Neural network optimization by comparing the performances of the training functions -Prediction of heat transfer from horizontal tube immersed in gas–solid fluidized bed

Kamble, L.V.; Pangavhane, D.R.; Singh, T. P.

doi:10.1016/j.ijheatmasstransfer.2014.11.085

Cited by 25 publications

(12 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The former two functions are based on Levenberg-Marquardt optimization, while the third function is based on the scaled conjugate gradient method. The three training functions' algorithms can be seen in [14,15].…”

Section: The Neural Network Regression Of the Pseudo Calculated Sizesmentioning

confidence: 99%

Evaluation of the Calculated Sizes Based on the Neural Network Regression

Zhao

et al. 2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The evaluation models of circumference diameter, area diameter, and volume diameter were established based on the cylindrical coordinate measuring method, respectively. Many groups of roundness profiles of cylindrical specimens were extracted, and their pseudo and actual circumference diameters, area diameters, and volume diameters were evaluated according to the established evaluation models and the sampling data of the extracted roundness profiles. The relationship models between the pseudo calculated sizes and the actual calculated sizes were built through a series of training based on the neural network regression. The checked experiments for the training models showed that the evaluation of the calculated sizes can meet their measurement accuracy requirement through the pseudo calculated sizes, which were evaluated based on the roundness profiles by using the cylindricity or roundness measuring instrument.

show abstract

Section: The Neural Network Regression Of the Pseudo Calculated Sizesmentioning

confidence: 99%

Evaluation of the Calculated Sizes Based on the Neural Network Regression

Zhao

et al. 2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…It is an iterative technique that works in such a way that performance function will always be reduced in each iteration of the algorithm. This feature makes trainlm back propagation optimization learning algorithm is the most rapid learning algorithm tool for moderate size network (Kamble, Pangavhane, & Singh, 2015). Both trainbfg and trainlm function has drawback of memory and computation overhead caused due to the calculation of the gradient and approximated Hessian matrix (Pham & Sagiroglu, 2001).…”

Section: Artificial Neural Networkmentioning

confidence: 99%

“…This function has additional advantage that the new search direction can be calculated without computing a matrix inverse. So, trainoss is considered a compromise between full quasi-Newton algorithms and conjugate gradient algorithms (Kamble, Pangavhane, & Singh, 2015).…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Optimization of Windspeed Prediction Using an Artificial Neural Network Compared With a Genetic Programming Model

Deo

Ghimire

Downs

et al. 2018

Advances in Computational Intelligence and Robotics

View full text Add to dashboard Cite

show abstract

“…In 2015 L.V. Kamble et al [25] described the prediction of heat transfer from horizontal tube immersed in gas-solid fluidized bed of large particles by the neural network optimization. The effect of fluidizing gas velocity on the average heat transfer coefficient between fluidizing bed and horizontal tube surface was studied by the Artificial Neural Network modeling.…”

Section: Literature Reviewmentioning

confidence: 99%

An effective krill herd based optimal NN for parameter evaluation in Shell-And-Tube heat exchangers

Roy¹,

Majumder²

2018

IJHT

View full text Add to dashboard Cite

Helical baffles are employed increasingly in shell-and-tube heat exchangers for their significant advantages in reducing pressure drop, vibration, and fouling while maintaining a higher heat transfer performance. In order to make good use of helical baffles, serial improvements have been made by many researchers. In this paper create model of optimal NN for prediction analysis in parameters compared to existing works. This hidden layer and neuron optimization process fish asked KHO technique used. For more verification, KHO is applied to six design problems reported in the literature. Further, the performance of the KH algorithm is compared with that of various algorithms representative of the state-of-the-art in the area. The results of different algorithms are breaking down and stood out from comparative systems, and the finest results rising out of them are discovered by standing out the results from least MSE values. From the results our proposed method achieves minimum MSE compared to existing works and maximum prediction accuracy in optimization model.

show abstract

Neural network optimization by comparing the performances of the training functions -Prediction of heat transfer from horizontal tube immersed in gas–solid fluidized bed

Cited by 25 publications

References 16 publications

Evaluation of the Calculated Sizes Based on the Neural Network Regression

Evaluation of the Calculated Sizes Based on the Neural Network Regression

Optimization of Windspeed Prediction Using an Artificial Neural Network Compared With a Genetic Programming Model

An effective krill herd based optimal NN for parameter evaluation in Shell-And-Tube heat exchangers

Contact Info

Product

Resources

About