How to Improve the Reliability of Wind Turbines

According to the failure of wind turbines in operation, the failure cause and phenomenon of wind turbines is analyzed, combined with the reliability of wind turbine subsystems, measures aiming at cooperation parts and purchased parts are proposed, the reliability of the whole wind turbines is improved in a certain extent. At the same time, condition monitoring system can carry through the early detecting and diagnosing to potential component failure maintain. Besides, automatic lubrication system can realize accurate and timeliness lubrication, also can reduce maintenance workload, preserve correct lubrication and smooth running of all parts.

Download Full-text

Design of a Condition Monitoring System for Wind Turbines

Energies ◽

10.3390/en15020464 ◽

2022 ◽

Vol 15 (2) ◽

pp. 464

Author(s):

Jinje Park ◽

Changhyun Kim ◽

Minh-Chau Dinh ◽

Minwon Park

Keyword(s):

Neural Network ◽

Wind Turbine ◽

Monitoring System ◽

Condition Monitoring ◽

Wind Turbines ◽

Offshore Wind ◽

Offshore Wind Turbines ◽

Diagnosis Model ◽

Condition Monitoring System ◽

Condition Diagnosis

Renewable energy is being adopted worldwide, and the proportion of offshore wind turbines is increasing. Offshore wind turbines operate in harsh weather conditions, resulting in various failures and high maintenance costs. In this paper, a condition diagnosis model for condition monitoring of an offshore wind turbine has been developed. The generator, main bearing, pitch system, and yaw system were selected as components subject to the condition monitoring by considering the failure rate and downtime of the wind turbine. The condition diagnosis model works by comparing real-time and predictive operating data of the wind turbine, and about four years of Supervisory Control and Data Acquisition (SCADA) data from a 2 MW wind turbine was used to develop the model. A deep neural network and an artificial neural network were used as machine learning to predict the operational data in the condition diagnosis model, and a confusion matrix was used to measure the accuracy of the failure determination. As a result of the condition monitoring derived by inputting SCADA data to the designed system, it was possible to maintain the failure determination accuracy of more than 90%. The proposed condition monitoring system will be effectively utilized for the maintenance of wind turbines.

Download Full-text

Perspectives on condition monitoring techniques of wind turbines

Wind Engineering ◽

10.1177/0309524x18807028 ◽

2018 ◽

Vol 43 (5) ◽

pp. 539-555 ◽

Cited By ~ 2

Author(s):

R Moeini ◽

M Entezami ◽

M Ratkovac ◽

P Tricoli ◽

H Hemida ◽

...

Keyword(s):

Wind Turbine ◽

Monitoring System ◽

Condition Monitoring ◽

Wind Turbines ◽

Power Plants ◽

High Reliability ◽

Monitoring Methods ◽

Technical Literature ◽

Monitoring Techniques ◽

Condition Monitoring System

The ever-increasing development of wind power plants has raised awareness that an appropriate condition monitoring system is required to achieve high reliability of wind turbines. In order to develop an efficient, accurate and reliable condition monitoring system, the operations of wind turbines need to be fully understood. This article focuses on the online condition monitoring of electrical, mechanical and structural components of a wind turbine to diminish downtime due to maintenance. Failure mechanisms of the most vulnerable parts of wind turbines and their root causes are discussed. State-of-the-art condition monitoring methods of the different parts of wind turbine such as generators, power converters, DC-links, bearings, gearboxes, brake systems and tower structure are reviewed. This article addresses the existing problems in some areas of condition monitoring systems and provides a novel method to overcome these problems. In this article, a comparison between existing condition monitoring techniques is carried out and recommendations on appropriate methods are provided. In the analysis of the technical literature, it is noted that the effect of wind speed variation is not considered for traditional condition monitoring schemes.

Download Full-text