DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. 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 Arguments
2. Applicant's arguments received 02/18/2026 have been fully considered but they are not persuasive.
Regarding the claim eligibility, Applicant argues (REMARKS, p.17):
PNG
media_image1.png
396
621
media_image1.png
Greyscale
Examiner respectfully disagrees. As discussed in details in section 5 below, Examiner considers that the limitation “(S2) constructing, by a computer processor in each of the sensor devices, a continuous wavelet transform (CWT) 3D image from the pipeline measurement data and classifying the image using a trained CNN model to identify a pressure surge event;” encompasses mathematical concepts that can be performed in the human mind or by a human using a pen and paper. For example, with the aid of pan and paper, one can build a 3D image from a continuous wavelet transform (CWT) by treating the CWT as a time–frequency representation and then reconstructing it in 3D space. See also Applicant’s Spec., US 20240361202 A1, para. 0229, 0242.
Examiner appreciates Applicant's discussion of and mentions to the October 2019 PEG Update regarding calculating coordinate position data of a "GPS receiver" (p. 7 of the of the October 2019 PEG Update). However, the decision in that case is fact specific and is not analogous to the instant claims of the present application. Specifically, the referenced claim (SiRF Technology, Inc. v. International Trade Commission) is directed to a method for calculating an absolute position of a GPS receiver and an absolute time of reception of satellite signals, where the claimed GPS receiver calculated pseudoranges that estimated the distance from the GPS receiver to a plurality of satellites. The claim is patentable subject matter because it explicitly required the use of a GPS receiver and could not be performed without it. In the instant case, however, the method step of constructing a continuous wavelet transform (CWT) 3D image from the existing pipeline measurement data and classifying the image using a pre-trained CNN model is not necessarily tied to the use of a particular machine or device such as a GPS receiver. Instead, constructing a continuous wavelet transform (CWT) 3D image from existing data can be performed by a human using pan and paper, while a general process of classifying data could be similar to how a human categorize or filter content or information. The recitation of “by a computer processor …” does not negate the mental nature of these limitations because the claim here merely uses the computer processor as a tool to perform the otherwise mental process. See MPEP 2106.04(a)(2). Accordingly, Applicant’s arguments in this regard are not persuasive.
Applicant further argues (REMARKS, p.18):
PNG
media_image2.png
214
611
media_image2.png
Greyscale
Examiner respectfully disagrees. Claim 3 of Example 47 of USPTO’s July 2024 AI Guidance recites a method of using an artificial neural network (ANN) to detect malicious network packets. The courts hold that: The claimed invention reflects its improvement in the technical field of network intrusion detection. Specifically, the claimed steps (d)-(f) provide for improved network security using the information from the detection to enhance security by taking proactive measures to remediate the danger by detecting the source address associated with the potentially malicious packets. In the instant case, unlike the steps (d)-(f) of Claim 3 of the Example 47 (USPTO’s July 17, 2024 Subject Matter Eligibility), the claimed limitations, such as “(S3) transferring, from each sensor device, via a computer network, the determined pressure surge event to a remotely located computer device separate from each of the plurality of sensor devices;” and “(S4) determining, in the remotely located computer device, whether the determined pressure surge event is a pipeline leak through analysis of the determined pressure surge event”, encompass merely a statement of performing data analysis in a remotely located computer device to determine whether the identified pressure surge event is a pipeline leak or not. Even considering the background discussed in the Spec., US 20240361202 A1, para. 0010-0011), it is unclear how said “determining, in the remotely located computer device, whether the determined pressure surge event is a pipeline leak …” would provide for improved leak detection in pipelines using the pressure information classified by the CNN, let along any fact specific features that can be considered to enhance anomaly/leak detection and/or proactive measures to remediate the anomaly/leak. At most, the claim, as a whole, recites an improved abstract idea, but an improved abstract idea is still an abstract idea.
