Korean Chemical Engineering Research

The Korean Institute of Chemical Engineers (한국화학공학회)
권호 표지
DOI QR코드

DOI QR Code

Modeling of a PEM Fuel Cell Stack using Partial Least Squares and Artificial Neural Networks

부분최소자승법과 인공신경망을 이용한 고분자전해질 연료전지 스택의 모델링

  • Received : 2014.08.22
  • Accepted : 2014.10.02
  • Published : 2015.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

We present two data-driven modeling methods, partial least square (PLS) and artificial neural network (ANN), to predict the major operating and performance variables of a polymer electrolyte membrane (PEM) fuel cell stack. PLS and ANN models were constructed using the experimental data obtained from the testing of a 30 kW-class PEM fuel cell stack, and then were compared with each other in terms of their prediction and computational performances. To reduce the complexity of the models, we combined a variables importance on PLS projection (VIP) as a variable selection method into the modeling procedure in which the predictor variables are selected from a set of input operation variables. The modeling results showed that the ANN models outperformed the PLS models in predicting the average cell voltage and cathode outlet temperature of the fuel cell stack. However, the PLS models also offered satisfactory prediction performances although they can only capture linear correlations between the predictor and output variables. Depending on the degree of modeling accuracy and speed, both ANN and PLS models can be employed for performance predictions, offline and online optimizations, controls, and fault diagnoses in the field of PEM fuel cell designs and operations.

고분자전해질 연료전지 스택의 성능 및 주요 운전 변수를 예측하기 위해 부분최소자승법과 인공신경망의 두 가지 데이터 기반 모델링 기법을 제시한다. 30 kW급 고분자전해질 연료전지 스택 실험으로부터 확보한 데이터를 사용하여 부분최소자승 및 인공신경망 모델들을 구성한 후 각 모델의 예측 성능 및 계산 시간을 비교하였다. 모델의 복잡성을 줄이기 위해 부분최소자승법에 기초한 VIP(Variable Importance on PLS Projections) 선정기준을 모델링 절차에 포함하여, 초기 입력변수의 집합으로부터 모델링에 필요한 입력변수들을 선정하였다. 모델링 결과, 인공신경망이 스택의 평균 셀전압과 캐소드(cathode) 출구 온도를 예측하는데 있어서, 부분최소자승법 보다 우수한 성능을 보였다. 그러나 부분최소자승법 또한 입력변수와 출력변수 간에 선형적 상관관계만을 모델링 할 수 있음에도 불구하고 비교적 만족할 만한 예측 성능을 나타냈다. 모델의 정확도와 계산속도의 요구조건에 따라 두 모델링 기법은 고분자전해질 연료전지의 설계 및 운전 분야의 성능 예측, 온라인 및 오프라인 최적화, 제어 및 이상 진단을 위해 적용될 수 있을 것으로 판단된다.

