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 Claims
Claims 1-10, 12, and 14-22 are pending and examined herein.
Claims 1-10, 12, and 14-22 are rejected under 35 U.S.C. 101.
Claims 1-10, 12, and 14-22 are rejected under 35 U.S.C. 103.
Information Disclosure Statement
The attached information disclosure statement(s) (IDS) filed on 09/12/2025 is/are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement(s) is/are being considered by the examiner.
Response to Arguments
Applicant's arguments filed 09/17/2025 regarding the 35 U.S.C. 101 rejection of claims 1-10, 12, and 14-22 have been fully considered but they are not persuasive. Applicant argues, see pages 2-3, that the claims reflect an improvement in the field of dry pumps and therefore integrate the judicial exception into a practical application. Specifically, Applicant cites the 2024 Patent Subject Matter Eligibility Guidance, which states “AI inventions may provide a particular way to achieve a desired output when they claim, for example, a specific application of AI to a particular technological field (i.e., a particular solution to a problem).” Applicant argues that the shutdown prediction model applied to the field of dry pumps is a particular solution to a problem. Examiner respectfully disagrees.
The 2024 Patent Subject Matter Eligibility Guidance, cited by Applicant, also states that “A key point of distinction to be made for AI inventions is between a claim that reflects an improvement to a computer or other technology described in the specification (which is eligible) and a claim in which the additional elements amount to no more than (1) a recitation of the words “apply it” (or an equivalent) or are no more than instructions to implement a judicial exception on a computer, or (2) a general linking of the use of a judicial exception to a particular technological environment or field of use (which is ineligible).” This is reflected in MPEP § 2106.05(a), which states "An important consideration in determining whether a claim improves technology is the extent to which the claim covers a particular solution to a problem or a particular way to achieve a desired outcome, as opposed to merely claiming the idea of a solution or outcome. McRO, 837 F.3d at 1314-15, 120 USPQ2d at 1102-03; DDR Holdings, 773 F.3d at 1259, 113 USPQ2d at 1107. In this respect, the improvement consideration overlaps with other considerations, specifically the particular machine consideration (see MPEP § 2106.05(b)), and the mere instructions to apply an exception consideration (see MPEP § 2106.05(f)). Thus, evaluation of those other considerations may assist examiners in making a determination of whether a claim satisfies the improvement consideration."
As written in the previous office action, the limitations that are “additional elements” are all either instructions to apply an exception or merely indicate a field of use. Thus, the claims do not represent a particular solution to a problem, and do not integrate the judicial exceptions into a practical application nor do they amount to significantly more than the judicial exceptions. Therefore, the claims are directed to an abstract idea without significantly more.
Applicant's arguments filed 09/17/2025 regarding the 35 U.S.C. 103 rejection of claims 1-10, 12, and 14-22 have been fully considered but they are not persuasive. Applicant argues, see pages 1-8, that Hur and Butler cannot be combined to obtain the solution of claims 1 in the present application. Specifically, Applicant argues that the operation of a dry pump has no relation to the “wind speed” of Hur. Examiner respectfully disagrees. MPEP § 2145(III) states "It is well-established that a determination of obviousness based on teachings from multiple references does not require an actual, physical substitution of elements." In re Mouttet, 686 F.3d 1322, 1332, 103 USPQ2d 1219, 1226 (Fed. Cir. 2012) (citing In re Etter, 756 F.2d 852, 859, 225 USPQ 1, 6 (Fed. Cir. 1985) (en banc)) ("Etter's assertions that Azure cannot be incorporated in Ambrosio are basically irrelevant, the criterion being not whether the references could be physically combined but whether the claimed inventions are rendered obvious by the teachings of the prior art as a whole."). See also In re Keller, 642 F.2d 413, 425, 208 USPQ 871, 881 (CCPA 1981) ("The test for obviousness is not whether the features of a secondary reference may be bodily incorporated into the structure of the primary reference.... Rather, the test is what the combined teachings of those references would have suggested to those of ordinary skill in the art."); In re Sneed, 710 F.2d 1544, 1550, 218 USPQ 385, 389 (Fed. Cir. 1983) ("[I]t is not necessary that the inventions of the references be physically combinable to render obvious the invention under review."); and In re Nievelt, 482 F.2d 965, 179 USPQ 224, 226 (CCPA 1973) ("Combining the teachings of references does not involve an ability to combine their specific structures."). The teachings of the prior art as a whole render the claimed invention obvious. As stated in the previous office action, see page 11, “Tower bending movement is a variable gathered for early warning of wind turbine shutdown. One of ordinary skill in the art would realize that having access to certain variables, as suggested by the introduction, would be helpful to maintenance and additionally would provide information for early warning of equipment shutdown. Therefore, this is a method for early warning of equipment shutdown. Though the method taught by Hur does not mention dry pumps, the method could be followed for dry pumps using a different measurement.”
Applicant further argues that the 3D wind model and the 3 bladed rotor model cannot be equivalent to historical operating data of a dry pump, and that a person skilled in the art could not easily envisage using the extended Kalman filter model of Hur in the dry pump of Butler. Firstly, page 14 maps obtaining historical operating data of a dry pump to Butler. The historical data obtained by Hur is included as it relates to the operating data of a piece of equipment. One of ordinary skill in the art would realize that a dry pump model could be built using historical operating data as the wind model is built using historical operating data.
Applicant further argues that the wind speed cannot be “operating data of the dry pump”. The previous office action, see page 13, states that the operating data is of, not the dry pump, but of the equipment. The dry pump is also a piece of equipment. One of ordinary skill would be motivated to replace the operating data of the equipment, taught by Hur, with the operating data of the dry pump, taught by Butler. Page 14 of the previous office action maps the operating data/shutdown early warning information of the dry pump to Butler. The teachings of the prior art as a whole render the claimed invention obvious.
