CN111761224B - Metal additive manufacturing online mobile monitoring mechanism and online appearance detection equipment - Google Patents
Metal additive manufacturing online mobile monitoring mechanism and online appearance detection equipment Download PDFInfo
- Publication number
- CN111761224B CN111761224B CN202010442944.XA CN202010442944A CN111761224B CN 111761224 B CN111761224 B CN 111761224B CN 202010442944 A CN202010442944 A CN 202010442944A CN 111761224 B CN111761224 B CN 111761224B
- Authority
- CN
- China
- Prior art keywords
- ccd camera
- fixing
- clamp
- additive manufacturing
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K26/00—Working by laser beam, e.g. welding, cutting or boring
- B23K26/34—Laser welding for purposes other than joining
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B33—ADDITIVE MANUFACTURING TECHNOLOGY
- B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- B33Y30/00—Apparatus for additive manufacturing; Details thereof or accessories therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8411—Application to online plant, process monitoring
Abstract
The invention provides a metal additive manufacturing online mobile monitoring mechanism and online appearance detection equipment, wherein the online mobile monitoring mechanism comprises a mobile platform, a CCD camera and a clamp assembly used for clamping the CCD camera and fixed on the mobile platform, the clamp assembly comprises a shovel-shaped clamp, a sleeve-type clamp and a grappling clamp, the shovel-shaped clamp is used for clamping the CCD camera with the weight ranging from 1.5kg to 4.0kg, the sleeve-type clamp is used for clamping the CCD camera with the weight ranging from 4.0kg to 9.0kg, and the grappling clamp is used for clamping the CCD camera with the weight of more than 9 kg. The invention comprises a plurality of different clamps, can select different clamps to clamp the CCD cameras with different weights, can fully cover the CCD cameras with various volume and weight, can effectively clamp and fix various CCD cameras on the market, has higher stability, is convenient to shoot high-precision metal additive manufacturing images, and meets the requirements of various online appearance detection methods on the image precision.
Description
Technical Field
The invention relates to the field of additive manufacturing, in particular to an online mobile monitoring mechanism for metal additive manufacturing and online appearance detection equipment.
Background
The metal additive manufacturing is a novel laser rapid prototyping manufacturing process, and belongs to additive manufacturing. The metal part with close to complete density and good mechanical property can be directly formed by using the die. Therefore, the technology has great potential and shows good application prospect in the fields of aerospace, automobiles, biomedical treatment and the like. However, in the metal additive manufacturing process, due to the influence of process parameters such as laser power density and scanning speed, defects (such as cracks, holes, and the like) may occur in the forming process of the component, and thus, there is an increasing demand for an online diagnosis device for defects in the metal additive manufacturing process.
At present, the clamps of the existing metal additive manufacturing online mobile monitoring mechanism on the market are not tightly occluded, screwed, loosened and shaken in the operation process. The above reasons may cause that the shooting precision during the moving process does not meet the requirements, and even the shooting range exceeds the target range. This is extremely disadvantageous for monitoring by our traceable mobile online monitoring mechanism. At present, one or more proper clamps are not applied to the movable online monitoring mechanism.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a metal additive manufacturing online mobile monitoring mechanism and online appearance detection equipment.
The invention is realized by the following steps:
in one aspect, the invention provides an online mobile monitoring mechanism for metal additive manufacturing, which comprises a mobile platform, a CCD camera and a clamp assembly, wherein the clamp assembly is used for clamping the CCD camera and is fixed on the mobile platform, the clamp assembly comprises a shovel-shaped clamp, a sleeve-shaped clamp and a grappling clamp, the shovel-shaped clamp is used for clamping the CCD camera with the weight ranging from 1.5kg to 4.0kg, the sleeve-shaped clamp is used for clamping the CCD camera with the weight ranging from 4.0kg to 9.0kg, and the grappling clamp is used for clamping the CCD camera with the weight of more than 9 kg.
Further, shovel shape anchor clamps include camera fixed plate and moving platform mounting, be equipped with the bolt hole on the camera fixed plate, the camera fixed plate is used for stretching into between two fixed planes of CCD camera and fixed through bolt and two fixed planes, the moving platform mounting is fixed in one side of camera fixed plate.
Further, the mobile platform mounting includes two fixed blocks that are located two faces about the camera fixed plate respectively and through the bolt with the camera fixed plate is fixed, two the fixed block all have protrusion in the protruding portion at camera fixed plate edge, two be equipped with corresponding bolt hole on the protruding portion.
