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 .
Status of the Claims
This Office Action is in response to the Application filed on January 13, 2025. Claims 1-5 are presently pending and are presented for examination.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on March 28, 2025 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-5 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
101 Analysis - Step 1
Claims 1-5 recite a system/apparatus, therefore claims 1-5 are within at least one of the four statutory categories.
101 Analysis - Step 2A, Prong 1
Regarding Prong 1 of the Step 2A analysis in the 2019 PEG, the claims are to be analyzed to determine whether they recite subject matter that falls within one of the follow groups of abstract ideas: a) mathematical concepts, b) certain methods of organizing human activity, and/or c) mental processes.
Independent claim 1 includes limitations that recites mathematical concepts and/or mental processes (emphasized below) and will be used as a representative claim for the remainder of the 101 rejection. Claim 1 recites:
An integrated distributed fiber optic sensing system for enhanced offshore wind turbine monitoring using physics-informed machine learning, the system comprising:
a distributed fiber optic sensing (DFOS) system for capturing temperature, acoustic, strain, or vibration data of the offshore wind turbines;
one or more physics-informed machine learning algorithms which are trained to determine, from the captured temperature, acoustic, strain, or vibration data, between routine operation and anomalies indicative of potential faults or damage to the wind turbines or components thereof.
These limitations, as drafted, is a system that, under its broadest reasonable interpretation, covers performance of the limitation as a mental process. That is, nothing in the claim elements preclude the steps from practically being performed as mental process. For example, " determine, from the captured..." encompass mental processes as a human can perform these limitations using observations, evaluations, judgments, and/or opinions. “determine, from the captured..." involves a human observing and/or evaluating if an anomaly has occurred based on received sensor data. Thus, the claim recites at least a mental process.
101 Analysis - Step 2A, Prong 2
Regarding Prong 2 of the Step 2A analysis in the 2019 PEG, the claims are to be analyzed to determine whether the claim, as a whole, integrates the abstract idea into a practical application. As noted in the 2019 PEG, it must be determined whether any additional elements in the claim beyond the abstract idea integrate the exception into a practical application in a manner that imposes a meaningful limit on the judicial exception. The courts have indicated that additional elements merely using a computer to implement an abstract idea, adding insignificant extra solution activity, or generally linking use of a judicial exception to a particular technological environment or field of use do not integrate a judicial exception into a "practical application."
In the present case, the additional limitations beyond the above-noted abstract idea are as follows (where the underlined portions are the "additional limitations" while the bolded portions continue to represent the "abstract idea"):
An integrated distributed fiber optic sensing system for enhanced offshore wind turbine monitoring using physics-informed machine learning, the system comprising:
a distributed fiber optic sensing (DFOS) system for capturing temperature, acoustic, strain, or vibration data of the offshore wind turbines;
one or more physics-informed machine learning algorithms which are trained to determine, from the captured temperature, acoustic, strain, or vibration data, between routine operation and anomalies indicative of potential faults or damage to the wind turbines or components thereof.
For the following reason(s), the examiner submits that the above identified additional limitations do not integrate the above-noted abstract idea into a practical application.
Regarding the additional limitation of " An integrated distributed fiber optic sensing system for enhanced offshore wind turbine monitoring using physics-informed machine learning” the examiner submits that this limitation characterizes the method as being associated with a fiber optic sensing system of a wind turbine, which merely amounts to indicating a field of use or technological environment in which to apply a judicial exception and cannot integrate the judicial exception into a practical application or amount to significantly more than the exception itself (see MPEP 2106.05(h)). Additionally, the claim limitation “a distributed fiber optic sensing (DFOS) system …” does not amount to an inventive concept since it is insignificant extra-solution activity as it is merely a form of data collection and outputting (MPEP § 2106.05(g) using generic computing components that merely apply the judicial exception (See 2106.05(f)). Additionally, “one or more physics-informed machine learning algorithms which are trained” does not integrate a judicial exception into a practical application or provide significantly more because this type of recitation is equivalent to the words “apply it” that using a generic algorithm to apply the abstract idea. The examiner submits that these limitations are mere data collection and outputting components to apply the above-noted abstract idea within an indicated field of use (MPEP §2106.05).
