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 .
Response to Arguments
Applicant's arguments filed 12/11/2025 have been fully considered and they are partially persuasive.
Regarding applicant’s remarks directed to the rejection of claims under 35 USC § 101, the applicant argues that the amended claims directed to a technical improvement. Examiner respectfully agrees and withdraws the prior rejection of claims under 35 USC § 101.
Regarding applicant’s remarks directed to the rejection of claims under 35 USC § 103, the arguments are directed to newly amended limitations that were not previously examined by the examiner. Therefore, applicants arguments are rendered moot. The examiner refers to the rejection under 35 USC § 103 in the current office action for more details.
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.
Claim(s) 1-4, 8-14, and 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over KR Pub No. KR20200043196A Baek et al. (“Baek”) in view of Q. Wang, S. Zheng, A. Farahat, S. Serita and C. Gupta, "Remaining Useful Life Estimation Using Functional Data Analysis," 2019 IEEE International Conference on Prognostics and Health Management (ICPHM), San Francisco, CA, USA, 2019, pp. 1-8, doi: 10.1109/ICPHM.2019.8819420 (“Wang”)
In regards to claim 1 and analogous claim 11,
Baek teaches A method for predicting a characteristic of a system, comprising: measuring, at a sample rate, data relating to an operation of the system over a first time period; producing a two-dimensional (2D) time-and-frequency first input data set by applying a wavelet transform to the measured data; and generating a set of one or more values associated with one or more system characteristics by processing the 2D time-and-frequency first input data set [using a functional neural network (FNN)]; and
(Baek, Abstract, “A residual life prediction device is disclosed [A method for predicting a characteristic of a system]. The residual life prediction apparatus uses a data conversion unit that converts each of a plurality of one-dimensional vibration signals into a two-dimensional image, and uses a plurality of two-dimensional images generated by the data conversion unit as input data. Predictive model generation unit that trains an artificial neural network (ANN) model that outputs HI), and predicts the residual useful life (RUL) of a predicted facility or a predicted component using the trained ANN model [generating a set of one or more values ie RUL associated with one or more system characteristics by processing the 2D time-and-frequency first input data set; wherein the 2D data is input to the ANN] And a residual life prediction unit, and the data transformation unit generates the two-dimensional images by performing continuous wavelet transformation (CWT) [producing a two-dimensional (2D) time-and-frequency first input data set by applying a wavelet transform to the measured data] on each of the one-dimensional vibration signals.”)
PNG
media_image1.png
561
704
media_image1.png
Greyscale
(Baek, Description para. 27, “FIG. 3 shows a contour plot of the wavelet power spectrum generated by the vibration signal and continuous wavelet transform (CWT). The vibration signal sampled at 0.1 s intervals at a frequency of 25.6 kHz has 2560 data points [measuring, at a sample rate, data relating to an operation of the system over a first time period].”
)
Baek discloses that the ANN may not be limited to the type of ANN(Baek, Description para. 20, “The predictive model generator 300 may generate a predictive model capable of predicting a residual life (RUL) of equipment or parts. Specifically, the prediction model generator 300 may generate an ANN (Artificial Neural Network) model, and train the ANN model using the two-dimensional images generated by the data converter 100. The ANN may be a convolutional neural network (CNN), but the scope of the present invention is not necessarily limited to the type of artificial neural network.”)
Baek teaches using the set of one or more values to perform a predictive maintenance task that improves a performance of one or more components of the system.
(Baek, Description para. 2, “Residual life prediction technology is being actively researched in the field of health predictive management (PHM), and has recently emerged as a more important factor in the emergence of smart factories. Residual life prediction can be useful mainly in the aviation industry, nuclear power generation, automotive industry, high-tech industries such as semiconductor / display, etc. It is mainly applied to facilities or parts that are expected to be fatally damaged in the event of a sudden abnormality or failure, and continuously monitors to collect and analyze data to predict the failure and life of the machine to predict predictive maintenance (PdM). . Proper use of the residual life prediction technology can reduce unnecessary equipment maintenance, reduce maintenance costs, and predict failures to improve safety [using the set of one or more values to perform a predictive maintenance task that improves a performance of one or more components of the system]. In particular, vibration monitoring is widely used because it is simple and accurate to estimate the overall condition of the machine. Therefore, the present invention proposes a method and system for predicting residual life based on a vibration signal, and incorporates a deep learning technique that greatly contributes to improving the accuracy of recent data analysis to improve the shortcomings in existing studies. We want to improve the performance of the residual life prediction.”)
