DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections – 35 USC § 112(b)
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.
Claims 1-20 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 pre-AIA the applicant regards as the invention.
Claims 1, 10 and 16 recite "the set of features." This term lacks antecedent basis.
Claim 4 recites the term, "high-sampling rate analog to digital converter." It is unclear what constitutes a "high-sample rate." For the purpose of examination, Examiner interprets the term as a converter using any sampling rate.
Claims 2-9, 11-15 and 17-20 are likewise rejected for failing to cure the deficiencies of their respective parent claims.
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 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.
Claims 1, 2, 7 and 9 are rejected under 35 U.S.C. 103 as being unpatentable over Hettegger (US 2025/0116564) in view of Quy (T. Quy et al., "Real-time Leak Detection for a Gas Pipeline Using a k-NN Classifier and Hybrid AE Features," published Jan. 7, 2021).
Quy was cited in an IDS filed 06/17/2024.
Regarding claim 1, Hettegger teaches a method for detecting passing valves, the method comprising:
acquiring vibrational data from one or more sensors associated with passing valves and non-passing valves ([0184-0185, 0093-0098], the system gathers acoustic emission/vibration sensor data from sensors on a test pipeline/stand for the purpose of generating training data; the sensors may be used, for example, to diagnose whether a valve is leaking or is tight; the data is labeled with such information);
extracting a plurality of features from the vibrational data ([0188, 0108], the system acquires specific data from the acoustic emission sensor data; for example, the system determines that a specific sub-range of frequencies is particularly desirable; also parameters such as the root mean square for the sub-range is obtained; as noted in [0108], particular characteristic numbers are extracted from the sensor data; such data is determined to be more significant).
determining, based on a feature importance criterion, a subset of the plurality of features having more significance than other features of the plurality of features ([0188, 0108], the system acquires specific data from the acoustic emission sensor data; for example, the system determines that a specific sub-range of frequencies is particularly desirable; also parameters such as the root mean square for the sub-range is obtained; as noted in [0108], particular characteristic numbers are extracted from the sensor data; such data is determined to be more significant; see also claim 5 and [0033-0038], a pre-filter may be applied to the acoustic emission sensor signals to obtain desired data based on prefilter criterion e.g., to extract at least one characteristic number, such as the root mean square (RMS) of the signals);
training a machine learning model, where inputs to the machine learning model include the set of features ([0184-0185], the above training data is used to train a machine learning model/algorithm);
detecting that a valve is a passing valve based on the trained machine learning model, where an input to the trained machine learning model includes the subset of features extracted from vibrational data ([0191-0192, 0006, 0007, 0010], claims 1, 15, the trained model is deployed to determine whether a valve is leaking or not).
However, Hettegger does not expressly disclose in response to detecting the passing valve, performing a corrective action to resolve the passing valve.
In the same field of endeavor, Quy teaches in response to detecting the passing valve, performing a corrective action to resolve the passing valve (page 8, 9, the device implementing the model may include an LCD screen, which indicates the outcome of the diagnostic program using the model i.e., indicating whether a leak is detected or not).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to have incorporated in response to detecting the passing valve, performing a corrective action to resolve the passing valve as suggested in Quy into Hettegger because Hettegger and Quy pertain to analogous fields of technology. Both Hettegger and Quy pertain to systems configured to detect leaks in valves for a pipeline by analyzing data from acoustic emission sensors. In both Hettegger and Quy, a machine learning model was used and trained to analyze the data and determine the state of the valve. (See, for example, Quy page 3, which indicates that the model was trained to detect leaks in pipeline valves.) Quy describes a variety of implementation features, such as indicating on a display screen the outcome of the above diagnosis process. It would be desirable to incorporate any such features into Hettegger, to provide additional techniques for enabling the analysis of acoustic emission signals and to inform users of the results of the analysis e.g., see Quy pages 8, 9.
Regarding claim 2, the combination of Hettegger and Quy teaches the invention as claimed in claim 1. The combination of Hettegger and Quy also teaches wherein the corrective action comprises at least one of generating an alert indicating the detection of the passing valve or automatically closing a valve upstream of the detected passing valve (Quy page 8, 9, the device implementing the model may include an LCD screen, which indicates the outcome of the diagnostic program using the model i.e., indicating whether a leak is detected or not).
Regarding claim 7, the combination of Hettegger and Quy teaches the invention as claimed in claim 1. The combination of Hettegger and Quy also teaches wherein extracting the plurality of features from the vibrational data includes determining one or more of a root mean square value, a spectral roll off, a spectral bandwidth, a zero-crossing rate, and Mel-Frequency Cepstral Coefficients (Hettegger [0063, 0068, 0075-0078, 0088], it is known to analyze acoustic emission signals by determining the root mean square (RMS) of the signal).
