Application of deep convolution neural network in chaotic vibration identification
TANG Yusi1, WANG Weihao1, CUI Hanguo1, LIU Shuyong1, CHAI Kai2
1.College of Power Engineering, Naval University of Engineering, Wuhan 430033, China;
2.College of Naval Architecture and Ocean, Naval University of Engineering, Wuhan 430033, China
Abstract:In recognition of chaotic vibration signals, the calculation amount of chaotic characteristic index is large and time-consuming, so it is difficult to meet the real-time requirements. Here, an intelligent chaotic recognition method based on deep convolution neural network was proposed. Firstly, attractor graphs of different vibration signals were obtained using the phase space reconstruction technique. Then, structural parameters of the classic network model AlexNet were optimized and trained. Finally, the improved model was applied in intelligent recognition of chaotic signals. The results of simulated and actually measured signals showed that the proposed method is feasible, it can provide a useful reference for on-line chaos recognition.
唐宇思1,王伟豪1,崔汉国1,刘树勇1,柴凯2. 深度卷积神经网络在混沌振动识别中的应用研究[J]. 振动与冲击, 2021, 40(13): 9-15.
TANG Yusi1, WANG Weihao1, CUI Hanguo1, LIU Shuyong1, CHAI Kai2. Application of deep convolution neural network in chaotic vibration identification. JOURNAL OF VIBRATION AND SHOCK, 2021, 40(13): 9-15.
[1]ROBINSON C. Phase plane analysis using the Poincaré map[J]. Nonlinear Analysis, 1985, 9(11): 1159-1164.
[2]MCDONOUGH P V, NOONAN J P, HALL G R. A new chaos detector[J]. Computers Elect Engng, 1995, 21(6): 417-431.
[3]廖明,张文明,方湄,等. 时间序列分形特征的判别[J]. 北京科技大学学报,1998,20(5):412-416.
LIAO Ming, ZHANG Wenming, FANG Mei, et al. Discrimination of fractal characteristics of time series[J]. Journal of University of Science and Technology Beijing, 1998, 20(5): 412-416.
[4]任辉,裴承鸣. 基于LVQ神经网络的混沌时间序列分类识别[J]. 机械科学与技术,2001,20(6):797.
REN Hui, PEI Chengming. Classification and recognition of chaotic time series based on LVQ neural network[J]. Mechanical Science and Technology for Aerospace Engineering, 2001, 20(6): 797.
[5]江亚东,吴竹青,陈因颀,等. 一种基于小波网络的混沌时间序列判定[J]. 北京科技大学学报,2002,24(3):295-298.
JIANG Yadong, WU Zhuqing, CHEN Yinqi, et al. Chaos time series determination based on wavelet network[J].
Journal of University of Science and Technology Beijing, 2002, 24(3): 295-298.
[6]XIE H, WANG Z, HUANG H. Identification determinism in time series based on symplectic geometry spectra[J]. Physics Letters A, 2005, 342(1): 156-161.
[7]席剑辉,魏茹,韩敏. EKF在多变量混沌序列辨识中的应用[J]. 系统仿真学报,2006,18(9):2525-2529.
XI Jianhui, WEI Ru, HAN Min. Application of EKF on identification of multivariate chaotic time series[J]. Journal of System Simulation, 2006, 18(9): 2525-2529.
[8]RAWAT W, WANG Z. Deep convolutional neural networks for image classification: a comprehensive review[J]. Neural Computation, 2017, 29(9): 2352-2449.
[9]FUKUSHIMA K. Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J]. Biological Cybernetics, 1980, 36(4): 193-202.
[10]PACKARD N H, CRUTCHFIELD J P, FARMER J D, et al. Geometry from a time series[J]. Physical Review Letters, 1980, 45(9): 712-715.
[11]KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems 25. New York: Curran Associates, Inc., 2012.
[12]SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout: a simple way to prevent neural networks from overfitting[J]. The Journal of Machine Learning Research, 2014, 15(1): 1929-1958.
[13]KINGMA D P, BA J. Adam: a method for stochastic optimization[C]//International Conference on Learning Representations. Ithaca, NY: ICLR, 2015.
[14]FRASER A M, SWINNEY H L. Independent coordinates for strange attractors from mutual information[J]. Physical Review A: General Physics, 1986, 33(2): 1134-1140.
[15]刘树勇,位秀雷,王基,等. 基于双势阱系统的混沌振动研究[J]. 振动与冲击,2017,36(24):23-29.
LIU Shuyong, WEI Xiulei, WANG Ji, et al. Chaotic vibration study based on two-well potential theory[J]. Journal of Vibration and Shock, 2017, 36(24): 23-29.