Furthermore, the sleeve type clamp comprises a thread fixing piece and a moving platform fixing block, one end of the thread fixing piece is fixed with the moving platform fixing block, and the surface of the other end of the thread fixing piece is provided with an external thread which is used for being screwed and fixed with an internal thread on the CCD camera fixing box.
Furthermore, a fixing hole is concavely formed in one end of the moving platform fixing block, one end of the thread fixing piece extends into the fixing hole for fixing, a lug is convexly arranged at the other end of the moving platform fixing block towards the periphery, and bolt holes are formed in the lug.
Furthermore, the end face of the end, provided with the threads, of the thread fixing piece is provided with a plurality of convex blocks, and the surface of the thread fixing piece is inwards concave to form a strip-shaped groove.
Further, grapple formula anchor clamps include grapple board and moving platform dead lever, the front end of grapple board is equipped with a plurality of grabs for it is fixed with the CCD camera in stretching into the hole of the fixed box of CCD camera, the one end of moving platform dead lever with the face of grapple board is fixed, and the other end is equipped with the bolt hole.
Further, moving platform includes two first dustproof guide rails along horizontal direction parallel arrangement, two all be equipped with first dustproof slider on the first dustproof guide rail, two be equipped with the dustproof guide rail of second between the first dustproof slider, be equipped with the dustproof slider of second on the dustproof guide rail of second, be equipped with the third dirt guide rail of vertical setting on the dustproof slider of second, be equipped with the third dirt slider on the third dirt guide rail, be equipped with CCD camera support on the third dirt slider, the CCD camera passes through the anchor clamps subassembly to be fixed on the CCD camera support.
Further, the CCD camera is provided with a plurality of CCD cameras, and the CCD cameras are all fixed on the CCD camera bracket through clamp assemblies.
The laser tracking instrument is fixed on the CCD camera support and used for positioning an area where laser processing is carried out on the surface of a processed workpiece and feeding back the area to the mechanism control system, and the mechanism control system is used for controlling the movement of the mobile platform according to information fed back by the laser tracking instrument so that the CCD camera can track and shoot the processing area.
On the other hand, the invention also provides metal additive manufacturing online appearance detection equipment, which comprises the metal additive manufacturing online mobile monitoring mechanism, an image processing system and a working system, wherein the image processing system is used for accurately positioning and identifying the defect area according to the molten pool and the sputtering image collected by the CCD camera of the online mobile monitoring mechanism and feeding back the result to the working system, and the working system is used for adjusting the process parameters of 3D printing according to the information fed back by the image processing system.
Further, the image processing system comprises an image preprocessing module, a generating type antagonistic neural network module and an LBP algorithm module, wherein the image preprocessing module is used for receiving the molten pool and the sputtering image collected by the CCD camera, carrying out graying processing and median filtering preprocessing operation on the image, the generating type antagonistic neural network module is used for repairing the defects in the preprocessed molten pool and the sputtering image, and the LBP algorithm module is used for identifying the difference between the molten pool and the original sputtering image and the repaired molten pool and the repaired sputtering image, so that the precise positioning and identification of the defect area are realized.
Compared with the prior art, the invention has the following beneficial effects:
the metal additive manufacturing online mobile monitoring mechanism and the online appearance detection device provided by the invention comprise a plurality of different clamps, and different clamps can be selected for clamping CCD cameras with different weights, so that the CCD cameras with various volume weights can be fully covered, various CCD cameras on the market can be effectively clamped and fixed, the stability is high, a high-precision metal additive manufacturing image can be conveniently shot, and the requirements of various online appearance detection methods on the image precision are met.
