针对航空发动机结构复杂、性能退化参数众多、寿命预测精度低等问题,提出了一种基于退化特征相似性的寿命预测方法。首先通过基于Relief算法的退化特征筛选、基于主成分分析(principal component analysis,PCA)的特征提取和基于核函数...针对航空发动机结构复杂、性能退化参数众多、寿命预测精度低等问题,提出了一种基于退化特征相似性的寿命预测方法。首先通过基于Relief算法的退化特征筛选、基于主成分分析(principal component analysis,PCA)的特征提取和基于核函数的特征平滑,提取低维正交多变量退化特征;然后进行特征的相似性匹配,寻找与当前样本特征片段最相似的一组历史样本中的特征片段集合,将这些片段对应的RUL信息融合并采用密度加权方法得到当前样本的寿命预测估计值;最后通过美国国家航空航天局(national aeronautics and space administration,NASA)提供的航空涡轮扇发动机仿真数据集验证了该方法的有效性,其寿命预测性能高于现有几种代表性方法。展开更多
Exploring structural characteristics implied in initialdecision making information is an important issue in the process of aggregation. In this paper we provide a new family of aggregation operator called density weig...Exploring structural characteristics implied in initialdecision making information is an important issue in the process of aggregation. In this paper we provide a new family of aggregation operator called density weighted averaging operator（abbreviated as DWA operator）, which carries out the aggregation by classification. In this case, not only the hidden structural characteristics can be identified, some commonly known aggregation operators can also be incorporated into the function of the DWA operator. We further discuss the basic properties of this new operator, such as commutativity, idempotency, boundedness and monotonicity withcertain condition. Afterwards, two important issues related to the DWA operator are investigated, including the arguments partition and the determination of density weights. At last a numerical example regarding performance evaluation of employees is developed to illustrate the using of this new operator.展开更多
文摘针对航空发动机结构复杂、性能退化参数众多、寿命预测精度低等问题,提出了一种基于退化特征相似性的寿命预测方法。首先通过基于Relief算法的退化特征筛选、基于主成分分析(principal component analysis,PCA)的特征提取和基于核函数的特征平滑,提取低维正交多变量退化特征;然后进行特征的相似性匹配,寻找与当前样本特征片段最相似的一组历史样本中的特征片段集合,将这些片段对应的RUL信息融合并采用密度加权方法得到当前样本的寿命预测估计值;最后通过美国国家航空航天局(national aeronautics and space administration,NASA)提供的航空涡轮扇发动机仿真数据集验证了该方法的有效性,其寿命预测性能高于现有几种代表性方法。
基金Supported by the National Natural Science Foundation of China(71671031,71701040)
文摘Exploring structural characteristics implied in initialdecision making information is an important issue in the process of aggregation. In this paper we provide a new family of aggregation operator called density weighted averaging operator（abbreviated as DWA operator）, which carries out the aggregation by classification. In this case, not only the hidden structural characteristics can be identified, some commonly known aggregation operators can also be incorporated into the function of the DWA operator. We further discuss the basic properties of this new operator, such as commutativity, idempotency, boundedness and monotonicity withcertain condition. Afterwards, two important issues related to the DWA operator are investigated, including the arguments partition and the determination of density weights. At last a numerical example regarding performance evaluation of employees is developed to illustrate the using of this new operator.
