Broad Multi-Parameter Dimensioning of Magnetocaloric Systems Using Statistical Learning Classifiers
authors Silva, DJ; Amaral, JS; Amaral, VS
nationality International
journal FRONTIERS IN ENERGY RESEARCH
author keywords magnetocaloric; machine learning; statistical method; caloric materials; dimensioning algorithm
keywords ACTIVE MAGNETIC REGENERATOR; MULTIOBJECTIVE OPTIMIZATION; TEMPERATURE SPAN; PYTHON FRAMEWORK; REFRIGERATION; PERFORMANCE; MODEL
abstract Prototyping innovative energy devices is a complex multivariable dimensioning problem. For the case of magnetocaloric systems, one aims to obtain an optimized balance between energy conversion performance, useful power generated, and power consumed. In these devices, modeling is entering a mature phase, but dimensioning is still time consuming. We have developed a technique that dimensions any type of magnetocaloric system by training statistical learning classifiers that are used to simulate the computation of a very large number of systems with different combinations of parameters to be dimensioned. We used this method in the dimensioning of a magnetocaloric heat pump aiming at optimizing the temperature span, heating power, and coefficient of performance, obtaining an f-score of 95%. The respective classifier was used to mimic over 940 thousand computed systems. The gain in computation time was 300 times that of computing numerically the system for each combination of parameters.
publisher FRONTIERS MEDIA SA
issn 2296-598X
year published 2020
volume 8
digital object identifier (doi) 10.3389/fenrg.2020.00121
web of science category Energy & Fuels
subject category Energy & Fuels
unique article identifier WOS:000548711000001
  ciceco authors
  impact metrics
journal analysis (jcr 2019):
journal impact factor 2.746
5 year journal impact factor Not Available
category normalized journal impact factor percentile 45.089
dimensions (citation analysis):
altmetrics (social interaction):



 


Apoio

1suponsers_list_ciceco.jpg