IDEAS home Printed from https://ideas.repec.org/a/eee/energy/v280y2023ics0360544223014822.html
   My bibliography  Save this article

Deep learning models in Python for predicting hydrogen production: A comparative study

Author

Listed:
  • Devasahayam, Sheila

Abstract

This study relates to predicting hydrogen production using deep learning models. The co-gasification of biomass and plastics dataset used gasification temperature, particle size of biomass rubber seed shell (RSS) and High-Density Polyethylene (HDPE), and the amount of plastic in the mixture as the independent variables, and the amount of hydrogen produced as the dependent variable. It was found that during the co-gasification particle size is a controlling factor for hydrogen production due to the influence on surface reactions, while temperature had no significant effect. The neural network models were developed using Keras and two different architectures were compared with and without L1 and L2 regularizers. The values for L1 and L2 are determined using the gridserach: for the 1 archtecture, the ideal L1 value = 0.010; and the ideal L2 value = 0.000001 and for the 2nd architecture, The ideal L1 value is 0.100; and the ideal L2 value is 0.000010 using the lowest mean squared error values for the test sets. The mean cross-validation scores indicated that the second architecture performed better. The mean cross_val_score using the negative mean square error, for the 1st architecture, with l2 regularizers (0.000001) is determined as −20.05 (13.10) nMSE for Kfold, 10; and for the 2nd architecture l2 regularizers (0.000010) as −8.22 (7.77) nMSE for Kfold, 10, indicate the 2nd architecture performs better. The best model parameters for both architectures were determined using Grid Search CV. The best model hyperparameters using Grid Search is batch_size, 3; epochs,100; optimizer, rmsprop for the first architechure with negative mean square error, −20.95; and for the 2nd architecture, batch_size, 5; epochs,100; optimizer, adam with negative mean square error, −7.38, indicating the 2nd architecture to be a better model. The Keras Wrapper improved the performance of the model for the first architecture, but not for the second architecture. The permutation feature importance for architecture 1 (in descending order) is: size of RSS, size of HDPE, per cent plastics in mixture and temperature. For architecture 2, in descending order: size of HDPE, size of RSS, per cent plastics in mixture and temperature. Overall, the study demonstrates the potential of deep learning models for predicting hydrogen production.

Suggested Citation

  • Devasahayam, Sheila, 2023. "Deep learning models in Python for predicting hydrogen production: A comparative study," Energy, Elsevier, vol. 280(C).
  • Handle: RePEc:eee:energy:v:280:y:2023:i:c:s0360544223014822
    DOI: 10.1016/j.energy.2023.128088
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0360544223014822
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.energy.2023.128088?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Zhang, Bowei & Guo, Simao & Jin, Hui, 2022. "Production forecast analysis of BP neural network based on Yimin lignite supercritical water gasification experiment results," Energy, Elsevier, vol. 246(C).
    2. Oyedun, Adetoyese Olajire & Gebreegziabher, Tesfaldet & Ng, Denny K.S. & Hui, Chi Wai, 2014. "Mixed-waste pyrolysis of biomass and plastics waste – A modelling approach to reduce energy usage," Energy, Elsevier, vol. 75(C), pages 127-135.
    3. Han, Si Woo & Lee, Jeong Jae & Tokmurzin, Diyar & Lee, Seok Hyeong & Nam, Ji Young & Park, Sung Jin & Ra, Ho Won & Mun, Tae-Young & Yoon, Sang Jun & Yoon, Sung Min & Moon, Ji Hong & Lee, Jae Goo & Kim, 2022. "Gasification characteristics of waste plastics (SRF) in a bubbling fluidized bed: Effects of temperature and equivalence ratio," Energy, Elsevier, vol. 238(PC).
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Liang, Xing-Yu & Zhang, Bo & Zhang, Chun-Lu, 2024. "Physics-informed deep residual neural network for finned-tube evaporator performance prediction," Energy, Elsevier, vol. 302(C).
    2. Izadi, Mohammad Javad & Hassani, Pourya & Raeesi, Mehrdad & Ahmadi, Pouria, 2024. "A novel WaveNet-GRU deep learning model for PEM fuel cells degradation prediction based on transfer learning," Energy, Elsevier, vol. 293(C).