However, Baek does not explicitly teach using a functional neural network (FNN)
Wang teaches using a functional neural network (FNN)
(Wang, Section II B., “RUL estimation using functional MLP proceeds as follows. Functional MLP [using a functional neural network (FNN)] consists of a layer of functional neurons followed by multiple layers of numerical neurons as in classic MLP. Functional neurons take the continuous sensor curves as input and output numerical numbers which are then fed into the subsequent numerical layers.”)
Baek and Wang are both considered to be analogous to the claimed invention because they are in the same field of predictive maintenance using neural networks. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Baek to incorporate the teachings of Wang in order to provide a functional MLP to discover the complex relationships between the sensor measurements and the RUL as functional MLP are more suitable to the nature of the equipment (Wang, Section II B., “Functional MLP, an algorithm that enables non-linear learning for the functional regression problem, is capable of discovering complex relationships between the continuous sensor curves and the RUL value. Due to the complicated nature of equipment, we believe that functional MLP is more suitable for the RUL estimation problem.”) (Wang, Abstract, “FDA explicitly incorporates both the correlations within the same equipment and the random variations across different equipment's sensor time series into the model. FDA also has the benefit of allowing the relationship between RUL and sensor variables to vary over time. We implement functional MLP on the benchmark NASA C-MAPSS data and evaluate the performance using two popularly-used metrics. Results show the superiority of our algorithm over all the other state-of-the-art methods.”)
In regards to claim 2 and analogous claim 12,
Baek and Wang teaches The method of claim 1,
Baek teaches wherein generating the set of one or more values associated with the one or more system characteristics comprises: providing the 2D time-and-frequency first input data set to the FNN as input;
(Baek, Abstract, “The residual life prediction apparatus uses a data conversion unit that converts each of a plurality of one-dimensional vibration signals into a two-dimensional image, and uses a plurality of two-dimensional images generated by the data conversion unit as input data [providing the 2D time-and-frequency first input data set to the FNN as input]”)
However, Baek does not explicitly teach generating, using the FNN, an output data set; and providing the output data set as a second input to a fully connected neural network (FCNN), wherein the generated set of one or more values associated with the one or more system characteristics is the output of the FCNN
Wang teaches generating, using the FNN, an output data set; and providing the output data set as a second input to a fully connected neural network (FCNN), wherein the generated set of one or more values associated with the one or more system characteristics is the output of the FCNN.
(Wang, Section II B., “In the linear transformation step, functional neurons compute the integral of the multiplication of a specific feature curve and a weight function within time range T, as a generalization of vector inner product in L2(t). In the non-linear transformation step, the numerical outputs in the previous step are fed into numerical activation functions. To simplify the description for the mathematical definition of functional MLP, let’s consider a two layer functional MLP where there are K functional neurons on the first layer and one numerical neurons on the second layer [and providing the output data set as a second input to a fully connected neural network (FCNN), wherein the generated set of one or more values associated with the one or more system characteristics is the output of the FCNN; see annotated figure 2]. Mathematically, let the weight function for the r-th functional feature Xi,r(t) in the k-th functional neuron be denoted as Vk,r(βk,r,t) for k = 1,…, K and r = 1,…,R. The weight function Vk,r(βk,r,t) is assumed to be an easily computable function determined by a Qk,r-dimensional vector βk,r. Let the activation function in the k-th functional neuron be denoted by Uk(•), which is a numerical mapping from R to R with numerical parameters ak and bk. To simplify the notation, let the concatenated unknown parameters in the weight functions across R features and K functional neurons be β = [β1,1,…,β1,R,….,βK,1,…, βK,R]T. And the R functional feature curves of the i-th subject is denoted as Xi = [Xi,1(t),…,Xi,R(t)]. Then the real output of the first layer H(Xi, β) is [generating, using the FNN, an output data set]
PNG
media_image2.png
69
586
media_image2.png
Greyscale
”
PNG
media_image3.png
413
859
media_image3.png
Greyscale
)
In regards to claim 3 and analogous claim 13,
Baek and Wang teaches The method of claim 2,
Wang teaches wherein the output data set is associated with a set of latent features of the 2D time-and-frequency input data set.
