A novel prediction model of frost growth on cold surface based on support vector machine

Cao, Zhikun; Han, Hongbin; Gu, Bin; Ren, Neng

doi:10.1016/j.applthermaleng.2008.11.015

Cited by 35 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the white noise having a much greater effect the prediction performance of the output targets than its effect on the input vectors [35], Gaussian noise targets (x) with standard deviation of s (s ¼ 0.04, 0.08) was added to each data point of the validation data set output. The effect of the addition of Gaussian noise on the prediction results is shown in Fig.…”

Section: Experimental Results For Gaussian Noisementioning

confidence: 99%

Modeling of variable speed refrigerated display cabinets based on adaptive support vector machine

Cao

Han

2010

Mechanical Systems and Signal Processing

Self Cite

View full text Add to dashboard Cite

Section: Experimental Results For Gaussian Noisementioning

confidence: 99%

Modeling of variable speed refrigerated display cabinets based on adaptive support vector machine

Cao

Han

2010

Mechanical Systems and Signal Processing

Self Cite

View full text Add to dashboard Cite

“…In the literature, a small number of intelligent techniques were used to approximate the thickness of the frost layer . The support vector machine (SVM) method was offered by Cao et al to model the thickness of the frost layer over the cold flat plates. Scientists proposed different intelligent methods, such as multiple linear regression, artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), , and least squares SVM to predict the hydrodynamic parameters of the CFD simulation cases. − They stated that the best results were obtained using the ANFIS method.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Nanofluid Characteristics and Flow Pattern on Artificial Differential Evolution Learning Nodes and Fuzzy Framework

et al. 2020

View full text Add to dashboard Cite

A combination of a fuzzy inference system (FIS) and a differential evolution (DE) algorithm, known as the differential evolution-based fuzzy inference system (DEFIS), is developed for the prediction of natural heat transfer in Cu–water nanofluid within a cavity. In the development of the hybrid model, the DE algorithm is used for the training process of FIS. For this purpose, first, the case study is simulated using the computational fluid dynamic (CFD) method. The CFD outputs, including velocity in the y -direction, the temperature of the nanofluid, and the nanoparticle content ( Ø ), are employed for the learning process of the DEFIS model. By choosing the optimum number of inputs and the number of population, the underlying DEFIS variable parameters are studied. After reaching the high value of DEFIS intelligence, in the learning step, a variety of Ø values (e.g., 0.5, 1, and 2) are reviewed. For the full intelligence of DEFIS, the velocity of the nanofluid is predicted in further nodes of the cavity domain. Finally, the velocity of the nanofluid is predicted by using the data at Ø = 0.15, which are absent in the DEFIS process.

show abstract

“…Mao et al [4] has pointed out some methods for measuring frost, Kmmati.AddchI et al [5] used frost mass to examine the frosting and defrosting, Yoon. Shinhyuk et al [6] studied frost thickness measurement and frost mass measurement, and there are other frost measurement study in the open literature [7][8][9]. Generally speaking, frost thickness is a key parameter in the study of frosting phenomenon and the technology of defrosting, especially in a small scale refrigeration experimental system.…”

Section: Introductionmentioning

confidence: 99%

Non-contact frost thickness measurement by using a micro-camera and image processing technology

Wang

Tao

Kang

et al. 2010

2010 IEEE International Conference on Mechatronics and Automation

View full text Add to dashboard Cite

Frost thickness is a key parameter to examine the effect of frosting or defrosting in refrigeration field, but frost thickness is not easy to measure through traditional methods for frost is soft and easily to be damaged by heat or pressure. Aim at the problem of frost thickness measurement, a measurement method based on a microscopic image system and image processing technology is brought forward, and the concept of bilateral frost thickness is proposed and explained. Experimental tests on the thickness of frost growing on the double sides of an aluminum sheet were carried out to clearly observe and record the dynamic growing process of tiny frost crystals. Experimental results show that the given measurement method does not undermine the patterns of frost during the whole frosting process, and it could observe frosting process easily, as well as measure the frost thickness with high accuracy. The given method is effective and it could be used to measure the growth of frost crystals and frost layer thickness on a cold surface, such as an aluminum sheet and a finned-tube evaporator.

show abstract

A novel prediction model of frost growth on cold surface based on support vector machine

Cited by 35 publications

References 17 publications

Modeling of variable speed refrigerated display cabinets based on adaptive support vector machine

Modeling of variable speed refrigerated display cabinets based on adaptive support vector machine

Prediction of Nanofluid Characteristics and Flow Pattern on Artificial Differential Evolution Learning Nodes and Fuzzy Framework

Non-contact frost thickness measurement by using a micro-camera and image processing technology

Contact Info

Product

Resources

About