Abstract: Methods and systems of optimizing battery charging are disclosed. Battery state sensors are used to determine anode overpotential of a battery multiple times during multiple charge cycles. In a first phase, a reinforcement learning model (e.g., actor-critic model) is trained with rewards given throughout each charge cycle of the battery to optimize training. The reinforcement learning model can determine state-of-health characteristics of the battery over the charge cycles, and in a second phase, the reinforcement learning model is augmented accordingly. During this augmentation, the reinforcement learning model is trained with rewards given on a charge cycle-by-cycle basis, wherein rewards are given after looking at the charging optimization after the conclusion of each charge cycle.

Abstract: An object-based data storage service receives a request to store a data object in a first location corresponding to a first data storage tier. The request may specify a parameter to enable transitioning of the data object to another data storage tier. In response to the request, the object-based data storage service stores the data object in the first location and monitors access of the data object to determine usage data associated with the data object. The object-based data storage service processes the usage data to determine that the data object is to be transitioned to a second data storage tier. As a result of this determination, the object-based data storage service transitions the data object to a second location corresponding to the second data storage tier.

Abstract: A method of monitoring and replacing fuel cells within a fuel cell stack assembly. The method includes measuring one or more operating conditions of a fuel cell within the fuel cell stack assembly. The method includes determining, using a processor, a state of health of the fuel cell based at least in part on the one or more operating conditions. The method includes detaching the fuel cell from an adjacent cell within the fuel cell stack assembly by removing a first electrically-conducing mating matrix associated with a first endplate of the fuel cell from a second electrically-conducing mating matrix associated with a second endplate of the adjacent cell. The method includes attaching a replacement fuel cell by mating a third electrically-conducing mating matrix associated with a third endplate of the replacement fuel cell with a fourth electrically-conducing mating matrix associated with a fourth endplate of the adjacent cell.

Abstract: An electrochemical battery system includes at least one electrochemical cell, a thermal control system operably connected to the at least one electrochemical cell, a memory in which a physics-based model of the at least one electrochemical cell is stored and in which program instructions are stored, and a controller operably connected to the at least one electrochemical cell, the thermal control system and the memory. The controller is configured to execute the program instructions to identify a first requested operation, obtain a first generated target temperature which is based on the physics-based model and the identified first requested operation, and control the thermal control system based upon the obtained first target temperature while controlling the at least one electrochemical cell based upon the identified first requested operation.

Abstract: A unit cell for a fuel cell stack including an anode catalyst layer separated by a polymer electrolyte membrane from a cathode catalyst layer, a first cell end plate separated by a first gas diffusion layer from the anode catalyst layer, and a second cell end plate separated by a second gas diffusion layer from the cathode catalyst layer, wherein the first cell end plate, the second cell end plate, or both include a matrix of electrically-conducting protrusions thereof.

Abstract: A method and system for charging a battery (e.g., including but not limited to lithium-ion batteries). The method may comprise: iteratively determining a plurality of charge profiles of the battery; based on the plurality of charge profiles, iteratively determining swelling of the battery; and adjusting a charge current during a subsequent charging of the battery.

Abstract: A method, system, and non-transitory computer readable medium for determining a pseudo-optimal charging algorithm for a specific battery are disclosed. An electrochemical battery model is characterized based on the physical characteristics of a specific battery. An optimal charging profile is determined for the specific battery using the highly accurate electrochemical battery model. A pseudo-optimal charging profile is determined which closely approximates the optimal charging profile. However, the pseudo-optimal charging profile is comprised of simple building blocks which are easily and efficiently implemented in embedded applications having limited computational power/memory. An optimization process is used to determine optimal control parameters for the simple building blocks, trigger conditions and thresholds, and adaptation parameters for adapting the pseudo-optimal charging profile as the battery ages.

Abstract: A Li-ion battery management system comprises a Li-ion cell, one or more sensors configured to sense one or more operating conditions of the Li-ion cell, a controller having non-transitory memory for storing machine instructions that are to be executed by the controller and operatively connected to the Li-ion cell, the machine instructions when executed by the controller implement the following functions: receive the one or more operating conditions and a trained machine learning (ML) model, and output an indicator value along a state of charge (SOC) trajectory in response to the one or more operating conditions and the trained ML model to control a fast charge state of the Li-ion cell from a current source.

Abstract: A unit cell for a fuel cell stack including an anode catalyst layer separated by a polymer electrolyte membrane from a cathode catalyst layer, a first cell end plate separated by a first gas diffusion layer from the anode catalyst layer, and a second cell end plate separated by a second gas diffusion layer from the cathode catalyst layer, wherein the first cell end plate, the second cell end plate, or both include a matrix of electrically-conducting protrusions thereof.

Abstract: A battery management system includes a memory, a current sensor that measures a current flow through a battery to a load, a voltage sensor that measures a voltage level between a first terminal and a second terminal of the battery that are each connected to the load, and the memory, a temperature sensor that measures a temperature level of the battery; and a controller configured to be operatively connected to the current sensor, temperature sensor, and voltage sensor. The controller is configured to receive a measurement of a first current level and a first voltage level and utilize a corrected capacity and corrected open circuit voltage estimate to output an estimated open circuit voltage of the battery as compared to an estimated capacity.

