# Performance Prediction of Proton Exchange Membrane Fuel Cells (PEMFC) Using Adaptive Neuro Inference System (ANFIS)

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Experimental Analysis

#### 2.1. Fuel Cell Testing Procedure

^{2}was used in this investigation. The bipolar plate channel designs were serpentine, and according to the manufacturer’s specifications, the membrane for these types of fuel cells had to be well humidified to reduce any form of resistance on the membrane. The operating parameters used in the investigation are depicted in Table 1.

#### 2.2. Experimental Set-Up

#### 2.3. Adaptive Neuro-Fuzzy Inference System (ANFIS)

#### 2.4. Multiple Linear Regression (MLR)

#### 2.5. Model Implementation

## 3. Results and Discussion

#### 3.1. Results from Experiment

#### 3.2. Analysis of Experimental Data Using Statistical Technique

#### 3.3. Adaptive Neuro-Fuzzy Inference System Results

^{2}into consideration, the model prediction for the current was slightly better compared to the voltage for both the training and the testing.

## 4. Conclusions

## Author Contributions

## Funding

## Conflicts of Interest

## References

- Nguyen, T.-T.; Fushinobu, K. Effect of operating conditions and geometric structure on the gas crossover in PEM fuel cell. Sustain. Energy Technol. Assess.
**2020**, 37, 100584. [Google Scholar] [CrossRef] - Baroutaji, A.; Wilberforce, T.; Ramadan, M.; Olabi, A.G. Comprehensive investigation on hydrogen and fuel cell technology in the aviation and aerospace sectors. Renew. Sustain. Energy Rev.
**2019**, 106, 31–40. [Google Scholar] [CrossRef] [Green Version] - Laribi, S.; Mammar, K.; Sahli, Y.; Koussa, K. Analysis and diagnosis of PEM fuel cell failure modes (flooding & drying) across the physical parameters of electrochemical impedance model: Using neural networks method. Sustain. Energy Technol. Assess.
**2019**, 34, 35–42. [Google Scholar] - Ijaodola, O.S.; Hassan, Z.E.; Ogungbemi, E.; Khatib, F.N.; Wilberforce, T.; Thompson, J.; Olabi, A.G. Energy efficiency improvements by investigating the water flooding management on proton exchange membrane fuel cell (PEMFC). Energy
**2019**, 179, 246–267. [Google Scholar] [CrossRef] - Sayed, E.T.; Eisa, T.; Mohamed, H.O.; Abdelkareem, M.A.; Allagui, A.; Alawadhi, H.; Chae, K.-J. Direct urea fuel cells: Challenges and opportunities. J. Power Sources
**2019**, 417, 159–175. [Google Scholar] [CrossRef] - Ogungbemi, E.; Ijaodola, O.; Khatib, F.N.; Wilberforce, T.; el Hassan, Z.; Thompson, J.; Ramadan, M.; Olabi, A.G. Fuel cell membranes—Pros and cons. Energy
**2019**, 172, 155–172. [Google Scholar] [CrossRef] [Green Version] - Priya, K.; Babu, T.S.; Balasubramanian, K.; Kumar, K.S.; Rajasekar, N. A novel approach for fuel cell parameter estimation using simple Genetic Algorithm. Sustain. Energy Technol. Assess.
**2015**, 12, 46–52. [Google Scholar] [CrossRef] - Khatib, F.N.; Wilberforce, T.; Ijaodola, O.; Ogungbemi, E.; El-Hassan, Z.; Durrant, A.; Thompson, J.; Olabi, A.G. Material degradation of components in polymer electrolyte membrane (PEM) electrolytic cell and mitigation mechanisms: A review. Renew. Sustain. Energy Rev.
