Neural network modeling and model predictive control of ionic electroactive polymer actuators

Sunjai Nakshatharan; Andres Punning; Alvo Aabloo

doi:10.1117/12.2218728

15 April 2016 Neural network modeling and model predictive control of ionic electroactive polymer actuators

Sunjai Nakshatharan, Andres Punning, Alvo Aabloo

Proceedings Volume 9798, Electroactive Polymer Actuators and Devices (EAPAD) 2016; 97982J (2016) https://doi.org/10.1117/12.2218728
Event: SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring, 2016, Las Vegas, Nevada, United States

Abstract

This work reports on the modelling and control of ionic electroactive polymer actuators with electrodes based on nanoporous carbon, which are working in ambient environment. The model incorporates the humidity level value as one of the input parameters, and so captures the environment-dependent dynamics of the actuator. The effect of ambient humidity on the actuators is studied through the frequency response analysis and is followed by neural network method of modelling. A closed loop set point tracking control system based on gain scheduled model predictive control is designed and developed for position control of actuator and is verified experimentally. The developed model and controller is capable to predict and control the actuators at under the humidity conditions varying in the range of 3% - 97%.

Conference Presentation

Citation Download Citation

Sunjai Nakshatharan, Andres Punning, and Alvo Aabloo "Neural network modeling and model predictive control of ionic electroactive polymer actuators", Proc. SPIE 9798, Electroactive Polymer Actuators and Devices (EAPAD) 2016, 97982J (15 April 2016); https://doi.org/10.1117/12.2218728

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