Detection and diagnosis method study of the civil aircraft surface fault based on LS-SVM

摘要

Large civil aircraft control surface failure occurred in flight will directly affect the handling and safety of the aircraft, so the flight control system needs to have an online surface fault diagnosis function. For large civil aircraft control surfaces and more features, this paper proposes online fault diagnosis algorithm control surfaces based on the use of least squares support vector machine (LS-SVM), using the Internet to search and cross-validation method to select SVM parameters identified online aircraft effectors fault parameters change, and to overcome the weak signal due to noise input to bring the problem of inaccurate identification. In this paper the application of the a large civil aircraft made publicly available flight data, the algorithm simulation results show that the method has strong generalization ability and higher recognition results.