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 .
Response to Amendment
The Amendment filed June 22, 2026 has been entered. Claims 1-18 & 20 remain pending in the application. Claim 19 was cancelled. Claims 1-2, 5-6, 8-10, 13, & 16-17 were amended. Applicant’s amendments to the Claims have overcome each and every objection previously set forth in the Non-Final Office Action mailed April 17, 2026, hereafter referred to as the Non-Final Office Action.
Response to Arguments
Applicant's arguments, see pp. 6-13, filed June 22, 2026 have, with respect to the rejections of amended independent claims 1 & 9, under 35 USC § 103 as being unpatentable over May (US 2005/0068026 A1), in view of Hardy (US 2017/0168016 A1), and further in view of Atherton (US 2004/0189289 A1), & amended independent claim 17 under 35 USC § 103 as being unpatentable over Koenig (US 2016/0290966 A1) have been entered, fully considered, and are persuasive. Therefore, the rejection(s) have been withdrawn. However, upon further consideration, in light of the amendments, new grounds of rejections have been made in view of Vaganay (US 2023/0003687 A1), in view of Denenberg (US 2016/0274060 A1), and further in view of Ona (US 2015/0206629 A1) for amended independent claims 1 & 9, and Vaganay, in view of Denenberg, and further in view of Fouda (US 2023/0213681 A1) for amended independent claim 17. The Applicant has presented a set of arguments pointing out their rationale of how the prior art references made of record in the most recent Non-Final Office Action do not teach the currently recited claim limitations. Applicant’s arguments have been fully considered but they are not persuasive.
Applicant in their submitted response presents the argument that the prior art references of record, “fail to disclose, teach, or suggest all of the claimed feature of claims 1-20,” and “for an obviousness rejection to be proper, the Examiner must meet the burden of establishing a prima facie case obviousness…,” in reference to claims 1-20. The Applicant did not provide their rationale on pp. 7 of the submitted response.
The Examiner respectfully disagrees and would to break the argument presented into two sections. The first part the Examiner would like to highlight is that 37 CFR 1.111(b) requires that a proper response to an OA “must be reduced to a writing which distinctly and specifically points out the supposed errors in examiner’s action…”. Also see MPEP 714.02 The remarks are directed to a listing of case law do not provide specific reasons, just generalizations not tied to the facts of the application, as to why either the findings of fact or legal conclusion of obviousness for claims 1-20 are allegedly in error. The second part the Examiner would like to highlight is the requirements for obviousness are discussed in MPEP 2142, 2143(I)(A), 2143(I)(B), 2143(I)(C), 2143(I)(D), 2143(I)(G), and 2143.02. The first argument is not persuasive because upon review, the rejections for claims 1-20 do make a prima facie cause using a combination of Rationales A, B, C, D, and G.
Applicant in their submitted response presents the argument that the prior art reference of record, Atherton, is not analogous art, “a reference is analogous art only if it is either from the same field of endeavor as the claimed invention..,” because it is allegedly restricted to detecting discontinuities in prestressing wire associated PCPP and is neither in the same field of endeavor nor reasonably pertinent to the problem faced by the inventors, in regard to independent claims 1 & 9. The Applicant provided their rationale on pp. 7-10 of the submitted response.
The Examiner respectfully disagrees and would like to highlight that a reference is analogous art if it is from the same field of endeavor, regardless of the problem addressed, or if it is reasonably pertinent to the particular problem with which the inventor is involved. Also see MPEP 2141.01(a). Atherton discusses the background of “Non-destructive testing of larger diameter steel pipes…using magnetic-inspection techniques,” and further details the use of “Remote field eddy-current (RFEC) devices,” ([Abstract],[0002]-[0003], & [0009]). Therefore, Atherton is in the same field of endeavor as the claimed invention which pertains to non-destructive eddy current testing of steel pipes.
Applicant in their submitted response presents the argument that the present application, “identifies the relevant problem of false PEC readings that occur when “energized high voltage cables are housed within oil filled conduits or pipes,” where “magnetic fields caused by the energized cables interfere with the PEC resting resulting in false data readings and/or increased inspection time and cost,”” in regard to independent claims 1 & 9, referring to the “Specification, [0003].” The Applicant provided their rationale on pp. 7-10 of the submitted response.
The Examiner respectfully disagrees and would to break the argument presented into two sections. In response to the Applicant's argument that the reference, Atherton, fails to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., “magnetic fields caused by the energized cables interfere with the PEC resting resulting in false data readings and/or increased inspection time and cost,”) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). Please also refer to MPEP 2145(VI). The second part the Examiner would like to highlight is that Atherton recognizes that “proximity to power lines or cables” act as “sources of interference or pick up” ([0027]) that affect signal responses, and notes the importance of the ability to “calculate or estimate corrections for these differences,” ([0027]). Therefore, Atherton is pertinent to the problem of identifying and correcting for electromagnetic interference caused by external cables during pipe inspection.
Applicant in their submitted response presents the argument that prior art references May and Hardy are “silent regarding energized high voltage cables located within the inspected substantially metal pipe or tank and is silent regarding compensating metal loss output measurements for errors caused by such cables..,” and that Atherton does not teach these features or generating compensated measurements, in regard to independent claims 1 & 9. The Applicant provided their rationale on pp. 7-10 of the submitted response.
The Examiner respectfully disagrees and would to break the argument presented into two sections. In response to the Applicant's argument that the reference, Atherton does not teach these features, it is well established that one cannot show non-obviousness by attacking references individually where the rejections are based on combinations of references. See MPEP 2145 (IV). In light of the amendments, and additional prior art references included in amended independent claims 1 & 9, the updated rejection does not rely on Atherton to teach the cable being physically inside the tank, nor does it rely on Atherton to teach the specific algorithmic or hardware mechanism for generating the compensated measurement . The second part the Examiner would like to highlight is regarding the cable within the tank, the updated combination relies on Vaganay to teach an inspection vehicle deployed with a cable routed internally within a tank. Regarding the compensation, the updated combination relies on Hardy and Denenberg for the compensation mechanisms. Hardy teaches cancelling out a “parasitic external magnetic field.” Denenberg teaches utilizing a “Calibration module 2101” to process raw impedance data and remove “Class 2: Parasitic coupling” errors. Atherton provides the motivation, recognizing that power lines and cables act as parasitic noise sources that require corrections ([0027]) taught by Hardy and Denenberg. In light of the amendments, please refer to updated rejections below, which now include new grounds of rejections made in view of Vaganay (US 2023/0003687 A1), in view of Denenberg (US 2016/0274060 A1), and further in view of Ona (US 2015/0206629 A1).
