Accurate and reliable wind speed forecasting is crucial for wind farm planning and grid operation security. To improve the accuracy of wind speed forecasting, a novel combined model is proposed for wind speed forecasting in this paper. First, the complete ensemble empirical mode decomposition adaptive noise (CEEMDAN) and permutation entropy (PE) are employed to decompose the original wind speed time series into the sub-series with obvious complexity different; To overcome the disadvantage of weak generalization ability of single deep learning method when facing diversiform data, a cluster of gated recurrent unit networks (GRUs) with different hidden layers and neurons are applied to capturing the unsteady characteristics and implicit information of each sub-series; The predictions of the GRUs of each sub-series are aggregated into a nonlinear-learning regression top-layer which is consisted of radial basis function neural network (RBFNN), and improved bat algorithm (IBA) is introduced to optimize the parameters of RBFNN; Lastly, the prediction values of each nonlinear-learning top-layer are superimposed to obtain the final prediction values. To validate the effectiveness of the model, 15-min and 1-h wind speed data from the wind farm in Zhangjiakou, China, are used as test cases. The experimental results demonstrate that the proposed combined model can achieve the best performance and stability compared to other models. Such as the performance evaluation indexes (RMSE=0.3294, MAPE=2.6169%) are smallest obtained from case study 1, and (RMSE=0.5876, MAPE=4.7875%) are smallest obtained from case study 2.INDEX TERMS Wind speed forecasting, combined model, complete ensemble empirical mode decomposition adaptive noise, gated recurrent unit.

No abstract

With the continuous elevation of demand for large-scale wind turbines and operation & maintenance cost an increasing interest has been rapidly generated on CM (Condition Monitoring) system. The main components of wind turbines are the focus on all CM as they overall lead to high repair costs and equipment downtime. Thus, it is difficult to make comprehensive assessment in the assessment. In the present study, intelligent machine learning algorithms are adopted to mine SCADA (Supervisory Control and Data Acquisition) system data of WTs (wind turbines). Besides, based on bidirectional long short-term memory (BiLSTM) neural networks and gaussian mixture model (GMM) algorithm, this study developed a multi-running state health assessment model for the drive system of wind turbines. First, the stateidentification model is built with health data to overcome the effect of the time-varying characteristics of running environment and alterations of running condition during the assessment. Then, in each state, the BiLSTM algorithm is adopted to extract the residual set of valid state variables, and the GMM algorithm is employed to accurately fit the distribution of residual set. The multi-running state benchmark model based on BiLSTM and GMM is built. Subsequently, the drive system of wind turbines health degree is calculated by health index. Lastly, based on multiple driving system faults data of a wind turbine, the feasibility and validity of the model are verified.

No abstract

No abstract