DEEP LEARNING FOR IDENTIFYING HYSTERESIS MODELS OF PIEZOCERAMIC ACTUATORS IN THE LINEAR FRAME

被引:1
作者
Qi, Xue [1 ,2 ]
Shi, Wei-jia [1 ,2 ]
Zhao, Bo [1 ,2 ]
Tan, Jiu-bin [1 ,2 ]
机构
[1] Harbin Inst Technol, Ctr Ultraprecis Optoelect Instrument Engn, Harbin 150080, Peoples R China
[2] Harbin Inst Technol, Minist Ind & Informat Technol, Key Lab Ultraprecis Intelligent Instrumentat, Harbin 150080, Peoples R China
来源
PROCEEDINGS OF THE 2019 14TH SYMPOSIUM ON PIEZOELECTRCITY, ACOUSTIC WAVES AND DEVICE APPLICATIONS (SPAWDA19) | 2019年
关键词
Piezoceramic actuators; Precision positioning; Preisach model; Neural networks; IDENTIFICATION;
D O I
10.1109/spawda48812.2019.9019229
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
Piezoceramic actuators have been already applied in precision positioning in terms of simple and compact structure, free from noise, and high theoretical positioning resolution. However, the hysteresis characteristic limits the further improvement of positioning accuracy. Nowadays neural networks (NNs) have revolutionized progress in the identification and global linearization tasks, which makes it potential to employ deep learning in identifying hysteresis model of piezoceramic actuators in the linear frame. This paper aims at achieving the identification of the hysteresis model by means of NNs. Based on the Preisach model, datasets are obtained in Matlab. Identification of nonlinear coordinates is accomplished by the auto-encoder afterwards. As a result, weights of the various network branches are computed. Comparing the hysteresis model displacement output with the NNs reconstruction, it is found that the curves are basically consistent. The experimental results confirm the correctness of this method, which is of great significance for analysis and control of nonlinear systems.
引用
收藏
页码:106 / 111
页数:6
相关论文
共 23 条
[1]   Using neural networks in the identification of Preisach-type hysteresis models [J].
Adly, AA ;
Abd-El-Hafiz, SK .
IEEE TRANSACTIONS ON MAGNETICS, 1998, 34 (03) :629-635
[2]  
[Anonymous], 2017, DEEP LEARNING UNIVER
[3]  
Dawson DM, 1992, SE CON 92 P IEEE IEE
[4]   Hysteresis characteristics of piezoelectric ceramic actuators [J].
Fan W. ;
Lin Y.-Y. ;
Li Z.-S. .
Guangxue Jingmi Gongcheng/Optics and Precision Engineering, 2016, 24 (05) :1112-1117
[5]   Oxidation Behaviour and Mechansim of MoSi2-CrSi2-SiC-Si Coating for Carbon/Carbon Composites from Room Temperature to 1873 K [J].
Feng, Tao ;
Li, He-Jun ;
Hu, Man-Hong ;
Li, Lu .
2015 THE 4TH INTERNATIONAL CONFERENCE ON MATERIAL SCIENCE AND ENGINEERING TECHNOLOGY (ICMSET 2015), 2015, 30
[6]   Dual-Stage Vertical Feedback for High-Speed Scanning Probe Microscopy [J].
Fleming, Andrew J. .
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2011, 19 (01) :156-165
[7]  
Guckenheimer J., 1983, Nonlinear Oscillations, Dynamical Systems and Bifurcations of Vector Fields, V1st edn
[8]   A harmonic piecewise linearisation-wavelet transforms method for identification of non-linear vibration "black box" systems: Application in wind-induced vibration of a high-rise building [J].
Huang, Dongmei ;
Zhu, Ledong ;
Ren, Weixin ;
Ding, Quanshun .
JOURNAL OF FLUIDS AND STRUCTURES, 2018, 78 :239-262
[9]   Modeling of nonlinear system based on deep learning framework [J].
Jin, Xiangjun ;
Shao, Jie ;
Zhang, Xin ;
An, Wenwei ;
Malekian, Reza .
NONLINEAR DYNAMICS, 2016, 84 (03) :1327-1340
[10]   CONSTRUCTING NARMAX MODELS USING ARMAX MODELS [J].
JOHANSEN, TA ;
FOSS, BA .
INTERNATIONAL JOURNAL OF CONTROL, 1993, 58 (05) :1125-1153