AI models for prediction of displacement and temperature in shape memory alloy (SMA) wire
| Autor: | Hari Narayan Bhargaw, Akshay Krishna Sheshadri, S. A. R. Hasmi, S. A. Akbar, Poonam Jangid, Samarth Singh, B. A. Botre |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
0209 industrial biotechnology
Artificial neural network Computer science 020208 electrical & electronic engineering Linear variable differential transformer 02 engineering and technology Shape-memory alloy SMA Smart material Displacement (vector) Nonlinear system 020901 industrial engineering & automation Control theory 0202 electrical engineering electronic engineering information engineering Actuator |
| Zdroj: | 4TH INTERNATIONAL CONFERENCE ON EMERGING TECHNOLOGIES; MICRO TO NANO, 2019: (ETMN 2019). |
| ISSN: | 0094-243X |
| DOI: | 10.1063/5.0043926 |
| Popis: | Shape Memory Alloys (SMAs) are a unique class of smart materials that have the ability to recover their shape on temperature stimuli. During this transformation, hysteresis and non-linear behavior can be observed and open-loop control design is inadequate for tracking control of these actuators. This is a major setback for the design and development of any SMA device. The main hurdle is that this nonlinearity cannot be modeled effectively even by 3rd degree differential equations. Additionally, the apparatus used for measurement of strain recovery during SMA actuation includes linear variable differential transducer (LVDT), which is rather bulky and expensive and does not let it fully utilize the potential of SMA applications in miniaturized devices. This research work presents a method to eliminate the bulky position sensor by introducing an Artificial Neural Networks (ANN) to compensate for the non-linearity. Various researchers have attempted to model the behavior of SMAs using ANN techniques but these models had a high RMS error. In this paper, a more complex neural network is developed to model SMA's behavior. This architecture models for (i) displacement prediction (ii) temperature prediction. The results of present research not only demonstrate the effectiveness of Neural Networks for prediction of displacement and temperature of the SMA but also show how the proposed architectures have a much lesser error as compared to earlier models and are much more effective at modeling SMAs. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|