**2019**, 111, 1–14. [Google Scholar] [CrossRef] - Thamer, B.M.; El-Newehy, M.H.; Barakat, N.A.; Abdelkareem, M.A.; Al-Deyab, S.S.; Kim, H.Y. In-situ synthesis of Ni/N-doped CNFs-supported graphite disk as effective immobilized catalyst for methanol electrooxidation. Int. J. Hydrogen Energy
**2015**, 40, 14845–14856. [Google Scholar] [CrossRef] - Marefati, M.; Mehrpooya, M. Introducing a hybrid photovoltaic solar, proton exchange membrane fuel cell and thermoelectric device system. Sustain. Energy Technol. Assess.
**2019**, 36, 100550. [Google Scholar] [CrossRef] - Abdelkareem, M.A.; al Haj, Y.; Alajami, M.; Alawadhi, H.; Barakat, N.A.M. Ni-Cd carbon nanofibers as an effective catalyst for urea fuel cell. J. Environ. Chem. Eng.
**2018**, 6, 332–337. [Google Scholar] [CrossRef] - Olabi, A.G.; Mahmoud, M.; Soudan, B.; Wilberforce, T.; Ramadan, M. Geothermal based hybrid energy systems, toward eco-friendly energy approaches. Renew. Energy
**2020**, 147 Pt 1, 2003–2012. [Google Scholar] [CrossRef] - Subin, K.; Jithesh, P.K. Experimental study on self-humidified operation in PEM fuel cells. Sustain. Energy Technol. Assess.
**2018**, 27, 17–22. [Google Scholar] [CrossRef] - Wilberforce, T.; Nisar, F.; Ogungbemi, E.; Olabi, A.G. Water Electrolysis Technology. Ref. Module Mater. Sci. Mater. Eng.
**2018**. [Google Scholar] [CrossRef] - Heck, J.D.; Vaz, W.S.; Koylu, U.O.; Leu, M.C. Decoupling pressure and distribution effects of flow fields on polymer electrolyte fuel cell system performance. Sustain. Energy Technol. Assess.
**2019**, 36, 100551. [Google Scholar] [CrossRef] - Wilberforce, T.; El-Hassan, Z.; Khatib, F.N.; al Makky, A.; Baroutaji, A.; Carton, J.G.; Olabi, A.G. Developments of electric cars and fuel cell hydrogen electric cars. Int. J. Hydrogen Energy
**2017**, 42, 25695–25734. [Google Scholar] [CrossRef] [Green Version] - Wilberforce, T.; El-Hassan, Z.; Khatib, F.N.; al Makky, A.; Baroutaji, A.; Carton, J.G.; Mooney, J.; Olabi, A.G. Development of Bi-polar plate design of PEM fuel cell using CFD techniques. Int. J. Hydrogen Energy
**2017**, 42, 25663–25685. [Google Scholar] [CrossRef] [Green Version] - Thamer, B.M.; El-Newehy, M.H.; Barakat, N.A.; Abdelkareem, M.A.; Al-Deyab, S.S.; Kim, H.Y. Influence of nitrogen doping on the catalytic activity of Ni-incorporated carbon nanofibers for alkaline direct methanol fuel cells. Electrochim. Acta
**2014**, 142, 228–239. [Google Scholar] [CrossRef] - Ma, L.; Ingham, D.B.; Pourkashanian, M.; Carcadea, E. Review of computational dynamics modeling of fuel cells. J. Fuel Cell Sci. Technol.
**2005**, 2, 246–257. [Google Scholar] [CrossRef] - Haddad, A.; Bouyekhf, R.; Moudni, A.E. Dynamic modeling and water management in proton exchange membrane fuel cell. Int. J. Hydrogen Energy
**2008**, 33, 6239–6252. [Google Scholar] [CrossRef] - Sharma, M. Artificial neural network fuzzy inference system (ANFIS) for brain tumor detection. arXiv
**2012**, arXiv:1212.0059. [Google Scholar] - Atuahene, S.; Bao, Y.; Ziggah, Y.; Gyan, P.; Li, F. Short-Term Electric Power Forecasting Using Dual-Stage Hierarchical Wavelet-Particle Swarm Optimization-Adaptive Neuro-Fuzzy Inference System PSO-ANFIS Approach Based on Climate