Thus, taken alone, the additional elements do not integrate the abstract idea into a practical application. Further, looking at the additional limitation(s) as an ordered combination or as a whole, the limitation(s) add nothing that is not already present when looking at the elements taken individually. For instance, there is no indication that the additional elements, when considered as a whole, reflect an improvement in the functioning or an improvement to another technology or technical field, apply or use the above-noted judicial exception to effect a particular process for safety performance evaluation, implement/use the above-noted judicial exception with a particular machine or manufacture that is integral to the claim, effect a transformation or reduction of a particular article to a different state or thing, or apply or use 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 not more than a drafting effort designed to monopolize the exception (MPEP § 2106.05). Accordingly, the additional limitation(s) do/does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
101 Analysis - Step 2B
Regarding Step 2B in the 2019 PEG, representative independent claim 1 does not include additional elements (considered both individually and as an ordered combination) that are sufficient to amount to significantly more than the judicial exception for the same reasons to those discussed above with respect to determining that the claim does not integrate the abstract idea into a practical application.
As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of ““a distributed fiber optic sensing (DFOS) system…" amounts to extra-solution data gathering and outputting. Additionally, the specification demonstrates the well-understood, routine, conventional nature of additional elements as it describes the additional elements as well-understood or routine or conventional (or an equivalent term), as a commercially available product, or in a manner that indicates that the additional elements are sufficiently well-known that the specification does not need to describe the particulars of such additional elements to satisfy 35 U.S.C. §112(a). Additionally, “a distributed fiber optic sensing (DFOS) system …” are each generic computing components that merely apply the judicial exception (See 2106.05(f)). Additionally, " An integrated distributed fiber optic sensing system for enhanced offshore wind turbine monitoring using physics-informed machine learning” is merely a technological environment or field of use as the limitations merely link the use of a judicial exception to a particular technological environment or field of use (See MPEP 2106.05(h)). In regards to ““one or more physics-informed machine learning algorithms which are trained” it is noted that the recitation of claim limitations that attempt to cover any solution to an identified problem with no restriction on how the result is accomplished and no description of the mechanism for accomplishing the result, does not integrate a judicial exception into a practical application or provide significantly more because this type of recitation is equivalent to the words “apply it”. See Electric Power Group, LLC v. Alstom, S.A., 830 F.3d 1350, 1356, 119 USPQ2d 1739, 1743-44 (Fed. Cir. 2016); Intellectual Ventures I v. Symantec, 838 F.3d 1307, 1327, 120 USPQ2d 1353, 1366 (Fed. Cir. 2016); Internet Patents Corp. v. Active Network, Inc., 790 F.3d 1343, 1348, 115 USPQ2d 1414, 1417 (Fed. Cir. 2015).
Dependent claims 2-5 specify limitations that elaborate on the abstract idea of claim 1, and thus are directed to an abstract idea nor do the claims recite additional limitations that integrate the claims into a practical application or amount to "significantly more" for similar reasons.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Kubo (US 20180363633).
