Premium
A coupled and interactive influence of operational parameters for optimizing power output of cleaner energy production systems under uncertain conditions
Author(s) -
Chen Dezhi,
Singh Surinder,
Gao Liang,
Garg Akhil,
Fan Zhun,
Wang ChinTsan
Publication year - 2019
Publication title -
international journal of energy research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.808
H-Index - 95
eISSN - 1099-114X
pISSN - 0363-907X
DOI - 10.1002/er.4347
Subject(s) - stack (abstract data type) , proton exchange membrane fuel cell , power (physics) , work (physics) , electricity generation , control theory (sociology) , function (biology) , computer science , process engineering , mathematical optimization , thermodynamics , mathematics , engineering , fuel cells , physics , control (management) , chemical engineering , artificial intelligence , evolutionary biology , biology , programming language
Summary The mechanisms in proton‐exchange membrane fuel cells (PEMFCs) cannot be explicitly represented by a mathematical function because the PEMFC system is multi‐dimensional and complex and represents uncertainty in operation variables, which cannot be modeled by experiments or by trial‐and‐error approach. Therefore, this work proposes to study the coupled and interactive influence of stack current (SC), stack temperature (ST), oxygen excess ratio (OER), hydrogen excess ratio (HER), and inlet air humidity (IAH) for optimizing the power output of PEMFC. The data obtained from the experiments have been inserted into architecture of automated neural‐network search, which automates the selection of error function, activation function, uncertainties in inputs and number of hidden neurons in formulation of a robust and accurate model for power density as a function of five operational variables. Among the operational variables, the correlation coefficient between the SC and the output power is the highest, followed by OER, and the ST. However, for HER and IAH, the power output follows negative nonlinear relation. The optimization converged at 130 th iteration results in maximum power output of 3410 W for an optimum value of SC (51A), ST (59°C), OER (3:2), HER (1:10), and IAH (0.8).