US 11,955,612 B2
Neural network, power storage system, vehicle, and electronic device
Kazutaka Kuriki, Kanagawa (JP); Ryota Tajima, Kanagawa (JP); Kouhei Toyotaka, Kanagawa (JP); Hideaki Shishido, Kanagawa (JP); and Toshiyuki Isa, Kanagawa (JP)
Assigned to Semiconductor Energy Laboratory Co., Ltd., Kanagawa-ken (JP)
Filed by SEMICONDUCTOR ENERGY LABORATORY CO., LTD., Atsugi (JP)
Filed on Jan. 6, 2023, as Appl. No. 18/093,833.
Application 18/093,833 is a continuation of application No. 16/603,487, granted, now 11,594,770, previously published as PCT/IB2018/052744, filed on Apr. 20, 2018.
Claims priority of application No. 2017-092024 (JP), filed on May 3, 2017; application No. 2017-124077 (JP), filed on Jun. 26, 2017; and application No. 2017-151306 (JP), filed on Aug. 4, 2017.
Prior Publication US 2023/0155199 A1, May 18, 2023
Int. Cl. H01M 10/48 (2006.01); G06N 3/04 (2023.01); G06N 3/065 (2023.01); H01M 10/44 (2006.01); H02J 7/00 (2006.01)
CPC H01M 10/482 (2013.01) [G06N 3/04 (2013.01); G06N 3/065 (2023.01); H01M 10/441 (2013.01); H01M 10/486 (2013.01); H02J 7/0013 (2013.01); H02J 7/0047 (2013.01); H02J 7/007 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A power storage system comprising:
a neural network; and
a storage battery,
wherein the neural network includes an input layer, an output layer, and one or more hidden layers between the input layer and the output layer,
wherein the predetermined hidden layer is connected to the previous hidden layer or the previous input layer by a first weight coefficient,
wherein the predetermined hidden layer is connected to the next hidden layer or the next output layer by a second weight coefficient,
wherein a plurality of graphs generated by measurement data of the storage battery are converted into a plurality of images,
wherein data of the plurality of images are input to the input layer, and
wherein an operational condition of the storage battery is changed in accordance with a signal output from the output layer.