Keywords

References

  1. Veziroglu, A. and Macario, R., "Fuel Cell Vehicles: State of the Art with Economic and Environmental Concerns," Int. J. Hydrog. Energy, 36, 25-43(2011). https://doi.org/10.1016/j.ijhydene.2010.08.145
  2. Wang, C. Y., "Fundamental Models for Fuel Cell Engineering," Chem. Rev., 104, 4727-4766(2004). https://doi.org/10.1021/cr020718s
  3. Ding, Y., Bi, X. T. and Wilkinson, D. P., "Numerical Investigation of the Impact of Two-Phase Flow Maldistribution on PEM Fuel Cell Performance," Int. J. Hydrog. Energy, 39, 469-480(2014). https://doi.org/10.1016/j.ijhydene.2013.10.047
  4. Han, I.-S., Lim, J., Jeong, J. and Shin, H. K., "Effect of Serpentine Flow-Field Designs on Performance of PEMFC Stacks for Micro-CHP Systems," Renew. Energy, 54, 180-188(2013). https://doi.org/10.1016/j.renene.2012.08.027
  5. Chung, H., Ha, T., Kim, H. and Han, C., "Simulation of PEM Fuel Cell with 2D Steady-State Model," Korean Chem. Eng. Res., 46, 915-921(2008).
  6. Jeong, J., Han, I.-S. and Shin, H. K., "Optimal Sizing of the Manifolds in a PEM Fuel Cell Stack using Three-Dimensional CFD Simulations," Trans. Korean Hydrogen & New Energy Soc., 24, 386-392 (2013). https://doi.org/10.7316/KHNES.2013.24.5.386
  7. Guo, N., Leu, M. C. and Koylu, U. O., "Network based Optimization Model for Pin-Type Flow Field of Polymer Electrolyte Membrane Fuel Cell," Int. J. Hydrog. Energy, 38, 6750-6761(2013). https://doi.org/10.1016/j.ijhydene.2013.03.066
  8. Hou, Y., Yang, Z. and Wan, G., "An Improved Dynamic Voltage Model of PEM Fuel Cell Stack," Int. J. Hydrog. Energy, 35, 11154-11160 (2010). https://doi.org/10.1016/j.ijhydene.2010.07.036
  9. Zhao, Y. and Pistikopoulos, E., "Dynamic Modeling and Parametric Control for the Polymer Electrolyte Membrane Fuel Cell System," J. Power Sources, 232, 270-278(2013). https://doi.org/10.1016/j.jpowsour.2012.12.116
  10. Khadom, A. A., "Modeling of Corrosion Reaction Data in Inhibited Acid Environment using Regressions and Artificial Neural Networks," Korean J. Chem. Eng., 30, 2197-2204(2013). https://doi.org/10.1007/s11814-013-0170-0
  11. Saengrung, A., Abtahi, A. and Zilouchian, A., "Neural Network Model for a Commercial PEM Fuel Cell System," J. Power Sources, 172, 749-759(2007). https://doi.org/10.1016/j.jpowsour.2007.05.039
  12. Li, X., Cao, G. and Zhu, X., "Modeling and Control of PEMFC Based on Least Squares Support Vector Machines," Energy Conv. Manag., 47, 1032-1050(2006). https://doi.org/10.1016/j.enconman.2005.04.002
  13. Zhong, Z., Zhu, X. and Cao, G., "Modeling a PEMFC by a Support Vector Machine," J. Power Sources, 160, 293-298(2006). https://doi.org/10.1016/j.jpowsour.2006.01.040
  14. Petrone, R., Zheng, Z., Hissel, D., Pera, M. C., Pianese, C., Sorrentino, M., Becherif, M. and Yousfi-Steiner, N., "A Review on Modelbased Diagnosis Methodologies for PEMFCs," Int. J. Hydrog. Energy, 38, 7077-7091(2013). https://doi.org/10.1016/j.ijhydene.2013.03.106
  15. Napoli, G., Ferraro, M., Sergi, F., Brunaccini, G. and Antonucci, V., "Data Driven Models for a PEM Fuel Cell Stack Performance Prediction," Int. J. Hydrog. Energy, 38, 11628-11638(2013). https://doi.org/10.1016/j.ijhydene.2013.04.135
  16. Hua, J., Li, J., Ouyang, M., Lu, L. and Xu, L., "Proton Exchange Membrane Fuel Cell System Diagnosis based on the Multivariate Statistical Method," Int. J. Hydrog. Energy, 36, 9896-9905(2011). https://doi.org/10.1016/j.ijhydene.2011.05.075