Regarding claim 9, the combination of Hettegger and Quy teaches the invention as claimed in claim 1. The combination of Hettegger and Quy also teaches
wherein acquiring vibrational data associated with passing valves and non-passing valves comprises:
acquiring, from a testing device, the vibrational data associated with multiple valve types and multiple pipe diameters (Hettegger [0107, 0006-0007, 0109, 0053, 0152], the training data can indicate the valve/pipe size or diameter; see also [0152, 0160], which provides examples where acoustic emission sensor signal samples are associated with a variety of valve/pipe diameters and types).
Claims 3, 10-13 and 16-19 are rejected under 35 U.S.C. 103 as being unpatentable over Hettegger and Quy, as applied in claim 1, and further in view of Prateepasen (A. Prateepasen et al., "Smart portable noninvasive instrument for detection of internal air leakage of a valve using acoustic emission signals," Measurement journal, published Oct. 28, 2010).
Prateepasen was cited in IDS filed 06/17/2024.
Regarding claim 3, the combination of Hettegger and Quy teaches the invention as claimed in claim 1. However, the combination of Hettegger and Quy does not expressly disclose wherein the one or more sensors comprise one or more analog piezoelectric vibrational sensors.
In the same field of endeavor, Prateepasen teaches wherein the one or more sensors comprise one or more analog piezoelectric vibrational sensors (page 380, it is known for an acoustic emission sensor to be made of a PZT material).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to have incorporated wherein the one or more sensors comprise one or more analog piezoelectric vibrational sensors as suggested in Prateepasen into Hettegger and Quy because Hettegger and Prateepasen pertain to analogous fields of technology. Both Hettegger and Prateepasen relate to systems that use vibration/acoustic emission sensors to determine leakage in a valve. In Prateepasen, the vibration sensor can be a PZT sensor. It would be desirable to incorporate this feature into Hettegger so that wide variety of known sensor types may be used e.g., see Prateepasen page 380.
Regarding claim 10, the claim corresponds to claim 3 and is rejected for the same reasons. The combination of Hettegger, Quy and Prateepasen also teaches a system for detecting passing valves, the system comprising:
one or more piezoelectric sensors coupled to a pipe adjacent to a valve (Hettegger Fig. 1, [0140-0142] describes a pipe adjacent to a valve 100; acoustic emission sensors are positioned on the pipe; see also Quy pages 3-4 and Figure 2; Prateepasen page 380 indicates it is known for such sensors to be made of a PZT material);
at least one processor and a memory storing instructions that, when executed by the at least one processor perform operations (inherently, the analysis methods of Hettegger, Quy and Prateepasen are performed using a processor, memory and instructions).
Regarding claim 11, the combination of Hettegger, Quy and Prateepasen teaches the invention as claimed in claim 10. Claim 11 also corresponds to claim 1 and is rejected for the same reasons.
Regarding claim 12, the combination of Hettegger, Quy and Prateepasen teaches the invention as claimed in claim 11. Claim 12 also corresponds to claim 2 and is rejected for the same reasons.
Regarding claim 13, the combination of Hettegger, Quy and Prateepasen teaches the invention as claimed in claim 10. Claim 13 also corresponds to claim 7 and is rejected for the same reasons.
Regarding claim 16, the claim corresponds to claim 3 and is rejected for the same reasons. The combination of Hettegger, Quy and Prateepasen also teaches one or more non-transitory machine-readable storage devices storing instructions for detecting passing valves, the instructions being executable by one or more processors, to cause performance of operations (inherently, the analysis methods of Hettegger, Quy and Prateepasen are performed using a processor, memory and instructions).
Regarding claim 17, the combination of Hettegger, Quy and Prateepasen teaches the invention as claimed in claim 16. Claim 17 also corresponds to claim 1 and is rejected for the same reasons.
Regarding claim 18, the combination of Hettegger, Quy and Prateepasen teaches the invention as claimed in claim 17. Claim 18 also corresponds to claim 2 and is rejected for the same reasons.
Regarding claim 19, the combination of Hettegger, Quy and Prateepasen teaches the invention as claimed in claim 16. Claim 19 also corresponds to claim 7 and is rejected for the same reasons.
Claims 4, 6 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Hettegger, Quy and Prateepasen, as applied in claim 3, and further in view of Liang (CN116842324 translation).
