Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/208977
Title: NEURAL NETWORK MODELLING OF POLYMER ELECTROLYE FUEL CELL STACK AND SYSTEM
Authors: YONG RUI YUAN
ORCID iD:   orcid.org/0000-0003-0129-2888
Keywords: PEMFC, Fuel Cell, Neural Network, Modelling
Issue Date: 5-Jul-2021
Citation: YONG RUI YUAN (2021-07-05). NEURAL NETWORK MODELLING OF POLYMER ELECTROLYE FUEL CELL STACK AND SYSTEM. ScholarBank@NUS Repository.
Abstract: The cost of designing new fuel cell modules for niche applications is significant due to orders being highly customised and small in quantity. One solution to reduce design and development cost is to conduct simulations of the fuel cell module before manufacturing the final design; however, three-dimensional (3D) simulations of a fuel cell module are computationally intensive and time consuming. We have developed simulation tools in the form of neural networks to reduce the computational and time requirements of 3D simulations of the fuel cell module that were fabricated, tested, and integrated into demonstration projects and products. In short, the neural networks can predict mean pressure drops and temperatures in the fuel cell module and through Monte Carlo simulations predict the standard deviations. These tools are then used to evaluate the current designs of the fuel cell modules and explore and recommend changes to improve their designs and products.
URI: https://scholarbank.nus.edu.sg/handle/10635/208977
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Yong Rui Yuan Thesis Revised.pdf13.69 MBAdobe PDF

OPEN

NoneView/Download

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.