In regards to claim 1, Kubo discloses of an integrated distributed fiber optic sensing system for enhanced offshore wind turbine monitoring using physics-informed machine learning (“A measurement value of a sensor mounted to a wind turbine blade for measuring a strain amount, for instance, is under influence of a mounted state of a sensor to the wind turbine blade and the external environment. The present inventors found that the level of the influence differs among the sensors, and that there is individual variability. For instance, a fiber-optic sensor measures a strain amount by utilizing a change in the optic characteristics of reflection light from a grating (FBG) constituting the sensor part in response to a change in the refractive index and the grating spacing of the grating in response to the strain amount. The refractive index and spacing of the grating changes depending not only the strain amount but also the ambient temperature, and the change due to the temperature differs among individual sensors.” (Para 0012), “In some embodiments, the group monitoring part 5 (see FIG. 1) detects an abnormality occurring in at least one of the wind turbine power generating apparatuses 6 belonging to the monitoring group G, through determination of whether the operational state of the monitoring group G obtained by seeing the monitoring group G as a whole is different from a normal state. Accordingly, it is possible to detect an abnormality in an earlier stage, while suppressing load of abnormality monitoring. Furthermore, since an abnormality can be detected quickly, it is possible to specify the wind turbine power generating apparatuses 6 with an abnormality and address to the abnormality in an earlier stage. More specifically, as described below, the group monitoring part 5 may perform abnormality monitoring through machine learning.” (Para 0116))), the system comprising:
a distributed fiber optic sensing (DFOS) system for capturing temperature, acoustic, strain, or vibration data of the offshore wind turbines (“Similarly, each wind turbine power generating apparatus includes a sensor for measuring a strain parameter Pt (hereinafter, also referred to as a strain parameter measurement sensor 7s). As shown in FIG. 2, in each wind turbine power generating apparatus 6, at least one strain parameter measurement sensor 7s is mounted to at least one of the wind turbine blades 61. The strain parameter Pt is an index showing a strong correlation to the strain amount of the wind turbine blade 61, and may be the strain amount itself, or a measurement value measured as a strain amount by the fiber-optic sensor 7 which is also affected by temperature, as described below. Furthermore, the strain parameter Pt may be a parameter calculated on the basis of the above strain amount of the wind turbine blade 61, such as load, moment, or the like derived from the strain amount. The strain amount or the parameter based on the above strain amount changes periodically in response to rotation of the wind turbine blade 61. The strain parameter Pt may be an amplitude value of the periodically-changing parameter, or a wavelength fluctuation index indicating the fluctuation amount of the wavelength of reflection light from the sensor part of the fiber-optic sensor 7. The wavelength fluctuation index is an index indicating the fluctuation amount of the wavelength obtained by the temporal change of the wavelength of reflection light from the sensor part. More specifically, if the reflection light changes from λ1 to λ2 between the two different times t1 and t2 (t1<t2), the fluctuation amount of the wavelength (wavelength fluctuation index) is λ2−λ1. The fluctuation amount of the wavelength is related to the strain amount, and the wavelength of reflection light normally depends on strain and temperature at the sensor part. Nevertheless, in such a short period as the rotational period of the wind turbine rotor 63 (normally, about four to seven minutes) and the above sampling interval, the temperature of the sensor part may be regarded as invariable, and thus the change amount of strain in the period (t1 to t2) depends (in proportion) to the fluctuation amount of the wavelength. Furthermore, the strain parameter Pt may be combination of at least one of the above parameters.” (Para 0071), see also Para 0085);
one or more physics-informed machine learning algorithms which are trained to determine, from the captured temperature, acoustic, strain, or vibration data, between routine operation and anomalies indicative of potential faults or damage to the wind turbines or components thereof (”That is, a measurement value of a strain parameter measurement sensor 7s mounted to the wind turbine blade 61 for measuring a strain amount, for instance, is under influence of a mounted state of a sensor to the wind turbine blade 61 and the external environment. The present inventors found that the level of the influence differs among the sensors and there is individual variability. For instance, a fiber-optic sensor 7 measures a strain amount by utilizing a change in the optic characteristics of reflection light from a grating (FBG) constituting the sensor part (7s) in response to a change the refractive index and the grating spacing of the grating in response to the strain amount. The refractive index and spacing of the grating change depending not only the strain amount but also the ambient temperature, and the change due to the temperature differs among individual sensors. Thus, by forming the monitoring