基于改进ReliefF-PNN的航空发动机起动系统异常状态识别
张雷鸣 , 蒋丽英 , 崔建国 , 李贺 , 刘明昆 , 郭濠
沈阳航空航天大学学报 ›› 2023, Vol. 40 ›› Issue (6) : 68 -75.
基于改进ReliefF-PNN的航空发动机起动系统异常状态识别
Abnormal state identification of aircraft engine starting system based on the improved ReliefF-PNN
在航空发动机起动系统异常状态的识别研究中,起动系统的参数具有数据间相关性强、数据维度高、数据冗余信息多等特点。为降低数据维度,提高异常状态识别的准确率,将改进ReliefF算法与概率神经网络(probabilistic neural network,PNN)结合,提出改进ReliefF-PNN的航空发动机起动系统异常状态识别方法,更加有效地降低了参数的维度,并提升了异常状态识别模型的性能。利用该模型针对起动系统进行识别验证和分析。结果表明,利用改进后的ReliefF-PNN算法得到的参数子集进行异常状态识别的准确率优于改进前的结果,模型性能得到了进一步改善。
In the study of abnormal state identification of aircraft engine starting systems, the parameters of the starting system have characteristics such as strong correlation between data, high data dimensions and a lot of redundant information in data. In order to reduce the data dimension and improve the accuracy of abnormal state identification, an improved ReliefF algorithm was combined with probabilistic neural network(PNN) and improved ReliefF-PNN was proposed for abnormal state identification of aircraft engine starting system, which effectively reduced the dimension of parameters and improved the performance of the abnormal state identification model. The obtained model was used for identification verification and analysis of the starting system.The results show that the accuracy of using the improved ReliefF-PNN algorithm to identify abnormal states is better than before, further improving the performance of the model.
发动机起动系统 / 参数选择 / ReliefF算法 / 概率神经网络 / 异常状态识别
engine starting system / parameter selection / ReliefF algorithm / PNN / abnormal state identification
| [1] |
李东辉,喻甲其,杨梅.航空发动机故障诊断与研究[J].设备管理与维修,2022,42(5):148-149. |
| [2] |
|
| [3] |
陈冰.面向智能制造的航空发动机协同设计与制造[J].航空制造技术,2016,59(5):16-21. |
| [4] |
梅晓川.基于改进BP网络的航空发动机起动过程辨识[J].航空计算技术,2009,39(6):58-61. |
| [5] |
林敏.极限学习机在航空发动机气路故障诊断中的应用[D].上海:上海交通大学,2016. |
| [6] |
|
| [7] |
吕卫民,孙晨峰,任立坤,一种基于TCN-LGBM的航空发动机气路故障诊断方法[J/OL].兵工学报,1-11(2023-01-30)[2023-10-29]. |
| [8] |
|
| [9] |
董智博.基于改进欧氏距离的三维点云分割算法分析研究[D].北京:华北电力大学,2022. |
| [10] |
王桥梅,吴浩,杨杰,基于曼哈顿距离的HVDC输电线路故障识别新方法[J].四川轻化工大学学报(自然科学版),2022,35(4):75-84. |
| [11] |
孙林,杜雯娟,李硕,基于标记相关性和ReliefF的多标记特征选择[J].西北大学学报(自然科学版),2022,52(5):834-846. |
| [12] |
|
| [13] |
陈佳豪,吴浩,胡潇涛,基于LMD和DE-PNN的高压断路器机械故障识别方法[J].计算机应用与软件,2023,40(6):57-62,165. |
| [14] |
陈立爱,俞宏艳,汪佳奇,基于PCA-SSA-PNN的齿轮故障诊断[J].长沙大学学报,2023,37(2):18-27. |
| [15] |
|
| [16] |
赵舒安.基于数据驱动模型的航空发动机剩余使用寿命预测及故障诊断研究[D].重庆:重庆邮电大学,2022. |
| [17] |
祝钊,曹鹏.基于改进PSO-PNN的大螺旋钻机故障诊断系统研究[J].煤炭工程,2022,54(11):193-198. |
国家自然科学基金(62003223)
/
| 〈 |
|
〉 |