概率神经网络用于机匣振动故障诊断

摘要: 对机匣振动加速度信号进行采集与分析是航空发动机振动故障诊断的重要方法。对振动信号进行处理与特征提取后，可以利用神经网络非线性映射的能力，对振动故障实现分类。利用转子-轴承-机匣耦合振动实验台模拟了5种风扇机匣的振动故障，从频谱的初步分析中并未能够实现对故障的准确判断。对振动数据进行了处理，提取了振动波形的频域与幅域参数，采用概率神经网络的方法实现单一故障的分类，并对不同参数所训练的网络进行了比较，检验了该诊断方法对于机匣振动故障的可行性。
- 风扇机匣 /
- 振动加速度 /
- 概率神经网络 /
- 故障诊断
Abstract: The acquisition and analysis of casing's acceleration vibration signal is a significant method to realize aero-engine's fault diagnosis. Neural networks can classify vibration faults with their strong nonlinear mapping ability. 5 different types of fan casing vibration faults are simulated on the rotor-bearing-casing coupled vibration experiment system. Accurate judgment of faults can't gain from the preliminary analysis of signal's frequency spectrum. Single fault is classified from faults by probabilistic neural networks (PNN) using vibration data's frequency and amplitude domain parameters. Methods with different parameters are compared and the feasibility of PNN using in casing vibration fault diagnosis is tested.
- fan casing /
- acceleration /
- vibration analysis /
- probabilistic neural networks

HTML全文

参考文献(15)

[1]	邓明,金业壮.航空发动机故障诊断[M].北京:北京航空航天大学出版社,2012 Deng M, Jin Y Z. Aeroengine fault diagnosis[M]. Beijing: Beihang University Press, 2012 (in Chinese)
[2]	史忠植.神经网络[M].北京:高等教育出版社,2009 Shi Z Z. Neural networks[M]. Beijing: Higher Education Press, 2009 (in Chinese)
[3]	Hoffman A J, van der Merwe N T. The application of neural networks to vibrational diagnostics for multiple fault conditions[J]. Computer Standards ＆ Interfaces, 2002,24(2):139-149
[4]	Chen G. Study on the recognition of aero-engine blade-casing rubbing fault based on the casing vibration acceleration[J]. Measurement, 2015,65:71-80
[5]	陈果,李成刚,王德友.航空发动机转子-滚动轴承-支承-机匣耦合系统的碰摩故障分析与验证[J].航空动力学报,2008,23(7):1304-1311 Chen G, Li C G, Wang D Y. Nonlinear dynamic analysis and experiment verification of rubbing faults of rotor-ball bearing-support-stator coupling system for aero-engine[J]. Journal of Aerospace Power, 2008,23(7):1304-1311 (in Chinese)
[6]	姜广义,王娟,姜睿.航空发动机风扇机匣振动故障分析[J].航空发动机,2011,37(5):38-40,44 Jiang G Y, Wang J, Jiang R. Aeroengine fan casing vibration fault analysis[J]. Aeroengine, 2011,37(5):38-40,44 (in Chinese)
[7]	王树兰,刘金南.某航空发动机风扇机匣振动故障诊断[C]//2010航空试验测试技术峰交会论文集.上海:中国航空学会,2010 Wang S L, Liu J N. The vibration fault diagnosis for the aeroengine fan case[C]//Aviation Test Technology Symposium. Shanghai: China Aviation Society, 2010 (in Chinese)
[8]	党相懿.机匣振动故障模拟实验和特征提取方法研究[D].北京:清华大学,2014 Dang X Y. Experimental faults simulation of casing and study on features extraction of casing virbration signals[D]. Beijing: Tsinghua University, 2014 (in Chinese)
[9]	李东文,熊晓燕,李博.振动加速度信号处理探讨[J].机电工程技术,2008,37(9):50-52 Li D W, Xiong X Y, Li B. Research on the processing of vibration acceleration signal[J]. Mechanical ＆ Electrical Engineering Technology, 2008,37(9):50-52 (in Chinese)
[10]	叶志锋,孙健国.基于概率神经网络的发动机故障诊断[J].航空学报,2002,23(2):155-157 Ye Z F, Sun J G. Probabilistic neural networks based engine fault diagnosis[J]. Acta Aeronautica et Astronautica Sinica, 2002,23(2):155-157 (in Chinese)
[11]	王仲民,周鹏,李充宁.基于改进概率神经网络的滚动轴承故障诊断[J].机械科学与技术,2013,32(5):729-732 Wang Z M, Zhou P, Li C N. Fault diagnosis of roller bearing based on an improved probabilistic neural network[J]. Mechanical Science and Technology for Aerospace Engineering, 2013,32(5):729-732 (in Chinese)
[12]	Samarasinghe S. Neural networks for applied sciences and engineering: from fundamentals to complex pattern recognition[M]. Boca Raton, FL: CRC Press, 2006
[13]	何正嘉.机械故障诊断理论及应用[M].北京:高等教育出版社,2010 He Z J. Theories and applications of machinery fault diagnostics[M]. Beijing: Higher Education Press, 2010 (in Chinese)
[14]	张德丰.MATLAB神经网络应用设计[M].机械工业出版社,2009 Zhang D F. MATLAB neural network design[M]. China Machine Press, 2009 (in Chinese)
[15]	韩捷,张瑞林.旋转机械故障机理及诊断技术[M].北京:机械工业出版社,1997 Han J, Zhang R L. Fault mechanism and diagnosis technology of rotating machinery[M]. Beijing: China Machine Press, 1997 (in Chinese)