Systems, methods, and storage media for arranging a plurality of cells in a vehicle battery pack

Patent metadata

Field	Value
Publication number	US-2020269709-A1
Application number	US-201916284483-A
Country	US
Kind code	A1
Filing date	Feb 25, 2019
Priority date	Feb 25, 2019
Publication date	Aug 27, 2020
Grant date	—

Abstract

Systems, methods, and storage media for arranging a plurality of cells in a vehicle battery pack are disclosed. A method includes receiving, by a processing device, 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 and one or more battery testing devices, providing, by the processing device, the data to a machine learning server, directing, by the processing device, the machine learning server to generate a predictive model, the predictive model based on machine learning of the data, estimating, by the processing device, one or more electrical characteristics of each cell to be included in the vehicle battery pack based on the predictive model, and directing, by the processing device, an arrangement of the cells within the battery pack based on the electrical characteristics.

First claim

What is claimed is:

1 . A method of arranging a plurality of cells in a vehicle battery pack, the method comprising:
receiving, by a processing device, 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 and one or more battery testing devices; providing, by the processing device, the data to a machine learning server; directing, by the processing device, the machine learning server to generate a predictive model, the predictive model based on machine learning of the data; estimating, by the processing device, one or more electrical characteristics of each of the plurality of cells to be included in the vehicle battery pack based on the predictive model; and directing, by the processing device, an arrangement of the plurality of cells within the battery pack based on the one or more electrical characteristics.

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

3 . The method of claim 1 , further comprising categorizing each of the plurality of cells.

4 . The method of claim 3 , wherein categorizing each of the plurality of cells comprises binning each of the cells based on one or more of a cell size, a cell impedance, a cell quality, and a cell performance.

5 . The method of claim 1 , wherein directing the arrangement of the plurality of cells comprises transmitting arrangement instructions to a manufacturing computer.

6 . The method of claim 1 , wherein the arrangement of the plurality of cells is an optimal arrangement that maximizes a life of the battery pack.

7 . The method of claim 1 , wherein the arrangement of the plurality of cells is an optimal arrangement that maximizes a performance of the battery pack.

8 . 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.

9 . A system configured for arranging a plurality of cells in 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; one or more battery testing devices; and one or more hardware processors communicatively coupled to each vehicle in the fleet of vehicles and to the one or more battery testing devices, the one or more hardware processors configured by machine-readable instructions to:
receive data pertaining to the plurality of cells in each vehicle of the fleet of vehicles, the data received from at least one of each vehicle in the fleet of vehicles and the one or more battery testing devices;
provide the data to a machine learning server;
direct the machine learning server to generate a predictive model, the predictive model based on machine learning of the data;
estimate one or more electrical characteristics of each of the plurality of cells to be included in the vehicle battery pack based on the predictive model; and
direct an arrangement of the plurality of cells within the battery pack based on the one or more electrical characteristics.

10 . The system of claim 9 , 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 by the machine learning server.

11 . The system of claim 9 , wherein the one or more hardware processors are further configured by machine-readable instructions to categorize each of the plurality of cells.

12 . The system of claim 11 , wherein categorizing each of the plurality of cells comprises binning each of the plurality of cells based on one or more of a cell size, a cell impedance, a cell quality, and a cell performance.

13 . The system of claim 9 , further comprising a manufacturing computer communicatively coupled to the one or more hardware processors, wherein directing the arrangement of the plurality of cells comprises transmitting arrangement instructions to the manufacturing computer.

14 . The system of claim 9 , wherein the arrangement of the plurality of cells is an optimal arrangement that maximizes a life of the battery pack or maximizes a performance of the battery pack.

15 . The system of claim 9 , wherein the arrangement of the plurality of cells causes one or more of the following: maximizes a charge capacity of the battery pack, maximizes a discharge capacity of the battery pack, minimizes a charge time of the battery pack, and minimizes a likelihood of a failure of the battery pack.

16 . The system of claim 9 , wherein the one or more battery testing devices comprise one or more high-throughput (HT) cyclers.

17 . 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 arranging a plurality of cells in 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 in the fleet of vehicles and one or more battery testing devices; providing the data to a machine learning server; directing the machine learning server to generate a predictive model, the predictive model based on machine learning of the data; estimating one or more electrical characteristics of each of the plurality of cells to be included in the vehicle battery pack based on the predictive model; and directing an arrangement of the plurality of cells within the battery pack based on the one or more electrical characteristics.

18 . The computer-readable storage medium of claim 17 , wherein the method further comprises storing the data and the predictive model in a battery database for subsequent access by the machine learning server.

19 . The computer-readable storage medium of claim 17 , wherein the method further comprises categorizing each of the plurality of cells.

20 . The computer-readable storage medium of claim 17 , wherein directing the arrangement of the plurality of cells comprises transmitting arrangement instructions to a manufacturing computer.

Assignees

• Toyota Res Inst Inc

Inventors

• Herring Patrick K
• Aykol Muratahan
• Anapolsky Abraham

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/0895

  Weakly supervised learning, e.g. semi-supervised or self-supervised learning · CPC title

• G06N3/092

  Reinforcement learning · CPC title

• G06N3/094

  Adversarial learning · CPC title