Abstract: A method and system for managing a battery system. The method including receiving at least one measured characteristic of the battery over a pre-defined time horizon from the at least one sensor, receiving at least one estimated characteristic of the battery from a electrochemical-based battery model based on differential algebraic equations, determining a cost function of a Moving Horizon Estimation based on the at least one measured characteristic and the at least one estimated characteristic, updating the electrochemical-based battery model based on the cost function, estimating at least one state of the at least one battery cell by applying the electrochemical-based battery model, and regulating at least one of charging or discharging of the battery based on the estimation of the at least one state of the at least one battery cell.

Abstract: In one embodiment, an electrochemical battery system includes at least one electrochemical cell, a thermal control system operably connected to the at least one electrochemical cell, a memory in which a physics-based model of the at least one electrochemical cell is stored and in which program instructions are stored, and a controller operably connected to the at least one electrochemical cell, the thermal control system and the memory. The controller is configured to execute the program instructions to identify a first requested operation, obtain a first generated target temperature which is based on the physics-based model and the identified first requested operation, and control the thermal control system based upon the obtained first target temperature while controlling the at least one electrochemical cell based upon the identified first requested operation.

Abstract: An All-Wheel-Drive (AWD), multi-mode, power-split hybrid vehicle employing a drive combining all electric motors and an internal combustion engine, together collocated on a 2-planetary-gear (PG) set. The present teachings are capable of delivering competitive performance while maximizing fuel economy through power-split hybrid design.

Abstract: A Li-ion battery management system comprises a Li-ion cell, one or more sensors configured to sense one or more operating conditions of the Li-ion cell, a controller having non-transitory memory for storing machine instructions that are to be executed by the controller and operatively connected to the Li-ion cell, the machine instructions when executed by the controller implement the following functions: receive the one or more operating conditions and a trained machine learning (ML) model, and output an indicator value along a state of charge (SOC) trajectory in response to the one or more operating conditions and the trained ML model to control a fast charge state of the Li-ion cell from a current source.

Abstract: Methods and systems are described of managing a battery system. The battery system including at least one battery cell and one or more sensors configured to measure a temperature of the at least one battery cell. The method includes receiving a measurement of the temperature of the at least one battery cell, estimating an open circuit potential of the at least one battery cell, estimating a capacity fade of the at least one battery cell based on the open circuit potential of the at least one battery cell and a ratio of a change in the open circuit potential relative to a change in the temperature of the at least one battery cell, and regulating at least one of charging or discharging of the at least one battery cell based on the estimation of the capacity fade.

Abstract: A method of managing a battery system, the battery system including at least one battery cell, at least one sensor configured to measure at least one characteristic of the battery cell, and a battery management system including a microprocessor and a memory, the method comprising receiving by the battery management system, from the at least one sensor at least one measured characteristic of the battery cell at a first time and at least one measured characteristic of the battery cell at a second time. The battery management system estimating, at least one state of the battery cell by applying a physics-based battery model, the physics based battery model being based on differential algebraic equations; and regulating by the battery management system, at least one of charging or discharging of the battery cell based on the at least one estimated state.

Abstract: A method, system, and non-transitory computer readable medium for determining a pseudo-optimal charging algorithm for a specific battery are disclosed. An electrochemical battery model is characterized based on the physical characteristics of a specific battery. An optimal charging profile is determined for the specific battery using the highly accurate electrochemical battery model. A pseudo-optimal charging profile is determined which closely approximates the optimal charging profile. However, the pseudo-optimal charging profile is comprised of simple building blocks which are easily and efficiently implemented in embedded applications having limited computational power/memory. An optimization process is used to determine optimal control parameters for the simple building blocks, trigger conditions and thresholds, and adaptation parameters for adapting the pseudo-optimal charging profile as the battery ages.

Abstract: A multi-mode, power-split hybrid transmission system having two planetary gear (PG) sets connected to one engine, two electric motors, one output shaft, and each other by several clutches, brakes, and direct connection elements. Depending on the specific location and actuation of the various clutch and brake elements, the multi-mode, power-split hybrid transmission system can be run in one of several modes (e.g. electric drive, power-split, parallel hybrid, series hybrid, electronic continuously variable transmission (eCVT), generator, neutral, and the like).

Abstract: An engine system uses data associated with at least one operating condition of an engine to set the engine system to an AI mode when the engine is in an SI mode 1) within first operating condition limits, and 2) when a rate of change of a first operating condition is within rate of change limits, maintain the engine system in the SI mode when the engine is outside of first operating condition limits or when the rate of change of the first operating condition is not within rate of change limits, set the engine system to the SI mode when the engine is in the AI mode outside second operating condition limits, and maintain the engine system in the AI mode when the engine is within second operating condition limits, wherein the second operating condition limits are different from the first operating condition limits.

Abstract: A battery system, having a battery management system configured to determine the state of charge and state of health of a secondary battery. The battery management system may export data to and receive inputs from a remote computer which calculates at least a portion of the state of health of the battery.