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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 06/02/2025 was filed. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Status of the Claims
Claims 1-20 have been examined.
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.
Claim.19 is/are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter because it is directed to a computer program. See MPEP 2106.03.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-19 is/are rejected under 35 U.S.C. 102(a)(1) as being unpatentable over Hellgren (US20210263109A1).
Claim.1 Hellgren discloses a computer system comprising processing circuitry (see at least abstract, estimating the state-of-health of a battery in a vehicle)configured to: acquire cell data from cell sensors of an electrical storage pack of an electrical energy storage system of a vehicle (see at least fig.1-2, abstract, calculating a state-of-health, SoH.sub.calc of a battery cell based on the determined first battery property using a predetermined model; providing a function f estimating a battery cell degradation rate, p4, the mathematical models include parameters describing cell properties such as for example resistance, capacity and open circuit voltage. Setting of these parameters is essential for efficient state monitoring, p39, accurately estimate the state-of-health for the battery as a whole, it is preferable to estimate the state-of-health for a plurality of cells in a battery pack to properly account for variations between the battery cells of a battery), determine at least two states of the cells based on evaluating the cell data input the at least two states as input to a reinforcement learning algorithm configured to calculate control signals to balance the at least two states across the cells (see at least fig.1-2, step 108, modify K for each time step using a reinforcement learning agent, abstract, a method for estimating the state-of-health, SoH.sub.est, of a battery in a vehicle, the method comprising: determining a first battery property and a battery temperature of a battery in a vehicle; calculating a state-of-health, SoH.sub.calc of a battery cell based on the determined first battery property using a predetermined model, p14, the function ƒ is a function of the power provided by the battery, the function ƒ may also depend on the state-of-charge and battery temperature, which may also influence the degradation rate of the battery. For example, battery degradation may be higher at low temperatures and/or at low state-of-charge, p37, A straightforward model ƒ estimating a battery cell degradation rate may be formulated as:
PNG
media_image1.png
29
115
media_image1.png
Greyscale
), and provide an output indicating the control signals (see at least fig.1-2, p41, a battery 204 in turn comprising a plurality of battery cells 206 and a battery control unit 208. The control unit 208 may include a microprocessor, microcontroller, programmable digital signal processor or another programmable device. The control unit 208 may also, or instead, include an application specific integrated circuit, a programmable gate array or programmable array logic, a programmable logic device, or a digital signal processor. Where the control unit 208 includes a programmable device such as the microprocessor, microcontroller or programmable digital signal processor, p24, The battery control unit is configured to: determine a first battery property and a battery temperature of a battery in a vehicle; calculate a state-of-health, SoH.sub.calc, of a battery cell for the determined first battery property using a predetermined model; provide a function ƒ estimating a battery cell degradation rate; update a state-of health estimated in a previous time step according to H.sub.est←SoH.sub.est+f.Math.dt+K.Math.(SoH.sub.calc−SoH.sub.est), where K is a gain factor which is a dependent on operating conditions of the vehicle, and wherein K is modified for each time step using a reinforcement learning agent).
Claim.2 Hellgren discloses wherein the processing circuitry is further configured to: iteratively perform the steps as the vehicle is travelling (see at least fig.1-2, p41, a battery 204 in turn comprising a plurality of battery cells 206 and a battery control unit 208. The control unit 208 may include a microprocessor, microcontroller, programmable digital signal processor or another programmable device. The control unit 208 may also, or instead, include an application specific integrated circuit, a programmable gate array or programmable array logic, a programmable logic device, or a digital signal processor. Where the control unit 208 includes a programmable device such as the microprocessor, microcontroller or programmable digital signal processor, p24, The battery control unit is configured to: determine a first battery property and a battery temperature of a battery in a vehicle; calculate a state-of-health, SoH.sub.calc, of a battery cell for the determined first battery property using a predetermined model; provide a function ƒ estimating a battery cell degradation rate; update a state-of health estimated in a previous time step according to H.sub.est←SoH.sub.est+f.Math.dt+K.Math.(SoH.sub.calc−SoH.sub.est), where K is a gain factor which is a dependent on operating conditions of the vehicle, and wherein K is modified for each time step using a reinforcement learning agent).