It is held that simply setting forth advantages (i.e. benefits) of use without providing any rational/evidence to how/why the claimed elements amount to significantly more than the judicial exception could be treated as mere instructions to apply the judicial exception on a computer component (MPEP 2106.05(f)), but not qualified for an improvement (i.e. enhancement) in the functioning of a computer or an improvement to another technology or technical field. The key is to show that the claim goes beyond just performing a math calculation/manipulation of existing data and provides a practical application or significant improvement through the use of that math calculation/manipulation, such as feedbacking the output of the math calculation/manipulation to the claimed sensor devices and/or the remotely located computer device to improve the functionality of these devices. See MPEP 2106.04(d)(I) and 2106.05(a). Accordingly, Applicant’s arguments in this regard are not persuasive.
The rest of the Applicant’s arguments with respect to the subject matter eligibility are reliant upon the issues discussed above or have been fully addressed in the detailed response as set forth in sections 4-5 below in this Office action.
Applicant's arguments regarding the 103 rejection have been considered but are moot in view of the new ground(s) of rejection. Detailed response is given in sections 6-8 as set forth below in this Office action.
Claim Objection
3. Claims 51 and 53 are objected to because of the following informalities:
Claim 51 is objected to since it improperly depends on itself.
Claim 53 is a system claim, its dependency on the method claim 41 is improper. It is suggested to change the phrase “as recited in claim 41” into -- as recited in claim 51--.
Appropriate correction is required.
Claim Rejections - 35 USC § 101
4. The following is a quotation of the appropriate paragraphs of 35 U.S.C. 101 that form the basis for the rejections under this section made in this Office action:
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
5. Claims 34-38, 40 and 42-59 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Under the 2019 PEG (now been incorporated into MPEP 2106), the revised procedure for determining whether a claim is "directed to" a judicial exception requires a two-prong inquiry into whether the claim recites: (1) any judicial exceptions, including certain groupings of abstract ideas (i.e., mathematical concepts, certain methods of organizing human interactions such as a fundamental economic practice, or mental processes); and (2) additional elements that integrate the judicial exception into a practical application (see MPEP § 2106.05(a)-(c), (e)-(h)).
Only if a claim (1) recites a judicial exception and (2) does not integrate that exception into a practical application, do we then look to whether the claim: (3) adds a specific limitation beyond the judicial exception that is not "well-understood, routine, conventional" in the field (see MPEP § 2106.0S(d)); or (4) simply appends well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception.
Claims 34-38, 40 and 42-59 describe an abstract idea of determining leaks in a pipeline. Specifically, representative claim 1 recites:
A computer-implemented method to detect leaks in a pipeline utilizing a plurality of sensor devices located adjacent the pipeline, the method comprising:
(S1) capturing, from each of the plurality of sensor devices, pipeline measurement data associated with a fluid flow in the pipeline;
(S2) constructing, by a computer processor in each of the sensor devices, a continuous wavelet transform (CWT) 3D image from the pipeline measurement data and classifying the image using a trained CNN model to identify a pressure surge event;
(S3) transferring, from each sensor device, via a computer network, the determined pressure surge event to a remotely located computer device separate from each of the plurality of sensor devices; and
(S4) determining, in the remotely located computer device, whether the determined pressure surge event is a pipeline leak through analysis of the determined pressure surge event.
The claim limitations in the abstract idea have been highlighted in bold above; the remaining limitations are “additional elements”.
The highlighted portion of the claim constitutes an abstract idea under the 2019 Revised Patent Subject Matter Eligibility Guidance and the additional elements are NOT sufficient to amount to significantly more than the judicial exceptions, as analyzed below:
1. Statutory Category ?
Yes.
Method
2A - Prong 1: Judicial Exception Recited?
Yes.
