Fast identification of power change rate of PEM fuel cell based on data dimensionality reduction approach

Abstract The efficiency, reliability and lifespan of the fuel cell are strongly affected by the dynamic load variation of its output, which renders it desperate to investigate the influence of the power change rate on the fuel cell. In this study, three data dimensionality reduction algorithms are applied to identify the power change rate of the fuel cell in a less time-consuming way. To achieve that, the cell voltages of the stack as high-dimensional dataset is instantly projected onto the one-dimensional eigenvector space by principal component analysis (PCA), Fisher discriminant analysis (FDA) and locally linear embedding (LLE), respectively. The eigenvalue of one-dimensional eigenvector has the potential for instantly identifying the power change rate of the fuel cell and can be used as a feedback parameter in the control, which can improve the dynamic response, reliability, and lifespan of the fuel cell stack. According to the performance indicators of the algorithms including monotonicity, linearity and program execution time, the result shows that the PCA algorithm is the best-matched method for the real-time control of the fuel cell system. In the end, this study discussed some potential applications of this method in the fuel cell system, be it to be used alone or in a vehicular fuel cell hybrid system.

[1]  Tao Zeng,et al.  Modelling and predicting energy consumption of a range extender fuel cell hybrid vehicle , 2018, Energy.

[2]  D. Candusso,et al.  PEMFC Durability Test under Specific Dynamic Current Solicitation, Linked to a Vehicle Road Cycle , 2007 .

[3]  Zhihua Yang,et al.  An experimental study on the dynamic process of PEM fuel cell stack voltage , 2011 .

[4]  Haoting Wang,et al.  An experimental study of the dynamic behavior of a 2 kW proton exchange membrane fuel cell stack under various loading conditions , 2015 .

[5]  Liejin Guo,et al.  Mitigation strategies for hydrogen starvation under dynamic loading in proton exchange membrane fuel cells , 2017 .

[6]  K. Min,et al.  Transient response of a unit proton-exchange membrane fuel cell under various operating conditions , 2008 .

[7]  Y. Zhao,et al.  Modeling and simulation of fuel cell hybrid vehicles , 2010 .

[8]  Huicui Chen,et al.  Main factors affecting the lifetime of Proton Exchange Membrane fuel cells in vehicle applications: A review , 2014 .

[9]  Phatiphat Thounthong,et al.  Energy management of fuel cell/battery/supercapacitor hybrid power source for vehicle applications , 2009 .

[10]  Young-Bae Kim,et al.  Improving dynamic performance of proton-exchange membrane fuel cell system using time delay control , 2010 .

[11]  Diego Feroldi,et al.  Performance improvement of a PEMFC system controlling the cathode outlet air flow , 2007 .

[12]  Richard D. Braatz,et al.  A combined canonical variate analysis and Fisher discriminant analysis (CVA-FDA) approach for fault diagnosis , 2015, Comput. Chem. Eng..

[13]  Li Honggui,et al.  Gait analysis using LLE , 2004, Proceedings 7th International Conference on Signal Processing, 2004. Proceedings. ICSP '04. 2004..

[14]  James K. Mills,et al.  Two-Stage Energy Management Control of Fuel Cell Plug-In Hybrid Electric Vehicles Considering Fuel Cell Longevity , 2012, IEEE Transactions on Vehicular Technology.

[15]  Hiromu Ohno,et al.  Dimensionality reduction for metabolome data using PCA, PLS, OPLS, and RFDA with differential penalties to latent variables , 2009 .

[16]  Guo-Ping Liu,et al.  Optimal fuzzy power control and management of fuel cell/battery hybrid vehicles , 2009 .

[17]  Caisheng Wang,et al.  Load Transient Mitigation For Stand-alone Fuel Cell Power Generation Systems , 2007, 2007 IEEE Power Engineering Society General Meeting.

[18]  Young-Bae Kim,et al.  Power source protection method for hybrid polymer electrolyte membrane fuel cell/lithium-ion battery system , 2017 .

[19]  Jianqiu Li,et al.  Performance comparison of two fuel cell hybrid buses with different powertrain and energy management strategies , 2006 .

[20]  S. Case,et al.  Durability study of proton exchange membrane fuel cells under dynamic testing conditions with cyclic current profile , 2006 .

[21]  D. Coomans,et al.  Recent developments in discriminant analysis on high dimensional spectral data , 1996 .

[22]  Sanggyu Kang,et al.  Dynamic simulation of a fuel cell hybrid vehicle during the federal test procedure-75 driving cycle , 2016 .

[23]  Werner Lehnert,et al.  Nonlinear dynamic mechanism modeling of a polymer electrolyte membrane fuel cell with dead-ended anode considering mass transport and actuator properties , 2018, Applied Energy.

[24]  Zhi-Hua Zhou,et al.  Supervised nonlinear dimensionality reduction for visualization and classification , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[25]  Abdolreza Ohadi,et al.  Comparison of FDA-based and PCA-based features in fault diagnosis of automobile gearboxes , 2013, Neurocomputing.

[26]  Jamel Ghouili,et al.  Energy management of fuel cell/battery/ultracapacitor in electrical hybrid vehicle , 2017 .

[27]  Yong-Song Chen,et al.  A purge strategy for proton exchange membrane fuel cells under varying-load operations , 2016 .

[28]  Fortunato Migliardini,et al.  Experimental analysis of a 20 kWe PEM fuel cell system in dynamic conditions representative of automotive applications , 2008 .

[29]  Huei Peng,et al.  Testing, modeling, and control of a fuel cell hybrid vehicle , 2005, Proceedings of the 2005, American Control Conference, 2005..

[30]  Norbert Schuff,et al.  Locally linear embedding (LLE) for MRI based Alzheimer's disease classification , 2013, NeuroImage.

[31]  Sergio A. Velastin,et al.  Local Fisher Discriminant Analysis for Pedestrian Re-identification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  Zhengkai Tu,et al.  Degradation behavior of a proton exchange membrane fuel cell stack under dynamic cycles between idling and rated condition , 2018 .

[33]  Sirivatch Shimpalee,et al.  The effect of stoichiometry on dynamic behavior of a proton exchange membrane fuel cell (PEMFC) during load change , 2004 .

[34]  Rayhane Koubaa,et al.  Double layer metaheuristic based energy management strategy for a Fuel Cell/Ultra-Capacitor hybrid electric vehicle , 2017 .

[35]  Jianqiu Li,et al.  Model-based temperature regulation of a PEM fuel cell system on a city bus , 2015 .

[36]  Zhongjun Hou,et al.  The voltage characteristics of proton exchange membrane fuel cell (PEMFC) under steady and transient states , 2008 .

[37]  Yong Tang,et al.  Experimental investigation of dynamic performance and transient responses of a kW-class PEM fuel cell stack under various load changes , 2010 .

[38]  Jianqiu Li,et al.  Multi-mode control strategy for fuel cell electric vehicles regarding fuel economy and durability , 2014 .

[39]  Azah Mohamed,et al.  A review on energy management system for fuel cell hybrid electric vehicle: Issues and challenges , 2015 .

[40]  Hugo Leonardo Rufiner,et al.  Dimensionality reduction for visualization of normal and pathological speech data , 2009, Biomed. Signal Process. Control..