Predictions of Electromotive Force of Magnetic Shape Memory Alloy (MSMA) Using Constitutive Model and Generalized Regression Neural Network

TL;DR

This paper combines an enhanced constitutive magneto-mechanical model with a generalized regression neural network to predict the electromotive force of Ni-Mn-Ga MSMAs, improving accuracy over traditional models.

Contribution

It introduces a new feature to the existing model accounting for magnetic easy axis offset and integrates a neural network for better prediction accuracy.

Findings

Model predictions align reasonably with experimental data.

Neural network improves prediction accuracy.

Magnetic easy axis offset explains power harvesting capabilities.

Abstract

Ferromagnetic shape memory alloys (MSMAs), such as Ni-Mn-Ga single crystals, can exhibit the shape memory effect due to an applied magnetic field at room temperature. Under a variable magnetic field and a constant bias stress loading, MSMAs have been used for actuation applications. This work introduced a new feature to the existing macroscale magneto-mechanical model for Ni-Mn-Ga single crystal. This model includes the fact that the magnetic easy axis in the two variants is not exactly perpendicular as observed by D silva et al. This offset helps explain some of the power harvesting capabilities of MSMAs. Model predictions are compared to experimental data collected on a Ni-Mn-Ga single crystal. The experiments include both stress-controlled loading with constant bias magnetic field load (which mimics power harvesting or sensing) and fieldcontrolled loading with constant bias compressive stress (which mimics actuation). Each type of test was performed at several different load levels, and the applied field was measured without the MSMA specimen present so that demagnetization does not affect the experimentally measured field as suggested by Eberle et al. Results show decent agreement between model predictions and experimental data. Although the model predicts experimental results decently, it does not capture all the features of the experimental data. In order to capture all the experimental features, finally, a generalized regression neural network (GRNN) was used to train the experimental data (stress, strain, magnetic field, and emf) so that it can make a reasonably better prediction.