Applicant in their submitted response presents the argument that prior art of record, Atherton, “reflects hindsight reconstruction rather than an articulated reason with rational underpinning…,” in regard to independent claim 1 (similar rational applies to independent claim 9). The Applicant provided their rationale on pp. 7-10 of the submitted response.
The Examiner respectfully disagrees and in response to the Applicant's argument that the reference, Atherton “reflects hindsight,” the rational underpinning has been updated and provided in the motivation to combine for amended independent claims 1 & 9. Combining known eddy current pipe testing methods (May) with known internal tank inspection environments (Vaganay), identifying known cable noise sources in those environments (Atherton), and applying standard mathematical/hardware noise-cancellation techniques to the signal (Hardy/Denenberg) yields predictable results. Please refer to updated rejections below. See MPEP 2145(X).
Applicant in their submitted response presents the argument that prior art of record, Koenig and May, do not teach or suggest, performing machine learning-assisted surrogate model training aligned with field-test calibration data…,” in regard to amended independent claim 17. The Applicant provided their rationale on pp. 10-11 of the submitted response.
In light of the amendment in independent claim 17, new grounds of rejections are made over Koenig (US 2016/0290966 A1), in view of May, in view of Vaganay, in view of Denenberg, and further in view of Fouda (US 2023/0213681 A1) and meet these requirements. Please refer to updated rejection below.
Therefore, the Applicant’s arguments are unconvincing and the rejections of independent claims 1, 9, & 17, and dependent claims 2-8, 10-16, 18, & 20, which depend from and incorporate the limitations of amended independent claims 1, 9, & 17, are respectively maintained. Rejections based on the newly cited prior art references follow.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-16 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites the limitation “a substantially metal pipe or a substantially metal tank…” in ll. 4-5, where the term “substantially” is considered indefinite in the claim limitations. The definition provided for this term refers to “degree of error associated with measurement of the particular quantity based upon the equipment available…,” but not to the mentioned “pipe” and/or “tank”. Claim 1 further recites, “are located within the pipe or tank;” in ll. 5-6, without prior disclosure. There is insufficient antecedent basis for these limitations in the claim language. For examination purposes, the examiner interprets this claim limitations to read as “are located within the substantially metal pipe or the substantially metal tank;”. Claims 2-8, which do not rectify the defect, are also rejected by virtue of dependency to claim 1.
Claim 9 recites the limitation “a substantially metal pipe or a substantially metal tank…” in line. 4 (similarly in claim 1), where the term “substantially” is considered indefinite in the claim limitations. The definition provided for this term refers to “degree of error associated with measurement of the particular quantity based upon the equipment available…,” but not to the mentioned “pipe” and/or “tank”. Claims 10-16, which do not rectify the defect, are also rejected by virtue of dependence to claim 9.
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 1-16 are rejected under 35 U.S.C. 103 as being unpatentable over May et al. (US 2005/0068026 A1, Pub. Date Mar. 31, 2005, hereinafter, May), in view of Hardy et al. (US 2017/0168016 A1, Pub. Date Jun. 15, 2017, hereinafter, Hardy), in view of Atherton (US 2004/0189289 A1, Pub. Date Sep. 30, 2004, hereinafter, Atherton), in view of Vaganay et al. (US 2023/0003687 A1, Pub. Date Jan. 5, 2023, hereinafter, Vaganay), in view of Denenberg et al. (US 2016/0274060 A1, Pub. Date Sep. 22, 2016, hereinafter, Denenberg), and further in view of Ona et al. (US 2015/0206629 A1, Pub. Date Jul. 23, 2015, hereinafter, Ona).
Regarding independent claim 1, May, teaches:
A method of pulsed eddy current (PEC) testing, the method comprising (Fig. 4; [Abstract], [0004], & [0018]):
receiving metal loss output measurements, the metal loss output measurements calculated based on an eddy current response (Fig. 1; [0003] & [0014]-[0019]: teaches calculating thickness/metal loss based on the eddy current response) captured by a probe at a location on a substantially metal pipe or a substantially metal tank ([0003] & [0014]-[0019]: teaches capturing eddy/current responses via a probe/sensor to calculate parameters such as corrosion (metal loss) and wall thickness on steel containers/tanks and pipes),
PNG
media_image1.png
764
940
media_image1.png
Greyscale
PNG
media_image2.png
778
556
media_image2.png
Greyscale
May, is silent in regard to:
wherein one or more energized high voltage cables are located within the pipe or tank;
generating compensated metal loss output measurements to compensate for errors in the metal loss output measurements caused by the energized high voltage cables; and
However, Vaganay, further teaches:
wherein one or more energized high voltage cables are located within the pipe or tank ([0146]-[0148] & [0150]: maps to cables being located physically within the tank environment during operation);
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the tank inspection method of May to include evaluating tanks containing internal cables as taught by Vaganay. May discloses pulsed eddy currents testing for metal loss on tanks. Vaganay teaches an internal tank inspection system where a cable is deployed and routed directly within the fluid-filled tank to support the vehicle. Ona further teaches energized high cables (138 kV) housed directly within a substantially metal pipe ([0022] & [0047]). The reason to combine these references is to improve inspection efficiency by allowing continuous, tethered internal evaluations without the need to drain the tank’s contents. This combination represents a substitution of applying a known inspection deployment technique to a known testing apparatus, yielding the predictable variation of a functional internal tank evaluation system (KSR).
However, Hardy, further teaches:
generating compensated metal loss output measurements to compensate for errors in the metal loss output measurements caused by the energized high voltage cables (Hardy: [0063]: discloses the probe and the presence of a parasitic external magnetic field 530, provides the hardware cancellation of parasitic magnetic noise); and
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to recognize that the high voltage cables within the pipe or tank of the prior combination introduce errors requiring correction as taught by Hardy. The prior combination provides for PEC testing of pipes or tanks containing internal high voltage cables. Hardy discloses a hardware compensation technique using dual-purpose coils in an antiparallel configuration to cancel out parasitic external magnetic fields, thereby compensating for induced noise voltages. Atherton teaches the necessity of compensating for power cable interference, correcting errors from power cables ([0027]-[0029]). Denenberg algorithmically generates a calibrated, compensated signal to correct for parasitic coupling errors ([0220], [0222], [0365]-[0371], [0373]-[0374], [0379], [0381]-[0382]). Further, it would have been obvious to a POSITA to incorporate Hardy’s noise cancellation hardware into the testing method. The benefit gained by this combination is the improved accuracy of the thickness measurements physically rejecting external magnetic interference from nearby cables. Modifying the probe design in this manner is a substitution of one known noise-reduction coil layout for another, leading to the predictable variation of an accurate, compensated PEC probe (KSR).
