Differential resistance based self-sensing recurrent neural network model for position estimation and control of antagonistic Shape Memory Alloy actuator
- 19 October 2021
- journal article
- research article
- Published by IOP Publishing in Engineering Research Express
- Vol. 3 (4), 045018
- https://doi.org/10.1088/2631-8695/ac310d
Abstract
The paper presents the development and experimental investigation of recurrent neural network (RNN) based self-sensing position estimation (SSPE) model for shape memory alloy actuator (SMA). RNN used as an estimator in position feedback control loop to replace the external additional position sensor. The model was inspired from the physics-based analogy of Mass-Spring-Damper (MSD) system for antagonistic SMA wire actuator. Actuator displacement presents the hysteresis and non-linear dynamic relationship with observed differential resistance (sensing signal) during phase transformation. The resistance variation causes due to dissimilar resistivity between primary phases of SMA material. The RNN based estimation model was considered because it consists of memory element for storing the processed information and feedback connections for dynamic modelling of system. RNN was trained with input sensing signal and target displacement datasets. Estimation accuracy of model was real time evaluated during trajectory tracking of reference signals in feedback control loop. A quantitative performance analysis is assessed in terms of correlation (), mean absolute error (MEA), and root mean square error (RSME) of learned model along with developed actuator system. The tracking results confirm the close agreement between estimated and measured displacement at reasonable accuracy.Keywords
This publication has 26 references indexed in Scilit:
- Thermo-electric behaviour of NiTi shape memory alloyTransactions of Nonferrous Metals Society of China, 2013
- Modeling of the electrical resistance of shape memory alloy wiresSmart Materials and Structures, 2010
- Hysteretic recurrent neural networks: a tool for modeling hysteretic materials and systemsSmart Materials and Structures, 2009
- Micro actuators on the basis of thin SMA foilsMicrosystem Technologies, 2008
- An enhanced SMA phenomenological model: II. The experimental studySmart Materials and Structures, 2005
- Differential Hysteresis Modeling of a Shape Memory Alloy Wire ActuatorIEEE/ASME Transactions on Mechatronics, 2005
- Position control of shape memory alloy actuators with internal electrical resistance feedback using neural networksSmart Materials and Structures, 2004
- Dynamic process modeling with recurrent neural networksAIChE Journal, 1993
- One-Dimensional Constitutive Behavior of Shape Memory Alloys: Thermomechanical Derivation with Non-Constant Material Functions and Redefined Martensite Internal VariableJournal of Intelligent Material Systems and Structures, 1993
- One-Dimensional Thermomechanical Constitutive Relations for Shape Memory MaterialsJournal of Intelligent Material Systems and Structures, 1990