Applicant further argues that the tower bending movement of Hur cannot be used to predict shutdown of the dry pump. Page 14 of the office action states that Butler teaches a method for early warning of dry pump shutdown. One of ordinary skill in the art would be motivated to replace the wind speed information of Hur with the dry pump information of Butler, meaning that the model would predict the shutdown of the dry pump when combined. Thus, the claims are rendered obvious.
Applicant further argues that "The Office Action asserted that "It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Hur with the teachings of Butler because as Butler states in the conclusion on page 1640, 'This could help reduce pump maintenance costs, but also, the costs associated with scrapped wafers, tool downtime and chamber cleaning, following an unexpected pump failure."' Emphasis added. Applicant respectfully disagrees. That is because the "this" in the text of Butler does not mean the solution of Hur. The true content of Butler is that "In this paper, we have presented a method to both, identify the current level of vacuum pump degradation, and to estimate the RUL of a dry vacuum pump. The developed solution has the potential to reduce the instances of unexpected pump failures caused by pump degradation. This could help reduce pump maintenance costs, but also, the costs associated with scrapped wafers, tool downtime and chamber cleaning, following an unexpected pump failure" (the section of CONCLUSIONS)." Examiner agrees that this is the context for the motivation. However, this is the motivation to combine the dry pump of Butler with Hur, meaning that the motivation stated in Butler is intended to be about Butler. The motivation to combine is “The developed solution has the potential to reduce the instances of unexpected pump failures caused by pump degradation. This could help reduce pump maintenance costs, but also, the costs associated with scrapped wafers, tool downtime and chamber cleaning, following an unexpected pump failure." Butler also teaches an early warning shutdown method for dry pumps. Therefore, one would be motivated to use the method of Hur using dry pumps as taught by Butler.
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 1-10, 12, and 14-22 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
MPEP § 2109(III) sets out steps for evaluating whether a claim is drawn to patent-eligible subject
matter. The analysis of claims 1-10, 12, and 14-22 in accordance with these steps, follows.
Step 1 Analysis:
Step 1 is to determine whether the claim is directed to a statutory category (process, machine,
manufacture, or composition of matter. Claims 1-10 are directed to a process, claims 12 and 15-22 are directed to a machine, and claim 14 is directed to a manufacture. All claims are directed to a statutory category and analysis proceeds.
Step 2A Prong One, Step 2A Prong Two, and Step 2B Analysis:
Step 2A Prong One asks if the claim recites a judicial exception (abstract idea, law of nature, or natural phenomenon). If the claim recites a judicial exception, analysis proceeds to Step 2A Prong Two, which asks if the claim recites additional elements that integrate the abstract idea into a practical application. If the claim does not integrate the judicial exception, analysis proceeds to Step 2B, which asks if the claim amounts to significantly more than the judicial exception. If the claim does not amount to significantly more than the judicial exception, the claim is not eligible subject matter under 35 U.S.C. 101.
None of the claims represent an improvement to technology.
Regarding claim 1, the following claim elements are abstract ideas:
building a Kalman filter model by using the historical operating data (Building a Kalman filter is implementing a series of mathematical calculations, which are mathematical concepts.)
predicting predicted operating data of the dry pump through the Kalman filter model; (Using the Kalman filter model is performing mathematical calculations, which are mathematical concepts.)
The following claim elements are additional elements which, taken alone or in combination with
the other additional elements, do not integrate the judicial exception into a practical application nor
amount to significantly more than the judicial exception: A method for early warning of dry pump shutdown, wherein the method comprises: (This merely indicates a field of use, early warning of dry pump shutdown. See MPEP § 2106.05(h).)
obtaining historical operating data of a dry pump; (This is the existing process of receiving data, meaning that this limitation is mere instructions to apply an exception. See MPEP § 2106.05(f)(2).)
training a shutdown prediction model by using the historical operating data and the predicted operating data; and (This recites generic training; this is mere instructions to apply an exception.)
inputting current operating data of the dry pump into the trained shutdown prediction model to obtain shutdown early warning information of the dry pump. (Inputting data is the existing process of transmitting data; this is mere instructions to apply an exception. See MPEP § 2106.05(f)(2).)
Regarding claim 2, the rejection of claim 1 is incorporated herein. Further, the following are abstract ideas:
identifying an operating state type of the predicted operating data; (Identifying a type of data is the mental process of evaluation.)
labeling the historical operating data according to the operating state type; and (One could practically label the data in the human mind with the aid of pen and paper. This is a mental process.)
The following claim elements are additional elements which, taken alone or in combination with the other additional elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
training the shutdown prediction model by using the labeled historical operating data. (This recites generic training; this is mere instructions to apply an exception.)
Regarding claim 3, the rejection of claim 2 is incorporated herein. Further, the following are abstract ideas:
the identifying the operating state type of the predicted operating data comprises: (Identifying a type of data is the mental process of evaluation.)
when the predicted operating data exceeds a normal operating data range, determining the predicted operating data as the shutdown type; and (Determining a type of data is the mental process of evaluation.)
when the predicted operating data does not exceed a normal operating data range, determining the predicted operating data as the normal type. (Determining a type of data is the mental process of evaluation.)
The following claim elements are additional elements which, taken alone or in combination with the other additional elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:]
wherein operating state type at least comprises: a shutdown type and a normal type; and (This merely limits the abstract idea to the field of use of anomaly detection. See MPEP § 2106.05(h).)
Regarding claim 4, the rejection of claim 1 is incorporated herein. Further, the following are abstract ideas:
analyzing correlations between operating data of different dimensions in the full operating data and a shutdown event of the dry pump; and (Analyzing data can be practically performed in the human mind. This is a mental process.)
taking the operating data of at least one dimension with the correlation meeting a correlation requirement of the shutdown event as the historical operating data. (This is identifying data as a type, which is the mental process of evaluation.)
The following claim elements are additional elements which, taken alone or in combination with the other additional elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
obtaining full operating data of the dry pump; (This is the existing process of receiving data; this is mere instructions to apply an exception.)
