A Comparative Study of Predictive Models for Nafion-117 IPMC Soft Actuators
- 12 July 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1124-1129
Abstract
Ionic polymer-metal composites are electro-active soft actuators that, when stimulated by an electric field, convert electrical energy into mechanical energy. This study focuses on an ionic polymer-metal composite soft actuator that has been realized with Nafion-117 and platinum electrodes. Three black-box models, i.e., curve fitting, multi-layer perceptron, and long short-term memory recurrent neural network, are designed based on the forces exerted by the soft actuator at fixed displacements when stimulated by different voltages. The capability of the three black-box models to predict unseen forces is evaluated and compared. This study shows that the multi-layer perceptron has the best predictive capability in capturing the dynamics of unseen force data, with a root mean square error of 0.109 mN and computation time of $13 \mu \mathrm{s}$
Keywords
Funding Information
- European Commission
This publication has 16 references indexed in Scilit:
- Nonlinear identification of IPMC actuators based on ANFIS–NARX paradigmSensors and Actuators A: Physical, 2014
- Recent advances in ionic polymer–metal composite actuators and their modeling and applicationsProgress in Polymer Science, 2013
- Ionic electroactive polymer metal composites: Fabricating, modeling, and applications of postsilicon smart devicesJournal of Polymer Science Part B: Polymer Physics, 2013
- Design and Verification of a Non-linear Black-Box Model for Ionic Polymer Metal Composite ActuatorsJournal of Intelligent Material Systems and Structures, 2011
- A Distributed Model of Ionomeric Polymer Metal CompositeJournal of Intelligent Material Systems and Structures, 2009
- Numerical Analysis of Muscle-Like Ionic Polymer ActuatorsBiotechnology Progress, 2006
- Ionic polymer–metal composites: IV. Industrial and medical applicationsSmart Materials and Structures, 2004
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1992
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- The Levenberg-Marquardt algorithm: Implementation and theory1978