自适应核模式分析方法及其在航空发动机部件性能衰退识别中的应用

推进技术 ›› 2013, Vol. 34 ›› Issue (9): 1272-1278.

自适应核模式分析方法及其在航空发动机部件性能衰退识别中的应用

李冬¹, 李本威², 杨欣毅²,朱飞翔¹

海军航空工程学院研究生管理大队, 山东烟台 264001;海军航空工程学院飞行器工程系, 山东烟台 264001;海军航空工程学院飞行器工程系, 山东烟台 264001;海军航空工程学院研究生管理大队, 山东烟台 264001

发布日期:2021-08-15
作者简介:李冬(1984—),男,博士生,研究领域为航空发动机性能衰退、评估与预测。E-mail:happyli.dong@163.com

Self-Adaptive Kernel Pattern Analysis Method and Its Application in Aeroengine Component Performance Deterioration Recognition

Graduate Students’ Brigade, Naval Aeronautical and Astronautical University, Yantai 264001, China;Department of Airbone Vehicle Engineering, Naval Aeronautical and Astronautical University, Yantai 264001, China;Department of Airbone Vehicle Engineering, Naval Aeronautical and Astronautical University, Yantai 264001, China;Graduate Students’ Brigade, Naval Aeronautical and Astronautical University, Yantai 264001, China

Published:2021-08-15

摘要/Abstract

摘要： 针对测量数据因其部件之间的耦合不能有效识别各个部件性能衰退程度的问题,提出一种基于性能修正因子核模式分析的发动机部件性能衰退识别方法,并能与传感器测量偏差区分开。首先将传感器测量数据输入到自适应模型中去,产生一组用于识别部件性能衰退的修正因子。将修正因子参考模式通过核模式映射到高维特征空间中去,在此可分(基本可分)空间中完成识别。考虑到修正因子参考模式在高维空间中映射的像呈带状分布,几何距离不能有效识别,基于此采用神经网络方法对模式进行识别。识别成功率达到94.34%。进一步分析了特征约简的输入维数对识别效果的影响以及所提方法的泛化能力。考查了噪声对模式识别的影响,得到幅值3%以内的噪声对识别结果无明显影响。证明了“自适应模型+核模式分析+神经网络”识别方法是可行的。 

关键词: 自适应模型; 核模式分析; 性能衰退; 修正因子 

Abstract: Aiming at component performance deterioration not being recognized because of coupling with components in measured parameter, a recognition method of component performance deterioration based on performance modified factor kernel pattern analysis was presented and deviation of sensor was distinguished. Measured parameters were fed to self-adaptive model, a group of component performance modified factor used as pattern recognition was generated. Modified factor reference mode was mapped to high-dimension character space and recognition was accomplished in this separable (basically separable) space. Considering that map of modified factor reference mode has shape of strap, geometry distance is not recognized well. Therefore neural network is adopted. Success ratio of recognition reaches 94.34%. Furtherly the effects of input dimension after simplification on recognition and generalizability were analyzed. The effects of noise on pattern recognition was examined and noise within 3% had little influence on recognition. It verifies the pattern recognition method ‘self-adaptive model+kernel pattern analysis+neural network’ is feasible.

Key words: Self-adaptive model; Kernel pattern analysis; Performance deterioration; Modified factor

李冬,李本威,杨欣毅,朱飞翔. 自适应核模式分析方法及其在航空发动机部件性能衰退识别中的应用[J]. 推进技术, 2013, 34(9): 1272-1278.

LI Dong¹, LI Ben-wei², YANG Xin-yi², ZHU Fei-xiang¹. Self-Adaptive Kernel Pattern Analysis Method and Its Application in Aeroengine Component Performance Deterioration Recognition[J]. Journal of Propulsion Technology, 2013, 34(9): 1272-1278.

参考文献

[1] Valter Crescenzi, Paolo Merialdo, Paolo Missier.Clustering Web Pages Based on Their Structure[J].Data and Knowledge Engineering, 2005,9(3):279-299.
[2] 杨震.分类和聚类中若干问题的研究[D].北京:北京邮电大学, 2007.
[3] 单晓明,宋云峰,黄金泉,等.基于神经网络和模糊逻辑的航空发动机状态监视[J].航空动力学报,2009,4(10):2356-2361.
[4] 张鹏, 黄金泉.基于双重卡尔曼滤波器的发动机故障诊断[J].航空动力学报, 2008,3(5):952-956.
[5] 李本威.某型发动机气路监测诊断方法研究[D].烟台:海军航空工程学院, 2008.
[6] 黄向华,丁毅.基于几何模式识别的发动机传感器故障诊断[J].航空学报, 2006,7(6):1018-1022.
[7] 胡金海,谢寿生,侯胜利,等.粗糙核主元分析方法及其在故障特征提取中的应用[J].振动与冲击, 2008,7(3):50-54,9.
[8] 张亮,张凤鸣,杜纯.复杂装备健康状态评估的粗糙核距离度量方法[J].计算机工程与设计, 2009,0(18):4269-4271.
[9] 胡金海, 谢寿生.基于遗传算法的航空发动机性能监控与故障诊断[J].推进技术, 2003,4(3).(HU Jin-hai, XIE Shou-sheng.Performance Monitoring and Fault Diagnosis of Aeroengine Based Genetic Algorithm[J].Journal of Propulsion Technology, 2003,4(3).)
[10] Tony Boutros, Ming Liang.Mechanical Fault Detection Using Fuzzy Index Fusion[J].Machine Tools and Manufacture, 2007,2(4):1702-1714.
[11] Mathioudakis K, Kamboukos Ph, Stamatis A.Turbofan Performance Deterioration Tracking Using Nonlinear Models and Optimization Techniques[J].ASME Laboratory of Thermal Turbomachines, 2002,4:580-587.
[12] 王信德.某型涡扇发动机自适应建模研究[D].南京:南京航空航天大学, 2003.
[13] Aretakis N, Mathioudakis K.Classification of Radial Compressor Faults Using Pattern Recognition Techniques[J].Control Engineering Practice, 1998,6(10).
[14] Scholkopf B, Smola A, Muller K R.Nonlinear Component Analysis as a Kernel Eigenvalue Problem[J].Neural Computation, 1998,0(5):1299-1319.
[15] 郭磊.基于核模式分析方法的旋转机械性能退化评估技术研究[D].上海:上海交通大学, 2009.
[16] 吴翊,李永乐,胡庆军,等.应用数理统计[M].长沙:国防科技大学出版社,1995.
[17] 李明,孙涛,胡海岩.齿轮传动转子—轴承系统动力学的研究进展[J].振动工程学报, 2002,5(3).