Additive manufacturing device and method based on machine vision

Abstract

The present application provides an additive manufacturing device and method based on machine vision, which relates to the field of additive manufacturing technology. The device includes a molding film, a molding base, an image acquisition device, a first light source for providing illumination light, a second light source for providing curing light, a third light source for providing guide light, and a control device; a gap for filling printing material can be formed between the molding film and the molding base, and the illumination light and the guide light are non-sensitive bands of the printing material; in the additive manufacturing process, the guide light can be combined with the curing light, and the guide light is configured to carry the target pattern of the layer to be molded and projected onto the molding base; the image acquisition device is configured to acquire a first image including the target pattern and the molding layer based on the illumination light and the guide light; the control device is configured to control the molding base to move to align the molding layer with the target pattern projected by the guide light based on the first image and preset alignment information. The present application can achieve precise overlay of additive manufacturing.

Description

Technical Field

[0001] The present application relates to the field of additive manufacturing technology, and in particular to an additive manufacturing device and method based on machine vision. Background Art

[0002] Additive manufacturing technology based on photocuring is an emerging manufacturing technology. When using additive manufacturing equipment for high-precision 3D or 4D printing, the layered design of the object to be printed is used to achieve layer-by-layer construction of the object. In the printing process of complex structures or involving multiple materials, there are problems with overlay alignment, which require high debugging accuracy of the equipment and alignment adjustment during the printing process. Existing additive manufacturing equipment is difficult to achieve, and it is necessary to rely on manual adjustment intervention or reduce the accuracy requirements of the object to be printed. Summary of the invention

[0003] The present application provides an additive manufacturing device and method based on machine vision, which can achieve precise overlay automatic alignment.

[0004] On the one hand, the present application provides an additive manufacturing device based on machine vision, the device comprising a molding film, a molding base, an image acquisition device, a first light source for providing illumination light, a second light source for providing curing light, a third light source for providing guide light, and a control device;

[0005] A gap for filling printing material can be formed between the molding film and the molding base, the curing light can cure the printing material in the gap into a molding layer, the illumination light and the guide light can be projected onto the molding film and the molding base, and the illumination light and the guide light are insensitive bands of the printing material;

[0006] In the additive manufacturing process, the guide light can be combined with the curing light, and the guide light is configured to carry a target pattern of the layer to be formed and projected onto the forming base; the image acquisition device is configured to acquire a first image including the target pattern and the forming layer based on the illumination light and the guide light;

[0007] The control device is configured to control the forming base to move until the forming layer is aligned with a target pattern projected by the guide light based on the first image and preset alignment information, wherein the preset alignment information is used to indicate a target stacking state between the forming layer and the layer to be formed corresponding to the target pattern.

[0008] In a possible implementation manner, the control device is configured as follows:

[0009] Performing image recognition on the first image to obtain first position information of the target pattern and second position information of the current pattern corresponding to the molding layer;

[0010] Perform motion trajectory calculation based on the first position information, the second position information and the preset alignment information to obtain motion trajectory data;

[0011] The molding base is controlled to move until the molding layer is aligned with the target pattern based on the motion trajectory data.

[0012] In a possible implementation manner, when the first image is captured, the target pattern of the guiding light and the molding layer are located at the same focal plane.

[0013] In a possible implementation manner, the motion trajectory data includes a rotation angle and translation trajectory information of the forming base, the rotation angle is used to indicate a rotation operation of the forming base, and the translation trajectory information is used to indicate a translation operation of the forming base.

[0014] In a possible implementation manner, the guide light is further configured to project a leveling pattern onto the molding film, and a plurality of first marking positions are provided on the molding film;

[0015] The control device is configured to: control the molding film to translate until the first marking position is aligned with the leveling pattern; determine the first focal plane position corresponding to the first marking position based on the imaging clarity of the leveling pattern when the first marking position is aligned with the leveling pattern; determine the first leveling parameter according to the first focal plane position corresponding to each of the first marking positions; and level the molding film based on the first leveling parameter.

[0016] In a possible implementation manner, the guide light is further configured to project a leveling pattern onto the molding base, and a plurality of second marking positions are provided on the molding base;

[0017] The control device is configured to: control the molding base to translate until the second mark position is aligned with the leveling pattern; determine the second focal plane position corresponding to the second mark position based on the imaging clarity of the leveling pattern when the second mark position is aligned with the leveling pattern; determine the second leveling parameters according to the second focal plane positions corresponding to each of the second mark positions; and level the molding base based on the second leveling parameters.

[0018] In a possible implementation manner, the image acquisition device is further configured to, during the separation process of the molding film and the molding layer, acquire a fourth image including the molding film and the molding layer based on the illumination light, wherein the fourth image is acquired with the molding film as a focal plane;

[0019] The control device is configured to perform separation state recognition based on the fourth image to obtain a state recognition result, wherein the state recognition result is used to indicate the release state of the molding film and the molding layer.

[0020] In a possible implementation manner, the control device is configured as follows:

[0021] Performing clarity detection on an image area corresponding to the forming layer in the fourth image to obtain a clarity result;

[0022] The state recognition result is generated based on the clarity result. If the clarity result indicates that the image clarity corresponding to the molding layer is lower than a preset clarity, and / or the image clarity gradually decreases, the state recognition result indicates that the molding layer is successfully separated from the molding film.

[0023] In a possible implementation manner, the control device is configured as follows:

[0024] The fourth image is input into a separation state recognition model to perform separation state recognition to obtain the state recognition result, and the state recognition result is used to indicate whether the forming layer and the forming film are successfully separated or unsuccessfully separated.

[0025] In a possible implementation manner, the control device is configured as follows:

[0026] Performing a graphic detection corresponding to the forming layer on the fourth image to obtain a first detection result, where the first detection result is used to indicate a graphic contour of the forming layer in the fourth image;

[0027] The state recognition result is generated based on a comparison result between the first detection result and the preset pattern information corresponding to the molding layer. If the comparison result indicates that the difference between the graphic contour indicated by the first detection result and the preset pattern information meets a preset difference condition, the state recognition result indicates that the molding layer is successfully separated from the molding film.

[0028] In a possible implementation manner, the image acquisition device is further configured to acquire a fifth image of the molding layer based on the illumination light, with the molding layer as a focusing plane, when the molding film and the molding layer are not separated;

[0029] The control device is configured to:

[0030] Performing graphic detection of the forming layer based on the fifth image to obtain a second detection result;

[0031] Based on the comparison result between the second detection result and the preset pattern information corresponding to the molding layer, a molding abnormality detection result is generated.

[0032] In a possible implementation manner, the curing light is a projection light capable of curing the printing material, and is used to carry the target pattern of the layer to be formed.

[0033] In a possible implementation manner, the device further comprises a material pool for accommodating the printing material, wherein the material pool is located below the forming base and the forming base can extend into the material pool.

[0034] In a possible implementation manner, the image acquisition device and the material pool are respectively located on different sides of the molding surface of the molding base.

[0035] In a possible embodiment, the device also includes an optical path component, including a whole beam component and a processing lens, wherein the whole beam component is used to adjust the illumination light and make the illumination light irradiate the molding film and the molding base through the processing lens, adjust the guide light and the curing light to combine into a beam, and make the guide light irradiate the molding film or the molding base through the processing lens, and adjust the curing light and make the curing light irradiate the interval through the processing lens.

[0036] In a possible implementation manner, a first lens group, a first beam splitter and a processing lens are arranged between the first light source and the molding film, a second lens group is arranged between the image acquisition device and the molding film, the first lens group, the first beam splitter and the processing lens are located in a first optical path between the first light source and the molding film, and the processing lens, the first beam splitter and the second lens group are located in a second optical path between the image acquisition device and the molding film.

[0037] In a possible implementation manner, the first lens group and the first beam splitter are arranged on a common optical axis, the first beam splitter and the processing lens are arranged on a common optical axis, and the second lens group and the image acquisition device are arranged on a common optical axis.

[0038] In a possible implementation manner, the illumination light is emitted to the processing lens after passing through the first lens group and the first beam splitter, and is projected onto the molding film and the spacer after passing through the processing lens. Then, the illumination light is reflected by the molding film and the molding layer in the spacer to form a light beam with molding layer characteristics, and is focused to the image acquisition device after passing through the processing lens, the first beam splitter and the second lens group to generate an image area of ​​the molding layer in the first image.

[0039] In a possible implementation manner, the light paths of the second light source and the third light source are at least partially the same, so that the curing light and the guiding photosynthetic beam are irradiated to the molding layer.

[0040] In a possible implementation manner, a beam combiner, a third lens group and a second beam splitter are arranged on the optical path between the second light source, the third light source and the molding film, and the beam combiner is used to combine the curing light and the guide light; the beam combiner, the third lens group, the second beam splitter and the processing lens are located in the third optical path between the second light source and the molding film, and in the fourth optical path between the third light source and the molding film.

[0041] In a possible implementation, the additive manufacturing device also includes a rotational alignment mechanism that is transmission-connected to the molding base, including a rotating component and a moving component; the rotating component can drive the molding base to rotate around the Z axis, and the moving component can drive the molding base to move horizontally and up and down along the Z axis.

[0042] In a possible implementation manner, the control device is specifically configured to: control the movement of the rotation alignment mechanism based on the operation trajectory data, so as to drive the molding base to move until the molding layer and the target pattern are aligned.

[0043] In a preferred embodiment, the rotational alignment mechanism is transmission-connected to the material pool and / or the forming film, and the forming base can move in coordination with at least one of the material pool and the forming film.

[0044] In a possible implementation manner, determining the second focal plane position corresponding to the second mark position based on the imaging clarity of the leveling pattern may specifically include:

[0045] When the second mark position and the leveling pattern are aligned, the image acquisition device is controlled to acquire a second leveling image of the leveling pattern; the second leveling image is subjected to a clarity detection to obtain the imaging clarity of the leveling pattern; if the imaging clarity indicates that the leveling pattern is clearly imaged, the current imaging focal plane is determined as the second focal plane position of the second mark position; if the imaging clarity indicates that the leveling pattern is not clearly imaged, the molding base is controlled to move along the Z axis, or the image acquisition device is controlled to adjust the focal length, until the imaging clarity corresponding to the updated second leveling image indicates that the leveling pattern is clearly imaged, to obtain the second focal plane position of the second mark position.

[0046] In a possible implementation manner, the control device is further configured to: if the molding base is controlled to move along the Z-axis until the leveling pattern is clearly imaged, before controlling the next second mark position to be aligned with the leveling pattern, control the longitudinal position of the molding base to be reset, so as to adjust the longitudinal position of the molding base to the longitudinal position at which the second mark position is initially aligned with the leveling pattern.

[0047] In some embodiments, the control device is configured to: control the projection position of the leveling pattern of the guide light to be aligned with a preset Z-axis position, and move the second marking position of the molding base to be aligned with the preset Z-axis position.

[0048] In a preferred embodiment, the preset Z-axis position is coaxial with the optical axis of the image acquisition device.