Examiner interprets the limitation in light of the specification, ([0045], “The output data set, in some aspects, is associated with a set of latent features of the 2D time-and-frequency input data set that may be identified by the FNN. The generated one or more system characteristics may include at least one of an RUL of the system, a probability of failing within a second time period following the first time period, or a detected anomaly (e.g., a value associated with a detected anomaly or an indication of an anomaly in a set of possible anomalies).”)
(Wang, Section II A., “The goal of the RUL estimation problem is to learn a mathematical mapping from Xi to Yi [the output data set is associated ie mathematical mapping with a set of latent features of the 2D time-and-frequency input data set].”)
In regards to claim 4 and analogous claim 14,
Baek and Wang teaches The method of claim 1,
Baek teaches wherein measuring the data relating to the operation of the system comprises continuously measuring the data, at the sample rate, over the first time period.
(Baek, Description para. 1, “The present invention relates to a technique for predicting a residual useful life (RUL) by analyzing vibration signals collected from a facility or a part, and in particular, it is possible to continuously collect signals by attaching a vibration sensor”)
In regards to claim 8 and analogous claim 18,
Baek and Wang teaches The method of claim 1, further comprising:
Baek teaches measuring, at the sample rate, additional data relating to the operation of the system over a second time period; and producing an additional 2D time-and-frequency third input data set by applying the wavelet transform to the measured additional data relating to the operation of the system over the second time period, wherein generating the set of one or more values associated with the one or more system characteristics further comprises processing the additional 2D time-and-frequency third input data set [using the FNN.]
(Baek, Abstract, “A residual life prediction device is disclosed. The residual life prediction apparatus uses a data conversion unit that converts each of a plurality of one-dimensional vibration signals into a two-dimensional image, and uses a plurality of two-dimensional images generated by the data conversion unit as input data. Predictive model generation unit that trains an artificial neural network (ANN) model that outputs HI), and predicts the residual useful life (RUL) of a predicted facility or a predicted component using the trained ANN model [wherein generating the set of one or more values associated with the one or more system characteristics further comprises processing the additional 2D time-and-frequency third input data set; wherein the 2D data is input to the ANN] And a residual life prediction unit, and the data transformation unit generates the two-dimensional images by performing continuous wavelet transformation (CWT) [producing an additional 2D time-and-frequency third input data set by applying the wavelet transform to the measured additional data relating to the operation of the system over the second time period] on each of the one-dimensional vibration signals.”)
(Baek, Description para. 27, “FIG. 3 shows a contour plot of the wavelet power spectrum generated by the vibration signal and continuous wavelet transform (CWT). The vibration signal sampled at 0.1 s intervals at a frequency of 25.6 kHz has 2560 data points [measuring, at the sample rate, additional data relating to the operation of the system over a second time period; this would be another vibration signal].”
PNG
media_image1.png
561
704
media_image1.png
Greyscale
)
However, Baek does not explicitly teach using the FNN
Wang teaches using the FNN
(Wang, Section II B., “RUL estimation using functional MLP proceeds as follows. Functional MLP [using the FNN] consists of a layer of functional neurons followed by multiple layers of numerical neurons as in classic MLP. Functional neurons take the continuous sensor curves as input and output numerical numbers which are then fed into the subsequent numerical layers.”)
In regards to claim 9 and analogous claim 19,
Baek in view of Wang teaches The method of claim 1,
Baek teaches wherein the measured data is one of vibration data, acoustic data, or other time-varying data relating to an operation of the system.
(Baek, Description para. 1, “The present invention relates to a technique for predicting a residual useful life (RUL) by analyzing vibration signals collected from a facility or a part, and in particular, it is possible to continuously collect signals by attaching a vibration sensor.”)
In regards to claim 10 and analogous claim 20,
Baek and Wang teaches The method of claim 1,
Baek teaches wherein the one or more system characteristics comprises at least one of a remaining useful life of the system, a probability of failing within a second time period following the first time period, or a detected anomaly.
(Baek, Abstract, “A residual life prediction device is disclosed.”)
Claim(s) 5-7 and 15-17 are rejected under 35 U.S.C. 103 as being unpatentable over Baek in view of Wang in further view of Peter, W. Tse, Wen-xian Yang, and H. Y. Tam. "Machine fault diagnosis through an effective exact wavelet analysis." Journal of sound and vibration 277.4-5 (2004): 1005-1024. (“Tse”)
In regards to claim 5 and analogous claim 15,
Baek and Wang teaches The method of claim 1,
Baek discloses that the CWT transform may be a Morlet-based CWT
(Baek, Description para. 26, “In the present invention, a continuous wavelet transform (CWT) is used to extract features (eg, image features) from a vibration signal. According to an embodiment, the continuous wavelet transform may be a Morlet-based CWT.”)
