scholarly journals A novel hybrid intelligent fault diagnosis method based on improved RBF neural network

2016 ◽  
Author(s):  
Yi Liu
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Rbf Neural Network ◽  
Intelligent Fault Diagnosis ◽  
Diagnosis Method

RBF Neural Network Model Training by Unscented Kalman Filter and its Application in Mechanical Fault Diagnosis

2014 ◽  
Vol 602-605 ◽  
pp. 2383-2386 ◽  
Author(s):  
Xu Sheng Gan ◽  
Hua Ping Li ◽  
Hai Long Gao
Keyword(s):  
Neural Network ◽  
Kalman Filter ◽  
Fault Diagnosis ◽  
Neural Network Model ◽  
Basis Function ◽  
Unscented Kalman Filter ◽  
Rbf Neural Network ◽  
Mechanical Equipment ◽  
Diagnosis Method ◽  
Model Training

To improve the ability of fault diagnosis for mechanical equipment, a Radial Basis Function Neural Network (RBFNN) diagnosis method based on Unscented Kalman Filter (UKF) algorithm is proposed. In the algorithm, at first, UKF algorithm is used to estimate the parameters of RBFNN, and then the proposed method is introduced into the fault diagnosis of mechanical equipment. The simulation indicates that the established model has a good diagnosis performance for mechanical fault diagnosis.

Fault Diagnosis of Cascaded Converter Based on Wavelet Packet RBF Neural Network

2013 ◽  
Vol 273 ◽  
pp. 300-304
Author(s):  
Xin Wang ◽  
Juan Xu ◽  
Guo Dong Zhang ◽  
Rui Min Qi
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Learning Algorithm ◽  
Rbf Neural Network ◽  
Wavelet Packet ◽  
Open Circuit ◽  
Learning Performance ◽  
Cascaded Converter ◽  
Diagnosis Method ◽  
Faults Diagnosis

To study the power component open circuit faults diagnosis method of the cascaded converter. Aiming at the insufficiency of the BP learning algorithm in the machinery fault diagnosis, such as the low learning convergence speed, the easily appearing local minimum, the instability learning performance caused by the initial value, to proposed a new method applied to the cascaded converter based on radial basis function (RBF) neural network. Experiments show that the method based on wavelet packet analysis and RBF neural network has better learning and fault identification capability, and it can meet the online real-time fault diagnosis of the cascaded converter.

Sign in / Sign up

Export Citation Format

Share Document