Intelligent computing approaches to forecast thickness and surface roughness of frost layer on horizontal plates under natural convection
Created by W.Langdon from
gp-bibliography.bib Revision:1.8081
- @Article{MORADKHANI:2022:applthermaleng,
-
author = "M. A. Moradkhani and S. H. Hosseini and
Lei Shangwen and Song Mengjie",
-
title = "Intelligent computing approaches to forecast thickness
and surface roughness of frost layer on horizontal
plates under natural convection",
-
journal = "Applied Thermal Engineering",
-
volume = "217",
-
pages = "119258",
-
year = "2022",
-
ISSN = "1359-4311",
-
DOI = "doi:10.1016/j.applthermaleng.2022.119258",
-
URL = "https://www.sciencedirect.com/science/article/pii/S1359431122011887",
-
keywords = "genetic algorithms, genetic programming, Frost
thickness, Frost surface roughness, Machine learning,
Horizontal plates, Natural convection",
-
abstract = "There is no existing predictive model for frost layer
thickness and surface roughness on horizontal cold
plates under the natural convection conditions.
Accordingly, intelligent approaches were designed based
upon 782 data for frost thickness and 191 data for
frost surface roughness, which covered four stages of
frosting process. Three machine learning methods of
multilayer perceptron (MLP), Gaussian process
regression (GPR), and radial basis function (RBF) were
employed to design the predictive models for frost
characteristics over horizontal cold plates in the
natural convection environment. For the frost
thickness, although almost all models provided
excellent outputs, the RBF based model showed the
highest accuracy with average absolute relative error
(AARE) and coefficient of determination (R2) values of
1.23percent and 99.93percent, respectively, for the
tested data. The RBF based model presented the superior
results for frost surface roughness with an AARE of
1.21percent for all analyzed data. The proposed
predictive methods were capable of predicting the
impact of surface temperature on the frost
characteristics at various stages of the process. A
statistical analysis of earlier correlations revealed
large deviations from the measured data caused by the
differences in operating conditions. Thus, new explicit
correlations were developed using the intelligent
method of genetic programming, which showed the AAREs
of 4.61percent and 16.72percent for frost thickness and
frost surface roughness, respectively",
- }
Genetic Programming entries for
Mohammad Amin Moradkhani
Seyyed Hossein Hosseini
Lei Shangwen
Song Mengjie
Citations