Evaluation of selection method for appropriate inspection points using diversity and consistency

Yosuke Takahashi*, Hisayoshi Matsuyama, Shigeyuki Tateno

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Corrosions of pipes have been disregarded as a management object in chemical or petrochemical plants because an outside corrosion phenomenon has a slow deterioration speed. Therefore, there is danger of a large number of pipes that have been used for 30 to 40 years without maintenance. It may cause penetration through pipes due to outside corrosion, in the worst case, a fatal accident will occur. In such a background, proper maintenance work should be carried out in advance. In this research, the case database is made from corrosion rates with environmental factors of design information and installation environment of pipes. A selection support system based on the case databases searches for corrosion points where corrosion is likely to progress. The case databases are successfully evaluated by the degree of diversity and the degree of consistency.

Original languageEnglish
Title of host publication2008 International Conference on Control, Automation and Systems, ICCAS 2008
Pages1061-1065
Number of pages5
DOIs
Publication statusPublished - 2008 Dec 1
Event2008 International Conference on Control, Automation and Systems, ICCAS 2008 - Seoul, Korea, Republic of
Duration: 2008 Oct 142008 Oct 17

Publication series

Name2008 International Conference on Control, Automation and Systems, ICCAS 2008

Conference

Conference2008 International Conference on Control, Automation and Systems, ICCAS 2008
Country/TerritoryKorea, Republic of
CitySeoul
Period08/10/1408/10/17

Keywords

  • Case database
  • Consistency
  • Decision tree
  • Diversity
  • Neural network
  • Surface corrosion

ASJC Scopus subject areas

  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Evaluation of selection method for appropriate inspection points using diversity and consistency'. Together they form a unique fingerprint.

Cite this