Prosecution Insights
Last updated: April 19, 2026
Application No. 18/535,632

MONITORING PIPELINE INTEGRITY USING MACHINE LEARNING AIDED FIBER-OPTIC DISTRIBUTED ACOUSTIC SENSING

Final Rejection §102§103
Filed
Dec 11, 2023
Examiner
FRANK, RODNEY T
Art Unit
2855
Tech Center
2800 — Semiconductors & Electrical Systems
Assignee
King Abdullah University Of Science And Technology
OA Round
2 (Final)
73%
Grant Probability
Favorable
3-4
OA Rounds
3y 3m
To Grant
76%
With Interview

Examiner Intelligence

Grants 73% — above average
73%
Career Allow Rate
663 granted / 913 resolved
+4.6% vs TC avg
Minimal +4% lift
Without
With
+3.6%
Interview Lift
resolved cases with interview
Typical timeline
3y 3m
Avg Prosecution
23 currently pending
Career history
936
Total Applications
across all art units

Statute-Specific Performance

§101
3.8%
-36.2% vs TC avg
§103
43.9%
+3.9% vs TC avg
§102
21.2%
-18.8% vs TC avg
§112
25.6%
-14.4% vs TC avg
Black line = Tech Center average estimate • Based on career data from 913 resolved cases

