DETAILED ACTION
1. This office action is in response to the Application No. 18619815 filed on 03/28/2024. Claims 1-20 are presented for examination and are currently pending.
Notice of Pre-AIA or AIA Status
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 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.
3. Claims 1-20 are rejected under 35 U.S.C 101 because the claimed invention is directed towards an abstract idea without significantly more.
Step 1
Independent claim 1 is directed to a system, and falls into one of the four statutory categories.
Step 2A, Prong 1
Claim 1 recites the following abstract ideas:
derive ground-truth parameters for a loss curve of an actual capacity using a physics model (Mathematical concept directed to derive ground-truth parameters for a loss curve of an actual capacity using a physics model. The physics model is formed by Arrhenius equation. According to the instant specification [0029], discloses that “the physics model 302 can be formed with utilizing an Arrhenius Law”.),
compare the ground-truth parameters with curve parameters estimated (Mental process directed to comparing the ground-truth parameters with curve parameters estimated. This can be done by observing the ground-truth parameters with curve parameters estimated and making a judgement on the comparison), and
and adjust the self-attention model by comparing predicted cycles from the self-attention model and actual cycles from the physics model for cycle life as additional tuning.
Step 2A, Prong 2
Claim 1 recites the following additional elements:
a memory storing instructions that, when executed by a processor, cause the processor to (This limitation is directed to a memory for storing instructions. This is directed to high level recitation of generic computer component and does not integrate the abstract idea into a practical application. See MPEP 2106.05(f)):
the actual capacity associated with a battery type (This limitation is directed to a particular type or source of data, which is field of use. This limitation does not integrate the abstract idea into a practical application. See MPEP 2106.05(h));
by a self-attention model for physical tuning of the self-attention model (This limitation is directed to mere instruction to apply a judicial exception. This limitation does not integrate the abstract idea into a practical application. See MPEP 2106.05(f))
the curve parameters being associated with a predicted capacity for the battery type (This limitation is directed to a particular type or source of data, which is field of use. This limitation does not integrate the abstract idea into a practical application. See MPEP 2106.05(h));
Step 2B
Claim 1 recites the following additional elements:
a memory storing instructions that, when executed by a processor, cause the processor to (This limitation is directed to a memory for storing instructions. This is directed to high level recitation of generic computer component. This does not amount to significantly more than judicial exception. See MPEP 2106.05(f)):
the actual capacity associated with a battery type (This limitation is directed to a particular type or source of data, which is field of use. This does not amount to significantly more than judicial exception. See MPEP 2106.05(h));
by a self-attention model for physical tuning of the self-attention model (This limitation is directed to mere instruction to apply a judicial exception. This does not amount to significantly more than judicial exception. See MPEP 2106.05(f))
the curve parameters being associated with a predicted capacity for the battery type (This limitation is directed to a particular type or source of data, which is field of use. This does not amount to significantly more than judicial exception. See MPEP 2106.05(h));
4. Dependent claim 2 is directed to a system, and falls into one of the four statutory categories.
Claim 2 recites the following abstract ideas:
fit the loss curve using a function derived from battery data that is raw, the function having exponential operations that factor the curve parameters and an initial charging capacity, and the ground-truth parameters and the curve parameters being similar constants for the function (Mathematical concepts directed to fitting the loss curve using a function).
Claim 2 do not recite any additional elements.
5. Dependent claim 3 is directed to a system, and falls into one of the four statutory categories.
Claim 3 recites the following abstract ideas:
guide the self-attention model towards approximations for the curve parameters (Mental process directed to guiding the self-attention model towards approximations for the curve parameters. This can be carried out with the use of pen and paper); and
identify a relationship between a cycle number and the curve parameters (Mental process directed to identifying the relationship between a cycle number and the curve parameters. This can be done by observing the cycle number and curve parameters and making a judgement on the identification of a relationship).
Claim 3 do not recite any additional elements.
6. Dependent claim 4 is directed to a system, and falls into one of the four statutory categories.
Claim 4 do not recite any abstract ideas.
Claim 4 recites the following additional elements:
train the self-attention model to reduce approximation losses associated with the physical tuning (This limitation is directed to mere instruction to apply a judicial exception. This limitation does not integrate the abstract idea into a practical application. See MPEP 2106.05(f)).
