2016
DOI: 10.1007/s40430-016-0698-0
|View full text |Cite
|
Sign up to set email alerts
|

Multi-objective optimization of asymmetric v-shaped ribs in a cooling channel using CFD, artificial neural networks and genetic algorithms

Abstract: List of symbols A Area of both top and bottom walls (m 2) B Channel width (m) c p Constant pressure specific heat (kJ kg −1 K −1) D Channel height (m) D h Channel hydraulic diameter (m) f Friction factor f 0 Friction factor obtained from Petukhov's empirical correlation H Rib height (m) k Fluid thermal conductivity (W m −1 K −1) Nu Local Nusselt number Nu s Nusselt number obtained from the Dittus-Boelter correlation Pi Rib pitch (m) p, p Pressure and pressure drop in a channel, respectively (Pa) p Periodic com… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
7

Relationship

0
7

Authors

Journals

citations
Cited by 16 publications
(2 citation statements)
references
References 25 publications
0
2
0
Order By: Relevance
“…Convolutional neural networks were first applied to image data, and later researchers found that they can also achieve good results on text data. Especially in the case of large datasets, text features can be extracted more fully and the feature dimension can be reduced [ 15 , 16 ]. The convolutional neural network consists of a convolutional layer, pooling layers, and a fully connected layer, as shown in Figure 7 .…”
Section: Deep Learning Methods Based On the Passing Methodsmentioning
confidence: 99%
“…Convolutional neural networks were first applied to image data, and later researchers found that they can also achieve good results on text data. Especially in the case of large datasets, text features can be extracted more fully and the feature dimension can be reduced [ 15 , 16 ]. The convolutional neural network consists of a convolutional layer, pooling layers, and a fully connected layer, as shown in Figure 7 .…”
Section: Deep Learning Methods Based On the Passing Methodsmentioning
confidence: 99%
“…They are now widely used in the structural design process. [36][37][38][39][40][41] It is a robust global optimization algorithm that does not require gradient information and does not easily fall into a local optimum. In addition, it is not constrained by the continuity of design variables and does not require a starting point at the beginning of the optimization process.…”
Section: Multi-island Genetic Optimization Algorithmmentioning
confidence: 99%