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

In a previous study, multiple regression techniques were applied to Flight Operations Quality Assurance-derived data to develop parsimonious model(s) for fuel consumption on the Boeing 757 airplane. The present study examined several data mining algorithms, including neural networks, on 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 methods reported correlation coefficients of .91 to .92, and General Linear Models and Multilayer Perceptron neural networks reported correlation coefficients of about .99. These data mining models show great promise for use in further examining large FOQA databases for operational and safety improvements. Alan Stolzer holds a Ph.D. in Technology Management—Quality Systems from Indiana State University. He holds FAA Airline Transport Pilot, Certified Flight Instructor, and Aircraft Mechanic certificates. He holds Quality Engineering, Manager, and Auditor certifications from ASQ, and a Project Manager certification from PMI. He is the Director of the Quality Engineering Systems in Transportation (QUEST) Research Center. Carl Halford is the Research Manager at SLU’s Center for Quality Engineering Systems in Transportation. Mr. Halford holds an Airline Transport Pilot certificate, with an assortment of type ratings, and has over 9000 hours of flight time in a variety of aircraft. Halford is a certified Manager of Quality/Organizational Excellence and Quality Auditor, and has been a Certified ISO 9001:2000 Lead Auditor.