TY - GEN
T1 - A new GA-based RBF neural network with optimal selection clustering algorithm for SINS fault diagnosis
AU - Liu, Zhide
AU - Chen, Jiabin
AU - Han, Yongqiang
AU - Song, Chunlei
PY - 2009
Y1 - 2009
N2 - In this paper, a new adaptive genetic algorithm (GA)-based radial basis function (RBF) neural network with optimal selection clustering algorithm (OSCA) is proposed for the fault diagnosis of micro electromechanical system (MEMS) gyroscopes and accelerometers of strapdown inertial navigation system (SINS). The number of hidden layer nodes and parameters of RBF neural network are obtained by using OSCA. The connection weights are encoded to generate the chromosome, which is operated by adaptive GA. Orthogonal least square algorithm (OLS) is used to train the weights and gradient descent algorithm (GDA) with momentum term is used to estimate the parameters of Gaussian function. Adaptive GA, OLS and GDA with momentum term iterate alternately. Experimental results show that the proposed GA-based RBF neural network with OSCA quickly converges and effectively improves the diagnostic accuracy rate of SINS fault diagnosis.
AB - In this paper, a new adaptive genetic algorithm (GA)-based radial basis function (RBF) neural network with optimal selection clustering algorithm (OSCA) is proposed for the fault diagnosis of micro electromechanical system (MEMS) gyroscopes and accelerometers of strapdown inertial navigation system (SINS). The number of hidden layer nodes and parameters of RBF neural network are obtained by using OSCA. The connection weights are encoded to generate the chromosome, which is operated by adaptive GA. Orthogonal least square algorithm (OLS) is used to train the weights and gradient descent algorithm (GDA) with momentum term is used to estimate the parameters of Gaussian function. Adaptive GA, OLS and GDA with momentum term iterate alternately. Experimental results show that the proposed GA-based RBF neural network with OSCA quickly converges and effectively improves the diagnostic accuracy rate of SINS fault diagnosis.
KW - Fault diagnosis
KW - Genetic algorithm
KW - Optimal selection clustering algorithm
KW - Radial basis function neural network
KW - Strapdown inertial navigation system
UR - http://www.scopus.com/inward/record.url?scp=77949533319&partnerID=8YFLogxK
U2 - 10.1109/IEEM.2009.5373007
DO - 10.1109/IEEM.2009.5373007
M3 - Conference contribution
AN - SCOPUS:77949533319
SN - 9781424448708
T3 - IEEM 2009 - IEEE International Conference on Industrial Engineering and Engineering Management
SP - 2348
EP - 2352
BT - IEEM 2009 - IEEE International Conference on Industrial Engineering and Engineering Management
T2 - IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2009
Y2 - 8 December 2009 through 11 December 2009
ER -
