GENERATIVE DESIGN과 MESHGRAPHNET을 활용한 패널 적층 구조 최적화 요소 기술 개발
Development of an AI Model for Mobile Display Panel Stress Prediction Using MeshGraphNet (2022.5 - 2023.2) We achieved over 80% accuracy in predicting maximum panel stress compared to commercial simulation programs (e.g., ANSYS, ABAQUS). We reduced cost and time while improving speed and efficiency by applying the AI model compared to conventional dynamic analysis methods. We aim to optimize thin film thickness, materials, and PO Mobile panel stacking structure through Ball Impact simulations.
February, 2023
GENERATIVE DESIGN 기술을 활용한 기기배치 자동화 개발(알고리즘 개발)
Large-scale Layout Optimization for Chemical Plant (2021.5 - 2022.10) In the equipment layout design stage, we solved an optimization problem to minimize the plant area and the length of connecting pipes between equipment by utilizing only the initial equipment positions and constraint information between equipment, without detailed drawings. We developed an optimization algorithm for large-scale layout optimization. We enabled design exploration that satisfies all constraints even for a large number of items. We aimed to minimize both area and pipe length.
October, 2022
TV 설계자동화 : AI GENERATIVE DESIGN 기반 설계자동화
AI-based Generative Design for TV Stand Design (2021.3 - 2021.12) We developed a data generation process for deep learning training using parametric design techniques for TV stands. We built a deep learning model to predict the maximum stress value and stand weight. We proposed a generative design algorithm capable of real-time exploration of TV stand designs that satisfy both performance and design requirements.
December, 2021