Claim 4 recites the following additional elements:
train the self-attention model to reduce approximation losses associated with the physical tuning (This limitation is directed to mere instruction to apply a judicial exception. This does not amount to significantly more than judicial exception. See MPEP 2106.05(f)).
7. Dependent claim 5 is directed to a system, and falls into one of the four statutory categories.
Claim 5 recites the following abstract ideas:
reconstruct a loss graph with the actual parameters (Mental process directed to reconstructing a graph with actual parameters. This can be done with the use of a pen and paper).
Claim 5 recites the following additional elements:
predict actual parameters by the self-attention model associated with a battery cell using a cycle number and a capacity loss for charge that are measured (This limitation is directed to generally linking the use of a judicial exception to a particular technological environment or field of use. This limitation does not integrate the abstract idea into a practical application. See MPEP 2106.05(h)),
the actual parameters corresponding to the curve parameters and the self-attention model executing computations without the physics model (This limitation is directed to a particular type or source of data, which is field of use. This limitation does not integrate the abstract idea into a practical application. See MPEP 2106.05(h)); and
Claim 5 recites the following additional elements:
predict actual parameters by the self-attention model associated with a battery cell using a cycle number and a capacity loss for charge that are measured (This limitation is directed to generally linking the use of a judicial exception to a particular technological environment or field of use. This does not amount to significantly more than judicial exception. See MPEP 2106.05(h)),
the actual parameters corresponding to the curve parameters and the self-attention model executing computations without the physics model (This limitation is directed to a particular type or source of data, which is field of use. This does not amount to significantly more than judicial exception. See MPEP 2106.05(h)); and
8. Dependent claim 6 is directed to a system, and falls into one of the four statutory categories.
Claim 6 recites the following abstract ideas:
adapt the physics model to output the ground-truth parameters by minimizing errors (Mental process directed to adapting the physics model to output the ground-truth parameters by minimizing errors. This can be done with the use of pen and paper),
Claim 6 recites the following additional elements:
wherein the physics model numerically represents a physical structure and a chemical structure about the battery type (This limitation is directed to a particular type or source of data, which is field of use. This limitation does not integrate the abstract idea into a practical application. See MPEP 2106.05(h)).
Claim 6 recites the following additional elements:
wherein the physics model numerically represents a physical structure and a chemical structure about the battery type (This limitation is directed to a particular type or source of data, which is field of use. This does not amount to significantly more than judicial exception. See MPEP 2106.05(h)).
9. Dependent claim 7 is directed to a system, and falls into one of the four statutory categories.
Claim 7 recites the following abstract ideas:
select by the self-attention model features associated with actual parameters corresponding to the curve parameters (Mental process directed to selecting by the self-attention model features associated with actual parameters corresponding to the curve parameters. This can be done by observing the model features and making a judgement on the selection).
Claim 7 recites the following additional elements:
during training using spearman correlations (This limitation is directed to mere instructions to apply the judicial exception. This limitation does not integrate the abstract idea into a practical application. See MPEP 2106.05(f))
Claim 7 recites the following additional elements:
during training using spearman correlations (This limitation is directed to mere instructions to apply the judicial exception. This does not amount to significantly more than judicial exception. See MPEP 2106.05(f))
10. Dependent claim 8 is directed to a system, and falls into one of the four statutory categories.
Claim 8 do not recite any abstract ideas.
Claim 8 recites the following additional elements:
wherein inputs to the self-attention model are one of a charge variance, a minimum charge, a mean charge, and a slope of a fade curve associated with a vehicle battery (This limitation is directed to a particular type or source of data, which is field of use. This limitation does not integrate the abstract idea into a practical application. See MPEP 2106.05(h)).
Claim 8 recites the following additional elements:
wherein inputs to the self-attention model are one of a charge variance, a minimum charge, a mean charge, and a slope of a fade curve associated with a vehicle battery (This limitation is directed to a particular type or source of data, which is field of use. This does not amount to significantly more than judicial exception. See MPEP 2106.05(h)).
11. Dependent claim 9 is directed to a system, and falls into one of the four statutory categories.
Claim 9 do not recite any abstract ideas.
Claim 9 recite the following additional elements:
wherein the physics model factors thermal degradation and the additional tuning is data-driven using acquired battery data (This limitation is directed to particular type or source of data, which is field of use. This limitation does not integrate the abstract idea into a practical application. See MPEP 2106.05(h)).