Regarding claim 5, the rejection of claim 4 is incorporated herein. Further, the following are abstract ideas:
determining the correlations between the operating data of different dimensions and the shutdown event of the dry pump according to variation values of the variation trends. (Determining correlations between data according to variation values is a mental process, as it can be practically performed by the human mind, given the data.)
The following claim elements are additional elements which, taken alone or in combination with the other additional elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
obtaining variation trends of the operating data of different dimensions in the full operating data near a shutdown time point of the dry pump; and (This is the existing process of receiving data; this is mere instructions to apply an exception.)
Regarding claim 6, the rejection of claim 4 is incorporated herein. Further, the following are abstract ideas:
building a multidimensional model of the operating data of different dimensions in the full operating data; (One could practically build a conceptual multidimensional model in the human mind. This is a mental process.)
determining the correlations between the operating data of different dimensions and the shutdown event of the dry pump according to the measures of dispersion. (One could practically determine correlations between data, given the data and using pen and paper, in the human mind. This is a mental process.)
The following claim elements are additional elements which, taken alone or in combination with the other additional elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
obtaining measures of dispersion of the operating data of different dimensions in the multidimensional model; and (This is the existing process of receiving data; this is mere instructions to apply an exception.)
Regarding claim 7, the rejection of claim 1 is incorporated herein. Further, the following are abstract ideas:
initializing dynamic parameters of the Kalman filter model; and (Initializing dynamic parameters is inserting numbers into a mathematical formula, which is a mathematical concept.)
adjusting the dynamic parameters in the initialized Kalman filter model by using the historical operating data until an execution of the adjusted Kalman filter model meets a building requirement. (Adjusting dynamic parameters is adjusting numbers into a mathematical formula, which is a mathematical concept. Executing the model is performing mathematical calculations, which is a mathematical concept.)
Claim 7 does not recite any additional elements.
Regarding claim 8, the rejection of claim 7 is incorporated herein. Further, the following is an abstract idea:
wherein the Kalman filter model is:
X
=
a
0
t
2
+
v
0
t
+
x
0
X
=
A
t
+
B
wherein, X represents a vector matrix of the historical operating data, t represents a time matrix, A represents a transition matrix, B represents a random term, and
a
0
,
v
0
, and
x
0
represent the dynamic parameters. (These are mathematical equations, which are mathematical concepts.)
Claim 8 does not recite any additional elements.
Regarding claim 9, the rejection of claim 1 is incorporated herein. Further, the following are abstract ideas:
filtering invalid data in the historical operating data, wherein the invalid data comprise: at least one of an error value, a null value and a duplicate value. (Filtering data can practically be performed in the human mind with the aid of pen and paper, i.e. crossing out data points that are null.)
Claim 9 does not recite any additional elements.
Regarding claim 10, the rejection of claim 1 is incorporated herein. Further, the following are abstract ideas:
normalizing the historical operating data to a target data field. (Normalizing data is a mathematical calculation, which is a mathematical concept.)
Regarding claim 12, the following claim elements are additional elements which, taken alone or in combination with the other additional elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
A computer-processing device, comprising: (This is a generic computer part; this is mere instructions to apply an exception.)
a memory in which a computer-readable code is stored; and (This is a generic computer part with a generic function; this is mere instructions to apply an exception.)
one or more processors, wherein when the computer-readable code is executed by the one or more processors (These are generic computer components and a generic function; this is mere instructions to apply an exception.), the computing-processing device executes a method for early warning of dry pump shutdown, wherein the method comprises: (This merely indicates a field of use, early warning of dry pump shutdown. See MPEP § 2106.05(h).)
The rest of claim 12 recites substantially similar subject matter to claim 1 and is rejected with the same rationale, mutatis mutandis.
Regarding claim 14, the rejection of claim 1 is incorporated herein. Further, the following claim elements are additional elements which, taken alone or in combination with the other additional elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
A non-transitory computer readable medium storing a computer program of the method (This is a generic computer part and generic function; this is mere instructions to apply an exception.) for early warning of dry pump shutdown according to claim 1. (This merely indicates a field of use, early warning of dry pump shutdown. See MPEP § 2106.05(h).)
Claims 15-22 recite substantially similar subject matter to claims 2, 4, 7, 9, 10, 3, 5, and 6 respectively and are rejected with the same rationale, mutatis mutandis.
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) 1, 12, and 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hur (“Estimation of Useful Variables in Wind Turbines and Farms Using Neural Networks and Extended Kalman Filter”, 2019) and Butler (“Prediction of Vacuum Pump Degradation in Semiconductor Processing”, 2009).
Regarding claim 1, Hur teaches A method for early warning of [machine] shutdown, wherein the method comprises: (The abstract states "Having access to certain variables, which are normally not measured, could be beneficial to maintenance, condition monitoring, and control of wind turbines and farms. However, incorporating additional sensors to measure such variables could increase the overall cost significantly. It is therefore proposed in this feasibility study that only one turbine in a wind cluster of several turbines be equipped with a sensor and each of the remaining turbines with an estimator, instead of equipping each turbine with an expensive sensor." The introduction states "In this paper, tower bending moment (TBM), which is normally not measured as an expensive strain gauge is otherwise required, is the variable considered and estimated using NN based estimators." Tower bending movement is a variable gathered for early warning of wind turbine shutdown. One of ordinary skill in the art would realize that having access to certain variables, as suggested by the introduction, would be helpful to maintenance and additionally would provide information for early warning of equipment shutdown. Therefore, this is a method for early warning of equipment shutdown. Though the method taught by Hur does not mention dry pumps, the method could be followed for dry pumps using a different measurement.)
obtaining historical operating data of a [piece of equipment]; (Page 24019 states "1) Turbine 1 is equipped with a sensor and each of the rest with a nonlinear NN-based estimator. 2) At regular intervals, i.e., every 1000s in this paper, the inputs (different several combinations of torque, rotor speed, and FAA as shown below) and the output (TBM) are measured and collected from Turbine 1 model." The inputs and output are interpreted as the historical operating data. Additionally, page 24022, section III-A discusses a wind speed model, and page 24024, section III-B discusses a nonlinear 3 bladed aerodynamic model. One of ordinary skill in the art would realize that these models are based on historical operating data of the equipment that they model. Therefore, this is also interpreted as historical operating data.)
