| Project/Area Number |
26330074
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Computer system
|
|---|
| Research Institution | Aichi Institute of Technology |
|---|
Principal Investigator |
CHUJO Naoya 愛知工業大学, 情報科学部, 教授 (30394498)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
水野 忠則 愛知工業大学, 情報科学部, 教授 (80252162)
|
|---|
| Research Collaborator |
ITO Nobuyuki 三菱電機エンジニアリング, 駆動制御部, 部長
KOBAYASHI Yukihiko 三菱電機エンジニアリング, 制御技術部, 主査
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2016: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2015: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
Fiscal Year 2014: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
|
|---|
| Keywords | リアルタイム / システム / 制御 / ソフトウェア / ログ / 障害診断 / 機械学習 / エージェント |
|---|
| Outline of Final Research Achievements |
In this research, agent system that performs adaptive log data collection for real-time control system were examined and demonstrated. Adaptive Cruise Control (ACC) was used as the real-time control system.
We made normal data models by measurements of ACC-equipped vehicles and detected abnormalities by detecting outliers. In the experiment, the detection system by machine learning could identify the outliers with high correct answer rate. The automatic generation of normal models for various signals remains as a future problem. In addition, real-time log collection by adaptive agents was examined. The log collection overhead is predictable and found to be small enough compared to the control task.
|