Regarding claim 4, the combination of Hettegger, Quy and Prateepasen teaches the invention as claimed in claim 3. The combination of Hettegger, Quy and Prateepasen also teaches wherein extracting a plurality of features comprises: converting the filtered vibrational data to digital vibrational data using a high-sampling rate analog to digital converter (Hettegger [0027], the acoustic emission sensor signals can be analogue; Quy pages 3-4, 8 teaches a modul that converts analog to digital signals at a high sampling rate e.g., 1 Mhz).
However, the combination of Hettegger, Quy and Prateepasen does not expressly disclose
the extracting a plurality of features comprises: filtering the vibrational data using a bandpass filter.
In the same field of endeavor, Liang teaches wherein extracting a plurality of features comprises:
filtering the vibrational data using a bandpass filter (Abstract, page 4, notes that when predicting valve leakage, it is known to apply band-pass filtering on the acoustic emission sensor data).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to have incorporated the extracting a plurality of features comprises: filtering the vibrational data using a bandpass filter as suggested in Liang into Hettegger, Quy and Prateepasen because Hettegger and Liang pertain to analogous fields of technology. Both Hettegger and Liang pertain to systems for determining leakage in valves by analyzing acoustic emission sensor signals. In Liang, the signals are pre-processed using band-pass filtering. It would be desirable to incorporate this feature into Hettegger to facilitate feature extraction and to use alternative, known methods for processing the signals e.g., see Liang Abstract, page 4.
Regarding claim 6, the combination of Hettegger, Quy, Prateepasen and Liang teaches the invention as claimed in claim 4. The combination of Hettegger, Quy, Prateepasen and Liang also teaches wherein the bandpass filter passes frequencies between 100 kHz and 300 kHz (Hettegger [0058-0059], it is known when analyzing acoustic emission signals, to analyze a limited sub-range of the frequency range, such as 200 to 250 kHz).
Regarding claim 15, the combination of Hettegger, Quy and Prateepasen teaches the invention as claimed in claim 10. Claim 15 also corresponds to claim 4 and is rejected for the same reasons.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Hettegger, Quy, Prateepasen and Liang, as applied in claim 4, and further in view of Mostfapour (A. Mostafapour et al., "Analysis of leakage in high pressure pipe using acoustic emission method," Applied Acoustics, published Oct. 24, 2012).
Regarding claim 5, the combination of Hettegger, Quy, Prateepasen and Liang teaches the invention as claimed in claim 4. However, the combination of Hettegger, Quy, Prateepasen and Liang does not expressly disclose wherein the sampling rate of the analog to digital converter is at least 2 MHz.
In the same field of endeavor, Mostfapour teaches wherein the sampling rate of the analog to digital converter is at least 2 MHz (page 335, Mostafapour teaches using a high sampling rate e.g, 10 Mhz, to model acoustic emission signals resulting from a leak).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to have incorporated wherein the sampling rate of the analog to digital converter is at least 2 MHz as suggested in Mostafapour into Hettegger, Quy, Prateepasen and Liang because Hettegger and Mostafapour pertain to analogous fields of technology. Both Hettegger and Mostafapour pertain to systems for determining leakage based on an analysis of acoustic emission signals. In Mostafapour, a high sampling rate e.g., 10 Mhz, is used to model acoustic emission signals to make the determination. It would be desirable to incorporate this feature into Hettegger to facilitate the analysis of acoustic emission signals using known methods e.g., see Mostafapour page 335.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Hettegger and Quy, as applied in claim 7, and further in view of Jensen (T. Jensen, "Feature Importance for Any Model using Permutation," Medium, published Sep. 23, 2022).
Regarding claim 8, the combination of Hettegger and Quy teaches the invention as claimed in claim 7. However, the combination of Hettegger and Quy does not expressly disclose wherein the feature importance criterion comprises a reduction in a percentage of results classified correctly when a feature is omitted; and a feature having more significance has a higher reduction in the percentage of results classified correctly when the feature is omitted relative to the reduction in the percentage of results when other features are omitted.
