BATTERY ADAPTIVE LEARNING MANAGEMENT SYSTEM

• US 20130091083A1
• Filed: 10/10/2011
• Published: 04/11/2013
• Est. Priority Date: 10/10/2011
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Lapins, Ingrid, Frisch, Israel
• Granted Patent: US 8,719,195 B2
• Time in Patent Office: Days
• US Class Current: 706/14
• CPC Class Codes: G01R 31/367 Software therefor, e.g. for battery testing using modelling or look-up tables
• CPC Class Codes: G01R 31/392 Determining battery ageing or deterioration, e.g. state of health
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

A system and methods for battery health diagnostics are disclosed. At least one battery property of a battery is measured in real-time to provide measured data, and at least one measurement time at which the measured data is measured is tracked. A battery history model is provided by adaptively modeling the measured data and the measurement time, and a future state of the battery is estimated based on the battery history model.

Claims

1. A method for battery health diagnostics, comprising:

measuring at least one battery property of a battery in real-time to provide measured data;

tracking at least one measurement time at which the measured data is measured;

providing a battery history model by adaptively modeling the measured data and the at least one measurement time; and

estimating a future state of the battery based on the battery history model.

2. The method of claim 1, wherein the at least one battery property comprises at least one member selected from the group consisting of:

a capacity, a charge state, a voltage, a current, a cell resistance, an operational environment, and a temperature.

3. The method of claim 1, further comprising calculating a change in the at least one battery property between a previous state and a present state of the battery.

4. The method of claim 1, further comprising calculating a rate of change of the at least one battery property.

5. The method of claim 1, further comprising calculating a health state of the battery using the battery history model.

6. The method of claim 1, further comprising forecasting a prognostic for a battery reliability-and-maintainability using the battery history model.

7. The method of claim 6, further comprising reporting the prognostic of the battery.

8. The method of claim 7, further comprising reporting a reliability-and-maintainability assessment of the battery based on the prognostic.

9. The method of claim 8, wherein the reliability-and-maintainability assessment comprises at least one member selected from the group consisting of:

a health state, a battery capacity warning, a state-of-charge, a potential anomaly, a thermal run-away warning, a need for maintenance, a system warning, a shutdown warning, and a battery replacement need.

10. The method of claim 1, further comprising determining a battery energy capacity based on the at least one battery property.

11. The method of claim 1, further comprising determining a state of charge based on the at least one battery property.

12. The method of claim 1, further comprising indicating one of a shorted cell, an discharged cell, and an under discharged cell, if a temperature change is too rapid.

13. A battery adaptive learning management system comprising:

measurement logic operable to;

measure at least one battery property of a battery in real-time to provide measured data; and

track at least one measurement time at which the measured data is measured;

adaptive logic operable to provide a battery history model by adaptively modeling the measured data and the at least one measurement time; and

prediction logic operable to estimate a future state of the battery based on the battery history model.

14. The battery adaptive learning management system of claim 13, further comprising a non-volatile memory operable to store the measured data, the at least one measurement time, and the battery history model.

15. The battery adaptive learning management system of claim 13, wherein the battery adaptive learning management system is coupled to the battery.

16. A computer readable storage medium comprising computer-executable instructions for performing a method for battery health diagnostics, the method executed by computer-executable instructions comprising:

measuring at least one battery property of a battery in real-time to provide measured data;

tracking at least one measurement time at which the measured data is measured;

providing a battery history model by adaptively modeling the measured data and the at least one measurement time; and

estimating a future state of the battery based on the battery history model.

17. The computer readable storage medium of claim 16, wherein the at least one battery property comprises at least one member selected from the group consisting of:

a capacity, a charge state, a voltage, a current, a cell resistance, an operational environment, and a temperature.

18. The computer readable storage medium of claim 16, further comprising computer-executable instructions for calculating:

a change in the at least one battery property between a previous state and a present state of the battery;

a rate of change of the at least one battery property; and

a health state of the battery using the battery history model.

19. The computer readable storage medium of claim 16, further comprising computer-executable instructions for forecasting a prognostic for a battery reliability-and-maintainability using the battery history model.

20. The computer readable storage medium of claim 19, further comprising computer-executable instructions for reporting:

the prognostic of the battery; and

a reliability-and-maintainability assessment of the battery based on the prognostic.