Turbo-generator vibration fault prediction using gray prediction model

Research on turbo-generator fault prediction is one of theory bases for its fault self-recovery, however, the lack of fault samples and the incompletion of fault information make it full difficulties. This paper presents an efficient method for turbo-generator vibration fault prediction in which the new model of gray forecasting with first-order fitting parameter is established. On the basis of the first-order exponent flatness operation for the energies in different frequency bands extracted by wavelet packet decomposition, a new turbo-generator fault gray prediction model is established to reconstruct feature vectors consisting of the energies in different frequency bands. And then, five typical turbo-generator vibration faults are identified by using SVM. Experimental results showed that the proposed method could effectively and efficiently forecast delitescent faults and typical fault genres for the turbo-generator vibration.