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 Claims
Claims 1-20 are pending in the application.
Response to Amendment
The amendment filed October 28th, 2025 has been entered. Applicant’s amendments to the Claims have overcome the 101 rejection set forth in the previous Office Action.
Response to Arguments
Applicant’s arguments with respect to claim 1 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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.
Claims 1-6, 8-13 and 15-20 are rejected under 35 U.S.C. 103 as being unpatentable over Bennett et al. (U.S. Publication No. 2020/0384693 A1) in view of Okada et al. (U.S. Publication No. 2022/0301315 A1).
Regarding Claim 1:
Bennett et al. teaches a computer-implemented method, comprising: accessing, by a computer of an additive manufacturing system, a model that is trained to identify defects within a build plane of the additive manufacturing system, (Paragraph [0029], machine learning model is trained to find defects
in powder bed)
wherein the build plane includes a metallic powder, and wherein the additive manufacturing system further includes a heat source arranged to form one or more objects from the metallic powder; (Paragraph [0014], metallic powder is heated to create three-dimensional object)
capturing, by an imaging system of the additive manufacturing system, an image of the build plane of the additive manufacturing system, the build plane comprising a layer of the metallic powder extending across the one or more objects being manufactured through an additive manufacturing process; (Paragraph [0031]-[0032], camera captures an image of the powder bed after the layer spreading is complete)
providing, by the computer, the captured image as an input to the model; (Paragraph [0032], image of the powder bed is compared to the training data)
and receiving, by the computer, an output from the model identifying a defect in the build plane; (Paragraph [0032], model identifies and classifies any defects found in the powder bed)
and generating, by the computer, one or more control signals in response to a determination of a defect to control the additive manufacturing system. (Paragraph [0032], corrective action can be taken to modify laser parameters to accommodate the powder bed defect)
Bennett et al. does not teach selecting, by the computer, the model from a model warehouse, wherein the selecting is based at least in part on the one or more objects.
However, Okada et al. teaches selecting, by the computer, the model from a model warehouse, (Paragraph [0112], storage unit stores a plurality of models that are selectively used)
wherein the selecting is based at least in part on the one or more objects. (Paragraph [0050], machine learned model can be used to detect vehicles and license plates or people and faces; Additionally, Paragraph [0110], depending on the travel environment, a tendency of an element appearing in the captured image changes and Paragraph [0112], travel environment is used to determine an appropriate model)
It would have been obvious to one of ordinary skill in the art, at the effective filing date of the claimed invention, to modify Bennett et al.'s using machine learning to determine powder bed defects with Okada et al.'s selecting a model in order to select which model is used to determine powder bed defects. One would be motivated to combine these teachings in order to apply a known technique (selecting a model) to a known device (machine learning to determine powder bed defects) ready for improvement to yield predictable results (select which model is appropriate to determine powder bed defects).
Regarding Claim 2:
The combination of Bennett et al. and Okada et al. additionally teaches the method of claim 1, further comprising: determining, by the computer, if the defect can be corrected. (Bennett et al. Paragraph [0032], additive manufacturing can take corrective action to modify laser para meters to accommodate the powder bed defect)
Regarding Claim 3:
The combination of Bennett et al. and Okada et al. additionally teaches the method of claim 2, further comprising: generating, by the computer, one or more control signals for one or more in process parameters in response a determination that the identified defect can be corrected, the one or more control signals configured to correct the defect. (Bennett et al. Paragraph [0032], additive manufacturing can take corrective action to modify laser parameters to accommodate the powder bed defect)
Regarding Claim 4:
The combination of Bennett et al. and Okada et al. additionally teaches the method of claim 2, further comprising: terminating, by the computer, the additive manufacturing process in response to a determination that the identified defect cannot be corrected. (Bennett et al. Paragraph [0032], additive manufacturing can abort the build process)
Regarding Claim 5:
The combination of Bennett et al. and Okada et al. additionally teaches the method of claim 1, wherein the receiving further comprises: providing, by the computer, the output of the model to a display device of the additive manufacturing system. (Bennett et al. Paragraph [0032], any deviations that are greater than a threshold can be identified and labelled as defects)
Regarding Claim 6:
The combination of Bennett et al. and Okada et al. additionally teaches the method of claim 1, wherein the output from the model includes a defect type for the identified defect. (Bennett et al. Paragraph [0032], model identifies and classifies any defects found in the powder bed; Additionally, Bennett et al. Paragraph [0028], each patch can be labelled with the type of defect such as streaking, hopping, incomplete spreading, etc.)
Regarding Claims 8-13:
Claims 8-13 are the system of claims 1-6 and are thus rejected under the same rational as cited above.
Regarding Claims 15-20:
Claims 15-20 are the non-transitory computer-readable medium of claims 1-6 and are thus rejected under the same rational as cited above.
Claims 7 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Bennett et al. (U.S. Publication No. 2020/0384693 A1) and Okada et al. (U.S. Publication No. 2022/0301315 A1) as applied to claims 1-6, 8-13 and 15-20 above, and further in view of Scime et al. (U.S. Publication No. 2022/0134435 A1).
Regarding Claim 7:
The combination of Bennett et al. and Okada et al. teaches the method of claim 1.
The combination of Bennett et al. and Okada et al. does not teach wherein accessing the
model further comprises: selecting, by the computer, the model from a model warehouse based on at least one of a powder bed layout, a powder material, a lighting angle, or a lighting type.
However, Scime et al. teaches wherein accessing the model further comprises: selecting, by the computer, the model from a model warehouse based on at least one of a powder bed layout, a powder material, a lighting angle, or a lighting type. (Paragraph [0048]-[0049], user can create, save, and load various workspaces, each workspace can include its own set of trained models; Paragraph [0132], material feedstock characteristics, lighting conditions, etc.)
It would have been obvious to one of ordinary skill in the art, at the effective filing date of the claimed invention, to modify Bennett et al. and Okada et al.'s using machine learning to determine powder bed defects with Scime et al.' s separate workspaces with separate models in order to have use models that have been trained for a certain printer or setup. One would be motivated to combine these teachings in order to apply a known technique (separate workspaces with separate models) to a known device (using machine learning to determine powder bed defects) ready for improvement to yield predictable results (use machine learning models that are better for that printer or environment).
Regarding Claim 14:
Claims 14 is the system of claim 7 and is thus rejected under the same rational as cited above.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TYLER DEAN HEDRICK whose telephone number is (571)272-5803. The examiner can normally be reached Monday-Friday: 9:00am - 5:00pm.
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, Kamini Shah can be reached at (571) 272-2279. 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.
/T.D.H./Examiner, Art Unit 2115
/KAMINI S SHAH/Supervisory Patent Examiner, Art Unit 2115