Wind Turbine Gearbox fault early warning based on NEST
Xiao Zhong Yan, Changliang Liu · 2016
The condition detection of gearbox is of great significance to improve the operation level and reduce the maintenance cost of the wind turbine.Based on the nonlinear state estimation (NSET) method, the temperature model of the gear box bearing is set up to estimate the states of gear box and the estimated value of the gearbox bearing temperature is obtained.Having obtained the residual error of the estimated value and the actual value of the gearbox bearing temperature, the residual distribution characteristics are analyzed by sliding window error statistics method.The residual distribution characteristic of the model will be changed when the working condition of the gearbox is abnormal, and when the residual mean or standard deviation exceeds the set threshold, the warning is given.