Working zone for a least-squares support vector machine for modeling polymer electrolyte fuel cell voltage

2020 ◽  
pp. 116191
Author(s):  
Wei Zou ◽  
Dieter Froning ◽  
Yan Shi ◽  
Werner Lehnert
Keyword(s):  
Support Vector Machine ◽  
Fuel Cell ◽  
Least Squares ◽  
Polymer Electrolyte ◽  
Cell Voltage ◽  
Polymer Electrolyte Fuel Cell ◽  
Support Vector ◽  
Working Zone

scholarly journals Exergy Analysis of Polymer Electrolyte Fuel Cell Systems Using Methanol

2003 ◽  
Author(s):  
Akimitsu Ishihara ◽  
Shigenori Mitsushima ◽  
Nobuyuki Kamiya ◽  
Ken-Ichiro Ota
Keyword(s):  
Fuel Cell ◽  
Polymer Electrolyte ◽  
Steam Reforming ◽  
Waste Heat ◽  
Material Balance ◽  
Cell Voltage ◽  
Exergy Efficiency ◽  
Exergy Loss ◽  
Polymer Electrolyte Fuel Cell ◽  
The Difference

An exergy (available energy) analysis has been conducted on a typical polymer electrolyte fuel cell (PEFC) system using methanol. The material balance and enthalpy balance were calculated for the PEFC system using methanol steam reforming, and the exergy flow was obtained. Based on these results, the exergy loss in each unit was obtained, and the difference between the enthalpy and exergy was discussed. The exergy loss in this system was calculated to be 178kJ/mole MeOH for the steam reforming process of methanol. Although the enthalpy efficiency approached unity as the recovery rate of the waste heat from the cell approached unity, the exergy efficiency remained around 0.45 since the cell’s operating temperature of 80°C is low. It was also found that the cell voltage should exceed 0.82V in order to obtain the exergy efficiency of 0.5 or higher. A direct methanol fuel cell (DMFC) was analyzed using the exergy and compared with the methanol reforming PEFC. In order to obtain the exergy efficiency higher than that of PEFC with steam reforming, the cell voltage of the DMFC should be 0.48V or greater at the current density of 600mA/cm2.

Transients of Polymer Electrolyte Fuel Cell and Hydrogen Tank

2009 ◽  
Author(s):  
Yun Wang ◽  
Xiaoguang Yang
Keyword(s):  
Fuel Cells ◽  
Fuel Cell ◽  
Polymer Electrolyte ◽  
Dynamic Models ◽  
Cell Voltage ◽  
Polymer Electrolyte Fuel Cells ◽  
Dynamic Responses ◽  
Polymer Electrolyte Fuel Cell ◽  
Electrochemical Double Layer ◽  
The One

This paper seeks to develop 3D dynamic models for polymer electrolyte fuel cells (PEFCs) and hydrogen tanks, respectively. The dynamic model of PEFCs consists of multiple layers of a single PEFC and couples the various dynamic mechanisms in fuel cells, such as electrochemical double-layer discharging/charging, species transport, heat transfer, and membrane water uptake. The one of hydrogen tanks includes a 3D description of the hydride kinetics coupled with mass/heat transport in the hydrogen tank. Transient of fuel cell during step change in current is simulated. Dynamic responses of the cell voltage and heat generation rate are discussed. Hydrogen absorption process in the tank is considered. Temperature, reaction rate and heat rejection in the fuel tank are presented. Efforts are also made to discuss the coupling of these two systems in practice and associated issues.

scholarly journals Multiple Degradation Phenomena in Polymer Electrolyte Fuel Cell Operation With Dead-Ended Anode

2011 ◽  
Author(s):  
Toyoaki Matsuura ◽  
Jason B. Siegel ◽  
Jixin Chen ◽  
Anna G. Stefanopoulou
Keyword(s):  
Fuel Cell ◽  
Polymer Electrolyte ◽  
Cell Voltage ◽  
Polymer Electrolyte Fuel Cell ◽  
Water Flooding ◽  
Ex Situ ◽  
Water Current ◽  
Membrane Electrode ◽  
Carbon Corrosion ◽  
Sem Images

Dead-ended anode (DEA) operation of Polymer Electrolyte Fuel Cell (PEFC) can simplify the fuel cell auxiliary and reduce system cost, however durability and lifetime in this operating mode requires further study. In this work, we investigate the electrode and membrane degradations of one 50 cm2 active area fuel cell under DEA operation using a combination of post-mortem evaluation and in-situ performance evaluation protocol. We experimentally identify multiple degradation patterns using a cell which we have previously modeled and experimentally verified the spatio-temporal patterns associated with the anode water flooding and nitrogen blanketing. The change in cell voltage and internal resistance during operation and ex situ Scanning Electron Microscope (SEM) images of aged electrode/membrane are analysed to determine and characterize the degradation of the membrane electrode assembly (MEA). Chemical degradations including carbon corrosion in the catalyst layer and membrane decomposition are found after operating the cell with a DEA. Mechanical degradations including membrane delamination are also observed. Unique features of DEA operation including fuel starvation/nitrogen blanketing in the anode and uneven local water/current distribution, are considered as culprits for degradation.

Q-learning System Based on Cooperative Least Squares Support Vector Machine

2009 ◽  
Vol 35 (2) ◽  
pp. 214-219 ◽  
Author(s):  
Xue-Song WANG ◽  
Xi-Lan TIAN ◽  
Yu-Hu CHENG ◽  
Jian-Qiang YI
Keyword(s):  
Support Vector Machine ◽  
Least Squares ◽  
Learning System ◽  
Support Vector ◽  
Q Learning

Development of small polymer electrolyte fuel cell stacks

1996 ◽  
Author(s):  
V A Paganin ◽  
E A Ticianelli ◽  
E R Gonzalez
Keyword(s):  
Fuel Cell ◽  
Polymer Electrolyte ◽  
Polymer Electrolyte Fuel Cell

scholarly journals Predicting Ink Transfer Rate of 3D Additive Printing Using EGBO Optimized Least Squares Support Vector Machine Model

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Shengpu Li ◽  
Yize Sun
Keyword(s):  
Support Vector Machine ◽  
Prediction Model ◽  
Least Squares ◽  
Transfer Rate ◽  
Coefficient Of Determination ◽  
Percentage Error ◽  
Support Vector ◽  
Experimental Sample ◽  
Machine Model ◽  
Ink Transfer

Ink transfer rate (ITR) is a reference index to measure the quality of 3D additive printing. In this study, an ink transfer rate prediction model is proposed by applying the least squares support vector machine (LSSVM). In addition, enhanced garden balsam optimization (EGBO) is used for selection and optimization of hyperparameters that are embedded in the LSSVM model. 102 sets of experimental sample data have been collected from the production line to train and test the hybrid prediction model. Experimental results show that the coefficient of determination (R2) for the introduced model is equal to 0.8476, the root-mean-square error (RMSE) is 6.6 × 10 (−3), and the mean absolute percentage error (MAPE) is 1.6502 × 10 (−3) for the ink transfer rate of 3D additive printing.

Sign in / Sign up

Export Citation Format

Share Document