Under the broadest reasonable interpretation (BRI), the limitation S2 recited in the bolded portion listed above encompasses mathematical concepts, namely a series of calculations leading to one or more numerical results or answers. For example, one can build a 3D image from a continuous wavelet transform (CWT) by treating the CWT as a time–frequency representation and then reconstructing it in 3D space. See also Applicant’s Spec., US 20240361202 A1, para. 0229, 0242. As such, the limitation S2 can be performed in the human mind or with the aid of pen and paper. Note, the courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. See CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011). See also to MPEP 2106.04(a)(2).III
The recitation of “a trained CNN model” does not negate the mental nature of the limitation S2 because the claim here merely uses the “trained CNN model” as a tool to perform the otherwise mental process. The claim does not provide any detail about how the CNN model is trained and/or how the trained CNN model is applied to the captured pipeline measurement data for classifying pipeline pressure measurement images included in the captured pipeline measurement data. In light of the USPTO’s July 2024 Subject Matter Eligibility Examples (e.g., ANN in Example 47 or DNN in Example 48), it is held that merely using machine learning models to perform classifications/predictions that are otherwise abstract does not take the claimed limitation(s) out of the categories of abstract idea.
Under the BRI, the limitation S4 encompasses a mental process, i.e. data recording, manipulation, evaluation and judgment, that can be performed in the human mind using mental steps/critical thinking or by a human using a pen and paper.
Under the BRI, elements such as “pressure surge event”, “pipeline measurement data”, “pipeline pressure measurement images”, etc. amount to merely data characterization which can be viewed as nothing more than an attempt to generally link the use of the judicial exception to the technological field of detecting/determining leaks of a pipeline.
The limitations regarding “a computer processor in each of the sensor devices” and “the remotely located computer device” are all recited at a high level of generality which encompass a general-purpose computer or generic microprocessor. That is, other than reciting a general-purpose computer or generic microprocessor used as a tool to apply the abstract idea, nothing in the bolded portion precludes the limitations S2 and S4 from practically being performed in the mind and/or using a pen and paper. According to the MPEP 2106.04(a)(2), if a claim limitation, under its broadest reasonable interpretation, covers mental processes except for the mention of generic computer components performing computing activities via basic function of the computer, then the claim is likely considered to be directed to an ineligible abstract idea, as it essentially describes a mental process that could be performed by a human without the computer components adding any significant practical application beyond the abstract concept itself.
The bolded portion of claim 1 therefore falls within a combination of the “Mathematical Concepts” and “Mental Process” Groupings of abstract ideas defined by the 2019 PEG.
2A - Prong 2: Integrated into a Practical Application?
No.
The claim as a whole does not integrate the abstract idea into a practical application.
Under the BRI, the limitation S1 reads on merely a process of gathering the data/information necessary for performing the abstract idea. See MPEP 2106.05(g)(3): … that were described as mere data gathering in conjunction with a law of nature or abstract idea. See also Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 13863, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering). Furthermore, the element of “the plurality of sensor devices” is recited at high level of generality. Thus claim 1 would monopolize the abstract idea across a wide range of applications.
Under the BRI, the limitation S3 encompasses an insignificant extra-solution of data output (“transferring”).
None of these additional steps is considered to be qualified for a significant or meaningful limitation that integrates the abstract idea into a practical application. At most, they only generally link the judicial exception to a particular technological environment or field of use.
Further, the pipeline is not specified and neither is the fluid (lots of machines and applications have fluid pipelines). As such, claim 1 would monopolize the algorithm across a wide range of applications.
In general, the claim as a whole does not meet any of the following criteria to integrate the abstract idea into a practical application:
An additional element reflects an improvement in the functioning of a computer, or an improvement to other technology or technical field;
an additional element that applies or uses a judicial exception to effect a particular treatment or prophylaxis for a disease or medical condition;
an additional element implements a judicial exception with, or uses a judicial exception in conjunction with, a particular machine or manufacture that is integral to the claim;
an additional element effects a transformation or reduction of a particular article to a different state or thing; and
an additional element applies or uses the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception.
Various considerations are used to determine whether the additional elements are sufficient to integrate the abstract idea into a practical application. However, in all of these respects, the claim fails to recite additional elements which might possibly integrate the claim into a particular practical application. Instead, based on the above considerations, the claim would tend to monopolize the algorithm across a wide range of applications.