Claim.3 Hellgren discloses wherein the output indicates discharge currents to be applied to the cells (see at least fig.1-2, p16, the gain factor K is a function of the battery temperature. Thereby, a more accurate setting of the gain factor K can be achieved since the setting can be adapted to current operating conditions, and in particular to the battery temperature, p17, K should change depending on the current operating condition).
Claim.4 Hellgren discloses wherein the states include at least two of state of charge, state of temperature, and state of health (see at least fig.1-2, step 108, modify K for each time step using a reinforcement learning agent, abstract, a method for estimating the state-of-health, SoH.sub.est, of a battery in a vehicle, the method comprising: determining a first battery property and a battery temperature of a battery in a vehicle; calculating a state-of-health, SoH.sub.calc of a battery cell based on the determined first battery property using a predetermined model, p14, the function ƒ is a function of the power provided by the battery, the function ƒ may also depend on the state-of-charge and battery temperature, which may also influence the degradation rate of the battery. For example, battery degradation may be higher at low temperatures and/or at low state-of-charge, p37, A straightforward model ƒ estimating a battery cell degradation rate may be formulated as:
PNG
media_image1.png
29
115
media_image1.png
Greyscale
).
Claim.5 wherein the processing circuitry is further configured to: simultaneously balance all of state of charge, state of temperature, and state of health (see at least fig.1-2, step 108, modify K for each time step using a reinforcement learning agent, abstract, a method for estimating the state-of-health, SoH.sub.est, of a battery in a vehicle, the method comprising: determining a first battery property and a battery temperature of a battery in a vehicle; calculating a state-of-health, SoH.sub.calc of a battery cell based on the determined first battery property using a predetermined model, p14, the function ƒ is a function of the power provided by the battery, the function ƒ may also depend on the state-of-charge and battery temperature, which may also influence the degradation rate of the battery. For example, battery degradation may be higher at low temperatures and/or at low state-of-charge, p37, A straightforward model ƒ estimating a battery cell degradation rate may be formulated as:
PNG
media_image1.png
29
115
media_image1.png
Greyscale
).
Claim.6 Hellgren discloses wherein the feedback from the cells, including estimations of the states are fed back to the reinforcement learning model, wherein the reinforcement learning model is configured to provide an action that includes the control signals (see at least fig.1-2, p41, a battery 204 in turn comprising a plurality of battery cells 206 and a battery control unit 208. The control unit 208 may include a microprocessor, microcontroller, programmable digital signal processor or another programmable device. The control unit 208 may also, or instead, include an application specific integrated circuit, a programmable gate array or programmable array logic, a programmable logic device, or a digital signal processor. Where the control unit 208 includes a programmable device such as the microprocessor, microcontroller or programmable digital signal processor, p24, The battery control unit is configured to: determine a first battery property and a battery temperature of a battery in a vehicle; calculate a state-of-health, SoH.sub.calc, of a battery cell for the determined first battery property using a predetermined model; provide a function ƒ estimating a battery cell degradation rate; update a state-of health estimated in a previous time step according to H.sub.est←SoH.sub.est+f.Math.dt+K.Math.(SoH.sub.calc−SoH.sub.est), where K is a gain factor which is a dependent on operating conditions of the vehicle, and wherein K is modified for each time step using a reinforcement learning agent, p12, the model may for example be determined for a limited number of specific temperatures. The problem at hand thereby becomes to set a proper filter gain K, and the present invention is based on the realization that K is advantageously set using a reinforcement learning agent. Reinforcement learning is a topic in the filed of machine learning where for an observed state, the agent takes an action with the aim of maximizing a reward. In the present context, the reward is to minimize the estimation error of the battery state-of-health. An advantage of using a reinforcement learning agent is that the value of K may change in relatively large steps which is not easily handled by a conventional Kalman filter).