May, and Hardy, are silent in regard to:
outputting the compensated metal loss output measurements as PEC test results.
However, Denenberg, further teaches:
outputting the compensated metal loss output measurements as PEC test results ( [0006]-[0007], [0012], [0023]-[0024], [0096], [0118], [0129], [0185], [0187]-[0188], [0191], [0193], [0196], [0201]-[0202], [0208], [0212]-[0215], [0220], [0222], [0226], [0233], [0237], [0302], [0353], [0367]-[0369], [0384], [0393]-[0397], [0399], [0404], [0406], [0410], [0415], [0417], [0426], [0442], [0509], [0512], [0522], [Claim 29]: both May and Denenberg teach outputting the finalized, compensated testing measurements to a display, memory, or assessment module).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply Denenberg’s computational calibration steps to the testing method of the prior combination to fully generate compensated output measurements. The previous references provide hardware-based noise cancellation. Denenberg teaches a Calibration Module that mathematically removes “parasitic coupling” errors induced in the sensor wiring by external magnetic fields to output calibrated, compensated impedance data. The motivation for this combination is to further improve measurement accuracy and resolve dynamic errors from energized high voltage cables that hardware cancellation alone may miss. Implementing this algorithmic correction is a known technique to improve similar devices by applying standard digital signal processing, resulting in the predictable variation of a compensated, reliable metal loss measurement system (KSR).
Regarding dependent claim 2, May, teaches:
The method of claim 1 (Fig. 4; [Abstract], [0004-[0005], & [0016]-[0018]),
May, is silent in regard to:
further comprising controlling the movement of the probe to another location on the substantially metal pipe or substantially metal tank.
However, Vaganay, further teaches:
further comprising controlling the movement of the probe to another location on the substantially metal pipe or substantially metal tank ([0005]-[0006], [0023], [0302], [0324], [0340], & [0342]-[0343]: teaches controlling the movement of an inspection vehicle (which carries the inspection probe) from a first position to a second position (another location) within the tank to conduct further testing).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the testing probe of May to include controlling the movement of the probe to another location inside the tan as taught by Vaganay. May discloses the base method of pulsed eddy current testing on metal objects, and further establishes the base PEC probe utilized on a metal object; Vaganay teaches an internal tank inspection system comprising a control unit that provides commands causing a propeller to move the vehicle, and its onboard inspection device, from a first position to a second position within the tank. The reason to combine these references is to improve inspection efficiency by allowing a controlled vehicle to symmetrically map and evaluate different sections of a large tank without requiring constant manual repositioning by an operator. Modifying the probe design in this manner represents a substitution of applying a known mobility technique to a known testing apparatus, yielding the predictable variation of a functional, mobile tank evaluation system capable of autonomously inspecting multiple locations (KSR).
Regarding dependent claim 3, May, teaches:
The method of claim 1 (Fig. 4; [Abstract], [0004], & [0018]), further comprising creating eddy currents by causing an electrical current to be supplied to the probe ([0018]: teaches supplying an electrical current to the probe/coil to initiate the PEC process, corroborated by Hardy: ([0042]))
May, is silent in regard to:
and causing the electrical current to be cut-off from the probe.
However, Hardy, further teaches:
and causing the electrical current to be cut-off from the probe ([0042]-[0044]: teaches cutting off the electrical current from the tester coil to trigger the magnetic variation that creates the eddy currents in the object).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to create eddy currents by supplying an electrical current to the probe and subsequently cutting off, as taught by Hardy, in the PEC method of May, according to known methods. The motivation to combine these teachings is that the “cut-off” phase is the required physical mechanism to produce the sharp magnetic field variation necessary to induce the transient eddy currents into the test object. A POSITA would operate May’s pulse generator in this manner, as it defines the standard and necessary operation of a PEC testing device, combined with Hardy’s “cut-off” phase, and yield predictable results (KSR).
Regarding dependent claim 4, May, teaches:
The method of claim 3 (Fig. 4; [Abstract], 0004], [0014], & [0023]),
May, is silent in regard to:
further comprising calculating the metal loss output measurements based at least in part on the eddy currents.
However, May, Hardy, further teaches:
The Examiner is combining May’s capturing of eddy current response and mathematical calculation of the thickness/loss of the metal based on that response with Hardy’s analysis of the eddy current signal to calculate “wall loss.”
further comprising calculating the metal loss output measurements based at least in part on the eddy currents ( [0001]-[0002] & [0034]-[0035]: teaches analyzing the eddy current signal to calculate “wall loss”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to calculate metal loss output measurements based on the eddy currents, as taught by May and Hardy, according to known methods, because determining wall/metal loss is the fundamental, well-known purpose of utilizing Pulsed Eddy Current testing on pipes and tanks. A POSITA would configure the signal analyzer to output the thickness difference as a “metal loss” measurement to inform the operator of corrosion or structural degradation, thus yielding predictable results (KSR).
Regarding dependent claim 5, May, teaches:
The method of claim 1 (Fig. 4; [Abstract], [0003]-[0004], & [0018]),
May, is silent in regard to:
wherein the substantially metal pipe or substantially metal tank comprises a ferrous material.
However, Hardy, further teaches:
wherein the substantially metal pipe or substantially metal tank comprises a ferrous material [0086]: provides an example where the electrically conductive object being inspected via the PEC method is carbon steel, a ferrous material).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention that the pipe or tank of the combined May, Hardy, and Atherton system comprises a ferrous material, because Hardy provides a working example of inspecting a “carbon steel” object, and Atherton ([0003] & [0037]) discusses testing “ferromagnetic” and “steel pipes”, according to known methods. May establishes that the metal object subjected to the pulsed eddy current testing is a container or pipe constructed of steel. Steel is an alloy and universally recognized as a ferrous material. The motivation to utilize a ferrous material for the pipe or tank is simply the intended real-world application of assessing structural degradation, wall loss, and corrosion in standard industrial steel pipelines and containers, yielding predictable results (KSR).
Regarding dependent claim 6, May, teaches:
The method of claim 1 (Figs. 1 & 4; [Abstract], [0004], [0014], [0018]-[0019], & [0023]),
May, is silent in regard to:
wherein the PEC test results indicate an estimated average thickness of the substantially metal pipe or substantially metal tank at the location.
