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 state-identification 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.
Highlights
Under the influence of uncontrollable factors such as bad weather, wind turbines of wind farms are easy to produce 9 types of faults, including electrical faults, control system faults, pitch faults, yaw faults, hydraulic faults, drive system faults, tower faults, generator faults and nacelle faults
With the development of deep learning, a multi-running state health assessment model for the drive system of wind turbines based on bidirectional long shortterm memory (BiLSTM) neural network and gaussian mixture model (GMM) is proposed
Based on the data of SCADA system, a multi-running state health assessment method of wind turbines drive system based on bidirectional long short-term memory (BiLSTM) and GMM is proposed
Summary
Under the influence of uncontrollable factors such as bad weather, wind turbines of wind farms are easy to produce 9 types of faults, including electrical faults, control system faults, pitch faults, yaw faults, hydraulic faults, drive system faults, tower faults, generator faults and nacelle faults. Dong et al [21] proposed a method to assess the health status of WTs based on GMM and ER (Evidential Reasoning) This method is proved effective by real case data, and has potential applications. Jing Zhang et al [23] proposed a method to assess the online health status based on GMM and operational condition recognition This method has a good effect for health assessment of wind turbine. With the development of deep learning, a multi-running state health assessment model for the drive system of wind turbines based on bidirectional long shortterm memory (BiLSTM) neural network and gaussian mixture model (GMM) is proposed.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
