Study on Sustainable Knowledge Interaction between Spacecraft Operators and Data-driven Anomaly Detection System
Project/Area Number |
26289320
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Partial Multi-year Fund |
Section | 一般 |
Research Field |
Aerospace engineering
|
Research Institution | The University of Tokyo |
Principal Investigator |
YAIRI TAKEHISA 東京大学, 大学院工学系研究科(工学部), 准教授 (90313189)
|
Research Collaborator |
KHAN Samir
TAKEISHI Naoya
AKIMOTO Kosuke
SAKAGAMI Ryo
SAKURADA Mayu
KUWABARA Junichi
|
Project Period (FY) |
2014-04-01 – 2018-03-31
|
Project Status |
Completed (Fiscal Year 2017)
|
Budget Amount *help |
¥11,570,000 (Direct Cost: ¥8,900,000、Indirect Cost: ¥2,670,000)
Fiscal Year 2017: ¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
Fiscal Year 2016: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2015: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2014: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
|
Keywords | 宇宙工学 / 機械学習 / 異常検知 / 健全性監視 / 運用支援 / 航空宇宙システム / 人工知能 / システム健全性監視 / 航空宇宙工学 / 人工衛星 / 予測保全 |
Outline of Final Research Achievements |
The purpose of this study is to establish a new methodology of sustainable knowledge interaction between operators of space systems such as artificial satellites and machine learning-based or data-driven health status monitoring systems. We developed a data-driven health monitoring method based on dimensionality reduction and clustering, which takes into account that artificial satellite systems consist of global discrete mode transition and local continuous state transition. We showed this method is able to provide operators with useful information, to acquire expert knowledge from the operators and to encourage continuing mutual interaction of them.
|
Report
(5 results)
Research Products
(27 results)