Drawings
Fig. 1 is a schematic structural view of a shovel clamp according to an embodiment of the present invention;
FIG. 2 is a schematic view of a shovel clamp according to an embodiment of the present invention;
FIG. 3 is a schematic view of a telescopic clamp according to an embodiment of the present invention;
FIG. 4 is a schematic view of a telescopic clamp according to an embodiment of the present invention;
FIG. 5 is a schematic structural view of a grapple type clamp according to an embodiment of the present invention;
FIG. 6 is a schematic view of a grapple type of clamp according to an embodiment of the present invention in use;
FIG. 7 is a flow chart of the use of the clamp assembly provided by an embodiment of the present invention;
FIG. 8 is a flow chart of fixture selection provided by an embodiment of the present invention;
FIG. 9 is a schematic view of a metal additive manufacturing online mobile monitoring mechanism according to an embodiment of the present invention;
fig. 10 is a schematic diagram of signal transmission of a metal additive manufacturing online appearance detection device according to an embodiment of the present invention;
fig. 11 is a diagram illustrating an example of image processing according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
as shown in fig. 9, an embodiment of the present invention provides an online mobile monitoring mechanism for metal additive manufacturing, including a mobile platform 4 and a CCD camera 5, where the mobile platform 4 is used to drive the CCD camera 5 to move, and the CCD camera 5 is used to online collect a part surface image in a selective laser melting manufacturing process. The mechanism also includes a gripper assembly as shown in fig. 1-6 for gripping the CCD camera 5 and securing it to the moving platform 4, which includes a spade gripper 1, a sleeve gripper 2, and a grapple gripper 3. The shovel clamp 1 is mainly used for clamping the CCD camera 5 with the weight of 1.5 kg-4.0 kg under the condition that the CCD camera 5 is light. The sleeve type clamp 2 is mainly used for clamping the CCD camera 5 with the weight within the range of 4.0 kg-9.0 kg under the condition that the weight of the CCD camera 5 is moderate, the sleeve type clamp 2 adopts a screwing and fixing mode, and the connecting section is longer, so the support strength is better, and the range of bearing the weight of the camera is larger. The grapple type clamp 3 is mainly used for clamping the CCD camera 5 with the weight of more than 9kg under the condition that the weight of the CCD camera 5 is large, and the grapple type clamp 3 can bear the CCD camera 5 with large volume and long length. The CCD camera 5 in the present invention is the whole of the CCD camera body plus the lens.
As shown in fig. 7 and 8, when the metal additive manufacturing online mobile monitoring mechanism according to the embodiment of the present invention is used, the CCD camera 5 is weighed, a corresponding clamp is selected according to the weight, then one end of the clamp is fixed to the mobile platform 4, the other end of the clamp is fixed to the CCD camera 5, and then a motion test clamping effect is simulated to realize reliable fixation.
The metal additive manufacturing online mobile monitoring mechanism and the online appearance detection device provided by the embodiment of the invention comprise a plurality of different clamps, and the different clamps can be selected for clamping CCD cameras with different weights, so that the CCD cameras with various volume weights can be fully covered, various CCD cameras on the market can be effectively clamped and fixed, the stability is high, a high-precision metal additive manufacturing image can be conveniently shot, and the requirements of various online appearance detection methods on the image precision are met.
As shown in fig. 1 and 2, shovel anchor clamps 1 include camera fixed plate 11 and moving platform mounting 12, be equipped with bolt hole 14 on the camera fixed plate 11, camera fixed plate 11 is used for stretching into between two stationary planes of CCD camera 5 and fixed through bolt and two stationary planes, realizes shovel anchor clamps 1 and CCD camera 5's fixed, and this fixed mode makes CCD camera 5 rotate to a certain extent, conveniently tracks and prints laser, and two stationary planes can be CCD camera 5 from the area, also can be the later stage and install additional on CCD camera 5. Moving platform mounting 12 is fixed in one side of camera fixed plate 11, moving platform mounting 12 including be located camera fixed plate 11 about respectively on two faces and through the bolt with two fixed blocks that camera fixed plate 11 is fixed, two the fixed block all have protrusion in the bulge 13 at camera fixed plate 11 edge, two be equipped with corresponding bolt hole on the bulge 13, two bulge 13 is used for the stationary plane that centre gripping moving platform 4 stretches out and fixes the two through the bolt, realizes shovel shape anchor clamps 1 and moving platform 4's fixed.
As shown in fig. 3 and 4, the sleeve-type fixture 2 includes a threaded fastener 21 and a moving platform fixing block 24, one end of the threaded fastener 21 is fixed to the moving platform fixing block 24, and an external thread is provided on the other end surface of the threaded fastener 21 for being screwed and fixed with an internal thread on a CCD camera 5 fixing box, so as to fix the sleeve-type fixture 2 and the CCD camera 5, and the CCD camera 5 fixing box with the internal thread may be a CCD camera 5 itself or a CCD camera 5 installed in a later stage. The fixing structure is characterized in that a fixing hole is concavely formed in one end of the moving platform fixing block 24, one end of the thread fixing piece 21 extends into the fixing hole for fixing, the specific fixing mode is not limited, for example, bolt fixing or clamping fixing and the like are achieved, a lug 25 is convexly arranged at the other end of the moving platform fixing block 24 towards the periphery, bolt holes are formed in the lug 25, the lug 25 is attached to one surface of the moving platform 4 and fixed through bolts, and the sleeve-type clamp 2 is fixed to the moving platform 4. Preferably, the end face of the end of the threaded fixing member 21 with threads is provided with a plurality of protrusions 22 for being screwed and then fixed with the camera fixing box. The surface of the threaded fixing part 21 is inwards concavely provided with a strip-shaped groove 23 for reducing the self weight of the clamp. The sleeve type clamp 2 is longer in screwing length in the fixing mode, and the bearing coefficient is larger than that of a shovel type clamp, so that the effective clamping range is larger, and the clamp is suitable for most CCD cameras.
