A RBF artificial neural network to predict a fuel cell maximum power point

• Autorzy: Foughali Yahia , Mankour Mohamed , Sekour Mohamed , Azzeddine Hocine Abdelhak , Larbaoui Ahmed , Chaouch Djamel Eddine , Berka Mohammed

Identyfikatory

DOI

10.15199/48.2022.07.17

Warianty tytułu

PL

Sztuczna sieć neuronowa RBF do przewidywania maksymalnego punktu mocy ogniwa paliwowego

• Języki publikacji: EN

Abstrakty

EN

In this article, an artificial neural network (ANN) based maximum power point tracker (MPTT) for proton exchange membrane fuel cell (PEMFC) is proposed. For this purpose, a Radial Basis Function Artificial Neural Network (RBF ANN) is used to predict the voltage and the current of a fuel cell maximum power point at different fuel cell operating conditions. To train the proposed artificial neural network, a set of maximum power points defined by their corresponding current and voltage values is generated using a validated electrochemical fuel cell model. To ensure the validity of the ANN, we compare the results found by the ANN to those obtained using the electrochemical PEMFC model. The results show that the developed ANN can accurately and quickly predict current and voltage fuel cells at maximum power point for any operating conditions.

PL

W tym artykule zaproponowano śledzenie maksymalnego punktu mocy (MPTT) oparte na sztucznej sieci neuronowej (ANN) dla ogniwa paliwowego z membraną do wymiany protonów (PEMFC). W tym celu wykorzystuje się sztuczną sieć neuronową Radial Basis Function (RBF ANN) do przewidywania napięcia i prądu punktu maksymalnej mocy ogniwa paliwowego w różnych warunkach pracy ogniwa paliwowego. Aby wytrenować proponowaną sztuczną sieć neuronową, przy użyciu sprawdzonego modelu elektrochemicznego ogniwa paliwowego generowany jest zestaw maksymalnych punktów mocy określonych przez odpowiadające im wartości prądu i napięcia. Aby zapewnić wiarygodność ANN, porównujemy wyniki uzyskane przez ANN z wynikami uzyskanymi przy użyciu elektrochemicznego modelu PEMFC. Wyniki pokazują, że opracowana SSN może dokładnie i szybko przewidywać prąd i napięcie ogniw paliwowych w punkcie maksymalnej mocy w dowolnych warunkach pracy.

Słowa kluczowe

EN

artificial neural network; ANN; proton exchange membrane fuel cell; PEMFC; maximum power point tracker; MPPT

PL

sztuczna sieć neuronowa; ANN; ogniwo paliwowe; MCFC; maksymalny punkt mocy

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2022
• Tom: R. 98, nr 7
• Strony: 100--104
• Opis fizyczny: Bibliogr. 32 poz., rys., tab.

Twórcy

autor

Foughali Yahia

• Faculty of Technology, University Dr. MoulayTahar, Saida Algeria

autor

Mankour Mohamed

• Faculty of Technology, University Dr. MoulayTahar, Saida Algeria

autor

Sekour Mohamed

• Faculty of Technology, University Dr. MoulayTahar, Saida Algeria

autor

Azzeddine Hocine Abdelhak

• University Mustapha Stambouli of Mascara, Algeria
• LSTE Laboratory, Faculty of Science

autor

Larbaoui Ahmed

• University Mustapha Stambouli of Mascara, Algeria

autor

Chaouch Djamel Eddine

• University Mustapha Stambouli of Mascara, Algeria
• LSTE Laboratory, Faculty of Science