Claim.7 Hellgren discloses wherein the reinforcement learning model is an offline reinforcement learning model that is trained in an offline session on data from cells of multiple electrical energy storage systems (see at least fig.1-2, p41, a battery 204 in turn comprising a plurality of battery cells 206 and a battery control unit 208. The control unit 208 may include a microprocessor, microcontroller, programmable digital signal processor or another programmable device. The control unit 208 may also, or instead, include an application specific integrated circuit, a programmable gate array or programmable array logic, a programmable logic device, or a digital signal processor. Where the control unit 208 includes a programmable device such as the microprocessor, microcontroller or programmable digital signal processor, p24, The battery control unit is configured to: determine a first battery property and a battery temperature of a battery in a vehicle; calculate a state-of-health, SoH.sub.calc, of a battery cell for the determined first battery property using a predetermined model; provide a function ƒ estimating a battery cell degradation rate; update a state-of health estimated in a previous time step according to H.sub.est←SoH.sub.est+f.Math.dt+K.Math.(SoH.sub.calc−SoH.sub.est), where K is a gain factor which is a dependent on operating conditions of the vehicle, and wherein K is modified for each time step using a reinforcement learning agent, p12, the model may for example be determined for a limited number of specific temperatures. The problem at hand thereby becomes to set a proper filter gain K, and the present invention is based on the realization that K is advantageously set using a reinforcement learning agent. Reinforcement learning is a topic in the filed of machine learning where for an observed state, the agent takes an action with the aim of maximizing a reward. In the present context, the reward is to minimize the estimation error of the battery state-of-health. An advantage of using a reinforcement learning agent is that the value of K may change in relatively large steps which is not easily handled by a conventional Kalman filter, p15, the determined battery property may also be another slowly changing parameter describing the battery, such as battery capacity. The relation between slowly varying battery properties and the battery State of Health can be determined “offline”, e.g. in a test laboratory, for certain temperatures and operating conditions).
Claim.8 Hellgren discloses wherein the object of the reinforcement learning model is to find
PNG
media_image2.png
139
566
media_image2.png
Greyscale
(see at least fig.1-2, step 108, modify K for each time step using a reinforcement learning agent, abstract, a method for estimating the state-of-health, SoH.sub.est, of a battery in a vehicle, the method comprising: determining a first battery property and a battery temperature of a battery in a vehicle; calculating a state-of-health, SoH.sub.calc of a battery cell based on the determined first battery property using a predetermined model, p14, the function ƒ is a function of the power provided by the battery, the function ƒ may also depend on the state-of-charge and battery temperature, which may also influence the degradation rate of the battery. For example, battery degradation may be higher at low temperatures and/or at low state-of-charge, p37, A straightforward model ƒ estimating a battery cell degradation rate may be formulated as:
PNG
media_image1.png
29
115
media_image1.png
Greyscale
, p12, the model may for example be determined for a limited number of specific temperatures. The problem at hand thereby becomes to set a proper filter gain K, and the present invention is based on the realization that K is advantageously set using a reinforcement learning agent. Reinforcement learning is a topic in the filed of machine learning where for an observed state, the agent takes an action with the aim of maximizing a reward. In the present context, the reward is to minimize the estimation error of the battery state-of-health. An advantage of using a reinforcement learning agent is that the value of K may change in relatively large steps which is not easily handled by a conventional Kalman filter)
Claim.9 Hellgren discloses wherein the processing circuitry is configured to iteratively: select an action that maximizes the reward function, feed the obtained output to an observation update, calculate an updated observation using Q-learning, and feed the updated observation back to the reward function (see at least fig.1-2, p41, a battery 204 in turn comprising a plurality of battery cells 206 and a battery control unit 208. The control unit 208 may include a microprocessor, microcontroller, programmable digital signal processor or another programmable device. The control unit 208 may also, or instead, include an application specific integrated circuit, a programmable gate array or programmable array logic, a programmable logic device, or a digital signal processor. Where the control unit 208 includes a programmable device such as the microprocessor, microcontroller or programmable digital signal processor, p24, The battery control unit is configured to: determine a first battery property and a battery temperature of a battery in a vehicle; calculate a state-of-health, SoH.sub.calc, of a battery cell for the determined first battery property using a predetermined model; provide a function ƒ estimating a battery cell degradation rate; update a state-of health estimated in a previous time step according to H.sub.est←SoH.sub.est+f.Math.dt+K.Math.(SoH.sub.calc−SoH.sub.est), where K is a gain factor which is a dependent on operating conditions of the vehicle, and wherein K is modified for each time step using a reinforcement learning agent, p12, the model may for example be determined for a limited number of specific temperatures. The problem at hand thereby becomes to set a proper filter gain K, and the present invention is based on the realization that K is advantageously set using a reinforcement learning agent. Reinforcement learning is a topic in the filed of machine learning where for an observed state, the agent takes an action with the aim of maximizing a reward. In the present context, the reward is to minimize the estimation error of the battery state-of-health. An advantage of using a reinforcement learning agent is that the value of K may change in relatively large steps which is not easily handled by a conventional Kalman filter).