However, Denenberg, further teaches:
wherein the PEC test results indicate an estimated average thickness of the substantially metal pipe or substantially metal tank at the location (Denenberg: Figs. 53 & 54; [0030], [0056], [0058]-[0059], [0067], [0120], [0235]-[0236], [0302], [0353], [0402], [0426], [0436], [0439], [0441]-[0443], [0448], [0450]-[0451], [0512], [0516]: May provides the base teaching for outputting PEC thickness measurements, Denenberg teaches that the PEC device calculates and outputs an estimated average of the wall thickness bounded by the spatial location (footprint) of the sensor array).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the thickness output of May to include an estimated average of the thickness at the location as taught by Denenberg and corroborated by Vaganay. May discloses outputting PEC test results regarding wall thickness. Denenberg teaches processing PEC sensor data to calculate an “average thickness response” or “averaged wall thickness measurements” within the spatial footprint of each sensor element. The benefit gained from this modification is improved structural evaluation, as averaging the thickness response across the sensor footprint would mitigate anomalous signals and provide a stable, representative measurement of the metal loss. Applying standard mathematical averaging to eddy current thickness data is a known technique to improve similar devices, yielding the predictable variation of a reliable metal loss inspection system (KSR).
Regarding dependent claim 7, May, teaches:
The method of claim 1 (Figs. 1 & 4; [Abstract], [0004], [0014], [0017]-[0019], & [0023]),
May, is silent in regard to:
wherein outputting is to one or both of a storage device and a user interface.
However, Atherton, further teaches:
wherein the outputting is to one or both of a storage device and a user interface ([0031]: provides secondary support listing various types of storage devices used to record the eddy current data).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to output the data to a user interface and/or storage device as taught by May and Atherton, according to known methods. The motivation to do so is because an operator would either immediately view the test results to identify pipeline degradation or store the data for subsequent analytical review. May discloses outputting the calculated properties (results) to display 26 (user interface) and/or saving them to memory 25 (storage device) ([0017] & [0019]). Atherton teaches the standard industry practice of outputting and storing the data on hard drives, disks, or solid-state memories. The combination of prior art teachings is a combination of known elements and/or methods to improve the processing/outputting of results to a user, for ease of interpretation, yielding predictable results (KSR).
Regarding dependent claim 8, May, teaches:
The method of claim 1 (Figs. 1 & 4; [Abstract], [0004], [0014], [0018]-[0019], & [0023]),
May, is silent in regard to:
wherein the PEC results are expressed as a percentage of thickness of a wall of the substantially metal pipe or substantially metal tank relative to a nominal thickness.
However, Vaganay, further teaches:
wherein the PEC results are expressed as a percentage of thickness of a wall of the substantially metal pipe or substantially metal tank relative to a nominal thickness (Fig. 13; [0257]-[0258]: teaches processing the PEC measurements and expressing the PEC results as a percentage that compares the measured wall thickness to the nominal/original plate thickness of the tank. Fig. 13 further illustrates the exact percentage output on a user interface).
PNG
media_image3.png
818
893
media_image3.png
Greyscale
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the thickness output of the PEC testing method of May, to express the results as a percentage relative to a nominal thickness, as taught by Vaganay, according to known methods. May discloses outputting PEC test results regarding wall thickness. Vaganay teaches outputting the PEC test results as a percentage by comparing the measured plate thickness to the nominal plate thickness to visually indicate the remaining wall thickness. The motivation to combine is provided by Vaganay, formatting the data as a percentage of the nominal thickness allows an operator to quickly configure display settings (e.g., color-coded heat maps) to easily identify specific regions that have a high risk of leakage due to severe wall loss (Vaganay: [0257]-[0259]). The benefit of this gained modification is improved evaluation, presenting the data as a percentage of nominal thickness, allowing human operators to identify high-ris corrosion zones without having to manually calculate the material loss. Applying standard mathematical ratios to express sensor thickness data as a percentage of a baseline is a known technique to improve similar devices, yielding the predictable variation of an intuitive and reliable metal loss inspection display (KSR).
Regarding independent claim 9, May, teaches:
A system for pulsed eddy current (PEC) testing, the system comprising (Fig. 1; [0016] & [0019]-[0020]):
a PEC tester configured to collect a plurality of metal loss output measurements ([0003]& [0016]: teaches a PEC array probe deployed on a steel (ferrous) container or pipe to measure metal loss);
a processing system comprising (Fig. 1; [0005], [0016]-[0017], [0019]-[0020], [0024]-[0025], [Claim 13], [Claim 23], & [Claim 24]):
a memory comprising computer readable instructions ([0017], [0019], [0021], [0027], & [Claim 23]); and
a processing device for executing the computer readable instructions, the computer readable instructions controlling the processing device to perform operations comprising (Fig. 1; [0005], 0016]-[0017], [0019]-[0021], [0024]-[0025], [0027], [Claim 13], [Claim 23], & [Claim 24]: teaches a processing system, with a memory that stores computer-readable instructions/stored programs to execute operations on the collected PEC data):
receiving metal loss output measurements (Fig. 1; [0003] & [0014]-[0019]: teaches the computer/processing system receiving the raw measurements from the PEC tester; thickness/metal loss based on the eddy current response);
May, is silent in regard to:
at various locations of a substantially metal pipe or substantially metal tank made up of a ferrous material; wherein one or more energized high voltage cables are located within the substantially metal pipe or substantially metal tank; and
generating compensated metal loss output measurements to compensate for errors in the metal loss output measurements caused by the energized high voltage cables; and
However, Vaganay, further teaches:
at various locations of a substantially metal pipe or substantially metal tank made up of a ferrous material ([0004], [0084], [0086], [0108], [0118], [0129]-[0130], [0133]-[0134], [0142], [0146]-[0148], [0150], [0195], [0202], [0237], [0239], [0248]-[0249], [0251], [0253]-[0254], [0260], [0263]-[0264], [0274], [0286]-[0288], [0291]-[0292], [0294], [0301], [0314], [0316], & [0333]-[0335]: teaches configuring the testing system to move and collect measurements at various locations, areas along a dive plan),
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the testing system of May to include a mobile PEC tester evaluating tanks containing internal cables as taught by Vaganay. May discloses a system for pulsed eddy current testing for metal loss on steel tanks. Vaganay teaches a tank inspection system where a vehicle moves along a traveling path to measure areas at various locations while a cable is deployed and routed directly within the fluid-filled tank. The reason to combine these references is to improve inspection efficiency by allowing a continuous, tethered system to autonomously evaluate multiple internal locations without draining the tank. This combination represents a substitution of applying a mobile inspection deployment technique to a known testing apparatus, yielding the predictable variation of a functional internal tank evaluation system (KSR).
