Mapping Indication Severity Using Bayesian Machine Learning from Indirect Inspection Data into Corrosion Severity for Decision-making in Pipeline Maintenance

The project will develop a fast, reliable and accurate tool that extracts corrosion severity and real corrosion rates by adapting current Direct Assessment practices. This approach will supplement survey technologies with a slightly broader database of environmental data to prioritize threat severity, and excavation schedule that can minimize their number and related integrity risk.

• Supplemental Notes:
  • USDOT Research Hub DisplayID 157806

Language

• English

Project

• Status: Active
• Funding: $310000
• Sponsor Organizations:

  Pipeline and Hazardous Materials Safety Administration

  ,    
• Managing Organizations:

  Texas A&M University

  College Staion, TX  United States  77843
• Project Managers:

  Smith, Robert

• Start Date: 20190901
• Expected Completion Date: 20211231
• Actual Completion Date: 0
• USDOT Program: Pipeline Safety
• Subprogram: Threat Prevention

Subject/Index Terms

• TRT Terms: Corrosion; Data mining; Inspection; Machine learning; Maintenance; Mapping; Pipelines
• Subject Areas: Data and Information Technology; Maintenance and Preservation; Pipelines;

Filing Info

• Accession Number: 01869522
• Record Type: Research project
• Source Agency: Department of Transportation
• Files: RIP, USDOT
• Created Date: Jan 3 2023 1:53PM