group G with at least two wind turbine power generating apparatuses 6 satisfying the above condition, it is possible to suppress influence of individual variability of sensors on abnormality monitoring accuracy, in the monitoring group G.” (Para 0085), “As shown in FIG. 1, a monitoring system of the wind farm 9 is a system for monitoring the wind farm 9 including a plurality of wind turbine power generating apparatuses 6, and includes at least one remote monitoring control device 94 (supervisory control and data acquisition (SCADA) server) connected to at least one wind turbine power generating apparatus 6, and an abnormality monitoring apparatus 1 of the wind farm 9 (hereinafter, also referred to as the abnormality monitoring apparatus 1). As shown in FIG. 1, the remote monitoring control device 94 is connected to each of the plurality of wind turbine power generating apparatuses 6 constituting the wind farm 9. The operational condition of each wind turbine power generating apparatus 6 can be monitored remotely by using the remote monitoring control device 94. The number of remote monitoring control device 94 may be determined depending on the size of the wind farm 9, for instance. In the embodiment shown in FIG. 1, a plurality of (seven) remote monitoring control devices 94 are provided. Further, each wind turbine power generating apparatus 6 is connected to one of the remote monitoring control devices 94 via a communication network, and thereby the plurality of remote monitoring control devices 94 are configured to monitor different wind turbine power generating apparatuses 6 from one another.” (Para 0066), “Furthermore, in the embodiment shown in FIG. 2, each of the strain parameter measurement sensors 7s mounted to the above described wind turbine blade 61 includes a sensor part such as a grating (Fiber Bragg Grating; FBG) formed on the optic fiber 71 of the fiber-optic sensor 7. Generally, the fiber-optic sensor 7 includes, as a basic configuration, a light source which emits light (not shown), an optic fiber 71 for transmitting light from the light source, at least one sensor part (strain parameter measurement sensor 7s) formed distanced from the optic fiber 71, and a light receiving device (not shown) for converting light (light characteristics) detected by receiving light from the optic fiber 71 into electric signals. In the present embodiment, in the light-source/signal processing unit 72 connected to the optic fiber 71, along with the above light source and the light receiving device, a signal processing device for processing electric signals inputted from the light receiving device (not shown) is accommodated. The signal processing device processes electric signals from the light receiving device on the basis of the information not affected by the external environment, such as light traveling speed difference, frequency, and wavelength, and thereby obtains the measurement value obtained by the strain parameter measurement sensor 7s, and turns the measurement value into data in a predetermined period such as 50 ms. In some other embodiments, each of the strain parameter measurement sensors 7s may be another kind of sensor, such as a strain gauge.” (Para 0074), “Then, in step S4, pre-processing (preparation) is performed, to prepare for abnormality monitoring on the monitoring group G set in the previous step. The pr-processing for abnormal monitoring may be machine learning described below. Alternatively, the pre-processing may be merely obtaining information of the monitoring group G.” (Para 0095), “First, machine learning will be described. In some embodiments, as shown in FIG. 7, the abnormality monitoring apparatus 1 further includes a canonical correlation learning part 5L configured to obtain a canonical correlation between the power generation parameter Pg and the strain parameter Pt of the wind turbine power generating apparatuses 6 belonging to the monitoring group G, in learning before performing abnormality monitoring by the group monitoring part 5. Furthermore, the group monitoring part 5 may be configured to perform abnormality monitoring on the monitoring group G on the basis of the canonical correlation obtained by the canonical correlation learning part 5L as described below. That is, learning by the canonical correlation learning part 5L (machine learning) is a process serving as the basis for the group monitoring part 5 to perform abnormality monitoring, and is performed by using learning data L in which measurement values of the power generation parameter Pg and the strain parameter Pt obtained before execution of abnormality monitoring by the group monitoring part 5 are accumulated. If the learning data includes data obtained under a condition in which it can be regarded that the normality of the wind turbine power generating apparatuses 6 belonging to the monitoring group G is ensured, such as when the monitoring group G is being used for the first time, or at the time of regular maintenance, the canonical correlation obtained by the canonical correlation learning part 5L is free from the influence at the time of abnormality, which makes it possible to achieve an even higher abnormality detection accuracy.” (Para 0117)).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim(s) 2-3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kubo in view of Perdikaris et al. (US 20250077875; hereinafter Perdikaris).
In regards to claim 2, Kubo discloses of the system of claim 1 wherein the physics-informed machine learning algorithms.
