DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of the Claims
Claims 21, 25-26, and 31 are amended. Claims 22-24, 27-30, and 32-40 are as previously presented. Therefore, claims 21-40 are currently pending and have been considered below.
Response to Amendment
The amendment filed on November 17, 2025 has been entered.
Response to Arguments
Applicant’s arguments, see Pages 8-13, filed 11/17/2025, with respect to the rejection(s) of claim(s) 21-40 under U.S.C. 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of applicant’s amendment regarding the mapping of a defect using a fingerprint and newly found prior art regarding this feature.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 21, 23, 25-31, 33, and 35-40 is/are rejected under 35 U.S.C. 103 as being unpatentable over Stecker et al. (WO 2019074827 A1, hereinafter Stecker) in view of Wada et al. (JP 2016221538 A, hereinafter Wada) and Alam et al. (US 10067065 B1, hereinafter Alam) and Mehr et al. (WO 2018217903 A1, hereinafter Mehr).
Regarding claim 21, discloses an additive manufacturing system (Title, “ELECTRON BEAM ADDITIVE MANUFACTURING SYSTEM”) comprising:
an imaging device including a sensor (Para. 0063, “The detector may include one or more sensors or other devices (e.g., one that derives its measurements optically, mechanically, by infrared imagery, by some other radiation detection, or otherwise).”) and a shutter (Para. 0064, “A preferred detector may employ suitable hardware adapted for machine vision applications, and thus may include one or more housing…The housing may contain a suitable substrate that includes an array of pixels, and optionally one or more lenses and/or shutters”),
the shutter triggered to expose the sensor to light to generate a time exposure image during a build of an object (Para. 0066, “a shutter and/or an electronic shutter (e.g. a shutter that controls exposure time electronically (i.e., allows the camera to collect light for a finite amount of time) without any mechanical or moving parts) that may be used for high speed applications with an exposure time of about 5 to about 1000 μs (e.g., about 10 μs).”, where the shutter for the camera allows for time exposure images to be generated),
the shutter located on an exterior side of the imaging device between the imaging device and the object (Para. 0078, “a solid physical barrier (e.g., a shutter”, where that barrier or shutter can be located on the exterior of the imaging device, Para. 0079, “The barrier with an aperture may be located juxtaposed the second opening of the housing.”, where the shutter is within an opening of the housing and not within the interior of the housing that holds the imaging device).
Stecker does not disclose:
a focused energy source having an operating characteristic, the operating characteristic of the focused energy source to trigger actuation of the shutter; and
a housing defining a viewport, the imaging device positioned adjacent to the viewport from an exterior side of the housing;
the time exposure image is to include a defect in the additive manufacturing system, wherein a machine learning model identifies the defect in the time exposure image by processing the time exposure image to extract a feature of the time exposure image, and wherein the extracted feature corresponds to a fingerprint indicative of an operation of the additive manufacturing system and the machine learning model identifies the defect using a mapping between the fingerprint and the defect;
and the focused energy source is to be adjusted based on the defect identified in the operation of the additive manufacturing system and included in the time exposure image and image data collected of the build.
However, Wada discloses, in the similar field of imaging devices (Abstract, “an imaging device”), where a focused energy source is able to trigger actuation of a shutter within an additive manufacturing system (Page 9, Para. 3, “even when the laser light 22a and the plasma light 22b having a sufficiently large light intensity are generated around the workpiece 50, the shutter 38 is moved during the non-irradiation time of the laser light 22a. Open. Further, the camera 30 synchronizes the opening / closing of the shutter 38 and the light irradiation timing of the light source 31 (that is, the on / off of the light source 31).”, where the shutter is triggered to open during non-irradiation times, where the ending of the focused energy source causes the shutter to open), and where a time exposure image can be generated (). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the shutter in modified Stecker to include this feature as taught by Wada.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to improve the image clarity by reducing the intensity of the light of the apparatus being processed, as stated by Wada, Page 9, Para. 3 from end, “Further, the camera 30 synchronizes the opening / closing of the shutter 38 and the light irradiation timing of the light source 31 (that is, the on / off of the light source 31). Therefore, the periphery of the workpiece 50 can be suitably imaged during a time when the presence of the laser light 22a and the plasma light 22b is small (non-irradiation time).”.
Further, Alam discloses, in the similar field of imaging devices (Abstract, “an imaging device”), where a housing includes a viewport, and where the imaging device is located adjacent to the viewport from an exterior side of the housing (Section 4, lines 29-31, “The imaging device 160 may be coupled to the interior of the enclosure 120, or may be coupled to the exterior of the enclosure 120 with the lens positioned in an aperture of the enclosure 120.”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the imaging device in modified Stecker to be located outside of the housing as taught by Alam.
Regarding the positioning of the imaging device, it is the Examiner's position that one of ordinary skill in the art would have found it obvious to try as Alam discloses that the camera or imaging device can be placed either within the housing or outside the housing with an aperture to allow for viewing. Thus, it is the Examiner’s position that either position offers advantages and disadvantages that a user would contemplate merely through design choices.