However, Ona, further teaches:
wherein one or more energized high voltage cables are located within the substantially metal pipe or substantially metal tank ([0022] & [0047]: establishes that steel pipes house energized high voltage cables 138kV internally); and
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply the PEC testing system of May and Vaganay to the steel pipe environment containing energized high voltage cables as taught by Ona. May and Vaganay ([0146]-[0148] & [0150]) provide a testing system evaluating tanks with internal cables. Ona discloses a power transmission infrastructure where three-phase alternating current transmission cables carrying energized high voltages (e.g., 138 kV) are inserted directly inside a steel pipe. The motivation to combine these references is to expand the utility of the PEC testing system of May and Vaganay to the steel pipe environment containing energized high voltage cables as taught by Ona and to ensure the structural integrity of high-capacity power transmission pipes. This is a substitution of applying a known testing system to a known structural environment, arriving at the predictable variation of a system monitoring metal loss in high voltage pipe enclosures (KSR).
However, Denenberg, further teaches:
generating compensated metal loss output measurements to compensate for errors in the metal loss output measurements caused by the energized high voltage cables (Hardy: [0063]: discloses the probe and the presence of a parasitic external magnetic field 530, provides the hardware cancellation of parasitic magnetic noise; Atherton: [0027]-[0029]: teaches the necessity of compensating for power cable interference, correcting errors from power cables; Denenberg: [0220], [0222], [0365]-[0371], [0373]-[0374], [0379], [0381]-[0382]: teaches the processing device utilizing a calibration module to algorithmically generate a calibrated, compensated signal to correct for parasitic coupling errors); and
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to configure the processing system of the prior combinations to recognize that the high voltage cables introduce errors as taught by Atherton, and incorporate the hardware cancellation of Hardy, along with the computational calibration instructions of Denenberg, to generate outputted compensated measurements. The prior combination provides a PEC testing system for pipes or tanks containing internal high voltage cables. Atherton teaches that proximity to power lines or cables act as a source of electromagnetic interference altering responses and requiring calculated corrections. Hardy discloses hardware compensation using dual-purpose coils in an antiparallel configuration to cancel out parasitic external magnetic fields. Denenberg teaches a processing system comprising a Calibration Module 2101 that execute computer-readable instructions to mathematically generate compensated output measurements by removing Class 2 parasitic coupling errors by induced external magnetic fields. The benefit gained by this combination is the improved accuracy of the thickness measurements physically rejecting external magnetic interference from nearby cables to digital processing and resolving remaining dynamic errors algorithmically. Implementing these integrated signal corrections is a known technique to improve similar devices, resulting in the predictable variation of a compensated, reliable and accurate, metal loss measurement system (KSR).
May, in combination with Vaganay, are silent in regard to:
outputting the compensated metal loss output measurements as PEC test results.
However, Denenberg, further teaches:
outputting the compensated metal loss output measurements as PEC test results ([0006]-[0007], [0012], [0023]-[0024], [0096], [0118], [0129], [0185], [0187]-[0188], [0191], [0193], [0196], [0201]-[0202], [0208], [0212]-[0215], [0220], [0222], [0226], [0233], [0237], [0302], [0353], [0367]-[0369], [0384], [0393]-[0397], [0399], [0404], [0406], [0410], [0415], [0417], [0426], [0442], [0509], [0512], [0522], [Claim 29]: teaches outputting the finalized, compensated testing measurements to a display, memory, or assessment module).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to program the processing device of the prior combination with Denenberg’s computational calibration instructions to fully generate compensated output measurements. The previous references provide hardware-based noise cancellation. Denenberg teaches a processing system comprising a Calibration Module 2101 that executes computer readable instructions to mathematically remove Class 2 parasitic coupling errors induced in the sensor wiring by external magnetic fields to output calibrated, compensated impedance data. The motivation for this combination is to further improve measurement accuracy and resolve dynamic errors from energized high voltage cables that hardware cancellation may miss. Implementing this algorithmic correction is a known technique to improve similar devices by applying standard digital signal processing via a computer, resulting in the predictable variation of a compensated, reliable metal loss measurement system (KSR).
Regarding dependent claim 10, May, teaches:
The system of claim 9 (Fig. 1; [0016]),
May, is silent in regard to:
wherein the operations further comprise controlling the movement of the PEC tester to another location on the substantially metal pipe or substantially metal tank.
However, Vaganay, further teaches:
The Examiner is combining May in view of Vaganay by implementing the base processing system utilized for eddy current testing of May ([0005] & [0016]-[0018]) with the moving inspection vehicle of Vaganay.
wherein the operations further comprise controlling the movement of the PEC tester to another location on the substantially metal pipe or substantially metal tank ([0005]-[0006], [0023], [0302], [0324], [0340], & [0342]-[0343]: teaches a control unit performing operations that comprise controlling the movement of an inspection vehicle (which houses the inspection probe/tester) from a first position to a second position (another location) within the tank to conduct further testing).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the processing operations of the PEC system of May to include controlling the movement of the PEC tester to another location as taught by Vaganay. May discloses a processing system for pulsed eddy current (PEC) testing on metal objects. Vaganay teaches an internal tank inspection system comprising a processing device/control unit performing operations that include commanding a propeller to move the vehicle, along with its onboard PEC tester, from a first position to a second position within the tank. The reason to combine these references is to improve inspection efficiency by allowing an automated system to navigate and evaluate different sections of a large infrastructure without requiring manual repositioning. Implementing mobility control into the processing operations represents a substitution of a known mobility technique to a known testing apparatus, yielding the predictable variation of a functional, mobile tank evaluation system capable of autonomously inspecting multiple locations (KSR).
Regarding dependent claim 11, May, teaches:
The system of claim 9 (Fig. 1; [0016]),
May, is silent in regard to:
wherein the operations further comprise creating eddy currents by causing an electrical current to be supplied to the PEC tester and causing the electrical current to be cut-off from the PEC tester.
However, Hardy, further teaches:
wherein the operations further comprise creating eddy currents by causing an electrical current to be supplied to the PEC tester ([0035] & [0042]: teaches supplying an electrical current to the PEC probe’s coil during a transmission phase to build up the magnetic field) and causing the electrical current to be cut-off from the PEC tester ([0042]-[0044]: teaches cutting off the electrical current from the tester coil to trigger the magnetic variation that creates the eddy currents in the object).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the pulsed eddy current testing system of May to incorporate the specific electrical current supply and cut-off operations taught by Hardy, according to known methods. The motivation for this modification is to implement a reliable and optimized method for generated transient magnetic fields within the PEC inspection system. A POSITA would recognize that to successfully execute the PEC testing taught by May, the system requires a specific electrical modulation scheme to induce the eddy currents. Incorporating Hardy’s teaching of supplying and then abruptly cutting off the current provides the electromagnetic transition necessary to induce and subsequently measure the decaying eddy currents. Combining these references represents the application of a known technique (Hardy’s current modulation phases for PEC) to a known system (May’s PEC inspection device) to yield the predictable result of measuring wall thickness and corrosion in industrial structures (KSR).
