Redirigiendo al acceso original de articulo en 16 segundos...
Inicio  /  Aerospace  /  Vol: 10 Par: 4 (2023)  /  Artículo
ARTÍCULO
TITULO

Attrition Risk and Aircraft Suitability Prediction in U.S. Navy Pilot Training Using Machine Learning

Jubilee Prasad-Rao    
Olivia J. Pinon Fischer    
Neil C. Rowe    
Jesse R. Williams    
Tejas G. Puranik    
Dimitri N. Mavris    
Michael W. Natali    
Mitchell J. Tindall and Beth W. Atkinson    

Resumen

The cost to train a basic qualified U.S. Navy fighter aircraft pilot is nearly USD 10 M. The training includes primary, intermediate, and advanced stages, with the advanced stage involving extensive flight training, and, thus, is very expensive as a result. Despite the screening tests in place and early-stage attrition, 4.5% of aviators undergo attrition in this most expensive stage. Key reasons for aviator attrition include poor flight performance, voluntary withdrawals, and medical reasons. The reduction in late-stage attrition offers several financial and operational benefits to the U.S. Navy. To that end, this research leverages feature extraction and machine learning techniques on the very sparse flight test grades of student aviators to identify those with a high risk of attrition early in training. Using about 10 years of historical U.S. Navy pilot training data, trained models accurately predicted 50% of attrition with a 4% false positive rate. Such models could help the U.S. Navy save nearly USD 20 M a year in attrition costs. In addition, machine learning models were trained to recommend a suitable training aircraft type for each student aviator. These capabilities could help better answer the need for pilots and reduce the time and cost to train them.