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Stančin, H. & Mikulčić, H. & Wang, X. & Duić, N., 2020. "A review on alternative fuels in future energy system," Renewable and Sustainable Energy Reviews, Elsevier, vol. 128(C).
    2. Fivga, Antzela & Dimitriou, Ioanna, 2018. "Pyrolysis of plastic waste for production of heavy fuel substitute: A techno-economic assessment," Energy, Elsevier, vol. 149(C), pages 865-874.
    3. Zhang, Bowei & Zhao, Xiao & Zhang, Jie & Wang, Junying & Jin, Hui, 2023. "An investigation of the density of nano-confined subcritical/supercritical water," Energy, Elsevier, vol. 284(C).
    4. Zhang, Hao & Tong, Xiangqian & Yin, Jun & Blaabjerg, Frede, 2023. "Neural network-aided 4-DF global efficiency optimal control for the DAB converter based on the comprehensive loss model," Energy, Elsevier, vol. 262(PA).
    5. Xue, Xiaodong & Han, Wei & Xin, Yu & Liu, Changchun & Jin, Hongguang & Wang, Xiaodong, 2023. "Proposal and energetic and exergetic evaluation of a hydrogen production system with synergistic conversion of coal and solar energy," Energy, Elsevier, vol. 283(C).
    6. Ghulamullah Maitlo & Imran Ali & Hubdar Ali Maitlo & Safdar Ali & Imran Nazir Unar & Muhammad Bilal Ahmad & Darya Khan Bhutto & Ramesh Kumar Karmani & Shamim ur Rehman Naich & Raja Umer Sajjad & Sikan, 2022. "Plastic Waste Recycling, Applications, and Future Prospects for a Sustainable Environment," Sustainability, MDPI, vol. 14(18), pages 1-27, September.
    7. Lucio Zaccariello & Maria Laura Mastellone, 2023. "Fuel Gas Production from the Co-Gasification of Coal, Plastic Waste, and Wood in a Fluidized Bed Reactor: Effect of Gasifying Agent and Bed Material," Sustainability, MDPI, vol. 15(9), pages 1-19, May.
    8. Lopez, Gartzen & Artetxe, Maite & Amutio, Maider & Bilbao, Javier & Olazar, Martin, 2017. "Thermochemical routes for the valorization of waste polyolefinic plastics to produce fuels and chemicals. A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 73(C), pages 346-368.
    9. Vera Marcantonio & Luisa Di Paola & Marcello De Falco & Mauro Capocelli, 2023. "Modeling of Biomass Gasification: From Thermodynamics to Process Simulations," Energies, MDPI, vol. 16(20), pages 1-30, October.
    10. Fazil, A. & Kumar, Sandeep & Mahajani, Sanjay M., 2022. "Downdraft co-gasification of high ash biomass and plastics," Energy, Elsevier, vol. 243(C).
    11. Navarro, M.V. & López, J.M. & Veses, A. & Callén, M.S. & García, T., 2018. "Kinetic study for the co-pyrolysis of lignocellulosic biomass and plastics using the distributed activation energy model," Energy, Elsevier, vol. 165(PA), pages 731-742.
    12. Xiao, Ruirui & Yang, Wei & Cong, Xingshun & Dong, Kai & Xu, Jie & Wang, Dengfeng & Yang, Xin, 2020. "Thermogravimetric analysis and reaction kinetics of lignocellulosic biomass pyrolysis," Energy, Elsevier, vol. 201(C).
    13. Liu, Qian & Sun, Jianguo & Gu, Yonghua & Zhong, Wenqi & Gao, Ke, 2024. "Experimental study on CO2 co-gasification characteristics of biomass and waste plastics: Insight into interaction and targeted regulation method," Energy, Elsevier, vol. 292(C).
    14. Guiliang Li & Bingyuan Hong & Haoran Hu & Bowen Shao & Wei Jiang & Cuicui Li & Jian Guo, 2022. "Risk Management of Island Petrochemical Park: Accident Early Warning Model Based on Artificial Neural Network," Energies, MDPI, vol. 15(9), pages 1-13, April.
    15. Hao, Yichen & Xie, Xinyu & Zhao, Pu & Wang, Xiaofang & Ding, Jiaqi & Xie, Rong & Liu, Haitao, 2023. "Forecasting three-dimensional unsteady multi-phase flow fields in the coal-supercritical water fluidized bed reactor via graph neural networks," Energy, Elsevier, vol. 282(C).
    16. Krishna Moorthy Rajendran & Deepak Kumar & Bhawna Yadav Lamba & Praveen Kumar Ghodke & Amit Kumar Sharma & Leonidas Matsakas & Alok Patel, 2023. "Effect of Plasto-Oil Blended with Diesel Fuel on the Performance and Emission Characteristics of Partly Premixed Charge Compression Ignition Engines with and without Exhaust Gas Recirculation (EGR)," Energies, MDPI, vol. 16(9), pages 1-15, April.
    17. Ramos, Ana & Monteiro, Eliseu & Silva, Valter & Rouboa, Abel, 2018. "Co-gasification and recent developments on waste-to-energy conversion: A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 81(P1), pages 380-398.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:energy:v:280:y:2023:i:c:s0360544223014822. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.journals.elsevier.com/energy .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.