[0049] In other embodiments, the image acquisition device is further configured to acquire a third image including the leveling pattern and at least one of the second marking positions based on the illumination light and the guide light; the control device is configured to control the molding base to translate until the second marking position is aligned with the leveling pattern based on the position of the leveling pattern and the position of the second marking position in the third image.

[0050] In a possible implementation manner, the plurality of second marking positions of the molding base include at least three non-collinear second marking positions, and the control device is configured to: respectively control the three non-collinear second marking positions to align with the leveling pattern and perform clear imaging; determine the second focal plane position of the clear image of each second marking position aligned with the leveling pattern; generate the second leveling parameters based on the second focal plane position of each non-collinear second marking position, and the second leveling parameters are used to level the inclined molding surface.

[0051] In a possible implementation, the additive manufacturing device further comprises a second leveling mechanism drivingly connected to the molding base, and the second leveling mechanism can drive the molding base to swing. In a specific implementation, the second leveling mechanism can drive the molding base to swing around at least one in-plane direction of the molding base.

[0052] In a possible implementation manner, determining the first focal plane position corresponding to the first mark based on the imaging clarity of the leveling pattern may specifically include: controlling the image acquisition device to acquire a first leveling image of the leveling pattern when the first mark is aligned with the leveling pattern; performing clarity detection on the first leveling image to obtain the imaging clarity of the leveling pattern; if the imaging clarity indicates that the leveling pattern is clearly imaged, determining the current imaging focal plane as the first focal plane position of the first mark; if the imaging clarity indicates that the leveling pattern is not clearly imaged, controlling the film to move along the Z axis, or controlling the acquisition device to adjust the focal length, until the imaging clarity corresponding to the updated first leveling image indicates that the leveling pattern is clearly imaged, to obtain the first focal plane position of the first mark.

[0053] In a possible implementation manner, the control device is further configured to: if the molding film is controlled to move along the Z-axis until the leveling pattern is clearly imaged, before controlling the first mark position to be aligned with the leveling pattern, control the longitudinal position of the molding film to be reset, so as to adjust the longitudinal position of the molding film to the longitudinal position at which the first mark position is initially aligned with the leveling pattern.

[0054] In a possible implementation manner, the control device is configured to: control the projection position of the leveling pattern of the guide light to be aligned with a preset Z-axis position, and move the first marking position of the molding film to be aligned with the preset Z-axis position.

[0055] In a possible implementation, the image acquisition device is further configured to acquire a second image including the leveling pattern and at least one of the first marking positions based on the illumination light and the guide light; and the control device is configured to control the molding film to translate until the first marking position is aligned with the leveling pattern based on the position of the leveling pattern and the position of the first marking position in the second image.

[0056] In a possible implementation, the multiple first marking positions of the molding film include at least three non-collinear first marking positions, and the control device is configured to: respectively control the three non-collinear first marking positions to align with the leveling pattern and perform clear imaging; determine the first focal plane position of the clear image of each first marking position aligned with the leveling pattern; generate the first leveling parameter based on the first focal plane position of each non-collinear first marking position, and the first leveling parameter is used to level the tilted molding film.

[0057] In a possible implementation manner, the additive manufacturing equipment further includes a first leveling mechanism transmission-connected to the molding film, and the first leveling mechanism can drive the molding film to swing.

[0058] In a specific implementation manner, the first leveling mechanism can drive the forming film to swing around at least one in-plane direction of the forming film.

[0059] In a possible implementation manner, the additive manufacturing equipment further includes a base moving device, which is transmission-connected to the molding base and can drive the molding base away from or close to the molding film; the base moving device is electrically connected to a control device, and the control device can control the movement of the base moving device to drive the molding base to move.

[0060] In a possible implementation, the control device is further configured to: in response to the printing material solidifying into a molding layer, trigger a separation process and control the base moving device to drive the molding base away from the molding film to form the gap between the surface of the molding layer and the molding film.

[0061] On the other hand, a machine vision-based additive manufacturing method is provided, which is applied to a machine vision-based additive manufacturing device, wherein the additive manufacturing device includes a molding film, a molding base, an image acquisition device, a first light source for providing illumination light, a second light source for providing curing light, and a third light source for providing guide light; a gap for filling a printing material can be formed between the molding film and the molding base, the curing light can cure the printing material in the gap into a molding layer, the illumination light and the guide light can be projected onto the molding film and the molding base, and the illumination light and the guide light are insensitive bands of the printing material; the method includes:

[0062] In the additive manufacturing process, the image acquisition device is controlled in a state where the guide light can be combined with the curing light to acquire a target pattern of the layer to be formed and a first image of the formed layer based on the illumination light and the guide light, wherein the target pattern is carried by the guide light and projected onto the forming base;

[0063] Based on the first image and preset alignment information, the molding base is controlled to move until the molding layer is aligned with the target pattern projected by the guide light, and the preset alignment information is used to indicate a target stacking state between the molding layer and the to-be-molded layer corresponding to the target pattern.

[0064] On the other hand, a control device for additive manufacturing is provided, which is applied to an additive manufacturing device based on machine vision, wherein the additive manufacturing device comprises a molding film, a molding base, an image acquisition device, a first light source for providing illumination light, a second light source for providing curing light, and a third light source for providing guide light; a gap for filling a printing material can be formed between the molding film and the molding base, the curing light can cure the printing material in the gap into a molding layer, the illumination light and the guide light can be projected onto the molding film and the molding base, and the illumination light and the guide light are insensitive bands of the printing material; the control device is configured as follows:

[0065] In the additive manufacturing process, the image acquisition device is controlled in a state where the guide light can be combined with the curing light to acquire a target pattern of the layer to be formed and a first image of the formed layer based on the illumination light and the guide light, wherein the target pattern is carried by the guide light and projected onto the forming base;

[0066] Based on the first image and preset alignment information, the molding base is controlled to move until the molding layer is aligned with the target pattern projected by the guide light, and the preset alignment information is used to indicate a target stacking state between the molding layer and the to-be-molded layer corresponding to the target pattern.

[0067] On the other hand, an electronic device is provided, comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the machine vision-based additive manufacturing method as described above.

[0068] On the other hand, a computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the machine vision-based additive manufacturing method as described above.

[0069] On the other hand, a computer program product or a computer program is provided, which includes computer instructions, and when the computer instructions are executed by a processor, the machine vision-based additive manufacturing method as described above is implemented.

[0070] The machine vision-based additive manufacturing equipment, method, control device, storage medium, computer program, and computer program product provided in this application have the following technical effects:

[0071] The machine vision-based additive manufacturing equipment of the present application is provided with an image acquisition device to acquire visual information, a first light source is provided to provide illumination light for image acquisition illumination, and a third light source is provided to provide guide light, wherein the guide light can be combined with the curing light beam, carry the target pattern of the layer to be formed and project it onto the forming base to simulate the forming position and pattern of the curing light, and then align the target pattern of the layer to be formed and the current forming layer in combination with the first image acquired by the image acquisition device, so as to achieve accurate automatic alignment of overlay and complete the preparatory work of curing light printing, without relying on manual debugging and with high alignment adjustment accuracy, the equipment structure is simple, and the equipment cost and complexity of alignment operations such as overlay are reduced; moreover, the illumination light and the guide light are both insensitive bands of the printing material, so as to avoid interfering with the forming effect of the curing light and the material, and can be applicable to 4D printing of complex structures and multiple materials or higher-dimensional printing tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0073] Figure 1 is a structural schematic diagram of an additive manufacturing device based on machine vision provided in an embodiment of the present application;

[0074] Figure 2 A schematic diagram of the structure of another machine vision-based additive manufacturing device provided in an embodiment of the present application;

[0075] Figure 3 is a structural principle diagram of an additive manufacturing process provided by an embodiment of the present application;

[0076] Figure 4 is a schematic diagram of a set of first images before and after alignment provided by an embodiment of the present application;

[0077] Figure 5 These are images of a group of out-of-focus (upper image), focused (middle image), and defocused (lower image) target patterns of guide light provided by an embodiment of the present application;

[0078] Figure 6 It is a structural principle diagram of leveling a molding base of an additive manufacturing device based on machine vision provided in an embodiment of the present application;

[0079] Description of the drawings: 101-image acquisition device, 102-first light source, 103-second light source, 104-molding film, 105-molding base, 106-material pool, 107-first lens group, 108-first beam splitter, 109-processing lens, 110-second lens group, 111-second beam splitter, 112-third lens group, 113-support seat, 114-spacer, 115-molding layer, 116-first mark, 117-second mark, 118-third mark, 119-third light source, 120-bundling component, 121-rotational alignment mechanism. DETAILED DESCRIPTION

[0080] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0081] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server comprising a series of steps or submodules is not necessarily limited to those steps or submodules clearly listed, but may include other steps or submodules that are not clearly listed or inherent to these processes, methods, products or devices.

[0082] The following is combined with Figure 1-6 An additive manufacturing device based on machine vision provided in an embodiment of the present application is introduced, wherein the device includes a molding film 104, a molding base 105, an image acquisition device 101, a first light source 102 for providing illumination light, a second light source 103 for providing curing light, a third light source 119 for providing guide light, and a control device.

[0083] In the embodiment of the present application, a gap 114 for filling the printing material can be formed between the molding film 104 and the molding base 105, and the curing light can cure the printing material in the gap 114 into a molding layer 115. More specifically, the curing light is a projection light that can cure the printing material, such as ultraviolet projection light, which carries the target pattern of the layer to be molded. Specifically, the molding film 104 is located above the molding base 105 and can pass the curing light. The gap 114 refers to the space formed between the molding film 104 and the molding surface of the molding base 105, or the space formed between the molding film 104 and the molding surface on the molding layer 115, and the molding surface refers to the working area surface on the molding base 105 for curing the printing material. The printing material refers to a liquid material that can react under the action of the curing light to form a cured layer, such as a resin. The molding film 104 is used to provide a flat and stable printing surface, which helps to obtain a better printing effect. During the printing process of additive manufacturing, the layer thickness is controlled by controlling the spacing height between the molding surface of the molding base 105 and the molding film 104, or the spacing height between the molding layer 115 on the molding surface and the molding film 104, and the moldable material is filled in the spacing 114, and layer-by-layer printing is achieved after photocuring.

[0084] In the embodiment of the present application, the illumination light and the guide light can be projected onto the molding film 104 and the molding base 105. Specifically, the molding film 104 can be illuminated by the illumination light and transmit the illumination light, so that it illuminates the molding surface of the molding base 105 or the molding layer 115 on the molding surface, and the guide light can be irradiated on the molding surface or the molding layer 115 of the molding base 105 through the molding film 104. The illumination light and the guide light are insensitive bands of the printing material, such as yellow light and red light, to avoid optical crosstalk on the curing of the material during the printing process, and to achieve 3D or 4D printing monitoring while ensuring the printing effect.

[0085] In an embodiment of the present application, in the additive manufacturing process, the guide light can be combined with the curing light, and the guide light is configured to carry the target pattern of the layer to be formed and projected onto the forming base 105; the image acquisition device 101 is configured to capture a first image including the target pattern and the forming layer 115 based on the illumination light and the guide light.