Regarding dependent claim 12, May, teaches:
The system of claim 11 (Fig. 1; [0003], [0016], & [0023]),
May, is silent in regard to:
wherein the operations further comprise calculating the metal loss output measurements based at least in part on the eddy currents (Disclosed in combination.
However, Hardy, further teaches:
The Examiner is combining May in view of Hardy by implementing May’s capturing of eddy current response and mathematical calculation of the thickness/loss of the metal ([0003] & [0023]) with Hardy’s calculated “wall loss.”
wherein the operations further comprise calculating the metal loss output measurements based at least in part on the eddy currents ([0001]-[0002] & [0034]-[0035]: describes an analyzer that calculates “wall loss” (metal loss) by applying algorithms to the received eddy current signal).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to calculate metal loss output measurements based on the eddy currents, as taught by May and Hardy, according to known methods, because determining wall/metal loss is the fundamental, well-known purpose of utilizing Pulsed Eddy Current testing on pipes and tanks. A POSITA would configure the signal analyzer to output the thickness difference as a “metal loss” measurement to inform the operator of corrosion or structural degradation, thus yielding predictable results (KSR).
Regarding dependent claim 13, May, teaches:
The system of claim 9 (Figs. 1 & 4; [Abstract], [0003]-[0004], [0014], [0016], [0018]-[0019], & [0023]),
May, is silent in regard to:
wherein the substantially metal pipe or substantially metal tank comprises a ferrous material.
However, Hardy, further teaches:
wherein the substantially metal pipe or substantially metal tank comprises a ferrous material ([0086]: provides an example where the electrically conductive object being inspected via the PEC method is carbon steel, a ferrous material).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention that the pipe or tank of the combined May, Hardy, and Atherton system comprises a ferrous material, because Hardy provides a working example of inspecting a “carbon steel” object, and Atherton ([0003] & [0037]) discusses testing “ferromagnetic” and “steel pipes”, according to known methods. May establishes that the metal object subjected to the pulsed eddy current testing is a container or pipe constructed of steel ([0003] & [0018]). Steel is universally recognized as a ferrous material. The motivation to utilize a ferrous material for the pink or tank is simply the intended real-world application of assessing structural degradation, wall loss, and corrosion in standard industrial steel pipelines and containers, yielding predictable results (KSR).
Regarding dependent claim 14, May, teaches:
The system of claim 9 (Figs. 1 & 4; [Abstract], [0004], [0016], [0018]-[0019], & [0023]),
May, is silent in regard to:
wherein the PEC test results indicate an estimated average thickness of the substantially metal pipe or substantially metal tank at the location.
However, Denenberg, further teaches:
wherein the PEC test results indicate an estimated average thickness of the substantially metal pipe or substantially metal tank at the location (Figs. 53 & 54; [0030], [0056], [0058]-[0059], [0067], [0120], [0235]-[0236], [0302], [0353], [0402], [0426], [0436], [0439], [0441]-[0443], [0448], [0450]-[0451], [0512], [0516]: teaches that the PEC device calculates and outputs an estimated average of the wall thickness bounded by the spatial location (footprint) of the sensor array).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the thickness output of May to include an estimated average of the thickness at the location as taught by Denenberg and corroborated by Vaganay ([0235], [0264], & [0329]). May discloses a processing system for outputting PEC test results regarding wall thickness. Denenberg teaches processing PEC sensor data to calculate an “average thickness response” or “averaged wall thickness measurements” within the spatial footprint of each sensor element. The benefit gained from this modification is improved structural evaluation, as averaging the thickness response across the sensor footprint would mitigate anomalous signals and provide a stable, representative measurement of the metal loss. Applying standard mathematical averaging to eddy current thickness data evaluated by a processing system is a known technique to improve similar devices, yielding the predictable variation of a reliable metal loss inspection system (KSR).
Regarding dependent claim 15, May, teaches:
The system of claim 9 (Fig. 1; [0016]),
May, is silent in regard to:
wherein the outputting is to one or both of a storage device and a user interface.
However, Atherton, further teaches:
The Examiner is combining May in view of Atherton by implementing memory 25 that corresponds to the “storage device” and display26/monitor26 corresponds to the user interface of May (Fig. 1; [0017] & [0019]) with Atherton’s additional types of storage devices.
wherein the outputting is to one or both of a storage device and a user interface ([0031]: provides secondary support listing various types of storage devices used to record the eddy current data).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to output the data to a user interface and/or storage device as taught by May and Atherton, according to known methods. The motivation to do so is because an operator would either immediately view the test results to identify pipeline degradation or store the data for subsequent analytical review. May discloses outputting the calculated properties (results) to display 26 (user interface) and/or saving them to memory 25 (storage device). Atherton teaches the standard industry practice of outputting and storing the data on hard drives, disks, or solid-state memories. The combination of prior art teachings is a combination of known elements and/or systems and/or methods to improve the processing/outputting of results to a user, for ease of interpretation, yielding predictable results (KSR).
Regarding dependent claim 16, May, teaches:
The system of claim 9 (Fig. 1; [0016] & [0019]: provides the base teaching for a processing system obtaining and outputting PEC thickness measurements),
May, is silent in regard to:
wherein the PEC results are expressed as a percentage of thickness of a wall of the substantially metal pipe or substantially metal tank relative to a nominal thickness.
However, Vaganay, further teaches:
wherein the PEC results are expressed as a percentage of thickness of a wall of the substantially metal pipe or substantially metal tank relative to a nominal thickness (Fig. 13; [0257]-[0258]: teaches expressing the PEC measurements as a percentage relative to the nominal/original thickness of the wall. Fig. 13 further illustrates the exact percentage output on a user interface).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the processing system’s output of May to express the test results as a percentage of the thickness relative to a nominal thickness as taught, as taught by Vaganay, according to known methods. May discloses a processing system for outputting PEC test results regarding wall thickness. Vaganay teaches configuring the processing system to output the PEC test results as a percentage by comparing the measured plate thickness to the nominal plate thickness to visually indicate the remaining wall thickness. The benefit of this modification is improved evaluation efficiency, presenting the data as a percentage of a nominal thickness, allowing human operators to identify high-risk corrosion zones without having to manually calculate the material loss. Applying standard mathematical ratios to express sensor thickness data as a percentage of a baseline is a known technique to improve similar devices, yielding the predictable variation of an intuitive and reliable metal loss inspection system display (KSR).
Claims 17 & 20 are rejected under 35 U.S.C. 103 as being unpatentable over Koenig et al. (US 2016/0290966 A1, Pub. Date Oct. 6, 2016, hereinafter, Koenig), in view of May, in view of Vaganay, in view of Denenberg, and further in view of Fouda et al. (US 2023/0213681 A1, Fil. Date Jan. 3, 2022, hereinafter, Fouda).
