Prosecution Insights
Last updated: May 04, 2026
Application No. 18/282,878

TRIANGULATION-BASED ANOMALY DETECTION IN THREE DIMENSIONAL PRINTERS

Non-Final OA §101
Filed
Sep 19, 2023
Priority
Mar 24, 2021 — nonprovisional of PCTUS2021023831
Examiner
ERDMAN, CHAD G
Art Unit
2116
Tech Center
2100 — Computer Architecture & Software
Assignee
Peridot Print LLC
OA Round
1 (Non-Final)
80%
Grant Probability
Favorable
1-2
OA Rounds
0m
Est. Remaining
99%
With Interview

Examiner Intelligence

Grants 80% — above average
80%
Career Allowance Rate
448 granted / 562 resolved
+24.7% vs TC avg
Strong +19% interview lift
Without
With
+19.0%
Interview Lift
resolved cases with interview
Typical timeline
2y 6m
Avg Prosecution
29 currently pending
Career history
591
Total Applications
across all art units

Statute-Specific Performance

§101
6.6%
-33.4% vs TC avg
§103
51.3%
+11.3% vs TC avg
§102
16.4%
-23.6% vs TC avg
§112
15.1%
-24.9% vs TC avg
Black line = Tech Center average estimate • Based on career data from 562 resolved cases

Office Action

§101
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 . DETAILED ACTION Claims 1 – 15 are pending in the application. Claims 8 – 15 were withdrawn subject to a restriction/election requirement. Claim 1 is independent. This is a non-final action. Claim Objections Claim 6 is objected to because of the following informalities: “…further comprising providing, by the processor and based on the detection of the anomaly a user one of a terminate print job option, an option for real-time adjustment…” Is awkwardly stated and/or grammatically incorrect. Appropriate correction is suggested. Claim Rejections - 35 USC § 101 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 1 - 7 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception {i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more. Claim 1 is directed to method, by a processor, of detecting an anomaly in a layer being printed based on triangulation of the first predicted anomaly and second predicted anomaly, wherein the predicted anomalies are generated from first and second machine learning model’s, respectively. Step 1: The claim (claim 1) recites a method for 3D printing of detecting anomalies. Thus, the claim is directed to a process and machine, which is one of the statutory categories of invention. Step 2A Prong 1: Abstract ideas have been identified by the courts by way of example, including fundamental economic practices, certain methods of organization of human activities, an idea 'of itself,' and mathematical relationships/formulas. Alice Corp., 134 S. Ct. at 2355 - 56. Claim 1 recites limitations of: -using a processor for collecting real time data; -using a 3D printer, -obtaining two predicted anomalies using machine learning models; and -detecting an anomaly. Using data by a processor for 3D printing and predicting anomalies by machine learning models and detecting an anomaly as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitations describing mathematical relationships, but for the recitation of generic processor or 3D printer components or methods. That is, other than reciting “data sets to a sequence of layers,” “a processor” and “3D printing of layers” nothing in the claim precludes the determining steps from practically being performed using mathematical relations, calculations, or formulas. The steps of using machine learning models to predict anomalies by triangulation of the predicted anomalies is a mathematical process. Accordingly, the claim recites an abstract idea. Step 2A Prong 2: This judicial exception is not integrated into a practical application. In particular, the claim only recites gathering data, a processor, a 3D printer, and a detection step. The elements, and the last detecting step, are recited at a high level of generality, and these limitations are no more than mere instructions to apply the exception using an unknown structure and these steps could be performed mathematical process. Accordingly, the last element of “detecting” does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to the abstract idea. Step (2B): The claims do not include additional elements that are sufficient to amount to significantly more than the abstract idea and do not provide an inventive concept. In this instance, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of the using real-time data, a process, a 3D printer, and the detecting step amounts to no more than mere generic or mathematical processes to apply the exception using generic computer components and concepts. Mere generalities of detecting and using the “detecting” with mathematical processes to apply an exception with generic computer and printer components cannot provide an inventive concept. The claim is not patent eligible. Thus the claim is not drawn to patent eligible subject matter as it is directed to the same abstract idea without significantly more. Claims 2 – 71, also do not add anything significantly more and are also rejected under 35 USC 101. Claim 2 that uses two different models such as an encoder-decoder based deep learning model and the second machine learning model is also mathematical concept and does not add anything significantly more and is also rejected under 35 USC 101. Claim 3 that uses an encoder-decoder based deep learning model comprises long short-term memory (LSTM) units to generate a summary of a sequence of the data set obtained for the sequence of layers does not add anything significantly more to the mathematical abstract idea and is also rejected under 35 USC 101. Claim 4 that categorizes the detected anomaly as one of a ghost layer anomaly, layer phase shifting anomaly, and a crazing anomaly does not add anything significantly more to the mathematical abstract idea and is also rejected under 35 USC 101. Claim 5 that outputs a notification to a user might be significantly more than the mathematical abstract idea and possibly overcome the rejection under 35 USC 101. However, this might be an insignificant extra-solution activity to the judicial exception and might not integrate the judicial exception into a practical application. Further analysis will be given under MPEP 2106.05(g) citing examples of extra-solution activities after final amendment of the claim. Claim 6 that outputs options to a user based on the detection might be significantly more than the mathematical abstract idea and possibly overcome the rejection under 35 USC 101. However, this might be an insignificant extra-solution activity to the judicial exception and might not integrate the judicial exception into a practical application. Further analysis will be given under MPEP 2106.05(g) citing examples of extra-solution activities after final amendment of the claim. Claim 7 that claims training the first machine learning model and the second machine learning model about a normal printing behavior of the 3D printer based on data sets pertaining to multiple sequences of printed layers; and a database, coupled to the training engine, to store storing a first trained machine learning model and a second trained machine learning model in a database does not add anything significantly more to the mathematical abstract idea and is also rejected under 35 USC 101. Examiner's Statement of Reasons for Allowance The following is an examiner’s statement of reasons for allowance: The applicant has claimed a method of using a computer processor to gathering data pertaining to a sequence of layers; and interpreting the data with a first and second learning model. The processor then predicts two anomalies using the two different machine learning models, respectively. The method then detects an anomaly in a subsequent layer being printed based on triangulation (a mathematical verification step) of the first and second predicted anomalies. No prior art could be found that teaches the element of a method comprising: providing, by a processor, a data set pertaining to a sequence of layers, printed by a 3D printer, for interpretation by a first machine learning model and a second machine learning model; provide providing, by the processor, real-time data of a subsequent layer being printed by the 3D printer to the first machine learning model and the second machine learning model; based on the interpretation and the real-time data, obtaining, by the processor, a first predicted anomaly and a second predicted anomaly for the subsequent layer being printed, from the first machine learning model and the second machine learning model, respectively; and detecting an anomaly in the subsequent layer being printed based on triangulation of the first predicted anomaly and the second predicted anomaly. However, the claims were rejected under 35 USC 101 as stated above. The claimed invention is distinguished over the following prior art: Van Der Velden et al. (EP 3739495 A2), cited by the Patent Cooperation Treaty International Preliminary Report on Patentability on November 15, 2021, teaches a process to train a machine-learning model to predict the behavior of a 3D printer. However, this reference does not incorporate the details of the current application that uses two models and triangulation of predicted anomalies using the two models, respectively. Also, the reference may detect an anomaly, but the anomaly is based on sensor detection and may not teach the anomalies of a subsequent layer being printed. (See figure 1 and Par. 0012). Non-patent literature of Goh et al. A review on machine learning in 3D printing: applications, potential, and challenges, Artificial Intelligence Review, 54:63-94, Published on July 16, 2020, teaches 3D printing and finding anomalies using Machine Learning Algorithms. But this application is far distinguished from the current claimed invention. Bottom of page 64 (PDF page 2), states: “To overcome the time-consuming physics-based modeling and to detect anomaly during the in-process monitoring for quality control, data-driven models have been used in the AM field. A large amount of data is collected and processed by the ML algorithms to predict certain behaviors and properties, which are essential for decision making. It is also used in AM to recognize certain patterns or irregularities in the dynamic manufacturing process.” However, Goh does not teach two ML models and does not teach triangulation of two anomalies with two different machine-learning models, respectively. Beckett et al. (US PG Pub. No. 20220042924) is on point with the instant application and teaches an additive manufacturing system comprising an apparatus arranged to distribute layer of metallic powder across a build plane and a power source arranged to emit a beam of energy at the build plane and fuse the metallic powder into a portion of a part and uses a machine learning algorithm to detect one or more defects in the fused metallic powder. (Abstract). However, this reference does not incorporate the details of the current application that uses two models and triangulation of predicted anomalies using the two models, respectively. Wang et al. (US PG Pub. No. 20200100871) is on point with the instant application and teaches printing 3D molds of aligners (Par. 0006) and uses a trained machine learning model trained to identify aligners having probable points of damage. (Par. 0056). Paragraph 0112 also teaches using a second machine learning model to predict damage on an aligner. However, this reference does not incorporate the details of the current application that uses two models and triangulation of predicted anomalies using the two models, respectively. No other prior art could be found that teaches the claim limitations in claim 1. Thus, the claims may be allowable if rewritten pending resolving all issues such as the claim objections and 35 U.S.C. §101 rejections. Reasons for allowance will be held in abeyance pending final recitation of the claims. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHAD G ERDMAN whose telephone number is (571)270-0177. The examiner can normally be reached Mon - Fri 7am - 3pm or 4pm EST.. 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, Kenneth Lo can be reached at (571) 272-9774. 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. /CHAD G ERDMAN/Primary Examiner, Art Unit 2116 1 Examiner’s Note – See specifically claims 5 and 6 rejections below; a combination of both 5 and 6 will probably add significantly more to the abstract idea and overcome the 35 USC 101 rejection.
Read full office action