2B: Claim provides an Inventive Concept?
No.
Focusing on what the inventors have invented exactly, it is deemed that the “heart” of the representative claim 1 is directed to an algorithm of identifying a pipeline pressure surge by applying a trained convolutional neural network (CNN) model for classifying pipeline pressure measurement images which encompasses math concepts that can be performed in human mind or with pen and paper. The claim does not recite any additional limitation/element that amounts to significantly more to integrate the math/mental algorithm, i.e. an abstract idea, into a practical application.
Furthermore, techniques of client-side computing or edge-computing and their practices in many industrial fields such as pipeline management are well-known in the art (see discussion of prior art set forth below in this Office action). They do not reflect an “inventive concept” and/or any qualified improvement under MPEP 2106.04(d) and 2106.05(a).
The claim is therefore ineligible under 35 USC 101.
Dependent claims 35-38, 40 and 42-44 inherit attributes of the independent claim 1, but do not add anything which would render the claimed invention a patent eligible application of the abstract idea. These claims merely extend (or narrow) the abstract idea which do not amount for "significantly more" because they merely add details to the algorithm which forms the abstract idea as discussed above.
In particular, it is deemed that the limitations regarding the “Adaptive Neural-Fuzzy Inference System (ANFIS) model” recited in claims 37 and 42-44 align with how the trained ANN was used in Example 47 of the USPTO’s July 2024 Subject Matter Eligibility Examples, which do not amount for "significantly more".
Claims 45-59 are rejected for the same reason as for claims 34-38, 40 and 42-44 set forth above.
Hence claims 34-38, 40 and 42-59 are treated as ineligible subject matter under 35 U.S.C. § 101.
Claim Rejections - 35 USC § 103
6. 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 of this title, 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.
7. Claims 34-35, 38-41, 45-46, 49-50, 54, 57 and 59 are rejected under 35 U.S.C. 103 as being unpatentable over Frackelton et al. (US 11047761 B1) in view of Eurek et al. (JP 2004529433 A, machine translation) and Zhou et al. (CN 109556797 A, machine translation) and Perkins et al. (US 20150205000 A1).
Regarding claims 34, 45 and 54, Frackelton discloses a computer-implemented method, and a system for practicing the method, for detecting leaks in a pipeline utilizing a plurality of sensor devices located adjacent the pipeline (Abstract: “a plurality of low-cost sensors installed multiple locations throughout a fluid system, e.g., throughout a house, to determine the presence of a leak in the fluid system”; see also col. 1, lines 13-20; col. 2, lines 42-46 and 50-56; col. 3, lines 10-15), wherein each sensor device includes: a memory, a processor disposed in communication with the memory, and configured to issue a plurality of computer executable instructions stored in the memory (col. 2, lines 50-55), said method comprising:
capturing, from each of the plurality of sensor devices (i.e., the smart sensor devices deployed at a plurality of sensor sites) located at respective sensor sites adjacent the pipeline, pipeline measurement data associated with a fluid flow in the pipeline (col. 2, lines 51-55);
determining, by a computer processor in each of the sensor devices (col. 2, lines 50-55), pressure surge event by analyzing the captured pipeline measurement data at each sensor site (col. 5, lines 58-67; col. 8, lines 34-51: under the BRI to the claim, Frackelton’s “signal corresponding to the deflection and, therefore, corresponding to the pressure (or a change in pressure) in the cold-water fluid path” encompasses the limitation “pressure surge event”);
transferring, from each sensor device, via a computer network, the determined pressure surge event to a remotely located computer device separate from each of the plurality of sensor devices (Fig. 1; col. 2, lines 26-30 and 42-49; col. 8, lines 39-42: “This signal is used by … (or another processor) to determine the presence of a leak using at least the signal or data extracted from the signal”; see also col. 8, lines 65-67 and col. 11, lines 56-63); and
determining, in the remotely located computer device, whether the determined pressure surge event is a pipeline leak through analysis of the determined pressure surge event (col. 5, line 65 – col. 6, line 10; col. 8, lines 61-67; col. 11, lines 51-58).