Claim.11 Hellgren discloses a vehicle comprising the computer system of claim 1 (see at least fig.1-2, p24, a battery system comprising a battery comprising a plurality of battery cells and a battery control unit. The battery control unit is configured to: determine a first battery property and a battery temperature of a battery in a vehicle; calculate a state-of-health, SoH.sub.calc, of a battery cell for the determined first battery property using a predetermined model).
Claim.10 Hellgren discloses an electrical energy storage system (see at least abstract, estimating the state-of-health of a battery in a vehicle) comprising multiple electrical energy storage packs each comprising multiple electrical energy storage cells, and a processing circuitry (see at least fig.1-2, p4, the battery management system are (1), energy level state monitoring, i.e. state of charge estimation (2), power capacity state monitoring (3), maintaining of safe operation of the battery pack (4), state of health estimation and (5) ensuring that the cells in the battery pack are balanced, p39, estimate the state-of-health for a plurality of cells in a battery pack to properly account for variations between the battery cells of a battery)configured to: acquire cell data from cells of an electrical energy storage pack of the electrical energy storage system (see at least fig.1-2, abstract, calculating a state-of-health, SoH.sub.calc of a battery cell based on the determined first battery property using a predetermined model; providing a function f estimating a battery cell degradation rate, p4, the mathematical models include parameters describing cell properties such as for example resistance, capacity and open circuit voltage. Setting of these parameters is essential for efficient state monitoring, p39, accurately estimate the state-of-health for the battery as a whole, it is preferable to estimate the state-of-health for a plurality of cells in a battery pack to properly account for variations between the battery cells of a battery), determine at least two states of the cells based on evaluating the cell data; input the at least two states as input to a reinforcement learning algorithm configured to calculate control signal to balance the at least two states across the cells (see at least fig.1-2, step 108, modify K for each time step using a reinforcement learning agent, abstract, a method for estimating the state-of-health, SoH.sub.est, of a battery in a vehicle, the method comprising: determining a first battery property and a battery temperature of a battery in a vehicle; calculating a state-of-health, SoH.sub.calc of a battery cell based on the determined first battery property using a predetermined model, p14, the function ƒ is a function of the power provided by the battery, the function ƒ may also depend on the state-of-charge and battery temperature, which may also influence the degradation rate of the battery. For example, battery degradation may be higher at low temperatures and/or at low state-of-charge, p37, A straightforward model ƒ estimating a battery cell degradation rate may be formulated as:
PNG
media_image1.png
29
115
media_image1.png
Greyscale
), provide an output indicating the control signals (see at least fig.1-2, p41, a battery 204 in turn comprising a plurality of battery cells 206 and a battery control unit 208. The control unit 208 may include a microprocessor, microcontroller, programmable digital signal processor or another programmable device. The control unit 208 may also, or instead, include an application specific integrated circuit, a programmable gate array or programmable array logic, a programmable logic device, or a digital signal processor. Where the control unit 208 includes a programmable device such as the microprocessor, microcontroller or programmable digital signal processor, p24, The battery control unit is configured to: determine a first battery property and a battery temperature of a battery in a vehicle; calculate a state-of-health, SoH.sub.calc, of a battery cell for the determined first battery property using a predetermined model; provide a function ƒ estimating a battery cell degradation rate; update a state-of health estimated in a previous time step according to H.sub.est←SoH.sub.est+f.Math.dt+K.Math.(SoH.sub.calc−SoH.sub.est), where K is a gain factor which is a dependent on operating conditions of the vehicle, and wherein K is modified for each time step using a reinforcement learning agent).
