Determination of operating parameters for PEM fuel cell using support vector machines approach

Abstract Polymer electrolyte membrane fuel cells (PEMFCs) are considered as an alternative source of power generation due to its high efficiency and environmental harmlessness. Studies were conducted to find out the relation between power density and operating parameters, such as operating temperature, fuel cell pressure, the relative humidity of anode, the relative humidity of cathode, porosity of gas diffusion electrode (GDE), conductivity of GDE. However, less focus was paid on determining the operating conditions which will maximize the power density of PEMFCs. The present work proposes the optimal design of a power density model for PEMFCs based on the artificial intelligence approach of support vector machine (SVM). The formulated power density model is in good agreement with the experimental data. Simulation profiler is then generated to verify its insensitivity to the variations in the operating conditions and the inferences on relationships between power density and operating parameters are investigated. The results show that the fuel cell pressure and conductivity of GDE are the two most dominant inputs in effective functioning of PEMFC. Optimization of the formulated model reveals that the operating temperature of 86.2 K, the fuel cell pressure of 3.44 atm, the relative humidity of anode of 50%, the relative humidity of cathode of 64.4%, the porosity of GED of 0.5 and the conductivity of GDE of 997.7 s/m gives the maximum power density value of 870 mW/cm2 of PEMFC.

[1]  Serge Demidenko,et al.  Efficient analytical moments for the robustness analysis in design optimisation , 2016 .

[2]  Shan-Jen Cheng,et al.  Numerical Optimization Design of PEM Fuel Cell Performance Applying the Taguchi Method , 2010 .

[3]  Jalal A. Nasiri,et al.  Least squares twin multi-class classification support vector machine , 2015, Pattern Recognit..

[4]  K. Tai,et al.  Framework based on number of basis functions complexity measure in investigation of the power characteristics of direct methanol fuel cell , 2016 .

[5]  M. Mohanraj,et al.  Optimization of surface roughness, cutting force and tool wear of nitrogen alloyed duplex stainless steel in a dry turning process using Taguchi method , 2014 .

[6]  Viral S. Mehta,et al.  Review and analysis of PEM fuel cell design and manufacturing , 2003 .

[7]  Sheng-Ju Wu,et al.  Parametric analysis of proton exchange membrane fuel cell performance by using the Taguchi method and a neural network , 2009 .

[8]  Ay Su,et al.  A three-dimensional full-cell CFD model used to investigate the effects of different flow channel designs on PEMFC performance , 2007 .

[9]  Zhenzhong Chen,et al.  An adaptive decoupling approach for reliability-based design optimization , 2013 .

[10]  Soe W. Myint,et al.  A support vector machine to identify irrigated crop types using time-series Landsat NDVI data , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[11]  Gunnar Rätsch,et al.  Support Vector Machines and Kernels for Computational Biology , 2008, PLoS Comput. Biol..

[12]  Y. Zhang,et al.  Comparing the Robustness of Offshore Structures with Marine Deteriorations — A Fuzzy Approach , 2015 .

[13]  P. Karthikeyan,et al.  Optimization of Operating and Design Parameters on Proton Exchange Membrane Fuel Cell by using Taguchi method , 2013 .

[14]  Xianglin Gu,et al.  Chloride penetration in concrete under marine atmospheric environment – analysis of the influencing factors , 2016 .

[15]  Akhil Garg,et al.  Functional characterization of current characteristic of direct methanol fuel cell , 2016 .

[16]  Omar Z. Sharaf,et al.  An overview of fuel cell technology: Fundamentals and applications , 2014 .

[17]  Yuan-Hai Shao,et al.  Least squares recursive projection twin support vector machine for multi-class classification , 2015, International Journal of Machine Learning and Cybernetics.

[18]  Bernard F. Buxton,et al.  Drug Design by Machine Learning: Support Vector Machines for Pharmaceutical Data Analysis , 2001, Comput. Chem..

[19]  Horng Wen Wu,et al.  Analysis of operating parameters considering flow orientation for the performance of a proton exchange membrane fuel cell using the Taguchi method , 2010 .

[20]  Thomas Aicher,et al.  Testing and model-aided analysis of a 2 kWel PEMFC CHP-system , 2005 .

[21]  Umberto Lucia,et al.  Overview on fuel cells , 2014 .

[22]  Divya Tomar,et al.  A comparison on multi-class classification methods based on least squares twin support vector machine , 2015, Knowl. Based Syst..

[23]  Soosan Rowshanzamir,et al.  Effects of operating parameters on performance of a proton exchange membrane fuel cell , 2006 .

[24]  Vera Chung,et al.  Forecasting wind power in the Mai Liao Wind Farm based on the multi-layer perceptron artificial neural network model with improved simplified swarm optimization , 2014 .

[25]  Jose Manuel Serra,et al.  Zeolite synthesis modelling with support vector machines: a combinatorial approach. , 2007, Combinatorial chemistry & high throughput screening.

[26]  Serge Demidenko,et al.  Reliability-based design optimisation of technical systems: analytical response surface moments method , 2017 .

[27]  Massimo Santarelli,et al.  Experimental analysis of the CHP performance of a PEMFC stack by a 24 factorial design , 2005 .

[28]  Yi Zhang,et al.  Maintenance management of offshore structures using Markov process model with random transition probabilities , 2017 .

[29]  Jalal A. Nasiri,et al.  Energy-based model of least squares twin Support Vector Machines for human action recognition , 2014, Signal Process..

[30]  Manish Kumar,et al.  Prediction of β-lactamase and its class by Chou's pseudo-amino acid composition and support vector machine. , 2015, Journal of theoretical biology.

[31]  Qing Li,et al.  A Comparative study on multiobjective reliable and robust optimization for crashworthiness design of vehicle structure , 2013 .

[32]  Massimo Santarelli,et al.  Experimental analysis of the effects of the operating variables on the performance of a single PEMFC , 2007 .