[0086] Specifically, the target pattern is the pattern to be cured and formed by the layer to be formed, that is, the pattern that the curing light needs to carry when printing the layer to be formed. By combining the light path of the guiding light in the non-sensitive band with the curing light and carrying the target pattern consistent with the curing light, the pattern position of the curing light can be simulated in the pre-printing and curing stage to adjust the alignment between the layer to be formed and the current forming layer.

[0087] Specifically, the image acquisition device 101 is used to receive the light formed by the illumination light and the guide light after passing through the molding layer 115 and the molding film 104 in the gap 114 and generate a first image. The illumination light irradiates the effective printing area on the molding base 105, and the generated first image includes an image area corresponding to the target pattern carried by the guide light and an image area corresponding to the molding layer 115, so as to present the positional relationship between the target pattern and the current pattern of the current molding layer 115.

[0088] In the embodiment of the present application, the device also includes a material pool 106 for accommodating printing materials, and the material pool 106 is located below the molding base 105 and the molding base 105 can extend into the material pool 106. During the printing process, the material pool 106 is filled with liquid printing material, and the molding base 105 can extend into the liquid printing material in the material pool 106, and a thin layer of printing material is formed in the gap 114 between the molding base 105 and the molding film 104, and then cured into a target pattern after being irradiated with curing light. Specifically, the image acquisition device 101 and the material pool 106 are respectively located on different sides of the molding surface of the molding base 105. In this way, the illumination light for imaging during the image acquisition process does not need to pass through the material pool 106, thereby reducing the image acquisition condition requirements and the transmittance requirements of the material pool 106 and the printing material, and improving the image clarity and accuracy. In a preferred embodiment, reference Figure 1The image acquisition device 101 is located above the molding surface of the moldable base 105, and the material pool 106 is located below the molding surface to reduce the layout complexity of the optical path components such as the lens group and the light splitter, and improve the imaging accuracy. In some embodiments, the device also includes a support seat 113, which is located below the material pool 106 and is used to support the material pool 106 and other components.

[0089] In an embodiment of the present application, the device also includes an optical path component, including a whole beam component and a processing lens 109. The whole beam component is used to adjust the illumination light and make the illumination light irradiate the molding film 104 and the molding base 105 through the processing lens 109, adjust the guide light and the curing light beam, and make the guide light irradiate the molding film 104 or the molding base 105 through the processing lens 109, and adjust the curing light and make the curing light irradiate the interval 114 through the processing lens 109.

[0090] Specifically, the whole beam assembly includes at least one beam splitter and at least one lens group.

[0091] In some embodiments, reference Figure 1 A first lens group 107, a first beam splitter 108 and a processing lens 109 are arranged between the first light source 102 and the molding film 104, a second lens group 110 is arranged between the image acquisition device 101 and the molding film 104, the first lens group 107, the first beam splitter 108 and the processing lens 109 are located in a first optical path L1 between the first light source 102 and the molding film 104, and the processing lens 109, the first beam splitter 108 and the second lens group 110 are located in a second optical path L2 between the image acquisition device 101 and the molding film 104. The illumination light is processed by the first lens group 107 to improve the beam stability and luminosity of the illumination light and remove stray light, the first lens group 107 and the first beam splitter 108 are arranged on the same optical axis, the first beam splitter 108 and the processing lens 109 are arranged on the same optical axis, and the second lens group 110 and the image acquisition device 101 are arranged on the same optical axis. The illumination light is emitted to the processing lens 109 after passing through the first lens group 107 and the first beam splitter 108, and is projected to the molding film 104 and the spacer 114 after passing through the processing lens 109. Then, the illumination light is reflected by the molding film 104 and the molding layer 115 in the spacer 114 to form a light beam with molding layer characteristics, and is focused to the image acquisition device 101 after passing through the processing lens 109, the first beam splitter 108 and the second lens group 110 to generate an image area of ​​the molding layer 115 in the first image. The second lens group 110 can improve the brightness of the field of view of the image acquisition device 101, and the imaging clarity and accuracy of the molding layer 115.

[0092] In some embodiments, reference Figure 1, the optical paths of the second light source 103 and the third light source 119 are at least partially common, so that the curing light and the guide light are combined to irradiate the molding layer 115. A beam combiner 120, a third lens group 112 and a second beam splitter 111 are arranged on the optical path between the second light source 103, the third light source 119 and the molding film 104. The beam combiner 120 is used to combine the curing light and the guide light. In one example, the beam combiner 120 can be a beam splitter. The beam combiner 120, the third lens group 112, the second beam splitter 111 and the processing lens 109 are located in the third optical path L3 (black dotted line) between the second light source 103 and the molding film 104, and the fourth optical path L4 (red dotted line) between the third light source 119 and the molding film 104.

[0093] In some embodiments, the optical path of the curing light and the optical path of the illumination light are at least partially the same. Specifically, the optical path of the curing light and the optical path of the illumination light are at least partially projected to the molding film 104 and the spacer 114 through the optical path of the processing lens 109 .

[0094] In some cases, before the curing light is used for curing printing, the illumination light is irradiated onto the molding layer 115 via the optical path L1, the guide light carrying the target pattern is irradiated onto the molding layer 115 via the optical path L4, and the illumination light is reflected by the molding layer 115 in the interval 114 and the molding film 104, forming a light beam carrying the characteristics of the molding layer, and then projected onto the image acquisition device 101 after passing through the processing lens 109, the second beam splitter 111, the first beam splitter 108 and the second lens group 110, so as to realize the imaging of the molding layer 115; the guide light is reflected by the molding layer 115 in the interval 114 and the molding film 104, and then projected onto the image acquisition device 101 after passing through the processing lens 109, the second beam splitter 111, the first beam splitter 108 and the second lens group 110, so as to realize the imaging of the target pattern and obtain the first image. After the alignment adjustment based on the first image, the curing light is turned on, and the curing light is irradiated onto the interval 114 via the third optical path L3 for curing and molding, so as to complete the printing molding of the layer to be molded.

[0095] In some cases, the light reflected by the curing light through the molding film 104, the molding base 105 or the molding layer 115 can also be projected to the image acquisition device 101 after passing through the processing lens 109, the second beam splitter 111, the first beam splitter 108 and the second lens group 110. Before performing the printing operation, the curing light is imaged by the image acquisition device 101, and the system is debugged based on the obtained curing light image, and then the printing operation is performed. Among them, the system debugging may include but is not limited to optical imaging quality detection, graphic direction adjustment, graphic detection, etc. The optical imaging quality detection refers to determining the focus state, resolution, etc. of the curing light based on the recognition and detection of the curing light image, the image direction adjustment refers to recognizing the position and direction of the projected curing light graphic relative to the molding base 105 based on the curing light image, and then realizing the direction adjustment of the graphic, and the graphic detection refers to recognizing the actual projection graphic of the curing light based on the curing light image, and then judging whether the actual projection graphic is consistent with the target pattern. It can be understood that the above-mentioned system debugging can be performed based on independent image recognition results, or can be realized based on the recognition and detection results of the same curing light image.

[0096] In the embodiment of the present application, the control device is configured to control the molding base 105 to move to align the molding layer 115 with the target pattern projected by the guide light based on the first image and the preset alignment information. The preset alignment information is used to indicate the target stacking state between the molding layer 115 and the layers to be molded corresponding to the target pattern. It can be understood that the first image includes the molding layer 115 and the image area of ​​the guide light. Based on the position of the image area of ​​the molding layer 115 in the first image and the position of the image area of ​​the guide light in the first image, the position of the molding base 105 is adjusted until the overlapping state between the molding layer 115 and the target pattern is consistent with the target stacking state indicated by the preset alignment information, and the alignment of the molding layer 115 and the target pattern is completed.

[0097] In this way, the machine vision-based additive manufacturing equipment of the present application is provided with an image acquisition device 101 for visual information acquisition, a first light source 102 is provided to provide illumination light for image acquisition illumination, and a third light source 119 is provided to provide guide light, which can be combined with the curing light beam, carry the target pattern of the layer to be formed and projected onto the forming base 105 to simulate the forming position and pattern of the curing light, and then align the target pattern of the layer to be formed and the current forming layer 115 in combination with the first image acquired by the image acquisition device 101, so as to achieve precise automatic alignment of overlay, complete the preliminary work of curing light printing, do not need to rely on manual debugging, and have high alignment adjustment accuracy, simple equipment structure, reduce equipment cost and complexity of alignment operations such as overlay; moreover, the illumination light and guide light are both insensitive bands of the printing material, so as to avoid interfering with the forming effect of the curing light and the material, and can be suitable for 4D printing of complex structures and multiple materials or higher-dimensional printing tasks.

[0098] In some embodiments, the control device is specifically configured to: perform image recognition on the first image to obtain the first position information of the target pattern and the second position information of the current pattern corresponding to the molding layer 115; perform motion trajectory calculation based on the first position information, the second position information and the preset alignment information to obtain motion trajectory data; and control the molding base 105 to move to align the molding layer 115 with the target pattern based on the motion trajectory data. In this way, a guide light is added to the optical path of the curing light, so that the guide light and the curing light are combined. When performing overlay alignment, a clear molding layer pattern of the sample to be overlaid is collected through the illumination light, and the pattern to be overlaid is obtained through the guide light. When the two are clearly imaged, the position difference between the two is determined through image recognition to determine the position adjustment trajectory of the mechanical structure, so that accurate overlay alignment can be achieved.

[0099] It can be understood that when the first image is captured, the target pattern of the guiding light and the molding layer 115 are located at the same focal plane.

[0100] In some cases, image recognition can be to perform graphic detection on the first image, obtain the first shape contour of the current pattern of the molding layer 115 and the second shape contour of the target pattern, and then determine the position of the current pattern in the image based on the first shape contour to obtain the first position information, and determine the position of the target pattern in the image based on the second shape contour to obtain the second position information. Optionally, the graphic detection here can be performed based on an edge detection algorithm, a frequency domain conversion method, an image segmentation algorithm, etc. Among them, the edge detection algorithm can be, for example, to locate the edge contour position of the molding layer 115 and the target pattern in the image based on the pixel gradient of the image; the frequency domain conversion can be, for example, to convert the image from the spatial domain to the frequency domain through Fourier transform, and determine the edge contour position of the molding layer 115 and the target pattern based on the energy distribution of the frequency domain image; image segmentation is implemented based on an image segmentation model, and the image segmentation model is obtained by constraining the initial segmentation model with sample images and sample image segmentation labels as training data, sample images as inputs of the initial segmentation model, and sample image segmentation labels as expected outputs. In other cases, image recognition can be performed by detecting feature points of the first image to obtain first feature point information corresponding to the molding layer 115 and second feature point information corresponding to the target pattern, and then determine the first position information based on the first feature point information and determine the second position information based on the second feature point information.

