High-precision positioning device for additive manufacturing of composite materials

Abstract

The present invention discloses a high-precision positioning device for additive manufacturing of composite materials in the field of additive manufacturing, including an additive manufacturing device body, the additive manufacturing device body including a printing platform, a printing nozzle, a nozzle moving drive device and a grating projector; a nozzle mounting seat is provided on the nozzle moving drive device, a positioning beam emitter is provided on the nozzle mounting seat, a stereo microscope is provided on the nozzle mounting seat, a camera is provided on the microscope head of the stereo microscope, and the camera signal is connected to a controller; the controller is used to obtain an imaging image of the stereo microscope, and a trained convolutional neural network is provided in the controller, and the convolutional neural network is used to identify the grating and the positioning beam strike point in the imaging image, and control the nozzle moving drive device to adjust the nozzle mounting seat position until the beam strike point is located at the cross intersection of the grating. The technical solution of the present invention is adopted, and positioning is performed through the grating and the positioning beam, so as to improve the moving accuracy of the printing nozzle.

Description

Technical Field

[0001] The invention belongs to the field of additive manufacturing, and in particular relates to a high-precision positioning device for additive manufacturing of composite materials. Background Art

[0002] 3D printing is a rapid prototyping technology. It is based on digital models and uses computer software to control various types of bondable materials such as metal powder, fluid materials, plastics, etc., and uses a layer-by-layer stacking method to build a three-dimensional object. In the prior art, the main motion mechanisms of the three axes of 3D printers often have a certain return difference, the Z-axis positioning accuracy of vertical motion is low, the effective travel range is small and limited by the structure, and the 3D printers of the prior art have a single function and can usually only complete the additive manufacturing function. Coordinate measurement technology is mainly used for geometric measurement. Objects of any shape are composed of spatial points, and the geometric measurement of objects can be attributed to the measurement of spatial points. In the additive manufacturing process, by accurately collecting the coordinates of the spatial points of the constructed object, the coordinate values ​​of these points are processed by computer data to obtain its shape, position and other geometric data.

[0003] In order to solve the above problems, patent publication number CN108515696A discloses an additive manufacturing equipment and a high-precision positioning method thereof, including a 3D printing unit, a positioning unit, a measuring unit and a control system. Among them, the 3D printing unit includes a feeding mechanism and one or more 3D printing nozzles, the feeding mechanism is used to transport printing consumables to the 3D printing nozzles to print objects; the positioning unit is arranged on a base, the 3D printing nozzles are installed on the positioning unit, the positioning unit includes an air-floating guide rail mechanism, and the air-floating guide rail mechanism drives the positioning unit to move in a three-dimensional direction relative to the base; the measuring unit is used to measure the spatial position of the printed object, and is used to measure the movement position of the positioning unit; the control system is used to receive and process the measurement results of the measuring unit, and control the corresponding movement of the air-floating guide rail mechanism based on the measurement results.

[0004] The above-mentioned additive manufacturing equipment and its high-precision positioning method adjust the corresponding movement of the air-floating guide mechanism by measuring the spatial position of the printed object. However, the printing process has high precision. Due to technical limitations, the relative position of the printed object and the printing nozzle is difficult to locate with high precision. In addition, the air-floating guide mechanism will produce precision errors due to thermal expansion and contraction or aging due to long-term use. Summary of the invention

[0005] In order to solve the problem in the prior art that the relative position of the printing object and the printing nozzle is difficult to locate with high precision, the purpose of the present invention is to provide a high-precision positioning device for additive manufacturing of composite materials, which improves the movement accuracy of the printing nozzle by positioning through a grating and a positioning beam.

[0006] In order to achieve the above-mentioned object, the technical solution of the present invention is as follows: a high-precision positioning device for additive manufacturing of composite materials, comprising an additive manufacturing device body, the additive manufacturing device body comprising a printing platform, a printing nozzle, a nozzle moving drive device and a grating projector;

[0007] The nozzle moving drive device is provided with a nozzle mounting seat, the nozzle mounting seat is provided with a feeding assembly, the printing nozzle is fixedly connected to the nozzle mounting seat, the printing nozzle is communicated with the feeding assembly, the nozzle mounting seat is provided with a positioning beam emitter, the nozzle mounting seat is provided with a stereo microscope, the light source and the microscope head of the stereo microscope are respectively located on both sides of the printing nozzle, a camera is provided on the microscope head of the stereo microscope, and the camera signal is connected with a controller;

[0008] The grating projector is located above the printing platform, and the grating projector is used to project the grating onto the printing platform;

[0009] The controller is used to obtain the imaging image of the stereo microscope. A trained convolutional neural network is provided in the controller. The convolutional neural network is used to identify the grating and the positioning beam impact point in the imaging image, determine the relative position of the grating cross intersection and the positioning beam impact point, and control the nozzle movement drive device to adjust the nozzle mounting position until the beam impact point is located on the grating cross intersection.

