Development of Intelligent learning control by using self-organizing map
| Project/Area Number |
26630075
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Dynamics/Control
|
|---|
| Research Institution | Hokkaido University |
|---|
Principal Investigator |
Honda Shinya 北海道大学, 工学(系)研究科(研究院), 准教授 (90548190)
|
|---|
| Research Collaborator |
KIDA Naohiro
SUGAHARA Kyoichi
|
|---|
| Project Period (FY) |
2014-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2015: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2014: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
|---|
| Keywords | 自己組織化マップ / 振動制御 / 適応制御 / 複合材料 / 機械力学・制御 |
|---|
| Outline of Final Research Achievements |
The present study proposes a new learning vibration control method by using the self-organizing map (SOM) which is a kind of neural networks. The proposed method is applicable to unknown control objects and adaptive to variation of structure due to troubles. The statistical model of the structure in terms of input and output signals is built by learning effect of SOM, and simultaneously appropriate control input to a certain state of structure is learned, resulting in vibration suppression. From numerical and experimental results, it was revealed that the present method is effective to the unknown control objects.
|
Report
(3 results)
Research Products
(5 results)