[0101] Further, the control device is specifically configured to: perform angle and position calculation according to the first position information, the second position information and the preset alignment information to obtain motion trajectory data, the motion trajectory data including the rotation angle and translation trajectory information of the molding base 105, the rotation angle is used to indicate the rotation operation of the molding base 105, and the translation trajectory information is used to indicate the translation operation of the molding base 105. In one embodiment, the preset alignment information indicates the target stacking state between the current pattern and the target pattern, and may include the target relative angle and target relative position between the current pattern and the target pattern, the target relative angle is used to indicate the angle of the two pattern pieces under the target stacking state, and the target relative position is used to indicate the coordinate difference between the feature points of the two patterns under the target stacking state; the relative angle and relative position between the current pattern and the target pattern can be determined based on the first position information and the second position information; the difference between the relative angle and the target relative angle, and the difference between the relative position and the target relative position are determined, and then the angle and position calculation are performed to obtain the running trajectory data. The difference between the relative position and the target relative position can be the position difference between the feature points of the two patterns, and the feature points can be midpoints, corner points, etc.

[0102] Further, the control device is specifically configured to: control the molding base 105 to rotate around the axis (Z-axis rotation) according to the rotation angle to adjust the relative angle to the target relative angle, and control the molding base 105 to translate in the plane (XY plane translation, Z axis is perpendicular to the XY plane) according to the translation trajectory information to adjust the relative position to the target relative position. It can be understood that the execution order of the rotation operation and the translation operation can be interchanged, or the position of the molding base can be adjusted by multiple rotations or multiple translations, etc., and the position adjustment can be achieved based on actual needs, not limited to the above description. In this way, the angle and position are calculated by image recognition, the rotation component is controlled to rotate the angle, and the motion component is controlled to move the position, so as to achieve precise alignment of the molding layer 115 with the target pattern.

[0103] In some embodiments, reference Figure 2 The additive manufacturing device also includes a rotation alignment mechanism 121 that is transmission-connected to the molding base 105, including a rotation component and a motion component. The rotation component can drive the molding base 105 to rotate around the Z axis, and the motion component can drive the molding base 105 to move horizontally and up and down along the Z axis. Accordingly, the control device is specifically configured to: control the movement of the rotation alignment mechanism 121 based on the running trajectory data to drive the molding base 105 to move until the molding layer 115 is aligned with the target pattern. In a preferred embodiment, the rotation alignment mechanism 121 is transmission-connected to the material pool 106 and / or the molding film 104, and the molding base 105 can move in coordination with at least one of the material pool 106 and the molding film 104.

[0104] For example, reference Figure 4, the figure shows the stacking state of the current pattern (solid five-pointed star) of the molding layer 115 before adjustment and the target pattern (dotted five-pointed star) carried by the guide light (left figure) and the stacking state of the two patterns after adjustment (right figure), and the target stacking state of the current pattern and the target pattern is overlapped. As shown in the left figure, before adjustment, there is an angle and position difference between the current pattern and the target pattern. After rotation and translation, the two patterns are adjusted to overlap so that the curing printing of the next layer can be performed. Through the pattern position indication of the guide light, the position alignment based on graphic recognition is realized without affecting the printing material, so that 4D printing with precise overlay alignment or printing with higher dimensions and more complex structures can be performed.

[0105] It should be noted that the first image is acquired when the molding layer 115 and the target pattern of the guiding light are located at the same focal plane, or the two focal planes are parallel. Accordingly, the control device is further configured to: before acquiring the first image, control the molding base 105 to perform a leveling movement until the molding surface of the molding base 105 is located at a horizontal plane.

[0106] Accordingly, the guide light is also configured to project a leveling pattern onto the molding base 105, and a plurality of second marking positions are provided on the molding base 105; accordingly, the control device is configured to: control the molding base 105 to move horizontally to the second marking position to align with the leveling pattern; in the state where the second marking position is aligned with the leveling pattern, determine the second focal plane position corresponding to the second marking position based on the imaging clarity of the leveling pattern; determine the second leveling parameter according to the second focal plane position corresponding to each second marking position; and perform leveling processing on the molding base 105 based on the second leveling parameter. In this way, the leveling pattern of the guide light is introduced to image the marking position, and the focal plane position of each second marking position is determined based on the clarity of the leveling pattern, so as to realize the leveling of the base, improve the calculation efficiency and recognition accuracy of the focal plane position of the marking position, and thus realize the precise positioning and leveling of the base.

[0107] Understandably, reference Figure 5 , in the out-of-focus (upper picture) and defocused (lower picture) states, the leveling patterns of the guide light are blurred. In the focal position (middle picture), the leveling image captured by the image acquisition device is clear.

[0108] Specifically, the second mark position can be a physical mark on the molding base 105, such as a raised structure, a recessed structure, a color mark, etc., or it can be a pre-stored virtual position mark, such as pre-stored coordinate information of a certain position of the molding base 105.

[0109] Specifically, determining the second focal plane position corresponding to the second mark position based on the imaging clarity of the leveling pattern may specifically include: when the second mark position and the leveling pattern are aligned, controlling the image acquisition device 101 to acquire a second leveling image of the leveling pattern, performing a clarity detection on the second leveling image, and obtaining the imaging clarity of the leveling pattern; if the imaging clarity indicates that the leveling pattern is clearly imaged, determining the current imaging focal plane as the second focal plane position of the second mark position; if the imaging clarity indicates that the leveling pattern is not clearly imaged, controlling the molding base 105 to move along the Z axis, or controlling the image acquisition device 101 to adjust the focal length, until the imaging clarity corresponding to the updated second leveling image indicates that the leveling pattern is clearly imaged, and obtaining the second focal plane position of the second mark position.

[0110] It should be noted that the control device is also configured as follows: if the molding base 105 is controlled to move along the Z axis until the leveling pattern is clearly imaged, before controlling the next second mark position to be aligned with the leveling pattern, the longitudinal position of the molding base 105 is controlled to be reset to adjust the longitudinal position of the molding base 105 to the longitudinal position at which the second mark position is initially aligned with the leveling pattern.

[0111] In some embodiments, a preset Z-axis position is set, and the control device is configured to: control the projection position of the leveling pattern of the guide light to be aligned with the preset Z-axis position, and the second mark position of the molding base 105 to be moved to be aligned with the preset Z-axis position, so as to achieve the alignment of the leveling pattern and the second mark position. Alignment with the preset Z-axis position can be exemplified as the center position of the leveling pattern or the center position of the second mark position being located on the preset Z-axis. It can be understood that the alignment setting can also be other forms of axis alignment, which can be set based on actual needs and is not limited to the above description. In a preferred embodiment, the preset Z-axis position is coaxial with the optical axis of the image acquisition device 101.

[0112] In some other embodiments, the image acquisition device 101 is further configured to acquire a third image including a leveling pattern and at least one second mark position based on the illumination light and the guide light; the control device is configured to: based on the position of the leveling pattern and the position of the second mark position in the third image, control the molding base 105 to move horizontally to align with the second mark position and the leveling pattern. Specifically, the aforementioned image recognition method can be used to determine the position of the leveling pattern and the position of the second mark position in the third image, and then calculate the position difference between the leveling pattern and the second mark position, determine the motion trajectory of the molding base 105 based on the position difference, and control the molding base 105 to move horizontally to align with the second mark position and the leveling pattern according to the motion trajectory.

[0113] In some embodiments, the control device is configured to: control the rotation alignment mechanism 121 to move, so as to drive the molding base 105 to move to align the second mark position with the leveling pattern. Exemplarily, the motion component can drive the molding base 105 to move in a translational manner, and can at least drive the molding base 105 to move along the X-axis and the Y-axis respectively, so as to facilitate the axial alignment of the second mark position with the leveling pattern.

[0114] It should be noted that the multiple second marking positions of the molding base 105 include at least three non-collinear second marking positions, and the control device is configured to: respectively control the three non-collinear second marking positions to align with the leveling pattern and perform clear imaging, and then determine the second focal plane position of the clear image in which each second marking position is aligned with the leveling pattern; and then generate a second leveling parameter based on the second focal plane position of each non-collinear second marking position, and the second leveling parameter is used to level the inclined molding surface.

[0115] Exemplarily, the second focal plane position may be specifically the height of the focal plane relative to the preset zero plane. In some embodiments, the preset zero plane may be a plane at a preset height. In other embodiments, each second marker includes a fixed mark, and the second focal plane position of the fixed mark is the preset zero plane. It is understandable that the second focal plane position may also use imaging focal plane data of the image acquisition device 101, or other focal plane calculation methods, and is not limited to the above description.

[0116] It can be understood that when the inclination angle of the molding surface of the molding base 105 is not 0, the focal plane positions of multiple non-coplanar second mark positions are located at different heights, and the focusing heights required for clear imaging of each second mark position are also different; based on the focal plane positions of each second mark position, the height difference between each second mark position can be determined, and then the second leveling parameter is generated through the height difference.

[0117] In some embodiments, the additive manufacturing device further includes a second leveling mechanism that is transmission-connected to the molding base 105, and the second leveling mechanism can drive the molding base 105 to swing, so as to perform swing adjustment based on the second leveling parameter, thereby adjusting the inclination angle of the molding base 105 so that the molding base 105 meets the horizontality requirement. Specifically, the second leveling mechanism can drive the molding base 105 to swing around at least one in-plane direction of the molding base 105 to achieve the inclination angle adjustment of the molding base 105.

[0118] In one example, after determining the second focal plane positions of at least three non-collinear second markers, the height of each second marker can be adjusted based on the height difference between each second focal plane position, until each focal plane position is adjusted to be coplanar, so as to achieve the leveling of the molding base 105. In one embodiment, the second leveling parameter includes the swing angle and the swing direction of the molding base 105. Accordingly, the control device is configured to: determine the current inclination angle and the inclination direction of the molding base 105 according to the height difference between each second focal plane position, and determine the swing angle and the swing direction of the second leveling mechanism based on the inclination angle and the inclination direction, and control the molding base 105 to swing to leveling based on the swing angle and the swing direction. In another embodiment, the second leveling parameter includes the height adjustment value of the molding base 105, and the control device is configured to: determine the height adjustment value of each second marker according to the height difference between each second focal plane position, and each height adjustment value is used to adjust each second marker to the same height; and control the second leveling mechanism to adjust the height of each second marker based on the height adjustment value until the molding base 105 is leveled.

[0119] In an example, refer to Figure 6 , the plurality of second marking positions include a first mark 116, a second mark 117 and a third mark 118, wherein the first mark 116 is a fixed mark, and the second mark 117 and the third mark 118 are adjustable marks during the leveling process. The leveling process of the molding base 105 may include: controlling the motion component to drive the molding base 105 to move horizontally, so as to respectively move the first mark 116, the second mark 117 and the third mark 118 to align with the leveling pattern, and in the aligned state, respectively perform focusing adjustment on the positions of the first mark 116, the second mark 117 and the third mark 118 for the leveling pattern, so as to respectively obtain a second leveling image including the first mark 116 with clear imaging and the leveling pattern, a second leveling image including the second mark 117 with clear imaging and the leveling pattern, and a second leveling image including the third mark 118 with clear imaging and the leveling pattern; based on the second leveling image of the first mark 116, determine the position of the first mark 116 corresponding to the first mark 116; The second focal plane position is determined as a preset zero plane; the second focal plane position of the second mark 117 is determined based on the second leveling image of the second mark 117 and the preset zero plane, and the third focal plane position of the third mark 118 is determined based on the second leveling image of the second mark 117 and the preset zero plane; the second leveling parameter is determined based on the height difference between the second focal plane position of the second mark 117 and the preset zero plane, and based on the height difference between the second focal plane position of the third mark 118 and the preset zero plane, and the second leveling parameter is used to instruct the second swing device to adjust the height of the second mark 117 and the third mark 118 until the second mark 117 and the third mark 118 are flush with the first mark 116 with a fixed height, so as to achieve base leveling.