Change. Energies
**2018**, 11, 2822. [Google Scholar] [CrossRef] [Green Version] - Ni, M.; Leung, D.Y.C.; Leung, M.K.H. Mathematical modeling of ammonia-fed solid oxide fuel cells with different electrolytes. Int. J. Hydrogen Energy
**2008**, 33, 5765–5772. [Google Scholar] [CrossRef] - Pramuanjaroenkij, A.; Kakac, S.; Zhou, X.Y. Mathematical analysis of planar solid oxide fuel cells. Int. J. Hydrogen Energy
**2008**, 33, 2547–2565. [Google Scholar] [CrossRef] - Rafiq, M.Y.; Bugmann, G.; Easterbrook, D.J. Neural network design for engineering applications. Comput. Struct.
**2001**, 79, 1541–1552. [Google Scholar] [CrossRef] - Gorzalczany, M.B. Computational Intelligence Systems and Applications; Physica-Verlag: Heidelberg, Germany, 2002. [Google Scholar]
- Arriagada, J.; Olausson, P.; Selimovic, A. Artificial neural network simulator for SOFC performance predictions. J. Power Sources
**2002**, 112, 54–60. [Google Scholar] [CrossRef] - Ou, S.; Achenie, L.E.K. A hybrid neural network model for PEM fuel cells. J. Power Sources
**2005**, 140, 319–330. [Google Scholar] [CrossRef] - Wu, X.J.; Zhu, X.J.; Cao, G.Y.; Tu, H.Y. Modelling a SOFC stack based on GA-RBF neural networks identification, networks identification. J. Power Sources
**2007**, 167, 145–150. [Google Scholar] [CrossRef] - Jurado, F. Predictive control of solid oxide fuel cells using fuzzy Hammerstein model. J. Power Sources
**2006**, 158, 245–253. [Google Scholar] [CrossRef] - Sun, T.; Yan, S.; Cao, G.; Zhu, X. Modeling and control PEMFC using fuzzy neural networks. Zhejiang Univ.
**2005**, 10, 1084–1089. [Google Scholar] - Entchev, E.; Yang, L. Application of adaptive neuro-fuzzy inference system techniques and artificial neural networks to predict solid oxide fuel cell performance in residential microgeneration installation. J. Power Sources
**2007**, 170, 122–129. [Google Scholar] [CrossRef] - Wang, R.; Qi, L.; Xie, X.; Ding, Q.; Li, C.; Ma, C.M. Modeling a 5-cell direct methanol fuel cell using adaptive-network based fuzzy inference systems. J. Power Sources
**2008**, 185, 1201–1208. [Google Scholar] [CrossRef] - Wu, X.; Zhu, X.; Cao, G.; Tu, H. Nonlinear modeling of a SOFC based on ANFIS identification. Simul. Model. Pract. Theor.
**2008**, 16, 399–409. [Google Scholar] [CrossRef] - Jang, J.S.R. ANFIS: Adaptive network-based fuzzy inference system. IEEE Trans. Syst. Man Cybern.
**1993**, 23, 665–685. [Google Scholar] [CrossRef] - Jang, J.S.R.; Sun, C.T. Neuro-fuzzy modeling and control. Proc. IEEE
**1995**, 83, 378–406. [Google Scholar] [CrossRef] - Fuzzy Logic. Toolbox User’s Guide; Version 2; The MathWorks, Inc.: Natick, MA, USA, 2001; Available online: https://www.tandfonline.com/toc/tfie20/current?gclid=CjwKCAjw26H3BRB2EiwAy32zhfLMQsHzBOxi7pKRErCr9LUq2cmn5dU5_jTDjL5EVxRSdac9iZoVeBoCrFkQAvD_BwE (accessed on 16 June 2020).
- Wang, L.; Husar, A.; Xhou, T.Z.; Liu, H. A parametric study of PEM fuel cell performances. Int. J. Hydrogen Energy
**2003**, 28, 1263–1272. [Google Scholar] [CrossRef] - Jang, J.S.R. Input selection for ANFIS Learning. In Proceedings of the IEEE 5th International Fuzzy Systems, New Orleans, LA, USA, 11 September 1996. [Google Scholar]

