基于ReliefF-LMBP算法的涡轴发动机气路故障模式识别—两机专刊

推进技术 ›› 2021, Vol. 42 ›› Issue (1): 0-.

• 测试试验控制 • 下一篇

基于ReliefF-LMBP算法的涡轴发动机气路故障模式识别—两机专刊

王召广¹, 杨宇飞¹, 闫召洪², 鲁峰²

中国航空动力机械研究所,中国航空动力机械研究所,南京航空航天大学能源与动力学院,南京航空航天大学能源与动力学院

出版日期:2021-01-15 发布日期:2021-01-15

Gas path Fault Mode Identification of Turboshaft Engine Based on ReliefF-LMBP Algorithm

AVIC Aviation Powerplant Research Institute,Zhuzhou,,,

Online:2021-01-15 Published:2021-01-15

摘要/Abstract

摘要： 针对涡轴发动机气路故障模式识别精度不高的问题，提出了一种基于ReliefF-LMBP故障特征提取的发动机故障模式识别方法。首先，应用ReliefF算法对发动机传感器参数赋予权值，然后对传感器参数特征权重值的进行迭代更新和排序，聚集好的特征样本，离散异类样本。之后根据筛选出的特征子集，利用LMBP神经网络算法进行发动机故障模式识别。以某型涡轴发动机为对象进行气路故障诊断验证，结果表明所提方法能有效提取特征传感器参数并实现有效的故障模式识别。

关键词: 涡轴发动机；气路故障诊断；特征提取；神经网络；ReliefF分析

Abstract: In order to improve the performance of gas path fault diagnosis for turbo shaft engine, a ReliefF-LMBP based method is proposed to fault feature extraction and pattern recognition. Firstly, the available engine sensor measurements are analyzed and assigned feature weights, and the fault feature subsets are determined after iterative selection by ReliefF algorithm. The effective feature measured parameters are gathered by similar samples, and the rest parameters fall in the discrete heterogeneous sample subsets. Afterwards, the LMBP Neural Network algorithm is employed to build up the relationship between the fault modes and features of reduced measurements. The tests of gas path fault diagnosis are carried out on a turbo shaft engine, and results show the superiority of the proposed methodology.

Key words: Turbo shaft engine; Gas path fault diagnosis; Feature extraction; Neural network；ReliefF analysis

王召广,杨宇飞,闫召洪,鲁峰. 基于ReliefF-LMBP算法的涡轴发动机气路故障模式识别—两机专刊[J]. 推进技术, 2021, 42(1): 0-.

参考文献

[1] Volponi A J. Gas Turbine Engine Health Management Past, Present and Future Trends, Journal of Engine for Gas Turbines and Power-Transactions of the ASME [J]. 2014, 136(5): 051201.
[2]Lu F, Ju H F, Huang J Q. An improved extended Kalman filter with inequality constraints for gas turbine engine health monitoring [J], Aerospace Science and Technology, 2016, 58(1): 36-47.
[3]You C X, Huang J Q, Lu F. Recursive reduced kernel based extreme learning machine for aero-engine fault pattern recognition[J]. Neurocomputing, 2016, 214: 1038-1045.
[4] Peng K, Hu Y J, Fan D, et al. An Adaptive Feedback Turning SIR Particle Filter and Its Application on Fault Diagnosis of Auxiliary Power Unit. Orleans: 9th International Conference on Mechanical and Aerospace Engineering [C], 2018.
[5] Yan X, Jia M P. Compound Fault Diagnosis of Rotating Machinery Based on OVMD and a 1.5-dimension Envelope Spectrum [J]. Measurement Science
[6]Li L, Wang Z, Jiang H. Aero-engine abrupt failure prognosis based on multi-states MOG-HMM and Viterbi algorithm[J]. Journal of Vibration Measurement Diagnosis, 2014, 34(2): 310 -314.
[7] 逄珊,杨欣毅,张勇,等.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. Pang S, Yang X Y, Zhang Y, et al. Application of Deep Kernel Extreme Learning Machine in Aero Engine Components Fault Diagnosis [J]. Journal of Propulsion Technology, 2017, 38(11): 2613-2621.
[8] 李本威,林学森,杨欣毅,等.深度置信网络在发动机气路部件性能衰退故障诊断中的应用研究[J].推进技术,2016, 37(11): 2173-2180. Li B W, Lin X S, Yang X Y, et al. Research on Application of Deep Belief Networks on Engine Gas Path Component Performance Degradation Defect Diagnostics [J]. Journal of Propulsion Technology, 2016, 37(11): 2173-2180.
[9] 吕升,郭迎清,孙浩.基于GA-AANN神经网络的SDQ算法的航空发动机传感器数据预处理[J].推进技术, 2018, 39(5): 1142-1150. Lv S, Guo Y Q, Sun H. Aero-engine Sensor Data Preprocessing Based on SDQ Algorithm of GA-AANN Neural Network. Journal of Propulsion Technology[J]. 2018, 39(5): 1142-1150.
[10] Gou L F, Zhong Y. A New Fault Diagnosis Method Based on Attributes Weighted Neutrosophic Set [J]. IEEE ACCESS, 2019, 7: 117740-117748.
[11] 刘元芳. 航空发动机气路故障的智能诊断方法研究[D].厦门大学,2018.
[12] Huang Z K, Yang C H, Zhou X J et al. A Hybrid Feature Selection Method Based on Binary State Transition Algorithm and ReliefF [J]. IEEE journal of biomedical and health informatics, 2019,23(5): 1888-1898.
[13] 潘锋. 特征提取与特征选择技术研究[D].南京航空航天大学,2011.

基于ReliefF-LMBP算法的涡轴发动机气路故障模式识别—两机专刊

Gas path Fault Mode Identification of Turboshaft Engine Based on ReliefF-LMBP Algorithm

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价