基于小波包和迁移学习的飞机燃油泵故障诊断

徐晶

PDF(1993 KB)
欢迎访问液压与气动官方网站!
PDF(1993 KB)
液压与气动 ›› 2020, Vol. 0 ›› Issue (06) : 183-188. DOI: 10.11832/j.issn.1000-4858.2020.06.029
工程技术

基于小波包和迁移学习的飞机燃油泵故障诊断

  • 徐晶
作者信息 +

Fault Diagnosis of Aircraft Fuel Pump Based on Wavelet Packet and Transfer Learning

  • XU Jing
Author information +
History +

摘要

飞机燃油系统需要在各种条件下持续向发动机供油。针对目前飞机燃油系统气蚀故障随机性和其故障数据相对不足,提出了基于小波包和迁移学习的飞机燃油泵气蚀故障诊断算法。首先利用小波包分解,对原始采样故障信号进行特征数据提取,再利用分解后的数据和相似结构下燃油泵故障数据构成目标数据和辅助数据,使用基于权重迭代调整的TrAdaboost迁移学习算法进行训练学习,最终完成故障类型的分类。通过已有的实验台和传统算法进行比较,验证了方法的有效性。

Abstract

The diagnosis of cavitation of fuel system are challenging due to complexity of structure. The objective of this work is to investigate failure mechanism and diagnosis method. This work describes an experimental study on fuel pump under normal mode and failure mode. In theory, the novel algorithm is proposed. The method extracts the feature data from the fault signal by wavelet packet decomposition in first step. These feature data and historical data from similar pump constitute auxiliary data and target data respectively to training set. These set are trained by TrAdaboost transfer learning algorithm which is based on the weight iteration adjustment for training learning. Finally, the novel algorithm is in good agreement with the experimental results.

关键词

飞机燃油泵,故障诊断;小波包分解;迁移学习

Key words

aircraft fuel pump, fault diagnosis, wavelet packet decomposition, transfer learning


引用本文

导出引用
徐晶. 基于小波包和迁移学习的飞机燃油泵故障诊断[J].液压与气动, 2020, 0(06): 183-188. https://doi.org/10.11832/j.issn.1000-4858.2020.06.029
XU Jing. Fault Diagnosis of Aircraft Fuel Pump Based on Wavelet Packet and Transfer Learning[J]. CHINESE HYDRAULICS & PNEUMATICS, 2020, 0(06): 183-188. https://doi.org/10.11832/j.issn.1000-4858.2020.06.029

参考文献

[1]乔琼.飞机燃油系统智能化故障诊断方法研究[D].西安:西北工业大学,2007. QIAO Qiong. Intelligent Diagnosis Method Research on Airplane System [D]. Xi'an: Xi'an Northwestern Polyte-chnical University, 2007. [2]杨野.基于粗糙集和支持向量机的离心泵气蚀故障诊断[J].软件导刊,2011,10(11):43-44. YANG Ye. Cavitation Fault Diagnosis of Centrifugal Pump Based on Rough Set and Support Vector Machine [J]. Software Tribune, 2011,10(11):43-44. [3]周云龙,刘永奇,薛广鑫,等.基于EMD和边际谱频带能量的离心泵汽蚀故障诊断[J].化工学报,2012,63(2):545-550. ZHOU Yunlong, LIU Yongqi, XUE Guangxin, et al. Fault Diagnosis of Cavitation for Centrifugal Pump Based on EMD and HHT Marginal Spectrum Energy [J]. Journal of Chemical Industry, 2012,63(2):545-550. [4]黄忠富,姜哲,赵斌娟,等.利用小波分析诊断水泵初始阶段的汽蚀故障[J].排灌机械,2005,23(2):4-7. HUANG Zhongfu, JIANG Zhe, ZHAO Binjuan,et al. Application of Wavelet Analysis to Early-stage Cavitation Diagnosis for Centrifugal Pumps [J]. Drainage and Irrigation Machinery, 2005,23(2):4-7. [5]黄忠富.小波分析在离心泵汽蚀故障诊断中的应用研究[J].江苏大学学报,2005,(4):8-10. HUANG Zhongfu. Research on the Applications of Analysis in Cavitation Fault Diagnosis for Centrifugal Pumps [J]. Journal of Jiangsu University, 2005,(4):8-10. [6]梁超.压力脉动法在离心泵汽蚀故障诊断中的研究[D].长春:东北电力大学,2010. LIANG Chao. Investigation of Fault Diagnosis of Cavitation in Centrifugal Pump Using Pressure Fluctuation Method [D]. Changchun: Northeast Dianli University, 2010. [7]寸文渊,赵正大,陈果,等.基于模态分析的某型飞机液压管路故障诊断[J].液压与气动,2019,(5):38-45. CUN Wenyuan, ZHAO Zhengda, CHEN Guo, et al. Fault Diagnosis Based on Modal Analysis for Certain Aircraft Hydraulic Pipe [J]. Chinese Hydraulics & Pneumatics, 2019,(5):38-45. [8]耿华,聂松林,王浩洁,等.基于DASP的海水马达振动分析和故障诊断研究[J].液压与气动,2017,(9):48-54. CENG Hua, NIE Songlin, WANG Haojie, et al. Vibration Analysis and Fault Diagnosis Based on DASP for Seawater Hydraulic Motor [J]. Chinese Hydraulics & Pneumatics, 2017,(9):48-54. [9]刘小平,鄂东辰,高强,等.基于BP神经网络的翻车机液压系统故障诊断[J].液压与气动,2016,(5):87-92. LIU Xiaoping, E Dongchen, GAO Qiang, et al. Fault Diagnosis Based on BP Network for Hydraulic Control System of Rotary Pump [J]. Chinese Hydraulics & Pneumatics, 2016,(5):87-92. [10]沈美杰,赵龙章,周兵,等.基于PSO优化的RBF网络液压泵故障诊断研究[J].液压与气动,2016,(5):87-92. SHEN Meijie, ZHAO Longzhang, ZHOU Bing, et al.Hydraulic Pump Fault Diagnosis of RBF Network Based on PSO Optimization [J]. Chinese Hydraulics & Pneumatics, 2016,(5):87-92. [11]李锋,林阳阳,赵辉,等.基于CEEMDAN-SVM的液压泵故障诊断方法研究[J].液压与气动,2016,(1):125-129. LI Feng, LIN Yangyang, ZHAO Hui, et al. Fault Diagnosis of Hydraulic Pump Based on CEEMDAN-SVM [J]. Chinese Hydraulics & Pneumatics, 2016,(1):125-129. [12]KANKAR P K, SHARMA S C, HARSHA S P. Fault Diagnosis of Ball Bearings Using Machine Learning Methods [J]. Expert Systems with Applications, 2011,38(3):1876-1886. [13]SHI W W, YAN H S, MA K P. A New Method of Early Fault Diagnosis Based on Machine Learning [C]//Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on. IEEE, 2005. [14]HUANG H H H, CHEN K S, ZENG L C. BP Neural Network Based on Fault Diagnosis of Hydraulic Servo Valves [C]//International Conference on Machine Learning & Cybernetics. IEEE, 2005. [15]RAMON J, DRIESSENS K, CROONENBORGHS T. Transfer Learning in Reinforcement Learning Problems Through Partial Policy Recycling [C]//European Conference on Machine Learning. Springer-verlag, 2007. [16]PAN S J, YANG Q. A Survey on Transfer Learning [J].IEEE Transactions on Knowledge and Data Engineering, 22,(10):1345-1359.
PDF(1993 KB)

26

Accesses

0

Citation

Detail

段落导航
相关文章

/