Regarding independent claim 17, Koenig, teaches:
A machine learning system, comprising ([0046], [0061], [0073], & [Claim 46]: establishes the fundamental computing system that utilizes machine learning algorithms for PEC inspection):
a memory comprising computer readable instructions ([0046]-[0047], [0050]-[0052] & [Claim 46]: teaches hardware components (processor/processing device and memory) required to store and execute the computer readable instructions to perform the system operations); and
a processing device for executing the computer readable instructions, the computer readable instructions controlling the processing device to perform operations comprising ([0032], [0046]-[0047], [0050]-[0052], [0064], & [Claim 46]):
preprocessing the training data by performing feature extraction on the PEC measurements, data normalization, and scaling ([0007], [0014], [0032], [0036], [0046]-[0047], [0051], [0062], [0064], [0071]-[0073], [Claim 36], [Claim 39], [Claim 40], [Claim 41], [Claim 44], [Claim 45], [Claim 46], [Claim 49] & [Claim 50]: discloses preprocessing steps: data normalization, feature extraction, and scaling on the PEC measurements); and
generating a trained machine learning model using results of the preprocessing of the training data, the trained machine learning model taking as input at least meat loss output measurements from a PEC tester and generated compensated metal loss output measurements ([0007], [0014], [0029]-[0032], [0036], [0041]-[0042], [0046]-[0048], [0051]-[0052], [0062]-[0064], [0073]-[0074], [Claim 15], [Claim 16], [Claim 17], [Claim 36], [Claim 37], [Claim 38], [Claim 39], [Claim 40], [Claim 41], [Claim 42], [Claim 43], [Claim 44], [Claim 45], [Claim 46], [Claim 47], [Claim 48], [Claim 49] & [Claim 50]: teaches generating the trained machine learning model algorithm with the data, using the processed calibration dataset, which then takes the actual field test dataset (metal loss), applying it as input to output and report the lift-off compensated PEC features to measure remaining wall thickness (metal loss)),
Koenig, is silent in regard to:
receiving training data as input, the training data comprising pulsed eddy current (PEC) measurements from field tests, simulated data from finite element modeling simulations, and pipe profiles from field testing;
wherein generating the trained machine learning model comprises performing machine learning-assisted surrogate model training aligned with field-test calibration data by performing an alignment process that begins with local training on the field-test calibration data and refines a relationship between simulated decay times and experimental decay times to minimize a difference between the simulated decay times and the experimental decay times,
However, Denenberg, further teaches:
The Examiner is combining Koenig, in view of Denenberg and Fouda by implementing Koenig’s received training/calibration data from PEC measurements ([Abstract], [0003]-[0004], [0006]-[0007], [0026], [0028]-[0031], [0033], [0045]-[0047], [0053], [0058]-[0059], [0061]-[0063], [0067], [0071]-[0074] & [Claim 46]) and incorporating simulated data from FEM simulations of Denenberg with Fouda’s input casing designs and pipe profiles alongside field testing logs ([0002], [0024]-[0026], [0028]-[0041], [0043], [0046]-[0048], [0052], [0059], [0061], [0063]-[0083], [0085], [0090], [0095], [0098]-[0103], [0105], [Claim 4], [Claim 9], [Claim 12], [Claim 13], [Claim 14], [Claim 15], [Claim 16], & [Claim 21])
receiving training data as input, the training data comprising pulsed eddy current (PEC) measurements from field tests, simulated data from finite element modeling simulations, and pipe profiles from field testing ([Abstract], [0014], [0024]-[0025], [0027], [0029], [0032]-[0037], [0039]-[0040], [0044], [0048]-[0049], [0055], [0059], [0067]-[0068], [0078], [0080], [0094], [0096], [0098], [0106]-[0110], [0203]-[0204], [0207]-[0217], [0222]-[0226], [0230], [0233], [0235]-[0236], [0301], [0378], [0386], [0397], [0399], [0404], [0406], [0410]-[0412], [0415]-[0416], [0422], [0424], [0427], [0429], [0436]-[0437], [0439], [0443], [0461], [0466], [0481], [0504], [0512], [0522], [0528]-[0529], & [Claim 11]: teaches incorporating simulated data from FEM simulations);
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the machine learning system of Koenig to incorporate the FEM simulated data of Denenberg, and the profile-based surrogate model alignment and double dipping pattern identification of Fouda. Koenig discloses a machine learning system comprising a processing device and memory that generates a trained machine learning model by preprocessing pulsed eddy current (PEC) measurements via extractions, data normalization, and scaling, taking as input metal loss and compensated metal loss output measurements. Denenberg teaches generating simulated data from finite element modeling (FEM) simulations, while Fouda teaches receiving pipe profiles from field testing, identifying patterns in decay time data including double dipping to adjust the model, and performing machine learning-assisted surrogate model training aligned with field-test calibration data that refines a relationship and minimizes a difference between synthetic (simulated) and measured (experimental) decay time responses. The benefit gained by this combination is improved efficiency and accuracy of the machine learning model by leveraging robust simulated datasets to supplement physical calibration samples, while eliminating false metal loss readings caused by complex structural artifacts during automated inspections. This combination represents the substitution of known algorithmic constraint and data modeling techniques to improve similar defect detection devices, yielding the predictable variation of an accurate evaluation model that aligns simulated and experimental decay times (KSR).
However, Vaganay, further teaches:
The Examiner is combining Vaganay in view of Fouda by implementing Vaganay’s evaluating the relationship between measured/experimental decay rates and calibration/simulated decay rates to Fouda’s surrogate model process and alignment optimization process ([Abstract], [0002], [0024], [0030]-[0032], [0035]-[0036], [0040], [0046], [0048], [0061], [0067]-[0070], [0073]-[0076], [0078]-[0085], [0087], [0091], [0094]-[0096], [0100]-[0103], [0105]-[0106], [Claim 1], [Claim 5], [Claim 8], [Claim 9], [Claim 10], [Claim 14], [Claim 15], [Claim 16], [Claim 21]: teaches the surrogate model process (replacing numerical forward modeling with an ML model) and the alignment optimization process that minimizes the difference (mismatch) between the synthetic/simulated models and the field-test measurements), further combined with Koenig’s machine learning system and Denenberg’s predicting sensor responses.
wherein generating the trained machine learning model comprises performing machine learning-assisted surrogate model training aligned with field-test calibration data by performing an alignment process that begins with local training on the field-test calibration data and refines a relationship between simulated decay times and experimental decay times to minimize a difference between the simulated decay times and the experimental decay times ([0014], [0021], [0133], [0154], [0162], [0164], [0166]-[0169], [0172], [0174]-[0178], [0204], [0238]-[0239], [0241], [0243]-[0244], [0249], [0255], [0260]-[0261], [0285], [0320], [0335], [0344]-[0345]: teaches evaluating the relationship between measured/experimental decay rates and calibration/simulated decay rates),
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the machine learning training method of Koenig to incorporate the experimental decay rate comparisons of Vaganay and the FEM simulations of Denenberg. Koenig discloses a machine learning system trained on PEC calibration data. Vaganay teaches comparing experimental eddy current decay rates measured during inspection against calibration decay rates to determine thickness. Denenberg teaches predicting sensor responses using FEM simulated data. The benefit gained by this combination is improved efficiency and accuracy of the machine learning model by providing simulated datasets to supplement physical calibration samples, therefore, preventing the under sizing of defects. This combination represents the substitution of known data modeling techniques to improve similar defect detection devices, yielding predictable results in accurately mapping simulated decay times to experimental decay times (KSR).