Office Action

§102 §103
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 . Claim Rejections - 35 USC § 102 The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action: A person shall be entitled to a patent unless – (a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention. Claim(s) 1, 2, 5, 9, 11, 12,15, 19, and 20 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Noetzli et al (WO Publication Number 2023/201389; hereinafter referred to as Noetzli). With respect to claim 1, Noetzli discloses and illustrates a method for monitoring pipeline integrity, comprising: obtaining, using at least one hardware processor (150), acoustic signal captured by at least one optical fiber (120) arranged along a pipeline (130), wherein the at least one optical fiber is coupled with a distributed acoustic sensing (DAS) system (see at least paragraph [0006]); inputting, using the at least one hardware processor, the acoustic signal to a machine learning model (see at least paragraph [0146]), wherein the machine learning model is trained to execute a first analysis on a first representation of the acoustic signal and a second analysis on a second representation of the acoustic signal (see at least paragraph [0146]), the first analysis being independent to the second analysis (see at least paragraph [0032]), wherein an output of the trained machine learning model is at least one of a first result based on the first analysis or a second result based on the second analysis (see at least paragraph [0037]); and determining, using the at least one hardware processor, an indication of pipeline integrity based on the at least one of the first result or the second result (see at least paragraph [0025]). With respect to claim 2, the method of claim 1, wherein the first analysis comprises a time-domain analysis, and the second analysis comprises a frequency-domain analysis (see at least paragraph [0008]. With respect to claim 5, the method of claim 1, wherein the indication comprises at least one of: a binary value indicating existence of a structural fault on the pipeline, or a non-binary value indicating a degree of metal loss on the pipeline (see at least paragraph [0168]). With respect to claim 9, the method of claim 1, wherein the at least one optical fiber is attached to a metallic surface of the pipeline or attached to a composite sleeve covering the pipeline (see at least paragraph [0118]). With respect to claim 11, Noetzli discloses and illustrates a non-transitory computer-readable medium storing program instructions (155) that, when executed, cause at least one hardware processor to perform operations for monitoring pipeline integrity, the operations comprising: obtaining, acoustic signal captured by at least one optical fiber (120) arranged along a pipeline (130), wherein the at least one optical fiber is coupled with a distributed acoustic sensing (DAS) system (see at least paragraph [0006]); inputting, using the at least one hardware processor, the acoustic signal to a machine learning model (see at least paragraph [0146]), wherein the machine learning model is trained to execute a first analysis on a first representation of the acoustic signal and a second analysis on a second representation of the acoustic signal (see at least paragraph [0146]), the first analysis being independent to the second analysis (see at least paragraph [0032]), wherein an output of the trained machine learning model is at least one of a first result based on the first analysis or a second result based on the second analysis (see at least paragraph [0037]); and determining, using the at least one hardware processor, an indication of pipeline integrity based on the at least one of the first result or the second result (see at least paragraph [0025]). With respect to claim 12, the non-transitory computer-readable medium of claim 11, wherein the first analysis comprises a time-domain analysis, and the second analysis comprises a frequency-domain analysis (see at least paragraph [0008]. With respect to claim 15, the non-transitory computer-readable medium of claim 11, wherein the indication comprises at least one of: a binary value indicating existence of a structural fault on the pipeline, or a non-binary value indicating a degree of metal loss on the pipeline (see at least paragraph [0168]). With respect to claim 9, the non-transitory computer-readable medium of claim 11, wherein the at least one optical fiber is attached to a metallic surface of the pipeline or attached to a composite sleeve covering the pipeline (see at least paragraph [0118]). With respect to claim 20, Noetzli discloses and illustrates a system for monitoring pipeline integrity, comprising: at least one optical fiber (120) arranged along a pipeline (130); and at least one hardware processor (150), wherein the at least one hardware processor is configured to perform operations comprising: obtaining acoustic signal captured by at least one optical fiber (120), inputting, the acoustic signal to a machine learning model (see at least paragraph [0146]), wherein the machine learning model is trained to execute a first analysis on a first representation of the acoustic signal and a second analysis on a second representation of the acoustic signal (see at least paragraph [0146]), the first analysis being independent to the second analysis (see at least paragraph [0032]), wherein an output of the trained machine learning model is at least one of a first result based on the first analysis or a second result based on the second analysis (see at least paragraph [0037]); and determining, an indication of pipeline integrity based on the at least one of the first result or the second result (see at least paragraph [0025]). 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. Claim(s) 8, 10, and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Noetzli. With respect to claims 8 and 18, Noetzli does not explicitly disclose a specific type of optical fiber being either single mode or a multi-mode fiber. However, single mode fibers are the most commonly used fibers. Therefore, it would have been obvious to one skilled in the art at the time the invention was filed to use a single mode optical fiber as it is practical and easily obtainable and a reliable fiber for a DAS system. With respect to claim 10, Noetzli doesn’t specifically disclose prompting a remedial measure to fix damage at a location. Noetzli does disclose locating damage at events in at least paragraph [0011]. However, providing a fix to a damaged location would be beneficial in order to prevent further damage to the system once damage has been identified. Therefore, it would have been obvious to one skilled in the art at the time the invention was filed to prompt remedial action to a damaged location in order to prevent further damage to the system once damage is identified. Claim(s) 6 and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Noetzli as applied to claims 1 and 11 above, and further in view of Ramsundar et al. (U.S. Patent Application Publication Number 2023/0111871; hereinafter referred to as Ramsundar). With respect to claim 6, Noetzli doesn’t disclose the method of claim 1, further comprising training the machine learning model using a training dataset in a supervised manner. However, Ramsundar teaches that machine learning algorithms can obtain data in numerous ways including supervised, semi-supervised, and unsupervised in at least paragraph [0052]. Therefore, it would have been obvious to one skilled in the art at the time the invention was filed to obtain the training data set in a supervised manner as it is known to improve accuracy (see at least paragraph [0053] of Ramsundar). With respect to claim 16, Noetzli doesn’t disclose the non-transitory computer-readable medium of claim 11, further comprising training the machine learning model using a training dataset in a supervised manner. However, Ramsundar teaches that machine learning algorithms can obtain data in numerous ways including supervised, semi-supervised, and unsupervised in at least paragraph [0052]. Therefore, it would have been obvious to one skilled in the art at the time the invention was filed to obtain the training data set in a supervised manner as it is known to improve accuracy (see at least paragraph [0053] of Ramsundar). Allowable Subject Matter Claims 3, 4, 7, 13, 14, and 17 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims. The following is a statement of reasons for the indication of allowable subject matter: Claims 3 and 13 require a convolutional neural network (CNN) having a time-domain branch trained to perform the time-domain analysis and a frequency-domain branch trained to perform the frequency-domain analysis, wherein the time-domain branch comprises: a first input layer configured to receive a time-domain representation of the acoustic signal; at least two first pairs of convolutional and max pooling layers; a first flattened layer; and a first dense layer, which is not disclosed in the prior art of record. Further, claims 7 and 17 require simulated data obtained from a computational fluid dynamics (CFD) simulation of sound pressure levels at simulated pipelines based on a metal thickness of the simulated pipelines, which is not disclosed in the prior art of record. Response to Arguments Applicant's arguments filed 17 March 2026 have been fully considered but they are not persuasive. The Applicant argues that the Examiner fails to show that Noetzli teaches any specific machine-learning model architecture, training method, or multi-branch model as recited by the present claims. For at least this reason, the present claims are allowable over Noetzli. Further, the Examiner fails to show that Noetzli teaches "wherein the machine learning model is trained to execute a first analysis on a first representation of the acoustic signal and a second analysis on a second representation of the acoustic signal." The Examiner disagrees. In at least Paragraph [0146], Noetzli teaches “Machine Learning Classifier Algorithm: A processing algorithm may be a machine learning classifier an algorithm that takes as input DAS sensor data, external sensor data or a multiple of Output States from other processing algorithms and returns Output States selected from a finite set of possibilities used to train the machine learning classifier model.” With respect to the claim, first, this teaches machine learning. The claim simply states machine learning model, with no specifics to the model, so no specific model is required. Next, Noetzli teaches an algorithm that takes as input DAS sensor data, so a single data input. Further, Noetzli teaches returns Output States selected from a finite set of possibilities used to train the machine learning classifier model, thus producing at least two analysis and at least two outputs from the single input. Therefore, Noetzli teaches machine-learning model architecture, wherein the machine learning model is trained to execute a first analysis on a first representation of the acoustic signal and a second analysis on a second representation of the acoustic signal. For at least this reason, the argument is not persuasive and the rejection is being maintained. Further the applicant argues: “The Examiner does not show that paragraph [0146] teaches or suggests a model "trained to execute a first analysis on a first representation of the acoustic signal and a second analysis on a second representation of the acoustic signal." Put another way, the Examiner fails to show that Noetzli teaches a multiple-branch machine learning model processing two representations of the same acoustic signal as described in the specification.” Again, as discussed above, Noetzli discloses machine-learning model architecture, wherein the machine learning model is trained to execute a first analysis on a first representation of the acoustic signal and a second analysis on a second representation of the acoustic signal. For at least this reason, the argument is not persuasive and the rejection is being maintained. The Applicant further argues “The Examiner fails to show that Noetzli teaches "wherein an output of the trained machine learning model is at least one of a first result based on the first analysis or a second result based on the second analysis." The Examiner relies on paragraph [0037] of Noetzli as teaching this claim feature. Noetzli is limited to describing a "processing algorithm may also receive information from one or a plurality of alternative sensors. A processing algorithm may receive one or more infrastructure states from previous iterations of the selection process." The Examiner fails to articulate why "one or more infrastructure states from previous iterations of the selection process" encompasses a trained machine learning model that outputs at least one of a first result based on the first analysis or a second result based on the second analysis as recited by the present claims.” Paragraph [0037] states: ”The method may further comprise the step of using the output states of at least two processing algorithms and a decision module to generate one or more infrastructure states in respect of each section of optical fibre cable adjacent to the infrastructure of interest.” With this in mind, Noetzli discloses “the step of using the output states of at least two processing algorithms”, which would be the output states generated by the machine learning model, as discussed above. As also discussed above, machine-learning model architecture, wherein the machine learning model is trained to execute a first analysis on a first representation of the acoustic signal and a second analysis on a second representation of the acoustic signal. For at least this reason, the argument is not persuasive. The Applicant argues the 35 USC 103 rejections form the standpoint that the independent claims are not properly rejected and that the secondary references do not cure the deficiencies of Noetzli. As discussed above, Noetzli does in fact cover the subject matter claimed, and thus the arguments to the contrary are not persuasive. With respect to an interview, the Examiner notes that the claims are now twice properly rejected and the claims, and thus in an after final rejection status. Interviews are not always granted in such a situation and further reason for the interview beyond mere claim discussion would be required and a decision on whether an interview would be granted or not would be made at that time. The Examiner would also remind the Applicant that since allowable subject matter is indicated, then incorporating that allowable subject matter into the independent claim should at least get around the current rejections. The Applicant should feel free to reach out to the Examiner should further discussion be needed. Conclusion THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a). A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action. Any inquiry concerning this communication or earlier communications from the examiner should be directed to RODNEY T FRANK whose telephone number is (571)272-2193. The examiner can normally be reached M-F 9am-5:30pm. 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, Peter Macchiarolo can be reached at (571) 272-2375. 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. RODNEY T. FRANK Examiner Art Unit 2855 /PETER J MACCHIAROLO/Supervisory Patent Examiner, Art Unit 2855 March 27, 2026
Read full office action