Claim 9 recite the following additional elements:
wherein the physics model factors thermal degradation and the additional tuning is data-driven using acquired battery data (This limitation is directed to particular type or source of data, which is field of use. This does not amount to significantly more than judicial exception. See MPEP 2106.05(h)).
12. Independent claim 10 is directed to a machine, and falls into one of the four statutory categories.
With regards to claim 10, it is substantially similar to claim 1, and is rejected in the same manner and reasoning applying.
Claim 10 further recites “A non-transitory computer-readable medium comprising: instructions that when executed by a processor cause the processor to”, this limitation is directed to computer comprising instruction executed by a processor. This is recited as a generic computer component. This limitation does not integrate the abstract idea into a practical application nor does it amount to significantly more than judicial exception. See MPEP 2106.05(f).
13. Independent claim 11 is directed to a method, and falls into one of the four statutory categories.
With regards to claim 11, it is substantially similar to claim 1, and is rejected in the same manner and reasoning applying.
14. Dependent claim 12 is directed to a method, and falls into one of the four statutory categories.
With regards to claim 12, it is substantially similar to claim 2, and is rejected in the same manner and reasoning applying.
15. Dependent claim 13 is directed to a method, and falls into one of the four statutory categories.
With regards to claim 13, it is substantially similar to claim 3, and is rejected in the same manner and reasoning applying.
16. Dependent claim 14 is directed to a method, and falls into one of the four statutory categories.
With regards to claim 14, it is substantially similar to claim 4, and is rejected in the same manner and reasoning applying.
17. Dependent claim 15 is directed to a method, and falls into one of the four statutory categories.
With regards to claim 15, it is substantially similar to claim 5, and is rejected in the same manner and reasoning applying.
18. Dependent claim 16 is directed to a method, and falls into one of the four statutory categories.
With regards to claim 16, it is substantially similar to claim 6, and is rejected in the same manner and reasoning applying.
19. Dependent claim 17 is directed to a method, and falls into one of the four statutory categories.
With regards to claim 17, it is substantially similar to claim 7, and is rejected in the same manner and reasoning applying.
20. Dependent claim 18 is directed to a method, and falls into one of the four statutory categories.
With regards to claim 18, it is substantially similar to claim 8, and is rejected in the same manner and reasoning applying.
21. Dependent claim 19 is directed to a method, and falls into one of the four statutory categories.
With regards to claim 19, it is substantially similar to claim 9, and is rejected in the same manner and reasoning applying.
22. Dependent claim 20 is directed to a method, and falls into one of the four statutory categories.
Claim 20 do not recite any abstract ideas.
Claim 20 recites the following additional elements:
wherein the physical tuning includes coarsely training the self-attention model (This limitation is directed to mere instructions to apply the judicial exception. This limitation does not integrate the abstract idea into a practical application. See MPEP 2106.05(f)) and
the additional tuning is fine-tuning the self-attention model (This limitation is directed to mere instructions to apply the judicial exception. This limitation does not integrate the abstract idea into a practical application. See MPEP 2106.05(f)).
Claim 20 recites the following additional elements:
wherein the physical tuning includes coarsely training the self-attention model (This limitation is directed to mere instructions to apply the judicial exception. This does not amount to significantly more than judicial exception. See MPEP 2106.05(f)) and
the additional tuning is fine-tuning the self-attention model (This limitation is directed to mere instructions to apply the judicial exception. This does not amount to significantly more than judicial exception. See MPEP 2106.05(f)).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, 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.
23. Claims 1, 3, 8-11, 13, 18 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al. ("Remaining useful life prediction of lithium-ion batteries: A temporal and differential guided dual attention neural network." IEEE Transactions on Energy Conversion 39.1 (2023): 757-771) in view of Hu et al. ("Lithium-Ion Battery Calendar Health Prognostics Based on Knowledge-Data-Driven Attention," in IEEE Transactions on Industrial Electronics, vol. 70, no. 1, pp. 407-417, Jan. 2023, doi: 10.1109/TIE.2022.3148743).