[0120] It can be understood that the flatness and levelness of the molding film 104 directly affect the structure of the object and the printing effect. Before the material is solidified and printed, the molding film 104 needs to be leveled. Accordingly, the guide light is also configured to project a leveling pattern onto the molding film 104, and a plurality of first marking positions are provided on the molding film 104; the image acquisition device 101 control device is configured to: control the molding film 104 to move horizontally to the first marking position to align with the leveling pattern; in the alignment state of the first marking position and the leveling pattern, determine the first focal plane position corresponding to the first marking position based on the imaging clarity of the leveling pattern; determine the first leveling parameter according to the first focal plane position corresponding to each first marking position; and perform leveling processing on the molding film 104 based on the first leveling parameter. In this way, positioning and leveling the molding film in combination with a plurality of first marking positions and the image acquisition device 101 can improve positioning efficiency and leveling accuracy.

[0121] Specifically, determining the first focal plane position corresponding to the first mark position based on the imaging clarity of the leveling pattern may specifically include: when the first mark position and the leveling pattern are aligned, controlling the image acquisition device 101 to acquire a first leveling image of the leveling pattern, performing a clarity detection on the first leveling image, and obtaining the imaging clarity of the leveling pattern; if the imaging clarity indicates that the leveling pattern is clearly imaged, determining the current imaging focal plane as the first focal plane position of the first mark position; if the imaging clarity indicates that the leveling pattern is not clearly imaged, controlling the molding film 104 to move along the Z axis, or controlling the image acquisition device 101 to adjust the focal length, until the imaging clarity corresponding to the updated first leveling image indicates that the leveling pattern is clearly imaged, and obtaining the first focal plane position of the first mark position.

[0122] It should be noted that the control device is also configured as follows: if the molding film 104 is controlled to move along the Z axis until the leveling pattern is clearly imaged, before controlling the next first mark position to be aligned with the leveling pattern, the longitudinal position of the molding film 104 is controlled to be reset to adjust the longitudinal position of the molding film 104 to the longitudinal position at which the first mark position is initially aligned with the leveling pattern.

[0123] In some embodiments, a preset Z-axis position is set, and the control device is configured to: control the projection position of the leveling pattern of the guide light to be aligned with the preset Z-axis position, and the first mark position of the molding film 104 to move to align with the preset Z-axis position, so as to achieve the alignment of the leveling pattern with the first mark position. Alignment with the preset Z-axis position can be exemplified as the center position of the leveling pattern or the center position of the first mark position being located on the preset Z-axis. It can be understood that the alignment setting can also be other forms of axis alignment, which can be set based on actual needs and is not limited to the above description. In a preferred embodiment, the preset Z-axis position is coaxial with the optical axis of the image acquisition device 101.

[0124] In some other embodiments, the image acquisition device 101 is further configured to acquire a second image including a leveling pattern and at least one first mark position based on the illumination light and the guide light; the control device is configured to: based on the position of the leveling pattern and the position of the first mark position in the second image, control the molding film 104 to move horizontally to the first mark position to align with the leveling pattern. Specifically, the aforementioned image recognition method can be used to determine the position of the leveling pattern and the position of the first mark position in the second image, and then calculate the position difference between the leveling pattern and the first mark position, determine the motion trajectory of the molding film 104 based on the position difference, and control the molding film 104 to move horizontally to the first mark position to align with the leveling pattern according to the motion trajectory.

[0125] In some embodiments, the additive manufacturing device further includes a molding film adjustment mechanism that is transmission-connected to the molding film 104, and can drive the molding film 104 to move in translation. In other embodiments, the rotation alignment mechanism is transmission-connected to the molding film 104, and can drive the molding film 104 to move in translation. Accordingly, the control device is configured to: control the molding film adjustment mechanism or the rotation alignment mechanism 121 to move, so as to drive the molding film 104 to move to the first mark position and align with the leveling pattern. Exemplarily, the motion component can drive the molding film 104 to move in translation, and can at least drive the molding film 104 to move along the X-axis and the Y-axis respectively, so as to facilitate the axial alignment of the first mark position and the leveling pattern.

[0126] It should be noted that the multiple first marking positions of the molding film 104 include at least three non-collinear first marking positions, and the control device is configured to: respectively control the three non-collinear first marking positions to align with the leveling pattern and perform clear imaging, and then determine the first focal plane position of the clear image in which each first marking position is aligned with the leveling pattern; and then generate a first leveling parameter based on the first focal plane position of each non-collinear first marking position, and the first leveling parameter is used to level the inclined molding film 104.

[0127] Exemplarily, the first focal plane position may be the height of the focal plane relative to the preset zero plane. In some embodiments, the preset zero plane may be a plane at a preset height. In other embodiments, each first mark position includes a fixed mark, and the first focal plane position of the fixed mark is the preset zero plane. It is understandable that the first focal plane position may also use the imaging focal plane data of the image acquisition device 101, or other focal plane calculation methods, and is not limited to the above description.

[0128] It can be understood that when the inclination angle of the molding surface of the molding film 104 is not 0, the focal plane positions of multiple non-coplanar first marking positions are located at different heights, and the focusing heights required for clear imaging of each first marking position are also different; based on the focal plane positions of each first marking position, the height difference between each first marking position can be determined, and then the first leveling parameter is generated through the height difference.

[0129] In some embodiments, the additive manufacturing device further includes a first leveling mechanism that is transmission-connected to the molding film 104, and the first leveling mechanism can drive the molding film 104 to swing, so as to perform swing adjustment based on the first leveling parameter, thereby adjusting the inclination angle of the molding film 104 so that the molding film 104 meets the horizontality requirement. Specifically, the first leveling mechanism can drive the molding film 104 to swing around the in-plane direction of at least one molding film 104, so as to adjust the inclination angle of the molding film 104.

[0130] In one example, after determining the first focal plane positions of at least three non-collinear first markers, the height of each first marker can be adjusted based on the height difference between each first focal plane position until each focal plane position is adjusted to be coplanar, so as to achieve the leveling of the molding film. In one embodiment, the first leveling parameter includes the swing angle and the swing direction of the molding film 104. Accordingly, the control device is configured to: determine the current tilt angle and tilt direction of the molding film 104 according to the height difference between each focal plane position, and determine the swing angle and the swing direction of the first leveling mechanism based on the tilt angle and the tilt direction, and control the molding film 104 to swing to leveling based on the swing angle and the swing direction. In another embodiment, the first leveling parameter includes the height adjustment value of the molding film 104, and the control device is configured to: determine the height adjustment value of each first marker according to the height difference between each focal plane, and each height adjustment value is used to adjust each first marker to the same height; based on the height adjustment value, control the first leveling mechanism to adjust the height of each first marker until the molding film 104 is leveled.

[0131] In some embodiments, the device further includes a base moving device, which is in transmission connection with the molding base 105, and can drive the molding base 105 away from or close to the molding film 104; the base moving device is electrically connected to the control device, and the control device can control the base moving device to move, so as to drive the molding base 105 to move. Accordingly, the control device is further configured to: in response to the printing material being solidified into the molding layer 115, trigger the separation process and control the base moving device to drive the molding base 105 away from the molding film 104, so as to form a gap 114 between the surface of the molding layer 115 and the molding film 104. In this way, by setting the base moving device and the molding base 105 in linkage, precise automatic control of the release and layer thickness during the printing process is achieved.

[0132] It can be understood that the printing process of additive manufacturing is to manufacture the object to be printed by accumulating materials layer by layer, that is, to cut the three-dimensional model of the object to be printed into a series of thin layers, each layer corresponding to a cross section in the printing process. Specifically, after the molding base 105 is controlled to extend into the material pool 106 and form a thin layer of printing material between the molding film 104, a thin layer of printing is completed by curing light curing molding, thereby triggering the separation process of the molding layer 115 on the molding base 105 and the molding film 104, so as to perform the process of releasing the mold after the printing of the layer, refer to Figure 3 During this process, the molding film 104 is fixed, and the molding base 105 is driven downward by the base moving device to separate the surface of the molding layer 115 from the molding film 104, forming a gap 114 for the next layer, so as to facilitate the printing operation of the next layer.

[0133] Based on some or all of the above embodiments, in some embodiments, the image acquisition device 101 is further configured to, during the separation process of the molding film 104 and the molding layer 115, based on the illumination light, collect a fourth image including the molding film 104 and the molding layer 115, and the fourth image is acquired with the molding film 104 as the focal plane. Specifically, the image acquisition device 101 is used to receive the light formed by the illumination light after passing through the molding layer 115 and the molding film 104 in the gap 114 and generate the fourth image. The illumination light irradiates the effective printing area on the molding base 105, and the generated fourth image includes at least a partial area of ​​the molding film 104 and the image area corresponding to the molding layer 115, so as to present the connection or separation state between the molding layer 115 and the molding film 104.

[0134] Accordingly, the control device is configured to perform separation state recognition based on the fourth image to obtain a state recognition result, and the state recognition result is used to indicate the release state of the molding film 104 and the molding layer 115. Specifically, the state recognition result includes the successful separation and unsuccessful separation of the molding film 104 and the molding layer 115. In this way, combined with the setting of the illumination light and the image acquisition device 101, the image-based release state recognition is realized, and the separation effect of the molding film 104 and the molding layer 115 can be monitored in real time during the printing process, and abnormalities such as unsuccessful separation can be discovered in time and the printing work can be terminated. Automatic detection of printing abnormalities is realized without changing the main printing components in the additive manufacturing equipment, reducing missed detection and delay in problem handling.

[0135] In some embodiments, the fourth image is obtained with the molding film 104 as the focal plane. It can be understood that after each cross-sectional thin layer is solidified, the molding layer 115 is in contact with the molding film 104, the molding layer 115 is located on the focal plane of the image acquisition, and is clearly imaged in the acquired fourth image, and a molding layer 115 area with a clear shape contour is correspondingly identified; during the separation process, if it is identified that the shape of the molding layer 115 area is inconsistent with the preset pattern information of the molding layer 115, and / or the shape contour of the molding layer 115 area is blurred, it indicates that the molding layer 115 is gradually blurred in the acquired fourth image, and further indicates that the molding layer 115 is away from the focal plane and is successfully separated from the molding film 104; during the separation process, if it is identified that at least part of the molding layer 115 area in the fourth image still has a clear contour, and / or the shape of the molding layer 115 area is consistent with the preset pattern information of the molding layer 115, it indicates that the molding layer 115 is not successfully separated from the molding film 104, and the separation is determined to be abnormal, and then a warning message is generated or the printing operation is stopped.

