公开(公告)号：US20250165683A1

公开(公告)日：2025-05-22

申请号：US18946547

申请日：2024-11-13

Applicant: Korea Electronics Technology Institute

Inventor： Jaekyu Lee ,  Sang Yub Lee ,  Inpyo Cho

IPC: G06F30/28 ,  G01R31/367

Abstract: Proposed is an artificial intelligence (AI) model-based analysis method for an optimal design of a secondary battery electrolyte. The AI model-based analysis method may include obtaining a tomography image of a calendared battery material, and inputting the tomography image to a pre-trained AI model. The method may also include outputting a viscosity and a transmittance of a battery electrolyte through the AI model. The AI model may include a first AI model configured to analyze porosity distribution and tortuosity information about the tomography image input thereto. The AI model may also include a second AI model configured to output a viscosity and a transmittance corresponding to the electrolyte, based on the porosity distribution and tortuosity information.

公开(公告)号：US20240273256A1

公开(公告)日：2024-08-15

申请号：US18440137

申请日：2024-02-13

Applicant: Korea Electronics Technology Institute

Inventor： Jaekyu Lee ,  Sang Yub Lee ,  Inpyo Cho

IPC: G06F30/20 ,  G06N5/04

CPC classification number: G06F30/20 ,  G06N5/04

Abstract: Proposed is a digital twin system for digitizing technologies related to development of perovskite solar cells, performing design, test, simulation, and verification on materials, physical/chemical properties, and structures in a virtual environment, and designing and manufacturing an optimal perovskite solar cell. The digital twin system may provide a digital twin system for, when developing perovskite solar cells, identifying the efficiency of solar cells without directly conducting experiments, and through simulation of various environments using various learning/inference models, optimally designing perovskite-based solar cells. Also proposed is a digital twin system that is designed with a machine learning operations (MLOps) structure to have a configuration in which initially designed learning/inference models are updated to resemble the real environment as the learning/inference models undergo experiments, enabling testing in a more realistic virtual environment.

公开(公告)号：US20240211296A1

公开(公告)日：2024-06-27

申请号：US18394242

申请日：2023-12-22

Applicant: Korea Electronics Technology Institute

Inventor： Jaekyu Lee ,  Sang Yub Lee ,  Inpyo Cho

IPC: G06F9/455 ,  G06F16/23 ,  G06F16/25

CPC classification number: G06F9/45558 ,  G06F16/2365 ,  G06F16/258 ,  G06F2009/45591

Abstract: Proposed is a container-based high availability big data framework system. The system may include an external server configured to provide structured data. The system may also include a data collection server constructed based on a docker container environment and configured to collect structured data by requesting the structured data from the external server at a predetermined time interval. The system may further include a monitoring server configured to execute a new docker image by generating a trigger when detecting the occurrence of an error while the structured data are collected.