Aeroengine Performance Deterioration Evaluation Using Clustering and Multi-Scaling Optimal Hyper Sphere Kernel Distance Assessment

Journal of Propulsion Technology ›› 2013, Vol. 34 ›› Issue (7): 977-983.

• Control ,Measurement and Fault Diagnosis • Previous Articles Next Articles

Aeroengine Performance Deterioration Evaluation Using Clustering and Multi-Scaling Optimal Hyper Sphere Kernel Distance Assessment

Graduate Students’ Brigade, Naval Aeronautical and Aeronautical University, Yantai 264001, China;Department of Aero-craft Engineering, Naval Aeronautical and Astronautical University, Yantai 264001, China;Graduate Students’ Brigade, Naval Aeronautical and Aeronautical University, Yantai 264001, China;Graduate Students’ Brigade, Naval Aeronautical and Aeronautical University, Yantai 264001, China

Published:2021-08-15

基于聚类和多尺度优化的超球体核距离评估的航空发动机性能衰退

李冬¹,李本威²,王永华^1,2,赵凯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;海军航空工程学院研究生管理大队, 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

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
基金资助:
国家自然科学基金青年基金(61102167)。

Abstract

Abstract: Aiming at repeated linearity and excessiveness of engine performance evaluating parameter, a cluster method according to variation and distance judgement was presented. Similar individuals were grouped, mean of every group was adopted as analysis objective, which reduced dimension greatly. On the basis of Support Vector Data Description, hyper sphere kernel distance metric was introduced while multi-parameter was converted to single parameter, and contradiction leaded by parameter overfull was settled. Distance between a point in the character space and core of hyper sphere denotes performance deterioration. Valve curve of beginning deterioration and worsening was obtained. Considering contribution of parameter after clustering to performance evaluation, multi-scaling kernel parameter and punish coefficient C are optimized by improved Particle Swarm Optimization algorithm. Results indicate that engine performance can be consistent to factual condition after considering multi-scaling parameter. Evaluating results of multi-scaling parameter after clustering are consistent with original parameter. 

Key words: Cluster; Multi-scaling parameter optimization; Hyper sphere kernel distance; Performance deterioration; Improved particle swarm optimization

摘要： 针对发动机性能评估参数存在多重共线性且数量过多的问题,提出一种依据类间方差和距离判别的聚类方法。将相似个体化为一类,并取类中均值作为分析对象,大大减少了参数维数；在支持向量数据描述(Support Vector Data Description)算法基础上,引入超球体核距离度量,将多参数转化为单参数,解决了参数过多相互矛盾的问题。特征空间上一点与超球体中心的距离表征发动机的性能衰退程度,并给出了性能开始衰退与性能明显恶化的阀值曲线。考虑聚类后类中参数对发动机性能评估的贡献不同,提出基于改进粒子群算法优化多尺度核函数参数和惩罚因子C。仿真结果表明:考虑了多尺度参数后,发动机性能状况较单尺度参数能更好的符合实际使用情况。聚类后多尺度参数与原参数的评估结果基本一致。 

关键词: 聚类; 多尺度参数优化; 超球体核距离; 性能衰退; 改进粒子群算法 

LI Dong¹, LI Ben-wei²,WAN Yong-hua^1,2,ZHAO Kai¹. Aeroengine Performance Deterioration Evaluation Using Clustering and Multi-Scaling Optimal Hyper Sphere Kernel Distance Assessment[J]. Journal of Propulsion Technology, 2013, 34(7): 977-983.

李冬,李本威,王永华,赵凯. 基于聚类和多尺度优化的超球体核距离评估的航空发动机性能衰退[J]. 推进技术, 2013, 34(7): 977-983.

References

[1] 张营, 左洪福, 任淑红, 等.一种航空发动机性能衰退预测的优化算法[J].中国机械工程, 2011,2(9):1009-1013.
[2] 张海军, 左洪福, 梁剑.航空发动机多指标模糊信息熵的性能排序研究[J].应用科学学报, 2006,4(3):288-392.
[3] 邹葆华.航空发动机性能综合评判模型[J].航空发动机, 2008,4(2):10-12.
[4] 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):198-200.(HU Jin-hai, XIE Shou-sheng.Performance Monitoring and Fault Diagnosis of Aeroengine Based Genetic Algorithm[J].Journal of Propulsion Technology, 2003,4(3):198-200.)
[5] 侯胜利, 胡金海, 李应红.基于混沌变量的航空发动机性能监控与故障诊断[J].航空动力学报, 2005,0(2):314-317.
[6] 胡金海, 谢寿生, 陈卫, 等.基于核函数主元分析的航空发动机故障检测方法[J].推进技术, 2008,9(1):79-83.(HU Jin-hai, XIE Shou-sheng, CHEN Wei,et al.An Aeroengine Fault Detection Method Based on Kernel Principal Component Analysis[J].Journal of Propulsion Technology, 2008,9(1):79-83.)
[7] 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.
[8] 崔晓飞, 蒋科艺, 王永华.基于贝叶斯信息融合的航空发动机健康状态评估方法研究[J].燃气涡轮试验与研究, 2009,2(4):39-42.
[9] Tony Boutros, Ming Liang.Mechanical Fault Detection Using Fuzzy Index Fusion[J].Machine Tools and Manufacture, 2007,(3):1702-1714.
[10] 于锦禄, 何立明, 孙冬.基于分形理论的航空发动机推力性能衰退规律[J].航空动力学报, 2010,5(10):2302-2306.
[11] 司守奎, 孙玺菁.数学建模算法与应用[M].北京:国防工业出版社, 2011.
[12] 李桂林,陈晓云.关于聚类分析中相似度的讨论[J].计算机工程与应用, 2004,1(1):64-66.
[13] 张智晟, 孙雅明, 张世英,等.基于数据挖掘多层次细节分解的负荷序列聚类分析[J].电网技术, 2006,0(2):51-56.
[14] 曹惠玲, 牛军, 涂讯来, 等.一种基于主成分分析法的发动机性能评估方法[J].中国民航大学学报,2011,29(6):8-11.
[15] 李凌均, 张周锁, 何正嘉.基于支持向量数据描述的机械故障诊断研究[J].西安交通大学学报, 2003,7(9):910-913.
[16] 罗自英, 徐刚.基于SVDD故障诊断方法中的非目标数据[J].自动化仪表, 2008,9(6):12-14.
[17] 杨欣毅, 刘剑锋, 张强,等.粒子群算法求解航空发动机模型的应用[J].航空计算技术, 2007,7(6):39-41.
[18] Naka S, Genji T, Yura T, et al.A Hybrid Particle Swarm Optimization for Distribution State Estimation[J].IEEE Transaction Power Systems, 2003,8(1):60-68.
[19] 张强.基于粒子群算法的X型涡扇发动机最优加速控制规律研究[D].烟台:海军航空工程学院, 2008.
[20] 尹大伟.某型发动机模型修正研究[D].烟台:海军航空工程学院, 2007.
[21] 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.
[22] 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.

Aeroengine Performance Deterioration Evaluation Using Clustering and Multi-Scaling Optimal Hyper Sphere Kernel Distance Assessment

基于聚类和多尺度优化的超球体核距离评估的航空发动机性能衰退

PDF

Knowledge

Cited

Abstract

Cite this article

share this article

References

Related Articles 0

Recommended Articles

Metrics

Comments