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
Acknowledgement is made of application #18/457,503 filed on 08/29/2023 in which claims 1-20 have been presented for prosecution in a first action on the merits.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 08/29/2023 has been considered and put on record. An initialed copy is attached herewith.
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.
Claims 1,3-16,18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Budan et al., (Budan) USPAT 11,658,356 in view of Dai et al., (“Dai”), Non-Patent Literature, “Advanced Battery Management Strategies for a Sustainable future: Multilayer design concepts and research trends”.
Regarding claims 18,1 and 19: Budan at least discloses and shows in Figs. 1-11: One or more non-transitory computer readable media having instructions stored thereon for performing a method( a tangible, non-transitory computer-readable medium may store instructions and a processing device may execute the instructions to perform one or more operations of any method disclosed herein; see col. 3, lines 6-9; col. 4, lines 14-29)( The computer system 2100 includes a processing device 2102, a volatile memory 2104 (e.g., random access memory (RAM)), a non-volatile memory 2106 (e.g., read-only memory (ROM), flash memory, solid state drives (SSDs), and a data storage device 2108, the foregoing of which are enabled to communicate with each other via a bus 2110. Processing device 2102 represents one or more general-purpose processing devices such as a microprocessor, central processing unit, or the like; see col. 27, lines 25-33), the method comprising: determining via a processor(2102/102/103/128; see col. 27, lines 1-10) a plurality of control profiles for a designated type of battery system(receiving data comprising one or more measurements and one or more user battery usage profiles; Raw sensor inputs such as cell voltage, current and temperature may be used to derive features during feature extraction 614 for the machine learning model 132. More features are extracted from data groups such as cell manufacturer data, fleet data, lab experiments, simulation data, and user battery usage profiles; see col. 9, lines 42-47 ), each control profile defining a respective pattern of charging and/or discharging the designated type of battery system(battery pack 121) over a period of time(see Fig. 8)(note-the user battery usage profile 610 such as the acceleration, braking, deceleration habits of the user, charging habits of the user, and the like. The user battery usage profile 610 may provide enhanced accuracy in predicting the RUL, see col. 16, lines 1-9); determining a plurality of simulated battery values by applying one or more physics models(600) to the plurality of control profiles via a processor(2102/102/103/128), the one or more physics models(600) modeling interactions between a plurality of states associated with the designated type of battery system(121); determining via a processor(2102/102/103/128) a pre-trained battery value temporal convolutional neural network based on a timeseries pre-training dataset(as performed by machine learning model 132 which is trained by training engine 130; col. 8, lines 55-65 and see col. 9, lines 16-18) that includes the plurality of control profiles and the plurality of simulated battery values(note-the one or more machine learning models 132 may comprise, e.g., a single level of linear or non-linear operations (e.g., a support vector machine (SVM) or the machine learning models 132 may be a deep network, i.e., a machine learning model comprising multiple levels of non-linear operations. Examples of deep networks are neural networks, including generative adversarial networks, recurrent neural networks with one or more hidden layers, and fully connected neural networks (e.g., each artificial neuron may transmit its output signal to the input of the remaining neurons, as well as to itself; see col. 9, lines 28-51); receiving as input a prospective control profile and observed battery system input values(construed as the observed targets in the dataset 602; see Fig. 6) for a designated battery system of the designated type of battery system(see col. 9, lines 18-27); determining a predicted one or more battery values for the designated battery system based on application of the temporal convolutional neural network(132) to the prospective control profile and the observed battery system input values(note- the vehicle 117 collects relevant data using sensors 131 or other mechanisms from the asset or battery (e.g., battery pack current, cell voltages, cell temperatures, cell capacity, etc. )( The battery ageing dataset 602 may be input into a pre-processing step 612 where the data is transformed from a first format to a second format that is able to be efficiently processed by the physics-based model 600 and the machine learning model 132. Once the data is pre-processed, feature extraction 614 may be performed to identify and extract one or more features for the machine learning model 132. Further, the formatted data may be input to the physics-based model 600 that outputs a capacity fade of the battery. Sensor data or simulation data pertaining to the battery pack current, cell current, cell voltages, and/or cell temperatures may be input into the physics-based model 600 and/or machine learning model 132. The physics-based model may be configured to output a solid electrolyte interphase (SEI) that is used as an input by the machine learning model, as well as the features extracted from the formatted battery ageing dataset 602 to predict a RUL; see col. 16, lines 10-40). While Budan teaches presenting the predicted RUL on a user interface 105 and further teaches that the instructions 2122 may further be transmitted or received over a network via the network interface device 2112(construed as communication interface)(as per claim 19) (see col. 28, lines 6-17 and col. 20, lines 3-15), Budan does not expressly disclose the limitations of:
and transmitting an operational instruction to the designated battery system based on the predicted one or more battery values.