Claim.12 Hellgren discloses a computer-implemented method (see at least abstract, estimating the state-of-health of a battery in a vehiclep4, the battery management system are (1), energy level state monitoring, i.e. state of charge estimation (2), power capacity state monitoring (3), maintaining of safe operation of the battery pack (4), state of health estimation and (5) ensuring that the cells in the battery pack are balanced, p39, estimate the state-of-health for a plurality of cells in a battery pack to properly account for variations between the battery cells of a battery)), comprising: acquiring, by processing circuitry of a computer system, cell data from cell sensors of an electrical energy storage pack of an electrical energy storage system of a vehicle, determining, by the processing circuitry, at least two states of the cells based on evaluating the cell data(see at least fig.1-2, abstract, calculating a state-of-health, SoH.sub.calc of a battery cell based on the determined first battery property using a predetermined model; providing a function f estimating a battery cell degradation rate, p4, the mathematical models include parameters describing cell properties such as for example resistance, capacity and open circuit voltage. Setting of these parameters is essential for efficient state monitoring, p39, accurately estimate the state-of-health for the battery as a whole, it is preferable to estimate the state-of-health for a plurality of cells in a battery pack to properly account for variations between the battery cells of a battery); providing, by the processing circuitry, the at least two states as input to a reinforcement learning algorithm configured to calculate control signals to balance the at least two states across the cells (see at least fig.1-2, step 108, modify K for each time step using a reinforcement learning agent, abstract, a method for estimating the state-of-health, SoH.sub.est, of a battery in a vehicle, the method comprising: determining a first battery property and a battery temperature of a battery in a vehicle; calculating a state-of-health, SoH.sub.calc of a battery cell based on the determined first battery property using a predetermined model, p14, the function ƒ is a function of the power provided by the battery, the function ƒ may also depend on the state-of-charge and battery temperature, which may also influence the degradation rate of the battery. For example, battery degradation may be higher at low temperatures and/or at low state-of-charge, p37, A straightforward model ƒ estimating a battery cell degradation rate may be formulated as:
PNG
media_image1.png
29
115
media_image1.png
Greyscale
), and providing, by the processing circuitry, an output indicating the control signals (see at least fig.1-2, p41, a battery 204 in turn comprising a plurality of battery cells 206 and a battery control unit 208. The control unit 208 may include a microprocessor, microcontroller, programmable digital signal processor or another programmable device. The control unit 208 may also, or instead, include an application specific integrated circuit, a programmable gate array or programmable array logic, a programmable logic device, or a digital signal processor. Where the control unit 208 includes a programmable device such as the microprocessor, microcontroller or programmable digital signal processor, p24, The battery control unit is configured to: determine a first battery property and a battery temperature of a battery in a vehicle; calculate a state-of-health, SoH.sub.calc, of a battery cell for the determined first battery property using a predetermined model; provide a function ƒ estimating a battery cell degradation rate; update a state-of health estimated in a previous time step according to H.sub.est←SoH.sub.est+f.Math.dt+K.Math.(SoH.sub.calc−SoH.sub.est), where K is a gain factor which is a dependent on operating conditions of the vehicle, and wherein K is modified for each time step using a reinforcement learning agent).
Claim.13 Hellgren discloses comprising: iteratively performing, by the processing circuitry, the steps as the vehicle is travelling (see at least fig.1-2, p41, a battery 204 in turn comprising a plurality of battery cells 206 and a battery control unit 208. The control unit 208 may include a microprocessor, microcontroller, programmable digital signal processor or another programmable device. The control unit 208 may also, or instead, include an application specific integrated circuit, a programmable gate array or programmable array logic, a programmable logic device, or a digital signal processor. Where the control unit 208 includes a programmable device such as the microprocessor, microcontroller or programmable digital signal processor, p24, The battery control unit is configured to: determine a first battery property and a battery temperature of a battery in a vehicle; calculate a state-of-health, SoH.sub.calc, of a battery cell for the determined first battery property using a predetermined model; provide a function ƒ estimating a battery cell degradation rate; update a state-of health estimated in a previous time step according to H.sub.est←SoH.sub.est+f.Math.dt+K.Math.(SoH.sub.calc−SoH.sub.est), where K is a gain factor which is a dependent on operating conditions of the vehicle, and wherein K is modified for each time step using a reinforcement learning agent).
Claim.14 Hellgren discloses wherein the output indicates discharge currents to be applied to the cells (see at least fig.1-2, p16, the gain factor K is a function of the battery temperature. Thereby, a more accurate setting of the gain factor K can be achieved since the setting can be adapted to current operating conditions, and in particular to the battery temperature, p17, K should change depending on the current operating condition).