Prosecution Timeline

Dec 11, 2023
Application Filed
Dec 26, 2025
Non-Final Rejection — §102, §103
Mar 17, 2026
Response Filed
Mar 27, 2026
Final Rejection — §102, §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12590944
METHOD AND APPARATUS FOR DETERMINING KETOSIS
2y 5m to grant Granted Mar 31, 2026
Patent 12584936
PIPETTING UNIT WITH CAPACITIVE LIQUID DETECTION, COMBINATION OF SUCH A PIPETTING UNIT AND A PIPETTING TIP, AND METHOD FOR CAPACITIVELY DETECTING PIPETTING LIQUID
2y 5m to grant Granted Mar 24, 2026
Patent 12584839
POINT-OF-USE DEVICES AND METHODS FOR DETERMINING RHEOLOGICAL PROPERTIES OF SAMPLES
2y 5m to grant Granted Mar 24, 2026
Patent 12584776
PROCESS MONITORING DEVICE
2y 5m to grant Granted Mar 24, 2026
Patent 12584891
GAS CHROMATOGRAPH
2y 5m to grant Granted Mar 24, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

3-4
Expected OA Rounds
73%
Grant Probability
76%
With Interview (+3.6%)
3y 3m
Median Time to Grant
Moderate
PTA Risk
Based on 913 resolved cases by this examiner. Grant probability derived from career allow 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