Dai teaches factual evidence of, and transmitting an operational instruction to the designated battery system based on the predicted one or more battery values( note- Safety and aging are two major challenges of battery management, as well as the primary concern of users for EVs. Battery safety issues are directly related to human casualties, property loss, and environmental damage, while the aging issues affect the maintenance cost and service
life of EVs. Generally, safety management aims to protect the battery system from overuse, fire, explosion, leakage, and other hazards, and the purpose of battery aging management is to extend battery life. Battery safety and aging management are closely related and are located in the higher part of the application layer; see page 3, col. 2, paragraph 2.3.5). It is noted that Fig. 3 shows that the battery modeling of the algorithm layers into the application layer and thus meet the limitations of, and transmitting an operational instruction to the designated battery system based on the predicted one or more battery values.
Budan and Dai are both in the same field of endeavor, namely battery health. It would have been obvious to one having ordinary skill in the art before the effective filing of the claimed invention to combine Budan and Dai to teach the limitations of, and transmitting an operational instruction to the designated battery system based on the predicted one or more battery values, as recited, for the advantages that the identified battery states can be used to prevent negative outcomes, as per the teachings of Dai, page 13, col. 2, paragraph 2.3.5.
Regarding claim 3, Budan in view of Dai teaches all the claimed invention as set forth and disclosed above in claim 1. Budan further discloses, wherein determining the pre-trained battery state for the designated battery system comprises introducing a plurality of intermittent blanked values simulating missing data in the timeseries pre-training dataset.(Note- the machine learning model 132 trained to use causal inference may accept one or more inputs, such as (i) assumptions, (ii) queries, and (iii) data. The machine learning model 132 may be trained to output one or more outputs, such as (i) a decision as to whether a query may be answered, (ii) an objective function (also referred to as an estimand) that provides an answer to the query for any received data, and (iii) an estimated answer to the query and an estimated uncertainty of the answer, where the estimated answer is based on the data and the objective function, and the estimated uncertainty reflects the quality of data (i.e., a measure which takes into account the degree or salience of incorrect data or missing data; col. 9, lines 55 - 67).
Regarding claim 4, Budan in view of Dai teaches all the claimed invention as set forth and disclosed above in claim 1. Budan further discloses, wherein determining the plurality of control profiles comprises accessing a database(150) storing field data characterizing operation of one or more physical battery systems(121) over time(note- The cloud-based computing system 116 may also include a database 150 that stores data, knowledge, and data structures used to perform various embodiments. For example, the database 150 may store fleet of electric vehicles since beginning of life (BOL), battery data (e.g., original anode thickness, expected cycle loss, etc.) received from a manufacturer of the battery, lab experiment data pertaining to the battery, user battery usage profile, etc. For example, the database 150 may store all or some of that data as a battery ageing dataset, see col. 8, lines 40-52).
Regarding claim 5, Budan in view of Dai teaches all the claimed invention as set forth and disclosed above in claim 1. Budan further discloses, wherein determining the plurality of control profiles comprises generating a function over time, the function being of a sinusoidal or sigmoid form(The gates in an LSTM are analog in the form of sigmoids, meaning they range from zero to one. The fact that they are analog enables them to do backpropagation, col. 25, lines 40-42).
Regarding claim 6, Budan in view of Dai teaches all the claimed invention as set forth and disclosed above in claim 1. Budan further discloses, wherein the one or more physics models(600) includes a pseudo two-dimensional model characterizing one or more electrochemical processes with the designated type of battery system(note- The physics-based model 600 may include a physics cloud-based model 600-1 and a physics edge model 600-2; see Fig. 8 and col. 18, lines 56-67).