Claim.15 Hellgren discloses wherein the states include at least two of state of charge, state of temperature, and state of health (see at least fig.1-2, step 108, modify K for each time step using a reinforcement learning agent, abstract, a method for estimating the state-of-health, SoH.sub.est, of a battery in a vehicle, the method comprising: determining a first battery property and a battery temperature of a battery in a vehicle; calculating a state-of-health, SoH.sub.calc of a battery cell based on the determined first battery property using a predetermined model, p14, the function ƒ is a function of the power provided by the battery, the function ƒ may also depend on the state-of-charge and battery temperature, which may also influence the degradation rate of the battery. For example, battery degradation may be higher at low temperatures and/or at low state-of-charge, p37, A straightforward model ƒ estimating a battery cell degradation rate may be formulated as:
PNG
media_image1.png
29
115
media_image1.png
Greyscale
).
Claim.16 Hellgren discloses comprising: simultaneously balancing all of state of charge, state of temperature, and state of health (see at least fig.1-2, step 108, modify K for each time step using a reinforcement learning agent, abstract, a method for estimating the state-of-health, SoH.sub.est, of a battery in a vehicle, the method comprising: determining a first battery property and a battery temperature of a battery in a vehicle; calculating a state-of-health, SoH.sub.calc of a battery cell based on the determined first battery property using a predetermined model, p14, the function ƒ is a function of the power provided by the battery, the function ƒ may also depend on the state-of-charge and battery temperature, which may also influence the degradation rate of the battery. For example, battery degradation may be higher at low temperatures and/or at low state-of-charge, p37, A straightforward model ƒ estimating a battery cell degradation rate may be formulated as:
PNG
media_image1.png
29
115
media_image1.png
Greyscale
).
Claim.17 Hellgren discloses wherein the feedback from the cells, including estimations of the states are fed back to the reinforcement learning model, wherein the reinforcement learning model is configured to provide an action that includes the control signals (see at least fig.1-2, p41, a battery 204 in turn comprising a plurality of battery cells 206 and a battery control unit 208. The control unit 208 may include a microprocessor, microcontroller, programmable digital signal processor or another programmable device. The control unit 208 may also, or instead, include an application specific integrated circuit, a programmable gate array or programmable array logic, a programmable logic device, or a digital signal processor. Where the control unit 208 includes a programmable device such as the microprocessor, microcontroller or programmable digital signal processor, p24, The battery control unit is configured to: determine a first battery property and a battery temperature of a battery in a vehicle; calculate a state-of-health, SoH.sub.calc, of a battery cell for the determined first battery property using a predetermined model; provide a function ƒ estimating a battery cell degradation rate; update a state-of health estimated in a previous time step according to H.sub.est←SoH.sub.est+f.Math.dt+K.Math.(SoH.sub.calc−SoH.sub.est), where K is a gain factor which is a dependent on operating conditions of the vehicle, and wherein K is modified for each time step using a reinforcement learning agent, p12, the model may for example be determined for a limited number of specific temperatures. The problem at hand thereby becomes to set a proper filter gain K, and the present invention is based on the realization that K is advantageously set using a reinforcement learning agent. Reinforcement learning is a topic in the filed of machine learning where for an observed state, the agent takes an action with the aim of maximizing a reward. In the present context, the reward is to minimize the estimation error of the battery state-of-health. An advantage of using a reinforcement learning agent is that the value of K may change in relatively large steps which is not easily handled by a conventional Kalman filter).
