Automization of structural design based on machine learning

• Project/Area Number: 18K05880
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 41030:Rural environmental engineering and planning-related
• Research Institution: Okayama University
• Principal Investigator: Shuku Takayuki 岡山大学, 環境生命科学学域, 准教授 (70625053)
• Project Period (FY): 2018-04-01 – 2023-03-31
• Project Status: Completed (Fiscal Year 2022)
• Budget Amount: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000); Fiscal Year 2022: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000); Fiscal Year 2021: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000); Fiscal Year 2020: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000); Fiscal Year 2019: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000); Fiscal Year 2018: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
• Keywords: 機械学習 / 設計自動化 / 既設構造物 / ガウス過程回帰 / ニューラルネットワーク / 地盤モデリング / 3次元 / エミュレータ / 判断の定量化 / スパースモデリング / 言語処理 / 統計的言語処理

Outline of Final Research Achievements

The purpose of this research project is to develop methodologies which can contribute to design full automation for infrastructures. Through this project, we have developed 1) the method that can create three-dimensional subsurface model with limited site investigation data and 2) a statistical model to perform design calculation without mechanical calculation or computation.

Academic Significance and Societal Importance of the Research Achievements

本研究は，これまで技術者により行われていた設計を機械により代替しようとする研究であり，業務の効率化だけでなく，技術者不足という業界の根本的な問題の解決にも貢献できる社会的意義のある研究である．また，データの少ない施設設計・施工の分野でも機械学習の方法論が適用可能であることを示した学術的意義もある研究である．

Research Products

• [Int'l Joint Research] National University of Singapore(シンガポール)
• [Int'l Joint Research] National Taiwan University(その他の国・地域)
• [Int'l Joint Research] National University of Singapore(シンガポール)
• [Int'l Joint Research] National Taiwan University(その他の国・地域)
• [Journal Article] Data-driven subsurface modelling using a Markov random field model (2023)
  • Author(s): Shuku Takayuki、Phoon Kok-Kwang
  • Journal Title: Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards Volume: 17 Issue: 1 Pages: 41-63
  • DOI: 10.1080/17499518.2023.2181973
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Comparison of data-driven site characterization methods through benchmarking: Methodological and application aspects (2023)
  • Author(s): Shuku, T. and Phoon, K.K
  • Journal Title: ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering Volume: 9(2) Issue: 2
  • DOI: 10.1061/ajrua6.rueng-977
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Geotechnical uncertainty, modeling, and decision making (2022)
  • Author(s): Phoon Kok-Kwang、Cao Zi-Jun、Ji Jian、Leung Yat Fai、Najjar Shadi、Shuku Takayuki、Tang Chong、Yin Zhen-Yu、Ikumasa Yoshida、Ching Jianye
  • Journal Title: Soils and Foundations Volume: 62 Issue: 5 Pages: 101189-101189
  • DOI: 10.1016/j.sandf.2022.101189
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Journal Article] A STUDY ON OPTIMAL DESIGN OF GEOTECHNICAL STRUCTURES USING QUANTUM ANNEALING (2022)
  • Author(s): SHUKU Takayuki、YAMAMOTO Shinya
  • Journal Title: Journal of Japan Society of Civil Engineers, Ser. C (Geosphere Engineering) Volume: 78 Issue: 2 Pages: 116-127
  • DOI: 10.2208/jscejge.78.2_116
  • ISSN: 2185-6516
  • Peer Reviewed / Open Access
• [Journal Article] Benchmark examples for data-driven site characterisation (2022)
  • Author(s): Phoon Kok-Kwang、Shuku Takayuki、Ching Jianye、Yoshida Ikumasa
  • Journal Title: Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards Volume: 1 Issue: 4 Pages: 1-23
  • DOI: 10.1080/17499518.2022.2025541
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Case Histories on 2D/3D Underground Stratification Using Sparse Machine Learning (2021)
  • Author(s): T. Shuku and J. Ching
  • Journal Title: International Journal of Geoengineering Case Histories Volume: 6 Pages: 35-47
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Journal Article] Three-dimensional subsurface modeling using Geotechnical Lasso (2021)
  • Author(s): Shuku Takayuki、Phoon Kok-Kwang
  • Journal Title: Computers and Geotechnics Volume: 133 Pages: 104068-104068
  • DOI: 10.1016/j.compgeo.2021.104068
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Challenges in data-driven site characterization (2021)
  • Author(s): Phoon Kok-Kwang、Ching Jianye、Shuku Takayuki
  • Journal Title: Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards Volume: 1 Issue: 1 Pages: 1-13
  • DOI: 10.1080/17499518.2021.1896005
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Bayesian Updating of Model Parameters by Iterative Particle Filter with Importance Sampling (2020)
  • Author(s): Yoshida Ikumasa、Shuku Takayuki
  • Journal Title: ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering Volume: 6 Issue: 2 Pages: 04020007-04020007
  • DOI: 10.1061/ajrua6.0001047
  • Peer Reviewed
• [Journal Article] Trend estimation and layer boundary detection in depth-dependent soil data using sparse Bayesian lasso (2020)
  • Author(s): Shuku Takayuki、Phoon Kok-Kwang、Yoshida Ikumasa
  • Journal Title: Computers and Geotechnics Volume: 128 Pages: 103845-103845
  • DOI: 10.1016/j.compgeo.2020.103845
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Surrogate models based on sparse estimation for geotechnical reliability analysis (2019)
  • Author(s): T. Shuku, M. Nishio, S. Nishimura, T. Shibata
  • Journal Title: Proc. of 16ARC Volume: 1
• [Journal Article] 機械学習に基づく室内試験用メタンハイドレートサンプルの自動選択 (2019)
  • Author(s): 珠玖隆行・津田大成・西村伸一・柴田俊文
  • Journal Title: 構造物の安全性および信頼性 Volume: 9 Pages: 523-524
• [Presentation] Automatic Selection of Methane Hydrate Soil Samples Based on Statistical Data Analysis (2020)
  • Author(s): Takayuki Shuku
  • Organizer: 7th Asian-Pacific Symposium on Structural Reliability and Its Application
  • Int'l Joint Research
• [Presentation] A Sparse Polynomial Surrogate Model for Geotechnical Reliability Design (2020)
  • Author(s): Takayuki Shuku
  • Organizer: 7th Asian-Pacific Symposium on Structural Reliability and Its Application
  • Int'l Joint Research
• [Remarks] Takayuki Shuku's website
  • URL: https://sites.google.com/view/takayukishukuswebsite/home
• [Remarks] 研究者個人website
  • URL: https://sites.google.com/view/takayukishukuswebsite/home