Regarding claim 1, Wang teaches a prediction system (A novel dual-branch network TDANet is proposed in this article to predict the RUL (remaining useful life) of Li-ion batteries, pg. 770, left col., second to the last para.)
comprising: a memory storing instructions that, when executed by a processor, cause the processor to (All experiments are carried out on a device with GPU: NVIDIA RTX 2060 (6G), memory: 16G, and CPU: Intel (R) Core (TM) i7-10875H, pg. 763, right col., section B. Implementation Details):
derive ground-truth parameters (Due to variations in the lifetimes of different batteries, the optimal value of parameter w needs to be determined through experimental analyses (pg. 760, right col. second para.); it can be seen that when w is 32, the model achieves the best prediction errors on B05 and B07. Compared with w of 16, RMSEs and MAEs are decreased by 0.0051 / 0.0034 and 0.0068 / 0.0048, respectively. The optimal won the CALCE database is 64. As w increases, the error decreases gradually, pg. 766, left col.,) for a loss curve of an actual capacity using a ... model (Fig. 9 shows the training and test loss curves of the model on B05 and C35 (pg. 764, left col., last para.); Specifically, given an SP and an initial window input L ∈ RN×1, i.e., the capacity value sequence containing N cycles, pg. 759, right col., last para.)
the actual capacity associated with a battery type (Based on the above, a novel temporal and differential guided dual attention neural network (TDANet) is proposed in this article for Li-ion battery RUL prediction. We evaluate the proposed TDANet on the NASA and CALCE databases, which are popular for RUL prediction of Li-ion batteries, pg. 759, left col., second para.);
compare the ground-truth parameters (Due to variations in the lifetimes of different batteries, the optimal value of parameter w needs to be determined through experimental analyses, pg. 760, right col. second para.) with curve parameters (the goal of auto-regressive is to predict the capacity of the next cycle, ˆy = f(L;θ), where θ is model parameters, pg. 759, right col., last para.) estimated by a self-attention model for ... tuning of the self-attention model (Two attention mechanisms, TGM and DGM, are proposed to capture prior inductive biases. Specifically, TGM is employed to extract the correlations between different historical moments and the predicted value, while DGM focuses on capturing local fluctuations, pg. 770, left col., second to the last para.), and
the curve parameters being associated with a predicted capacity for the battery type (We perform several experimental analyses to verify the effect of model parameters on prediction performance, (pg. 765, right col., last para.); TDANet exhibits a remarkable performance on the Li-ion battery RUL prediction, pg. 763, left col., second para.); and
Wang does not explicitly teach using a physics model, physical tuning of the self-attention model; and adjust the self-attention model by comparing predicted cycles from the self-attention model and actual cycles from the physics model for cycle life as additional tuning.
Hu teaches derive ground-truth parameters (feature built based on the intermediate variables inside SEMj([t(i+1),T,S];θj) (pg. 411, right col., second para.); Some crucial parameters of CFKDA are as following: θ1 = [0.00072,0.87652,−2.23347,0.44987], θ2 = [0.00058,0.73985,−0.89084,0.48257], θ3 = [0.00062,0.00045,−0.76487,0.49182], θ4 = [0.00044,1.14846,−7.13875,4.10847,0.49571], pg. 416, left col., The Examiner notes θj are parameters) for a loss curve of an actual capacity using a physics model (semiempirical models (SEMs) for calendar health prognostics ... based on the Arrhenius law are widely used to grasp the battery degradation process. According to the Arrhenius law, the calendar capacity degradation can be finally expressed by a specific semiempirical form as
PNG
media_image1.png
58
388
media_image1.png
Greyscale
where both f(S) and Ea(S) in (3) are SoC dependence terms, R is the gas constant, z is a power low parameter to denote the dependence of time duration (pg. 409, right col., last para.); C(i) denotes the ith measurement in the capacity series, pg. 409, right col., second para. The Examiner notes C(i) is the actual capacity measured and SEM (semiempirical model) based on the Arrhenius law is a physics model because instant specification discloses: “Here, the physics model 302 can be formed with utilizing an Arrhenius Law to model loss curves for capacity”(US20250252284 [0029])),
the actual capacity associated with a battery type (In this study, an effective solution that applied the attention mechanism to the Li-ion battery, pg. 416, left col., first para. The Examiner notes a li-ion battery is the battery type); and
adjust the self-attention model (Adam ... is adopted to train CFKDA further to optimize all the learnable parameters, pg. 412, left col., second to the last para.) by comparing predicted cycles from the self-attention model and actual cycles from the physics model (where the attention of forecast target C(i+1) to each SEM(i.e., to their preliminary forecast result {¯C(j,i+1)}4 j=1) is designed based on the fitting goodness of each SEM model on past true capacities, pg. 411, left col., second para. The Examiner notes goodness-of-fit compares the forecasted model to the true data) for cycle life as additional tuning (batteries would degrade with both calendar and cycling modes, pg. 407, right col., first para.).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Wang to incorporate the teachings of Hu for the benefit of Li-ion batteries aimed to forecast their capacity along with storage time (pg. 409, right col., second para.) and improve prognostic performance significantly (Hu, abstract)
Regarding claim 3, Wang and Hu teaches the prediction system of claim 1, Wang teaches wherein the instructions to compare the ground-truth parameters further include instructions to: guide the self-attention model towards approximations for the curve parameters (Therefore, DGM is used to focus on the fluctuations in the capacity degradation curve (pg. 762, left col., last para.); First, the raw and differential capacity degradation data are separately fed into the proposed temporal-guided module (TGM) and differential-guided module (DGM) to capture global time space correlations and local fluctuations, abstract); and
identify a relationship between a cycle number and the curve parameters (Specifically, given an SP and an initial window input L ∈ RN×1, i.e., the capacity value sequence containing N cycles, the goal of auto-regressive is to predict the capacity of the next cycle, ˆy = f(L;θ), where θ is model parameters, pg. 759, right col., last para.).
