Back to results
US 11,691,518 B2Granted
Predictive model for estimating battery states
AssigneeQuantumScape Battery, Inc.
InventorTim Holme
Life of this patent
Estimating the term…
Abstract
A battery management system (BMS) for a vehicle includes a module for estimating the state of a rechargeable battery, such as its state of charge, in real time. The module includes a learning model for predicting the state of a battery based on the vehicle's usage and related factors unique to the vehicle, in addition to a sensed voltage, current and temperature of a battery.
Claims21
A management system for electrochemical batteries, comprising
- at least one series string of battery cells, wherein the battery cells comprise a solid-state lithium secondary battery, wherein the solid-state lithium secondary battery includes a lithium-stuffed garnet electrolyte;
- one or more sensors configured to provide sensor data obtained from the series string of battery cells, the sensor data comprising at least one of a measured voltage, current, impedance, pressure, or temperature;
- and
- a prediction module for a battery type, coupled to the one or more sensors, the prediction module comprising:
- a battery model that includes a plurality of input parameters and at least one target, wherein the plurality of input parameters include at least one of a voltage, current, impedance, pressure, and temperature input parameter, and the target is at least one battery state,
- a learning component that trains the battery model using training sets comprising values for the input parameters and targets, the learning component providing a trained battery model, and
- a prediction component that uses the trained battery model and a new set of values for the input parameters to predict a battery state;
- wherein the predicted battery state is at least one of a
- (a) state-of-charge (SOC),
- (b) state-of-health (SOH),
- (c) voltage response to current demand,
- (d) power available,
- (e) energy available,
- (f) energy available with respect to a planned route,
- (g) presence of a safety condition,
- (h) presence of a repair condition,
- (i) battery life,
- (j) battery temperature,
- (k) battery voltage,
- (l) battery impedance, and
- (m) battery cell pressure
- wherein the battery model includes additional input parameters, the additional input parameters comprising one or more of
- (a) the age of the battery,
- (b) a last battery, or power train servicing date,
- (c) a vehicle identification number (VIN), or make and model,
- (d) a driving pattern,
- (e) a geographic location or predicted weather forecast,
- (f) an age of a registered driver,
- (g) number of discharge cycles, or average percentage of battery discharges between charges using an external power source, and
- (h) number of warning conditions issued on the battery,
- wherein the trained battery model is trained on both the one or more sensor data and the additional parameters.
28 more elements
A method, comprising:
- using a vehicle;
- using a battery model having input parameters including at least one of a voltage, current, impedance, pressure, or temperature input parameter for a battery type, and at least one target for the battery type;
- using at least one or more sensors located on the vehicle, obtaining data on at least one physical state of at least one series string of battery cells of the vehicle, wherein the at least one series string of battery cells is a solid-state lithium secondary battery, wherein the solid-state lithium secondary battery includes a lithium-stuffed garnet electrolyte, wherein the data obtained comprises at least one of a measured voltage, current, impedance, pressure, or temperature of the at least one series string of battery cells;
- making a trained battery model, including training the battery model using training sets comprising values for each one of the input parameters and a corresponding value for the at least one target using at least the obtained data,
- wherein the trained battery model includes additional input parameters, the additional input parameters comprising one or more of
- (a) the age of the battery,
- (b) a last battery, or power train servicing date,
- (c) a vehicle identification number (VIN), or make and model,
- (d) a driving pattern,
- (e) a geographic location or predicted weather forecast,
- (f) an age of a registered driver,
- (g) number of discharge cycles, or average percentage of battery discharges between charges using an external power source,
- (h) number of warning conditions issued on the battery,
- wherein the trained battery model is trained on both the one or more sensor data and the additional parameters;
- wherein the obtaining data step occurs while the series string of battery cells is
- (a) in an open circuit condition,
- (b) under an operating load,
- (b) during a charging event,
- (c) during a diagnostic event,
- (d) during a repair event, or
- (e) during a safety event.
18 more elements
Dependencies are inferred from the claim text.