autor

Berka Mohammed

• University Mustapha Stambouli of Mascara, Algeria

Bibliografia

• 1. Jianxin L , Tiebiao Z, Yang Q C. - Maximum Power Point Tracking With Fractional Order High Pass filter for proton Exchange Membrane Fuel Cell. IEEE/CAA Journal of a Automatica Sinica, 4(2017) ,No. 1, 70–79
• 2. Rashid A., Yousaf K., Shah S, Shaukat N., Electricity crisis and the significance of indigenous coal for electric power generation. Electronic Devices, 4 (2015), No. 1, 1−11
• 3. Owusu P.A., Sakordi S.A., A review of renewable energy sources, sustainability issues and climate change mitigation. Cogent Engineering, 3 (2016), 1167990
• 4. D Bruijn F., The current status of fuel cell technology for mobile and stationary applications, Green Chemistry, 7 (2005), 132–150
• 5. Reddy, K.J., Sudhakar, N.,A new RBFN based MPPT controller for grid connected PEMFC system with high step-up three-phase IBC, Int. J. Hydrogen Energy 43(2018), No.1-14, 17835-17848
• 6. Wang, T., Li, Q., Qiu, Y., Yin, L., Liu, L., Chen, W., Efficiency extreme point tracking strategy based on FFRLS online identification for PEMFC system, IEEE Trans Energy Convers, 34(2019), No.2, 952-963
• 7. Savrun M M., Inci M., Adaptive neuro-fuzzy inference system combined with genetic algorithm to improve power extraction capability in fuel cell applications,Journal of Cleaner Production 299 (2021), No.126944
• 8. Srinivasan S., Tiwari R., Krishnamooty M., Lalitha M.P., Raj K.K., Neural network based MPPT control with reconfigured quadratic boost converter for fuel cell. International Journal of Hydrogen Energy, 46 (2021), No. 9, 6709-9719
• 9. Krishnamooty M., Ajay P., Raj V., Energy storage based MG connected system for optimal management of energy: An ANFMDA technique. International Journal of Hydrogen Energy, 46 (2019), No. 16, 255-257
• 10. Dargahi M,. Rouhi J., Rezanejad M., Shakerie M., Maximum Power Point Tracking for Fuel Cell in Fuel Cell/Battery Hybrid Power Systems. European Journal of Scientific Research, 24 (2009), No.4, 538-548
• 11. Wang M.H., Yau H.T., Wang T.Y., Extension Sliding Mode Controller for Maximum Power Point Tracking of Hydrogen Fuel Cells. Abstract and Applied Analysis, (2013), 371064
• 12. Derbeli M., Brambones O., Sbita L., A Robust Maximum Power Point Tracking Control Method for a PEM Fuel Cell Power System. Applied Sciences, 8 (2018), 2449 13.
• 13. Inci, M., Caliskan, A., Performance enhancement of energy extraction capability for fuel cell implementations with improved Cuckoo search algorithm. Int. J. Hydrogen Energy, 45(2020), No.19,11309-11320.
• 14. Rana, K.P.S., Kumar, V., Sehgal, N., George, S.,. A Novel dPdI feedback based control scheme using GWO tuned PIDcontroller for efficient MPPT of PEM fuel cell. ISA (Instrum. Soc. Am.) Trans, 93(2019), 312-324
• 15. Mumtaz S., Khan L., Adaptive control paradigm for photovoltaic and solid oxide fuel cell in a grid-integrated hybrid renewable energy system. PLoS ONE, 12 (2017à), No. 3, 0173966
• 16. Harrag A., Bahri H., Novel neural network IC-based variablestep size fuel cell MPPT controller Performance,efficiencyand life time improvement. International Journal of Hydrogen Energy,42 (2017), No. 5, 3549-63
• 17. Srinivasan S., Tiwari R., Krishnamoorthy M., Lalitha M.P., Raj K.K., Neural network based MPPT control with reconfigured quadratic boost converter for fuel cell application. International Journal of Hydrogen Energy, 42 (2017), No. 5, 3549-3563
• 18. Azzeddine H.A., Tioursi M., Chaouch D., khiari B., An offline trained artificial neural network to predict a photovoltaic panel maximum power point. Revue Roumaine des Sciences Techniques – Série Electrotechnique et Energétique, 61 (2016), No. 3, 7996-8010
• 19. Yu H, Xie T, Paszczynski S, Wilamowski B.K. Advantages of radial basis function networks for dynamic system design IEEE Transactions on Industrial Electronics, 58 (2011), No. 12, 5438-5450
• 20. Azzeddine H.A., Chaouch D., Berka M , Hebali M, Larbaoui A, Tioursi M. Fuel cell grid connected system with active power generation and reactive power compensation features.Przegląd Elektrotechniczny, 11 (2020), 124-127
• 21. Yuan X.Z., Wang H., PEM Fuel Cell Fundamentals, In: Zhang J. (editor), PEM Fuel Cell Electrocatalysts and Catalyst Layers, Springer (2008), 1-87
• 22. Samal S., Ramana M., Barik P.K, Modeling and simulation of Interleaved boost converter with MPPT for Fuel Cell Application. IEEE International Conference on Technologies for Smart-City Energy Security and Power (ICSESP-2018),March 28-30, 2018, Bhubaneswar, India
• 23. Xu L., Hong P.,Fang C., Li J., Ouyang M., Lehnert W., interactions between a polymer electrolyte membrane fuel cell and boost converter utilizing a multiscale model. Journal of Power Sources, 395 (2018) 237-250
• 24. Mann R.F., Amphlett J.C., Hooper M.A.I., Jensen H.M. Peppley B.A., Roberge P.R., Development and application of a generalised steady - state electrochemical model for a PEM fuel cell. Journal of Power Sources, 86 (2000),No.1–2,173-180
• 25. Fowler M.W., Mann R.F., Amphlett J.C., Peppley B.A., Roberge P.R., Incorporation of voltage degradation into a generalized steady state electrochemical model for a PEM fuel cell. Journal of Power Sources, 10 (2002), No.1–2, 274–283
• 26. Maxoulis C.N., Tsinoglou D.N., Koltaskis G.C., Modeling ofautomotive fuel cell operation in driving cycles Energy Conversion. Energy Conversion and Management, 45 (2004) 559–573
• 27. Maher A.R., Al-Baghdadi S., Modelling of proton exchange membrane fuel cell performance based on semi-empirical equations. Renewable Energy, 30 (2005), 1587-1599
• 28. Reddy K.J., Sudhakar N., High voltage gain interleaved boost converter with neural network based MPPT controller for fuel cell based electric vehicle applications. IEEE Access, 6 (2018), No.3899-3908
• 29. Saravanan S., Babu N.R., Maximum power point tracking algorithms for photovoltaic system – A review. Renewable Energy and Sustainable Energy Review, 57 (2016), No 192–204
• 30. Kasabo N., Foundations of neural networks, fuzzy system and knowledge engineering. The MIT Press, London, 1998.,
• 31. Al–Majidi S.D, Abbod M.F, Al-RaweshidyH.S, A particle swarm optimisation-trained feedforward neural network for predicting the maximum power point of a photovoltaic array. Engineering Applications of Artificial Intelligence, 92 (2020) 103688
• 32. Gu P., Xing L., Wang Y., Feng J., Peng X., A multi-objective parametric study of the claw hydrogen pump for fuel cell veicles using taguchi method and ANN. International Journal of Hydrogen Energy, 46 (2021), No. 9, 6680-6692

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).