摘要
针对漂浮式风力机平台长期受风、浪及海流作用下系泊发生蠕变加快腐蚀,造成系泊失效的问题,基于深度学习与混沌理论对局部系泊失效下的风力机平台进行了动态响应分析,重点研究系泊是否发生蠕变以及蠕变系泊位置。以美国国家可再生能源实验室开发的5 MW漂浮式风力机为研究对象,基于Barge平台验证所提方法的有效性。结果表明:系泊失效后各自由度响应急剧增大,但在蠕变阶段,响应变化极小,艏摇响应更为敏感;采用卷积神经网络及混沌可有效识别系泊状态与蠕变系泊位置,对预防系泊失效,保证风力机正常运行具有重要意义。
Aiming at the problem of mooring failure caused by creep and accelerated corrosion of floating wind turbine platform under the action of wind, wave and sea current for a long time, based on deep learning and chaos theory, the dynamic response of the wind turbine platform under local mooring failure was analyzed, focusing on the mooring creep occuring and the location of the creep mooring. Taking the 5 MW floating wind turbine developed by the National Renewable Energy Laboratory of the United States as the research object, the effectiveness of the proposed method was verified based on the Barge platform. Results show that the response in each degree of freedom increases sharply after mooring failure, but the changes of response is small during creep period. The bow roll response is more sensitive, and convolutional neural network and chaos can effectively identify the mooring state and creep mooring position, which is of great significance to prevent mooring failure and ensure the normal operation of the wind turbine.
作者
孙康
金江涛
李春
李蜀军
许子非
肖俊青
SUN Kang;JIN Jiangtao;LI Chun;LI Shujun;XU Zifei;XIAO Junqing(School of Energy and Power Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China;Shanghai Key Laboratory of Multiphase Flow and Heat Transfer in Power Engineering,Shanghai 200093,China)
出处
《动力工程学报》
CAS
CSCD
北大核心
2022年第10期933-943,共11页
Journal of Chinese Society of Power Engineering
基金
国家自然科学基金资助项目(52006148,51976131,52106262)
上海"科技创新行动计划"地方院校能力建设资助项目(19060502200)。
关键词
漂浮式风力机
系泊蠕变
深度学习
混沌
状态识别
floating wind turbine
mooring creep
deep learning
chaos
state recognition
