Northwestern Polytechnical University，Xian 710072，China)(1.Jiangsu Province Key Laboratory of Aerospace Power System

College of Energy and Power Engineering

Nanjing University of Aeronautics and Astronautics

Nanjing 210016

China;2.Collaborative Innovation Center for Advanced AeroEngine

Beijing 100191

China;3.AeroEngine Control System Institute

Aero Engine (Group) Corporation of China

Wuxi Jiangsu 214063

China)Abstract：A fast leaveoneout cross validation method was presented to provide a criterion for kernelbased extreme learning machine (K-ELM) used for sensor signal reconfiguration of aeroengine. The procedure can avoid N times explicit training (N is the number of training samples) so that the computation cost was reduced 1/N when compared with normal leaveoneout procedure. Simulation results show that this method can provide a fast and accurate criterion

allowing to select best kernel parameters for K-ELM.