Pattern based charge scheduling

• US 9,731,617 B2
• Filed: 12/04/2014
• Issued: 08/15/2017
• Est. Priority Date: 12/04/2014
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Michelini, John Ottavio, Tseng, Fling, Yang, Hsin-hsiang, Prakah-Asante, Kwaku O., Filev, Dimitar Petrov
• Primary Examiner(s): Whitmore, Stacy
• Application Number:
  US14/560,323
• Publication Number:
  US 20160159240A1
• Time in Patent Office: 985 Days
• Field of Search: 320104
• CPC Class Codes: B60L 2250/20 by driver identification
• CPC Class Codes: B60L 53/14 Conductive energy transfer
• CPC Class Codes: B60L 53/66 Data transfer between charging stations and vehicles
• CPC Class Codes: B60L 58/10 for monitoring or controlling batteries
• CPC Class Codes: B60L 58/12 responding to state of charge [SoC]
• CPC Class Codes: H02J 7/1446 in response to parameters of a vehicle
• CPC Class Codes: Y02T 10/70 Energy storage systems for electromobility, e.g. batteries
• CPC Class Codes: Y02T 10/7072 Electromobility specific charging systems or methods for batteries, ultracapacitors, supercapacitors or double-layer capacitors
• CPC Class Codes: Y02T 10/92 Energy efficient charging or discharging systems for batteries, ultracapacitors, supercapacitors or double-layer capacitors specially adapted for vehicles
• CPC Class Codes: Y02T 90/12 Electric charging stations
• CPC Class Codes: Y02T 90/14 Plug-in electric vehicles
• CPC Class Codes: Y02T 90/16 Information or communication technologies improving the operation of electric vehicles

Abstract

A method according to an exemplary aspect of the present disclosure includes, among other things, scheduling charging of an energy storage device of an electrified vehicle based on a learned key-on pattern. The learned key-on pattern is derived by recursively updating the probability that a subsequent key-on event is likely to occur at any given time and day.

Claims

1. A method, comprising:

scheduling charging of an energy storage device of an electrified vehicle based on a learned key-on pattern, the learned key-on pattern derived by recursively updating the probability that a subsequent key-on event is likely to occur at any given time and day each time a key-on signal associated with the electrified vehicle is received,

charging the energy storage device based on a charging schedule derived from the learned key-on pattern.

2. The method as recited in claim 1, wherein the scheduling step includes scheduling a charging start time and a charging end time for charging the energy storage device.

3. The method as recited in claim 1, wherein the scheduling step includes:

estimating an energy requirement for an upcoming trip; and

charging the energy storage device to a level sufficient to meet the energy requirement prior to a predicted upcoming key-on event.

4. The method as recited in claim 3, wherein the energy requirement is learned based on a learned driving pattern of the electrified vehicle.

5. The method as recited in claim 1, wherein the learned key-on pattern is learned at a predefined learning rate.

6. The method as recited in claim 5, wherein the predefined learning rate is at least 100 key-on events.

7. The method as recited in claim 1, wherein the updating step includes applying a low pass filter to each of a plurality of key-on signals.

8. The method as recited in claim 1, wherein, upon receiving each key-on signal, the updating step includes:

increasing the probability that the subsequent key-on event will occur on the same day and the same time as the key-on signal; and

decreasing the probability that the subsequent key-on event will occur at a different day and a different time from the key-on signal.

9. The method as recited in claim 1, wherein the updating step includes:

partitioning each day of a week into a plurality of predefined segments; and

each time another key-on event occurs, updating the probability that the subsequent key-on event is likely to occur during the same predefined segment.

10. The method as recited in claim 9, wherein the updating step includes:

increasing the probability that the subsequent key-on event will occur on the same day and the same time as each key-on signal occurs; and

decreasing the probability that the subsequent key-on event will occur at a different day and a different time than each key-on signal occurred.

11. The method as recited in claim 1, comprising performing a learning process for learning the key-on pattern, wherein the learning process includes:

identifying a driver operator associated with the electrified vehicle.

12. The method as recited in claim 11, wherein the learning process includes:

confirming a first key-on event; and

communicating a first key-on signal indicative of the first key-on event.

13. The method as recited in claim 12, wherein the learning process includes:

accessing key-on probability information associated with the driver operator.

14. The method as recited in claim 13, wherein the learning process includes:

modifying the key-on probability information by either increasing or decreasing the probability that the subsequent key-on event will occur at the same time and same day as the first key-on event.

15. The method as recited in claim 1, wherein recursively updating the probability that the subsequent key-on event is likely to occur at any given time and day includes adjusting a key-on probability plot to either increase or decrease the probability that the subsequent key-on event will occur at the same time and same day as a confirmed key-on event.

16. A vehicle system, comprising:

an electrical storage device; and

a control module configured to charge of said electrical storage device based on a learned key-on pattern that is derived by recursively updating the probability that a subsequent key-on event is likely to occur at any given time and day each time a key-on signal is received by said control module.

17. The vehicle system as recited in claim 16, comprising a power electronics module configured to control charging of said electrical storage device.

18. The vehicle system as recited in claim 17, comprising a charger configured to supply electrical power to said power electronics module.

19. The vehicle system as recited in claim 16, wherein said control module includes a processing unit and non-transitory memory, and a key-on probability plot is stored in said non-transitory memory.

20. The vehicle system as recited in claim 16, wherein said control module is configured to estimate an energy requirement for an upcoming trip.

21. The vehicle system as recited in claim 16, wherein said control module adjusts a key-on probability plot when recursively updating the probability.

22. A method, comprising:

charging an energy storage device of an electrified vehicle based on a learned key-on pattern that is derived by recursively updating the probability that a subsequent key-on event is likely to occur at any given time each time a key-on signal is received, wherein the updating includes increasing or decreasing the probability that the subsequent key-on event will occur at the same time as previous key-on events.