Aid for Decision Making in Multi-Objective Design Optimization Based on Learning and Game Theories

• Project/Area Number: 24686015
• Research Category: Grant-in-Aid for Young Scientists (A)
• Allocation Type: Partial Multi-year Fund
• Research Field: Engineering fundamentals
• Research Institution: Tohoku University
• Principal Investigator: SHIMOYAMA Koji 東北大学, 流体科学研究所, 准教授 (80447185)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Project Status: Completed (Fiscal Year 2014)
• Budget Amount: ¥13,650,000 (Direct Cost: ¥10,500,000、Indirect Cost: ¥3,150,000); Fiscal Year 2014: ¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000); Fiscal Year 2013: ¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000); Fiscal Year 2012: ¥8,450,000 (Direct Cost: ¥6,500,000、Indirect Cost: ¥1,950,000)
• Keywords: 意思決定 / 多目的最適設計 / 学習

Outline of Final Research Achievements

This study has developed an approach for decision making, which can choose appropriate design candidates to be adopted by designers from many optimal solutions available in multi-objective optimization. This approach consists of new modules for distinguishing a trade-off structure based on leaning theory and for presenting neutral design candidates based on game theory together with the existing multi-objective design optimization module. This approach has been applied to test problems and real-world design problem, which demonstrates superior performance and effectiveness compared to conventional approaches.

Research Products

• [Journal Article] A Study on Many-Objective Optimization Using the Kriging-Surrogate-Based Evolutionary Algorithm Maximizing Expected Hypervolume Improvement (2015)
  • Author(s): Chang Luo, Koji Shimoyama, and Shigeru Obayashi
  • Journal Title: Mathematical Problems in Engineering Volume: 2015
  • Peer Reviewed / Open Access
• [Journal Article] Updating Kriging Surrogate Models Based on the Hypervolume Indicator in Multi-Objective Optimization (2013)
  • Author(s): Koji Shimoyama, Koma Sato, Shinkyu Jeong, and Shigeru Obayashi
  • Journal Title: Journal of Mechanical Design, Transactions of the ASME Volume: 135 Issue: 9
  • DOI: 10.1115/1.4024849
  • Peer Reviewed
• [Journal Article] Comparison of Sample Addition Criteria for Kriging Response Surface Models in Multi-Objective Optimization (2012)
  • Author(s): 下山幸治, 鄭信圭, 大林茂
  • Journal Title: Transaction of the Japanese Society for Evolutionary Computation Volume: 3 Issue: 3 Pages: 173-184
  • DOI: 10.11394/tjpnsec.3.173
  • NAID: 130004566778
  • ISSN: 2185-7385
  • Peer Reviewed
• [Presentation] 多数制約進化計算法を用いたスマートホームシステム最適制御の基礎研究 (2015)
  • Author(s): 嘉藤太河，下山幸治，秋山直寛，江原由希子，山田想，國領喬，大林茂
  • Organizer: 日本機械学会東北支部第50期総会・講演会
  • Place of Presentation: 仙台
  • Year and Date: 2015-03-13
• [Presentation] 多数制約条件下での制約違反量を考慮した実行可能解・実行不可能解の並列評価による進化計算法 (2014)
  • Author(s): 嘉藤太河，下山幸治，大林茂，ロッケンバッハ怜
  • Organizer: 進化計算シンポジウム2014
  • Place of Presentation: 廿日市
  • Year and Date: 2014-12-20 – 2014-12-21
• [Presentation] 高効率EHVI計算を用いたKrigingモデルベース多数目的最適化 (2014)
  • Author(s): Luo Chang，下山幸治，大林茂
  • Organizer: 日本機械学会第27回計算力学講演会
  • Place of Presentation: 盛岡
  • Year and Date: 2014-11-22 – 2014-11-24
• [Presentation] Multi-Objective Design Exploration Toward Intelligent Energy Management (2014)
  • Author(s): Koji Shimoyama
  • Organizer: 11th International Conference on Flow Dynamics
  • Place of Presentation: Sendai, Japan
  • Year and Date: 2014-10-08 – 2014-10-10
  • Invited
• [Presentation] Kriging-Based Dynamic Adaptive Sampling for Effective Uncertainty Quantification (2014)
  • Author(s): Koji Shimoyama and Soshi Kawai
  • Organizer: 11th World Congress on Computational Mechanics, 5th European Conference on Computational Mechanics, and 6th European Conference on Computational Fluid Dynamics
  • Place of Presentation: Barcelona, Spain
  • Year and Date: 2014-07-20 – 2014-07-25
• [Presentation] Uncertainty Quantification in Fluid Dynamics: Kriging Model Based Approach (2014)
  • Author(s): Soshi Kawai and Koji Shimoyama
  • Organizer: 11th World Congress on Computational Mechanics, 5th European Conference on Computational Mechanics, and 6th European Conference on Computational Fluid Dynamics
  • Place of Presentation: Barcelona, Spain
  • Year and Date: 2014-07-20 – 2014-07-25
• [Presentation] Kriging Model Based Many-Objective Optimization with Efficient Calculation of Expected Hypervolume Improvement (2014)
  • Author(s): Chang Luo, Koji Shimoyama and Shigeru Obayashi
  • Organizer: 2014 IEEE Congress on Evolutionary Computation
  • Place of Presentation: Beijing, China
  • Year and Date: 2014-07-06 – 2014-07-11
• [Presentation] Kriging-Model-Based Uncertainty Quantification in Computational Fluid Dynamics (2014)
  • Author(s): Soshi Kawai and Koji Shimoyama
  • Organizer: 32nd AIAA Applied Aerodynamics Conference
  • Place of Presentation: Atlanta, GA, USA
  • Year and Date: 2014-06-16 – 2014-06-20
• [Presentation] Comparison of the Criteria for Updating Kriging Response Surface Models in Multi-Obective Optimization (2012)
  • Author(s): Koji Shimoyama, Koma Sato, Shinkyu Jeong, and Shigeru Obayashi
  • Organizer: 2012 IEEE Congress on Evolutionary Computation
  • Place of Presentation: Brisbane, Australia
• [Presentation] Kriging-Surrogate-Based Optimization Considering Expected Hypervolume Improvement in Non-Constrained Many-Objective Test Problems
  • Author(s): Koji Shimoyama, Shinkyu Jeong, and Shigeru Obayashi
  • Organizer: 2013 IEEE Congress on Evolutionary Computation
  • Place of Presentation: Cancun, Mexico