Frackelton does not mention explicitly: said step of determining the pressure surge event comprises: constructing, by a computer processor in each of the sensor devices, a continuous wavelet transform (CWT) 3D image from the pipeline measurement data and classifying the image using a trained CNN model to identify/determine the pressure surge event; wherein the analyses of the pressure surge data and the classification with the trained CNN model applied to the captured pipeline measurement data are performed by the computer processor in each of the sensor devices at each sensor site.
Eurek teaches a technique of constructing a pressure measurement image using continuous wavelet transform (CWT) comprising: collecting pressure measurement data from a plurality of pipelines transmitting one or more fluids (Abstract; para. 0005-0008; 0060-0061); processing the pressure measurement data using one or more filtering algorithms (para. 0039); selecting representative data patterns from a windowed time series (para. 0022, 0029, 0032: “The real-time clock reading associated with each digital pressure data point is reassembled into the correct time sequence …”; see also para. 0036, 0064); creating 3D images from the representative data patterns using continuous wavelet transform (CWT) (para. 0064-0065); and classifying the image using a trained neural network model to identify/determine a representative pressure data pattern (para. 0063-0064, 0069-0070, 0073).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Eurek’s teaching of 3D images including the CWT and related data processing algorithm into Frackelton to arrive the claimed invention. Doing so would allow to provide improved reliability and reduced complexity for obtaining training data set of historical pressure data during the training mode (Eurek, para. 0008; Frackelton col. 4, lines 54-59).
The combination of Frackelton/Eurek is silent on: said trained neural network model is a trained convolutional neural network (CNN) model. However, Zhou discloses system and method for detecting pipeline leaks (Abstract), comprising: identifying a specific pipeline pressure event by applying a trained convolutional neural network (CNN) model to pipeline pressure measurement data captured at a plurality of sensor sites for classifying pipeline pressure measurement images on each sensor site (para. 0045: “The upstream and downstream pressure measurement points are node1 and node2”) of the plurality of sensor sites (para. 0009: “the present invention uses a convolutional neural network model to classify pressure images of different leakage apertures”; see also para. 0011, 0045, 0050), the plurality of sensor sites collecting pipeline pressure measurement data (para. 0045-0046); and determining whether the identified pressure event is a pipeline leak using the identified pressure event information (para. 0011, 0028-0029).
Since Eurek teaches the general condition of the neural network model (0069-0070, 0073), in view of Zhou, 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 combination of Frackelton/Eurek with Zhou’s teaching of the CNN model applied to pressure measurement image data for classifying the pressure measurement image data to identify a target pressure event. Doing so would provide higher accuracy and generalization capabilities (e.g., detecting different leak sizes) than conventional detection methods (Zhou, para. 0009, 0011).
Further, Perkins discloses a system/method for in-situ analysis of fluids related to the oil and gas industry (Abstract; para. 0018-0019: “… thereby allowing qualitative and/or quantitative analyses of the substance to occur without having to extract a sample and undertake time-consuming analyses of the sample at an off-site laboratory”; see also para. 0025), comprising: a plurality of sensor devices (i.e., optical computing devices) located adjacent a target substance for monitoring and determining chemical and/or physical properties of the substance (para. 0017-0019); captured substance measurement data using the plurality of sensor devices, and performing discriminant analyses of the captured measurement data by applying a trained neural network model for classifying the measurement data at each sensor site (para. 0025: “This determination may be performed in parallel with the collection of optical measurements in situ. While ICE technology generally enables a near real-time, in situ measurement of a sample substance, qualitative uses of discriminant analysis techniques using ICE technology can infer, for example, a particular chemical grouping based on optical spectroscopic data”; see also para. 0026).