  17. Wold, S., Sjostrom, M. and Eriksson, L., "PLS-Regression: a Basic Tool of Chemometrics," Chemometrics Intell. Lab. Syst., 58, 109-130(2001). https://doi.org/10.1016/S0169-7439(01)00155-1
  18. Han, I.-S., Kim, M., Lee, C.-H., Cha, W., Ham, B.-K., Jeong, J.-H., Lee, H., Chung, C.-B. and Han, C., "Application of Partial Least Squares Methods to a Terephthalic Acid Manufacturing Process for Product Quality Control," Korean J. Chem. Eng., 20, 977-984(2003). https://doi.org/10.1007/BF02706925
  19. Han, I.-S., Han, C. and Chung, C.-B., "Melt Index Modeling with Support Vector Machines, Partial Least Squares, and Artificial Neural Networks," J. Appl. Polym. Sci., 95, 967-974(2004).
  20. Han, I.-S. and Han, C., "Modeling of Multistage Air-Compression Systems in Chemical Processes," Ind. Eng, Chem. Res., 42, 2209-2218(2003). https://doi.org/10.1021/ie020270l
  21. Min, K. G., Han, I.-S. and Han, C., "Iterative Error-based Nonlinear PLS Method for Nonlinear Chemical Process Modeling," J. Chem. Eng. Japan, 35, 613-625(2002). https://doi.org/10.1252/jcej.35.613
  22. Geladi, P. and Kowalski, B., "Partial Least-Squares Regression: a Tutorial," Anal. Chim. Acta, 185, 1-17(1986). https://doi.org/10.1016/0003-2670(86)80028-9
  23. Kalogirou, S. A., "Artificial Neural Networks in Renewable Energy Systems Applications: a Review," Renew. Sust. Energ. Rev., 5, 373-401(2001). https://doi.org/10.1016/S1364-0321(01)00006-5
  24. Hagan, M. T., Demuth, H. B. and Beale, M., Neural Network Design, PWS Publishing, Boston, MA(1996).
  25. Hornik, K., Stinchcombe, M. and White, H., "Multilayer Feedforward Networks are Universal Approximatiors," Neural Networks, 2, 359-366(1989). https://doi.org/10.1016/0893-6080(89)90020-8
  26. Han, I.-S., Jeong, J., Kho, B. K., Choi, C. H., Yu, S. and Shin, H. K., "Development of a 25 kW-Class PEM Fuel Cell System for the Propulsion of a Leisure Boat," Trans. Korean Hydrogen & New Energy Soc., 25, 271-279(2014). https://doi.org/10.7316/KHNES.2014.25.3.271
  27. Han, I.-S., Jeong, J. and Shin, H. K., "PEM Fuel-Cell Stack Design for Improved Fuel Utilization," Int. J. Hydrog. Energy, 38, 11996-12006(2013). https://doi.org/10.1016/j.ijhydene.2013.06.136
  28. Andersen, C. M. and Bro, R., "Variable Selection in Regression - Tutorial," J. Chemometr., 24, 728-737(2010). https://doi.org/10.1002/cem.1360
  29. Chong, I.-G. and Jun, C.-H., "Performance of Some Variable Selection Methods When Multicollinearity is Present," Chemometrics Intell. Lab. Syst., 78, 103-112(2005). https://doi.org/10.1016/j.chemolab.2004.12.011

Cited by

  1. Effect of gas diffusion layer compression on the polarization curves of a polymer electrolyte membrane fuel cell: Analysis using a polarization curve-fitting model vol.33, pp.11, 2016, https://doi.org/10.1007/s11814-016-0157-8
  2. Pattern Recognition for Typification of Whiskies and Brandies in the Volatile Components using Gas Chromatographic Data vol.21, pp.5, 2016, https://doi.org/10.9708/jksci.2016.21.5.167
  3. PCBs 독성 예측을 위한 주요 분자표현자 선택 기법 및 계산독성학 기반 QSAR 모델 개발 vol.54, pp.5, 2015, https://doi.org/10.9713/kcer.2016.54.5.621
  4. Fuel cell-based CHP system modelling using Artificial Neural Networks aimed at developing techno-economic efficiency maximization control systems vol.123, pp.None, 2015, https://doi.org/10.1016/j.energy.2017.02.043