As shown in fig. 5 and 6, the grapple type clamp 3 includes a grapple plate 31 and a movable platform fixing rod 33, the front end of the grapple plate 31 is provided with a plurality of grapples 32 for extending into the holes of the CCD camera 5 fixing box for engagement and fixation, so as to realize the grapple type clamp 3 and fix the CCD camera 5, the lower part of the CCD camera 5 with high precision and large volume has holes for fixation, and if there is no hole, the CCD camera 5 can be additionally provided with the fixing box with holes. One end of the moving platform fixing rod 33 is fixed to the plate surface of the grappling plate 31, the other end of the moving platform fixing rod is provided with a bolt hole 34, and the grappling clamp 3 is fixed to the moving platform 4 by passing a bolt through the bolt hole 34. The fixing mode of the grapple type clamp 3 can effectively reduce the occupied space, and the grapple is more suitable for an ultra-high precision CCD camera with large weight and large volume compared with other fixing modes.
As shown in fig. 9, the moving platform 4 is a three-axis moving platform, and includes two first dustproof guide rails 41 arranged on a bottom plate 49 in parallel along the horizontal direction, and a first dustproof slider 42 is arranged on each of the two first dustproof guide rails 41 and is used for realizing x-axis linear motion of the CCD camera 5; two it is equipped with the dustproof guide rail 43 of second to span between the first dustproof slider 42, be equipped with the dustproof slider 44 of second on the dustproof guide rail 43 of second for realize CCD camera 5's y axle linear motion, be equipped with the third dirt guide rail 45 of vertical setting on the dustproof slider 44 of second, be equipped with third dirt slider 46 on the third dirt guide rail 45, be used for realizing CCD camera 5's z axle linear motion. And a CCD camera support 47 is arranged on the third dust prevention sliding block 46, and the CCD camera 5 is fixed on the CCD camera support 47 through a clamp assembly. Preferably, the CCD cameras 5 are provided with a plurality of CCD cameras 5, and are all fixed on the CCD camera support 47 through a clamp assembly, two CCD cameras in this embodiment, and the plurality of CCD cameras 5 can comprehensively photograph the processing area of the workpiece 48 to be processed, so that the surface image of each layer of the part in the selective laser melting manufacturing process can be acquired on line, and the accuracy of image detection is improved. Further preferably, the system further comprises a laser tracker 6 and a mechanism control system (not shown), wherein the laser tracker 6 is fixed on the CCD camera support 47, and is used for positioning an area on the surface of the workpiece 48 being subjected to laser processing and feeding back the area to the mechanism control system, and the mechanism control system is used for accurately controlling the movement of the moving platform 4 according to information fed back by the laser tracker 6, so that the CCD camera 5 performs tracking shooting on the processing area.
Example 2:
as shown in fig. 10, an embodiment of the present invention further provides an online appearance inspection apparatus for metal additive manufacturing, including the online mobile monitoring mechanism for metal additive manufacturing in embodiment 1, further including an image processing system and a working system, where the image processing system is configured to accurately locate and identify a defect region according to a molten pool and a sputtered image collected by a CCD camera of the online mobile monitoring mechanism, and feed back a result to the working system, and the working system is configured to adjust process parameters of 3D printing according to information fed back by the image processing system, so as to manufacture a high-quality defect-free part.
Specifically, the image processing system comprises an image preprocessing module, a Generative adaptive neural Network (GAN) module and an LBP (Local Binary Pattern) algorithm module, wherein the image preprocessing module is used for receiving a molten pool and a sputtering image collected by a CCD camera and performing image preprocessing operations such as graying processing and median filtering on the image, the Generative adaptive neural Network module is used for repairing defects in the preprocessed molten pool and sputtering image, and the LBP algorithm module is used for identifying differences between the molten pool and sputtering original image and the repaired molten pool and sputtering image, so as to accurately locate and identify a defect region.
