Open Access Open Access  Restricted Access Subscription Access

Aero Engine Fault Diagnosis Using an Optimized Extreme Learning Machine


Affiliations
1 Department of Aerocraft Engineering, Naval Aeronautical and Astronautical University, Yantai 264001, China
2 College of Information and Electrical Engineering, Ludong University, Yantai 264025, China
 

A new extreme learning machine optimized by quantum-behaved particle swarm optimization (QPSO) is developed in this paper. It uses QPSO to select optimal network parameters including the number of hidden layer neurons according to both the root mean square error on validation data set and the norm of output weights. The proposed Q-ELM was applied to real-world classification applications and a gas turbine fan engine diagnostic problem and was compared with two other optimized ELM methods and original ELM, SVM, and BP method. Results show that the proposed Q-ELM is a more reliable and suitable method than conventional neural network and other ELM methods for the defect diagnosis of the gas turbine engine.
User
Notifications
Font Size

Abstract Views: 58

PDF Views: 1




  • Aero Engine Fault Diagnosis Using an Optimized Extreme Learning Machine

Abstract Views: 58  |  PDF Views: 1

Authors

Xinyi Yang
Department of Aerocraft Engineering, Naval Aeronautical and Astronautical University, Yantai 264001, China
Shan Pang
College of Information and Electrical Engineering, Ludong University, Yantai 264025, China
Wei Shen
Department of Aerocraft Engineering, Naval Aeronautical and Astronautical University, Yantai 264001, China
Xuesen Lin
Department of Aerocraft Engineering, Naval Aeronautical and Astronautical University, Yantai 264001, China
Keyi Jiang
Department of Aerocraft Engineering, Naval Aeronautical and Astronautical University, Yantai 264001, China
Yonghua Wang
Department of Aerocraft Engineering, Naval Aeronautical and Astronautical University, Yantai 264001, China

Abstract


A new extreme learning machine optimized by quantum-behaved particle swarm optimization (QPSO) is developed in this paper. It uses QPSO to select optimal network parameters including the number of hidden layer neurons according to both the root mean square error on validation data set and the norm of output weights. The proposed Q-ELM was applied to real-world classification applications and a gas turbine fan engine diagnostic problem and was compared with two other optimized ELM methods and original ELM, SVM, and BP method. Results show that the proposed Q-ELM is a more reliable and suitable method than conventional neural network and other ELM methods for the defect diagnosis of the gas turbine engine.