• Title/Summary/Keyword: 학부

Search Result 18,049, Processing Time 0.042 seconds

Development of a Flooding Detection Learning Model Using CNN Technology (CNN 기술을 적용한 침수탐지 학습모델 개발)

  • Dong Jun Kim;YU Jin Choi;Kyung Min Park;Sang Jun Park;Jae-Moon Lee;Kitae Hwang;Inhwan Jung
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.23 no.6
    • /
    • pp.1-7
    • /
    • 2023

  • This paper developed a training model to classify normal roads and flooded roads using artificial intelligence technology. We expanded the diversity of learning data using various data augmentation techniques and implemented a model that shows good performance in various environments. Transfer learning was performed using the CNN-based Resnet152v2 model as a pre-learning model. During the model learning process, the performance of the final model was improved through various parameter tuning and optimization processes. Learning was implemented in Python using Google Colab NVIDIA Tesla T4 GPU, and the test results showed that flooding situations were detected with very high accuracy in the test dataset.

  • https://doi.org/10.7236/JIIBC.2023.23.6.1 인용 PDF HTML

Effect of Cu Content and Annealing Temperature on the Shape Memory Effect of NiTi-based Alloy (구리함량과 어닐링 온도가 NiTi 합금의 형상기억효과에 미치는 영향)

  • Hyeok-Jin Yang;Hyeong Ju Mun;Ye-Seul Cho;Jun-Hong Park;Hyun-Jun Youn;In-Chul Choi;Myung-Hoon Oh
    • Journal of the Korean Society for Heat Treatment
    • /
    • v.37 no.2
    • /
    • pp.79-85
    • /
    • 2024

  • The effects of annealing heat treatment and the addition of Cu element on the shape memory effect of the NiTi-based alloy were investigated by analyzing differential scanning calorimeter results and characterizing recovery rate through 3D scanning after Vickers hardness test. Through 3D scanning of impressions after Vickers hardness test, the strain recovery rates for specimens without annealing treatment and annealed specimens at 400, 450, and 500℃ were measured as 45.96%, 46.76%, 52.37%, and 43.57%, respectively. This is because as the annealing temperature increases, both B19' and NiTi2 phases, which can impede martensitic transformation, are incorporated within the NiTi matrix. Particularly, additional phase transformation from R-phase to B19' observed in specimens annealed at 400 and 450℃ significantly contributes to the improvement in strain recovery rates. Additionally, the results regarding the Cu element content indicate that when the total content of Ni and Cu is below 49.6 at.%, the precipitation of fine B19' and NiTi2 phases within the matrix can greatly influence the transformation enthalpy and temperature range, resulting in relatively lower strain recovery rates in NiTi alloys with a small amount of Cu element produced in this study.

  • https://doi.org/10.12656/jksht.2024.37.2.79 인용 PDF