The principle of the generative antagonistic neural network is as follows: a network of generated pictures is formed which receives a random noise z from which the picture is generated, denoted G. Then, a discrimination network is generated to discriminate whether a picture is "real". The input parameter is x, x represents a sputtering or molten pool picture, and the output D (x) represents the probability that x is the molten pool or sputtering picture shot by a real camera, if the x is 1, the x represents a picture which is 100% real, and the output is 0, the x represents a picture which is not possible to be real. In the training process, the aim of generating the network G is to generate a real picture as much as possible to deceive the discrimination network D. And the aim of D is to separate the picture generated by G and the real picture as much as possible. Thus, G and D constitute a dynamic "gaming process". The generating type antagonistic neural network module utilizes the principle, the G module of the generating type antagonistic neural network module continuously performs image defect repairing learning according to input training set pictures, namely a melting pool and an original sputtering image (as shown in figure 11a) in the metal additive manufacturing process, the G module learns the defect repairing capability through a certain amount of sample training, so that defects in the pretreated melting pool and the sputtering image are repaired to obtain the repaired melting pool and the sputtering image (as shown in figure 11b), and the pretreated melting pool and sputtering image and the repaired melting pool and sputtering image are input into the LBP algorithm module together.
The generation type antagonistic neural network module firstly trains a generation type antagonistic neural network by using a training set formed by a defective molten pool and a defective sputtering image and a non-defective molten pool and a non-defective sputtering image to obtain the generation type antagonistic neural network with defect repairing capability, wherein the generation type antagonistic neural network comprises a generation network G and a discrimination network D, and the training process comprises the following steps:
inputting the defective molten pool and sputtering image X in the training set into a generating network G to generate a repaired molten pool and sputtering image G (X);
inputting a molten pool and sputtering image Y without defects in the training set and the repaired molten pool and sputtering image G (X) into the judgment network D to obtain judgment results D (Y) and D (G (X));
calculating and generating a loss function G _ loss of the network and a loss function D _ loss of the discrimination network according to the discrimination results D (Y) and D (G (X));
and respectively updating the generating network G and the judging network D according to the loss function G _ loss of the generating network and the loss function D _ loss of the judging network until the training is completed.
In the training process, the aim of generating the network G is to generate a real picture as much as possible to deceive the discrimination network D, and the aim of discriminating the network D is to separate the picture generated by the network G and the real picture as much as possible, so that the network G and the network D form a dynamic game process. Through a certain amount of sample training, the generated network G learns to obtain the defect repairing capability.
The generative antagonistic neural network module then utilizes the trained generative antagonistic neural network to repair the defects in the pretreated molten pool and the sputtering image, and the method specifically comprises the following steps:
the generating type countermeasure neural network firstly carries out size transformation on a molten pool and a sputtering image to be repaired, transforms the molten pool and the sputtering image to the input size of the adaptive defect feature extraction network, carries out defect feature extraction through the defect feature extraction network, outputs a convolution feature map of an original image, carries out image semantic segmentation according to the convolution feature map, and further generates a network output through a candidate region through the convolution feature map to obtain a molten pool region and a sputtering region;
and repairing the defects in the molten pool area and the sputtering area respectively by using the trained generative antagonistic neural network.
In the embodiment, the molten pool area and the sputtering area are classified through image semantic segmentation, so that the molten pool area and the sputtering area can be conveniently and respectively processed in a follow-up manner.
The principle of the LBP algorithm is: the original LBP operator is defined as that in a window of 3 × 3, the central pixel of the window is used as a threshold value, the gray values of the adjacent 8 pixels are compared with the central pixel, if the values of the surrounding pixels are greater than the value of the central pixel, the position of the pixel is marked as 1, otherwise, the position is 0. Thus, 8 points in the 3-by-3 neighborhood can generate 8-bit binary numbers (usually converted into decimal numbers, namely LBP codes, which are 256 in total) through comparison, namely the LBP value of the central pixel point of the window is obtained, and the value is used for reflecting the texture information of the area, so that the accurate positioning and identification of the defect area are realized. The LBP algorithm module adopts the principle, the LBP values of the molten pool, the original sputtering image and the repaired molten pool and the repaired sputtering image are obtained through the local binary pattern algorithm, the difference between the molten pool and the original sputtering image and the repaired molten pool and the repaired sputtering image is identified according to the numerical difference of the LBP values of the molten pool and the original sputtering image, the image (such as figure 11c) of the difference part is the image of the defect area, and the displayed image is the position and the form of the defect area, so that the defect area is accurately positioned and identified according to the image of the defect area.
The LBP algorithm module is used for accurately positioning and identifying the defect area according to the image of the defect area and specifically comprises the following steps:
positioning the defect area according to the numerical difference of LBP values of the molten pool and the original sputtering image and the repaired molten pool and the repaired sputtering image to obtain the position of a target frame of the defect area; and comparing the image of the defect area with the defect image of the known defect type in the picture library, wherein the defect type of the defect image which is closest to the defect image in the picture library is the defect type corresponding to the image of the defect area to be identified. In general, blow hole defects, spheroidization defects, inclusion defects, and non-fusion defects are the more common defects of the molten pool. Sputtering may induce porosity and spheroidization defects.