Regarding claim 7, Budan in view of Dai teaches all the claimed invention as set forth and disclosed above in claim 6. Budan further discloses, wherein the predicted one or more battery values include an electrolyte connectivity value or a cathode conductivity value (Note- The SEI growth model acts as the SOH estimate. Additional ageing mechanisms (porosity change, plating models) may also be included in SOH. RUL model 800 may start from 100% SOC. The physics edge model 600-2 may output the SEI growth model that is input to the physics cloud-based model 600-1. The physics clod-based model 600-1 may receive an initial SEI thickness as input; see Fig. 8, col. 16, lines 62-col. 17, line 25 and col. 18, lines 56-col. 19, lines 12)
Regarding claim 8, Budan in view of Dai teaches all the claimed invention as set forth and disclosed above in claim 1. Budan further discloses, wherein the one or more physics models includes(600) an equivalent circuit model characterizing one or more operational characteristics of the designated type of battery system(see col. 17, lines 1-25).
Regarding claim 9, Budan in view of Dai teaches all the claimed invention as set forth and disclosed above in claim 8. Budan further discloses, wherein the predicted one or more battery values include a resistance value or a capacitance value(the physics-based model 600 model may output an internal state of the battery pack 121 or asset 119 describing properties including, but not limited to, over-potentials related to the electrodes, loss of cyclable lithium, loss of active material, change in SEI layer thickness, SOH (state of health), capacity loss and resistance increase due to various degradation phenomena, etc, see col. 17, lines 17-23).
Regarding claim 10, Budan in view of Dai teaches all the claimed invention as set forth and disclosed above in claim 1. Budan further discloses, wherein a designated control profile of the plurality of control profiles includes a designated current profile defining an amount of current over a designated period of time(Figs. 6, 9 and 11)(note- The inputs to the physics edge model 600-2 may include the model parameters (time (S), cell voltage (V), current (A), charge throughput (Ah), average SEI thickness (m)), initial SOC, cell temperature, and cell current. The raw sensor inputs such as cell voltage, cell current, and cell temperature may be used to derive features for physics edge model SEI thickness output, see col. 19, lines 22-28).
Regarding claim 11, Budan in view of Dai teaches all the claimed invention as set forth and disclosed above in claim 1. Budan further discloses, wherein a designated control profile of the plurality of control profiles includes a designated power profile defining an amount of power over a designated period of time(note- the cell manufacturer data 606 may enhance the prediction of the RUL because it provides characterization data (e.g., how many cycles they expect), static capacity and open voltage set, hybrid pulse power characteristics, open circuit voltage test, etc, see col. 15, lines 50-61).
Regarding claim 12, Budan in view of Dai teaches all the claimed invention as set forth and disclosed above in claim 1. Budan further discloses, wherein the predicted one or more battery values includes a voltage value(see col. 19, lines 22-28).
Regarding claim 13, Budan in view of Dai teaches all the claimed invention as set forth and disclosed above in claim 1. Budan further discloses, wherein the predicted one or more battery values includes a value selected from the group consisting of: an open-circuit voltage value, an internal resistance value, an external resistance value, a battery system temperature value, a state-of-charge value, and a state of health value(e.g., the simulation data may include battery pack current (I), cell voltages (V), and/or cell temperatures (T) of the battery pack and the physics-based model 600 model may output an internal state of the battery pack 121 or asset 119 describing properties including, but not limited to, over-potentials related to the electrodes, loss of cyclable lithium, loss of active material, change in SEI layer thickness, SOH (state of health), capacity loss and resistance increase due to various degradation phenomena, etc. These estimates may be used as additional data in the machine learning model 132; col. 16, lines 62-col. 17, line 29).
Regarding claim 14, Budan in view of Dai teaches all the claimed invention as set forth and disclosed above in claim 1. Budan further discloses, wherein the temporal convolutional neural network(132) includes an input layer comprising a plurality of input neurons, a subset of the input neurons corresponding to input battery data values observed of a plurality of time intervals(see col. 9, lines 28-51).
