基于SCADA参数关系的风电机组部件重要度分析  

Component importance analysis of wind turbine based on SCADA parameter relations

作　　者：程诗雨 刘航[2] 曾天生 陈汉斯 王峥[1] 褚学宁[1] Cheng Shiyu;Liu Hang;Zeng Tiansheng;Chen Hansi;Wang Zheng;Chu Xuening(Shanghai Jiao Tong University,Shanghai 200240,China;Zhengzhou University of Aeronautics,Zhengzhou 451015,China)

机构地区：[1]上海交通大学,上海200240 [2]郑州航空工业管理学院,河南郑州450015

出　　处：《可再生能源》2021年第10期1335-1341,共7页Renewable Energy Resources

基　　金：国家自然科学基金资助项目(51875345;51475290)。

摘　　要：在风电机组部件重要度分析中,通常将机组性能状态简单划分为"正常运行"和"停机"两种,忽视其他中间状态,且大多依赖专家打分,主观性较强。为解决上述问题,文章提出一种基于SCADA参数关系的风电机组部件重要度分析方法。首先,对原始数据进行预处理,基于"风速-功率"多项式模型评估整机性能;然后,采用高斯过程回归拟合"风速-部件性能参数"基准关系,以偏离基准的程度来评估部件性能;最后,提出森林优化-K近邻回归方法,建立部件性能与整机性能的特征加权回归模型,根据最优特征权重确定部件重要度。基于公开数据集的实验证明了所提方法的有效性。In the component importance analysis of wind turbine,the performance state is usually simply divided into"operating"and"hutdown",ignoring other intermediate states that actually exist.In addition,the analysis is highly dependent on expert scoring,bringing in strong subjectivity.In order to solve the above problems,a component importance analysis method of wind turbine based on SCADA parameter relations is proposed.First,the raw data are pre-processed and the turbine performance is evaluated based on polynomial model of"wind speed-power"relationship.Then,a Gaussian process regression is used to fit the benchmark relationship between"wind speed"and"component performance parameters",and the component performance is evaluated by the degree of deviation from the benchmark.Finally,a forest optimization-K nearest neighbor regression method is proposed to establish a feature-weighted regression model of component performance and turbine performance,and the component importance is determined according to the optimal feature weights.Experiments based on public data set demonstrate the effectiveness of the proposed method.

关 键 词：风电机组 部件重要度 SCADA参数关系 性能评估 森林优化算法 

分 类 号：TK83[动力工程及工程热物理—流体机械及工程]