Support Vector Regression Ensemble for Effective Modeling of Magnetic Ordering Temperature of Doped Manganite in Magnetic Refrigeration

Abstract

Magnetic refrigeration technology (MRT) is an affordable and efficient refrigeration system that can conveniently replace the present conventional gas compression and expansion (GCE) system of refrigeration. Apart from the fact that GCE refrigeration system has reached its thermodynamic limit and releases ozone depleting gases that is harmful to the environment, its non-compactness and lower energy efficiency are of serious concerns that remain unaddressed. Utilization of solid magnetic refrigerant in MRT aids its compactness and enhances environmental friendliness system of refrigeration. Manganite refrigerants have recently attracted attention from experimental and modeling perspectives due to its stability, cost-effectiveness as well as tunable magnetic properties as compared to the existing metal gadolinium refrigerant. However, magnetic ordering temperature of manganite refrigerants plays a crucial role in the implementation of MRT at ambient condition. Support vector regression (SVR) ensemble models with gravitational search algorithm (GSA) hyper-parameter optimization are hereby proposed for modeling the magnetic ordering temperature of manganite using ionic radii and dopant concentrations as descriptors. Ensemble model (EMS) developed using average of the outputs of five different SVR base estimators performs better than the ensemble model (EMM) developed using individual outputs without averaging with performance improvement of 25.4%. Similarly, EMS performs better than the conventional SVR-based model as well as GSA-optimized SVR-based model (GSVR). The proposed ensemble models also outperform other existing models in the literature. The results of this research work will not only serve to circumvent the experimental challenges of magnetic ordering temperature measurement but also further promotes environmental-friendly system of refrigeration.