Since Frackelton teaches the general applicability of the sensor’s processor (col. 4, lines 30-31; col. 6, lines 51-54; col. 8, lines 39-42; col. 11, line 63 – col. 12, line 8) and the concept of client-side computing (or edge-computing) is well-known in the art (e.g., Frackelton, col. 11, line 63 – col. 12, line 8), as being motivated by Perkins, 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 combination of Frackelton/Eurek/Zhou to provide each of the sensor device of said plurality of sensor devices with an integrated computational element (ICE) through which sophisticated discriminant analyses of the captured measurement data can be performed by applying a trained neural network model for classifying the measurement data at each sensor site. Doing so would allow, for example, operators to optimize measurement parameters and/or procedures (Perkins, para. 0025). Also, an unknown data sample/event may be classified and/or otherwise quantified without the need to employ a large library of calibrations which can be very time-consuming and expensive to develop (Perkins, para. 0026).
Regarding claims 35 and 46, Frackelton discloses: wherein the determined pressure surge event includes associated timestamps (col. 2, lines 50-54).
Regarding claims 38, 49 and 57, Frackelton discloses: wherein the remotely located computer device is located in a cloud site (Fig. 1; col. 2, lines 24-30 and 42-49; col. 11, lines 56-63).
Regarding claim 39, Frackelton discloses: constructing the pipeline pressure measurement database (col. 2, lines 28-30: “stored data” reads on “database”; see also col. 3, lines 13-16; col. 4, lines 54-55 and 64-67; col. 5, lines 31-35), comprising: collecting pressure measurement data from a plurality of pipelines transmitting one or more fluids (col. 3, lines 13-16; col. 4, lines 54-55 and 64-67; col. 5, lines 31-35); processing the measurement data, and selecting representative data patterns from a windowed time series (col. 2, lines 26-28; col. 4, lines 47-48; col. 5, lines 7-35); assigning the representative data patterns into different classes (e.g., normal vs. abnormal, etc.; see col. 5, lines 7-35).
Frackelton does not mention explicitly: said database is a pipeline pressure measurement image database; said pressure measurement image database is used to train the CNN model applied in each sensor device; wherein constructing the pipeline pressure measurement image database further includes: processing the pressure measurement data using one or more filtering algorithms; creating 3D images from the representative data patterns using continuous wavelet transform (CWT); checking image class assignment of the created 3D images and removing outliers; and storing the created 3D images as measurement images with their class labels.
Eurek teaches a technique of constructing a pressure measurement image database comprising: collecting pressure measurement data from a plurality of pipelines transmitting one or more fluids (Abstract; para. 0005-0008; 0060-0061); processing the pressure measurement data using one or more filtering algorithms (para. 0039); selecting representative data patterns from a windowed time series (para. 0022, 0029, 0032: “The real-time clock reading associated with each digital pressure data point is reassembled into the correct time sequence …”; see also para. 0036, 0064); creating 3D images from the representative data patterns using continuous wavelet transform (CWT) (para. 0064-0065); checking image class assignment of the created 3D images and removing outliers (para. 0068); storing the created 3D images as measurement images with their class labels (para. 0049: “An increase in the relative frequency component of the power spectrum indicates a deterioration of the main factor”; para. 0062: “a signal preprocessor algorithm that separates signal components in pressure data …”; para. 0063: “The signal components are separated by signal processing techniques that identify only other signal characteristics, such as the desired frequency or amplitude, and provide an indication of their identification”; para. 0064, 0069: labels of the “frequency components” or “decomposition levels” reads on the claimed class labels; see also Fig. 12); and applying the constructed pressure measurement image database to train a neural network model (para. 0008, 0036; para. 0056: “Digital pressure data is collected in training mode or time intervals as indicated at 804. … The obtained power spectrum is identified as a training power spectrum at 808 and stored in non-volatile memory 810”; para. 0065: “FIG. 10 is a graph of amplitude versus frequency versus time for a process variable signal, such as reading pressure data from a pressure transmitter”; see also Fig. 14 and related discussion about the sensor signal/data 284). The teaching of Eurek further includes: constructing a continuous wavelet transform (CWT) 3D testing image using windowed data inputs around an anomaly triggering point (para. 0036, 0064); and identifying a representative pressure data pattern by classifying labeled testing data using the trained neural network model (para. 0063-0064, 0068-0069).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Eurek’s teaching of constructing a pressure measurement database including the CWT and related data processing algorithm into the combination of Frackelton/Zhou/Perkins to arrive the claimed invention. Doing so would allow to provide improved reliability and reduced complexity for obtaining training data set of historical pressure data during the training mode (Eurek, para. 0008).