[0136] In some embodiments, the control device is configured to: perform clarity detection on the image area corresponding to the molding layer 115 in the fourth image to obtain a clarity result; generate a state recognition result based on the clarity result, if the clarity result indicates that the image clarity corresponding to the molding layer 115 is lower than the preset clarity, and / or the image clarity gradually decreases, the state recognition result indicates that the molding layer 115 is successfully separated from the molding film 104; if the clarity result indicates that the image clarity corresponding to the molding layer 115 is higher than the preset clarity, and / or the image clarity remains unchanged, the state recognition result indicates that the molding layer 115 is not successfully separated from the molding film 104. It can be understood that if the clarity result indicates that the image clarity of the molding layer 115 is lower, it indicates that the separation interval 114 between the molding layer 115 and the molding film 104 is larger, and vice versa.

[0137] The above-mentioned clarity detection is used to evaluate the visibility of the edge of the molding layer 115 in the image. In one embodiment, an edge detection-based algorithm is used for clarity detection. First, the edge contour position of the molding layer 115 in the fourth image is located based on the pixel gradient of the image, and the clarity result is determined by the gradient value of the edge contour, wherein the higher the gradient value of the edge, the higher the clarity value corresponding to the clarity result, and vice versa. In another embodiment, the fourth image is converted into the frequency domain, such as converting the image from the spatial domain to the frequency domain through Fourier transform, and the clarity of the image area corresponding to the molding layer 115 is determined based on the energy distribution of the frequency domain image. The higher the energy and the more concentrated the distribution, the higher the image clarity, and vice versa. In another embodiment, a deep learning algorithm is trained based on sample images and sample clarity labels to learn the relationship between image features and clarity, obtain a clarity recognition model, and then the fourth image is input into the clarity recognition model for clarity detection to obtain a clarity result. In this way, the image clarity and clarity change during the release process of the molding layer 115 are determined by clarity detection, reducing the complexity of separation state judgment and improving state recognition efficiency.

[0138] In some other embodiments, the control device is configured to: input the fourth image into the separation state recognition model to perform separation state recognition, and obtain a state recognition result, and the state recognition result is used to indicate whether the molding layer 115 is successfully separated from the molding film 104 or not. Specifically, the separation state recognition model is obtained by performing constraint training of separation state recognition based on the sample image as the input of the initial recognition model and the image label as the expected output. The sample image includes a physical object, and the image label here is used to characterize whether the physical object in the sample image is clear or not. If it is clear, it indicates successful separation, and if it is not clear, it indicates unsuccessful separation. The separation state is judged by the trained separation state recognition model to improve the efficiency and accuracy of separation state recognition.

[0139] In some other embodiments, the control device is configured to: perform a graphic detection corresponding to the molding layer 115 on the fourth image to obtain a first detection result, the first detection result is used to indicate the graphic outline of the molding layer 115 in the fourth image; based on the comparison result of the first detection result and the preset pattern information corresponding to the molding layer 115, generate a state recognition result, if the comparison result indicates that the difference between the graphic outline indicated by the first detection result and the preset pattern information meets the preset difference condition, the state recognition result indicates that the molding layer 115 is successfully separated from the molding film 104; if the comparison result indicates that the difference between the graphic outline indicated by the first detection result and the preset pattern information does not meet the preset difference condition, the state recognition result indicates that the molding layer 115 is not successfully separated from the molding film 104. In this way, the graphic outline of the molding layer 115 during the separation process is determined by graphic detection, and then the separation state is determined by the comparison result with the preset pattern information, which can improve the accuracy of the determination of the separation state.

[0140] Specifically, the graphic detection here can be performed based on an edge detection algorithm, a frequency domain conversion method, an image segmentation algorithm, etc. Exemplarily, during the separation process of the molding film 104 and the molding base 105 , the fourth image is segmented to obtain an image segmentation result, and the image segmentation result includes graphic contour information corresponding to the molding layer 115 .

[0141] In some cases, the preset pattern information indicates the preset pattern required for molding of the molding layer 115, that is, the pattern carried by the projection type curing light, which can be obtained from the pre-stored printing information. When the molding film 104 is in contact with the molding layer 115, the image area of ​​the molding layer 115 is in a focused state, and the graphic contour corresponding to the graphic contour information is consistent with the preset pattern corresponding to the preset pattern information or the shape similarity is higher than the first preset similarity; when the molding film 104 is successfully separated from the molding layer 115, the image area of ​​the molding layer 115 is in a non-focused state, and the corresponding graphic contour is blurred, forming a significant difference with the preset pattern information. Accordingly, if the similarity between the graphic contour information indicated by the comparison information and the preset pattern information is lower than the second preset similarity, it indicates that the preset difference condition is met and the separation is determined to be successful. Otherwise, it indicates that the separation is unsuccessful. Among them, the second preset similarity can be consistent with the first preset similarity, or lower than the first preset similarity. In this way, the graphic contour is compared with the pre-stored preset pattern information to improve the efficiency of separation state recognition.

[0142] In other cases, the preset pattern information indicates the target contour information obtained based on image segmentation in the fourth image obtained when the molding layer 115 is in contact with the molding film 104, that is, the contour of the molding layer 115 under clear imaging is used as the reference pattern. During the separation process, if the similarity between the detected pattern contour information and the target contour information is lower than the second preset similarity, it indicates that the preset difference condition is met and the separation is determined to be successful. Otherwise, it indicates that the separation is unsuccessful. In this way, the image shape is compared with the actual pattern of the molding layer 115 in the unseparated state to improve the accuracy of separation state recognition.

[0143] It can be understood that the preset difference condition may also be satisfied when the shape corresponding to the graphic outline information is inconsistent with the preset pattern information corresponding to the preset pattern information. Conversely, if the shapes are consistent, the preset difference condition is not satisfied.

[0144] Based on some or all of the above embodiments, in some embodiments, the image acquisition device 101 is further configured to collect a fifth image of the molding layer 115 based on the illumination light, with the molding layer 115 as the focus plane, when the molding film 104 and the molding layer 115 are not separated; accordingly, the control device is configured to: perform a graphic detection of the molding layer 115 based on the fifth image to obtain a second detection result; and generate a molding abnormality detection result based on a comparison result of the second detection result and the preset pattern information corresponding to the molding layer 115. Specifically, the molding abnormality detection result is used to indicate whether the shape of the molding layer 115 of the to-be-molded layer is abnormal. In this way, the combination of the image acquisition device 101 and the illumination light can not only realize separation detection, but also can evaluate the printing effect before separation, and identify printing abnormalities in a timely manner.

[0145] Specifically, similar to the separation state identification of the fourth image, the graphic detection here can obtain the second detection result based on the edge detection algorithm, the frequency domain conversion method, the image segmentation algorithm, etc. The second graphic detection result indicates the current pattern of the molding layer 115, and the preset pattern information indicates the preset pattern required to be molded by the molding layer 115. If the comparison information indicates that the similarity between the current pattern corresponding to the molding layer 115 and the preset pattern is lower than the third preset similarity, it indicates that the shape of the molding layer 115 is abnormal, that is, it indicates that the printing result is abnormal, and the printing is suspended; if the comparison information indicates that the similarity between the current pattern corresponding to the molding layer 115 and the preset pattern is higher than the third preset similarity, it is determined that the shape of the molding layer 115 is normal, that is, it indicates that the printing result is normal, and the separation operation of the molding film 104 and the molding layer 115 is triggered.

[0146] The following describes an additive manufacturing method based on machine vision provided by an embodiment of the present application. This specification provides method operation steps such as an embodiment or a flowchart, but more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the order of many steps and does not represent the only execution order. When the actual system or server product is executed, it can be executed in the order of the method shown in the embodiment or the accompanying drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment).

[0147] Specifically, the method is applied to an additive manufacturing device based on machine vision, the additive manufacturing device includes a molding film, a molding base, an image acquisition device, a first light source for providing illumination light, a second light source for providing curing light, and a third light source for providing guide light; a gap for filling a printing material can be formed between the molding film and the molding base, the curing light can cure the printing material in the gap into a molding layer, the illumination light and the guide light can be projected onto the molding film and the molding base, and the illumination light and the guide light are non-sensitive bands of the printing material; the method may include:

[0148] S201: In the additive manufacturing process, in a state where the guide light can be combined with the curing light, the image acquisition device is controlled to acquire a target pattern of the layer to be formed and a first image of the formed layer based on the illumination light and the guide light, wherein the target pattern is carried by the guide light and projected onto the forming base;

[0149] S203: Based on the first image and preset alignment information, the molding base is controlled to move to align the molding layer with the target pattern projected by the guide light, wherein the preset alignment information is used to indicate a target stacking state between the molding layer and the layers to be molded corresponding to the target pattern.

[0150] In some embodiments, S201 includes:

[0151] S2011: performing image recognition on the first image to obtain first position information of the target pattern and second position information of the current pattern corresponding to the molding layer;

[0152] S2012: Calculating a motion trajectory based on the first position information, the second position information and the preset alignment information to obtain motion trajectory data;

[0153] S2013: Control the molding base to move until the molding layer is aligned with the target pattern based on the motion trajectory data.

[0154] In some embodiments, the guide light is further configured to project a leveling pattern onto a forming film, and a plurality of first marking positions are provided on the forming film; the method further comprises:

[0155] S301: Control the forming film to move horizontally to the first marking position and align with the leveling pattern;

[0156] S303: When the first mark position and the leveling pattern are aligned, determine a first focal plane position corresponding to the first mark position based on the imaging clarity of the leveling pattern;

[0157] S305: Determine a first leveling parameter according to the first focal plane positions corresponding to the first marking positions; and perform leveling processing on the molding film based on the first leveling parameter.

[0158] In some embodiments, the guide light is further configured to project a leveling pattern onto a molding base, and a plurality of second marking positions are provided on the molding base; the method further includes:

[0159] S401: Control the molding base to move horizontally to the second marking position and align with the leveling pattern;

[0160] S403: When the second mark position and the leveling pattern are aligned, determine a second focal plane position corresponding to the second mark position based on the imaging clarity of the leveling pattern;

[0161] S405: Determine a second leveling parameter according to the second focal plane positions corresponding to the second markers;

[0162] S407: performing leveling processing on the molding base based on the second leveling parameter.

[0163] In some embodiments, the image acquisition device is further configured to, during the separation process of the molding film and the molding layer, acquire a fourth image including the molding film and the molding layer based on the illumination light, wherein the fourth image is acquired with the molding film as the focal plane;

[0164] The method further includes S501: performing separation state recognition based on the fourth image to obtain a state recognition result, where the state recognition result is used to indicate the release state of the molding film and the molding layer.

[0165] In some other embodiments, the method further comprises:

[0166] S503: Performing clarity detection on the image area corresponding to the forming layer in the fourth image to obtain a clarity result;

[0167] S505: Generate a state recognition result based on the clarity result. If the clarity result indicates that the image clarity corresponding to the forming layer is lower than a preset clarity and / or the image clarity gradually decreases, the state recognition result indicates that the forming layer is successfully separated from the forming film.