[0010] The above solution achieves the following beneficial effects: the print head can perform additive manufacturing on the printing platform to produce workpieces. When manufacturing starts, the grating projector projects a grating on the printing platform, and then the print head starts additive manufacturing under the drive of the print head moving drive device.

[0011] The stereo microscope is used to obtain an enlarged image of the spraying location. Since the distance between the print head and the workpiece is stable when the print head is printing, the image of the spraying location can be obtained by fixing the focus of the stereo microscope. The workpiece is irradiated by the grating, so the grating will appear on the surface of the workpiece, and the positioning beam emitted by the positioning beam emitter will also hit the surface of the workpiece. The controller identifies the image of the spraying location and determines whether the impact point of the positioning beam and the cross intersection of the grating coincide. If they do not coincide, the control head movement drive device adjusts the print head position through negative feedback regulation to align the positioning beam with the cross intersection of the grating. The distance between the print head and the positioning beam emitter is a fixed value, so the spraying position of the print head is also calibrated.

[0012] Compared with the prior art, a grating projector projects a grating grid as a reference system, a stereo microscope magnifies the image at the spraying location, and a convolutional neural network is used to determine the relative position of the positioning beam and the grating grid, so that the moving position of the nozzle moving drive device can be detected and negative feedback adjustment can be performed to ensure accuracy. The requirements for camera equipment are reduced through the stereo microscope, and the movement difference of the nozzle moving drive device is displayed in the lens of the stereo microscope through the light beam.

[0013] Furthermore, the grid of the grating is square, and the distance between the positioning beam emitter and the center of the printing nozzle is a multiple of the grid length.

[0014] Beneficial effect: The distance between the positioning beam emitter and the center of the print head is a multiple of the grid length, which makes it easier to calculate the position of the print head and to perform operations according to the grid.

[0015] Furthermore, the material feeding assembly includes a material changing wheel, which is rotatably connected to the nozzle mounting seat, and a plurality of material feeding pipes are circumferentially connected to the material changing wheel. A tooth pattern is provided on the lower outer side of the material changing wheel, and a motor is provided in the nozzle mounting seat. A gear is fixedly connected to the output shaft of the motor, and the gear is meshed with the tooth pattern. A raw material heater is provided in the nozzle mounting seat, and the material changing wheel is used to rotate and switch the type of raw material entering the raw material heater, and the raw material heater is connected to the printing nozzle.

[0016] Beneficial effect: The device can drive the gear to rotate through the motor to drive the material changing wheel to rotate, switch the material sprayed by the printing nozzle, and produce composite material workpieces.

[0017] Furthermore, the controller is connected to the raw material heater signal. The controller stores the number of the feed pipe, the relationship function between the motor rotation angle and the number of the feed pipe connected to the raw material heater, and the rated heating temperature of each raw material. The controller obtains the current material temperature that needs to be preheated through the relationship function and controls the raw material heater to change the temperature.

[0018] Beneficial effects: Materials of different textures have different heating temperatures. Improper temperatures can easily cause the raw materials to solidify before forming or solidify too slowly, resulting in poor forming quality. By identifying the type of raw materials and heating them, materials of different textures can achieve better solidification effects.

[0019] Furthermore, the convolutional neural network is also used to identify the solidification process of the raw material after it is ejected, and to rate the solidification effect, and to adjust the heating temperature of the raw material heater for the material according to the rating results.

[0020] Beneficial effects: The raw material process, indoor temperature and raw material heater aging will affect the melting and solidification of the raw materials. The convolutional neural network is used to analyze the solidification image, and the heating temperature of the material is continuously adjusted according to the molding shape and solidification time, so as to further improve the solidification effect of each material and improve the microscopic quality of the workpiece.

[0021] Furthermore, the controller is used to record process data of controlling the nozzle mounting seat until the light beam impact point is located at the cross intersection of the grating. When the same process data is recorded multiple times, the control parameters of the nozzle movement drive device are corrected according to the process data.

