基于储备池计算的电机系统混沌预测与同步研究

摘要
图/表
参考文献(20)
相关文章 (10)

全文: PDF (1776 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要已有的研究表明电机系统在某些参数及工作条件下会出现的混沌振荡，是电机运行失稳的重要因素之一。因此研究电机系统混沌预测,为及早提出保护措施,确保电机系统稳定运行具有重要意义。提出一种基于储备池计算的机器学方法对永磁同步电机(PMSM)的混沌行为进行预测,研究结果表明一个训练好的神经网络,即使在电机系统数学模型未知的情况下,只依据状态变量的时间序列数据也能预测系统的混沌行为,并且只需要通过一个状态变量就能够实现受训神经网络与电机系统之间的混沌同步。此外，该方法对外界环境扰动具有鲁棒性。以永磁同步电动机为例,利用数值仿真验证了该方法的有效性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	陈豪昌
	韦笃取

关键词 ：永磁同步电动机(PMSM), 储备池计算网络, 混沌同步, 混沌预测

Abstract：

The existing literature shows that a motor system will appear chaotic oscillation when their systemic parameters fall into a certain area or under some operating conditions, which can lead to the instability and the collapse of the system.Therefore, it is of great significance to study the chaos prediction and make a protection measure to ensure the stable operation of the motor system.The paper proposed a mechanical method based on reservoir computing to predict the chaotic behavior of a permanent magnet synchronous motor (PMSM).The research results show that even if the mathematical model of the motor system under the condition is unknown, a trained neural network can predict chaotic behavior of the motor system only based on time series data of state variables.It was also found that reservoir computing can realize chaos synchronization between the trained neural network and the motor system by sending just a single variable.In addition, the method is robust to external environmental disturbances.Lastly, taking the permanent magnet synchronous motor as an example, the effectiveness of the proposed method was verfied by means of numerical simulation.

Key words： permanent magnet synchronous motor(PMSM) reservoir computing network chaotic synchronization chaos prediction

收稿日期: 2020-04-23 出版日期: 2021-08-28

引用本文:

陈豪昌,韦笃取. 基于储备池计算的电机系统混沌预测与同步研究[J]. 振动与冲击, 2021, 40(16): 199-203.
CHEN Haochang,WEI Duqu . Chaos prediction and synchronization of a motor system based on reservoir computing. JOURNAL OF VIBRATION AND SHOCK, 2021, 40(16): 199-203.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2021/V40/I16/199

［1］梅春草, 韦笃取.基于时间加权反馈控制的永磁同步风力发电机混沌振荡研究［J］.振动与冲击, 2020, 39(2):79-86.
MEI Chuncao, WEI Duqu.Chaos control in permanent magnet synchronous generators based on time-weighted feedback control［J］.Journal of Vibration and Shock, 2020, 39(2):79-86.

［2］XUE W, ZHANG M, LIU S, et al.Mechanical analysis and ultimate boundary estimation of the chaotic permanent magnet synchronous motor［J］.Journal of the Franklin Institute, 2019, 356(10): 5378-5394.

［3］牛治东, 吴光强.电动汽车混沌振动信号的小波神经网络预测［J］.振动与冲击, 2018, 37(8): 120-124.
NIU Zhidong, WU Guangqiang.Wavelet neural network prediction of electric vehicle chaotic vibration signals［J］.Journal of Vibration and Shock, 2018, 37(8): 120-124.

［4］张春涛, 马千里, 彭宏.基于信息熵优化相空间重构参数的混沌时间序列预测［J］.物理学报, 2016,59 (11):7623-7629.
ZHANG Chuntao, MA Qianli, PENG Hong.Chaotic time series prediction based on information entropy optimized parameters of phase space reconstruction ［J］.Acta Physica Sinica, 2016, 59(11):7623-7629.

［5］QIN T, WU K L, XIU D B.Data driven governing equations approximation using deep neural networks［J］.Journal of Computational Physics, 2019,395: 620-635.

［6］XIONG Y C, ZHAO H.Chaotic time series prediction based on long short-term memory neural networks［J］.Scientia Sinica: Physica,Mechanica & Astronomica, 2019, 49(12): 120501.

［7］HEIDARI A A, FARIS H, ALJARAH I, et al.An efficient hybrid multilayer perceptron neural network with grasshopper optimization［J］.Soft Computing, 2019,23(17): 7941-7958.

［8］LI K J, XIE X M, XUE W P, et al.Hybrid teaching learning artificial neural network for city-level electrical load prediction［J］.Science China: Information Sciences, 2020, 63(5): 159204.

［9］KONG W C, DONG Z Y, JIA Y W.Short-term residential load forecasting based on lstm recurrent neural network［J］.IEEE Trans Smart Grid, 2017, 10(1): 841-851.

［10］MOON S H, KIM Y H, LEE Y H, et al.Application of machine learning to an early warning system for very short-term heavy rainfall［J］.Journal of Hydrology, 2019, 568: 1042-1054.

［11］LYMBURN T, KHOR A, STEMLER T, et al.Consistency in echo-state networks［J］.Chaos, 2019, 29(2): 023118.

［12］LU Z X, HUNT B R, EDWARD O.Attractor reconstruction by machine learning［J］.Chaos, 2018, 28(6): 061104.

［13］PATHAK J, HUNT B, GIRVAN M, et al.Model-free prediction of large spatiotemporally chaotic systems from data: a reservoir computing approach［J］.Physical Review Letters, 2018, 120(2): 024102.

［14］JAEGER H.The “echo state” approach to analysing and training recurrent neural networks［R］.Bonn: German National Research Center for Information Technology, 2001.

［15］MAASS W, NATSCHLGER T, MARKRAM H.Real-time computing without stable states: a new framework for neural computation based on perturbations［J］.Neural Computation, 2002, 14(11): 2531-2560.

［16］WENG T F, YANG H J, GU C G, et al.Synchronization of chaotic systems and their machine-learning models［J］.Physical Review.E:Statistical Physics Plasmas Fluids & Related Interdisciplinary Topics, 2019, 99(4): 042203.

［17］CARROLL T L.Using reservoir computers to distinguish chaotic signals［J］.Physical Review.E: Statistical Physics Plasmas Fluids & Related Interdisciplinary Topics, 2018, 98(5): 52209.

［18］JAEGER H, HAAS H.Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication［J］.Science, 2004, 304(5667): 78-80.

［19］钟国翔,韦笃取,张波.永磁同步电机系统、网络混沌振荡同步中断分析与控制［J］. 振动与冲击, 2020, 39(7): 8-14.
ZHONG Guoxiang, WEI Duqu, ZHANG Bo.Analysis and control of interruption of chaotic synchronization in permanent magnet synchronous motor system and network［J］.Journal of Vibration and Shock, 2020, 39(7): 8-14.

［20］李健昌,韦笃取,罗晓曙,等.混沌电机自适应时滞同步控制研究［J］.振动与冲击, 2014, 33(16):105-108.
LI Jianchang, WEI Duqu, LUO Xiaoshu, et al.Research on adaptive time-delay synchronization control of chaotic motor ［J］.Journal of Vibration and Shock, 2014, 33 (16): 105-108.