公开(公告)号：US20240316493A1

公开(公告)日：2024-09-26

申请号：US18611133

申请日：2024-03-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Yujin KO ,  Hyunho YUN ,  Jungsoo KANG ,  Sungmin JANG ,  Hyunmin JEONG

IPC: B01D53/26 ,  B01D53/04

CPC classification number: B01D53/261 ,  B01D53/0454 ,  B01D2257/80 ,  B01D2259/40088

Abstract: An air dryer includes a first adsorption tower configured to perform any one of a compressed air dehumidification process and a regeneration process of a first adsorbent provided therein, a second adsorption tower configured to perform a regeneration process of a second adsorbent or alternately perform a compressed air dehumidification process, in response to an operation of the first adsorption tower, and a controller configured to (i) control the operation of the first adsorption tower for the first adsorption tower to perform either the compressed air dehumidification process or the regeneration process of the first adsorbent and (ii) control the operation of the second adsorption tower for the second adsorption tower to perform either the compressed air dehumidification process or the regeneration process of the second adsorbent.

公开(公告)号：US20240168674A1

公开(公告)日：2024-05-23

申请号：US18127922

申请日：2023-03-29

Applicant: Samsung Electronics Co., Ltd.

Inventor： Kibeen JUNG ,  Han Kyoo LEE ,  Byeonghui KIM ,  Hyunkyo OH ,  Sungmin JANG

IPC: G06F3/06

CPC classification number: G06F3/0653 ,  G06F3/061 ,  G06F3/0656 ,  G06F3/0679

Abstract: A throttling method for a storage device is provided. The throttling method includes: receiving a write command from a host; identifying, using a first machine learning model, a throttling delay time; transmitting a completion message to the host according to the throttling delay time; collecting weights of the first machine learning model and performance information of the storage device corresponding to the weights; learning the weights and the performance information to generate an objective function indicating a relationship between the weights and the performance information using a second machine learning model of a weight learning device; selecting a weight corresponding to a maximum performance using the objective function; and updating the first machine learning model with the weight.