A
Aijun Hu
Researcher at North China Electric Power University
Publications - 36
Citations - 793
Aijun Hu is an academic researcher from North China Electric Power University. The author has contributed to research in topics: Computer science & Nonlinear system. The author has an hindex of 9, co-authored 21 publications receiving 262 citations.
Papers
More filters
Journal ArticleDOI
Fault detection of wind turbine based on SCADA data analysis using CNN and LSTM with attention mechanism
TL;DR: A new method is proposed for fault detection of wind turbine, in which the convolutional neural network cascades to the long and short term memory network (LSTM) based on attention mechanism, which verifies the effectiveness of the proposed method.
Journal ArticleDOI
Deterministic and probabilistic multi-step forecasting for short-term wind speed based on secondary decomposition and a deep learning method
TL;DR: The proposed model based on secondary decomposition (SD) and bidirectional gated recurrent unit (BiGRU) can accommodate long-range dependency and extract the semantic information of raw data and could obtain better forecasting performance.
Journal ArticleDOI
Condition monitoring and anomaly detection of wind turbine based on cascaded and bidirectional deep learning networks
TL;DR: A new method is proposed to extract multidirectional spatio-temporal features of SCADA data for wind turbine condition monitoring based on convolutional neural network and bidirectional gated recurrent unit with attention mechanism with better feasibility of practical wind energy application.
Journal ArticleDOI
Dynamic analysis of a planetary gear system with multiple nonlinear parameters
Ling Xiang,Nan Gao,Aijun Hu +2 more
TL;DR: Analysis results show that the variation of meshing frequency as the external excitation could transit the states of the system and the higher damping coefficient and suitable backlash could suppress the region of chaos.
Journal ArticleDOI
A novel method based on meta-learning for bearing fault diagnosis with small sample learning under different working conditions
TL;DR: In this paper , a novel method called data reconstruction hierarchical recurrent meta-learning (DRHRML) is proposed for bearing fault diagnosis with small samples under different working conditions, which contains data reconstruction and meta learning stages.