A novel combined model for vibration trend prediction of a hydropower generator unit

Abstract

It is significant to predict the vibration trend of a hydropower generator unit (HGU) based on historical data for the stable operation of units and the maintenance of power system safety. Therefore, a novel combined model based on ensemble empirical mode decomposition (EEMD), sample entropy (SE), a Gaussian process regression (GPR) model and an autoregressive moving average model (ARMA) is proposed. Firstly, according to the non-linear and non-stationary characteristics of the vibration series, the vibration time series is decomposed into a single component and relatively stable subsequences using EEMD. Then, the SE algorithm reconstructs the subsequences with similar complexity to reduce the number of prediction sequences. Moreover, after judging the stationarity test of the reconstructed sequence, the GPR model and ARMA model are used to predict the non-stationary and stable subsequences, respectively. Finally, the predicted values of each subsequence are synthesised. Furthermore, five related methods are employed to evaluate the effectiveness of the proposed approach. The results illustrate that: (1) compared with EEMD only, EEMD combined with SE can improve prediction accuracy; (2) the reconstruction strategy based on SE can reduce the influence of false modes and improve the prediction accuracy; and (3) the prediction effect of the hybrid prediction model, which reduces the influence of accidental factors, is better than that of a single model in predicting the vibration sequence of an HGU.