Prosecution Timeline

Sep 19, 2023
Application Filed
Jan 16, 2026
Response after Non-Final Action
Mar 30, 2026
Non-Final Rejection — §101 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12573163
METHOD FOR MANUFACTURING PLATE-SHAPED THREE-DIMENSIONAL OBJECT
2y 5m to grant Granted Mar 10, 2026
Patent 12550838
DEVICES, SYSTEMS, AND METHODS FOR IRRIGATION CONTROL
3y 2m to grant Granted Feb 17, 2026
Patent 12547136
Control Platform for Exchanges of Energy Between a Plurality of Energy Systems and Energy Exchange System
3y 5m to grant Granted Feb 10, 2026
Patent 12535793
INTELLIGENT EDGE INTERROGATOR, SERVER, AND CONTROL METHOD OF INTEGRATED FACILITY SAFETY CONTROL SYSTEM INCLUDING THE INTELLIGENT EDGE INTERROGATOR AND THE SERVER
3y 1m to grant Granted Jan 27, 2026
Patent 12530019
INFORMATION PROCESSING SYSTEM
3y 11m to grant Granted Jan 20, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

1-2
Expected OA Rounds
80%
Grant Probability
99%
With Interview (+19.0%)
2y 6m (~0m remaining)
Median Time to Grant
Low
PTA Risk
Based on 562 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month