The defect example segmentation is realized through the method, and the manufacturing process parameter control system can adjust the manufacturing process parameters in a targeted manner according to the segmentation result of the defect example.
Preferably, the image processing system further comprises a molten pool size measuring module, specifically configured to:
matching the template image, establishing a measuring frame ROI, and processing and identifying picture features in the measuring frame; for a molten pool image to be measured, firstly, drawing a gray level histogram along the length direction in an ROI (region of interest) and smoothing the gray level histogram by utilizing Gaussian filtering, then judging the edge of the molten pool according to the gray level change condition on the gray level histogram and establishing a measurement edge pair, and meanwhile, calculating the size of the molten pool according to the number of pixels between adjacent edges in the edge pair.
Preferably, the image processing system further comprises a sputtering number statistics module, specifically configured to:
and generating a confidence density map required by the sputtering image to be counted by using a generating type antagonistic neural network, performing antagonistic generation network training, comparing the confidence density map with the sputtering images in the image library, and reading the sputtering number prestored in the corresponding image in the image library after comparison, namely the sputtering number of the sputtering image to be counted.
The image processing system can position and identify defects in a molten pool and a sputtering image in the metal additive manufacturing process, so that the result of segmentation and identification according to a defect example is fed back to the manufacturing process parameter control system in real time in the additive manufacturing process, the manufacturing process parameters are adjusted in real time, the yield of part manufacturing is improved, and parts which do not meet the part process quality requirements can be stopped in time to reduce the manufacturing cost. The recognition perception information of the defects can be used as environmental data for regulating and controlling the process parameters by a reinforcement learning method, so that an intelligent agent (a decision system of the process parameters) makes an optimal decision, and integrated manufacturing from perception to decision is realized.
The working system firstly receives the inspection result of the image processing system, then makes corresponding parameter adjustment according to the defect condition, and if the inspection result has problems after adjustment, continues adjustment until the inspection result is adjusted to the optimal parameter, thereby manufacturing the high-quality defect-free part.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. The utility model provides a metal vibration material disk online movement monitoring mechanism, includes moving platform and CCD camera, its characterized in that: the clamp assembly comprises a shovel-shaped clamp, a sleeve-type clamp and a grappling clamp, wherein the shovel-shaped clamp is used for clamping the CCD camera with the weight ranging from 1.5kg to 4.0kg, the sleeve-type clamp is used for clamping the CCD camera with the weight ranging from 4.0kg to 9.0kg, and the grappling clamp is used for clamping the CCD camera with the weight of more than 9 kg; the shovel-shaped clamp comprises a camera fixing plate and a moving platform fixing piece, wherein a bolt hole is formed in the camera fixing plate, the camera fixing plate is used for extending between two fixing surfaces of the CCD camera and is fixed with the two fixing surfaces through bolts, and the moving platform fixing piece is fixed on one side of the camera fixing plate; the sleeve type clamp comprises a thread fixing piece and a movable platform fixing block, wherein one end of the thread fixing piece is fixed with the movable platform fixing block, and the surface of the other end of the thread fixing piece is provided with an external thread which is used for being screwed and fixed with an internal thread on a CCD camera fixing box; the grapple type clamp comprises a grapple plate and a moving platform fixing rod, wherein a plurality of grabs are arranged at the front end of the grapple plate and used for fixing the CCD camera in a hole extending into the CCD camera fixing box, one end of the moving platform fixing rod is fixed with the plate surface of the grapple plate, and bolt holes are formed in the other end of the moving platform fixing rod.
2. The metal additive manufacturing online movement monitoring mechanism of claim 1, wherein: the mobile platform fixing part comprises two fixing blocks which are respectively positioned on the upper surface and the lower surface of the camera fixing plate and are fixed by the camera fixing plate through bolts, the two fixing blocks are provided with protruding parts protruding out of the edge of the camera fixing plate, and the protruding parts are provided with corresponding bolt holes.
3. The metal additive manufacturing online movement monitoring mechanism of claim 1, wherein: the movable platform is characterized in that a fixing hole is concavely formed in one end of the movable platform fixing block, one end of the thread fixing piece extends into the fixing hole to be fixed, a lug is convexly arranged at the other end of the movable platform fixing block towards the periphery, and bolt holes are formed in the lug.
