Citation

Dai Y, Tian J, Rong H, Zhao T. Safety Sci. 2015; 80: 56-65.

Copyright

(Copyright © 2015, Elsevier Publishing)

DOI

10.1016/j.ssci.2015.07.006

PMID

unavailable

Abstract

To reduce landing mishap risk, one of the greatest challenges is how to accurately determine whether a landing process is safe or not. This paper presents a landing safety analysis method based on a combination of support vector machine (SVM) and rough set theory (RST). In this hybrid approach, the carrier landing data are first analyzed with RST to identify parameters that are sensitive to changes in the state of landing safety. With a landing data set composed of the identified sensitive parameters, the SVM model is trained and the optimal separating hyperplane is obtained to distinguish between the two classes of landing samples (i.e., safe and hazardous), so as to establish the relationship between landing parameters and safety. 635 real landing samples of the aircraft carrier USS Enterprise (CVN 65) are used in the case study, and it is shown that the proposed method is able to identify those parameters contributing more significantly to landing safety and thus deserving more attention paid to. Furthermore, the hyperplane is used as a basis for formulating landing parameter design and control requirements, so that the landing parameters match well and safe landing is guaranteed.