building a Kalman filter model by using the historical operating data (Page 24026, section D goes over the extended Kalman filter model that uses "The combination of the 3D wind model in Section III-A and 3 bladed rotor model in Section III-B". As above, these models are created by historical operating data, and therefore the Kalman filter model is build using the historical operating data.)
predicting predicted operating data of the dry pump through the Kalman filter model; (Page 24027 states "In Figure 12, both point wind speed (Figure 12(a)) and effective wind speed (Figure 12(b)) are estimated (in blue) and compared with the actual wind speed (in red), which would be unavailable in real life. The results demonstrate that the EKF estimates the actual wind speed closely." The estimation of wind speed is interpreted as the predicted operating data because it is predicted using the Kalman filter.)
training a shutdown prediction model by using the historical operating data and the predicted operating data; and (Page 24027 states "The NN-based estimator introduced in Section II is improved in this section by incorporating the wind speed estimate
V
0
from the EKF introduced in Section III into the training process. This essentially improves the resolution of the NN-based estimators." Page 24027 further states "The procedure described in Section II-C is repeated, introducing a new scenario as follows: Scenario 4: torque, rotor speed, FAA, and wind speed (estimate)". As before, the torque, rotor speed and FAA are interpreted as the historical operating data, as it is collected, and the estimated wind speed is interpreted as the predicted operating data. The NN-based estimator is interpreted as the shutdown prediction model because, as the introduction states, "In this paper, tower bending moment (TBM), which is normally not measured as an expensive strain gauge is otherwise required, is the variable considered and estimated using NN based estimators." Tower bending movement is a variable gathered for early warning of wind turbine shutdown. One of ordinary skill in the art would realize that having access to certain variables, as suggested by the introduction, would be helpful to maintenance and additionally would provide information for early warning of equipment shutdown.)
inputting current operating data of [the equipment] into the trained shutdown prediction model to obtain shutdown early warning information of [the equipment]. (Page 24020 states "Figure 4 illustrates that the estimate from each NN-based estimator does not track the measurement closely enough with Turbine 4 demonstrating the poorest performance. Figure 5 shows that the tracking is significantly improved by including an additional variable, FAA, in the training process. Even with a fault present, Figure 6 demonstrates that the estimates seem to follow the measurements more closely than Figure 4." As the estimates are shown in the figures, the current operating data of Turbine 1 (torque, rotor speed, and FAA) must be input into the trained model. The output of tower bending movement is interpreted as the shutdown early warning information, because, as established above, tower bending movement is used for early warning of shutdown for windmills.)
Hur does not appear to explicitly teach
[a method for early warning of] dry pump [shutdown]
[obtaining historical data of] a dry pump
[obtain shutdown early warning information of] the dry pump
However, Butler—directed to analogous art—teaches
[a method for early warning of] dry pump [shutdown] (Page 1636, section 2 states "During its lifetime, a dry vacuum pump is exposed to largequantities of often toxic and corrosive gases. … The proposed solution comprises two elements. A diagnostic element to determine the current level of pump degradation and a prognostic element to provide an estimate of the RUL of the pump, given the current degradation level and rate of degradation. Artificial Neural Networks (ANNs) are employed to model the level of pump degradation, and a Double Exponential Smoothing Prediction (DESP) method is used to estimate the RUL of the pump." The remaining useful life indicates how long it will be until the dry pump shuts down, and is therefore an early warning of shutdown for the dry pump.)
[obtaining historical data of] a dry pump (Page 1636, section 3 states "In this study, dry pump data from 14 processing chambers in a major semiconductor manufacturing facility was available. Each of the chambers run a similar deposition process. Pump data covering approximately one full year of operation is available. The recorded data includes variables such as current, power, temperature and exhaust pressure." The recorded data is historical data.)
[obtain shutdown early warning information of] the dry pump (Page 1640 states "Figure 5 illustrates the performance of the DESP method applied to the prediction of the RUL of a pump from 80% observed degradation. Also shown is the actual rate of degradation in the pump, and the approximate 95% confidence limits of the prediction." The remaining useful life indicates how long it will be until the dry pump shuts down, and is therefore an early warning of shutdown for the dry pump.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Hur with the teachings of Butler because as Butler states in the conclusion on page 1640, "This could help reduce pump maintenance costs, but also, the costs associated with scrapped wafers, tool downtime and chamber cleaning, following an unexpected pump failure."
Regarding claim 12, Hur teaches
A computer-processing device, comprising: (Page 24019 states "The algorithm is implemented using the Neural Networks ToolboxTM in Matlab/Simulink." Matlab and Simulink are programs implemented on a computer. Therefore, a computer-processing device is used for the method taught.)
a memory in which a computer-readable code is stored; and (In order for a program to run, code must be available in memory. As the method is implemented on Matlab/Simulink, a memory with code is present.)
one or more processors, wherein when the computer-readable code is executed by the one or more processors, the computing-processing device executes a method for early warning of dry pump shutdown, wherein the method comprises: (In order for the method to run, a processor must execute the computer-readable code. Therefore, a processor that executes the computer-readable code with the method is present. The abstract states "Having access to certain variables, which are normally not measured, could be beneficial to maintenance, condition monitoring, and control of wind turbines and farms. However, incorporating additional sensors to measure such variables could increase the overall cost significantly. It is therefore proposed in this feasibility study that only one turbine in a wind cluster of several turbines be equipped with a sensor and each of the remaining turbines with an estimator, instead of equipping each turbine with an expensive sensor." The introduction states "In this paper, tower bending moment (TBM), which is normally not measured as an expensive strain gauge is otherwise required, is the variable considered and estimated using NN based estimators." Tower bending movement is a variable gathered for early warning of wind turbine shutdown. One of ordinary skill in the art would realize that having access to certain variables, as suggested by the introduction, would be helpful to maintenance and additionally would provide information for early warning of equipment shutdown. Therefore, this is a method for early warning of equipment shutdown. Though the method taught by Hur does not mention dry pumps, the method could be followed for dry pumps using a different measurement.)