**Figure 3.**Performance of proton exchange membrane fuel cell at lower pressure and flow rate of the reactant.

Level of numerical design | −1 | +1 |

Input variable level | Minimum | Maximum |

${H}_{2}$ pressure | 1 bar | 2.5 bar |

${O}_{2}$ pressure | 0.8 bar | 2.3 bar |

${H}_{2}$ flow rates | 15 mL/min | 150 mL/min |

${O}_{2}$ flow rates | 15 mL/min | 150 mL/min |

Fuel Cell Component | Material | Characteristics |
---|---|---|

Housing | Acetyl | Supplier: (Fuel Cell Store) |

Membrane electrode assembly | Nafion 212 | Active area: 3.4 × 3.4 cm Catalyst loading 0.4 mg/cm ^{2} Pt/c.0.55 g cm^{3} bulkSupplier: Fuel cell store |

Bipolar plate | Graphite | 24 pores/cm Thickness: 0.65 mm Supplier: Fuel Cell Store |

Sealing | Silicon | Thickness: 0.8 mm Supplier: Fuel Cell Store |

Data | N | Mean | Standard Deviation | Sum | Minimum | Median | Maximum |
---|---|---|---|---|---|---|---|

Hydrogen Pressure | 22 | 1.71591 | 0.48975 | 37.75 | 1 | 1.75 | 2.5 |

Oxygen Pressure | 22 | 1.51591 | 0.4316 | 33.35 | 0.8 | 1.55 | 2.3 |

Hydrogen flow rate | 22 | 85.56818 | 48.75187 | 1882.5 | 15 | 82.5 | 150 |

Oxygen Flow Rate | 22 | 85.56818 | 44.07739 | 1882.5 | 15 | 82.5 | 150 |

Current | 22 | 0.50955 | 0.44897 | 11.21 | 0.065 | 0.339 | 1.464 |

Voltage | 22 | 0.62314 | 0.12953 | 13.709 | 0.357 | 0.6645 | 0.768 |

DF | Sum of Squares | Mean Square | F Value | Prob > F | |
---|---|---|---|---|---|

Model | 4 | 1.38408 | 0.34602 | 2.06468 | 0.13053 |

Error | 17 | 2.84904 | 0.16759 | ||

Total | 21 | 4.23312 |

DF | Sum of Squares | Mean Square | F Value | Prob > F | |
---|---|---|---|---|---|

Model | 4 | 0.10697 | 0.02674 | 1.85269 | 0.16532 |

Error | 17 | 0.24538 | 0.01443 | ||

Total | 21 | 0.35235 |

Current | Voltage | ||||
---|---|---|---|---|---|

Variable | Value | Std. Error | Variable | Value | Std. Error |

Constant | 1.5481 | 0.48767 | Constant | 0.33199 | 0.14312 |

Hydrogen Pressure | −0.36593 | 0.18367 | Hydrogen Pressure | 0.09843 | 0.0539 |

Oxygen Pressure | −0.14583 | 0.20849 | Oxygen Pressure | 0.04059 | 0.06119 |

Hydrogen flow rate | −0.00336 | 0.00185 | Hydrogen flow rate | 9.722 × 10^{−4} | 5.42 × 10^{−4} |

Oxygen Flow Rate | 0.00114 | 0.00204 | Oxygen Flow Rate | −2.62 × 10^{−4} | 5.989 × 10^{−4} |

Adjusted R^{2} | 0.1686 | Adjusted R^{2} | 0.1397 |

Variable | Current | Voltage |
---|---|---|

Value | Value | |

Number of nodes | 55 | 193 |

Number of linear parameters | 80 | 405 |

Number of nonlinear parameters | 16 | 24 |

Total number of parameters | 96 | 429 |

Number of training data pairs | 18 | 19 |

Number of checking data pairs | 0 | 0 |

Number of fuzzy rules | 16 | 16 |

Training Time (s) | RMSE | R^{2} | ||||
---|---|---|---|---|---|---|

Training | Testing | Training | Testing | Training | Testing | |

Current | 8.04 | 8.32 | 0.028235 | 0.42473 | 0.99193 | 0.9998 |

voltage | 9.92 | 8.620 | 0.006513 | 0.078608 | 0.99069 | 0.99958 |

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Wilberforce, T.; Olabi, A.G.
Performance Prediction of Proton Exchange Membrane Fuel Cells (PEMFC) Using Adaptive Neuro Inference System (ANFIS). *Sustainability* **2020**, *12*, 4952.
https://doi.org/10.3390/su12124952

**AMA Style**

Wilberforce T, Olabi AG.
Performance Prediction of Proton Exchange Membrane Fuel Cells (PEMFC) Using Adaptive Neuro Inference System (ANFIS). *Sustainability*. 2020; 12(12):4952.
https://doi.org/10.3390/su12124952

**Chicago/Turabian Style**

Wilberforce, Tabbi, and Abdul Ghani Olabi.
2020. "Performance Prediction of Proton Exchange Membrane Fuel Cells (PEMFC) Using Adaptive Neuro Inference System (ANFIS)" *Sustainability* 12, no. 12: 4952.
https://doi.org/10.3390/su12124952