4. The metal additive manufacturing online movement monitoring mechanism of claim 1, wherein: the terminal surface that the screw thread mounting was equipped with screwed one end is equipped with a plurality of lugs, the surface of screw thread mounting is inwards sunken to be equipped with the recess of rectangular shape.
5. The metal additive manufacturing online movement monitoring mechanism of claim 1, wherein: moving platform includes two along horizontal direction parallel arrangement's first dustproof guide rail, two all be equipped with first dustproof slider on the first dustproof guide rail, two be equipped with the dustproof guide rail of second between the first dustproof slider, be equipped with the dustproof slider of second on the dustproof guide rail of second, be equipped with the third dustproof guide rail of vertical setting on the dustproof slider of second, be equipped with the third dustproof slider on the third dustproof guide rail, be equipped with CCD camera support on the third dustproof slider, the CCD camera passes through the anchor clamps subassembly to be fixed on the CCD camera support.
6. The metal additive manufacturing online movement monitoring mechanism of claim 5, wherein: the CCD cameras are provided with a plurality of CCD cameras and are all fixed on the CCD camera bracket through the clamp assembly.
7. The metal additive manufacturing online movement monitoring mechanism of claim 5, wherein: the laser tracking instrument is fixed on the CCD camera support and used for positioning an area where laser processing is carried out on the surface of a processed workpiece and feeding back the area to the mechanism control system, and the mechanism control system is used for controlling the movement of the moving platform according to information fed back by the laser tracking instrument, so that the CCD camera tracks and shoots the processing area.
8. The utility model provides a metal additive manufacturing online appearance check out test set which characterized in that: the metal additive manufacturing online mobile monitoring mechanism comprises the metal additive manufacturing online mobile monitoring mechanism according to any one of claims 1 to 7, and further comprises an image processing system and a working system, wherein the image processing system is used for accurately positioning and identifying the defect area according to the molten pool and the sputtering image collected by the CCD camera of the online mobile monitoring mechanism, and feeding the result back to the working system, and the working system is used for adjusting the process parameters of 3D printing according to the information fed back by the image processing system.
9. The metal additive manufacturing online appearance inspection device of claim 8, wherein: the image processing system comprises an image preprocessing module, a generating type antagonistic neural network module and an LBP algorithm module, wherein the image preprocessing module is used for receiving a molten pool and a sputtering image collected by a CCD camera and carrying out preprocessing operations of graying processing and median filtering on the image, the generating type antagonistic neural network module is used for repairing defects in the preprocessed molten pool and the preprocessed sputtering image, and the LBP algorithm module is used for identifying differences between the molten pool and an original sputtering image and the repaired molten pool and the repaired sputtering image so as to realize accurate positioning and identification of a defect area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010442944.XA CN111761224B (en) | 2020-05-22 | 2020-05-22 | Metal additive manufacturing online mobile monitoring mechanism and online appearance detection equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010442944.XA CN111761224B (en) | 2020-05-22 | 2020-05-22 | Metal additive manufacturing online mobile monitoring mechanism and online appearance detection equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111761224A CN111761224A (en) | 2020-10-13 |
| CN111761224B true CN111761224B (en) | 2022-05-10 |
Family
ID=72719677
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010442944.XA Active CN111761224B (en) | 2020-05-22 | 2020-05-22 | Metal additive manufacturing online mobile monitoring mechanism and online appearance detection equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111761224B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112991304A (en) * | 2021-03-23 | 2021-06-18 | 武汉大学 | Molten pool sputtering detection method based on laser directional energy deposition monitoring system |
| CN113111870A (en) * | 2021-04-16 | 2021-07-13 | 嘉兴云切供应链管理有限公司 | 5G remote central control system and method for multiple metal processing devices |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202655967U (en) * | 2012-05-29 | 2013-01-09 | 河南航天精工制造有限公司 | Fixture for clamping external threaded shaft and sleeve workpieces |
| CN105921940A (en) * | 2016-06-07 | 2016-09-07 | 广东工业大学 | Clamping device for repair of blade top |