Tse teaches wherein the first time period is divided into a set of time-windows at each of a plurality of scales with each scale in the plurality of scales corresponding to a range of frequencies represented in the 2D time-and-frequency first input data set.
(Tse, pg. 7 para. 1, “According to the definition of Eq. (2), the results of the Morlet CWT should only exist as a temporal waveform x1(t) from 0.075 to 0.1 s at frequency level 200 Hz, and another temporal waveform x2(t) from 0.125 to 0.15 s at frequency level 100 Hz. However, as shown in Fig. 4, the unexpected waveforms appear also at levels of 220 and 180 Hz, which are adjacent to 200 Hz.”; see annotated figure 4 below wherein Tse also teaches a time window (see time axes wherein a time window is 0.5 seconds)
PNG
media_image4.png
496
952
media_image4.png
Greyscale
)
Tse is considered to be analogous to the claimed invention because they are in the same field of machine fault diagnosis using wavelet analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Baek and Wang to incorporate the teachings of Tse in order to provide an exact wavelet analysis that improves upon CWT by providing the desirable result of no overlapping, distortion or redundant information. (Tse, Section 1.2, “Idealistically, each of the three temporal features of the raw signal should only appear in one scale that has the same frequency content and defined time frame as shown in Fig. 3. However, due to the problems of overlapping in adjacent scales and the distortion of the signal, the three temporal features appear in all three scales of the defined time frame as shown in Fig. 2. For the benefit of vibration-based machine fault diagnosis, the decomposed features that are obtained from an effective analyzing tool should possess all of the information on the amplitude, time and frequency exactly as they are in the original raw signal. That is, after the decomposition of the raw signal, each temporal feature should appear only in its expected scale and time frame exactly as it is displayed in the raw signal. The ideal results should have no overlapping, distortion or redundant information. Such a clear and precise result is called exact analysis. The aim of this paper is to develop an effective algorithm that will allow CWTs to achieve such a desirable result.”)
In regards to claim 6 and analogous claim 16,
Baek in view of Wang and Tse teaches The method of claim 5,
Tse teaches wherein applying the wavelet transform to the measured data to produce the 2D time-and-frequency first input data set comprises: applying, to each set of time-windows at each of the plurality of scales, a wavelet associated with the range of frequencies corresponding to the scale in the plurality of scales.
(Tse, pg. 7 para. 1, “According to the definition of Eq. (2), the results of the Morlet CWT [applying, to each set of time-windows at each of the plurality of scales, a wavelet (provided by the CWT) associated with the range of frequencies corresponding to the scale in the plurality of scales] should only exist as a temporal waveform x1(t) from 0.075 to 0.1 s at frequency level 200 Hz, and another temporal waveform x2(t) from 0.125 to 0.15 s at frequency level 100 Hz. However, as shown in Fig. 4, the unexpected waveforms appear also at levels of 220 and 180 Hz, which are adjacent to 200 Hz.”; see annotated figure 4 below
PNG
media_image4.png
496
952
media_image4.png
Greyscale
)
In regards to claim 7 and analogous claim 17,
Baek in view of Wang and Tse teaches The method of claim 6,
Tse teaches wherein each set of time-windows is a set of equal-size time- windows and the wavelet associated with each range of frequencies spans the equal-size time- windows in the set of equal-size time-windows associated with the range of frequencies.
(Tse, pg. 7 para. 1, “According to the definition of Eq. (2), the results of the Morlet CWT should only exist as a temporal waveform x1(t) from 0.075 to 0.1 s at frequency level 200 Hz, and another temporal waveform x2(t) from 0.125 to 0.15 s at frequency level 100 Hz. However, as shown in Fig. 4, the unexpected waveforms appear also at levels of 220 and 180 Hz, which are adjacent to 200 Hz.”; see annotated figure 4 below wherein the equal-size time-windows is 0.5
PNG
media_image5.png
496
925
media_image5.png
Greyscale
)
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JASMINE THAI whose telephone number is (703)756-5904. The examiner can normally be reached M-F 8-4.
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, Michael Huntley can be reached at (303) 297-4307. 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.
/J.T.T./Examiner, Art Unit 2129
/MICHAEL J HUNTLEY/Supervisory Patent Examiner, Art Unit 2129