Regarding claim 15, Budan in view of Dai teaches all the claimed invention as set forth and disclosed above in claim 12. Budan further discloses, wherein the input battery data values include control profile values encoding information corresponding with the plurality of control profiles(note- The term “computer-readable storage medium” shall also be taken to include any medium capable of storing, encoding, or carrying a set of instructions for execution by the machine, where such set of instructions cause the machine to perform any one or more of the methodologies of the present disclosure; see col. 28, lines 18-29).
Regarding claim 16, Budan in view of Dai teaches all the claimed invention as set forth and disclosed above in claim 1. Budan further discloses, wherein the temporal convolutional neural network includes one or more hidden layers each comprising a respective plurality of hidden layer neurons, a designated hidden layer neuron receiving as input data values corresponding to a respective two or more different time periods, the designated hidden layer neuron including an activation function configured to transmit an output signal to a recipient neuron based on the input data values (see col. 9, lines 28-51).
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Budan et al., (Budan) USPAT 11,658,356 in view of Dai et al., (“Dai”), Non-Patent Literature, “Advanced Battery Management Strategies for a Sustainable future: Multilayer design concepts and research trends” and in further view of Bockrath, et al., (“Bockrath”), Non-Patent Literature “State of Health Estimation of Lithium-Ion Batteries with a Temporal Convolutional Neural Network Using Partial Load Profiles”
Regarding claim 17, Budan in view of Dai discloses all the claimed invention as set forth and discussed above in claim 14 but fails to expressly teach the limitations of:
wherein the hidden layers collectively perform time-dilation on a plurality of input values spread over a period of time to predict an output value corresponding to a single period of time.
However, Bockrath teaches factual evidence of, wherein the hidden layers collectively perform time-dilation on a plurality of input values spread over a period of time to predict an output value corresponding to a single period of time(see Bockrath; page 5, cols. 1-2 and Fig. 6, “Therefore dilated causal convolutions [65,66]] are used for an efficient processing of the reference discharge profiles. In Fig. 6, a stack of dilated convolutions are visualized, where the blue circles representing the active neurons).
Budan, Dai and Bockrath are all in the same field of endeavor, namely battery health. It would have been obvious to one having ordinary skill in the art before the effective filing of the claimed invention to combine Budan in view of Dai and Bockrath to teach the limitations of, wherein the hidden layers collectively perform time-dilation on a plurality of input values spread over a period of time to predict an output value corresponding to a single period of time, as recited, for the advantages of providing an efficient processing of the reference discharge profiles, as per the teachings of Bockrath (page 5, under paragraph Dilated convolutions).
Allowable Subject Matter
Claims 2 and 20 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Regarding claim 2, patentability exists at least in part with the claimed limitations of, wherein determining the pre-trained battery state for the designated battery system comprises introducing a plurality of blanked outcome values into the timeseries pre-training dataset, and wherein the pre-trained battery value temporal convolutional neural network is trained based on gradient descent via loss function reflecting a difference between predicted outcome values and blanked outcome values.
Regarding claim 20, patentability exists at least in part with the claimed limitations of, wherein the temporal convolutional neural network includes one or more hidden layers each comprising a respective plurality of hidden layer neurons, a designated hidden layer neuron receiving as input data values corresponding to a respective two or more different time periods, the designated hidden layer neuron including an activation function configured to transmit an output signal to a recipient neuron based on the input data values, wherein the hidden layers collectively perform time-dilation on a plurality of input values spread over a period of time to predict an output value corresponding to a single period of time, wherein determining the pre-trained battery state for the designated battery system comprises introducing a plurality of blanked outcome values into the timeseries pre-training dataset, and wherein the pre-trained battery value temporal convolutional neural network is trained based on gradient descent via loss function reflecting a difference between predicted outcome values and blanked outcome values.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to M'BAYE DIAO whose telephone number is (571)272-6127. The examiner can normally be reached M-F; 10:00AM-6:30PM and OFF most of the time Friday when working IFP.
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, DREW A DUNN can be reached at 571-272-2312. 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'BAYE DIAO
Primary Examiner
Art Unit 2859
/M BAYE DIAO/Primary Examiner, Art Unit 2859 June 3, 2026
Prosecution Insights