[0022] Beneficial effect: Negative feedback adjustment can ensure accuracy, but the processing time is prolonged. By recording the process data during the adjustment process, the control parameters of the nozzle movement drive device are corrected, the adjustment amount in subsequent processing is reduced, and the processing speed is increased.

[0023] Furthermore, the light beams produced by the raster projector and the positioning beam emitter are different in color.

[0024] Beneficial effect: Different light beam colors are conducive to the recognition of convolutional neural networks, making the light beams generated by the grating projector and the positioning beam transmitter have more features, thereby accelerating the recognition and judgment speed of the convolutional neural network.

[0025] Furthermore, a curtain is provided on the printing platform for blocking natural light.

[0026] Beneficial effect: The curtain can reduce the interference of natural light on the light beam, making the light beam less obvious. By blocking the natural light with the curtain, the interference of natural light on the light beam can be reduced, and the recognition and judgment speed of the convolutional neural network can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 Schematic diagram of an embodiment of the present invention.

[0028] Figure 2 This is a schematic diagram of the structure of the nozzle mounting base.

[0029] List of reference numerals:

[0030] Printing platform 1, printing nozzle 2, nozzle moving drive device 3, grating projector 4, nozzle mounting seat 5, feeding assembly 6, positioning beam emitter 7, stereo microscope 8, camera 9, controller 10, material changing wheel 11, feeding tube 12, tooth pattern 13, motor 14, gear 15, raw material heater 16, curtain 17. DETAILED DESCRIPTION

[0031] The present invention is further explained below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the following specific embodiments are only used to illustrate the present invention and are not used to limit the scope of the present invention. It should be noted that the words "front", "rear", "left", "right", "upper" and "lower" used in the following description refer to directions in the accompanying drawings, and the words "inner" and "outer" refer to directions toward or away from the geometric center of a specific component, respectively.

[0032] Embodiment 1

[0033] The embodiment is basically as shown in the attached Figure 1 and attached Figure 2 As shown:

[0034] A high-precision positioning device for additive manufacturing of composite materials, comprising an additive manufacturing device body, wherein the additive manufacturing device body comprises a printing platform 1, a printing nozzle 2, a nozzle moving drive device 3 and a grating projector 4, wherein the model of the printing nozzle 2 is Ender-3, and the model of the grating projector 4 is DBF6;

[0035] The nozzle moving drive device 3 is an electric lead screw, the model of the electric lead screw is 6mEMG6y5, the nozzle moving drive device 3 is slidably connected with a nozzle mounting seat 5, a feeding assembly 6 is installed on the nozzle mounting seat 5, the printing nozzle 2 is screwed to the nozzle mounting seat 5, the printing nozzle 2 is connected to the feeding assembly 6, a positioning beam emitter 7 is screwed to the nozzle mounting seat 5, the beam emitter is a laser pen, the model of the beam emitter is TIP-015, a stereo microscope 8 is installed on the nozzle mounting seat 5, the light source and the microscope head of the stereo microscope 8 are respectively located on both sides of the printing nozzle 2, a camera 9 is bolted to the microscope head of the stereo microscope 8, the model of the camera 9 is DV255K, the camera 9 signal is connected to the controller 10, the model of the controller 10 is CLB-SMP01;

[0036] The grating projector 4 is located above the printing platform 1, and the grating projector 4 is used to project the grating onto the printing platform 1;

[0037] The controller 10 is used to obtain the imaging image of the stereo microscope 8. A trained convolutional neural network is provided in the controller 10. The convolutional neural network is used to identify the grating and the positioning beam impact point in the imaging image, determine the relative position of the grating cross intersection and the positioning beam impact point, and control the nozzle moving drive device 3 to adjust the nozzle mounting seat 5 position until the beam impact point is located on the grating cross intersection.

[0038] The specific implementation process is as follows: the print head 2 can perform additive manufacturing on the printing platform 1 to produce a workpiece. When manufacturing starts, the grating projector 4 projects a grating on the printing platform 1, and then the print head 2 starts additive manufacturing under the drive of the print head moving drive device 3.