Regarding claim 8, Wang and Hu teaches the prediction system of claim 1, Wang teaches wherein inputs to the self-attention model are one of a charge variance (charge variance input data, Fig. 2, pg. 760; (Li-ion) batteries are widely used in various fields such as electric vehicles, pg. 758, left col., first para.), a minimum charge, a mean charge, and a slope of a fade curve associated with a vehicle battery.
Regarding claim 9, Wang and Hu teaches the prediction system of claim 1, Hu teaches wherein the physics model factors thermal degradation (This experimental platform consists of a thermal chamber to control the environmental temperature of stored batteries, pg. 408, right col., last para.) and
the additional tuning is data-driven using acquired battery data (battery empirical knowledge ... calendar ageing mechanism modeling, pointing out a promising direction to further customize a pure data-driven model dedicated solely to calendar health prognostics. In this work, a fusion of SEMs and data-driven modeling paradigm is proposed, pg. 410, left col., last para.).
The same motivation to combine independent claim 1 applies here.
Regarding claim 10, claim 10 is similar to claim 1. It is rejected in the same manner and reasoning applying. Further, Wang teaches a non-transitory computer-readable medium comprising: instructions that when executed by a processor cause the processor to (a device with GPU: NVIDIA RTX 2060 (6G), memory: 16G, and CPU: Intel (R) Core (TM) i7-10875H, pg. 763, right col., section B. Implementation Details):
Regarding claim 11, claim 11 is similar to claim 1. It is rejected in the same manner and reasoning applying.
Regarding claim 13, claim 13 is similar to claim 3. It is rejected in the same manner and reasoning applying.
Regarding claim 18, claim 18 is similar to claim 8. It is rejected in the same manner and reasoning applying.
Regarding claim 19, claim 19 is similar to claim 9. It is rejected in the same manner and reasoning applying.
24. Claims 2, 4-6,12, 14-16 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al. ("Remaining useful life prediction of lithium-ion batteries: A temporal and differential guided dual attention neural network." IEEE Transactions on Energy Conversion 39.1 (2023): 757-771) in view of Hu et al. ("Lithium-Ion Battery Calendar Health Prognostics Based on Knowledge-Data-Driven Attention," in IEEE Transactions on Industrial Electronics, vol. 70, no. 1, pp. 407-417, Jan. 2023, doi: 10.1109/TIE.2022.3148743) in view of Lui et al. ("Physics-based prognostics of implantable-grade lithium-ion battery for remaining useful life prediction." Journal of Power Sources 485 (2021): 229327).
Regarding claim 2, Wang and Hu teaches the prediction system of claim 1, they do not explicitly teach the limitations of claim 2.