Additionally, Mehr discloses, in the similar field of additive manufacturing (Abstract, “machine learning-based methods and systems for automated object defect classification and adaptive, real-time control of additive manufacturing and/or welding processes.”),
where an image can include a defect in the additive manufacturing system (Para. 0007, “a classification of detected object defects using a machine learning algorithm that has been trained using the training data set of step (a)”, where training data sets can include process characterization data that comes from image sensors, Para. 0113, “process characterization data from past fabrication runs is used as part of a training data set used to "teach" the machine learning algorithm used to run the process control. In some embodiments, real-time (or "in-process") process characterization data is fed to the machine learning algorithm so that it may adaptively adjust one or more process control parameters in real-time.”, and Para. 0114, “Any of a variety of process monitoring tools known to those of skill in the art may be used including, but not limited to…image sensors and machine vision systems”),
where a machine learning model identifies the defect in the image by processing the image to extract a feature that corresponds to a fingerprint indicative of an operation in the additive manufacturing system (Para. 0123, “FIGS. 7 A-C illustrate in-process feature extraction from images of a laser-metal wire deposition process obtained using a machine vision system…FIG. 7C shows the processed image after application of a feature extraction algorithm used to identify, for example, the angel of the wire relative to the build plate and the height (thickness) of the new layer.”, where images can have features extracted, where those features correspond to a fingerprint indicative of operations in the additive manufacturing system, Para. 0182, “In some embodiments, automated feature extraction allows one to correlate part features with build-time actions. During the build (e.g., when printing), in addition to building a machine learning model that correlates process control parameters (e.g., laser power, feed rate, travel speed, etc.) and result of the deposition process (e.g., the shape of melt pool, defects in the melt pool, etc.), one may also create a mapping between the process control parameters and a specific location in the part.”, where the features extracted are correlated to build-time actions that include process control parameters, where the list of process control parameters that create the feature is construed as a “fingerprint”),
where the machine learning model identifies the defect using a mapping between the fingerprint and defect (Para. 0128, “One or more training data sets may be used to train the machine learning algorithm used for object defect detection and classification.”, and Para. 0129, “the training data set may comprise all of these types of data, i.e., process simulation data, process characterization data, in-process inspection data, and post-build inspection data.”, where the training set would include fingerprints for each image regarding the process control parameters and then have a defect or no defect mapping, where the machine learning system would use that training data set in order to learn which process parameters product defects), and
where energy in the system can be adjusted based on the defected identified in the operation of the additive manufacturing system (Para. 0135, “wherein real-time process characterization data is provided by one or more sensors as input to the machine learning algorithm to adjust one or more process control parameters in real-time.”, and where process control parameters can include focused energy source adjustments through adjusting the intensity of the heat flux, Para. 0004, “In some embodiments, the one or more process control parameters to be predicted or controlled comprise an intensity of heat flux into a material during deposition, a size and shape of a heat flux surface, a flow rate and angle of shielding gas flow, a temperature of a baseplate, an ambient temperature control during a deposition process, a temperature of a deposition material prior to deposition, a current or voltage setting in a resistive heating apparatus, a voltage frequency or amplitude in an inductive heating apparatus, a choice of deposition material, a ratio by volume or a ratio by weight of deposition materials if more than one deposition material is used, or any combination thereof.”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the time exposure images in modified Stecker to undergo machine learning defect analysis using fingerprints so that repairs can be made as taught by Mehr.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to use machine learning to classify defects so that they can be mapped to process control parameters, which can then be adjusted in real-time in order to prevent predicted defects, which can help prevent defected objects from being produced, as stated by Mehr, Para. 0007, “c) providing a processor programmed to provide a classification of detected object defects using a machine learning algorithm that has been trained using the training data set of step (a), wherein the real-time data from the one or more sensors is provided as input to the machine learning algorithm and allows the classification of detected object defects to be adjusted in real-time.”.
Regarding claim 23, modified Stecker teaches the apparatus according to claim 21, as set forth above.
Modified Stecker does not disclose:
wherein the operating characteristic includes an amount of light contacting a melt pool of the object for build during operation of the focused energy source.
However, Wada discloses where the laser beam is capable of generating a melt pool with light irradiation coming off of the melt pool (Page 3, Para. 5 from end, “the laser beam 22a is irradiated from the nozzle 21 to the base material 26, and the metal powder 23a and the shield gas 24a are injected. Around the position where the laser beam 22a is irradiated on the base material 26, a melting basin 27 is formed. The melting pond 27 is formed by melting the base material 26”), where the operating characteristic depends upon this melt pool irradiation (Page 9, Para. 3, “even when the laser light 22a and the plasma light 22b having a sufficiently large light intensity are generated around the workpiece 50, the shutter 38 is moved during the non-irradiation time of the laser light 22a. Open. Further, the camera 30 synchronizes the opening / closing of the shutter 38 and the light irradiation timing of the light source 31 (that is, the on / off of the light source 31).”, where the shutter is triggered to open during non-irradiation times, where the ending of the focused energy source causes the shutter to open). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the operating characteristic in modified Stecker to include the feature as taught by Wada.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to improve the image clarity by reducing the intensity of the light of the apparatus being processed, as stated by Wada, Page 9, Para. 3 from end, “Further, the camera 30 synchronizes the opening / closing of the shutter 38 and the light irradiation timing of the light source 31 (that is, the on / off of the light source 31). Therefore, the periphery of the workpiece 50 can be suitably imaged during a time when the presence of the laser light 22a and the plasma light 22b is small (non-irradiation time).”.
Regarding claim 25, modified Stecker teaches the apparatus according to claim 21, as set forth above, discloses wherein, based on the operating characteristic, the shutter moves to an open position; (Teaching from Wada, Page 9, Para. 3, “even when the laser light 22a and the plasma light 22b having a sufficiently large light intensity are generated around the workpiece 50, the shutter 38 is moved during the non-irradiation time of the laser light 22a. Open. Further, the camera 30 synchronizes the opening / closing of the shutter 38 and the light irradiation timing of the light source 31 (that is, the on / off of the light source 31).”, where the shutter is synced to open when the light source is off)
and, after a predetermined amount of time, the shutter moves to a closed position (Stecker, Para. 0066, “a shutter and/or an electronic shutter (e.g. a shutter that controls exposure time electronically (i.e., allows the camera to collect light for a finite amount of time) without any mechanical or moving parts) that may be used for high speed applications with an exposure time of about 5 to about 1000 μs (e.g., about 10 μs).”, where after the exposure time has passed, the shutter would be closed).