[0168] In some other embodiments, the method further includes S507: inputting the fourth image into a separation state recognition model to perform separation state recognition to obtain a state recognition result, wherein the state recognition result is used to indicate whether the forming layer and the forming film are successfully separated or not.

[0169] In some embodiments, the method further comprises:

[0170] S601: Performing a graphic detection corresponding to the forming layer on the fourth image to obtain a first detection result, where the first detection result is used to indicate a graphic outline of the forming layer in the fourth image;

[0171] S603: Based on the comparison result of the first detection result and the preset pattern information corresponding to the molding layer, a state recognition result is generated. If the comparison result indicates that the difference between the graphic contour indicated by the first detection result and the preset pattern information meets a preset difference condition, the state recognition result indicates that the molding layer is successfully separated from the molding film.

[0172] In some embodiments, the image acquisition device is further configured to acquire a fifth image of the molding layer based on the illumination light with the molding layer as the focusing plane when the molding film and the molding layer are not separated; the method further includes:

[0173] S701: Performing graphic detection of the forming layer based on the fifth image to obtain a second detection result;

[0174] S703: Generate a molding abnormality detection result based on a comparison result between the second detection result and the preset pattern information corresponding to the molding layer.

[0175] The embodiment of the present application further provides a control device for additive manufacturing, which is applied to an additive manufacturing device based on machine vision. The additive manufacturing device includes a molding film, a molding base, an image acquisition device, a first light source for providing illumination light, a second light source for providing curing light, and a third light source for providing guide light; a gap for filling a printing material can be formed between the molding film and the molding base, the curing light can cure the printing material in the gap into a molding layer, the illumination light and the guide light can be projected onto the molding film and the molding base, and the illumination light and the guide light are non-sensitive bands of the printing material; the control device is configured as follows:

[0176] In the additive manufacturing process, the image acquisition device is controlled to acquire a target pattern of the layer to be formed and a first image of the formed layer based on the illumination light and the guide light, when the guide light can be combined with the curing light, wherein the target pattern is carried by the guide light and projected onto the forming base;

[0177] Based on the first image and preset alignment information, the molding base is controlled to move until the molding layer is aligned with the target pattern projected by the guide light, and the preset alignment information is used to indicate a target stacking state between the molding layer and the layers to be molded corresponding to the target pattern.

[0178] It should be noted that the above-mentioned machine vision-based additive manufacturing equipment embodiments, method embodiments, and control embodiments are based on the same implementation method.

[0179] An embodiment of the present application provides an electronic device, including a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the machine vision-based additive manufacturing method provided in the above method embodiment.

[0180] The memory can be used to store software programs and modules. The processor executes various functional applications and abnormality detection by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required for functions, etc.; the data storage area can store data created according to the use of the device, etc. In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory can also include a memory control device to provide the processor with access to the memory.

[0181] An embodiment of the present application also provides a computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to an abnormality detection method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the machine vision-based additive manufacturing method provided in the above method embodiment.

[0182] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0183] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0184] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0185] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0186] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing the relevant hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0187] The above are only preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. An additive manufacturing device based on machine vision, characterized in that: The device comprises a molding film (104), a molding base (105), an image acquisition device (101), a first light source (102) for providing illumination light, a second light source (103) for providing curing light, a third light source (119) for providing guide light, a control device and a first leveling mechanism; A gap (114) for filling a printing material can be formed between the molding film (104) and the molding base (105); the curing light can cure the printing material in the gap (114) into a molding layer (115); the illumination light and the guide light can be projected onto the molding film (104) and the molding base (105); the illumination light and the guide light are insensitive wavelength bands of the printing material; and the first leveling mechanism is in transmission connection with the molding film (104); During the additive manufacturing process, the guide light can be combined with the curing light, and the guide light is configured to carry a target pattern of the layer to be formed and projected onto the forming base (105); the image acquisition device (101) is configured to acquire a first image including the target pattern and the forming layer (115) based on the illumination light and the guide light; The control device is configured to control the molding base (105) to move until the molding layer (115) is aligned with the target pattern projected by the guide light based on the first image and preset alignment information, wherein the preset alignment information is used to indicate a target stacking state between the molding layer (115) and the to-be-molded layer corresponding to the target pattern; The guide light is further configured to project a leveling pattern onto the molding film (104), and a plurality of first marking positions are provided on the molding film (104); The control device is configured to: control the forming film (104) to move horizontally until the first marking position is aligned with the leveling pattern; In a state where the first mark position and the leveling pattern are aligned, determining a first focal plane position corresponding to the first mark position based on an imaging clarity of the leveling pattern; A first leveling parameter is determined according to the first focal plane positions corresponding to the first marking positions; and a leveling process is performed on the molding film (104) based on the first leveling parameter.

2. The device according to claim 1, characterized in that The control device is configured to: Performing image recognition on the first image to obtain first position information of the target pattern and second position information of the current pattern corresponding to the molding layer (115); Perform motion trajectory calculation based on the first position information, the second position information and the preset alignment information to obtain motion trajectory data; Based on the motion trajectory data, the molding base (105) is controlled to move until the molding layer (115) is aligned with the target pattern.

3. The device according to claim 2, characterized in that The motion trajectory data comprises a rotation angle and translation trajectory information of the molding base, the rotation angle being used to indicate a rotation operation of the molding base (105), and the translation trajectory information being used to indicate a translation operation of the molding base (105).

4. The device according to claim 1, characterized in that The guide light is further configured to project a leveling pattern onto the molding base (105), and a plurality of second marking positions are provided on the molding base (105); The control device is configured to: control the molding base (105) to move horizontally until the second marking position is aligned with the leveling pattern; In a state where the second mark position is aligned with the leveling pattern, determining a second focal plane position corresponding to the second mark position based on the imaging clarity of the leveling pattern; A second leveling parameter is determined according to the second focal plane position corresponding to each of the second marking positions; and a leveling process is performed on the molding base (105) based on the second leveling parameter.

5. The device according to claim 4, characterized in that The image acquisition device (101) is further configured to acquire a third image including the leveling pattern and at least one of the second marking positions based on the illumination light and the guide light; the control device is configured to control the molding base (105) to translate until the second marking position is aligned with the leveling pattern based on the position of the leveling pattern and the position of the second marking position in the third image.

6. The device according to any one of claims 1 to 5, characterized in that The image acquisition device (101) is further configured to, during the separation process of the molding film (104) and the molding layer (115), acquire a fourth image including the molding film (104) and the molding layer (115) based on the illumination light, wherein the fourth image is acquired with the molding film (104) as a focal plane; The control device is configured to perform separation state recognition based on the fourth image to obtain a state recognition result, wherein the state recognition result is used to indicate the release state of the molding film (104) and the molding layer (115).

7. The device according to claim 6, characterized in that The control device is configured to: Performing clarity detection on an image area corresponding to the molding layer (115) in the fourth image to obtain a clarity result; The state recognition result is generated based on the clarity result; if the clarity result indicates that the image clarity corresponding to the molding layer (115) is lower than a preset clarity, and / or the image clarity gradually decreases, the state recognition result indicates that the molding layer (115) is successfully separated from the molding film (104).

8. The device according to claim 6, characterized in that The control device is configured to: The fourth image is input into a separation state recognition model to perform separation state recognition, thereby obtaining the state recognition result, wherein the state recognition result is used to indicate whether the forming layer (115) and the forming film (104) are successfully separated or unsuccessfully separated.

9. The device according to claim 6, characterized in that The control device is configured to: Performing a graphic detection corresponding to the molding layer (115) on the fourth image to obtain a first detection result, wherein the first detection result is used to indicate a graphic outline of the molding layer (115) in the fourth image; The state recognition result is generated based on a comparison result between the first detection result and the preset pattern information corresponding to the molding layer (115); if the comparison result indicates that the difference between the graphic outline indicated by the first detection result and the preset pattern information satisfies a preset difference condition, the state recognition result indicates that the molding layer (115) is successfully separated from the molding film (104).

10. The device according to any one of claims 1 to 5, characterized in that The image acquisition device (101) is further configured to, in a state where the molding film (104) and the molding layer (115) are not separated, use the molding layer (115) as a focusing plane and acquire a fifth image of the molding layer (115) based on the illumination light; The control device is configured to: Performing graphic detection of the molding layer (115) based on the fifth image to obtain a second detection result; Based on the comparison result between the second detection result and the preset pattern information corresponding to the molding layer (115), a molding abnormality detection result is generated.

11. The device according to any one of claims 1 to 5, characterized in that When the first image is collected, the target pattern of the guiding light and the molding layer are located at the same focal plane.

12. The device according to any one of claims 1 to 5, characterized in that The device also includes an optical path component, including a beam assembly and a processing lens (109); The whole beam assembly is used to adjust the illumination light and make the illumination light irradiate the molding film (104) and the molding base (105) through the processing lens (109); adjust the guide light and the curing light to combine into a beam and make the guide light irradiate the molding film (104) or the molding base (105) through the processing lens (109); and adjust the curing light and make the curing light irradiate the interval (114) through the processing lens (109).

13. The device according to any one of claims 1 to 5, characterized in that A first lens group (107), a first beam splitter (108) and a processing lens (109) are arranged between the first light source (102) and the molding film (104), and a second lens group (110) is arranged between the image acquisition device (101) and the molding film (104); The first lens group (107), the first beam splitter (108) and the processing lens (109) are located in a first light path between the first light source (102) and the molding film (104); The processing lens (109), the first beam splitter (108) and the second lens group (110) are located in a second optical path between the image acquisition device (101) and the molding film (104).

14. The device according to claim 13, characterized in that The first lens group (107) and the first beam splitter (108) are arranged on a common optical axis, the first beam splitter (108) and the processing lens (109) are arranged on a common optical axis, and the second lens group (110) and the image acquisition device (101) are arranged on a common optical axis.

15. The device according to claim 13, characterized in that The illumination light is emitted to the processing lens (109) after passing through the first lens group (107) and the first beam splitter (108), and is projected onto the molding film and the spacer after passing through the processing lens (109); The illumination light is reflected by the molding film (104) and the molding layer (115) in the spacer (114) to form a light beam with molding layer characteristics, and is focused to the image acquisition device (101) after passing through the processing lens (109), the first beam splitter (108) and the second lens group (110) to generate an image area of ​​the molding layer (115) in the first image.

16. The device according to any one of claims 1 to 5, characterized in that The light paths of the second light source (103) and the third light source (119) are at least partially the same, so that the curing light and the guiding photosynthetic beam are irradiated onto the molding layer (115).

17. The device according to any one of claims 1 to 5, characterized in that A beam combiner (120), a third lens group (112) and a second beam splitter (111) are arranged on the optical path between the second light source (103), the third light source (119) and the molding film (104), and the beam combiner (120) is used to combine the curing light and the guiding light; The beam combiner (120), the third lens group (112), the second beam splitter (111) and the processing lens (109) are located on a third light path between the second light source (103) and the molding film (104), and on a fourth light path between the third light source (119) and the molding film (104).

18. The device according to any one of claims 1 to 5, characterized in that The curing light is a projection light capable of curing the printing material, and is used to carry the target pattern of the layer to be formed.

