Development of Vehicle Occupant Restraint System Design Method integrating Intelligent Information Processing Technologies
Project/Area Number |
26330274
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Soft computing
|
Research Institution | University of Yamanashi |
Principal Investigator |
HORII Hirosuke 山梨大学, 大学院総合研究部, 助教 (00447715)
|
Project Period (FY) |
2014-04-01 – 2018-03-31
|
Project Status |
Completed (Fiscal Year 2017)
|
Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2016: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2015: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2014: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
|
Keywords | 遺伝的アルゴリズム / 多目的最適化 / 機械学習 / ロバスト設計 / 衝突安全設計 / 進化的計算 / ロバスト最適化 / 進化的多目的最適化 / 自己組織化マップ |
Outline of Final Research Achievements |
This research constructed a system indicating valuable design information for design engineers at vehicle occupant restraint system design by integrating and applying various intelligent information processing techniques. Accurate response surface models of objective functions were constructed by machine learning method. Then, design candidates in large-scale and multi-modal design space were explored fast by evolutionary multi-objective optimization with the response surface model. Trade-off relationship, interaction and correlation among objective functions and design variables were visualized and valuable design information was obtained by analyzing non-dominated solutions. Furthermore, a system indicating optimality and stability under uncertainty of perturbation of design variables simultaneously by using multi-objective robust design optimization was constructed. The system provides an environment for design engineers who need to consider optimality and stability simultaneously.
|
Report
(5 results)
Research Products
(5 results)