【作者】 杜现平； 卢英剑； 林泽帆； 张凯；

【Author】 Xianping Du;Yingjian Lu;Zefan Lin;Kai Zhang;School of Marine Engineering and Technology, Sun Yat-Sen University;School of Naval Architecture, Ocean & Civil Engineering,Shanghai Jiao Tong University;

【机构】 中山大学海洋工程与技术学院珠海； 上海交通大学船舶海洋与建筑工程学院闵行区；

【摘要】 随着风力发电机的大型化,风机叶片的细长比不断增加,引起结构的大柔性及结构稳定性问题,导致叶片结构的快速失效断裂。对叶片结构的稳定性进行快速识别,可以为叶片结构设计及运维控制提供参考数据。基于此,本研究通过开发不确定性数据学习的决策树算法,对风机叶片结构仿真数据的学习,进行叶片结构稳定性识别,并考虑工程不确定性建模,对输入参数及叶片结构设计参数的不确定性条件下的结构失稳风险进行评估,并基于决策树产生的可解释性规则,揭示参数变化与结构稳定性之间的关联机制。所识别获得的叶片结构失稳知识,为理解叶片在风载荷下的结构失稳提供了参考,并为叶片的结构设计及后期的风机运维控制提供参考。更多还原

【Abstract】 With the development of large wind turbines,the increasing slenderness of blade causes the large flexibility and structural stability problem.This may lead to the failure and break of blade structure.The efficient recognition of blade instability can provide information for the structural design and the operational and maintenance controls.In this study,an uncertain decision tree algorithm was developed and is used to learn the simulation data for structural stability recognition.The risk of structural instability is modeled with the parameters of blade structures,inflow wind,and blade pitch angle under the engineering uncertainty modeling.The interpretable rules can be generated form the decision tree for uncovering the interrelation between system parameters and structural instability.The knowledge of blade structural instability can help understand the structural instability under the wind and provide the reference for the later structural design and maintenance control.更多还原