| CN205614168U (en) * | 2016-05-13 | 2016-10-05 | 华中科技大学 | A multifunction clamp for welding molten bath on -line monitoring platform |
| CN108067714A (en) * | 2017-11-30 | 2018-05-25 | 清华大学 | A kind of thin-walled circumferential weld termination quality on-line monitoring and defect positioning system and method |
| WO2018233193A1 (en) * | 2017-06-19 | 2018-12-27 | 广船国际有限公司 | Assembly jig |
| CN109676135A (en) * | 2018-11-28 | 2019-04-26 | 大连理工大学 | A kind of laser gain material manufacture vision grey value difference on-line monitoring and bug repairing apparatus |
| CN110053067A (en) * | 2019-06-10 | 2019-07-26 | 深圳市力众成科技有限公司 | A kind of robot fixture of automatically replaceable fixture |
| CN210360043U (en) * | 2019-08-06 | 2020-04-21 | 十堰悦通机械制造有限公司 | Railway fork bent plate combination welding frock |
| CN111151748A (en) * | 2019-12-31 | 2020-05-15 | 江苏亚威创科源激光装备有限公司 | On-line monitoring method for manufacturing ceramic-containing reinforced phase composite material by using laser additive |
-
2020
- 2020-05-22 CN CN202010442944.XA patent/CN111761224B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202655967U (en) * | 2012-05-29 | 2013-01-09 | 河南航天精工制造有限公司 | Fixture for clamping external threaded shaft and sleeve workpieces |
| CN205614168U (en) * | 2016-05-13 | 2016-10-05 | 华中科技大学 | A multifunction clamp for welding molten bath on -line monitoring platform |
| CN105921940A (en) * | 2016-06-07 | 2016-09-07 | 广东工业大学 | Clamping device for repair of blade top |
| WO2018233193A1 (en) * | 2017-06-19 | 2018-12-27 | 广船国际有限公司 | Assembly jig |
| CN108067714A (en) * | 2017-11-30 | 2018-05-25 | 清华大学 | A kind of thin-walled circumferential weld termination quality on-line monitoring and defect positioning system and method |
| CN109676135A (en) * | 2018-11-28 | 2019-04-26 | 大连理工大学 | A kind of laser gain material manufacture vision grey value difference on-line monitoring and bug repairing apparatus |
| CN110053067A (en) * | 2019-06-10 | 2019-07-26 | 深圳市力众成科技有限公司 | A kind of robot fixture of automatically replaceable fixture |
| CN210360043U (en) * | 2019-08-06 | 2020-04-21 | 十堰悦通机械制造有限公司 | Railway fork bent plate combination welding frock |
| CN111151748A (en) * | 2019-12-31 | 2020-05-15 | 江苏亚威创科源激光装备有限公司 | On-line monitoring method for manufacturing ceramic-containing reinforced phase composite material by using laser additive |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111761224A (en) | 2020-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111951237B (en) | Visual appearance detection method | |
| CN111300144B (en) | Automatic detection method for tool wear state based on image processing | |
| CN108332689B (en) | Optical measurement system and method for detecting surface roughness and surface damage | |
| CN111761224B (en) | Metal additive manufacturing online mobile monitoring mechanism and online appearance detection equipment | |
| CN109543587B (en) | Method and system for detecting flow velocity of high-temperature molten fluid | |
| CN108760747A (en) | A kind of 3D printing model surface defect visible detection method | |
| CN110211101A (en) | A kind of rail surface defect rapid detection system and method | |
| CN111815555A (en) | Metal additive manufacturing image detection method and device combining anti-neural network with local binary | |
| CN115760654B (en) | Industrial microscope image processing system | |
| CN110216080A (en) | A kind of Quality Monitoring Control System of the PCB processing producing line based on image comparison | |
| CN102455171B (en) | Method for detecting geometric shape of back of tailor-welding weld and implementing device thereof | |
| CN102538672A (en) | CMOS (complementary metal-oxide-semiconductor)-machine-vision-based component size measuring system and measurement test method | |
| CN108896577A (en) | A kind of automatic testing method of brake block profile defects | |
| CN107688028B (en) | Laser additive manufacturing lap joint rate online monitoring method | |
| CN111612737A (en) | Artificial board surface flaw detection device and detection method | |
| CN113177924A (en) | Industrial production line product flaw detection method | |
| CN112858351A (en) | X-ray nondestructive inspection method based on machine vision | |
| CN112763349A (en) | Method for monitoring impact damage of composite material structure | |
| CN110728269B (en) | High-speed rail contact net support pole number plate identification method based on C2 detection data | |
| CN113935971A (en) | Method and device for detecting surface defects of composite material | |
| CN106645170B (en) | A kind of step electrode automaticly inspects machine | |
| CN113610054A (en) | Underwater structure disease depth detection method, system and device and storage medium | |
| CN116060317A (en) | Weld pool defect detection and position measurement mechanism and detection method thereof | |
| CN112858341B (en) | Detection method, shooting system and detection system | |
| Lei et al. | Automated vision inspection system for the size measurement of workpieces |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |