多跨转子系统多频传递力变步长神经网络控制

doi:10.3901/JME.2021.04.010

机械工程学报 ›› 2021, Vol. 57 ›› Issue (4): 10-20.doi: 10.3901/JME.2021.04.010

扫码分享

多跨转子系统多频传递力变步长神经网络控制

王金健, 徐晖, 祝长生

浙江大学电气工程学院杭州 310058

收稿日期:2020-02-04 修回日期:2020-07-03 出版日期:2021-02-20 发布日期:2021-04-28
通讯作者: 祝长生(通信作者),男,1963年出生,教授,博士研究生导师。主要研究方向为转子系统动力学、高速电机及飞轮储能等。E-mail:zhu_zhang@zju.edu.cn
作者简介:王金健,男,1995年出生。主要研究方向为转子传递力主动控制。E-mail:21810143@zju.edu.cn
基金资助:
国家自然科学基金（11632015）和国家重点研发计划（2018YF0905500）资助项目。

Variable-step Neural Network Control for Multi-frequency Transmission Forces of Multi-span Rotor Systems

WANG Jinjian, XU Hui, ZHU Changsheng

College of Electrical Engineering, Zhejiang University, Hangzhou 310058

Received:2020-02-04 Revised:2020-07-03 Online:2021-02-20 Published:2021-04-28

摘要/Abstract

摘要： 转子在旋转过程中，转子上的各种激励力会通过轴承传递给基础，从而导致基础的振动。为了抑制多频传递力，提出一种基于跟踪滤波后轴颈位移和传递力误差信号的变步长神经网络算法。设计一种集电磁执行器与固定瓦滑动轴承于一体的混合支承结构，并建立其动力学模型。用有限元法建立多跨转子系统的动力学模型，分析传递力控制的基本原理，采用离散跟踪微分器和状态观测器分别解决位移信号夹杂白噪声不易微分和传感器与执行器不同位时执行器位置处轴颈位移的重构问题。提出一种能够抑制多跨转子系统多频传递力的变步长神经网络算法。以一个四轴承二跨转子系统的仿真模型为例进行仿真分析，对所提出的变步长神经网络算法抑制双跨转子系统传递力的有效性进行了验证。结果表明，变步长神经网络算法能够有效地抑制转子系统对基础的多频传递力。

关键词: 多跨转子, 电磁执行器, 跟踪微分器, 状态观测器, 自适应变步长, 神经网络

Abstract: When the rotor system is in operation, the vibration of the base will be caused by the rotor’s multi-frequency excitation forces which transmitted to the base through support bearings. A variable-step neural network algorithm based on tracking filtered journal displacements and transmission forces error signals is proposed to suppress the multi-frequency transmission forces. Firstly, a hybrid bearing integrating electromagnetic actuator and journal bearing is designed and its dynamic model is established. Secondly, the dynamic model of a multi-span rotors system is built by the finite element method, and the theoretical principle of reducing the transmission forces is analyzed. The discrete tracking differentiator and the state observer are used to solve the problem that the displacement signal is not easy to differentiate with white noise and reconstruction of the journal displacement at the actuator position when the sensor and actuator are non-collocated. Then a variable-step neural network algorithm for suppressing the multi-frequency transmission forces from the multi-span rotor system is proposed. Finally, numerical simulations are carried out in a four-bearing double-span rotor system to verify the effectiveness of variable-step neural network algorithm for suppressing the multi-frequency transmission forces from the rotor system to the base. The simulation results show that the variable-step neural network algorithm can effectively suppress the multi-frequency transmission forces from the rotor system to the base.

Key words: multi-span rotors, electromagnetic actuator, tracking filter, state observer, active variable-step, neural network

中图分类号:

TG156

王金健, 徐晖, 祝长生. 多跨转子系统多频传递力变步长神经网络控制[J]. 机械工程学报, 2021, 57(4): 10-20.

WANG Jinjian, XU Hui, ZHU Changsheng. Variable-step Neural Network Control for Multi-frequency Transmission Forces of Multi-span Rotor Systems[J]. Journal of Mechanical Engineering, 2021, 57(4): 10-20.

参考文献

[1] HERZOG R,BUHLER P,GAHLER C,et al. Unbalance compensation using generalized notch filters in the multivariable feedback of magnetic bearings[J]. IEEE Transactions on Control Systems Technology,1996,4(5):580-586.
[2] DARBANDI S M,BEHZAD M,SALARIEH H,et al. Harmonic disturbance attenuation in a three-pole active magnetic bearing test rig using a modified notch filter[J]. Journal of Vibration and Control,2017,23(5):770-781.
[3] PENG C,SUN J,MIAO C,et al. A novel cross-feedback notch filter for synchronous vibration suppression of an MSFW with significant gyroscopic effects[J]. IEEE Transactions on Industrial Electronics,2017,64(9):7181-7190.
[4] PENG C,ZHU M,WANG K,et al. A two-stage synchronous vibration control for magnetically suspended rotor system in the full speed range[J]. IEEE Transactions on Industrial Electronics,2020,67(1):480-489.
[5] 毛川,祝长生. 主动电磁轴承-刚性转子系统实时变步长迭代不平衡补偿[J]. 中国电机工程学报,2018,38(13):3960-3968.Mao Chuan,Zhu Changsheng. A real-time variable step size iterative unbalance compensation for active magnetic bearing-rigid rotor systems[J]. Proceedings of the CSEE,2018,38(13):3960-3968.
[6] Mystkowski A. µ-Synthesis control of flexible modes of AMB rotor[C]//Conference on Smart Materials,Adaptive Structures and Intelligent Systems,September 21-23,2009,Oxnard,California. ASME,2009:357-363.
[7] Noshadi A,Zolfagharian A. Unbalance and harmonic disturbance attenuation of a flexible shaft with active magnetic bearings[J]. Mechanical Systems and Signal Processing,2019,129:614-628.
[8] Sahinkaya M,Hadi A,Keogh P S,et al. Experiments on the transient performance of an adaptive multi-objective controller for rotating machinery[J]. Journal of Engineering for Gas Turbines and Power,2010,133(2):022503.1-022503.7.
[9] Chen Q,Liu G,Han B C. Unbalance vibration suppression for AMBs system using adaptive notch filter[J]. Mechanical Systems and Signal Processing,2017,93:136-150.
[10] 毛川,祝长生. 电磁轴承-刚性转子系统轴承传递力主动控制[J]. 机械工程学报,2019,55(19):35-42. MAO Chuan,ZHU Changsheng. Active control of bearing force transmissibility for active magnetic bearing-rigid rotor systems[J]. Journal of Mechanical Engineering,2019,55(19):35-42.
[11] Heidari H,SAFARPOUR P. Optimal design of support parameters for minimum force transmissibility of a flexible rotor based on H_∞ and H₂ optimization methods[J]. Engineering optimization,2018,50(4):671-683.
[12] Zheng S Q,Han B C,Feng R,et al. Vibration suppression control for AMB supported motor driveline system using synchronous rotating frame transformation[J]. IEEE Transactions on Industrial Electronics,2015,62(9):5700-5708.
[13] 汤恩琼,房建成,郑世强. 磁悬浮电动机柔性转子振动控制与试验研究[J]. 机械工程学报,2015,51(1):106-116. TANG Enqiong,FANG Jiancheng,ZHENG Shiqiang. Vibration control and experimental study of flexible rotor in magnetically suspended motor[J]. Journal of Mechanical Engineering,2015,51(1):106-116.
[14] Heindel S,Becker F,Rinderknecht S. Unbalance and resonance elimination with active bearing on a Jeffcott rotor[J]. Mechanical System and Signal Processing,2017,85:339-353.
[15] Heindel S,Müller P C,Rinderknecht S. Unbalance and resonance elimination with active bearing on general rotors[J]. Journal of Sound and Vibration,2017:422-440.
[16] ZAPOMEL J,FERFECKI P,FORTE P. analysis of the steady state unbalance response of rigid rotors on magnetorheological dampers:stability, force transmission and energy dissipation[J]. International Journal of Applied Mechanics,2014,6(3):14500022.
[17] 韩京清. 自抗扰控制技术[M],北京:国防工业出版社,2018:69-71. Han Jingqing. Auto disturbances rejection control technique[M]. Beijing:National Defense Industry Press,2018:69-71.
[18] Gosiewski Z,Kulesza Z. Virtual collocation of sensors and actuators for a flexible rotor supported by active magnetic bearings[C]//International Carpathian Control Conference,May,26-29,2013,Rytro,Poland. IEEE,2013:94-99.
[19] Kulesza Z. Virtual collocation method for a flexible rotor supported by active magnetic bearings[J]. Journal of Vibration and Control,2015,21(8):1522-1538.
[20] Jeng J T,Lee T T. Control of magnetic bearing systems via the Chebyshev polynomial-based unified model (CPBUM) neural network[J]. IEEE Transactions on Systems,Man,and Cybernetics,2000,30(1):85-92.
[21] Chen S C,Nguyen V S,Le D K. An online trained adaptive neural network controller for an active magnetic bearing system[C]//International Symposium on Computer,Consumer and Control,June 10-12,2014,Taiwan,China:IEEE,2014:741-744.

