公开(公告)号：US20170214252A1

公开(公告)日：2017-07-27

申请号：US15406149

申请日：2017-01-13

Applicant: McMaster University

Inventor： Matthias Preindl ,  Ali Emadi

IPC: H02J7/00 ,  H02M3/04

CPC classification number: H02J7/0014 ,  H02J7/0018 ,  H02J7/345 ,  H02M3/04 ,  H02M3/24 ,  H02M2001/0074 ,  Y02B40/90 ,  Y02E70/40 ,  Y02T10/7055 ,  Y02T50/54

Abstract: The integration of the auxiliary power module (APM) functionality into non-dissipative balancing hardware of a high voltage battery or supercapacitor pack enables a more cost-effective non-dissipative balancing system while maintaining a similar complexity in topologies. The system uses state-space equations and three control problems to balance high-voltage energy storage elements and charge low voltage energy storage elements. Two optimization based controllers are employed to optimize both balancing and charging simultaneously.

公开(公告)号：US20220271549A1

公开(公告)日：2022-08-25

申请号：US17497537

申请日：2021-10-08

Applicant: The Trustees of Columbia University in the City of New York ,  McMaster University

Inventor： Ephram Chemali ,  Matthias Preindl

IPC: H02J7/00 ,  G06N3/04 ,  G01R31/382

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.

公开(公告)号：US20230280410A1

公开(公告)日：2023-09-07

申请号：US18118231

申请日：2023-03-07

Applicant: The Trustees of Columbia University in the City of New York ,  McMaster University

Inventor： Ephram Chemali ,  Matthias Preindl

IPC: G01R31/392 ,  G01R31/382 ,  H01M10/48 ,  H02J7/00 ,  G06N3/045

CPC classification number: G01R31/392 ,  G01R31/382 ,  H01M10/486 ,  H02J7/0048 ,  G06N3/045 ,  G06N3/08

Abstract: An approach to control or monitoring of battery operation makes use of an artificial neural network (ANN), 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) and/or a state-of-health (SOH) estimate for the Li-ion battery. The ANN includes at least one of a recurrent neural network (RNN) and a convolutional neural network (CNN), and the series of values of the battery attributes includes at one of battery voltage values, battery current values, and battery temperature values.

公开(公告)号：US11637331B2

公开(公告)日：2023-04-25

申请号：US16688260

申请日：2019-11-19

Applicant: The Trustees of Columbia University in the City of New York ,  McMaster University

Inventor： Ephram Chemali ,  Matthias Preindl

IPC: H01M10/48 ,  H02J7/00 ,  G01R31/392 ,  G01R31/382 ,  G06N3/04 ,  G06N3/08 ,  H01M10/0525 ,  G06N20/20

Abstract: An approach to control or monitoring of battery operation makes use of an artificial neural network (ANN), 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) and/or a state-of-health (SOH) estimate for the Li-ion battery. The ANN includes at least one of a recurrent neural network (RNN) and a convolutional neural network (CNN), and the series of values of the battery attributes includes at one of battery voltage values, battery current values, and battery temperature values.

公开(公告)号：US20200081070A1

公开(公告)日：2020-03-12

申请号：US16688260

申请日：2019-11-19

Applicant: The Trustees of Columbia University in the city of New York ,  McMaster University

Inventor： Ephrem Chemali ,  Matthias Preindl

IPC: G01R31/392 ,  G01R31/382 ,  G06N3/08 ,  G06N3/04 ,  G06N20/20 ,  H01M10/48 ,  H01M10/0525

Abstract: An approach to control or monitoring of battery operation makes use of an artificial neural network (ANN), 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) and/or a state-of-health (SOH) estimate for the Li-ion battery. The ANN includes at least one of a recurrent neural network (RNN) and a convolutional neural network (CNN), and the series of values of the battery attributes includes at one of battery voltage values, battery current values, and battery temperature values.

公开(公告)号：US10581253B2

公开(公告)日：2020-03-03

申请号：US15406149

申请日：2017-01-13

Applicant: McMaster University

Inventor： Matthias Preindl ,  Ali Emadi

IPC: H02J7/00 ,  H02J7/34 ,  H02M3/04 ,  H02M3/24 ,  H02M1/00

Abstract: The integration of the auxiliary power module (APM) functionality into non-dissipative balancing hardware of a high voltage battery or supercapacitor pack enables a more cost-effective non-dissipative balancing system while maintaining a similar complexity in topologies. The system uses state-space equations and three control problems to balance high-voltage energy storage elements and charge low voltage energy storage elements. Two optimization based controllers are employed to optimize both balancing and charging simultaneously.