Data Mining Methods Applied to Flight Operations Quality Assurance Data: A Comparison to Standard Statistical Methods

In a prior study, multiple regression techniques were applied to Flight Operation Quality Assurance-derived data to develop parsimonious models for fuel consumption on the Boeing 757 aircraft. This study applied several data mining algorithms, including neural networks, to the fuel consumption problem and compared them to the multiple regression results obtained earlier. Using regression methods, parsimonious models were obtained that explained approximately 85% of the variation in fuel flow. In general, data mining methods were more effective in predicting fuel consumption. Classification and Regression Tree models and Multilayer Perception neural networks reported correlation coefficients of about .99. These data mining models show great potential for use in further examining large FOQA databases for operational and safety improvements.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/49807676
• Authors:
  • Stolzer, Alan J
  • Halford, Carl D
• Publication Date: 2007

Language

• English

Media Info

• Media Type: Print
• Features: Figures; References; Tables;
• Pagination: pp 6-24
• Serial:
  • Journal of Air Transportation
  • Volume: 12
  • Issue Number: 1
  • Publisher: Aviation Institute
  • ISSN: 1544-6980

Subject/Index Terms

• TRT Terms: Aircraft; Aircraft operations; Algorithms; Data mining; Data quality; Fuel consumption; Multiple regression analysis; Neural networks
• Identifier Terms: Boeing 757 aircraft
• Subject Areas: Aviation; Energy; Vehicles and Equipment;

Filing Info

• Accession Number: 01055288
• Record Type: Publication
• Files: TRIS
• Created Date: Aug 10 2007 1:47PM