Regarding claims 40, 50 and 59, Frackelton discloses: identifying, in the remotely located computer device, a location of the pipeline leak (col. 14, lines 39-58).
Regarding claim 41, Frackelton discloses: wherein applying the trained neural network model further comprises: receiving the pipeline pressure measurement data from a sensor device (col. 4, line 47 – col. 5, line 10; col. 6, lines 51-55; col. 7, lines 8-24); screening the pipeline pressure measurement data to detect an anomaly triggering point (col. 6, lines 51-67; col. 14, lines 39-58: the location of the leak reads on the claimed an anomaly triggering point); and identifying a pressure surge associated with the anomaly triggering point using the trained neural network model (col. 5, lines 7-35; col. 5, line 44 – col. 6, line 10).
The combination of Frackelton/Zhou/Perkins does not mention explicitly: constructing a continuous wavelet transform (CWT) 3D testing image using windowed data inputs around the anomaly triggering point; and identifying the pressure surge by classifying the testing image using the trained CNN model.
Eurek further teaches: constructing a continuous wavelet transform (CWT) 3D testing image using windowed data inputs around an anomaly triggering point (para. 0036, 0064); and identifying a representative pressure data pattern by classifying labeled testing data using the trained CNN model (para. 0063-0064, 0068-0069).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Eurek’s teaching of CWT and related data processing algorithm into the combination of Frackelton/Zhou/Perkins to arrive the claimed invention. Doing so would allow to provide improved reliability but reduced complexity for obtaining training data set of historical pressure data during the training mode (Eurek, para. 0008).
8. Claims 37, 42, 44, 48, 51, 53, 56 and 58 are rejected under 35 U.S.C. 103 as being unpatentable over Frackelton et al. in view of Eurek et al., Zhou et al and Perkins et al. as applied to claim 34, 45 or 54, further in view of Ardel et al. (US 20230018960 A1).
Regarding claims 37, 48 and 56, the combination of Frackelton/Eurek/Zhou/Perkins does not mention explicitly: wherein determining whether the determined pressure surge event is a pipeline leak includes applying the pressure surge event to an Adaptive Neural-Fuzzy Inference System (ANFIS) model.
Ardel discloses an adaptive neuro-fuzzy inference system (ANFIS) type of machine-learning model (para. 0030, 0039), wherein the ANFIS model is adapted to determine a particular state or condition of an evaluation target (para. 0041-0042, 0044); wherein said particular state or condition is determined by: applying sensor-generated measurement data representative of a state or condition of the evaluation target to the ANFIS model (para. 0043-0046); differentiating the particular state or condition from other similar state or condition of the evaluation target based on the applied measurement data (para. 0055: “ … the classification system 130 may select a particular trained classifier that is trained to classify objects having similar states or conditions”; para. 0058: “Based on the classification generated by the trained classifier 134 (e.g., the first result 154), the classification system 130 may select a particular adaptive neuro-fuzzy inference system that is trained to classify objects having similar states or conditions”; see also para. 0064).
Since Frackelton teaches the general conditions of determining whether the identified pressure surge event is a pipeline leak (col. 5, line 65 – col. 6, line 10; col. 11, lines 51-58), it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Ardel’s ANFIS model into the machine-learning or CNN model in the combination of Frackelton/Eurek/Zhou/Perkins to differentiate the pipeline leak from other pressure surge events, so that the combined output produces an improvement over decisions made merely by the machine-learning or CNN model in the combination of Frackelton/Eurek/Zhou/Perkins (Ardel, para. 0063, 0065).