The rest of claim 12 recites substantially similar subject matter to claim 1 and is rejected with the same rationale, mutatis mutandis.
Regarding claim 14, the rejection of claim 1 is incorporated herein. Hur teaches
A non-transitory computer readable medium storing a computer program of the method for early warning of dry pump shutdown according to claim 1. (Page 24019 states "The algorithm is implemented using the Neural Networks ToolboxTM in Matlab/Simulink." Matlab and Simulink are programs implemented on a computer. In order for a program to run, code must be available in a non-transitory computer readable medium. As the method is implemented using a program, the code is available on a non-transitory computer readable medium.)
Claim(s) 2 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hur (“Estimation of Useful Variables in Wind Turbines and Farms Using Neural Networks and Extended Kalman Filter”, 2019) and Butler (“Prediction of Vacuum Pump Degradation in Semiconductor Processing”, 2009) as applied to claim 1 above, further in view of Chao (US 2015/0142384 A1).
Regarding claim 2, the rejection of claim 1 is incorporated herein. The combination of Hur and Butler does not appear to explicitly teach
identifying an operating state type of the predicted operating data;
labeling the historical operating data according to the operating state type; and
training the shutdown prediction model by using the labeled historical operating data.
However, Chao—directed to analogous art—teaches
identifying an operating state type of the predicted operating data; ([0049] states "The model of FIG. 2 may be fully described by parameters
Ω
=
(
θ
,
w
}
, with
θ
being the parameters for the Kalman filters and
w
being the parameters for the logistic function. Once
Ω
is known, for every test point
x
t
, the class label may be assigned based on:
P
y
t
-
1
x
1
:
t
,
Ω
=
∫
u
t
P
y
t
u
t
,
w
P
u
t
x
1
:
t
,
θ
d
u
t
≈
P
y
t
m
t
,
w
.
" As the parameterized Kalman filter is involved in the identification of the labels, the label is assigned to the predicted operating data (the data going through the equation). [0032] states "This binary output may be expressed as a class label y, where y may equal one of two discrete values, for example, +1 indicating failure and -1 indicating normal operation." Therefore, the labels are operating state type.)
labeling the historical operating data according to the operating state type; and (According to the above, the test points, interpreted as the historical operating data, are assigned based on the operating state type.)
training the shutdown prediction model by using the labeled historical operating data. ([0054] states "For example, the training may include two steps. In the first step,
w
and
θ
may be learned, as described in detail above. In the second step,
m
t
, the mean of hidden variable
u
t
, for every training data point, may be extracted and a nonlinear classifier may be learned based on all pairs of
m
t
and
y
t
. As above,
θ
and
w
are used to find the label. Thus, the classifier is learned based on the labeled historical operating data."
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Hur and Butler with the teachings of Chao because, as stated by Chao, "In contrast, exemplary embodiments of the present invention may incorporate hid den variables (for example, as seen in FIG. 2) into the model such that feature extraction or inference of hidden variable
u
t
is done automatically. The features extracted in this way may increase the discriminative power of this model."\
Claim 15 recites substantially similar subject matter to claim 2 and is rejected with the same rationale, mutatis mutandis.
Claim(s) 3 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hur (“Estimation of Useful Variables in Wind Turbines and Farms Using Neural Networks and Extended Kalman Filter”, 2019) and Butler (“Prediction of Vacuum Pump Degradation in Semiconductor Processing”, 2009) as applied to claim 1 above, further in view of Chao (US 2015/0142384 A1) as applied to claim 2 above, further in view of Yang (“State Estimation for Predictive Maintenance using Kalman filter”, 1999).
Regarding claim 3, the rejection of claim 2 is incorporated herein. The combination of Hur and Butler does not appear to explicitly teach
wherein operating state type at least comprises: a shutdown type and a normal type; and
the identifying the operating state type of the predicted operating data comprises:
when the predicted operating data exceeds a normal operating data range, determining the predicted operating data as the shutdown type; and
when the predicted operating data does not exceed a normal operating data range, determining the predicted operating data as the normal type.
However, Chao—directed to analogous art—teaches
wherein operating state type at least comprises: a shutdown type and a normal type; and ([0032] states "This binary output may be expressed as a class label y, where y may equal one of two discrete values, for example, +1 indicating failure and -1 indicating normal operation." Failure is interpreted as shutdown.)
[identifying operating state type of] the predicted operating data (See explanation of claim 2.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Hur and Butler with the teachings of Chao for the reasons given above in regards to claim 2.
Chao does not appear to explicitly teach
the identifying the operating state type of the [data] comprises:
when the predicted operating data exceeds a normal operating data range, determining the predicted operating data as the shutdown type; and
when the predicted operating data does not exceed a normal operating data range, determining the predicted operating data as the normal type.
However, Yang—directed to analogous art—teaches
the identifying the operating state type of the [data] comprises: (Page 35 states "Besides, the following parameters are used to conduct failure prediction:")
when the predicted operating data exceeds a normal operating data range, determining [the data] as the shutdown type; and (Pages 35-26 state "The failure threshold of the motor is defined as 5% less than the normal value, which is set to be the initial estimate in the Kalman prediction procedure. That is, the motor is judged to fail if the rotating speed drops to 95%
of the normal value." 95%-100% of the normal value is interpreted as the normal range. Thus, if the motor’s rotating speed exceeds (goes outside of) the range, the motor is judged to fail (shutdown).)
when the predicted operating data does not exceed a normal operating data range, determining [the data] as the normal type. (As above, when the motor is not outside of the range, it is normal.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Hur, Butler, and Chao with the teachings of Yang because, as stated by Yang, "If a device is judged to know that it is going to fail by the predicted future state variables, the failure can be prevented in time by PM. However, future state variables should be accurately predicted at a reasonably long time ahead of failure occurrence."