Regarding claim 26, modified Stecker teaches the apparatus according to claim 25, as set forth above.
Modified Stecker does not disclose:
wherein, the fingerprint is indicative of a shape of a melt pool, wherein the shape of the melt pool correlates to the defect.
However, Mehr discloses where the training data can include melt pool shape that depends upon process control parameters (Para. 0137, “the training data set may comprise all of these types of data, i.e., process simulation data, process characterization data, in-process inspection data, and post-build inspection data.”, and Para. 0138, “Process characterization data…In some embodiments, for example, laser interferometers are used to monitor the dimensions of the melt pool (in the case of laser-metal wire deposition) or other part dimensions as the part is being fabricated.”, and Para. 0059, “Laser beam size and shape: control the size and the shape of the melt pool (together with the laser power and the traverse speed).”, where defects can be determined from training data that can include melt pool shape, Para. 0128, “One or more training data sets may be used to train the machine learning algorithm used for object defect detection and classification.”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the training data in modified Stecker to include melt pool shape as taught by Mehr.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to use machine learning to classify defects so that they can be mapped to process control parameters, which can then be adjusted in real-time in order to prevent predicted defects, which can help prevent defected objects from being produced, as stated by Mehr, Para. 0007, “c) providing a processor programmed to provide a classification of detected object defects using a machine learning algorithm that has been trained using the training data set of step (a), wherein the real-time data from the one or more sensors is provided as input to the machine learning algorithm and allows the classification of detected object defects to be adjusted in real-time.”.
Regarding claim 27, modified Stecker teaches the apparatus according to claim 21, as set forth above, discloses wherein, based on the operating characteristic, the shutter moves to a closed position (Teaching from Wada, Page 9, Para. 3, “even when the laser light 22a and the plasma light 22b having a sufficiently large light intensity are generated around the workpiece 50, the shutter 38 is moved during the non-irradiation time of the laser light 22a. Open. Further, the camera 30 synchronizes the opening / closing of the shutter 38 and the light irradiation timing of the light source 31 (that is, the on / off of the light source 31).”, where the shutter is synced to close when the light source opens).
Regarding claim 28, modified Stecker teaches the apparatus according to claim 27, as set forth above.
Modified Stecker does not disclose:
wherein, after a predetermined amount of time, the shutter moves to an open position.
However, Wada discloses where the shutter operation can be synchronized with the laser beam operation (Page 7, Para. 5, “The CPU 35 of the camera 30 uses the synchronization signal of the laser beam 22a acquired from the processor 25 of the metal working machine 20 to synchronize the non-irradiation period of the laser beam 22a with the opening / closing timing of the shutter 38”), where there can also be an extension of time depending upon the controller (Page 7, Para. 4 from end, “The CPU 35 may shorten the exposure time by shortening the time during which the shutter 38 is closed. The shorter the exposure time, the longer the time that the image sensor 36 is shielded, the less the amount of light taken in, and the darker the captured image.”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the control over the shutter in modified Stecker to include a predetermined time as taught by Wada.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to have that predetermined time be dependent upon the laser signal to improve image quality or if there is a desire to image high-intensity particles, as stated by Wada, Page 7, Para. 4, “Thereby, since possibility that the laser beam 22a and the plasma beam 22b will reach the image sensor 36 can be reduced, the image quality can be improved.”, and Page 7, Para. 4 from end, “The CPU 35 may shorten the exposure time by shortening the time during which the shutter 38 is closed. The shorter the exposure time, the longer the time that the image sensor 36 is shielded, the less the amount of light taken in, and the darker the captured image. Therefore, although it is highly possible that the camera 30 can image high-intensity particles that are the high-temperature metal powder 23a”.
Regarding claim 29, modified Stecker teaches the apparatus according to claim 21, as set forth above, discloses wherein actuation of the shutter between an open position and a closed position generates a sequence of exposures (Stecker, Para. 0065, “The detector may be configured so that it operates at an image acquisition rate or frame rate that ranges from about on the order of at least about 25 frames per second, e.g., about 30 frames per second (fps) or higher. The detector may operate at least at about 40 fps, at least at about 50 fps, or even at about 60 fps, or more.”, and Para. 0066, “high speed applications with an exposure time of about 5 to about 1000 μs (e.g., about 10 μs).”).
Modified Stecker does not disclose:
the sequence of exposures corresponding to a plurality of images combined to generate the time exposure image of the object for build.
However, Wada discloses where a time exposure image can be a composite image of two different time exposure images (Page 7, Para. 2 from end, “movement of the metal powder 23a is reflected in the picked-up image P11 picked up with a long exposure time. In addition, the movement trajectory Q12 of the metal powder 23a is reflected in the captured image P12 captured with the exposure time shortened. The second image processor 41 synthesizes the captured image P11 and the captured image P12 to obtain a composite image P13.”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the time exposure image in modified Stecker to be a composite image of multiple time exposures as taught by Wada.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to track the movement and temperature of the metal powder within the housing, as stated by Wada, Page 7, last Para., “The composite image P13 can be displayed on the monitor 42. In FIG. 7A, since the trajectory Q12 is reflected in the captured image P12 having a short exposure time, the user 70 confirming the monitor 42 can estimate that the captured metal powder 23a is at a high temperature. Moreover, this user 70 can estimate that the speed of the imaged metal powder 23a is high.”.
