Optimization of characteristics of an array of thin fins using PSO algorithm in confined cavities heated from a side with free convection

Azimifar, A.; Payan, S.

doi:10.1016/j.applthermaleng.2016.08.012

Cited by 22 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whatever boosting or bagging, the key problem in ensemble learning is to find a suitable strategy to get a strong classifier, such as meaning and voting [25]. For radar signal, there are no complete data sets can be trained by ensemble learning, intelligent algorithm is a considerable method to get optimal results, particle swarm optimization algorithm (PSO) [26] and artificial bee colony algorithm (ABC) [27] are two classical intelligent algorithms, which can be applied as the strategy of ensemble learning.…”

Section: Introductionmentioning

confidence: 99%

A Radar Signal Recognition System Based on Non-Negative Matrix Factorization Network and Improved Artificial Bee Colony Algorithm

Gao

et al. 2019

IEEE Access

View full text Add to dashboard Cite

The development of cognitive radio and electronic warfare brings new challenges to radar electronic reconnaissance, the recognition of radar signal plays an extreme important role in radar electronic reconnaissance. In order to realize the reliable recognition of radar signal at the condition of low signalto-noise ratio (SNR), we propose a new radar signal recognition system based on non-negative matrix factorization network (NMFN) and ensemble learning, which can recognize radar signals including BPSK, LFM, NLFM, COSTAS, FRANK, P1, P2, P3 and P4. First, we explore feature extractor based on convolutional neural network (CNN), which applies transfer learning to solve the problem of small sample size. Second, we propose non-negative matrix factorization network to extract features, which can reduce the redundant information. Third, we develop feature fusion algorithm based on stacked autoencoder (SAE), which can acquire essential expression of features and reduce dimension of features. Finally, we propose improved artificial bee colony algorithm (IABC) as the strategy of ensemble learning, which can improve the recognition rate. The simulation results show that the recognition rates reach 94.23% at −4 dB, 99.82% at 6 dB. INDEX TERMS Radar signal recognition, non-negative matrix factorization network, transfer learning, feature fusion, improved artificial bee colony algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%

A Radar Signal Recognition System Based on Non-Negative Matrix Factorization Network and Improved Artificial Bee Colony Algorithm

Gao

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…They found that the thickness of fins does not affect the heat transfer rate, significantly; however, increasing the fin length results in increasing the heat transfer rate. To optimize the characteristics of applied fins using the PSO algorithm, Azimifar and Payan (2017) analyzed the natural convection in a finned cavity heated from one side. They found that applying optimal thin fins can reduce the heat transfer from the cavity wall up to 8 per cent.…”

Section: Introductionmentioning

confidence: 99%

Natural convection from heated fin shapes in a nanofluid-filled porous cavity using incompressible smoothed particle hydrodynamics

Aly

Raizah

Asai

2019

HFF

View full text Add to dashboard Cite

Purpose This study aims to focus on the numerical simulation of natural convection from heated novel fin shapes in a cavity filled with nanofluid and saturated with a partial layer of porous medium using improved incompressible smoothed particle hydrodynamics (ISPH) method. Design/methodology/approach The dimensionless of Lagrangian description for the governing equations were numerically solved using improved ISPH method. The current ISPH method was improved in term of wall boundary treatment by using renormalization kernel function. The effects of different novel heated (Tree, T, H, V, and Z) fin shapes, Rayleigh number Ra(103 – 106 ), porous height Hp (0.2-0.6), Darcy parameter Da(10−5 − 10−1 ) and solid volume fraction ϕ(0.0-0.05) on the heat transfer of nanofluid have been investigated. Findings The results showed that the variation on the heated novel fin shapes gives a suitable choice for enhancement heat transfer inside multi-layer porous cavity. Among all fin shapes, the H-fin shape causes the maximum stream function and Z-fin shape causes the highest value of average Nusselt number. The concentrations of the fluid flows in the nanofluid region depend on the Rayleigh and Darcy parameters. In addition, the penetrations of the fluid flows through porous layers are affected by porous heights and Darcy parameter. Originality/value Natural convection from novel heated fins in a cavity filled with nanofluid and saturated with a partial layer of porous medium have been investigated numerically using improved ISPH method.

show abstract

“…It was shown that the heat transfer is a function of the Rayleigh number and the fin positions. Azimifar and Payan [30] analyzed the natural convection in a finned cavity heated from one side. They found that applying optimal thin fins reduces the heat transfer at the cavity wall up to 8%.…”

Section: Introductionmentioning

confidence: 99%

“…• A system of equations is performed for the hybrid nanofluid and another one is presented for the dusty phase. Under all the above assumptions, the governing equations (continuity, momentum and energy equations for both the hybrid nanofluid and dusty phases) are expressed as follows; see [7,24,29,30]: Under all the above assumptions, the governing equations (continuity, momentum and energy equations for both the hybrid nanofluid and dusty phases) are expressed as follows; see [7,24,29,30]:…”

mentioning

confidence: 99%

Natural Convection of Dusty Hybrid Nanofluids in an Enclosure Including Two Oriented Heated Fins

Raizah

2019

Applied Sciences

View full text Add to dashboard Cite

In the current work, the natural convection of dusty hybrid nanofluids in an enclosure including two inclined heated fins has been studied via mathematical simulation. The inclined heated fins are arranged near to the enclosure center with variations on their orientations and lengths. The present simulation is represented by two systems of equations for the hybrid nanofluids that are dusty. The pressure distributions for the dusty phase and hybrid nanofluids phase are evaluated using a SIMPLE algorithm based on the finite volume method. The numerical results are examined using contours of the streamlines, isotherms for the hybrid nanofluids and velocity components for the dusty phase. In addition, the graphical illustrations for profiles of the local and average Nusselt numbers are presented. The main results reveal that an increase in the mixture densities ratio and dusty parameter reduces the rate of the heat transfer. Both the local and average Nusselt numbers are supported as the fins lengths increase regardless of the fins’ rotation. In addition, the nanoparticles volume fraction enhances the thermal boundary layer near the top wall.

show abstract

Optimization of characteristics of an array of thin fins using PSO algorithm in confined cavities heated from a side with free convection

Cited by 22 publications

References 33 publications

A Radar Signal Recognition System Based on Non-Negative Matrix Factorization Network and Improved Artificial Bee Colony Algorithm

A Radar Signal Recognition System Based on Non-Negative Matrix Factorization Network and Improved Artificial Bee Colony Algorithm

Natural convection from heated fin shapes in a nanofluid-filled porous cavity using incompressible smoothed particle hydrodynamics

Natural Convection of Dusty Hybrid Nanofluids in an Enclosure Including Two Oriented Heated Fins

Contact Info

Product

Resources

About