Modelling and Computational Experiment to Obtain Optimized Neural Network for Battery Thermal Management Data

The focus of this work is to computationally obtain an optimized neural network (NN) model to predict battery average Nusselt number (Nuavg) data using four activations functions. The battery Nuavg is highly nonlinea...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Asif Afzal, Javed Khan Bhutto, Abdulrahman Alrobaian, Abdul Razak Kaladgi, Sher Afghan Khan
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	neural network battery heat transfer activation functions hidden layers Technology T
Acceso en línea:	https://doaj.org/article/01bfa23bd5b34175abe2316eb1f1c428
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:01bfa23bd5b34175abe2316eb1f1c428
record_format	dspace
spelling	oai:doaj.org-article:01bfa23bd5b34175abe2316eb1f1c4282021-11-11T16:05:04ZModelling and Computational Experiment to Obtain Optimized Neural Network for Battery Thermal Management Data10.3390/en142173701996-1073https://doaj.org/article/01bfa23bd5b34175abe2316eb1f1c4282021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/21/7370https://doaj.org/toc/1996-1073The focus of this work is to computationally obtain an optimized neural network (NN) model to predict battery average Nusselt number (<i>Nu<sub>avg</sub></i>) data using four activations functions. The battery <i>Nu<sub>avg</sub></i> is highly nonlinear as reported in the literature, which depends mainly on flow velocity, coolant type, heat generation, thermal conductivity, battery length to width ratio, and space between the parallel battery packs. <i>Nu<sub>avg</sub></i> is modeled at first using only one hidden layer in the network (NN<sub>1</sub>). The neurons in NN<sub>1</sub> are experimented from 1 to 10 with activation functions: Sigmoidal, Gaussian, Tanh, and Linear functions to get the optimized NN<sub>1</sub>. Similarly, deep NN (NN<sub>D</sub>) was also analyzed with neurons and activations functions to find an optimized number of hidden layers to predict the <i>Nu<sub>avg</sub></i>. RSME (root mean square error) and R-Squared (R<sup>2</sup>) is accessed to conclude the optimized NN model. From this computational experiment, it is found that NN<sub>1</sub> and NN<sub>D</sub> both accurately predict the battery data. Six neurons in the hidden layer for NN<sub>1</sub> give the best predictions. Sigmoidal and Gaussian functions have provided the best results for the NN<sub>1</sub> model. In NN<sub>D,</sub> the optimized model is obtained at different hidden layers and neurons for each activation function. The Sigmoidal and Gaussian functions outperformed the Tanh and Linear functions in an NN<sub>1</sub> model. The linear function, on the other hand, was unable to forecast the battery data adequately. The Gaussian and Linear functions outperformed the other two NN-operated functions in the NN<sub>D</sub> model. Overall, the deep NN (NN<sub>D</sub>) model predicted better than the single-layered NN (NN<sub>1</sub>) model for each activation function.Asif AfzalJaved Khan BhuttoAbdulrahman AlrobaianAbdul Razak KaladgiSher Afghan KhanMDPI AGarticleneural networkbatteryheat transferactivation functionshidden layersTechnologyTENEnergies, Vol 14, Iss 7370, p 7370 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	neural network battery heat transfer activation functions hidden layers Technology T
spellingShingle	neural network battery heat transfer activation functions hidden layers Technology T Asif Afzal Javed Khan Bhutto Abdulrahman Alrobaian Abdul Razak Kaladgi Sher Afghan Khan Modelling and Computational Experiment to Obtain Optimized Neural Network for Battery Thermal Management Data
description	The focus of this work is to computationally obtain an optimized neural network (NN) model to predict battery average Nusselt number (<i>Nu<sub>avg</sub></i>) data using four activations functions. The battery <i>Nu<sub>avg</sub></i> is highly nonlinear as reported in the literature, which depends mainly on flow velocity, coolant type, heat generation, thermal conductivity, battery length to width ratio, and space between the parallel battery packs. <i>Nu<sub>avg</sub></i> is modeled at first using only one hidden layer in the network (NN<sub>1</sub>). The neurons in NN<sub>1</sub> are experimented from 1 to 10 with activation functions: Sigmoidal, Gaussian, Tanh, and Linear functions to get the optimized NN<sub>1</sub>. Similarly, deep NN (NN<sub>D</sub>) was also analyzed with neurons and activations functions to find an optimized number of hidden layers to predict the <i>Nu<sub>avg</sub></i>. RSME (root mean square error) and R-Squared (R<sup>2</sup>) is accessed to conclude the optimized NN model. From this computational experiment, it is found that NN<sub>1</sub> and NN<sub>D</sub> both accurately predict the battery data. Six neurons in the hidden layer for NN<sub>1</sub> give the best predictions. Sigmoidal and Gaussian functions have provided the best results for the NN<sub>1</sub> model. In NN<sub>D,</sub> the optimized model is obtained at different hidden layers and neurons for each activation function. The Sigmoidal and Gaussian functions outperformed the Tanh and Linear functions in an NN<sub>1</sub> model. The linear function, on the other hand, was unable to forecast the battery data adequately. The Gaussian and Linear functions outperformed the other two NN-operated functions in the NN<sub>D</sub> model. Overall, the deep NN (NN<sub>D</sub>) model predicted better than the single-layered NN (NN<sub>1</sub>) model for each activation function.
format	article
author	Asif Afzal Javed Khan Bhutto Abdulrahman Alrobaian Abdul Razak Kaladgi Sher Afghan Khan
author_facet	Asif Afzal Javed Khan Bhutto Abdulrahman Alrobaian Abdul Razak Kaladgi Sher Afghan Khan
author_sort	Asif Afzal
title	Modelling and Computational Experiment to Obtain Optimized Neural Network for Battery Thermal Management Data
title_short	Modelling and Computational Experiment to Obtain Optimized Neural Network for Battery Thermal Management Data
title_full	Modelling and Computational Experiment to Obtain Optimized Neural Network for Battery Thermal Management Data
title_fullStr	Modelling and Computational Experiment to Obtain Optimized Neural Network for Battery Thermal Management Data
title_full_unstemmed	Modelling and Computational Experiment to Obtain Optimized Neural Network for Battery Thermal Management Data
title_sort	modelling and computational experiment to obtain optimized neural network for battery thermal management data
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/01bfa23bd5b34175abe2316eb1f1c428
work_keys_str_mv	AT asifafzal modellingandcomputationalexperimenttoobtainoptimizedneuralnetworkforbatterythermalmanagementdata AT javedkhanbhutto modellingandcomputationalexperimenttoobtainoptimizedneuralnetworkforbatterythermalmanagementdata AT abdulrahmanalrobaian modellingandcomputationalexperimenttoobtainoptimizedneuralnetworkforbatterythermalmanagementdata AT abdulrazakkaladgi modellingandcomputationalexperimenttoobtainoptimizedneuralnetworkforbatterythermalmanagementdata AT sherafghankhan modellingandcomputationalexperimenttoobtainoptimizedneuralnetworkforbatterythermalmanagementdata
_version_	1718432395135287296

Modelling and Computational Experiment to Obtain Optimized Neural Network for Battery Thermal Management Data

Ejemplares similares