Regarding claim 30, modified Stecker teaches the apparatus according to claim 29, as set forth above, discloses wherein the generation of the time exposure image of the object for build is based on a sum of a first amount of time and a second amount of time, the first amount of time corresponding to a length of time in which the shutter moves from the open position to the closed position, and the second amount of time corresponding to a length of time in which the shutter moves from the closed position to the open position (Teaching from Wada, Page 7, Para. 2 from end, “movement of the metal powder 23a is reflected in the picked-up image P11 picked up with a long exposure time. In addition, the movement trajectory Q12 of the metal powder 23a is reflected in the captured image P12 captured with the exposure time shortened. The second image processor 41 synthesizes the captured image P11 and the captured image P12 to obtain a composite image P13.”, where the captured image P11 and P12 are both exposures that have a set amount of time in which the shutter is open for exposure, where the composite image P13 would then be a sum of the time that the shutter is open for both P11 and P12).
Regarding claim 31, Stecker discloses an apparatus (Title, “ELECTRON BEAM ADDITIVE MANUFACTURING SYSTEM”) comprising:
an imaging device including a sensor (Para. 0063, “The detector may include one or more sensors or other devices (e.g., one that derives its measurements optically, mechanically, by infrared imagery, by some other radiation detection, or otherwise).”) and a shutter (Para. 0064, “A preferred detector may employ suitable hardware adapted for machine vision applications, and thus may include one or more housing…The housing may contain a suitable substrate that includes an array of pixels, and optionally one or more lenses and/or shutters”),
the shutter triggered to expose the sensor to light to generate a time exposure image during a build of an object (Para. 0066, “a shutter and/or an electronic shutter (e.g. a shutter that controls exposure time electronically (i.e., allows the camera to collect light for a finite amount of time) without any mechanical or moving parts) that may be used for high speed applications with an exposure time of about 5 to about 1000 μs (e.g., about 10 μs).”),
the shutter located on an exterior side of the imaging device between the imaging device and the object (Para. 0078, “a solid physical barrier (e.g., a shutter”, where that barrier or shutter can be located on the exterior of the imaging device, Para. 0079, “The barrier with an aperture may be located juxtaposed the second opening of the housing.”, where the shutter is within an opening of the housing and not within the interior of the housing that holds the imaging device).
Stecker does not disclose:
a focused energy source having an operating characteristic, the operating characteristic of the focused energy source to trigger actuation of the shutter; and
a housing defining a viewport, the imaging device positioned adjacent to the viewport from an exterior side of the housing;
the time exposure image is to include a defect in the build of the object, the defect identified in the time exposure image using a machine learning model, wherein the machine learning model identifies the defect in the time exposure image by processing the time exposure image to extract a feature of the time exposure image, and wherein the extracted feature corresponds to a fingerprint indicative of an operation of the apparatus and the machine learning model identifies the defect using a mapping between the fingerprint and the defect;
and the focused energy source is to be adjusted based on the defect identified in the operation of the apparatus and included in the time exposure image and image data collected of the build.
However, Wada discloses, in the similar field of imaging devices (Abstract, “an imaging device”), where a focused energy source is able to trigger actuation of a shutter within an additive manufacturing system (Page 9, Para. 3, “even when the laser light 22a and the plasma light 22b having a sufficiently large light intensity are generated around the workpiece 50, the shutter 38 is moved during the non-irradiation time of the laser light 22a. Open. Further, the camera 30 synchronizes the opening / closing of the shutter 38 and the light irradiation timing of the light source 31 (that is, the on / off of the light source 31).”, where the shutter is triggered to open during non-irradiation times, where the ending of the focused energy source causes the shutter to open). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the shutter in modified Stecker to include this feature as taught by Wada.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to improve the image clarity by reducing the intensity of the light of the apparatus being processed, as stated by Wada, Page 9, Para. 3 from end, “Further, the camera 30 synchronizes the opening / closing of the shutter 38 and the light irradiation timing of the light source 31 (that is, the on / off of the light source 31). Therefore, the periphery of the workpiece 50 can be suitably imaged during a time when the presence of the laser light 22a and the plasma light 22b is small (non-irradiation time).”.
Further, Alam discloses, in the similar field of imaging devices (Abstract, “an imaging device”), where a housing includes a viewport, and where the imaging device is located adjacent to the viewport from an exterior side of the housing (Section 4, lines 29-31, “The imaging device 160 may be coupled to the interior of the enclosure 120, or may be coupled to the exterior of the enclosure 120 with the lens positioned in an aperture of the enclosure 120.”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the imaging device in modified Stecker to be located outside of the housing as taught by Alam.
Regarding the positioning of the imaging device, it is the Examiner's position that one of ordinary skill in the art would have found it obvious to try as Alam discloses that the camera or imaging device can be placed either within the housing or outside the housing with an aperture to allow for viewing. Thus, it is the Examiner’s position that either position offers advantages and disadvantages that a user would contemplate merely through design choices.