In the same field of endeavor, Jensen teaches
wherein the feature importance criterion comprises a reduction in a percentage of results classified correctly when a feature is omitted; and
a feature having more significance has a higher reduction in the percentage of results classified correctly when the feature is omitted relative to the reduction in the percentage of results when other features are omitted (Jensen pages 2-3, 9-10, 18-19, it is known to estimate the importance of features for a model; the technique involves selecting a feature/column among multiple features and shuffling its values i.e., effectively removing the feature's values; the model is executed to generate prediction results over a dataset; a comparison is performed between results of an unadjusted model and a model using the shuffled/removed feature e.g., by calculating a change in mean square error; this process is repeated with each feature and the relative performance of the features can be compared; the features whose values result in the greatest amounts of error are those that are most significant for the model; put another way, a model using a first shuffled/removed feature may generate less/a lower percentage of results accurately compared to a second feature, meaning that the first feature is more significant for the model accuracy.)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to have incorporated wherein the feature importance criterion comprises a reduction in a percentage of results classified correctly when a feature is omitted; and a feature having more significance has a higher reduction in the percentage of results classified correctly when the feature is omitted relative to the reduction in the percentage of results when other features are omitted as suggested in Jensen into Hettegger and Quy, because Hettegger and Quy pertain to analogous fields of technology. Both Hettegger and Jensen pertain to analyzing data using machine learning, in part by identifying various features in the data. In Jensen, the importance of each feature is determined by effectively removing a feature and assessing the associated accuracy of a model; this process is performed for each feature and the results are compared to determine which features most contribute to the accuracy of the model. It would be desirable to incorporate this feature into Hettegger to improve the accuracy of the machine learning model used to analyze acoustic emission signals and to determine the possibility of leakage in a pipe or valve e.g., see Jensen pages 2-3, 9-10, 18-19.
Claims 14 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Hettegger, Quy and Prateepasen, as applied in claim 13, and further in view of Jensen.
Regarding claim 14, the combination of Hettegger, Quy and Prateepasen teaches the invention as claimed in claim 13. However, the combination of Hettegger, Quy and Prateepasen does not expressly disclose wherein the feature importance criterion comprises a reduction in a percentage of results classified correctly when a feature is omitted; and a feature having more significance has a higher reduction in the percentage of results classified correctly when the feature is omitted relative to the reduction in the percentage of results when other features are omitted.
In the same field of endeavor, Jensen teaches
wherein the feature importance criterion comprises a reduction in a percentage of results classified correctly when a feature is omitted; and
a feature having more significance has a higher reduction in the percentage of results classified correctly when the feature is omitted relative to the reduction in the percentage of results when other features are omitted (Jensen pages 2-3, 9-10, 18-19, it is known to estimate the importance of features for a model; the technique involves selecting a feature/column among multiple features and shuffling its values i.e., effectively removing the feature's values; the model is executed to generate prediction results over a dataset; a comparison is performed between results of an unadjusted model and a model using the shuffled/removed feature e.g., by calculating a change in mean square error; this process is repeated with each feature and the relative performance of the features can be compared; the features whose values result in the greatest amounts of error are those that are most significant for the model; put another way, a model using a first shuffled/removed feature may generate less/a lower percentage of results accurately compared to a second feature, meaning that the first feature is more significant for the model accuracy.)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to have incorporated wherein the feature importance criterion comprises a reduction in a percentage of results classified correctly when a feature is omitted; and a feature having more significance has a higher reduction in the percentage of results classified correctly when the feature is omitted relative to the reduction in the percentage of results when other features are omitted as suggested in Jensen into Hettegger, Quy and Prateepasen because Hettegger and Quy pertain to analogous fields of technology. Both Hettegger and Jensen pertain to analyzing data using machine learning, in part by identifying various features in the data. In Jensen, the importance of each feature is determined by effectively removing a feature and assessing the associated accuracy of a model; this process is performed for each feature and the results are compared to determine which features most contribute to the accuracy of the model. It would be desirable to incorporate this feature into Hettegger to improve the accuracy of the machine learning model used to analyze acoustic emission signals and to determine the possibility of leakage in a pipe or valve e.g., see Jensen pages 2-3, 9-10, 18-19.
Regarding claim 20, the combination of Hettegger, Quy and Prateepasen teaches the invention as claimed in claim 19. Claim 20 also corresponds to claim 14 and is rejected for the same reasons.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Huang (US 2021/0208021) teaches a system for analyzing acoustic emission signals to analyze the state of a mechanical seal e.g., a valve or pipeline; see Huang Abstract, [0022, 0023].
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ERIC YOON whose telephone number is (408)918-7581. The examiner can normally be reached on 9 am to 5 pm ET Monday through Friday.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Scott Baderman, can be reached at telephone number 571-272-3644. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center. Status information for published applications may be obtained from Patent Center. Status information for unpublished applications is available through Patent Center for authorized users only. Should you have questions about access to Patent Center, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/ERIC J YOON/Primary Examiner, Art Unit 2118