2022 Fiscal Year Final Research Report
3D Visualization of Internal Structure for Infrastructure Using Deep Learning and Electromagnetic Radar and Development of Contrast Repair Agent
Project/Area Number |
20H02401
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Review Section |
Basic Section 25020:Safety engineering-related
|
Research Institution | Sendai National College of Technology |
Principal Investigator |
Jun Sonoda 仙台高等専門学校, 総合工学科, 教授 (30290696)
|
Co-Investigator(Kenkyū-buntansha) |
木本 智幸 大分工業高等専門学校, 電気電子工学科, 教授 (30259973)
金澤 靖 豊橋技術科学大学, 工学(系)研究科(研究院), 准教授 (50214432)
山本 佳士 法政大学, デザイン工学部, 教授 (70532802)
|
Project Period (FY) |
2020-04-01 – 2023-03-31
|
Keywords | 地中レーダ / 深層学習 / 3次元可視化 / レーダ画像処理 / FDTDシミュレーション / インフラ点検 / 災害捜索 |
Outline of Final Research Achievements |
In recent years, the number of natural disasters such as earthquakes, torrential rains, and damage caused by aging social infrastructure such as roads and bridges has been increasing, requiring rapid and highly accurate detection of abnormalities in the ground and concrete. Electromagnetic radar, which uses radio waves in the several hundred to several GHz band, can detect the presence of objects inside. However, it has to be able to estimate or visualize the material, size, and shape to a high degree. In this study, we have developed an innovative electromagnetic radar that uses deep learning, an artificial intelligence technology, to reverse-estimate the internal structure from radar images and visualize abnormal locations, such as cavities and cracks, in three dimensions. We have also developed a contrast repair agent for electromagnetic wave radar that can provide a complete picture of anomalous areas during inspection and inspection, ensure repairs, and maintain repair histories.
|
Free Research Field |
安全工学
|
Academic Significance and Societal Importance of the Research Achievements |
本研究により、地中やコンクリート内の3次元マップを作成でき、内部の物体の材質や大きさとその位置を3次元的かつ高精度に把握可能となる。これよりインフラ内部の異常箇所の危険度定量化や寿命予測も可能になり、限られたコストの中で事故を未然に防ぐ効果的な対策工事が可能になる。
|