The Trend Estimate of the Wind Turbine Based on the Wavelet Neural Network
In this paper，adopting wavelet neural network，fault forecast of characteristic parameters of Wind turbine are realized by forecasting time series of key characteristic parameters of Wind turbine that include vibration intensity. With more degree of freedom in relation to the general neural network, wavelet neural network is in possession of more vivid and more valid ability in function approximation. With the good partial characteristic and distinguish rate learning wavelet neural network realizes the signal with good matching, and then wavelet neural network had stronger self-adaptation ability, more sooner convergence rate and higher forecast accuracy. Emulation and experiment result show that the forecast accuracy of the wavelet neural network meets demand and is of far reaching importance to guarantee the steam turbine circulate efficiently safety .
Z. J. Wang et al., "The Trend Estimate of the Wind Turbine Based on the Wavelet Neural Network", Advanced Materials Research, Vols. 443-444, pp. 1039-1044, 2012