Regarding claims 42, 51 and 58, Frackelton discloses: a trained machine-learning model that is pipeline specific, and wherein said machine-learning model is trained with recorded historic pressure surge data inputs from one or more of actual pipeline leak events, simulated leak events, and the events associated with pipeline routine operations (col. 4, line 59 – col. 5, line 10; col. 5, lines 58-64; col. 6, lines 2-10; col. 7, lines 41-43).
Frackelton does not mention explicitly: said training is applied to the ANFIS model.
However, the teaching of Ardel includes: training the ANFIS model with recorded historic data inputs from one or more of actual state or condition of said evaluation target and/or the events associated with routine operations of said evaluation target (para. 0026-0037).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Frackelton’s teaching of the pipeline specific machine-learning model and Ardel’s training of the ANFIS model into the CNN model in combination of Frackelton/Eurek/Zhou/Perkins/Ardel such that the trained models are pipeline specific to enable their application to differentiating the pipeline leak from other pressure surges. Doing so would provide an improvement over decisions made by only the Frackelton machine-learning model (Ardel, para. 0063, 0065).
Regarding claims 44 and 53, Frackelton discloses: wherein the recorded historic pressure surge data inputs are calculated from a pair of sensor devices (col. 3, lines 4-9; col. 4, line 59 – col. 5, line 10: “It is contemplated that the exemplary faucet or other smart sensor device …”; see also col. 6, lines 34-36), wherein output from the machine-learning model is a scalar output (col. 4, lines 54-59; col. 6, lines 48-50; col. 7, lines 1-7; see also Fig. 33 and related discussion about the output).
Frackelton does not mention explicitly: said machine-learning model is an ANFIS model. However, Ardel teaches: training an ANFIS model and adapting it to determine a particular state or condition of an evaluation target (para. 0041-0042, 0044). As such the combination of Frackelton/Eurek/Zhou/Perkins/Ardel discussed for claim 42 above renders the claimed invention obvious.
Allowable Subject Matter
9. Claims 36, 43, 47, 52 and 55 would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims and further overcome the rejection under 35 USC 101 as set forth in sections 4-5 above in this Office action.
Reasons for Allowance
10. The following is a statement of reasons for the indication of allowable subject matter:
The primary reason for the allowance of claims 36, 47 and 55 is the inclusion of the claimed limitation: wherein the pressure surge event further includes at least one of: a magnitude of a triggering value (MT) from a simulation output of enhanced filtering, and a sum of a scalogram (SS) of a continuous wavelet transform (CWT). It is this limitation as claimed in the combination recited in independent claim 34 or 45, that has not been found, taught or suggested by the prior art of record which makes claims 36, 47 and 55 distinguish over the prior art.
The primary reason for the allowance of claims 43 and 52 is the inclusion of the claimed limitation: wherein the recorded historic pressure surge data inputs comprise a DT gradient and at least one of a ratio parameter value of a pressure drop (DP) over a distance between the adjacent sensor pair, a simulated change of a flow rate (DV) for the given pressure drop over a distance between the adjacent sensor pair, a magnitude of a triggering value (MT) from a simulation output of enhanced filtering over a distance between the adjacent sensor pair, and a sum of a scalogram (SS) of a continuous wavelet transform (CWT) over a distance between the adjacent sensor pair. It is this limitation as claimed in the combination recited in claim 42 or 51, that has not been found, taught or suggested by the prior art of record which makes claims 43 and 52 distinguish over the prior art.
Conclusion
11. 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 extension fee 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 date of this final action.
Contact information
12. Any inquiry concerning this communication or earlier communications from the examiner should be directed to XIUQIN SUN whose telephone number is (571)272-2280. The examiner can normally be reached 9:30am-6:00pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Shelby A. Turner can be reached on (571) 272-6334. 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.
/X.S/Examiner, Art Unit 2857
/SHELBY A TURNER/Supervisory Patent Examiner, Art Unit 2857
Prosecution Insights