Lui teaches wherein the instructions to derive the ground-truth parameters further include instructions to: fit the loss curve using a function derived from battery data that is raw, the function having exponential operations that factor the curve parameters and an initial charging capacity, and the ground-truth parameters and the curve parameters being similar constants for the function (We use two empirical, simple mathematical models to track the nonlinear trends of both the cell capacity and corresponding degradation parameters. Model I involves two exponential terms and four coefficients:
PNG
media_image2.png
38
514
media_image2.png
Greyscale
where M(t)is the model output, which can be either the cell capacity or a degradation parameter, t is the time elapsed during the test, αI, βI, γ, and λ are model coefficients estimated from measurements, pg. 4, right col., second full para. The Examiner notes a coefficient can be a constant).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Wang and Hu to incorporate the teachings of Lui for benefit of using a physics-based approach, which extrapolates the degradation parameters, provides a more accurate and conservative RUL (remaining useful life) prediction of a lithium-ion battery (Lui, abstract)
Regarding claim 4, Wang and Hu teaches the prediction system of claim 1, Wang already teaches self-attention model (Firstly, two attention mechanisms, temporal-guided module (TGM) and differential-guided module (DGM), are proposed to capture the prior inductive bias ... Combining TGM with self-attention forms a temporal-guided global information extraction branch, enabling it to extract features that not only preserve long-term dependencies but also are guided by global temporal correlations, pg. 770, left col., second to the last para.), but they do not explicitly teach wherein the instructions to adjust the self-attention model further include instructions to: train the ... model to reduce approximation losses associated with the physical tuning.
Lui teaches wherein the instructions to adjust the self-attention model further include instructions to: train the ... model (A set of training data is used only to estimate the coefficients of a best-fit degradation model, pg. 5, right col., last para.) to reduce approximation losses associated with the physical tuning (Based on the half-cell model fitting, all the cells in group G4 exhibit around 32% m p losses, whereas those in group G2 exhibit approximately 15% losses. In contrast, all the cells in group G4 exhibit around 18% of LII losses, while those in group G2 exhibit about 11% losses, pg. 9, left col., first para.).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Wang and Hu to incorporate the teachings of Lui for benefit of using a physics-based approach, which extrapolates the degradation parameters, provides a more accurate and conservative RUL (remaining useful life) prediction of a lithium-ion battery (Lui, abstract)
Regarding claim 5, Wang, Hu and Lui teaches the prediction system of claim 4 , Wang already teaches self-attention model (Firstly, two attention mechanisms, temporal-guided module (TGM) and differential-guided module (DGM), are proposed to capture the prior inductive bias ... Combining TGM with self-attention forms a temporal-guided global information extraction branch, enabling it to extract features that not only preserve long-term dependencies but also are guided by global temporal correlations, pg. 770, left col., second to the last para.)
Lui teaches further including instructions to: predict actual parameters by the ... model associated with a battery cell (we utilize the best-fit model to extrapolate the degradation parameters for capacity and RUL prediction on a test set (containing data from cells other than the training cells), pg. 2, right col., second to the last para.) using a cycle number and a capacity loss for charge that are measured (We develop a quantitative analysis of the degradation mechanisms in implantable-grade Li-ion battery cells considering a 1.5-year cycle aging test at two different discharge rates, pg. 3, left col., second para.),
the actual parameters corresponding to the curve parameters and the ... model executing computations without the physics model (whereas the predicted capacity trends by the capacity-based approach solely depend on the available capacity measurements, Fig. 6, pg. 11); and
reconstruct a loss graph with the actual parameters (In fact, lost features may yield a very large error in the degradation parameter estimation if curve fitting is solely based on the similarity of the two curves, namely, the experimental VQ (or dV/ dQ) curve and the VQ (or dV/dQ) curve reconstructed from the half-cell model. Moreover, the cutoff cell voltages are not considered when optimizing the degradation parameters using only the dV/dQ curves (Fig. S3). Therefore, we manually adjust the degradation parameters after the BOL considering the potential shortcomings of fitting the VQ, pg. 8, left col., last para.).
The same motivation to combine dependent claim 4 applies here.
Regarding claim 6, Wang and Hu teaches the prediction system of claim 1, they do not explicitly teach the limitations of claim 6,
Lui teaches further including instructions to: adapt the physics model to output the ground-truth parameters by minimizing errors, wherein the physics model numerically represents a physical structure (The proposed prognostics approach captures degradation trends from three major mechanisms, namely, loss of active material on the positive electrode (LAM PE ), loss of active material on the negative electrode (LAM NE ), and loss of lithium inventory (LLI), pg. 2, right col, second para.) and
a chemical structure about the battery type (Specifically, the approach traces the evolution of the corresponding degradation parameters: active masses of the positive electrode (PE) and the negative electrode (NE), mp and mn , respectively, pg. 2, right col, second para.).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Wang and Hu to incorporate the teachings of Lui for benefit of using a physics-based approach, which extrapolates the degradation parameters, provides a more accurate and conservative RUL (remaining useful life) prediction of a lithium-ion battery (Lui, abstract)
Regarding claim 12, claim 12 is similar to claim 2. It is rejected in the same manner and reasoning applying.
