A review of wind speed and wind power forecasting with deep neural networks

Fault detection of wind turbine based on SCADA data analysis using CNN and LSTM with attention mechanism

Short-term wind speed prediction based on LMD and improved FA optimized combined kernel function LSSVM

Order tracking (OT), which is realized by signal sampling in equal-angle increment according to the measured rotating speed, is a powerful technique for rotating machine fault diagnosis under variable-speed condition. However, if the tachometer cannot be installed on the rotating machine or the speed signal is not available for some reasons, OT is difficult to be realized. This review summarizes recent advances in the development of tacholess speed estimation methods for OT with its applications to fault diagnosis. First, the basis of rotating speed estimation and OT is revisited. Then, the methods are categorized into three groups including vibration or sound signal, electrical motor current signal, and video stream according to the signal source from which the speed is estimated. The principle, implementation procedures, key techniques, along with the merits, and shortcuts of these methods are summarized and discussed in detail. Afterward, a contrastive case study using three kinds of methods is provided to intuitively illustrate the performances of OT along with the applications in motor bearing fault diagnosis. A bibliography of the recent publications related to this topic is also provided to facilitate the selection and improvement of the tacholess OT methods in fault diagnosis applications. Finally, the research prospects are discussed.

Tacholess Speed Estimation in Order Tracking: A Review With Application to Rotating Machine Fault Diagnosis

Renewable energy is essential for planet sustainability. Renewable energy output forecasting has a significant impact on making decisions related to operating and managing power systems. Accurate prediction of renewable energy output is vital to ensure grid reliability and permanency and reduce the risk and cost of the energy market and systems. Deep learning's recent success in many applications has attracted researchers to this field and its promising potential is manifested in the richness of the proposed methods and the increasing number of publications. To facilitate further research and development in this area, this paper provides a review of deep learning-based solar and wind energy forecasting research published during the last five years discussing extensively the data and datasets used in the reviewed works, the data pre-processing methods, deterministic and probabilistic methods, and evaluation and comparison methods. The core characteristics of all the reviewed works are summarised in tabular forms to enable methodological comparisons. The current challenges in the field and future research directions are given. The trends show that hybrid forecasting models are the most used in this field followed by Recurrent Neural Network models including Long Short-Term Memory and Gated Recurrent Unit, and in the third place Convolutional Neural Networks. We also find that probabilistic and multistep ahead forecasting methods are gaining more attention. Moreover, we devise a broad taxonomy of the research using the key insights gained from this extensive review, the taxonomy we believe will be vital in understanding the cutting-edge and accelerating innovation in this field.

Aijun Hu

Papers

Fault detection of wind turbine based on SCADA data analysis using CNN and LSTM with attention mechanism

Deterministic and probabilistic multi-step forecasting for short-term wind speed based on secondary decomposition and a deep learning method

Condition monitoring and anomaly detection of wind turbine based on cascaded and bidirectional deep learning networks

Dynamic analysis of a planetary gear system with multiple nonlinear parameters

A novel method based on meta-learning for bearing fault diagnosis with small sample learning under different working conditions