基于BDPCA聚类算法的航空发动机故障数据标记

吕超1,程弓2,刘云清1

振动与冲击 ›› 2020, Vol. 39 ›› Issue (9) : 35-41.

PDF(1530 KB)
PDF(1530 KB)
振动与冲击 ›› 2020, Vol. 39 ›› Issue (9) : 35-41.
论文

基于BDPCA聚类算法的航空发动机故障数据标记

  • 吕超1,程弓2,刘云清1
作者信息 +

Aeroengine fault data tag using on improved BDPCA algorithm

  • LV Chao1, CHENG Gong2,LIU Yunqing1
Author information +
文章历史 +

摘要

航空发动机作为飞行器的动力核心对飞行器的安全飞行有着举足轻重的作用,保证航空发动机的平稳运行对飞行安全有着重大意义。在基于有监督学习的航空发动机故障诊断技术不断取得进展的同时,如何将平时获取的大量未标记数据转换为能够用来训练故障诊断模型的带标记数据,成为了制约行业发展的一大瓶颈。针对这一问题引入了基于无监督学习的DPCA算法,用以实现对未标记数据集的准确分类与标记,并针对DPCA算法在局部密度计算与簇类别数选择方面的缺陷进行了优化:针对原始DPCA算法应用标准高斯核计算局部密度易造成误识别的状况,引入共享邻域算法对局部密度的计算方法进行优化;针对原始DPCA算法需要人工研判确定簇类别数易造成的误识别状况,引入BIC选择准则对簇类别数的选择方法进行优化;提出了原始DPCA算法与共享邻域算法以及BIC选择准则相结合的BDPCA算法。最后应用航空发动机转子故障数据对BDPCA算法进行了性能验证并取得了良好的结果,证实了BDPCA算法在航空发动机气路故障诊断领域有较高的实用价值。

Abstract

As the power core of an aircraft,the aeroengine plays an important role in the safe flight of the aircraft.It is of great significance to ensure the smooth operation of aeroengine for flight safety.While the technology of aeroengine fault diagnosis based on supervised learning has been progressing continuously, how to convert a large number of unlabeled data obtained at ordinary time into labeled data that can be used to train the fault diagnosis model has become a bottleneck restricting the development of the industry.In the paper, the DPCA algorithm based on unsupervised learning was introduced to realize the accurate classification and marking of unmarked data sets.Aiming at some defects of the DPCA algorithm, the algorithm was optimized by using the shared neighborhood algorithm and BIC selection criteria.Finally, the performance of the improved algorithm was verified by applying gas path fault data of some aeroengine, and good results were obtained.

关键词

航空发动机 / 气路故障 / 密度峰值聚类分析 (DPCA) / 贝叶斯信息准则 (BIC) / 共享邻域

Key words

aeroengine / gas path fault / desity peaks clustering algorithm (DPCA) / Bayseian information criterion (BIC) / shared neighbourhood

引用本文

导出引用
吕超1,程弓2,刘云清1. 基于BDPCA聚类算法的航空发动机故障数据标记[J]. 振动与冲击, 2020, 39(9): 35-41
LV Chao1, CHENG Gong2,LIU Yunqing1. Aeroengine fault data tag using on improved BDPCA algorithm[J]. Journal of Vibration and Shock, 2020, 39(9): 35-41

参考文献

[1] Yang Hongfu,Jia Xiaobang,et al. Review of Data-driven Aeroengine Fault Diagnosis and Prognosis Methods[J].Aviation Precision Manufacturing Technology,2016,52(05):6-9(in Chinese) (杨洪富,贾晓亮等.基于数据驱动的航空发动机故障诊断与预测方法综述[J].航空精密制造技术,2016,52(05):6-9.) [2] Boutsidis C, Gittens A, Kambadur P. Spectral clustering via the power method - provably[C] International Conference on International Conference on Machine Learning. JMLR.org, 2015:40-48. [3] 李丽敏,王仲生,姜洪开.基于相似性传播聚类的航空发动机突发故障诊断[J].振动与冲击,2014, 33(1):51-55. LI Limin, WANG Zhongsheng , JIANG Hongkai. Abrupt fault diagnosis of aero-engine based on affinity propagation clustering[J]. Journal of Vibration and Shock, 2014, 33(1):51-55. [4] Lu Junwen,Wu Rui, et al. Research on the Fault Diagnostic Based on Improved Neural Network for Gas Path of Aeroengine[J]. Process Automation Instrumentation,2015,36(1):5-8.(in Chinese) (卢俊文,吴瑞等.航空发动机气路改进神经网络故障诊断研究[J].自动化仪表,2015,36(1):5-8.) [5] Zhang Yun,Yang Don,et al. Aero-Engine Vibration Fault Diagnosis Based on Supervised Manifold Learning[J].Journal of Propulsion Technology, 2017,38(5):1147-1154.(in Chinese) (张赟,杨栋,斯彦刚,方旭萌.基于监督流形学习的航空发动机振动故障诊断方法[J].推进技术,2017,38(05):1147-1154.) [6] Pang Shan,Yang Xinyi .Application of Deep Kerne1 Extreme Learning Machine in Aero Engine Components Fault Diagnosis[J].Journal of Propulsion Technology, 2017,38(11):2613-2621.(in Chinese) (逄珊,杨欣毅,张勇,韦祥.应用深度核极限学习机的航空发动机部件故障诊断[J].推进技术,2017,38(11):2613-2621.) [7] Yang Hui,Wang Iijing.QAR data outlier detection algorithm based on clustering and fitting[J].Computer Engineering and Design, 2015,36(1):174-177.(in Chinese) (杨慧, 王丽婧. 基于聚类和拟合的QAR数据离群点检测算法[J]. 计算机工程与设计, 2015.) [8] LI Limin,Fang Zhongsheng,et al.Abrupt fault diagnosis of aero-engxne based on affinity propagation clustering[J].Journal of Vibration and Shock,2014,33(1):51-55(in Chinese) (李丽敏,王仲生等.基于相似性传播聚类的航空发动机突发故障诊断[J].振动与冲击,2014,33(1):51-55.) [9] Ding Weiming.Fault Diagnosis of Aero-engine Rotor System Based on Grid Refinement WaveCluster[D].Nanchang Hangkong University, Nanchang, China.2015(in Chinese) (丁伟明. 基于网格细化小波聚类的航空发动机转子系统故障诊断[D].南昌航空大学,2015.) [10] Rodriguez A, Laio A. Clustering by fast search and find of density peaks.[J]. Science (New York, N.Y.), 2014, 344(6191):1492. [11] Zhang, X.,Li, J.,Yu, H. Local density adaptive similarity measurement for spectral clustering[J]. Pattern Recognition Letters, 2011, 32 (2): 352-358. [12] Chen Guo,, Li Ai. Introduction to aircraft detection and diagnosis technology[M]. Aeronautical Industry Press, Beijing,2012.(in Chinese) (陈果, 李爱. 航空器检测与诊断技术导论[M]. 航空工业出版社, 北京,2012) [13]Lin Min.Application of Extreme Learning Machine in aero-engine Gas Path Fault Diagnosis[D].Shanghai Jiao Tong University.2015 (林敏. 极限学习机在航空发动机气路故障诊断中的应用[D]. 2015.)

PDF(1530 KB)

Accesses

Citation

Detail

段落导航
相关文章

/