航空电子设备故障预测特征参数提取方法研究 -- 西北工业大学学报,2017,35(3):364-373
论文:2017,Vol:35,Issue(3):364-373
引用本文:
陈华坤, 章卫国, 史静平, 何启志, 占正勇. 航空电子设备故障预测特征参数提取方法研究[J]. 西北工业大学学报
Chen Huakun, Zhang Weiguo, Shi Jingping, He Qizhi, Zhan Zhengyong. Research on Feature Extraction Method for Fault Prediction of Avionics[J]. Northwestern polytechnical university

航空电子设备故障预测特征参数提取方法研究
陈华坤1, 章卫国1, 史静平1, 何启志1, 占正勇2
1. 西北工业大学 自动化学院, 陕西 西安 710072;
2. 中航工业自控所 飞行控制一体化重点实验室, 陕西 西安 710065
摘要:
故障特征提取是航空电子设备故障预测的关键技术,对于少量测试点的电子设备可以采用小波变换、傅里叶变换、经验模态分解等方法提取故障特征,但是由于航空电子设备属于大规模集成电路,测试点比较多,采用上述方法提取的故障特征可能相互混叠并且数量比较大会严重影响故障预测精度及速度,因此如何从众多故障信息中提取故障特征是一个难题。文章提出基于极大似然和降噪自编码神经网络方法从大量故障信息中提取故障特征。首先,使用极大似然法分析由多个测试点提取的故障信息和历史退化过程的故障信息组成的高维数据集,估计需要提取故障特征的维数;然后使用降噪自编码神经网络方法将高维故障信息映射到指定维数的数据空间,从中提取关键的故障特征,去除冗余信息;最后,以航空电子系统电源模块为例,采用新方法提取故障特征,分别通过将故障特征可视化和使用故障特征进行健康评估来验证其有效性。
关键词:    综合模块化航电系统    故障预测和健康管理    特征提取    降噪自编码神经网络    极大似法    维数估计    DC-DC变换器    支持向量机   
Research on Feature Extraction Method for Fault Prediction of Avionics
Chen Huakun1, Zhang Weiguo1, Shi Jingping1, He Qizhi1, Zhan Zhengyong2
1. School of Aulomation, Northwestern Polytechnical University, Xi'an 710072, China;
2. Science and Technology on Aircraft Control Laboratory, FACRI, Xi'an 710065, China
Abstract:
Feature extraction is the key technique for fault prediction of avionics, Wavelet transform, Fourier transform, empirical mode decomposition methods can be used to extract fault features of the electronic equipment with few test points. Due to the fact that the avionics is large-scale integrated circuits which includes many test points, fault features extracted based on the method above may be mixed with each other and the number is large, which will seriously affect the accuracy and speed of fault prediction. It is a difficult problem to extract fault features from many fault information. In this paper, we propose the method based on denoising autoencoder and maximum likelihood to extract fault features from a large number of fault information. First of all, maximum likelihood is taken to analyze the high dimensional data comprised of the fault information which were extracted from many test points and historical degradation process, and to estimate the intrinsic dimension of fault features; Then, the high dimensional data is mapped to the specified dimension data space by using denoising autoencoder method. The key fault features are extracted from the data, and the redundant information is removed. Finally, taking the avionics power system as an example, through the fault feature visualization and health assessment demonstrate that the method proposed in the paper which can extract fault features is effective.
Key words:    integrated modular avionics    prognostics and health management    feature extraction    denoising autoencoder    maximum likelihood    dimension estimation    DC-DC converters    support vector machines   
收稿日期: 2016-10-11     修回日期:
DOI:
基金项目: 国家自然科学基金(61374032、61573286)及航空科学基金(20140753012)资助
通讯作者:     Email:
作者简介: 陈华坤(1982-),西北工业大学博士研究生,主要从事智能控制、故障诊断与故障预测研究。
相关功能
PDF(1413KB) Free
打印本文
把本文推荐给朋友
作者相关文章
陈华坤  在本刊中的所有文章
章卫国  在本刊中的所有文章
史静平  在本刊中的所有文章
何启志  在本刊中的所有文章
占正勇  在本刊中的所有文章

参考文献:
[1] 王少萍. 大型飞机机载系统预测与健康管理关键技术[J]. 航空学报, 2014, 35(6):1459-1472 Wang Shaoping. Prognostics and Health Management Key Technology of Aircraft Airborne System[J]. Acta Aeronautica et Astronautica Sinica, 2014, 35(6):1459-1472(in Chinese)
[2] 范庚, 马登武. 基于组合优化相关向量机的航空发动机性能参数概率预测方法[J]. 航空学报, 2013, 34(9):2110-2121 Fan Geng, Ma Dengwu. Probabilistic Prediction Method for Aeroengine Performance Parameters Based on Combined Optimum Relevance Vector Machine[J]. Acta Aeronautica et Astronautica Sinica, 2013, 34(9):2110-2121(in Chinese)
[3] 陈雄姿, 于劲松, 陆文高,等. 基于综合健康指数与RVM的系统级失效预测[J]. 系统工程与电子技术, 2015, 37(10):2298-2305 Chen Xiongzi, Yu Jinsong, Lu Wengao, et al. System-Level Failure Prognostics Using Synthesized Health Index and Relevance Vector Machine[J]. Systems Engineering & Electronics, 2015, 37(10):2298-2305(in Chinese)
