Back to results
US 2019/0157891 A1Published application
Neural-network state-of-charge estimation
AssigneeThe Trustees of Columbia University in the City of New York
InventorsEphram Chemali, Matthias Preindl
Life of this patent
Estimating the term…
Abstract
An approach to control or monitoring of battery operation makes use of a recurrent neural network (RNN), which receives one or more battery attributes for a Lithium ion (Li-ion) battery, and determines, based on the received one or more battery attributes, a state-of-charge (SOC) estimate for the Li-ion battery.
Claims15
A method for monitoring battery operation, the method comprising:
- receiving by a recurrent neural network (RNN) a time series of values one or more battery attributes for a battery;
- and
- determining by the RNN, based on the received time series, a state estimate for the battery.
A system for monitoring battery operation comprising:
- at least one sensor for measuring one or more battery attributes of at least one battery;
- and
- a recurrent neural network (RNN) system configured according to stored numerical parameters to
- receive a time series of values one or more battery attributes for a battery from the at least one sensor, and
- determining, based on the received time series, a state estimate for the battery;
- wherein the RNN comprises a memory cell configured to be selectively updated according to inputs to the recurrent neural network.
3 more elements
Dependencies are inferred from the claim text.