection of the line connecting the dimension measuring instrument 10 and the backlight and the ray starting from the lens of the white light interferometer 7 at the top grinding area on the left side of the grinding wheel to ensure that the area measured by the system is the same grinding area; turn on the system and the backlight 12 and connect to the industrial control computer, observe the displayed image, adjust the height of the fixture 9 until the industrial camera of the dimension measuring instrument 10 can capture a clear image, adjust the brightness of the backlight 12 or the system exposure according to the detection working environment, adjust it until a V-shaped image outline appears in the camera's field of view, and fine-tune it until the outline is clear; adjust the lifting platform 5. Stage 5 performs coarse positioning of the white-light interferometer 7 light source. Adjust the stepper motor to drive the ball screw drive assembly 6 to move the white-light interferometer 7 horizontally, gradually moving until a clearer image is observed within the field of view. The adjustment step is then reduced, and further movement is performed until some annular, envelope-like interference fringes appear within the field of view. When these annular, envelope-like interference fringes appear within the field of view, the annular piezoelectric positioning stage 8 is adjusted for precise movement, performing a stepwise tomographic scan with nanometer-scale displacement, and recording the current height and displacement data. The stage is then moved gradually with a fixed step size until the envelope-like interference fringes disappear within the camera's field of view. The current height is then recorded again. The same procedure is repeated for testing the notch in the V-shaped rod.

[0036] After obtaining the upper and lower limits of the appearance and disappearance of the envelope-shaped interference fringes, the system automatically starts tomographic scanning, and automatically moves step by step again at the upper and lower limits of the height to collect the current height image;

[0037] Perform super-depth image fusion to obtain highly sequential images and 3D point cloud data;

[0038] After calculating the surface roughness, the height of the exposed micro-abrasive grains on the grinding wheel and other micro-morphological parameters, a data set was created. 75% of the data in the machine learning data set obtained in the above steps was used as the training data set, and the remaining 25% was used as the validation data set.

[0039] Machine learning algorithms including prediction models such as multi-layer perceptron are applied to predict the roughness of the notch bottom of the test rod. MPL is used to establish the mapping relationship between the micromorphological parameters of the grinding wheel surface and the surface roughness of the notch bottom of the test rod. The MPL prediction model is then evaluated on the validation set.

[0040] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0041] Unless otherwise expressly specified or limited, the terms "disposed," "installed," "connected," and "connected" should be understood broadly. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediary; and internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this application.

[0042] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

[0043] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. The V-notch test bar profile grinding in-situ detection system based on white light interferometry and microscopic vision is characterized by: The invention comprises a system base (1), a white light interference test device (4) is installed on the system base (1), high-precision limit detection devices (3) are installed on both sides of the white light interference test device (4), and the high-precision limit detection devices (3) are also fixedly arranged on the system base (1), and a test wheel fixing device (2) is provided on the system base (1), and the test wheel fixing device (2) and the surface where the white light interference test device (4) are located are perpendicular.

2. The V-notch test bar profile grinding in-situ detection system based on white light interferometry and microscopic vision according to claim 1 is characterized by: The white light interference test device (4) comprises a lifting platform (5), a ball screw transmission group (6) is fixedly mounted on the lifting platform (5), the ball screw transmission group (6) is driven by a stepping motor, a white light interferometer (7) is mounted on the ball screw transmission group (6) via an adapter thread connection, and an annular piezoelectric positioning platform (8) is mounted on the white light interferometer (7).

3. The V-notch test bar profile grinding in-situ detection system based on white light interferometry and microscopic vision according to claim 2 is characterized by: The high-precision limit detection device (3) comprises a fixture (9) and a dimension measuring instrument (10); the fixture (9) is fixed on the system base (1) via a vertical bracket (11); and the dimension measuring instrument (10) is mounted on the fixture (9).

4. The V-notch test bar profile grinding in-situ detection system based on white light interferometry and microscopic vision according to claim 3 is characterized by: The clamps (9) and vertical supports (11) are respectively provided in two groups, and a backlight (12) is installed on a group of clamps (9) away from the size measuring instrument (10).

Images