[4] 吴祎, 王友仁, 姜媛媛,等. 基于特征参数退化的DC/DC变换器故障预测[J]. 仪器仪表学报, 2013, 34(6):1380-1387 Wu Yi, Wang Youren, Jiang Yuanyuan, et al. Fault Prediction Method of DC/DC Converter Based on Characteristic Parameter Degradation[J]. Chinese Journal of Scientific Instrument, 2013, 34(6):1380-1387(in Chinese)
[5] 徐宇亮, 孙际哲, 陈西宏,等. 电子设备健康状态评估与故障预测方法[J]. 系统工程与电子技术, 2012, 34(5):1068-1072 Xu Yuliang, Sun Jizhe, Chen Xihong, et al. Method of Health Performance Evaluation and Fault Prognostics for Electronic Equipment[J]. Systems Engineering & Electronics, 2012, 34(5):1068-1072(in Chinese)
[6] Xu J, Xu L. Health Management Based on Fusion Prognostics for Avionics Systems[J]. Journal of Systems Engineering and Electronics, 2011, 22(3):428-436
[7] 孙健, 王成华, 杜庆波. 基于小波包能量谱和NPE的模拟电路故障诊断[J]. 仪器仪表学报, 2013, 34(9):2021-2027 Sun Jian, Wang Chenghua, Du Qingbo. Analog Circuit Fault Diagnosis Based on Wavelet Packet Energy Spectrum and NPE[J]. Chinese Journal of Scientific Instrument, 2013, 34(9):2021-2027(in Chinese)
[8] 黄艳秋, 蒲鹏. 基于能量熵对SVM的电路故障诊断[J]. 计算机仿真, 2011, 28(4):199-202 Huang Yanqiu, Pu Peng. Circuit Fault Diagnosis Based on Energy Entropy and SVM[J]. Computer Simulation, 2011, 28(4):199-202(in Chinese)
[9] Long B, Tian S, Wang H. Feature Vector Selection Method Using Mahalanobis Distance for Diagnostics of Analog Circuits Based on LS-SVM[J]. Journal of Electronic Testing, 2012, 28(5):745-755
[10] 汤巍, 景博, 黄以锋,等. 振动载荷下面向电子设备PHM的板级封装潜在故障分析方法[J]. 电子学报, 2016, 44(4):944-951 Tang Wei, Jing Bo, Huang Yifeng, et al. Latent Fault Analysis of Board-Level Package for Electronics PHM Subjected to Vibration[J]. Acta Electronica Sinica, 2016, 44(4):944-951(in Chinese)
[11] Zhu Z B, Song Z H. A Novel Fault Diagnosis System Using Pattern Classification on Kernel Fda Subspace[J]. Expert Systems with Applications An International Journal, 2011, 38(6):6895-6905
[12] Govindan A, Deng G, Kalman J, et al. Independent Component Analysis Applied to Electrogram Classification during Atrial Fibrillation[C]//Fourteenth International Conference on Pattern Recognition, 1998:1662-1664
[13] Xiao Y, He Y. A Novel Approach for Analog Fault Diagnosis Based on Neural Networks and Improved Kernel PCA[J]. Neurocomputing, 2011, 74(7):1102-1115
[14] Hinton G E, Salakhutdinov R R. Reducing the Dimensionality of Data with Neural Networks[J]. Science, 2006, 313(5786):504-507
[15] Vincent P, Larochelle H, Bengio Y, et al. Extracting and Composing Robust Features with Denoising Autoencoders[C]//Proceedings of the 25th International Conference on Machine Learning, 2008:1096-1103
[16] Maaten L J P V D, Postma E O, Herik H J V D. Dimensionality Reduction:A Comparative Review[J]. Journal of Machine Learning Research, 2009, 10:66-71
[17] Levina E, Bickel P J. Maximum Likelihood Estimation of Intrinsic Dimension[J]. Advances in Neural Information Processing Systems, 2004, 17:777-784
[18] Rozza A, Lombardi G, Ceruti C, et al. Novel High Intrinsic Dimensionality Estimators[J]. Machine Learning, 2012, 89(1/2):37-65
[19] Zhang Y. Enhanced Statistical Analysis of Nonlinear Processes Using KPCA, KICA and SVM[J]. Chemical Engineering Science, 2009, 64(5):801-811
[20] Alwan M, Beydoun B, Ketata K, et al. Bias Temperature Instability From Gate Charge Characteristics Investigations in N-Channel Power MOSFET[J]. Microelectronics Journal, 2007, 38(6):727-734
[21] Alwitt R, Hills R. The Chemistry of Failure of Aluminum Electrolytic Capacitors[J]. IEEE Tans on Parts, Materials and Packaging, 1965, 1(2):28-34
[22] Mantooth H Alan, Perry R Glenn. A Unified Diode Model for Circuit Simulation[C]//The 26th IEEE Power Electronics Specialists Conference, Atlanta,GA,USA,1995:851-857
[23] Lahyani A, Venet P, Grellet G, et al. Failure Prediction of Electrolytic Capacitors during Operation of a Switch Mode Power Supply[J]. IEEE Trans on Power Electronics, 1998, 13(6):1199-1207
相关文献:
1.杨宏晖, 王芸, 戴健.水下目标识别中样本选择与SVME融合算法[J]. 西北工业大学学报, 2014,32(3): 362-367
2.王仲生, 李明, 王翔.航空发动机突发故障识别与监控方法研究[J]. 西北工业大学学报, 2013,31(3): 401-405
3.赵金, 谢松云, 郭正, 于海勋.基于HOC-SVM的运动状态下脑电的特征提取与分类[J]. 西北工业大学学报, 2012,30(3): 435-439