Feature extract based on improved fuzzy neural network
Che Hao Chang, Dan Hu · 2010
By changing the construction of the fuzzy neural network based on wavelet basis function, an improved fuzzy neural network is introduced for feature extraction of fault information. By the selection of wavelet base and the orthogonal least-square (OLS) algorithm, an improved fuzzy neural network is described for feature extraction so as to improve the system convergence. Finally, according to the cutting force sample data, it is proved that this method has fast convergence and excellent optimization feature subset property, reduces the significant over-fitting problem.