Systems, methods, and storage media for adapting machine learning models for optimizing performance of a battery pack

Patent metadata

Field	Value
Publication number	US-11065978-B2
Application number	US-201916284515-A
Country	US
Kind code	B2
Filing date	Feb 25, 2019
Priority date	Feb 25, 2019
Publication date	Jul 20, 2021
Grant date	Jul 20, 2021

Abstract

Systems, methods, and storage media for optimizing performance of a vehicle battery pack are disclosed. A method includes receiving data pertaining to cells within a battery pack installed in each vehicle of a fleet of vehicles, the data received from at least one of each vehicle, providing the data to a machine learning server, and directing the machine learning server to generate a predictive model. The predictive model is based on machine learning of the data. The method further includes providing the predictive model to each vehicle, the predictive model providing instructions for adjusting configuration parameters for each of the cells in the battery pack such that the battery pack is optimized for a particular use, and directing each vehicle to optimize performance of the vehicle battery pack based on the predictive model.

First claim

What is claimed is:

1. A method of optimizing performance of a vehicle battery pack, the method comprising:
receiving data pertaining to cells within a battery pack installed in each vehicle of a fleet of vehicles, the data received from at least one of each vehicle in the fleet of vehicles;
providing the data to a machine learning server;
directing the machine learning server to generate a predictive model based on machine learning of the data;
providing the predictive model to each vehicle, the predictive model providing instructions for adjusting one or more configuration parameters for each of the cells in the battery pack such that the battery pack is optimized for a particular use; and
directing each vehicle to optimize performance of the vehicle battery pack based on the predictive model.

2. The method of claim 1 , further comprising storing the data and the predictive model in a battery database for subsequent access.

3. The method of claim 1 , further comprising receiving test data pertaining to cells within a battery pack tested by a battery testing device.

4. The method of claim 1 , further comprising:
providing the predictive model to a manufacturing facility that manufactures new battery packs; and
directing the manufacturing facility of optimize performance of the new battery packs based on the predictive model.

5. The method of claim 1 , wherein directing each vehicle in the fleet of vehicles to optimize performance of the vehicle battery pack comprises directing each vehicle to alter a state of charge of the vehicle battery pack.

6. The method of claim 1 , wherein directing each vehicle in the fleet of vehicles to optimize performance of the vehicle battery pack comprises directing each vehicle to cause a change in a state of health of the vehicle battery pack.

7. The method of claim 1 , wherein receiving the data comprises receiving supplemental data from one or more vehicle-specific sensors in each vehicle of the fleet of vehicles.

8. The method of claim 1 , wherein directing the machine learning server to generate the predictive model comprises directing the machine learning server to utilize a descriptor based algorithm that analyzes a capacity-voltage curve for individual cell cycles to generate the predictive model.

9. The method of claim 1 , wherein directing the machine learning server to generate the predictive model comprises directing the machine learning server to utilize a long short-term memory neural network to generate the predictive model.

10. The method of claim 1 , further comprising receiving, by the processing device, new data from each vehicle in the fleet of vehicles, the new data indicating an optimized performance of the vehicle battery pack based on the predictive model.

11. A system configured for optimizing performance of a vehicle battery pack, the system comprising:
a fleet of vehicles, each vehicle in the fleet of vehicles comprising a battery pack having a plurality of cells; and
one or more hardware processors communicatively coupled to each vehicle and configured by machine-readable instructions to:
receive data pertaining to cells within a battery pack installed in each vehicle, the data received from at least one of each vehicle;
provide the data to a machine learning server;
direct the machine learning server to generate a predictive model based on machine learning of the data;
provide the predictive model to each vehicle, the predictive model providing instructions for adjusting one or more configuration parameters for each of the cells in the battery pack such that the battery pack is optimized for a particular use; and
direct each vehicle to optimize performance of the vehicle battery pack based on the predictive model.

12. The system of claim 11 , further comprising a battery database communicatively coupled to the one or more hardware processors, wherein the one or more hardware processors are further configured by machine-readable instructions to store the data and the predictive model in the battery database for subsequent access.

13. The system of claim 11 , wherein the one or more hardware processors are further configured by machine-readable instructions to receive test data pertaining to cells within a battery pack tested by a battery testing device.

14. The system of claim 11 , wherein directing each vehicle in the fleet of vehicles to optimize performance of the vehicle battery pack comprises directing each vehicle to alter a state of charge of the vehicle battery pack.

15. The system of claim 11 , wherein directing each vehicle in the fleet of vehicles to optimize performance of the vehicle battery pack comprises directing each vehicle to cause a change in a state of health of the vehicle battery pack.

16. The system of claim 11 , wherein directing the machine learning server to generate the predictive model comprises directing the machine learning server to utilize a descriptor based algorithm that analyzes a capacity-voltage curve for individual cell cycles to generate the predictive model.

17. The system of claim 11 , wherein directing the machine learning server to generate the predictive model comprises directing the machine learning server to utilize a long short-term memory neural network to generate the predictive model.

18. The system of claim 11 , wherein the one or more hardware processors are further configured by machine-readable instructions to receive new data from each vehicle in the fleet of vehicles, the new data indicating an optimized performance of the vehicle battery pack based on the predictive model.

19. A non-transitory computer-readable storage medium having instructions embodied thereon, the instructions being executable by one or more processors to perform a method for optimizing performance of a vehicle battery pack, the method comprising:
receiving data pertaining to cells installed in each vehicle of a fleet of vehicles, the data received from at least one of each vehicle;
providing the data to a machine learning server;
directing the machine learning server to generate a predictive model based on machine learning of the data;
providing the predictive model to each vehicle, the predictive model providing instructions for adjusting one or more configuration parameters for each of the cells in the battery pack such that the battery pack is optimized for a particular use; and
directing each vehicle to optimize performance of the vehicle battery pack based on the predictive model.

20. The computer-readable storage medium of claim 19 , wherein directing the machine learning server to generate the predictive model comprises:
directing the machine learning server to utilize a descriptor based algorithm that analyzes a capacity-voltage curve for individual cell cycles to generate the predictive model; or
directing the machine learning server to utilize a long short-term memory neural network to generate the predictive model.

Assignees

• Toyota Res Inst Inc

Inventors

• Aykol Muratahan
• Herring Patrick K
• Anapolsky Abraham

Classifications

• G05B13/042

  in which a parameter or coefficient is automatically adjusted to optimise the performance · CPC title

• B60L2260/46

  by self learning · CPC title

• B60L58/18 Primary

  of two or more battery modules · CPC title

• B60L3/12

  Recording operating variables {; Monitoring of operating variables} · CPC title

• H01M10/4207

  for several batteries or cells simultaneously or sequentially · CPC title