基于对抗生成网络的滑动轴承支撑转子动平衡
Balancing of Sliding Bearing Supported Rotor Based on Generative Adversarial Network
DOI: 10.12677/OJAV.2020.82009, PDF,    国家自然科学基金支持
作者: 曹俊灵, 钟 顺*, 龙 菲：天津大学力学系，天津；韩佳杰, 王 超：河北瑞兆激光再制造股份有限公司，河北 唐山
关键词: 动平衡；转子系统；对抗生成网络；Dynamic Balancing； Rotor System； Generative Adversarial Network
摘要: 转子动平衡是转子系统检修和出厂所必要的基本步骤。本文基于对抗生成网络的思想旨在解决转子测试信号数量较少特征单一的问题，将神经网络技术应用于转子动平衡过程中。结果表明，利用生成数据进行训练的神经网络可有效的预测不平衡大小和位置，进行动平衡，特别是对于非线性支撑的转子系统，神经网络动平衡的效果要优于传统线性方法(影响系数法)。
Abstract: Rotor balancing is a basic step for maintenance and delivery of rotor systems. Based on the adversarial generative network, we try to solve the limitation of the small quantity and monotony of the data, and apply neural network technology to the rotor balancing process. The results show that using the generated data, the neural network can effectively predict the size and position of the imbalance. Especially for the nonlinearly supported rotor system, the neural network dynamic balancing is better than the traditional linear method (influence coefficient method).
文章引用：曹俊灵, 钟顺, 龙菲, 韩佳杰, 王超. 基于对抗生成网络的滑动轴承支撑转子动平衡[J]. 声学与振动, 2020, 8(2): 66-76. https://doi.org/10.12677/OJAV.2020.82009

参考文献

[1] 蒋剑. 基于深度卷积神经网络的旋转机械复合故障诊断方法研究[D]: [硕士学位论文]. 徐州: 中国矿业大学, 2019.
[2] Zhang, Z.X., Zhang, Q., Li, X.L. and Qian, T.L. (2011) The Whole-Beat Correlation Method for the Identi-fication of an Unbalance Response of a Dual-Rotor System with a Slight Rotating Speed Difference. Mechanical Systems and Signal Processing, 25, 1667-1673. [Google Scholar] [CrossRef] 
[3] Zhang, Z.X., Wang, L.Z., Jin, Z.J., Zhang, Q. and Li, X.L. (2013) Non-Whole Beat Correlation Method for the Identification of an Unbalance Re-sponse of a Dual-Rotor System with a Slight Rotating Speed Difference. Mechanical Systems and Signal Processing, 39, 452-460. [Google Scholar] [CrossRef] 
[4] Yue, C., Ren, X., Yang, Y. and Deng, W. (2015) Un-balance Identification of Speed-Variant Rotary Machinery without Phase Angle Measurement. Shock and Vibration, 2015, Article ID: 934231. [Google Scholar] [CrossRef] 
[5] Pennacchi, P., Vania, A. and Bachschmid, N. (2007) Increasing the Robustness of Fault Identification in Rotor Dynamics by Means of M-Estimators. Mechanical Systems and Signal Processing, 21, 3003-3029. [Google Scholar] [CrossRef] 
[6] Sudhakar, G.N.D.S. and Sekhar, A.S. (2011) Identification of Unbalance in a Rotor Bearing System. Journal of Sound and Vibration, 330, 2299-2313. [Google Scholar] [CrossRef] 
[7] 徐宾刚, 屈梁生, 孙瑞祥. 基于影响系数法的柔性转子无试重平衡法研究[J]. 西安交通大学学报, 2000(7): 63-67.
[8] 肖健. 先进控制技术在主动平衡系统中的研究与应用[D]: [硕士学位论文]. 北京: 北京化工大学, 2008.
[9] Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., et al. (2014) Generative Adversarial Nets. Proceedings of the 27th International Conference on Neural Information Processing Sys-tems, Montreal, 8-13 December 2014, Article ID: 26722680.
[10] 余萍, 曹洁. 深度学习在故障诊断与预测中的应用[J/OL]. 计算机工程与应用, 1-25.
[11] Jeffcott, H.H. (1919) The Lateral Vibration of Loaded Shafts in the Neigh-bourhood of a Whirling Speed. Philosophy Magazine, 6, 304-314. [Google Scholar] [CrossRef] 
[12] Hsieh, S.C., Chen, J.H. and Lee, A.C. (2006) A Modified Transfer Matrix Method for the Coupling Lateral and Torsional Vibrations of Symmetric Rotor-Bearing Systems. Jour-nal of Sound and Vibration, 289, 294-333. [Google Scholar] [CrossRef] 
[13] Homer, G.G. and Pilkey, W.D. (1978) The Riccati Transfer Matrix Method. ASME Journal of Mechanical Design, 100, 297-302. [Google Scholar] [CrossRef] 
[14] Cao, Y.Z. and Altintas, Y. (2004) A General Method for the Modeling of Spindle-Bearing Systems. Journal of Mechanical Design, 126, 1089-1104. [Google Scholar] [CrossRef] 
[15] Capone, G. (1991) Analytical Description of Flu-id-Dynamic Force Field in Cylindrical Journal Bearing. L’energia Elettrica, 3, 105-110.

为你推荐