Intelligent preconditioning for high voltage electric vehicle batteries

1. A system for preconditioning a battery pack of a vehicle to support fast charging, comprising:

a processor;

a memory in communication with the processor, the memory storing a plurality of instructions executable by the processor to cause the system to:

detect a trigger that indicates the vehicle will be traveling or the battery pack of the vehicle has been reduced to a predetermined capacity;

collect a plurality of samples of real-time current location data of the vehicle;

convey the plurality of samples to a journey management machine learning model;

predict, using the journey management machine learning model, a plurality of destinations of the vehicle based on the plurality of samples;

determine, using a propensity to charge machine learning model, a propensity of a user to fast charge the vehicle based on the predicted plurality of destinations and one or more of:

the user's distance traveled in the vehicle since a last known charging event,

whether other users are present in the vehicle with the user, or

the user's historic fast charging behavior;

receive, via an analytics cluster, charging station availability data that indicates whether one or more charging stations are available; and

schedule preconditioning of the battery pack based on determining:

a charging station is available based on the charging station availability data for one of the plurality of predicted destinations, and

the predicted user's propensity to fast charge the vehicle at the one of the plurality of predicted destinations.

2. The system of claim 1 , further comprising instructions executable by the processor to cause the system to:

cancel a scheduled or currently-executing preconditioning of the battery pack in response to determining, based on the charging station availability data, that no available charging stations exist for the one of the plurality of predicted destinations.

3. The system of claim 1 , wherein

the preconditioning of the battery pack of the vehicle deliberately increases the temperature of the battery pack.

4. The system of claim 1 , further comprising instructions executable by the processor to cause the system to:

determine an estimated arrival time that the vehicle will arrive at the predicted destination; and

determine a preconditioning time prior to the estimated arrival time when the vehicle will begin preconditioning the battery pack.

5. The system of claim 1 , further comprising instructions executable by the processor to cause the system to:

determine a time window needed to increase a temperature of the battery pack to a target preconditioned temperature.

6. The system of claim 5 , further comprising instructions executable by the processor to cause the system to:

compare the time window with an estimated arrival time that the vehicle will arrive at the predicted destination; and

start to precondition the battery pack based on the comparison.

7. The system of claim 1 , wherein

the charging station availability data received via the analytics cluster is based on aggregate data published by a plurality of other vehicles that attempted to charge at the predicted destination.

8. The system of claim 1 , wherein

the instructions executable by the processor to cause the system to predict the destination of the vehicle are based on a determination that no destination has been set in a navigation function of the vehicle.

9. The system of claim 1 , further comprising instructions executable by the processor to cause the system to:

cancel a scheduled or currently-executing preconditioning of the battery pack based on a confidence score generated by the journey management machine learning model not meeting a threshold.

10. The system of claim 1 , wherein the determined propensity of the user to fast charge the vehicle is further based on at least one of:

the predicted location;

a total distance driven on a day;

a price of recharging at a charging station of the predicted location;

scheduled events and appointments stored within a personal computing device of the user;

a predicted driver of the vehicle;

a remaining state of charge of the battery pack; or

whether amenities are available near a charging station of the predicted location.

11. A method of preconditioning a battery pack of a vehicle to support fast charging, comprising:

detecting a trigger that indicates the vehicle will be traveling or the battery pack of the vehicle has been reduced to a predetermined capacity;

collecting a plurality of samples of real-time current location data of the vehicle;

conveying the plurality of samples to a journey management machine learning model;

predicting, using the journey management machine learning model, a plurality of destinations of the vehicle based on the plurality of samples;

determining, using a propensity to charge machine learning model, a propensity of a user to fast charge the vehicle based on the predicted plurality of destinations and one or more of:

the user's distance traveled in the vehicle since a last known charging event,

whether other users are present in the vehicle with the user, or

the user's historic fast charging behavior;

receiving, via an analytics cluster, charging station availability data that indicates whether one or more charging stations are available; and

scheduling preconditioning of the battery pack based on determining:

a charging station is available based on the charging station availability data for one of the plurality of predicted destinations, and

the predicted user's propensity to fast charge the vehicle at the one of the plurality of predicted destinations.

12. The method of claim 11 , further comprising:

canceling a scheduled or currently-executing preconditioning of the battery pack in response to determining, based on the charging station availability data, that no available charging stations exist for the one of the plurality of predicted destinations.

13. The method of claim 11 , wherein

the preconditioning of the battery pack of the vehicle deliberately increases the temperature of the battery pack.

14. The method of claim 11 , further comprising:

determining an estimated arrival time that the vehicle will arrive at the predicted destination; and

determining a preconditioning time prior to the estimated arrival time when the vehicle will begin preconditioning the battery pack.

15. The method of claim 11 , further comprising:

determining a time window needed to increase a temperature of the battery pack to a target preconditioned temperature.

16. The method of claim 15 , further comprising:

comparing the time window with an estimated arrival time that the vehicle will arrive at the predicted destination; and

starting to precondition the battery pack based on the comparison.

17. The method of claim 11 , wherein

the charging station availability data received via the analytics cluster is based on aggregate data published by a plurality of other vehicles that attempted to charge at the predicted destination.

18. The method of claim 11 , wherein

the predicting of the destination of the vehicle is based on determining that no destination has been set in a navigation function of the vehicle.

19. The method of claim 11 , further comprising:

canceling a scheduled or currently-executing preconditioning of the battery pack based on a confidence score generated by the journey management machine learning model not meeting a threshold.

20. The method of claim 11 , wherein the determined propensity of the user to fast charge the vehicle is further based on at least one of:

the predicted location;

a total distance driven on a day;

a price of recharging at a charging station of the predicted location;

scheduled events and appointments stored within a personal computing device of the user;

a predicted driver of the vehicle;

a remaining state of charge of the battery pack; or

whether amenities are available near a charging station of the predicted location.