However, Kubo does not specifically disclose of the physics-informed machine learning algorithms include physics-informed neural networks (PINNs) which incorporate governing physical equations directly into the PINN structure.
Perdikaris, in the same field of endeavor, teaches of the physics-informed machine learning algorithms include physics-informed neural networks (PINNs) which incorporate governing physical equations directly into the PINN structure (“This specification describes methods, systems, and computer readable media for training physics-informed neural networks. Physics-informed neural networks (PINNs) are a class of neural networks that incorporate physical principles and laws into the training process. These networks are used to solve partial differential equations (PDEs) that describe physical phenomena, such as fluid dynamics, electromagnetism, and mechanics.” (Para 0022), see also Para 0028).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the physics-informed machine learning algorithms, as taught by Kubo to include Physics-informed neural networks, as taught by Perdikaris, with a reasonable expectation of success in order to improve the accuracy of models (Perdikaris Para 0005).
In regards to claim 3, Kubo in view of Perdikaris teaches of the system of claim 2 wherein the PINNs are trained with both historical data and synthetic data generated using physics-based simulations (“The parameter obtaining part 2 obtains the power generation parameter Pg (described above) related to power generation of the wind turbine power generating apparatus 6, and the strain parameter Pt (described above) measured by the strain parameter measurement sensor 7s mounted to the wind turbine blade 61 of the wind turbine power generating apparatus 6, from at least two (N) of the plurality of (Na) wind turbine power generating apparatuses 6 constituting the wind farm 9. This is, as described below, to evaluate the correlation between the different kinds of power generation parameter Pg and strain parameter Pt among the at least two wind turbine power generating apparatuses 6. In the embodiment shown in FIG. 2, the parameter obtaining part 2 is configured to obtain previous data of the two parameters P (Pg, Pt) measured in past, through access to the cloud 96 or the like. The data to be obtained may be learning data L described below. At this time, the parameter obtaining part 2 may obtain two parameters P from each of the entire (Na) wind turbine power generating apparatuses 6 of the wind farm 9, or from a plurality of (N) wind turbine power generating apparatuses 6 selected from the entire wind turbine power generating apparatuses 6 of the wind farm 9. That is, provided that Na is the total number of the wind turbine power generating apparatuses 6 of the wind farm 9 (Na≥2) and N is the total number of the wind turbine power generating apparatuses 6 from which the parameter obtaining part 2 is to obtain parameters (N≥2), N≤N.sub.a is satisfied.” (Kubo Para 0081), “These unlabeled samples can be used to enforce physical constraints on the learned model, and can be incorporated into the training process in several ways. For example, they can be used to regularize the neural network during training, or to generate synthetic training data to augment the labeled samples.” (Perdikaris Para 0039), “The movement predictor 120 can then use the PINN model 118 to predict movement of a physical component of the mechanical system. For example, once the PINN model 118 is trained, it can be used to predict the position and velocity of the mechanical component at any future time. The input variables are fed into the model 118, and the output variables are predicted using the trained neural network. The predicted values can be compared with actual measurements to assess the accuracy of the model 118. The model 118 can be refined and improved by tuning hyperparameters, such as the number of layers or nodes in the neural network, or by adjusting the regularization strength or learning rate. The model 118 can also be updated with new data as it becomes available, to improve the accuracy of the predictions.” (Perdikaris Para 0044)).
The motivation for combining Kubo and Perdikaris is the same as that recited for claim 2 above.
Claim(s) 4-5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kubo in view of Perdikaris, as applied in claim 2 above, further in view of Titsias et al. (US 20240394516; hereinafter Titsias).
In regards to claim 4, Kubo in view of Perdikaris teaches of the system of claim 3.
However, Kubo in view of Perdikaris does not specifically teach of further comprising hybrid Kalman Neural Networks that provide real-time state estimation of wind turbine components.