Additionally, Mehr discloses, in the similar field of additive manufacturing (Abstract, “machine learning-based methods and systems for automated object defect classification and adaptive, real-time control of additive manufacturing and/or welding processes.”),
where an image can include a defect in the additive manufacturing system (Para. 0007, “a classification of detected object defects using a machine learning algorithm that has been trained using the training data set of step (a)”, where training data sets can include process characterization data that comes from image sensors, Para. 0113, “process characterization data from past fabrication runs is used as part of a training data set used to "teach" the machine learning algorithm used to run the process control. In some embodiments, real-time (or "in-process") process characterization data is fed to the machine learning algorithm so that it may adaptively adjust one or more process control parameters in real-time.”, and Para. 0114, “Any of a variety of process monitoring tools known to those of skill in the art may be used including, but not limited to…image sensors and machine vision systems”),
where a machine learning model identifies the defect in the image by processing the image to extract a feature that corresponds to a fingerprint indicative of an operation in the additive manufacturing system (Para. 0123, “FIGS. 7 A-C illustrate in-process feature extraction from images of a laser-metal wire deposition process obtained using a machine vision system…FIG. 7C shows the processed image after application of a feature extraction algorithm used to identify, for example, the angel of the wire relative to the build plate and the height (thickness) of the new layer.”, where images can have features extracted, where those features correspond to a fingerprint indicative of operations in the additive manufacturing system, Para. 0182, “In some embodiments, automated feature extraction allows one to correlate part features with build-time actions. During the build (e.g., when printing), in addition to building a machine learning model that correlates process control parameters (e.g., laser power, feed rate, travel speed, etc.) and result of the deposition process (e.g., the shape of melt pool, defects in the melt pool, etc.), one may also create a mapping between the process control parameters and a specific location in the part.”, where the features extracted are correlated to build-time actions that include process control parameters, where the list of process control parameters that create the feature is construed as a “fingerprint”),
where the machine learning model identifies the defect using a mapping between the fingerprint and defect (Para. 0128, “One or more training data sets may be used to train the machine learning algorithm used for object defect detection and classification.”, and Para. 0129, “the training data set may comprise all of these types of data, i.e., process simulation data, process characterization data, in-process inspection data, and post-build inspection data.”, where the training set would include fingerprints for each image regarding the process control parameters and then have a defect or no defect mapping, where the machine learning system would use that training data set in order to learn which process parameters product defects), and
where energy in the system can be adjusted based on the defected identified in the operation of the additive manufacturing system (Para. 0135, “wherein real-time process characterization data is provided by one or more sensors as input to the machine learning algorithm to adjust one or more process control parameters in real-time.”, and where process control parameters can include focused energy source adjustments through adjusting the intensity of the heat flux, Para. 0004, “In some embodiments, the one or more process control parameters to be predicted or controlled comprise an intensity of heat flux into a material during deposition, a size and shape of a heat flux surface, a flow rate and angle of shielding gas flow, a temperature of a baseplate, an ambient temperature control during a deposition process, a temperature of a deposition material prior to deposition, a current or voltage setting in a resistive heating apparatus, a voltage frequency or amplitude in an inductive heating apparatus, a choice of deposition material, a ratio by volume or a ratio by weight of deposition materials if more than one deposition material is used, or any combination thereof.”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the time exposure images in modified Stecker to undergo machine learning defect analysis using fingerprints so that repairs can be made as taught by Mehr.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to use machine learning to classify defects so that they can be mapped to process control parameters, which can then be adjusted in real-time in order to prevent predicted defects, which can help prevent defected objects from being produced, as stated by Mehr, Para. 0007, “c) providing a processor programmed to provide a classification of detected object defects using a machine learning algorithm that has been trained using the training data set of step (a), wherein the real-time data from the one or more sensors is provided as input to the machine learning algorithm and allows the classification of detected object defects to be adjusted in real-time.”.
Regarding claim 33, modified Stecker teaches the apparatus according to claim 31, as set forth above.
Modified Stecker does not disclose:
wherein the operating characteristic includes an amount of light contacting a melt pool of the object for build during operation of the focused energy source.
However, Wada discloses where the laser beam is capable of generating a melt pool with light irradiation coming off of the melt pool (Page 3, Para. 5 from end, “the laser beam 22a is irradiated from the nozzle 21 to the base material 26, and the metal powder 23a and the shield gas 24a are injected. Around the position where the laser beam 22a is irradiated on the base material 26, a melting basin 27 is formed. The melting pond 27 is formed by melting the base material 26”), where the operating characteristic depends upon this melt pool irradiation (Page 9, Para. 3, “even when the laser light 22a and the plasma light 22b having a sufficiently large light intensity are generated around the workpiece 50, the shutter 38 is moved during the non-irradiation time of the laser light 22a. Open. Further, the camera 30 synchronizes the opening / closing of the shutter 38 and the light irradiation timing of the light source 31 (that is, the on / off of the light source 31).”, where the shutter is triggered to open during non-irradiation times, where the ending of the focused energy source causes the shutter to open). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the operating characteristic in modified Stecker to include the feature as taught by Wada.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to improve the image clarity by reducing the intensity of the light of the apparatus being processed, as stated by Wada, Page 9, Para. 3 from end, “Further, the camera 30 synchronizes the opening / closing of the shutter 38 and the light irradiation timing of the light source 31 (that is, the on / off of the light source 31). Therefore, the periphery of the workpiece 50 can be suitably imaged during a time when the presence of the laser light 22a and the plasma light 22b is small (non-irradiation time).”.
Regarding claim 35, modified Stecker teaches the apparatus according to claim 31, as set forth above, discloses wherein, based on the operating characteristic, the shutter moves to an open position (Teaching from Wada, Page 9, Para. 3, “even when the laser light 22a and the plasma light 22b having a sufficiently large light intensity are generated around the workpiece 50, the shutter 38 is moved during the non-irradiation time of the laser light 22a. Open. Further, the camera 30 synchronizes the opening / closing of the shutter 38 and the light irradiation timing of the light source 31 (that is, the on / off of the light source 31).”, where the shutter is synced to open when the light source is off).