Claim 20 recites substantially similar subject matter to claim 3 and is rejected with the same rationale, mutatis mutandis.
Claim(s) 4-6, 16, 21, and 22 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hur (“Estimation of Useful Variables in Wind Turbines and Farms Using Neural Networks and Extended Kalman Filter”, 2019) and Butler (“Prediction of Vacuum Pump Degradation in Semiconductor Processing”, 2009) as applied to claim 1 above, further in view of Lim (US 2008/0294382 A1).
Regarding claim 4, the rejection of claim 1 is incorporated herein. The combination of Hur and Butler does not appear to explicitly teach
obtaining full operating data of the dry pump;
analyzing correlations between operating data of different dimensions in the full operating data and a shutdown event of the dry pump; and
taking the operating data of at least one dimension with the correlation meeting a correlation requirement of the shutdown event as the historical operating data.
However, Lim—directed to analogous art—teaches
obtaining full operating data of the dry pump; (The abstract states "A method of predicting a pump fault according to example embodiments may include collecting data in real time for qualitative variables associated with a pump and a corresponding semiconductor fabricating process, wherein the pump is configured to create a vacuum in a chamber during the semiconductor fabricating process." Therefore, the pump is a dry pump. [0037] states "According to example embodiments, the pump replacement time may be determined by analyzing the correlation and contribution level after an abnormal condition of a pump is detected from a T2 chart. Principal components may be extracted from qualitative variables related to a semiconductor fabricating process and a pump using a PCA method. The dispersion of the principal components may be observed, for instance, with a T2 curve, and control lines may be generated. Thus, various qualitative variables relating to the pump and corresponding semiconductor fabrication process may be monitored in real time, principal components (e.g., two or three principal components) may be selected using a PCA algorithm, and the abnormal state of a pump may be detected by managing the dispersion of the selected principal components." The operating data that is used during selection using a PCA algorithm is interpreted as the full operating data, as components of this data are chosen as the principal components.)
analyzing correlations between operating data of different dimensions in the full operating data and a shutdown event of the dry pump; and ([0092] states "FIG. 7 is a contribution level chart for a period C or D in a T2 chart of FIG.3 when a pump is in an abnormal state. In the T2 chart, the contribution level for the normal state period may have a different value from the contribution level for the abnormal state period. The contribution level of each variable in FIG. 6 is relatively uniform in that a variable having a relatively large contribution level is not observed. On the contrary, the contribution level of each variable in FIG. 7 is not uniform in that the contribution level of the variable T3 is relatively large." This is analyzing correlations in the abnormal state, interpreted as a shutdown event.)
taking the operating data of at least one dimension with the correlation meeting a correlation requirement of the shutdown event as the historical operating data. ([0093] states "FIG. 8 may illustrate the contribution level of each variable at a time point approximately one week before the pump stops because of a pump fault. In FIG. 8, the contribution of the variable T3 is about 31 and is comparatively larger than the contribution levels of the other variables. If a T2 chart is referred to, it may be possible to determine whether the UCL of the T2 chart has been exceeded at the time points of FIG. 7 and FIG. 8. " [0094] states "On the other hand, because the relatively large contribution level of the variable T3 is shown in FIG. 7, it may be possible to predict that the variable T3 will cause the pump fault. Also, because the contribution level of the variable T3 increases in FIG. 8, it may be possible to predict that the pump will stop in a relatively short period of time. Thus, the T 2chart may be used to detect an abnormal state, and the contribution level chart may be used to detect the variable causing the abnormal state. The pump fault may be predicted by monitoring the variation of the contribution level of the variable causing the abnormal state." Therefore, the variable (dimension) is higher than (meets a requirement) and is used to monitor the abnormal state (shutdown event), and is therefore historical operating data.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Hur and Butler with the teachings of Lim because, as stated by Lim in [0109] "As described above, the pump fault prediction apparatus and the method according to example embodiments may sufficiently consider the correlation of multivariate data including numerous variables related to pumps and their corresponding semiconductor fabricating processes. Thus, the apparatus and method according to example embodiments may provide increased productivity associated with the maintenance and replacement of pumps. Accordingly, pumps may be repaired and/or replaced without process interruption and product yield deterioration may be reduced or prevented."
Regarding claim 5, the rejection of claim 4 is incorporated herein. The combination of Hur and Butler does not appear to explicitly teach
obtaining variation trends of the operating data of different dimensions in the full operating data near a shutdown time point of the dry pump; and
determining the correlations between the operating data of different dimensions and the shutdown event of the dry pump according to variation values of the variation trends.
However, Lim—directed to analogous art—teaches
obtaining variation trends of the operating data of different dimensions in the full operating data near a shutdown time point of the dry pump; and ("FIG. 8 may illustrate the contribution level of each variable at a time point approximately one week before the pump stops because of a pump fault." The variables are interpreted as dimensions in the full operating data. As there is a chart, the contribution levels, interpreted as variation trends, are obtained.)
determining the correlations between the operating data of different dimensions and the shutdown event of the dry pump according to variation values of the variation trends. (The correlations are determined in [0094], "On the other hand, because the relatively large contribution level of the variable T3 is shown in FIG. 7, it may be possible to predict that the variable T3 will cause the pump fault. Also, because the contribution level of the variable T3 increases in FIG. 8, it may be possible to predict that the pump will stop in a relatively short period of time. Thus, the T2 chart may be used to detect an abnormal state, and the contribution level chart may be used to detect the variable causing the abnormal state. The pump fault may be predicted by monitoring the variation of the contribution level of the variable causing the abnormal state.")
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Hur and Butler with the teachings of Lim for the reasons given above in regards to claim 4.
Regarding claim 6, the rejection of claim 4 is incorporated herein. The combination of Hur and Butler does not appear to explicitly teach
building a multidimensional model of the operating data of different dimensions in the full operating data;
obtaining measures of dispersion of the operating data of different dimensions in the multidimensional model; and
determining the correlations between the operating data of different dimensions and the shutdown event of the dry pump according to the measures of dispersion.