19. The device according to any one of claims 1 to 5, characterized in that The device further comprises a material pool (106) for accommodating the printing material, wherein the material pool (106) is located below the molding base (105) and the molding base (105) can extend into the material pool (106).

20. The device according to claim 19, characterized in that The image acquisition device (101) and the material pool (106) are respectively located on different sides of the molding surface of the molding base (105).

21. The device according to any one of claims 1 to 5, characterized in that The additive manufacturing device further comprises a rotation alignment mechanism (121) drivingly connected to the molding base (105), the rotation alignment mechanism comprising a rotation component and a motion component; The rotating component can drive the molding base (105) to rotate around the Z axis, and the moving component can drive the molding base (105) to move horizontally and up and down along the Z axis.

22. The device according to claim 21, characterized in that The control device is specifically configured as follows: The rotation alignment mechanism (121) is controlled to move based on the motion trajectory data, so as to drive the molding base (105) to move until the molding layer (115) is aligned with the target pattern.

23. The device according to claim 21, characterized in that The rotation alignment mechanism (121) is transmission-connected to the material pool (106) and / or the molding film (104), and the molding base (105) is capable of moving in coordination with at least one of the material pool (106) and the molding film (104).

24. The device according to any one of claims 1 to 5, characterized in that The determining the first focal plane position corresponding to the first mark position based on the imaging clarity of the leveling pattern comprises: In a state where the first mark position and the leveling pattern are aligned, controlling the image acquisition device (101) to acquire a first leveling image of the leveling pattern; Performing clarity detection on the first leveling image to obtain imaging clarity of the leveling pattern; If the imaging clarity indicates that the leveling pattern is clearly imaged, determining the current imaging focal plane as the first focal plane position of the first mark position; If the imaging clarity indicates that the leveling pattern is not clearly imaged, the molding film (104) is controlled to move along the Z axis, or the image acquisition device (101) is controlled to adjust the focal length, until the imaging clarity corresponding to the updated first leveling image indicates that the leveling pattern is clearly imaged, thereby obtaining a first focal plane position of the first mark position.

25. The device according to claim 24, characterized in that The control device is also configured to: If the molding film (104) is controlled to move along the Z axis until the leveling pattern is clearly imaged, the longitudinal position of the molding film (104) is controlled to be reset before the first mark position is controlled to be aligned with the leveling pattern, so as to adjust the longitudinal position of the molding film (104) to the longitudinal position at which the first mark position is initially aligned with the leveling pattern.

26. The device according to claim 24, characterized in that The control device is configured to: The projection position of the leveling pattern of the guide light is controlled to be aligned with a preset Z-axis position, and the first marking position of the molding film (104) is moved to be aligned with the preset Z-axis position.

27. The device according to claim 24, characterized in that The image acquisition device (101) is further configured to acquire a second image including the leveling pattern and at least one of the first marking positions based on the illumination light and the guide light; and the control device is configured to: Based on the position of the leveling pattern in the second image and the position of the first marking position, the molding film (104) is controlled to translate until the first marking position is aligned with the leveling pattern.

28. The device according to claim 24, characterized in that The plurality of first marking positions of the molding film (104) include at least three non-collinear first marking positions, and the control device is configured to: Controlling three non-collinear first marking positions to align with the leveling pattern respectively, and performing clear imaging; Determine a first focal plane position of a clear image where each of the first marking positions is aligned with the leveling pattern; The first leveling parameter is generated based on the first focal plane positions of the non-collinear first marking positions, and the first leveling parameter is used to level the inclined molding film.

29. The device according to any one of claims 1 to 5, characterized in that The first leveling mechanism can drive the forming film to swing.

30. The device according to claim 29, characterized in that The first leveling mechanism can drive the forming film to swing around an in-plane direction of at least one of the forming films.

31. The device according to claim 4 or 5, characterized in that Determining a second focal plane position corresponding to the second mark position based on the imaging clarity of the leveling pattern includes: In a state where the second mark position and the leveling pattern are aligned, controlling the image acquisition device (101) to acquire a second leveling image of the leveling pattern; Performing a clarity detection on the second leveling image to obtain an imaging clarity of the leveling pattern; if the imaging clarity indicates that the leveling pattern is clearly imaged, determining a current imaging focal plane as a second focal plane position of the second marker; If the imaging clarity indicates that the leveling pattern is not clearly imaged, the molding base (105) is controlled to move along the Z axis, or the image acquisition device (101) is controlled to adjust the focal length, until the imaging clarity corresponding to the updated second leveling image indicates that the leveling pattern is clearly imaged, thereby obtaining a second focal plane position of the second mark position.

32. The device according to claim 31, characterized in that The control device is also configured to: If the molding base (105) is controlled to move along the Z axis until the leveling pattern is clearly imaged, before the second mark position is controlled to be aligned with the leveling pattern, the longitudinal position of the molding base (105) is controlled to be reset, so as to adjust the longitudinal position of the molding base (105) to the longitudinal position at which the second mark position is initially aligned with the leveling pattern.

33. The device according to claim 31, characterized in that The control device is configured to: The projection position of the leveling pattern of the guide light is controlled to be aligned with a preset Z-axis position, and the second marking position of the molding base (105) is moved to be aligned with the preset Z-axis position.

34. The device according to claim 33, characterized in that The preset Z-axis position is coaxial with the optical axis of the image acquisition device.

35. The device according to claim 31, characterized in that The image acquisition device (101) is further configured to acquire a third image including the leveling pattern and at least one of the second marking positions based on the illumination light and the guide light; and the control device is configured to: Based on the position of the leveling pattern in the third image and the position of the second marking position, the molding base (105) is controlled to translate until the second marking position is aligned with the leveling pattern.

36. The device according to claim 31, characterized in that The plurality of second marking positions of the molding base include at least three non-collinear second marking positions, and the control device is configured as follows: respectively controlling the three non-collinear second marking positions to align with the leveling pattern and perform clear imaging; Determine a second focal plane position of a clear image in which each of the second marking positions is aligned with the leveling pattern; The second leveling parameter is generated based on the second focal plane position of each non-collinear second mark position, and the second leveling parameter is used to level the inclined molding surface.

37. The device according to any one of claims 1 to 5, characterized in that The additive manufacturing equipment further comprises a second leveling mechanism which is transmission-connected to the molding base (105), and the second leveling mechanism is capable of driving the molding base (105) to swing.

38. The device according to claim 37, characterized in that The second leveling mechanism is capable of driving the molding base (105) to swing in an in-plane direction around at least one of the molding bases (105).

39. The device according to any one of claims 1 to 5, characterized in that The additive manufacturing equipment further comprises a base moving device, the base moving device being in transmission connection with the molding base (105), and the base moving device being capable of driving the molding base (105) away from or close to the molding film (104); The base moving device is electrically connected to the control device, and the control device is capable of controlling the movement of the base moving device to drive the molding base (105) to move.

40. The device according to claim 39, characterized in that The control device is also configured to: in response to the printing material solidifying into a molding layer (115), trigger a separation process and control the base moving device to drive the molding base (105) away from the molding film (104) to form the gap (114) between the surface of the molding layer (115) and the molding film (104).

41. A machine vision-based additive manufacturing method, applied to the machine vision-based additive manufacturing device according to any one of claims 1 to 17, characterized in that: The additive manufacturing equipment comprises a molding film (104), a molding base (105), an image acquisition device (101), a first light source (102) for providing illumination light, a second light source (103) for providing curing light, a third light source (119) for providing guide light, and a first leveling mechanism; a gap (114) for filling a printing material can be formed between the molding film (104) and the molding base (105), the curing light can cure the printing material in the gap (114) into a molding layer (115), the illumination light and the guide light can be projected onto the molding film (104) and the molding base (105), and the illumination light and the guide light are in the non-sensitive wavelength band of the printing material; the first leveling mechanism is in transmission connection with the molding film (104); the method comprises: In an additive manufacturing process, the image acquisition device (101) is controlled in a state where the guide light can be combined with the curing light to acquire a target pattern of the layer to be formed and a first image of the forming layer (115) based on the illumination light and the guide light, wherein the target pattern is carried by the guide light and projected onto the forming base (105); Based on the first image and preset alignment information, controlling the molding base (105) to move until the molding layer (115) is aligned with the target pattern projected by the guide light, the preset alignment information being used to indicate a target stacking state between the molding layer (115) and the layers to be molded corresponding to the target pattern; The guiding light is further configured to project a leveling pattern onto a forming film, and a plurality of first marking positions are provided on the forming film; the method further includes: Controlling the forming film (104) to move horizontally until the first marking position is aligned with the leveling pattern; In a state where the first mark position and the leveling pattern are aligned, determining a first focal plane position corresponding to the first mark position based on an imaging clarity of the leveling pattern; Determine a first leveling parameter according to the first focal plane positions corresponding to the first marking positions; The forming film (104) is leveled based on the first leveling parameter.

42. A control device for additive manufacturing based on machine vision, applied to the additive manufacturing equipment based on machine vision according to any one of claims 1 to 17, characterized in that: The additive manufacturing device comprises a molding film (104), a molding base (105), an image acquisition device (101), a first light source (102) for providing illumination light, a second light source (103) for providing curing light, a third light source (119) for providing guide light, and a first leveling mechanism; a gap (114) for filling a printing material can be formed between the molding film (104) and the molding base (105), the curing light can cure the printing material in the gap (114) into a molding layer (115), the illumination light and the guide light can be projected onto the molding film (104) and the molding base (105), and the illumination light and the guide light are in the non-sensitive wavelength band of the printing material; the first leveling mechanism is in transmission connection with the molding film (104); The control device is configured to: In an additive manufacturing process, the image acquisition device (101) is controlled in a state where the guide light can be combined with the curing light to acquire a target pattern of the layer to be formed and a first image of the forming layer (115) based on the illumination light and the guide light, wherein the target pattern is carried by the guide light and projected onto the forming base (105); Based on the first image and preset alignment information, controlling the molding base (105) to move until the molding layer (115) is aligned with the target pattern projected by the guide light, the preset alignment information being used to indicate a target stacking state between the molding layer (115) and the layers to be molded corresponding to the target pattern; The guiding light is further configured to project a leveling pattern onto a forming film, and a plurality of first marking positions are provided on the forming film; the method further comprises: Controlling the forming film (104) to move horizontally until the first marking position is aligned with the leveling pattern; In a state where the first mark position and the leveling pattern are aligned, determining a first focal plane position corresponding to the first mark position based on an imaging clarity of the leveling pattern; Determine a first leveling parameter according to the first focal plane positions corresponding to the first marking positions; The forming film (104) is leveled based on the first leveling parameter.

43. An electronic device, comprising a processor and a memory, characterized in that: The memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the machine vision-based additive manufacturing method as described in claim 41.

44. A computer-readable storage medium, characterized in that The storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the machine vision-based additive manufacturing method as described in claim 41.

45. A computer program product or a computer program, characterized in that The computer program product or computer program includes computer instructions, which, when executed by a processor, implement the machine vision-based additive manufacturing method as claimed in claim 41.

Images