Support Vector Machine and ROC Curves for Modeling of Aircraft Fuel Consumption
Journal of Management Analytics
Taylor & Francis
To estimate the fuel consumption of a civil aircraft, we propose to use the receiver operating characteristic (ROC) curve to optimize a support vector machine (SVM) model. The new method and procedure has been developed to build, train, validate, and apply an SVM model. A conceptual support vector network is proposed to model fuel consumption, and the flight data collected from routes are used as the inputs to train an SVM model. During the training phase, an ROC curve is defined to evaluate the performance of the model. To validate the applicability of the trained model, a case study is developed to compare the data from an aircraft performance manual and from the implemented simulation model. The investigated aircraft in the case study is a Boeing 737-800 powered by CFM-56 engines. The comparison has shown that the trained SVM model from the proposed procedure is capable of representing a complex fuel consumption function accurately for all phases during the flight. The proposed methodology is generic, and can be extended to reliably model the fuel consumption of other types of aircraft, such as piston engine aircraft or turboprop engine aircraft.
support vector machine, receiver operating characteristic (ROC) curve, fuel consumption, aviation, regression, model optimization
Xuhui Wang, Xinfeng Chen, and Zhuming M. Bi (2015).
Support Vector Machine and ROC Curves for Modeling of Aircraft Fuel Consumption. Journal of Management Analytics.2 (1), 22-34. Taylor & Francis.