• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2002 Fiscal Year Final Research Report Summary

Neural Network Based Quantitative Prediction of Corrosion Phenomena in Cars and Their Anti-Corrosion Design

Research Project

Project/Area Number 12450043
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Research Field Materials/Mechanics of materials
Research InstitutionThe University of Tokyo

Principal Investigator

YOSHIMURA Shinobu  The University of Tokyo, Graduate School of Frontier Sciences, Professor, 大学院・新領域創成科学研究科, 教授 (90201053)

Co-Investigator(Kenkyū-buntansha) NAGASAKI Shinya  The University of Tokyo, Graduate School of Frontier Sciences, Associate, 大学院・新領域創成科学研究科, 助教授 (20240723)
FURUTA Kazuo  The University of Tokyo, Graduate School of Frontier Sciences, Professor, 大学院・新領域創成科学研究科, 教授 (50199436)
YAGAWA Genki  The University of Tokyo, Graduate School of Engineering, Professor, 大学院・工学系研究科, 教授 (40011100)
KANTO Yasuhiro  Toyohashi University of Technology, School of Engineering, Associate Professor, 機械システム工学科, 助教授 (60177764)
HORIE Tomoyoshi  Kyushu institute of Technology, Faculty of Computer Science & Systems Engineering, Professor, 情報工学部, 教授 (40229224)
Project Period (FY) 2000 – 2002
KeywordsCorrosion / Cars / Life Time Prediction / Neural Network / Multi-variate Analysis / Car Parameters / Corrosion Parameters / Anti-Corrosion Design
Research Abstract

In this research, we have developed a method to quantitatively predict long-term corrosion occurring m cars, and additionally the method to perform anti-corrosion design. As the key technology, a multilayered neural network is employed to analyze a number of case studies of practical corrosion in cars. The process of the developed method is as follows.
(1)At first, a number of case studies of corrosion of cars are given to a multilayered neural network, which is trained. Performance of the trained network in accuracy of learning and training and its network topology are investigated in detail.
(2)Sensitivity studies are performed using the trained network. Here, various kinds of corrosion parameters are considered for the sensitivity study. Influential parameters for corrosion phenomena are then selected.
(3)The case studies are again learned using the compacted neural network with the selected parameters. Its performances are again investigated in detail.
(4)Using the trained compacted neural network, solutions for anticorrosion design of cars are effectively searched and visualized as a multidimensional design window.

  • Research Products

    (10 results)

All Other

All Publications (10 results)

  • [Publications] 吉村忍: "事例データとニューロ非線形情報処理ソフトn・DESIGNを活用した寿命予測法"日本機械学会・材料力学部門講演論文集. No.00-19. 683-684 (2000)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 八重樫英明, 坂内恒雄, 吉村忍: "ニューラルネットワークを用いた腐食寿命予測技術"自動車技術会講演会前刷集. 13-16 (2000)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 八重樫英明, 坂内恒雄, 吉村忍: "ニューラルネットワークを用いた腐食寿命予測技術"塗装工学. 36・9. 308-315 (2001)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 八重樫英明, 坂内恒雄, 吉村忍: "ニューラルネットワークを用いた腐食現象予測技術"第17回塗料・塗装研究会発表会講演予稿集. 26-30 (2001)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 八重樫英明, 坂内恒雄, 吉村忍: "ニューロ非線形多変量解析に基づく自動車防錆設計"材料と環境. 51・6. 262-268 (2002)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Shinobu Yeshimura: "Life management of artifacts using failure case studies and neuro-based nonlinear data analysis system n-DESIGN"Proc. 2000 JSME Materials & Mechanics Conference. No.00-19. 683-684 (2000)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Hideaki Yaegashi, Tsuneo Sckauchi, Shinobu Yoshimura: "Application of Neural Network as Predictive Tools for Corrosion in Automobile Parts"Proc. Conference of Society of Automotive Engineers Japan. 13-16 (2000)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Hideaki Yaegashi, Tsuneo Sakauchi, Shinobu Yoshmura: "Neural Network Based Prediction of Corrosion Phenomena in Automobile Parts"Journal of Coating Engineering. Vol.36, No.9. 308-315 (2001)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Hideaki Yaegashi, Tsuneo Sakauhi, Shinobu Yoshimura: "Prediction of Corrosion in Automobile Parts Using Neural Networks Coating"Proc. 17th Conference on Coating Materials and Technology. 26-30 (2001)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Hideoki Yaegashi, Tsuneo Sakauchi, Shinobu Yoshimura: "Anti-Corrosion Design of Automotive Vehicles Using Neural Network Based Nonlinear Multivariate Analysis"Zairyo-to-Kankyo. Vol.51,No.6. 262-268 (2002)

    • Description
      「研究成果報告書概要(欧文)」より

URL: 

Published: 2005-04-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi