An interpretable Dahl-LRN neural-network for accurately modelling the systems with rate-dependent asymmetric hysteresis

被引:0
作者
Ni, Lei [1 ,2 ]
Wang, Hongfei [1 ,2 ]
Chen, Guoqiang [3 ]
Zhang, Lanqiang [4 ]
Yao, Na [5 ]
Wang, Geng [1 ,2 ]
机构
[1] Southwest Univ Sci & Technol, Key Lab Testing Technol Mfg Proc Minist Educ, Mianyang 621010, Peoples R China
[2] Southwest Univ Sci & Technol, Tianfu Inst Res & Innovat, Chengdu 610299, Peoples R China
[3] Henan Polytech Univ, Sch Mech & Power Engn, Jiaozuo 454000, Peoples R China
[4] Chinese Acad Sci, Natl Lab Adapt Opt, Chengdu 610209, Peoples R China
[5] Univ Elect Sci & Technol China, Sch Aeronaut & Astronaut, Chengdu 610054, Peoples R China
关键词
Piezoelectric actuator; Rate-dependent hysteresis; Interpretability; Dahl model; Layered recurrent neural network; PIEZOELECTRIC ACTUATORS; IDENTIFICATION; COMPENSATION; DESIGN;
D O I
10.1016/j.asoc.2025.112936
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The motion accuracy and stability of piezoelectric positioning systems are significantly compromised by inherent hysteresis and other nonlinearities. This paper presents an innovative method integrating the Dahl model with Layer Recurrent Neural Networks (LRN) to model piezoelectric actuators accurately. Initially, the Dahl model is reformulated into a neural network structure, resulting in the Dahl Neural Network (DahlNN), which strictly adheres to the underlying mathematical equations. The weights of this network directly correspond to the parameters of the Dahl equations, thereby creating a transparent neural network architecture with clear physical significance and interpretability. Subsequently, the DahlNN is enhanced by incorporating feedback mechanisms and recurrent effects from LRN, improving its ability to describe asymmetric and rate-dependent hysteresis characteristics. Extensive experiments demonstrate that, compared to LRN models without physical knowledge guidance, the proposed Dahl-LRN model reduces peak-to-valley fluctuations by 70 % and decreases the average error by approximately 97.3 %, with only a 5 % increase in computational time while maintaining interpretability and achieving superior modelling performance. Through this approach, this paper aims to provide a novel perspective on leveraging physical information to advance the application of deep learning in modelling complex physical phenomena.
引用
收藏
页数:22
相关论文
共 107 条
[1]   Modeling and Identification of Rate Dependent Hysteresis in Piezoelectric Actuated Nano-Stage: A Gray Box Neural Network Based Approach [J].
Ahmed, Khubab ;
Yan, Peng .
IEEE ACCESS, 2021, 9 :65440-65448
[2]  
Amos B, 2017, PR MACH LEARN RES, V70
[3]   Physics-informed recurrent neural networks and hyper-parameter optimization for dynamic process systems [J].
Asrav, Tuse ;
Aydin, Erdal .
COMPUTERS & CHEMICAL ENGINEERING, 2023, 173
[4]   Nonlinear Circuit Macromodeling Using New Heterogeneous-Layered Deep Clockwork Recurrent Neural Network [J].
Azodi, Maedeh ;
Sadrossadat, Sayed Alireza ;
Savaria, Yvon .
IEEE ACCESS, 2024, 12 :89506-89519
[5]   Precision Motion Control of a Piezoelectric Actuator via a Modified Preisach Hysteresis Model and Two-Degree-of-Freedom H-Infinity Robust Control [J].
Baziyad, Ayad G. ;
Ahmad, Irfan ;
Bin Salamah, Yasser .
MICROMACHINES, 2023, 14 (06)
[6]   Inverse parameter identifications and forward strip temperature simulations of the continuous annealing line with physics-informed neural network and operation big data [J].
Chen, Kai ;
Dai, Mingyang ;
Xu, Lei ;
Xu, Songjiang ;
Xie, Xin ;
Hu, Xiaoguang ;
Huang, Feng ;
Zhang, Heming .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 127
[7]   Fuzzy-Based Adaptive Reliable Motion Control of a Piezoelectric Nanopositioning System [J].
Chen, Liheng ;
Xu, Qingsong .
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2024, 32 (08) :4413-4425
[8]   Hysteresis modeling and tracking control for piezoelectric stack actuators using neural-Preisach model [J].
Chen, Yuansheng ;
Huang, Qinbin ;
Wang, Hao ;
Qiu, Jinhao .
INTERNATIONAL JOURNAL OF APPLIED ELECTROMAGNETICS AND MECHANICS, 2019, 61 (03) :445-459
[9]   AT-PINN: Advanced time-marching physics-informed neural network for structural vibration analysis [J].
Chen, Zhaolin ;
Lai, Siu-Kai ;
Yang, Zhichun .
THIN-WALLED STRUCTURES, 2024, 196
[10]   A modified direct inverse Prandtl-Ishlinskii model based on two sets of operators for the piezoelectric actuator hysteresis compensation [J].
Cheng, Liqun ;
Chen, Wanzhong ;
Tian, Liguo .
INTERNATIONAL JOURNAL OF APPLIED ELECTROMAGNETICS AND MECHANICS, 2022, 68 (02) :177-191