Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
February 2, 2026Advanced Intelligent SystemsOpen Access

A Neural Network‐Based Self‐Sensing Embedded Position Control System for Shape Memory Alloy Wire Actuators

View Full Paper
Ask AI
Bookmark
Share

Authors

KKKrunal Jagdishbhai KoshiyaGRGianluca RizzelloIHIng Hau

Discussion

Loading...

Member takes

Overview

Artificial intelligence enables accurate self-sensing position control in shape memory alloy actuators, indicating improved performance.

Key Points

  • The aim is to develop an artificial intelligence-based system for accurate self-sensing in shape memory alloy actuators.
  • Developed a neural network combining recurrent and simple neurons.
  • Used electrical power and SMA wire's resistance as inputs for real-time position estimation.
  • Implemented the neural network on a microcontroller for embedded control.
  • Achieved root mean squared errors of 0.028 and 0.021 mm in position estimation.
  • Validated accuracy against a sensor-based control system using a 2 mm displacement range.

Cite This Study

Koshiya et al. (2026) studied this question.

synapsesocial.com/papers/6980fde8c1c9540dea80fa57https://doi.org/10.1002/aisy.202501204
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Resistance Feedback for miniaturization of Shape Memory Alloys actuators2024 · 1 citations
  2. 2Resistance Feedback for miniaturization of Shape Memory Alloys actuators2024 · 1 citations
  3. 3<scp>Electro‐thermo‐mechanical</scp> characterization of shape memory alloy wires for actuator and sensor applications—Part 1: The effects of training2024 · 10 citations
  4. 4Resistance Feedback of a Ni-Ti Alloy Actuator at Room Temperature in Still Air2024 · 3 citations
  5. 5Performance analysis of position sensorless control of antagonistic shape memory alloy actuators2024 · 2 citations