Abstract
This paper deals with a novel prediction method for wind turbine by using neural network and operating data. As wind turbine transfer wind energy to electrical power energy, its structure has rotation part that capture wind energy, mechanical part, and electrical part that convert from mechanical rotation to electrical energy. Its working environmental situation is so bad like high mountain, sand desert, and offshore to capture good wind situation. Therefore, its control and monitoring should have high reliability for long terms during operation because its maintenance and repairing is very difficult and economically high cost. As wind turbine system is composed of three parts, there are many components that should be monitored to failure. This paper suggests neural network and operation data-based prediction method that can predict components' failure through data comparison and neural network's training function with easy expression of 'Yes' or 'No' for operator.
Highlights
Many policies, scientists, and engineers have been interesting in research motivation wind of turbine because of energy issues and environmental problems [1, 2].Wind turbine system have large rotors and energy converter that run under wind condition and weather environments
Monitoring system for many components including sensor signal failure has been using sensor-based mechanical system. It is limited in overall system's fault tolerance monitoring because wind turbine system has many components in nacelle including turbine and tower, and sensors
This paper provides fault tolerance prediction method by neural network and operation data of control system
Summary
Many policies, scientists, and engineers have been interesting in research motivation wind of turbine because of energy issues and environmental problems [1, 2]. Almost cases, WTEP (Wind Turbine Electric Power system) are located in mountain and offshore to receive strong wind energy. Because WTEP is composed of many components such as mechanical part, electric components, sensor, and converters, its dynamic system has strong multivariable and highly nonlinear behavior It is required strong safety and reliability for running over a wide range from bottom to up. This paper provides fault tolerance prediction method by neural network and operation data of control system. The resultant value produces 'Yes' or 'No' signal to announce for operator's failure easy understanding It means that this paper's idea is unique
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 callMore From: International Journal of Recent Technology and Engineering (IJRTE)
Disclaimer: 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.
