Robert Boschgmbh

Robert Bosch Gmbh

Reinhardt Klein

John F Christensen

Nikhil Ravi

Anahita MirTabatabaei

Ashish S Krupadanam

Anantharaman Subbaraman

Aleksandar Kojic

Nalin Chaturvedi

Yelena Gorlin

Gerd Simon Schmidt

Yongfang Cheng

Christopher Mayhew

Christoph Klee

Sarah Stewart

Maksim Subbotin

Abdul-Kader Srouji

Farshad Ramezan Pour Safaei

Camille Usubelli

Rebecca Wilhelm

Bernd Schumann

Soo Kim

Jasim Ahmed

Christoph Woll

Jake Christensen

Christian Simonis

Christina Johnston

Jens Grimminger

Andras Gabor Kupcsik

Martin Holger Koenigsmann

Joerg Ziegler

Jörg Ziegler

Aleksander Kojic

Sun Ung Kim

Kevin Kimura

Jared Evans

Christoph Kroener

Ashish Krupadanam

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. Commands are given to charge an on-field battery based on the augmented reinforcement learning model, associated state-of-health characteristics of the on-field battery are determined, and the reinforcement learning model is further augmented accordingly.

Reinforcement learning for continued learning of optimal battery charging

An electric vehicle (EV) chassis is disclosed that may be a modular platform flexible as a basis for numerous other EV platforms. It is contemplated that the entire electric drivetrain (i.e., powertrain, wheels, steering) may be supplied to an automotive original equipment manufacturer (OEM). The OEM may use the EV chassis for integration within a representative passenger compartment. The chassis may also be reconfigurable with the modularity at various levels that include the energy storage system, the entire chassis system, or any level in-between. The chassis may further be designed to allow connection of multiple modules to enable a larger scale energy storage that may be provided to homes, buildings, or the electric power grid.

Reconfigurable electric vehicle chassis

A computer-implemented method for operating a motor vehicle, in particular an electrically drivable motor vehicle, depending on a predicted state of health of an electrical energy store, in particular a vehicle battery. The method includes: providing vehicle parameters which influence the state of health of the electrical energy store; predicting the vehicle parameters at a prediction point in time; ascertaining the predicted state of health depending on the predicted vehicle parameters with the aid of a data-based state of health model which is trained to output a state of health of the electrical energy store depending on the vehicle parameters; and signaling the predicted state of health.

Method and device for operating an electrically drivable motor vehicle depending on a predicted state of health of an electrical energy store

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.

Physics-based control of battery temperature

Battery management systems and methods for use with lithium-ion batteries that employ silicon-based negative electrodes. The battery management systems and methods consider the lithiation/delithiation properties of silicon-based anode materials by considering voltage relaxation behavior. The battery management systems and methods may also be applied to other materials that similarly display an apparent hysteresis in the lithiation/delithiation processes and/or form multiple phases with different electrochemical properties.

Management systems and methods for silicon-containing lithium-ion batteries

A battery includes an electrode that exhibits a crystal structure change when lithiated beyond a threshold potential and a battery management system. The battery management system includes a controller configured to, while the battery is online, determine the threshold potential, determine battery operating parameters based on the determined threshold potential, and operate the battery based on the determined battery operating parameters.

System and method for operating batteries based on electrode crystal structure change

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.

Method for approximating algorithms for fast charging li-ion batteries based on electrochemical battery models

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.

System and method for fast charging of lithium-ion batteries

A method for generating battery characteristics for a battery having a target composition includes identifying open-circuit potential (OCP) characteristics for two similar battery compositions having different proportions of elements. The OCP characteristics are converted to dQ/dV characteristics and linearly combined to derived a target dQ/dV characteristic. The target dQ/dV characteristic is integrated to derived a target OCP characteristic. A battery constructed of the target composition is operated according to the target OCP characteristic.

Method for predicting an open-circuit potential curve as a function of lithiation for a class of cathode materials

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.

Secondary battery management system

A battery system in one embodiment includes a cell with an anode including graphite and a minor active material that displays an apparent thermodynamic hysteresis. A controller is operably connected to a memory which is configured to execute program instructions in the memory to perform a charge of the cell to a first potential, and a discharge of the cell from the first potential to generate a first discharge versus capacity curve. After a second charge of the cell to a second potential and a second discharge of the cell from the second potential to generate a second discharge versus capacity curve, the controller identifies a shift between the first discharge versus capacity curve and the second discharge versus capacity curve and updates a model of the cell based upon the identified shift. The controller then modifies at least one operating parameter of the cell based upon the updated model.

Battery management system with mixed electrode

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.

Evaluating capacity fade in dual insertion batteries using potential and temperature measurements

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.

Secondary battery management

A method of managing a battery system, the method including receiving at least one measured characteristic of the at least one battery cell from the at least one sensor, estimating at least one state of the at least one battery cell at a first time by applying an electrochemical-based battery model, estimating at least one physical parameter of the at least one battery cell based on the at least one measured characteristic and the estimation of the at least one state, estimating the at least one state at a second time, subsequent to the first time, by applying the electrochemical-based battery model based on the estimated at least one parameter, and regulating at least one of charging or discharging of the at least one battery cell based on the estimation of the at least one state.

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.

Growing community of inventors

Mountain View, CA, United States of America

Reinhardt Klein