IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v14y2021i2p439-d480824.html
   My bibliography  Save this article

Detection of Knocking Combustion Using the Continuous Wavelet Transformation and a Convolutional Neural Network

Author

Listed:
  • Achilles Kefalas

    (Institute of Internal Combustion Engines and Thermodynamics, Graz University of Technology, 8010 Graz, Austria)

  • Andreas B. Ofner

    (Know-Center GmbH, Research Center for Data-Driven Business & Big Data Analytics, 8010 Graz, Austria)

  • Gerhard Pirker

    (LEC GmbH, Large Engine Competence Center, 8010 Graz, Austria)

  • Stefan Posch

    (LEC GmbH, Large Engine Competence Center, 8010 Graz, Austria)

  • Bernhard C. Geiger

    (Know-Center GmbH, Research Center for Data-Driven Business & Big Data Analytics, 8010 Graz, Austria)

  • Andreas Wimmer

    (Institute of Internal Combustion Engines and Thermodynamics, Graz University of Technology, 8010 Graz, Austria
    LEC GmbH, Large Engine Competence Center, 8010 Graz, Austria)

Abstract

The phenomenon of knock is an abnormal combustion occurring in spark-ignition (SI) engines and forms a barrier that prevents an increase in thermal efficiency while simultaneously reducing CO 2 emissions. Since knocking combustion is highly stochastic, a cyclic analysis of in-cylinder pressure is necessary. In this study we propose an approach for efficient and robust detection and identification of knocking combustion in three different internal combustion engines. The proposed methodology includes a signal processing technique, called continuous wavelet transformation (CWT), which provides a simultaneous analysis of the in-cylinder pressure traces in the time and frequency domains with coefficients. These coefficients serve as input for a convolutional neural network (CNN) which extracts distinctive features and performs an image recognition task in order to distinguish between non-knock and knock. The results revealed the following: (i) The CWT delivered a stable and effective feature space with the coefficients that represents the unique time-frequency pattern of each individual in-cylinder pressure cycle; (ii) the proposed approach was superior to the state-of-the-art threshold value exceeded (TVE) method with a maximum amplitude pressure oscillation (MAPO) criterion improving the overall accuracy by 6.15 percentage points (up to 92.62%); and (iii) The CWT + CNN method does not require calibrating threshold values for different engines or operating conditions as long as enough and diverse data is used to train the neural network.

Suggested Citation

  • Achilles Kefalas & Andreas B. Ofner & Gerhard Pirker & Stefan Posch & Bernhard C. Geiger & Andreas Wimmer, 2021. "Detection of Knocking Combustion Using the Continuous Wavelet Transformation and a Convolutional Neural Network," Energies, MDPI, vol. 14(2), pages 1-19, January.
    • Handle: RePEc:gam:jeners:v:14:y:2021:i:2:p:439-:d:480824
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/14/2/439/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/14/2/439/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Seokwon Cho & Jihwan Park & Chiheon Song & Sechul Oh & Sangyul Lee & Minjae Kim & Kyoungdoug Min, 2019. "Prediction Modeling and Analysis of Knocking Combustion using an Improved 0D RGF Model and Supervised Deep Learning," Energies, MDPI, vol. 12(5), pages 1-25, March.
    2. Zhen, Xudong & Wang, Yang & Xu, Shuaiqing & Zhu, Yongsheng & Tao, Chengjun & Xu, Tao & Song, Mingzhi, 2012. "The engine knock analysis – An overview," Applied Energy, Elsevier, vol. 92(C), pages 628-636.
    3. Linfeng Gou & Huihui Li & Hua Zheng & Huacong Li & Xiaoning Pei, 2020. "Aeroengine Control System Sensor Fault Diagnosis Based on CWT and CNN," Mathematical Problems in Engineering, Hindawi, vol. 2020, pages 1-12, January.
    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. Sok, Ratnak & Jeyamoorthy, Arravind & Kusaka, Jin, 2024. "Novel virtual sensors development based on machine learning combined with convolutional neural-network image processing-translation for feedback control systems of internal combustion engines," Applied Energy, Elsevier, vol. 365(C).
    2. Stefan Posch & Clemens Gößnitzer & Andreas B. Ofner & Gerhard Pirker & Andreas Wimmer, 2022. "Modeling Cycle-to-Cycle Variations of a Spark-Ignited Gas Engine Using Artificial Flow Fields Generated by a Variational Autoencoder," Energies, MDPI, vol. 15(7), pages 1-16, March.
    3. Hosseini, M. & Chitsaz, I., 2023. "Knock probability determination employing convolutional neural network and IGTD algorithm," Energy, Elsevier, vol. 284(C).
    4. Haruki Tajima & Takuya Tomidokoro & Takeshi Yokomori, 2022. "Deep Learning for Knock Occurrence Prediction in SI Engines," Energies, MDPI, vol. 15(24), pages 1-14, December.
    5. Jian Gao & Anren Yao & Yeyi Zhang & Guofan Qu & Chunde Yao & Shemin Zhang & Dongsheng Li, 2021. "Investigation into the Relationship between Super-Knock and Misfires in an SI GDI Engine," Energies, MDPI, vol. 14(8), pages 1-18, April.

