| 航空发动机传感器信号重构的K-ELM方法 |
| |
| 引用本文： | 尤成新,鲁峰,黄金泉.航空发动机传感器信号重构的K-ELM方法[J].航空动力学报,2017,32(1):221-116. |
| |
| 作者姓名： | 尤成新 鲁峰 黄金泉 |
| |
| 作者单位： | 1.南京航空航天大学 能源与动力学院 江苏省航空动力系统重点实验室，南京 210016 |
| |
| 基金项目： | 国家自然科学基金(51276087)；中央高校基本科研业务费专项资金(NP2012504)；南京航空航天大学研究生创新基地（实验室）开放基金（kfjj20150205） |
| |
| 摘 要： | 针对航空发动机传感器信号重构，提出了评价核极限学习机（K ELM）模型性能的一种快速留一交叉验证方法.结果表明:该方法可以避免原始的留一验证方法N次模型的显式训练，将计算复杂度降低为原来的1/N（N为样本数目）.该算法可以快速准确评价核极限学习机的性能，为核极限学习机确定最优的核参数.
|
| 关 键 词： | 航空发动机 燃烧室航空发动机 传感器信号重构 核极限学习机 留一交叉验证方法 核参数 |
| 收稿时间： | 2015/5/14 0:00:00 |
K-ELM method for sensor signal reconfiguration of aero engine |
| |
| YOU Cheng-xin,LU Feng,HUANG Jin-quan.K-ELM method for sensor signal reconfiguration of aero engine[J].Journal of Aerospace Power,2017,32(1):221-116. |
| |
| Authors: | YOU Cheng-xin LU Feng HUANG Jin-quan |
| |
| Abstract: | Northwestern Polytechnical University，Xian 710072，China)(1.Jiangsu Province Key Laboratory of Aerospace Power System,College of Energy and Power Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China;2.Collaborative Innovation Center for Advanced Aero Engine,Beijing 100191,China;3.Aero Engine Control System Institute,Aero Engine (Group) Corporation of China,Wuxi Jiangsu 214063,China)Abstract:A fast leave one out cross validation method was presented to provide a criterion for kernel based extreme learning machine (K-ELM) used for sensor signal reconfiguration of aero engine. The procedure can avoid N times explicit training (N is the number of training samples) so that the computation cost was reduced 1/N when compared with normal leave one out procedure. Simulation results show that this method can provide a fast and accurate criterion, allowing to select best kernel parameters for K-ELM. |
| |
| Keywords: | aero engine combustoraero engine sensor signal reconfiguration kernel based extreme learning machine (K-ELM) leave one out cross validation method kernel parameters |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《航空动力学报》浏览原始摘要信息 |
|
点击此处可从《航空动力学报》下载全文 |