Regarding claim 36, modified Stecker teaches the apparatus according to claim 35, as set forth above, discloses wherein, after a predetermined amount of time, the shutter moves to a closed position (Stecker, Para. 0066, “a shutter and/or an electronic shutter (e.g. a shutter that controls exposure time electronically (i.e., allows the camera to collect light for a finite amount of time) without any mechanical or moving parts) that may be used for high speed applications with an exposure time of about 5 to about 1000 μs (e.g., about 10 μs).”, where after the exposure time has passed, the shutter would be closed).
Regarding claim 37, modified Stecker teaches the apparatus according to claim 31, as set forth above, discloses wherein, based on the operating characteristic, the shutter moves to a closed position (Teaching from Wada, Page 9, Para. 3, “even when the laser light 22a and the plasma light 22b having a sufficiently large light intensity are generated around the workpiece 50, the shutter 38 is moved during the non-irradiation time of the laser light 22a. Open. Further, the camera 30 synchronizes the opening / closing of the shutter 38 and the light irradiation timing of the light source 31 (that is, the on / off of the light source 31).”, where the shutter is synced to close when the light source opens).
Regarding claim 38, modified Stecker teaches the apparatus according to claim 37, as set forth above.
Modified Stecker does not disclose:
wherein, after a predetermined amount of time, the shutter moves to an open position.
However, Wada discloses where the shutter operation can be synchronized with the laser beam operation (Page 7, Para. 5, “The CPU 35 of the camera 30 uses the synchronization signal of the laser beam 22a acquired from the processor 25 of the metal working machine 20 to synchronize the non-irradiation period of the laser beam 22a with the opening / closing timing of the shutter 38”), where there can also be an extension of time depending upon the controller (Page 7, Para. 4 from end, “The CPU 35 may shorten the exposure time by shortening the time during which the shutter 38 is closed. The shorter the exposure time, the longer the time that the image sensor 36 is shielded, the less the amount of light taken in, and the darker the captured image.”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the control over the shutter in modified Stecker to include a predetermined time as taught by Wada.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to have that predetermined time be dependent upon the laser signal to improve image quality or if there is a desire to image high-intensity particles, as stated by Wada, Page 7, Para. 4, “Thereby, since possibility that the laser beam 22a and the plasma beam 22b will reach the image sensor 36 can be reduced, the image quality can be improved.”, and Page 7, Para. 4 from end, “The CPU 35 may shorten the exposure time by shortening the time during which the shutter 38 is closed. The shorter the exposure time, the longer the time that the image sensor 36 is shielded, the less the amount of light taken in, and the darker the captured image. Therefore, although it is highly possible that the camera 30 can image high-intensity particles that are the high-temperature metal powder 23a”.
Regarding claim 39, modified Stecker teaches the apparatus according to claim 31, as set forth above, discloses wherein actuation of the shutter between an open position and a closed position generates a sequence of exposures (Stecker, Para. 0065, “The detector may be configured so that it operates at an image acquisition rate or frame rate that ranges from about on the order of at least about 25 frames per second, e.g., about 30 frames per second (fps) or higher. The detector may operate at least at about 40 fps, at least at about 50 fps, or even at about 60 fps, or more.”, and Para. 0066, “high speed applications with an exposure time of about 5 to about 1000 μs (e.g., about 10 μs).”).
Modified Stecker does not disclose:
the sequence of exposures corresponding to a plurality of images combined to generate the time exposure image of the object for build.
However, Wada discloses where a time exposure image can be a composite image of two different time exposure images (Page 7, Para. 2 from end, “movement of the metal powder 23a is reflected in the picked-up image P11 picked up with a long exposure time. In addition, the movement trajectory Q12 of the metal powder 23a is reflected in the captured image P12 captured with the exposure time shortened. The second image processor 41 synthesizes the captured image P11 and the captured image P12 to obtain a composite image P13.”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the time exposure image in modified Stecker to be a composite image of multiple time exposures as taught by Wada.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to track the movement and temperature of the metal powder within the housing, as stated by Wada, Page 7, last Para., “The composite image P13 can be displayed on the monitor 42. In FIG. 7A, since the trajectory Q12 is reflected in the captured image P12 having a short exposure time, the user 70 confirming the monitor 42 can estimate that the captured metal powder 23a is at a high temperature. Moreover, this user 70 can estimate that the speed of the imaged metal powder 23a is high.”.
Regarding claim 40, modified Stecker teaches the apparatus according to claim 39, as set forth above, discloses wherein the generation of the time exposure image of the object for build is based on a sum of a first amount of time and a second amount of time, the first amount of time corresponding to a length of time in which the shutter moves from the open position to the closed position, and the second amount of time corresponding to a length of time in which the shutter moves from the closed position to the open position (Teaching from Wada, Page 7, Para. 2 from end, “movement of the metal powder 23a is reflected in the picked-up image P11 picked up with a long exposure time. In addition, the movement trajectory Q12 of the metal powder 23a is reflected in the captured image P12 captured with the exposure time shortened. The second image processor 41 synthesizes the captured image P11 and the captured image P12 to obtain a composite image P13.”, where the captured image P11 and P12 are both exposures that have a set amount of time in which the shutter is open for exposure, where the composite image P13 would then be a sum of the time that the shutter is open for both P11 and P12).
Claims 22 and 32 is/are rejected under 35 U.S.C. 103 as being unpatentable over Stecker et al. (WO 2019074827 A1, hereinafter Stecker) in view of Wada et al. (JP 2016221538 A, hereinafter Wada) and Alam et al. (US 10067065 B1, hereinafter Alam) and Mehr et al. (WO 2018217903 A1, hereinafter Mehr) in further view of Shi et al. (CN 110355465 A1, hereinafter Shi).
Regarding claim 22, modified Stecker teaches the apparatus according to claim 21, as set forth above.