However, Lim—directed to analogous art—teaches
building a multidimensional model of the operating data of different dimensions in the full operating data; ([0051] states "A method of calculating a covariance matrix, an eigenvalue, and an eigenvector will be described below. Table 1 shows a data matrix formed of data collected based on, for instance, five social economical parameters (TOP, MSY. TOE, HSE, and MVH) for 14 regions. TOP denotes the total population, MSY denotes a middle tier of academic back ground, TOE denotes the total number of the employed, HSE denotes people in the medical service field, and MVH denotes the price of a middle tier house." This data matrix is interpreted as the multidimensional model.)
obtaining measures of dispersion of the operating data of different dimensions in the multidimensional model; and([0053] states “Table 3 shows a covariance matrix of the data matrix. The covariance matrix is a square matrix calculated by multiplying the data matrix and a transpose matrix of the data matrix.” [0058] states "Table 5 shows eigenvectors of each principal com ponent. Because it may be beneficial to calculate the eigen vectors from a square matrix, the eigenvectors may be calculated from the covariance matrix." [0061] states "Because the dispersion of each principal component may be identical to the eigenvalue, a ratio of each eigenvalue and the sum of the eigenvalues may be calculated. The calculated ratio may denote a ratio where each principal component describes the entire dispersion.")
determining the correlations between the operating data of different dimensions and the shutdown event of the dry pump according to the measures of dispersion. ([0062] states "Consequently, two principal components may be selected from among five principal components to represent the information of the five variables. Therefore, the equation degree may be reduced through PCA." [0065] states "Once the principal components are obtained, the control lines may be established. The control lines may provide limits for determining whether a monitored variable is in an abnormal state (e.g., fault state) with respect to its correlation with the entire data. To set up the values of the control lines, a Hotelling T2 chart may be used." See claims 4 and 5 for how the T2 chart is used to determine correlations.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Hur and Butler with the teachings of Lim for the reasons given above in regards to claim 4.
Claims 16, 21, and 22 recite substantially similar subject matter to claims 4-6 respectively and are rejected with the same rationale, mutatis mutandis.
Claim(s) 7 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hur (“Estimation of Useful Variables in Wind Turbines and Farms Using Neural Networks and Extended Kalman Filter”, 2019) and Butler (“Prediction of Vacuum Pump Degradation in Semiconductor Processing”, 2009) as applied to claim 1 above, further in view of Chan (“Applied Intelligent Control of Induction Motor Drives: Chapter 9”, 2011).
Regarding claim 7, the rejection of claim 1 is incorporated herein. Hur and Butler do not appear to explicitly teach
initializing dynamic parameters of the Kalman filter model; and
adjusting the dynamic parameters in the initialized Kalman filter model by using the historical operating data until an execution of the adjusted Kalman filter model meets a building requirement.
However, Chan—directed to analogous art—teaches
initializing dynamic parameters of the Kalman filter model; and (Page 1, section 9.2 introduces the Kalman filter model: “(9.1)
x
˙
=
A
x
+
B
u
+
G
t
w
t
(System) (9.2)
y
=
C
x
+
v
t
(Measurement)”. Page 2 states “In Equations (9.1) and (9.2),
G
(
t
)
is the noise-weight matrix,
w
(
t
)
is noise matrix of output model (measurement noise). The covariance matrices
Q
and
R
of these noises are defined as:”. Page 7, section 9.5 states "In order to find the best matrices
G
,
Q
, and
R
for the EKF, a real-coded GA is employed." Page 7 further states "b. Initial Generation. It begins by randomly generating an initial population of the long real-coded strings." As the matrices are changed, they are interpreted as the dynamic parameters, which are initialized.)
adjusting the dynamic parameters in the initialized Kalman filter model by using the historical operating data until an execution of the adjusted Kalman filter model meets a building requirement. (Page 7 states "6. Performance measure: the mean squared error between the actual rotor speed and the estimated speed." The estimate comes from the Kalman filter, and the actual rotor speed is interpreted as the historical operating data. Page 7 further states "g. Iteration. The real-coded GA runs iteratively repeating the processes (c) to (g) until a population convergence condition is met or the given maximum number of iterations is reached." The population convergence condition is interpreted as the building requirement.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Hur and Butler with the teachings of Chan, because, as Chan states on page 1, "Kalman filter is a special kind of observer which provides optimal filtering of the noises in measurement and inside the system if the covariances of these noises are known. When rotor speed (as an extended state) is added into the dynamic model of an induction motor, the extended Kalman filter (EKF) can be used to re-linearize the nonlinear state model for each new estimate as it becomes available." In the instant application, the model is also nonlinear (see claim 8), and it would therefore be obvious to combine.
Claim 17 recites substantially similar subject matter to claim 7 and is rejected with the same rationale, mutatis mutandis.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hur (“Estimation of Useful Variables in Wind Turbines and Farms Using Neural Networks and Extended Kalman Filter”, 2019) and Butler (“Prediction of Vacuum Pump Degradation in Semiconductor Processing”, 2009) as applied to claim 1 above, further in view of Chan (“Applied Intelligent Control of Induction Motor Drives: Chapter 9”, 2011), as applied to claim 7 above, further in view of Math’s Fun (“Real World Examples of Quadratic Equations, 2021).
Regarding claim 8, the rejection of claim 7 is incorporated herein. Hur and Butler do not appear to explicitly teach
wherein the Kalman filter model is:
X
=
a
0
t
2
+
v
0
t
+
x
0
X
=
A
t
+
B
wherein, X represents a vector matrix of the historical operating data, t represents a time matrix, A represents a transition matrix, B represents a random term, and
a
0
,
v
0
, and
x
0
represent the dynamic parameters.