Regarding claim 14, claim 14 is similar to claim 4. It is rejected in the same manner and reasoning applying.
Regarding claim 15, claim 15 is similar to claim 5. It is rejected in the same manner and reasoning applying.
Regarding claim 16, claim 16 is similar to claim 6. It is rejected in the same manner and reasoning applying.
Regarding claim 20, Wang and Hu teaches the method of claim 11, Wang already teaches self-attention model (Firstly, two attention mechanisms, temporal-guided module (TGM) and differential-guided module (DGM), are proposed to capture the prior inductive bias ... Combining TGM with self-attention forms a temporal-guided global information extraction branch, enabling it to extract features that not only preserve long-term dependencies but also are guided by global temporal correlations, pg. 770, left col., second to the last para.), but they do not explicitly teach wherein the physical tuning includes coarsely training the ... model and the additional tuning is fine-tuning the ... model.
Liu teaches wherein the physical tuning includes coarsely training the ... model (A set of training data is used only to estimate the coefficients of a best-fit degradation model, pg. 5, right col., last para)
and the additional tuning is fine-tuning the ... model (Subsequently, the fitting of the reconstructed full-cell curve to the experimental VQ and dV/dQ full-cell curve is achieved by adjusting the half-cell model parameters to obtain a more reliable estimation of the degradation parameters, pg. 2, right col., second para.)
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Wang and Hu to incorporate the teachings of Lui for benefit of using a physics-based approach, which extrapolates the degradation parameters, provides a more accurate and conservative RUL (remaining useful life) prediction of a lithium-ion battery (Lui, abstract)
25. Claims 7 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al. ("Remaining useful life prediction of lithium-ion batteries: A temporal and differential guided dual attention neural network." IEEE Transactions on Energy Conversion 39.1 (2023): 757-771) in view of Hu et al. ("Lithium-Ion Battery Calendar Health Prognostics Based on Knowledge-Data-Driven Attention," in IEEE Transactions on Industrial Electronics, vol. 70, no. 1, pp. 407-417, Jan. 2023, doi: 10.1109/TIE.2022.3148743) and further in view of Liu et al. (Capacity estimation of Li-ion battery based on transformer-adversarial discriminative domain adaptation. AIP Advances 1 July 2023; 13 (7): 075113. https://doi.org/10.1063/5.0152038, hereinafter “Liu-2023”)
Regarding claim 7, Wang and Hu teaches the prediction system of claim 1. Wang already teaches self-attention model (Firstly, two attention mechanisms, temporal-guided module (TGM) and differential-guided module (DGM), are proposed to capture the prior inductive bias ... Combining TGM with self-attention forms a temporal-guided global information extraction branch, enabling it to extract features that not only preserve long-term dependencies but also are guided by global temporal correlations, pg. 770, left col., second to the last para.), but they do not teach further including instructions to: select by the ... model features associated with actual parameters corresponding to the curve parameters during training using spearman correlations.
Liu-2023 teaches further including instructions to: select by the ... model features associated with actual parameters corresponding to the curve parameters (The multi-head attention MultiHead(Q,K,V) is
PNG
media_image3.png
122
524
media_image3.png
Greyscale
where h is the number of multi-heads and WO, WQ i , WK i , and WV i are the parameter matrices, pg. 13, 075113-5, right col.) during training using spearman correlations (In order to verify the correlation between the selected health characteristics and the battery life, Spearman correlation analysis is performed in this paper (pg. 13, 075113-4, left col., second para.); The training process of the lithium-ion battery life prediction model ... is shown in Fig. 8, pg. 13, 075113-7, right col., first para.).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Wang and Hu to incorporate the teachings of Liu-2023 for the benefit of a lithium-ion battery capacity estimation model (Liu-2023, abstract)
Regarding claim 17, claim 17 is similar to claim 7. It is rejected in the same manner and reasoning applying.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MORIAM MOSUNMOLA GODO whose telephone number is (571)272-8670. The examiner can normally be reached Monday-Friday 8:00am-5:00pm EST.
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, Michelle T. Bechtold can be reached on (571) 431-0762. 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.
/M.G./Examiner, Art Unit 2148
Prosecution Insights