Modified Stecker does not disclose:
wherein the time exposure image includes a first image and a second image, and a combination of the first image and the second image forms the time exposure image by reducing light exposure from a portion of the object for build included in the time exposure image.
However, Wada discloses where a time exposure image can be a composite image of two different time exposure images (Page 7, Para. 2 from end, “movement of the metal powder 23a is reflected in the picked-up image P11 picked up with a long exposure time. In addition, the movement trajectory Q12 of the metal powder 23a is reflected in the captured image P12 captured with the exposure time shortened. The second image processor 41 synthesizes the captured image P11 and the captured image P12 to obtain a composite image P13.”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the time exposure image in modified Stecker to be a composite image of multiple time exposures as taught by Wada.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to track the movement and temperature of the metal powder within the housing, as stated by Wada, Page 7, last Para., “The composite image P13 can be displayed on the monitor 42. In FIG. 7A, since the trajectory Q12 is reflected in the captured image P12 having a short exposure time, the user 70 confirming the monitor 42 can estimate that the captured metal powder 23a is at a high temperature. Moreover, this user 70 can estimate that the speed of the imaged metal powder 23a is high.”.
Further, Shi discloses, in the similar field of imaging devices (Abstract, “laser welding head or welding gun, an industrial camera”), where a composite image can be formed from multiple images that all have different exposure times, where that would reduce the amount of light exposure in each image (Page 6, Para. 2 from end, “a camera shooting a frame of image is 25ms; and T1h, T2h, T3h, T4h is a high-level section of four different time length, which are 18ms, 3ms, 12ms, 6ms, corresponding to four types of different exposure times, obtaining one image of four different exposure times within the time period T of the back on the industrial control machine using image fusion algorithm to synthesize a high dynamic image”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the multiple exposures in modified Stecker to be of different exposure times as taught by Shi.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to capture different areas of the weld clearly through different exposure times, as stated by Shi, Page 6, last Para., “Because the dynamic range of plasma, molten, bead and matrix are too large, clear image cannot use the same exposure parameters to at the same time, collects the plasma, molten, bead and a matrix, can control the camera exposure amount so as to respectively clear shooting image of molten pool part and a lock hole part ratio change the exposure time by adjusting the duty of the rectangular wave.”.
Regarding claim 32, modified Stecker teaches the apparatus according to claim 31, as set forth above.
Modified Stecker does not disclose:
wherein the time exposure image includes a first image and a second image, and a combination of the first image and the second image forms the time exposure image by reducing light exposure from a portion of the object for build included in the time exposure image.
However, Wada discloses where a time exposure image can be a composite image of two different time exposure images (Page 7, Para. 2 from end, “movement of the metal powder 23a is reflected in the picked-up image P11 picked up with a long exposure time. In addition, the movement trajectory Q12 of the metal powder 23a is reflected in the captured image P12 captured with the exposure time shortened. The second image processor 41 synthesizes the captured image P11 and the captured image P12 to obtain a composite image P13.”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the time exposure image in modified Stecker to be a composite image of multiple time exposures as taught by Wada.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to track the movement and temperature of the metal powder within the housing, as stated by Wada, Page 7, last Para., “The composite image P13 can be displayed on the monitor 42. In FIG. 7A, since the trajectory Q12 is reflected in the captured image P12 having a short exposure time, the user 70 confirming the monitor 42 can estimate that the captured metal powder 23a is at a high temperature. Moreover, this user 70 can estimate that the speed of the imaged metal powder 23a is high.”.
Further, Shi discloses, in the similar field of imaging devices (Abstract, “laser welding head or welding gun, an industrial camera”), where a composite image can be formed from multiple images that all have different exposure times, where that would reduce the amount of light exposure in each image (Page 6, Para. 2 from end, “a camera shooting a frame of image is 25ms; and T1h, T2h, T3h, T4h is a high-level section of four different time length, which are 18ms, 3ms, 12ms, 6ms, corresponding to four types of different exposure times, obtaining one image of four different exposure times within the time period T of the back on the industrial control machine using image fusion algorithm to synthesize a high dynamic image”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the multiple exposures in modified Stecker to be of different exposure times as taught by Shi.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to capture different areas of the weld clearly through different exposure times, as stated by Shi, Page 6, last Para., “Because the dynamic range of plasma, molten, bead and matrix are too large, clear image cannot use the same exposure parameters to at the same time, collects the plasma, molten, bead and a matrix, can control the camera exposure amount so as to respectively clear shooting image of molten pool part and a lock hole part ratio change the exposure time by adjusting the duty of the rectangular wave.”.
Claims 24 is/are rejected under 35 U.S.C. 103 as being unpatentable over Stecker et al. (WO 2019074827 A1, hereinafter Stecker) in view of Wada et al. (JP 2016221538 A, hereinafter Wada) and Alam et al. (US 10067065 B1, hereinafter Alam) and Mehr et al. (WO 2018217903 A1, hereinafter Mehr) in further view of Hwang et al. (US 20190283333 A1, hereinafter Hwang).
Regarding claim 24, modified Stecker teaches the apparatus according to claim 23, as set forth above.
Modified Stecker does not disclose:
wherein the feature is a set of features, and wherein the machine learning model reduces the time exposure image to the set of features, wherein the set of features is a lowest number of features to represent the time exposure image, and the machine learning model reconstructs the time exposure image based on the set of features to identify the defect.
