Title :
Application of RBF Neural Network Based on ENN2 Clustering in Fault Diagnosis
Author :
Tianzhu Wen ; Aiqiang Xu ; Chunxia Liu ; Nan Li
Author_Institution :
Naval Aeronaut. & Astronaut. Univ., Yantai, China
Abstract :
Radial basis function (RBF) neural network is widely used in engineering with its powerful advantage in solving nonlinear problems. But the number of hidden layer as well as the center and standard deviation of radial basis function are difficult to get, so RBF neural network based on ENN2 is proposed to solve the fault diagnosis problem. Firstly, the structure of RBF neural network is introduced, afterwards, the learning algorithm of RBF neural network is analyzed, the center and standard deviation of RBF in hidden layer are obtained by clustering method of extension neural network type 2(ENN2), meanwhile the weight matrix between hidden layer and output layer are calculated by generalized inverse method. Ultimately, the method is used to solve fault diagnosis problem, the results show that it has the advantages of simple structure, fast learning speed and high diagnostic accuracy.
Keywords :
fault diagnosis; learning (artificial intelligence); matrix algebra; pattern clustering; radial basis function networks; ENN2 clustering; RBF neural network learning algorithm; RBF standard deviation; extension neural network type 2 clustering; fault diagnosis; generalized inverse method; nonlinear problems; radial basis function neural network; weight matrix; Clustering algorithms; Fault diagnosis; Inverse problems; Neural networks; Standards; Turbogenerators; Vectors; ENN2 clustering; RBF neural network; extension theory; fault diagnosis; unsupervised learning;
Conference_Titel :
Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2014 Sixth International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-4799-4956-4
DOI :
10.1109/IHMSC.2014.120
