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

Asif Afzal, Javed Khan Bhutto, Abdulrahman Alrobaian, Abdul Razak Kaladgi and Sher Afghan Khan
Additional contact information
Asif Afzal: Department of Mechanical Engineering, P. A. College of Engineering, Visvesvaraya Technological University, Mangaluru 574153, India
Javed Khan Bhutto: Department of Electrical Engineering, College of Engineering, King Khalid University, P.O. Box 394, Abha 61421, Saudi Arabia
Abdulrahman Alrobaian: Department of Mechanical Engineering, College of Engineering, Qassim University, Buraydah 51452, Saudi Arabia
Abdul Razak Kaladgi: Department of Mechanical Engineering, P. A. College of Engineering, Visvesvaraya Technological University, Mangaluru 574153, India
Sher Afghan Khan: Department of Mechanical Engineering, Faculty of Engineering, International Islamic University, Kuala Lumpur 50728, Malaysia

Energies, 2021, vol. 14, issue 21, 1-19

Abstract: The focus of this work is to computationally obtain an optimized neural network (NN) model to predict battery average Nusselt number ( Nu avg ) data using four activations functions. The battery Nu avg 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. Nu avg is modeled at first using only one hidden layer in the network (NN 1 ). The neurons in NN 1 are experimented from 1 to 10 with activation functions: Sigmoidal, Gaussian, Tanh, and Linear functions to get the optimized NN 1 . Similarly, deep NN (NN D ) was also analyzed with neurons and activations functions to find an optimized number of hidden layers to predict the Nu avg . RSME (root mean square error) and R-Squared (R 2 ) is accessed to conclude the optimized NN model. From this computational experiment, it is found that NN 1 and NN D both accurately predict the battery data. Six neurons in the hidden layer for NN 1 give the best predictions. Sigmoidal and Gaussian functions have provided the best results for the NN 1 model. In NN D, 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 1 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 D model. Overall, the deep NN (NN D ) model predicted better than the single-layered NN (NN 1 ) model for each activation function.

Keywords: neural network; battery; heat transfer; activation functions; hidden layers (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
https://www.mdpi.com/1996-1073/14/21/7370/pdf (application/pdf)
https://www.mdpi.com/1996-1073/14/21/7370/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:14:y:2021:i:21:p:7370-:d:672817

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().