However, Mehr discloses where an image can be reduced to a set of features (Para. 0123, “FIGS. 7 A-C illustrate in-process feature extraction from images of a laser-metal wire deposition process obtained using a machine vision system…FIG. 7C shows the processed image after application of a feature extraction algorithm used to identify, for example, the angel of the wire relative to the build plate and the height (thickness) of the new layer.”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the time exposure images in modified Stecker to be reduced to a set of features as taught by Mehr.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to use machine learning to classify defects so that they can be mapped to process control parameters, which can then be adjusted in real-time in order to prevent predicted defects, which can help prevent defected objects from being produced, as stated by Mehr, Para. 0007, “c) providing a processor programmed to provide a classification of detected object defects using a machine learning algorithm that has been trained using the training data set of step (a), wherein the real-time data from the one or more sensors is provided as input to the machine learning algorithm and allows the classification of detected object defects to be adjusted in real-time.”.
Further, Hwang discloses, in the similar field of correcting for defects in additive manufacturing (Abstract, “automatic correcting any detected error in additive manufacturing”), where a machine learning model can take in images and find features within the images (Para. 0045, “Once the preprocessed image applied to a predictive model 200, then it identifies any defect of the applied powder layer from the extracted data-set (i.e., the preprocessed images), step 519, thereby determines any corrective actions to be followed, step 520.”, where the predictive model is determined using a machine learning model), where the features within the preprocessed image are used to reconstruct the image to determine the defect through machine learning (Para. 0033, “using machine learning algorithm and generating a predictive model therefrom according to an exemplary embodiment. The method begins, step 100, as described above, with collecting data sources 30 obtaining from preprocessed captured images at predetermined setting in sequence layer by layer 105, job files 5, build parameters 15, inspection output of solidification quality level and corresponding layers thereof 25, step 115, generating training data-set with curves 20 from preprocessed image in sequence 10 and corresponding build parameter values 15”, where the preprocessed image when inserted into the predictive model has the model search through training data set for a reconstructed match so that a defect can be identified, where this occurs through a machine learning model). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the machine learning model of detecting feedback strategy in modified Stecker to also be used for generating a predictive model for determining if defects are present as taught by Hwang.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of allowing a user to have correlations between the reference and actual data sets be done through machine learning, where this can allow for automatic adjustment of the additive manufacturing system, as stated by Hwang, Para. 0058, “identify the level of solidification quality using a predictive model, step 539. The present disclosed embodiment of system then applies the feature-set into a predictive model to calculate correlations from the feature-set and labeled data-set… Then the model 200 determines whether any adjustment of build parameters is required or not, step 540… Accordingly, adjust the build parameters via coupled controller 542 automatically”.
Claims 34 is/are rejected under 35 U.S.C. 103 as being unpatentable over Stecker et al. (WO 2019074827 A1, hereinafter Stecker) in view of Wada et al. (JP 2016221538 A, hereinafter Wada) and Alam et al. (US 10067065 B1, hereinafter Alam) and Mehr et al. (WO 2018217903 A1, hereinafter Mehr) in further view of Behrooz et al. (CA 3079400 A1, hereinafter Behrooz).
Regarding claim 34, modified Stecker teaches the apparatus according to claim 33, as set forth above.
Modified Stecker does not disclose:
wherein the operating characteristic includes commencement of a layer build and completion of the layer build.
However, Behrooz discloses where the camera shutter can be synchronized with illumination starting and ending, where the shutter opens when the light starts and closes when the light ends, where this light start/end is construed as being the start and end of building a layer in additive manufacturing (Para. 0012, “the CCD camera is aligned and operable to (i) detect light (e.g., fluorescent light and/or bioluminescent light) emitted from the one or more object(s) (e.g., from within the one or more object(s), and/or from a surface of the one or more object(s)) as a result of illumination of the one or more object(s) by the beam of illumination light and/or (ii) detect illumination light transmitted through or reflected by the one or more object(s), and acquiring each of the one or more images comprises: (A) responsive to a first trigger signal indicating a start of a global exposure phase of the CCD camera, rotating the source galvanometer mirror to the first rotational angle such that during the global exposure phase of the CCD camera the one or more object(s) is/are illuminated with the bean1 of illumination light; and (B) responsive to a second trigger signal indicating an end of the global exposure phase of the CCD camera, rotating the galvanometer mirror to the second rotational angle such that when the CCD camera is not in the global exposure phase, the one or more object(s) is/are not illuminated with the beam of illumination light, thereby synchronizing illumination of the one or more object(s) with the global exposure phase of the CCD camera for rapid image acquisition by the CCD camera.”). It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention to have modified the shutter operating rule in modified Stecker to include the feature as taught by Behrooz; where Examiner notes that Behrooz shows another method of capture images that is essentially the opposite of Wada, where each method has their own advantages and choosing between them would be a mere matter of user design choice.
One of ordinary skill in the art would have been motivated to make this modification in order to gain the advantage of being able to reduce image artifacts through the synchronized illumination method and prevent other light from reaching the image device, as stated by Behrooz, Para. 0218, “In this manner, the synchronized illumination approaches described herein substantially reduce and/or eliminate image artifacts that result from differences in local exposure times for different detector pixels by preventing illumination of the one or more object(s) to be image and, accordingly, preventing image forn1ing light from being produced and/or reaching the CCD sensor array. "foe systems and methods described herein may also utilize various housings to prevent other light, such as stray light and ambient light, from reaching the CCD sensor array, thereby minimizing the amount of light of any kind that reaches the CCD sensor array when it is not folly exposed.”.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KEVIN GUANHUA WEN whose telephone number is (571)272-9940 and whose email is kevin.wen@uspto.gov. The examiner can normally be reached Monday-Friday 10:00 am - 6:00 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Ibrahime Abraham can be reached on 571-270-5569. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/KEVIN GUANHUA WEN/Examiner, Art Unit 3761
03/10/2026