Koenig, in combination with Vaganay, and Denenberg, are silent in regard to:
and further comprises identifying patterns in decay time data, including double dipping to adjust the trained machine learning model.
However, Fouda, further teaches:
and further comprises identifying patterns in decay time data, including double dipping to adjust the trained machine learning model ([0042]-[0043], [0045], & [0085]:teaches identifying anomalous patterns in the data, noting that “double dip” indications complicate interpretation, and utilizes machine learning models to adjust and handle these complex signal behaviors to increase consistency and repeatability).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply the profile-based alignment, surrogate machine learning model training, and double dipping pattern identification taught by Fouda to the machine learning training method of the prior combination. Koenig, Vaganay, and Denenberg provide a machine learning system trained on FEM data and decay rates. Fouda teaches an inversion software system that incorporates casing designs or pipe profiles, identifies signal complications like “double dip” indications, and performs surrogate model training by replacing computationally expensive numerical forward modeling calculations with machine learning models that minimize a mismatch between synthetic models and measured field-test data. The problem being solved is the elimination of false metal loss readings caused by structural artifacts during automated inspections while reducing the computational load of the system. This combination constitutes a predictable variation of known algorithmic constraint techniques to improve similar devices, yielding an accurate evaluation model capable of adjusting for complex decay time patterns like double dipping (KSR).
Regarding dependent claim 20, Koenig, teaches:
The machine learning system of claim 17 ([0046], [0061], [0073], & [Claim 46]: established the ML system), wherein generating the trained machine learning model comprises ([[0046], [0061], [0073], & [Claim 46]: establishes the generation of the trained ML model)
using additional field test data ([0073] & [Claim 46]: teaches acquiring new signals from physical calibration samples in the field to use as training data).
Koenig, is silent in regard to:
fine tuning the trained machine learning model
However, May, further teaches:
fine tuning the trained machine learning model ([0015] & [0026]-[0029]: updates a baseline simulation model with new empirical calibration data to correct for field errors is the functional equivalent of fine-tuning the model)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to generate the trained machine learning model of Koenig and May by fine-tuning a baseline model using additional field test data, according to known methods. A POSITA would be motivated to utilize the calibration steps taught by Koenig (acquiring a PEC signal on a physical calibration sample) not just to build a model, but to update, adjust, or “fine-tune” the weights and parameters of the existing baseline simulation model. Applying additional field test data (Koenig’s physical calibration samples) to adjust an already trained machine learning model (May’s simulated transfer function) is a standard machine learning practice designed to yield the predictable result of localized, accurate wall thickness measurements that compensate for specific field conditions (KSR).
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Koenig, in view of May, in view of Vaganay, in view of Denenberg, in view of Fouda, and further in view of Hardy.
Regarding dependent claim 18, Koenig, teaches:
The machine learning system of claim 17 ([0046], [0061], [0073], & [Claim 46]: established the ML system),
Koenig, is silent in regard to:
wherein generating the trained machine learning model comprises mapping an artificial intelligence-based surrogate model relative permeability
to features extracted from the PEC measurements
However, May, further teaches:
The Examiner is combining Koenig in view of May by implementing Koenig’s feature extraction ([0073] & [Claim 46]) into May’s mathematical features.
wherein generating the trained machine learning model comprises mapping ([0015] & [0026]-[0029]: teaches building the model by mapping measurement inputs to simulated object properties) an artificial intelligence-based surrogate model ([0015] & [0026]-[0029]: creates surrogate model by training an empirical transfer function (multivariate regression, an AI/ML technique) to approximate finite element computational simulations) relative permeability ([0015]: lists permeability as one of the target properties being mapped by the model)
to features extracted from the PEC measurements ([0015] & [0026]-[0029]: teaches “fit coefficients” which are the mathematical features extracted from the raw PEC signal mapped to the properties).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the machine learning system of Koenig to incorporate the mapping of features to permeability using surrogate modeling techniques taught by May, according to known methods. The motivation for this modification is to improve the accuracy and robustness of the machine learning model’s thickness predictions. A POSITA would recognize that in real-world scenarios, variations in the magnetic permeability of the pipe or tank wall distort the induced eddy currents. By incorporating May’s teaching to map the extracted features relative to permeability, the machine learning system can compensate for the material variations. Combining the references represents the simple combination of known elements (Koenig’s ML pipeline and May’s permeability surrogate mapping) to yield the predictable result of an accurate predictive model that isolates true metal loss from permeability fluctuations (KSR).
Koenig, in combination with May, are silent in regard to:
and magnetic field strengths
However, Hardy, further teaches:
and magnetic field strengths ([0035]: confirms that the PEC sensors are measuring the magnetic fields)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to configure the machine learning system of Koenig and May to map features extracted from the magnetic fields strengths, as detailed by Hardy, according to known methods. The motivation for this modification is to ground the machine learning feature extraction in the physical parameters being measured by the hardware. A POSITA understands that a PEC probe does not directly measure “thickness”; it measures the decay of the produced magnetic field over time. Incorporating Hardy’s teaching ensures the pipeline data is accurately configured to recognize the raw input data, from which the ML features are extracted, are precisely time-varying magnetic field strengths. This is the application of a known physical property of the sensor (Hardy) to a known data processing method (Koenig/May) to achieve the predictable result of linking the raw sensor hardware outputs to the software feature extraction algorithms (KSR).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 HUGO NAVARRO whose telephone number is (571)272-6122. The examiner can normally be reached Monday-Friday 08:30-5:00 pm 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, Eman Alkafawi can be reached at 571-272-4448. 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.
/HUGO NAVARRO/Examiner, Art Unit 2858 August 10, 2026
/A.A/Primary Examiner, Art Unit 2858
Prosecution Insights