Piezoelectric ceramics control model based on neural network

Yunpeng Tan; Zhihao Yuan; Jianjun Lai

doi:10.1117/12.2585470

4 December 2020 Piezoelectric ceramics control model based on neural network

Yunpeng Tan, Zhihao Yuan, Jianjun Lai

Proceedings Volume 11617, International Conference on Optoelectronic and Microelectronic Technology and Application; 116173J (2020) https://doi.org/10.1117/12.2585470
Event: International Conference on Optoelectronic and Microelectronic Technology and Application, 2020, Nanjing, China

Abstract

Devices driven by piezoelectric actuators has many advantages such as easy control, fast response speed and high availability. But piezoelectric actuators have unavoidable nonlinear problems to the spreading of piezoelectric-actuator-drive optoelectronic devices when we need a linear mapping relationship of voltage-to-displacement in many situations. Many ways have been tried to solve this problem, many models like Preisach model and Polynomial model have a bad robustness when facing up with different voltage and the piezoelectric actuator’s displacement. Based on convolutional neural network, we put up with a new way to fix the hysteresis problem by building fine neural network structure, which can learn many features of piezoelectric actuators’ electromagnetic properties and mechanical properties. Combined with other classic algorithm of system control such as PID algorithm, we bring up with universal framework for piezoelectric-actuator-driven devices, especially FabryPerot interferometer(FPI). Researchers can use our solutions to build their optic-mechanical-electric systems quickly without spending too many time on coding and system control.

Citation Download Citation

Yunpeng Tan, Zhihao Yuan, and Jianjun Lai "Piezoelectric ceramics control model based on neural network", Proc. SPIE 11617, International Conference on Optoelectronic and Microelectronic Technology and Application, 116173J (4 December 2020); https://doi.org/10.1117/12.2585470

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available