However, Chan—directed to analogous art—teaches
[a system model] and [a measurement model] (Page 1, section 9.2 introduces the Kalman filter model: “(9.1)
x
˙
=
A
x
+
B
u
+
G
t
w
t
(System) (9.2)
y
=
C
x
+
v
t
(Measurement)”.)
wherein, X represents a vector matrix of the historical operating data, … A represents a transition matrix, B represents a random term, and
a
0
,
v
0
, and
x
0
represent the dynamic parameters. (Page 1 shows the historical operating data matrix as
x
, composed of stator currents and rotor fluxes. In the measurement model,
C
is the transition matrix mapped to
A
in the instant application on page 2, and
v
(
t
)
is the random term (noise) mapped to B in the present application. The dynamic parameters are
G
(
t
)
and
w
(
t
)
.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Hur and Butler with the teachings of Chan for the reasons given above in regards to claim 7.
The combination of Hur, Butler, and Chan does not appear to explicitly teach
X
=
a
0
t
2
+
v
0
t
+
x
0
wherein t represents time
However, Math’s Fun—directed to analogous art—teaches
X
=
a
0
t
2
+
v
0
t
+
x
0
(Page 2 gives an example of a quadratic equation in standard form:
-
5
t
2
+
14
t
+
3
. This is the same equation used as a model in the instant application, as 3 is input as the height,
x
0
, 14 as the velocity
v
0
, and -5 as the acceleration
a
0
.)
wherein t represents time (Page 1 states “Note: t is time in seconds”.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Hur, Butler, and Chan with the teachings of Math’s Fun, because as Math’s Fun states on page 7, “And many questions involving time, distance, and speed need quadratic equations.” The dry pump model involves at least speed and time, and therefore would need a model that include those.
Claim(s) 9 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hur (“Estimation of Useful Variables in Wind Turbines and Farms Using Neural Networks and Extended Kalman Filter”, 2019) and Butler (“Prediction of Vacuum Pump Degradation in Semiconductor Processing”, 2009) as applied to claim 1 above, further in view of Math’s Fun (“Real World Examples of Quadratic Equations, 2021).
Regarding claim 9, the rejection of claim 1 is incorporated herein. Hur teaches
the historical data (Page 24019 states "1) Turbine 1 is equipped with a sensor and each of the rest with a nonlinear NN-based estimator. 2) At regular intervals, i.e., every 1000s in this paper, the inputs (different several combinations of torque, rotor speed, and FAA as shown below) and the output (TBM) are measured and collected from Turbine 1 model." The inputs and output are interpreted as the historical operating data. Additionally, page 24022, section III-A discusses a wind speed model, and page 24024, section III-B discusses a nonlinear 3 bladed aerodynamic model. One of ordinary skill in the art would realize that these models are based on historical operating data of the equipment that they model. Therefore, this is also interpreted as historical operating data.)
The combination of Hur and Butler does not appear to explicitly teach
filtering invalid data in [the data], wherein the invalid data comprise: at least one of an error value, a null value and a duplicate value.
However, Variawa—directed to analogous art—teaches
filtering invalid data in [the data], wherein the invalid data comprise: at least one of an error value, a null value and a duplicate value. (Page 3 states that invalid data includes “Inaccurate data (missing data)”, “The presence of noisy data (erroneous data and outliers)”, and “Inconsistent data—the presence of inconsistencies are due to the reason such that existence of duplication with data”. Page 4 states “Data Preprocessing is carried out to remove the cause of unformatted real-world data which we discussed above.” Removing is interpreted as filtering.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Hur and Butler with the teachings of Variawa because, as Variawa states in reference to raw data collected from various sources, on page 1, “This collected data cannot be used directly in performing the analysis process. Therefore, to solve this problem *Data Preparation* is required.” In a dry pump setting, it is also possible to have unclean data, and one would therefore be motivated to filter the data.
Claim 18 recites substantially similar subject matter to claim 9 and is rejected with the same rationale, mutatis mutandis.
Claim(s) 10 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hur (“Estimation of Useful Variables in Wind Turbines and Farms Using Neural Networks and Extended Kalman Filter”, 2019) and Butler (“Prediction of Vacuum Pump Degradation in Semiconductor Processing”, 2009) as applied to claim 1 above, further in view of Brownlee (“How to use Data Scaling Improve Deep Learning Model Stability and Performance”, August 25, 2020).
Regarding claim 10, the rejection of claim 1 is incorporated herein. Hur teaches
the historical data (Page 24019 states "1) Turbine 1 is equipped with a sensor and each of the rest with a nonlinear NN-based estimator. 2) At regular intervals, i.e., every 1000s in this paper, the inputs (different several combinations of torque, rotor speed, and FAA as shown below) and the output (TBM) are measured and collected from Turbine 1 model." The inputs and output are interpreted as the historical operating data. Additionally, page 24022, section III-A discusses a wind speed model, and page 24024, section III-B discusses a nonlinear 3 bladed aerodynamic model. One of ordinary skill in the art would realize that these models are based on historical operating data of the equipment that they model. Therefore, this is also interpreted as historical operating data.)
The combination of Hur and Butler does not appear to explicitly teach
normalizing [the data] to a target data field.
However, Brownlee—directed to analogous art—teaches
normalizing [the data] to a target data field. (Page 5 states “A value is normalized as follows: y = (x – min) / (max – min) Where the minimum and maximum values pertain to the value x being normalized.” The value x is interpreted as the target data field.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Hur and Butler with the teachings of Brownlee because, as Brownlee states on page 3, “Scaling input and output variables is a critical step in using neural network models.” As the method in the instant application’s specification uses a neural network, one would be motivated to scale the input variables.
Claim 19 recites substantially similar subject matter to claim 10 and is rejected with the same rationale, mutatis mutandis.
Conclusion
THIS ACTION IS MADE FINAL. 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 JESSICA THUY PHAM whose telephone number is (571)272-2605. The examiner can normally be reached Monday - Thursday, 7:30 A.M. - 5:30 P.M..
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, Li Zhen can be reached at (571) 272-3768. 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.P./Examiner, Art Unit 2121
/Li B. Zhen/Supervisory Patent Examiner, Art Unit 2121
Prosecution Insights