Device including battery

Patent metadata

Field	Value
Publication number	US-2020074297-A1
Application number	US-201816181271-A
Country	US
Kind code	A1
Filing date	Nov 5, 2018
Priority date	Sep 3, 2018
Publication date	Mar 5, 2020
Grant date	—

Abstract

A method of controlling a battery is disclosed. The method includes training an artificial neural network to calculate an internal characteristic parameter value of the battery corresponding to a sensed input/output parameter value using training data, sensing the input/output parameter value of the battery, acquiring the characteristic parameter value corresponding to the sensed input/output parameter value using the trained artificial neural network, and controlling charging or discharging of the battery based on the acquired characteristic parameter value.

First claim

What is claimed is:

1 . A method for controlling a battery of a device comprising a sensing unit and a controller, the method comprising:
sensing, by the sensing unit, an input/output parameter value of the battery; acquiring, by the controller, a characteristic parameter value of the battery corresponding to the sensed input/output parameter value using a trained artificial neural network; and controlling, by the controller, charging or discharging of the battery based on the acquired characteristic parameter value, wherein the trained artificial neural network is an artificial neural network trained to calculate the characteristic parameter value corresponding to the sensed input/output parameter value using training data.

2 . The method of claim 1 , wherein the training data includes an input/output parameter value of one or more batteries corresponding to the battery and a characteristic parameter value corresponding to the input/output parameter value of the one or more batteries.

3 . The method of claim 1 , wherein:
the controlling of charging or discharging of the battery comprises: acquiring internal state information of the battery based on the characteristic parameter value; and controlling charging or discharging of the battery based on the internal state information; and the internal state information is at least one of deterioration of the battery, a degree of abnormality, a charge threshold, or a discharge threshold.

4 . The method of claim 1 , wherein the input/output parameter value includes at least one of a voltage, current, or a temperature as a parameter measured outside the battery.

5 . The method of claim 1 , wherein the characteristic parameter value includes at least one of electronic conductivity, solid diffusivity, a reaction rate constant of exchange current, tortuosity, porosity, electrolyte concentration, electrolyte conductivity, electrolyte diffusivity, a transference number, difference between capacity of an anode and capacity of a cathode due to degradation, or a degree of reduction in capacity of the anode/cathode as a parameter indicating a state of an internal material of the battery.

6 . The method of claim 1 , wherein the controlling of charging or discharging of the battery comprises controlling charging or discharging of the battery according to a control rule corresponding to the acquired characteristic parameter value among a plurality of control rules stored in a storage unit.

7 . The method of claim 1 , wherein the controlling of charging or discharging of the battery comprises:
displaying a plurality of control options, each corresponding to a respective one of a plurality of control rules, based on the acquired characteristic parameter value; and when an input of selecting a specific control option among the plurality of control options is received, controlling charging or discharging of the battery according to a control rule corresponding to the specific control option.

8 . The method of claim 1 , further comprising:
training a second artificial neural network to acquire a control rule corresponding to the sensed input/output parameter value and the acquired characteristic parameter value based on reinforcement learning for achieving a specific goal; and acquiring a control rule corresponding to the sensed input/output parameter value and the acquired characteristic parameter value using the trained second artificial neural network.

9 . The method of claim 1 , wherein:
the trained artificial neural network is a deep neural network; and the acquiring of the characteristic parameter value includes acquiring the characteristic parameter value using the input/output parameter value sensed for a predetermined time.

10 . The method of claim 1 , further comprising:
acquiring internal state information of the battery based on the characteristic parameter value; and displaying the internal state information.

11 . A device comprising:
a battery; a sensing unit configured to sense an input/output parameter value of the battery; and a controller configured to: acquire a characteristic parameter value of the battery corresponding to the sensed input/output parameter value using a trained artificial neural network; and control charging or discharging of the battery based on the acquired characteristic parameter value, wherein the trained artificial neural network is an artificial neural network trained to calculate the characteristic parameter value corresponding to the sensed input/output parameter value using training data.

12 . The device of claim 11 , wherein the training data includes an input/output parameter value of one or more batteries corresponding to the battery and a characteristic parameter value corresponding to the input/output parameter value of the one or more batteries.

13 . The device of claim 11 , wherein:
the controller is further configured to: acquire internal state information of the battery based on the characteristic parameter value; and control charging or discharging of the battery based on the internal state information; and the internal state information is at least one of deterioration of the battery, a degree of abnormality, a charge threshold, or a discharge threshold.

14 . The device of claim 11 , wherein the input/output parameter includes at least one of a voltage, current, or a temperature as a parameter measured outside the battery.

15 . The device of claim 11 , wherein the characteristic parameter includes at least one of electronic conductivity, solid diffusivity, a reaction rate constant of exchange current, tortuosity, porosity, electrolyte concentration, electrolyte conductivity, electrolyte diffusivity, a transference number, difference between capacity of an anode and capacity of a cathode due to degradation, or a degree of reduction in capacity of the anode/cathode as a parameter indicating a state of an internal material of the battery.

16 . The device of claim 11 , further comprising a storage unit configured to store a plurality of control rules,
wherein the controller is further configured to control charging or discharging of the battery according to a control rule corresponding to the acquired characteristic parameter value among the plurality of control rules.

17 . The device of claim 11 , further comprising:
a display; and an input unit, wherein the controller is further configured to: cause the display to display a plurality of control options, each corresponding to a respective one of a plurality of control rules, based on the acquired characteristic parameter value; and when an input of selecting a specific control option among the plurality of control options is received through the input unit, control charging or discharging of the battery according to a control rule corresponding to the specific control option.

18 . The device of claim 11 , wherein:
the controller is further configured to acquire a control rule corresponding to the sensed input/output parameter value and the acquired characteristic parameter value using a trained second artificial neural network; and the trained second artificial neural network is an artificial neural network trained to acquire a control rule corresponding to the sensed input/output parameter value and the acquired characteristic parameter value based on reinforcement learning for achieving a specific goal.

19 . The device of claim 11 , wherein:
the trained artificial neural network is a deep neural network; and the cont

Assignees

• Lg Electronics Inc

Inventors

• Lee Kamin
• Kim Suyeon
• Kim Minjung

Classifications

• H01M10/44

  Methods for charging or discharging (circuits for charging H02J7/00) · CPC title

• H01M10/425 Primary

  Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing (printed circuits H05K1/00) · CPC title

• H01M2010/4271

  Battery management systems including electronic circuits, e.g. control of current or voltage to keep battery in healthy state, cell balancing · CPC title

• H01M10/4257

  Smart batteries, e.g. electronic circuits inside the housing of the cells or batteries · CPC title

• G06N3/08 Primary

  Learning methods · CPC title