BEGIN:VCALENDAR
METHOD:PUBLISH
PRODID:www-matsim-tf-fau-de//Events//EN
VERSION:2.0
BEGIN:VEVENT
SUMMARY:Computationally Efficient Torque Estimation in SMA Microactuat
 ion Systems: A Neural Network Surrogate Trained on Parametric FEM Data
  - Rundong Jia
UID:9bf4f881-a60a-4438-9c0d-60d2e39074e5
DESCRIPTION:Rundong Jia WW8\, FAU 21. Juni 2025\, 17:00 WW8\, Fürth T
 he design of complex micro-origami systems actuated by bi-directional 
 Shape Memory Alloy (SMA) components is a significant challenge\, often
  hindered by the high computational cost of traditional Finite Element
  Method (FEM) simulations for parametric design space exploration. Thi
 s thesis presents a neural network (NN) surrogate model which predicts
  the non-linear torque-angle characteristics of SMA self-bending micro
 actuators with significantly lower computational cost. A comprehensive
  parametric dataset was first generated using a validated FEM framewor
 k in Abaqus\, which employed a UMAT subroutine to capture the thermo-m
 echanical behavior of NiTi actuators. The study systematically varied 
 key geometric parameters (bending radius\, width\, thickness) and oper
 ational conditions (maximum bending angle for passive loading-release\
 , temperature for active actuation). Subsequently\, a feedforward neur
 al network was trained on this dataset to map the input parameters to 
 the resulting torque curves for both passive (antagonist) and active (
 protagonist) modes. The results demonstrate that the trained NN achiev
 es excellent predictive accuracy while preserving good robustness. Spe
 cific case studies further verify that the surrogate model replicates 
 well the non-linear torque-angle curves for both the martensite loadin
 g-release and the austenite actuation processes. The validated neural 
 network serves as a surrogate model\, enabling rapid and accurate perf
 ormance prediction. Crucially\, by intersecting the predicted torque c
 urves of the antagonist and protagonist\, the equilibrium point of the
  actuated bi-directional system can be determined\, allowing for the d
 irect prediction of the balance angle for any given parameter configur
 ation without new FEM simulations. This work provides a powerful frame
 work for accelerating the design\, system-level optimization\, and rap
 id exploration of the vast parameter space for advanc
DTSTART:20250618T150000Z
DTEND:20250618T160000Z
LOCATION:WW8\, Room 2.018-2\, Dr.-Mack-Str. 77\, Fürth
DTSTAMP:20260427T014306Z
END:VEVENT
END:VCALENDAR