Abstract

본 연구에서는 풍력발전기 타워의 효과적인 상태 모니터링을 위하여 타워의 고유진동수 및 모드형상을 이용한 손상추정기법을 제안하였다. 풍력발전기에 대한 동력학 시뮬레이션 프로그램을 이용하여 타워의 거동을 시뮬레이션하고 결과를 이용하여 타워의 모드특성을 추정하였다. 다양한 손상에 의한 타워의 고유진동수와 모드형상의 변화를 모드특성 추정 프로그램을 이용하여 해석적으로 구하여 훈련패턴을 생성하고 이를 이용하여 신경망을 훈련시켰다. 복수 손상 경우를 포함한 10가지 손상경우에 대한 모드특성을 훈련된 신경망에 입력하여 손상을 추정하였으며, 모든 손상 경우에 대하여 비교적 정확하게 손상위치와 손상정도를 판정할 수 있었다. 단, 미소 손상의 경우 손상정도가 약간 과소평가되는 경향을 보였으나 손상위치는 합리적으로 추정됨을 알 수 있었다. 향후, 미소 손상 추정결과의 정확성을 개선하고, 실험을 통하여 제안된 기법을 검증할 계획이다. A damage estimation method of wind turbine tower using natural frequency and mode shape is presented for effective condition monitoring. Dynamic analysis for a wind turbine was carried out to obtain the response of tower from which modal properties were identified. A neural network was learned based on training patterns generated by the changes of natural frequency and mode shape due to various damages. The changes of modal property were calculated using a program for modal parameter estimation. Damage locations and severities could be successfully estimated for 10 damage cases including multi-damage cases using the trained neural network. The damage severities for very small damages generally tends to be slightly under-estimated however, the identified damage locations agreed reasonably well with the accurate locations. Enhancement of the estimation result for very small damage and verification of the proposed method through experiment will be carried out by further study.

Full Text
Paper version not known

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 call

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.