[0039] The stereo microscope 8 is used to obtain an enlarged image of the spraying location. Since the distance between the print head 2 and the workpiece is stable when the print head 2 is in operation, the image of the spraying location can be obtained by fixing the focus of the stereo microscope 8. The workpiece is irradiated by the grating, so the grating will appear on the surface of the workpiece, and the positioning beam emitted by the positioning beam emitter 7 will also hit the surface of the workpiece. The controller 10 identifies the image of the spraying location and determines whether the impact point of the positioning beam and the cross intersection of the grating coincide. If they do not coincide, the nozzle moving drive device 3 is controlled to adjust the position of the print head 2 through negative feedback regulation so that the positioning beam is aligned with the cross intersection of the grating. The distance between the print head 2 and the positioning beam emitter 7 is a fixed value, so the spraying position of the print head 2 is also calibrated.

[0040] The invention uses a grating projector 4 to project a grating grid as a reference system, a stereo microscope 8 to magnify the image at the spraying location, and a convolutional neural network to determine the relative position of the positioning light beam and the grating grid, so that it can detect the moving position of the nozzle moving drive device 3, and perform negative feedback adjustment to ensure accuracy. The stereo microscope 8 reduces the requirements for the camera equipment, and the movement difference of the nozzle moving drive device 3 is displayed in the lens of the stereo microscope 8 through the light beam.

[0041] Embodiment 2

[0042] The difference from the above embodiment is that the grid of the grating is square, and the distance between the positioning beam emitter 7 and the center of the print head 2 is a multiple of the grid length.

[0043] The specific implementation process is as follows: the distance between the positioning beam emitter 7 and the center of the print head 2 is a multiple of the grid length, which makes it easier to calculate the position of the print head 2 and to perform operations according to the grid.

[0044] Embodiment 3

[0045] The difference from the above embodiment is that: the feeding assembly 6 includes a material changing wheel 11, which is rotatably connected to the nozzle mounting seat 5, and a plurality of feeding pipes 12 are circumferentially connected to the material changing wheel 11. A tooth pattern 13 is integrally formed on the lower outer side of the material changing wheel 11. A motor 14 is fixed by screws in the nozzle mounting seat 5. The model of the motor 14 is GSR120-L i. A gear 15 is welded and fixed on the output shaft of the motor 14. The gear 15 is meshed with the tooth pattern 13. A raw material heater 16 is fixed by screws in the nozzle mounting seat 5. The model of the raw material heater 16 is OLOEY yy8. The material changing wheel 11 is used to rotate and switch the type of raw material entering the raw material heater 16. The raw material heater 16 is connected to the printing nozzle 2.

[0046] The specific implementation process is as follows: the device can drive the gear 15 to rotate through the motor 14, thereby driving the material changing wheel 11 to rotate, switching the material sprayed by the printing nozzle 2, and manufacturing the composite material workpiece.

[0047] Embodiment 4

[0048] The difference from the above-mentioned embodiment is that the controller 10 is connected to the raw material heater 16 signal, and the controller 10 stores the number of the feed pipe 12, the relationship function between the rotation angle of the motor 14 and the number of the feed pipe 12 connected to the raw material heater 16, and the rated heating temperature of each raw material. The controller 10 obtains the current material temperature that needs to be preheated through the relationship function, and controls the raw material heater 16 to change the temperature.

[0049] The specific implementation process is as follows: different materials have different heating temperatures. Improper temperatures can easily cause the raw materials to solidify before forming or solidify too slowly, resulting in poor forming quality. By identifying the type of raw materials and heating them, materials of different textures can achieve better solidification effects.

[0050] Embodiment 5

[0051] The difference from the above embodiment is that the convolutional neural network is also used to identify the solidification process of the raw material after it is ejected, and to rate the solidification effect, and to adjust the heating temperature of the material by the raw material heater 16 according to the rating result.

[0052] The specific implementation process is as follows: the raw material process, indoor temperature and aging of the raw material heater 16 will affect the melting and solidification of the raw materials. The image during solidification is analyzed through a convolutional neural network, and the heating temperature of the material is continuously adjusted according to the molding shape and solidification time to further improve the solidification effect of each material and improve the microscopic quality of the workpiece.

[0053] Embodiment 6

[0054] The difference from the above embodiment is that the controller 10 is used to record the process data of controlling the nozzle mounting seat 5 until the light beam impact point is located at the cross intersection of the grating. When the same process data is recorded multiple times, the control parameters of the nozzle moving drive device 3 are corrected according to the process data.

[0055] The specific implementation process is as follows: the accuracy can be guaranteed through negative feedback adjustment, but the processing time is prolonged. By recording the process data during the adjustment process, the control parameters of the nozzle moving drive device 3 are corrected to reduce the adjustment amount in subsequent processing and improve the processing speed.

