Please wait a minute...
浙江大学学报(工学版)
J4  2013, Vol. 47 Issue (12): 2188-2194    DOI: 10.3785/j.issn.1008973X.2013.12.018
航空、航天     
基于仿真数据的旋翼系统故障识别
杨茂, 李小龙
西北工业大学 航天学院,陕西 西安 710072
Rotor system fault diagnosis based on simulation data
YANG Mao, LI Xiao-long
School of Astronautics, Northwestern Polytechnical University, Xi’an 710072, China
 全文: PDF  HTML
摘要：

采用广义回归神经网络（GRNN）对3种直升机旋翼故障（配平调整片误调、变距拉杆误调、质量不平衡）进行识别.采用三层网络分别识别旋翼故障的类型、位置和程度.网络训练集和测试集采用基于耦合的旋翼机身仿真结果（包含故障旋翼响应、桨毂载荷、机身振动水平）.为提高网络泛化能力,在仿真结果中添加了噪声.结果表明：1）训练好的GRNN能从包含噪声的直升机响应中对故障做出识别,使用仿真数据训练的GRNN可用于旋翼健康和使用监测系统(HUMS)的开发；2)使用包含噪声的数据训练网络能显著提升GRNN的泛化能力；3）合理选择网络扩展常数对于预测准确性非常重要.
Abstract:

General regression neural network (GRNN) was used to diagnose three types of rotor system faults,namely,misadjusted trimtab,misadjusted pitch control rod, and imbalanced mass. Three cascaded levels of networks were used to identify fault type, location, and extend,respectively. Simulation results, which include faulty rotor responses, hub loads, and fuselage vibration, from a coupled rotorfuselage analytical model were used for training and testing. Artificial noises were added to simulation data to enhance network generality. Results show that: 1) trained GRNN is capable of diagnosing faults from noisy helicopter responses, which indicating the feasibility of simulation datatrained GRNN being used in rotor health and usage monitoring system (HUMS) development; 2) using noiseadded training data can significantly improve GRNN’s generality; 3) properly selecting the spread of network is important for fault diagnosis accuracy.
出版日期: 2013-12-01
:  V 275.1  
作者简介: 杨茂（1973—），男，副教授，从事旋翼动力学方面研究.E-mail: yang_mao@nwpu.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

杨茂, 李小龙. 基于仿真数据的旋翼系统故障识别[J]. J4, 2013, 47(12): 2188-2194.

YANG Mao, LI Xiao-long. Rotor system fault diagnosis based on simulation data. J4, 2013, 47(12): 2188-2194.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008973X.2013.12.018    或    http://www.zjujournals.com/eng/CN/Y2013/V47/I12/2188

［1］ PAWAR P M, GANGULI R. Helicopter rotor health monitoring-a review ［J］. Journal of Aerospace Engineering,2007, 221(G): 631-647.

［2］ 史峰,王辉,郁磊,等, Matlab神经网络30个案例分析［M］.北京：北京航空航天大学出版社,2009: 73-80.

［3］ 刘红梅,王少萍,欧阳平超.基于GRNN网络和遗传算法的旋翼动平衡调整［J］.北京航空航天大学学报,2008, 34(5): 507-511.

LIU Hong-mei, WANG Shao-ping, QUYANG Ping-chao. Helicopter rotor smoothing based on GRNN neural network and genetic algorithm ［J］. Journal

of Beijing University of Aeronautics and Astronautics, 2008, 34(5): 507-511.

［4］ HAAS D J, SCHAEFER C G Jr. Emerging technologies for rotor system health monitoring ［C］∥ Proceedings of the 52nd Annual Forum of the

American Helicopter Society. Washington, D.C: AHS International, 1996: 1717-1731.

［5］ 高亚东,邓升平.基于支持向量机的直升机旋翼不平衡故障分类研究［J］.南京航空航天大学学报,2011,43(3): 435-438.

GAO Ya-dong, DENG Sheng-ping. Unbalance fault identification of helicopter rotor using support vector machine［J］. Journal of Nanjing

University of Aeronautics & Astronautics, 2011, 43(3): 435-438.

［6］ 高亚东,张曾昌.直升机旋翼不平衡故障诊断试验研究［J］.振动、测试与诊断,2009,29 (2): 214-217.

GAO Ya-dong, ZHANG Zeng-chang. Experimental study on unbalance fault diagnosis of helicopter rotor ［J］.Journal of Vibration, Measurement &

Diagnosis, 2009, 29(2): 214-217.

［7］ YANG M, CHOPRA I, HAAS D J. Vibration prediction for a rotor system with faults using coupled rotor-fuselage Model ［J］.Journal of

Aircraft, 2004, 41(2): 348-358.

［8］ GANGULI R, CHOPRA I. Helicopter rotor system fault detection using physics-based model and neural networks ［J］.AIAA Journal, 1998,

36(6): 1078-1086.

［9］ REDDY R K, GANGULI R. Structural damage detection in a helicopter rotor blade using radial basis function neural networks ［J］.Smart

Materials & Structures, 2003, 12(2): 232-241.

［10］ PAWAR P M, GANGULI R. Fuzzy-logic-based health monitoring and residual-life prediction for composite helicopter rotor ［J］.Journal of

Aircraft, 2007, 44(3)： 981-995.

［11］ 边肇祺,张学工.模式识别 ［M］.2版.北京：清华大学出版社,2000: 72-80.
No related articles found!