IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v366y2024ics0306261924006408.html
   My bibliography  Save this article

Machine learning-based screening of fuel properties for SI and CI engines using a hybrid group extraction method

Author

Listed:
  • Chen, Yong
  • Zheng, Zunqing
  • Lu, Zhiyuan
  • Wang, Hu
  • Wang, Changhui
  • Sun, Xingyu
  • Xu, Linxun
  • Yao, Mingfa

Abstract

The design of high-performance fuels is crucial for achieving clean and efficient combustion of engines. In the current study, a framework for machine learning (ML) model-based fuel design is presented to identify compounds with desired properties for internal combustion engine (ICE) applications. Descriptors computed from newly proposed structural and positional-based group extraction method in this study are used as input in ML models due to the simplicity and computational-efficiency. The ML models were trained and validated using publically available experimental data for up to 1135 compounds. The results demonstrated a high level of predictive accuracy, with R2 values generally exceeding 0.99 for 11 physicochemical properties including melting point, boiling point, enthalpy of vaporization, surface tension, dynamic viscosity, low heating value, liquid density, yield sooting index, cetane number, research octane number and motor octane number. Furthermore, by employing the developed ML models to predict new data, a Fuel Property Database containing 1135 fuels with 12 fuel properties is established, enhanced by an interface for a user-friendly Fuel Physicochemical Properties Prediction Tool that facilitates swift property predictions and database expansion. The Pearson correlation coefficient (PCC) approach is subsequently employed to assess the correlation between descriptors and predicted or experimental properties. The strong agreement between the correlations affirms the effective predictive performance of the ML models within the calibrated data range. Additionally, a PCC analysis is conducted to reveal the individual effects of influential factors and their interactions, highlighting significant features like molecular weight size, degree of branching, and functional group content that influence physical and chemical properties, thereby providing valuable insights for fuel design and optimization. Finally, a initial comprehensive data-driven screening was carried out to identify potential fuel candidates that meet the key property limits for combustion applications in both spark-ignition (SI) and compression-ignition (CI) engines.

Suggested Citation

  • Chen, Yong & Zheng, Zunqing & Lu, Zhiyuan & Wang, Hu & Wang, Changhui & Sun, Xingyu & Xu, Linxun & Yao, Mingfa, 2024. "Machine learning-based screening of fuel properties for SI and CI engines using a hybrid group extraction method," Applied Energy, Elsevier, vol. 366(C).
  • Handle: RePEc:eee:appene:v:366:y:2024:i:c:s0306261924006408
    DOI: 10.1016/j.apenergy.2024.123257
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261924006408
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.apenergy.2024.123257?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. Razali, S.Z. & Yunus, R. & Abdul Rashid, Suraya & Lim, H.N. & Mohamed Jan, B., 2018. "Review of biodegradable synthetic-based drilling fluid: Progression, performance and future prospect," Renewable and Sustainable Energy Reviews, Elsevier, vol. 90(C), pages 171-186.
    2. Zhang, Fengyu & Su, Xinchao & Tan, Aoli & Yao, Jingjing & Li, Haipu, 2022. "Prediction of research octane number loss and sulfur content in gasoline refining using machine learning," Energy, Elsevier, vol. 261(PA).
    Full references (including those not matched with items on IDEAS)

    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. Jian Chen & Jiajun Zhu & Xu Qin & Wenxiang Xie, 2023. "Reducing Octane Number Loss in Gasoline Refining Process by Using the Improved Sparrow Search Algorithm," Sustainability, MDPI, vol. 15(8), pages 1-21, April.
    2. Alaa Ahmed & Amin Sharifi Haddad & Roozbeh Rafati & Ahmed Bashir & Ahmed M. AlSabagh & Amany A. Aboulrous, 2021. "Developing a Thermally Stable Ester-Based Drilling Fluid for Offshore Drilling Operations by Using Aluminum Oxide Nanorods," Sustainability, MDPI, vol. 13(6), pages 1-18, March.

    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:appene:v:366:y:2024:i:c:s0306261924006408. 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.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    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.