Battery fault detection

Patent metadata

Field	Value
Publication number	US-11573271-B1
Application number	US-202117411945-A
Country	US
Kind code	B1
Filing date	Aug 25, 2021
Priority date	Aug 25, 2021
Publication date	Feb 7, 2023
Grant date	Feb 7, 2023

Abstract

A control system, responsive to receiving values of one or more parameters of a battery of a vehicle for a particular time in service, generates via a machine learning determination a level of confidence at which the values of the one or more parameters of the battery match values of one or more parameters of a set of batteries for a same time in service, and responsive to the level exceeding a predefined threshold, causes a mitigation action to be implemented.

First claim

What is claimed is:

1. A control system comprising:
one or more processors programmed to,
responsive to receiving values of one or more parameters of a battery of a vehicle for a particular time in service, generate via a machine learning determination a level of confidence at which the values of the one or more parameters of the battery match values of one or more parameters of a set of batteries for a same time in service, and
responsive to the level exceeding a predefined threshold, cause a mitigation action to be implemented, wherein a value of the predefined threshold depends on the mitigation action.

2. The control system of claim 1 , wherein the mitigation action is deactivation of stop-start functionality or a reduction in on-time for accessory loads while the vehicle is parked.

3. The control system of claim 1 , wherein the one or more processors are further programmed to, responsive to the level exceeding the predefined threshold, output an alert indicative of an aging battery.

4. The control system of claim 3 , wherein the one or more processors are further programmed to, responsive to the level not exceeding the predefined threshold, preclude output of the alert.

5. The control system of claim 1 , wherein the battery is a vehicle battery.

6. The battery management system of claim 1 , wherein the one or more processors are in a vehicle.

7. A battery management system comprising:
one or more processors programmed to
output an alert for a vehicle responsive to a machine learning determination that values of one or more parameters of a battery of the vehicle for a particular time in service match values of one or more parameters of a set of batteries for a same time in service with a level of confidence that exceeds a predefined threshold, and
preclude output of the alert responsive to a machine learning determination that the values of the one or more parameters of the battery match the values of the one or more parameters of the set with a level of confidence that does not exceed the predefined threshold.

8. The battery management system of claim 7 , wherein the one or more processors are further programmed to cause a mitigation action to be implemented responsive to the level exceeding the predefined threshold, and wherein a value of the predefined threshold depends on the mitigation action.

9. The battery management system of claim 7 , wherein the one or more processors are further programmed to generate the machine learning determination responsive to receiving the values of the one or more parameters of the battery.

10. The battery management system of claim 7 , wherein the machine learning determination is a supervised machine learning determination.

11. The battery management system of claim 7 , wherein the one or more parameters of the battery include capacity or internal resistance.

12. The battery management system of claim 7 , wherein the one or more parameters of the battery include weight.

13. The battery management system of claim 7 , wherein the one or more processors are in the vehicle.

14. A method comprising:
causing a mitigation action for a vehicle to be implemented responsive to a machine learning determination that values of one or more parameters of a battery of the vehicle for a particular time in service match values of one or more parameters of a set of batteries for a same time in service with a level of confidence that exceeds a predefined threshold.

15. The method of claim 14 , wherein a value of the predefined threshold depends on the mitigation action such that different mitigation actions have different corresponding predefined thresholds.

16. The method of claim 14 , wherein the mitigation action is deactivation of stop-start functionality or a reduction in on-time for accessory loads while the vehicle is parked.

17. The method of claim 14 further comprising outputting an alert for the vehicle responsive to the level exceeding the predefined threshold.

18. The method of claim 17 further comprising precluding output of the alert responsive to the level not exceeding the predefined threshold.

19. The method of claim 14 , wherein the machine learning determination is a supervised machine learning determination.

20. The method of claim 14 , wherein the values of the one or more parameters of the set are indicative of an aging of the batteries of the set.

Assignees

• Ford Global Tech Llc

Inventors

• Eifert Mark
• Kumar Pankaj
• Loiselle Matthew
• Rampiaray Timothy

Classifications

• G06N20/00

  Machine learning · CPC title

• B60L2260/44

  by parameter estimation · CPC title

• B60L2250/10

  by alarm · CPC title

• B60L2240/70

  Interactions with external data bases, e.g. traffic centres · CPC title

• B60L2250/16

  by display · CPC title