[0056] Embodiment 7

[0057] The difference from the above-mentioned embodiment is that the colors of the light beams generated by the grating projector 4 and the positioning light beam emitter 7 are different.

[0058] The specific implementation process is as follows: different light beam colors are conducive to the recognition of the convolutional neural network, so that the light beams generated by the grating projector 4 and the positioning beam emitter 7 have more features, thereby accelerating the recognition and judgment speed of the convolutional neural network.

[0059] Embodiment 8

[0060] The difference from the above embodiment is that a curtain 17 for shielding natural light is slidably connected to the printing platform 1 .

[0061] The specific implementation process is as follows: the curtain 17 can reduce the interference of natural light on the light beam, making the light beam less obvious. By blocking the natural light by the curtain 17, the interference of natural light on the light beam can be reduced, and the recognition and judgment speed of the convolutional neural network can be improved.

[0062] The technical means disclosed in the scheme of the present invention are not limited to the technical means disclosed in the above-mentioned implementation mode, but also include technical schemes composed of any combination of the above technical features.

Claims

1. A high-precision positioning device for composite material additive manufacturing, characterized in that: The device comprises an additive manufacturing device body, wherein the additive manufacturing device body comprises a printing platform, a printing nozzle, a nozzle moving drive device and a grating projector; The nozzle moving drive device is provided with a nozzle mounting seat, the nozzle mounting seat is provided with a feeding assembly, the printing nozzle is fixedly connected to the nozzle mounting seat, the printing nozzle is communicated with the feeding assembly, the nozzle mounting seat is provided with a positioning beam emitter, the nozzle mounting seat is provided with a stereo microscope, the light source and the microscope head of the stereo microscope are respectively located on both sides of the printing nozzle, a camera is provided on the microscope head of the stereo microscope, and the camera signal is connected with a controller; The grating projector is located above the printing platform, and is used to project a grating onto the printing platform; The controller is used to obtain the imaging image of the stereo microscope. A trained convolutional neural network is provided in the controller. The convolutional neural network is used to identify the grating and the positioning beam impact point in the imaging image, determine the relative position of the grating cross intersection and the positioning beam impact point, and control the nozzle movement drive device to adjust the nozzle mounting position until the beam impact point is located on the grating cross intersection.

2. The high-precision positioning device for composite material additive manufacturing according to claim 1, characterized in that: The grid of the raster grid is square, and the distance between the positioning beam emitter and the center of the print head is a multiple of the grid length.

3. The high-precision positioning device for composite material additive manufacturing according to claim 1, characterized in that: The material feeding assembly includes a material changing wheel, which is rotatably connected to the nozzle mounting seat. A plurality of material feeding pipes are circumferentially connected to the material changing wheel. A tooth pattern is provided on the lower outer side of the material changing wheel. A motor is provided in the nozzle mounting seat. A gear is fixedly connected to the output shaft of the motor. The gear is meshed with the tooth pattern. A raw material heater is provided in the nozzle mounting seat. The material changing wheel is used to rotate and switch the type of raw material entering the raw material heater. The raw material heater is connected to the printing nozzle.

4. The high-precision positioning device for composite material additive manufacturing according to claim 1, characterized in that: The controller is connected to the raw material heater signal. The controller stores the number of the feed pipe, the relationship function between the motor rotation angle and the number of the feed pipe connected to the raw material heater, and the rated heating temperature of each raw material. The controller obtains the current material temperature that needs to be preheated through the relationship function and controls the raw material heater to change the temperature.

5. The high-precision positioning device for composite material additive manufacturing according to claim 1, characterized in that: The convolutional neural network is also used to identify the solidification process of the raw material after it is ejected, and to rate the solidification effect, and to adjust the heating temperature of the raw material heater according to the rating results.

6. The high-precision positioning device for composite material additive manufacturing according to claim 1, characterized in that: The controller is used to record the process data of controlling the nozzle mounting seat until the light beam impact point is located at the cross intersection of the grating. When the same process data is recorded multiple times, the control parameters of the nozzle movement drive device are corrected according to the process data.

7. The high-precision positioning device for composite material additive manufacturing according to claim 1, characterized in that: The light beams produced by the raster projector and the positioning beam transmitter are different in color.

8. The high-precision positioning device for composite material additive manufacturing according to claim 1, characterized in that: The printing platform is equipped with a curtain to block natural light.

Images