多跨转子系统多频传递力变步长神经网络控制

Variable-step Neural Network Control for Multi-frequency Transmission Forces of Multi-span Rotor Systems

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	郑杰, 权伟, 刘洋, 卢学民, 刘晓红, 岳雅楠, 周腾, 蔡振兵. Cr/Zr涂层环向压缩表面裂纹识别研究[J]. 机械工程学报, 2024, 60(8): 1-10.
[2]	刘占广, 张云, 刘晴雨. 基于差分融合长短期记忆神经网络数控机床热误差建模[J]. 机械工程学报, 2024, 60(7): 249-257.
[3]	狄子钧, 袁东风, 李东阳, 梁道君, 周晓天, 信苗苗, 曹凤, 雷腾飞. 基于多尺度-高效通道注意力网络的刀具故障诊断方法[J]. 机械工程学报, 2024, 60(6): 82-90.
[4]	王俊玖, 刘金玉, 侯秀娟, 齐振国, 李志敏, 刘涛. 列车车体柔性装配精度预测的力学-数据混合建模方法[J]. 机械工程学报, 2024, 60(6): 177-186.
[5]	李春凯, 王嘉昕, 石玗, 代悦. GTAW熔池激光条纹动态行为与熔透预测方法研究[J]. 机械工程学报, 2024, 60(6): 236-244.
[6]	周宁, 姚建勇, 邓文翔. 基于神经网络的比例伺服阀阀芯液动力补偿鲁棒智能控制[J]. 机械工程学报, 2024, 60(4): 126-133.
[7]	王丹丹, 黄伟迪, 张军辉, 赵守军, 于斌, 刘施镐, 吕飞, 苏琦, 徐兵. 基于边缘计算的轴向柱塞泵磨损状态辨识方法研究[J]. 机械工程学报, 2024, 60(4): 189-199.
[8]	张昊, 魏超, 胡纪滨, 陈泳丹. 基于转向模式切换的三轴独立转向车辆路径跟踪控制研究[J]. 机械工程学报, 2024, 60(2): 243-251.
[9]	段书用, 杨建华, 韩旭, 刘桂荣. 高维数据自适应降维方法[J]. 机械工程学报, 2024, 60(17): 283-296.
[10]	刘建琴, 胡桂菘, 乔金丽, 郭晓. 基于双路神经网络的TBM实时性能预测研究[J]. 机械工程学报, 2024, 60(16): 43-53.
[11]	胡伟飞, 廖家乐, 郭云飞, 鄢继铨, 李光, 岳海峰, 谭建荣. 基于物理信息神经网络的时变可靠性分析方法[J]. 机械工程学报, 2024, 60(13): 141-153.
[12]	张德权, 李星奥, 张宁, 宁国松, 韩旭. 工业机器人全域误差场精细化建模方法及其误差补偿策略[J]. 机械工程学报, 2024, 60(13): 316-329.
[13]	王俊, 杨轶青, 刘金朝, 沈长青, 黄伟国, 朱忠奎. 小波核编码的脉冲卷积神经网络在可解释性智能诊断中的应用研究[J]. 机械工程学报, 2024, 60(12): 41-50.
[14]	袁静, 任港星, 蒋会明, 赵倩, 魏臣隽, 朱骏. 基于多元提升核神经网络的机械故障诊断方法及其特征提取可解释性研究[J]. 机械工程学报, 2024, 60(12): 51-64.
[15]	陈钱, 陈康康, 董兴建, 皇甫一樊, 彭志科, 孟光. 一种面向机械设备故障诊断的可解释卷积神经网络[J]. 机械工程学报, 2024, 60(12): 65-76.