Claim.18 Hellgren discloses wherein the reinforcement learning model is an offline reinforcement learning model that is trained in an offline session on data from cells of multiple electrical energy storage devices (see at least fig.1-2, p41, a battery 204 in turn comprising a plurality of battery cells 206 and a battery control unit 208. The control unit 208 may include a microprocessor, microcontroller, programmable digital signal processor or another programmable device. The control unit 208 may also, or instead, include an application specific integrated circuit, a programmable gate array or programmable array logic, a programmable logic device, or a digital signal processor. Where the control unit 208 includes a programmable device such as the microprocessor, microcontroller or programmable digital signal processor, p24, The battery control unit is configured to: determine a first battery property and a battery temperature of a battery in a vehicle; calculate a state-of-health, SoH.sub.calc, of a battery cell for the determined first battery property using a predetermined model; provide a function ƒ estimating a battery cell degradation rate; update a state-of health estimated in a previous time step according to H.sub.est←SoH.sub.est+f.Math.dt+K.Math.(SoH.sub.calc−SoH.sub.est), where K is a gain factor which is a dependent on operating conditions of the vehicle, and wherein K is modified for each time step using a reinforcement learning agent, p12, the model may for example be determined for a limited number of specific temperatures. The problem at hand thereby becomes to set a proper filter gain K, and the present invention is based on the realization that K is advantageously set using a reinforcement learning agent. Reinforcement learning is a topic in the filed of machine learning where for an observed state, the agent takes an action with the aim of maximizing a reward. In the present context, the reward is to minimize the estimation error of the battery state-of-health. An advantage of using a reinforcement learning agent is that the value of K may change in relatively large steps which is not easily handled by a conventional Kalman filter, p15, the determined battery property may also be another slowly changing parameter describing the battery, such as battery capacity. The relation between slowly varying battery properties and the battery State of Health can be determined “offline”, e.g. in a test laboratory, for certain temperatures and operating conditions).
Claim.19 Hellgren discloses a computer program product comprising program code for performing, when executed by the processing circuitry, the method of claim 12 (see at least fig.1-2, p41, the control unit 208 may include a microprocessor, microcontroller, programmable digital signal processor or another programmable device. The control unit 208 may also, or instead, include an application specific integrated circuit, a programmable gate array or programmable array logic, a programmable logic device, or a digital signal processor. Where the control unit 208 includes a programmable device such as the microprocessor, microcontroller or programmable digital signal processor mentioned above, the processor may further include computer executable code that controls operation of the programmable device).
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.
Claim(s) 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hellgren (US20210263109A1) as applied to claim 12 above, and further in view of Song (US20170205469A1).
Claim.20 Hellgren does not discloses a non-transitory computer-readable storage medium comprising instructions, which when executed by the processing circuitry, cause the processing circuitry to perform the method of claim 12.
However, Song discloses a non-transitory computer-readable storage medium comprising instructions, which when executed by the processing circuitry, cause the processing circuitry to perform the method of claim 12 (see at least fig.3, p81, on one or more non-transitory computer-readable storage media. Examples of a non-transitory computer-readable storage medium include read-only memory (ROM), random-access memory (RAM), flash memory, CD-ROMs, CD-Rs, CD+Rs, CD-RWs, CD+RWs, DVD-ROMs, DVD-Rs, DVD+Rs, DVD-RWs, DVD+RWs, DVD-RAMs, BD-ROMs, BD-Rs, BD-R LTHs, BD-REs, magnetic tapes, floppy disks, magneto-optical data storage devices, optical data storage devices, hard disks, solid-state disks, and any other device that is configured to store the instructions or software and any associated data, data files, and data structures in a non-transitory manner and provide the instructions or software and any associated data, data files, and data structures to one or more processors or computers so that the one or more processors or computers can execute the instructions).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the instant application to modify Hellgren to include a non-transitory computer-readable storage medium comprising instructions, which when executed by the processing circuitry, cause the processing circuitry to perform the method of claim 12 by Song in order to estimate SOH of a battery based on degradation of the battery and the data acquired from the battery (see Song’s abstract).
Conclusion
Related References
The relevant art made of record and not relied upon is considered pertinent to applicant’s disclosure.
Sidiropoulos (US20230216313A1) discloses charging and/or discharging of one or more units (e.g., battery cells and/or multi-cell battery clusters of battery cells) based at least in part on state of charge and/or state of health monitoring at one or more of the cell-level and/or cluster-level. An exemplary method can comprise monitoring, by a system operatively coupled to a processor, cell states of cells of a multi-cell battery cluster, and selectively determining, by the system, based on the cell states, a time-based order for electrically connecting the cells to an external apparatus for current flow between the external apparatus and the cluster. The cell states can be provided as a function of a cluster state of the cluster. The cell states can be provided as one or more of states of health of the cells or states of charge of the cells determined from the monitoring.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHARDUL D PATEL whose telephone number is (571)270-7758. The examiner can normally be reached Monday-Friday 8am-5pm (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, KITO ROBINSON can be reached at (571)270-3921. 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.
/SHARDUL D PATEL/Primary Examiner, Art Unit 3664
Prosecution Insights