Titsias, in the same field of endeavor, teaches of further comprising hybrid Kalman Neural Networks that provide real-time state estimation of wind turbine components (“In some implementations, the system uses a state space model (e.g., a linear Gaussian or diffusion model) for the transition distribution, parametrized by a forgetting coefficient that quantifies the degree of “memory” the system has of past observations in the data stream. In these cases, the system can perform predictions by implementing computationally efficient and low latency Kalman filter recursions, while flexibly adapting to non-stationarity in the data via online updates of the forgetting coefficient. For example, the Kalman filter recursions generally involve a fixed number of computations at each time step which, in many implementations, is on the order of ˜O(d.sup.2), where d is the size of the base neural network's embedding space. Moreover, in general, the Kalman filter model does not need to store additional data in memory beyond the Kalman statistics and the parameters of the neural network at the time step. Hence, the system can be computationally fast and memory cheap, and implementable in situations where computational resources such as processing power and memory are scarce, e.g., mobile devices, tablets, laptops, edge computing devices, etc. The predictive ability of the Kalman filter model, and its flexibility to capture non-stationarity, was demonstrated in a set of experiments involving regression on an artificial, non-stationary data stream and multi-class classification on data sets such as CIFAR-100and CLOC. The results of which are provided herein.” (Para 0049), “Algorithm 1 below is an example implementation of the process 200 for online inference and learning using the neural network 110 and probabilistic Kalman filtering, e.g., using exact Kalman filter recursions for a regression or classification task. As shown in Algorithm 1, since Kalman filtering is analytic, the system 100 can avoid direct computations of the probability distributions, e.g., via marginalization and Bayes' rule, and instead update the parameters of the probability distributions via fast Kalman recursions.” (Para 0178), see also Para 0045).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the physics-informed neural network, as taught by Kubo in view of Perdikaris, to include hybrid Kalman Neural Networks, as taught by Titsias, with a reasonable expectation of success in order to allow the system to be computationally fast and memory cheap (Titsias Para 0049).
In regards to claim 5, Kubo in view of Perdikaris further in view of Titsias teaches of the system of claim 4 wherein the PINNs are continuously refined using newly collected data from the DFOS system (“Similarly, for the strain parameter Pt, in some embodiments, the different strain parameter measurement sensors 7s (different kinds of measurement) of each wind turbine power generating apparatus 6 may be each inputted into the canonical correlation learning part 5L as a variate group y (see FIGS. 8 and 9). At this time, the measurement values of all of the strain parameter measurement sensors 7s of the wind turbine power generating apparatus 6 may be inputted to the canonical correlation learning part 5L (see FIG. 9), or at least one of the measurement values of the strain parameter measurement sensors 7s may be inputted thereto (see FIG. 8). In this case, the canonical correlation learning part 5L obtains the canonical correlation with the power generation parameter Pg for each kind of strain parameter Pt.” (Kubo Para 0122) “The movement predictor 120 can then use the PINN model 118 to predict movement of a physical component of the mechanical system. For example, once the PINN model 118 is trained, it can be used to predict the position and velocity of the mechanical component at any future time. The input variables are fed into the model 118, and the output variables are predicted using the trained neural network. The predicted values can be compared with actual measurements to assess the accuracy of the model 118. The model 118 can be refined and improved by tuning hyperparameters, such as the number of layers or nodes in the neural network, or by adjusting the regularization strength or learning rate. The model 118 can also be updated with new data as it becomes available, to improve the accuracy of the predictions.” (Perdikaris Para 0044)).
The motivation for combining Kubo, Perdikaris, and Titsias is the same as that recited for claim 4 above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Pathuvoth et al. (US 20240200535) discloses of a method for monitoring damage of a slewing ring bearing of a wind turbine includes arranging at least one optical fiber sensor adjacent to or at least partially on at least one of an inner race or an outer race of the slewing ring bearing.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Kyle J Kingsland whose telephone number is (571)272-3268. The examiner can normally be reached Monday-Friday from 8:00-4:30.
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, Abby Flynn can be reached at (571) 272-9855. 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.
/KYLE J KINGSLAND/Primary Examiner, Art Unit 3663
Prosecution Insights