    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. Zhu, Sipeng & Akehurst, Sam & Lewis, Andrew & Yuan, Hao, 2022. "A review of the pre-chamber ignition system applied on future low-carbon spark ignition engines," Renewable and Sustainable Energy Reviews, Elsevier, vol. 154(C).
    2. Haruki Tajima & Takuya Tomidokoro & Takeshi Yokomori, 2022. "Deep Learning for Knock Occurrence Prediction in SI Engines," Energies, MDPI, vol. 15(24), pages 1-14, December.
    3. Tehseen Johar & Chiu-Fan Hsieh, 2023. "Design Challenges in Hydrogen-Fueled Rotary Engine—A Review," Energies, MDPI, vol. 16(2), pages 1-22, January.
    4. Zhen, Xudong & Wang, Yang, 2013. "Study of ignition in a high compression ratio SI (spark ignition) methanol engine using LES (large eddy simulation) with detailed chemical kinetics," Energy, Elsevier, vol. 59(C), pages 549-558.
    5. Amaral, Lucimar Venâncio & Santos, Nathália Duarte Souza Alvarenga & Roso, Vinícius Rückert & Sebastião, Rita de Cássia de Oliveira & Pujatti, Fabrício José Pacheco, 2021. "Effects of gasoline composition on engine performance, exhaust gases and operational costs," Renewable and Sustainable Energy Reviews, Elsevier, vol. 135(C).
    6. La Xiang & Enzhe Song & Yu Ding, 2018. "A Two-Zone Combustion Model for Knocking Prediction of Marine Natural Gas SI Engines," Energies, MDPI, vol. 11(3), pages 1-23, March.
    7. Guardiola, C. & Pla, B. & Bares, P. & Barbier, A., 2018. "An analysis of the in-cylinder pressure resonance excitation in internal combustion engines," Applied Energy, Elsevier, vol. 228(C), pages 1272-1279.
    8. Wei, Haiqiao & Feng, Dengquan & Pan, Mingzhang & Pan, JiaYing & Rao, XiaoKang & Gao, Dongzhi, 2016. "Experimental investigation on the knocking combustion characteristics of n-butanol gasoline blends in a DISI engine," Applied Energy, Elsevier, vol. 175(C), pages 346-355.
    9. Pla, Benjamí n & Bares, Pau & Jiménez, Irina & Guardiola, Carlos & Zhang, Yahui & Shen, Tielong, 2020. "A fuzzy logic map-based knock control for spark ignition engines," Applied Energy, Elsevier, vol. 280(C).
    10. Meng, Hao & Ji, Changwei & Shen, Jianpu & Yang, Jinxin & Xin, Gu & Chang, Ke & Wang, Shuofeng, 2023. "Analysis of combustion characteristics under cooled EGR in the hydrogen-fueled Wankel rotary engine," Energy, Elsevier, vol. 263(PB).
    11. Wang, Chenyao & Zhang, Fujun & Wang, Enhua & Yu, Chuncun & Gao, Hongli & Liu, Bolan & Zhao, Zhenfeng & Zhao, Changlu, 2019. "Experimental study on knock suppression of spark-ignition engine fuelled with kerosene via water injection," Applied Energy, Elsevier, vol. 242(C), pages 248-259.
    12. Vafamehr, Hassan & Cairns, Alasdair & Sampson, Ojon & Koupaie, Mohammadmohsen Moslemin, 2016. "The competing chemical and physical effects of transient fuel enrichment on heavy knock in an optical spark ignition engine," Applied Energy, Elsevier, vol. 179(C), pages 687-697.
    13. Meng, Hao & Ji, Changwei & Su, Teng & Yang, Jinxin & Chang, Ke & Xin, Gu & Wang, Shuofeng, 2022. "Analyzing characteristics of knock in a hydrogen-fueled Wankel rotary engine," Energy, Elsevier, vol. 250(C).
    14. Wang, Shuofeng & Ji, Changwei & Zhang, Bo & Liu, Xiaolong, 2014. "Lean burn performance of a hydrogen-blended gasoline engine at the wide open throttle condition," Applied Energy, Elsevier, vol. 136(C), pages 43-50.
    15. Xi, Haoran & Fu, Jianqin & Zhou, Feng & Yu, Juan & Liu, Jingping & Meng, Zhongwei, 2023. "Experimental and numerical studies of thermal power conversion and energy flow under high-compression ratios of a liquid methane engine (LME)," Energy, Elsevier, vol. 284(C).
    16. Li, Yangtao & Khajepour, Amir & Devaud, Cécile & Liu, Kaimin, 2017. "Power and fuel economy optimizations of gasoline engines using hydraulic variable valve actuation system," Applied Energy, Elsevier, vol. 206(C), pages 577-593.
    17. Chintala, V. & Subramanian, K.A., 2015. "An effort to enhance hydrogen energy share in a compression ignition engine under dual-fuel mode using low temperature combustion strategies," Applied Energy, Elsevier, vol. 146(C), pages 174-183.
    18. Lounici, M.S. & Benbellil, M.A. & Loubar, K. & Niculescu, D.C. & Tazerout, M., 2017. "Knock characterization and development of a new knock indicator for dual-fuel engines," Energy, Elsevier, vol. 141(C), pages 2351-2361.
    19. Jeonghyun Park & Kyung-Hwan Lee & Suhan Park, 2020. "Comprehensive Spray Characteristics of Water in Port Fuel Injection Injector," Energies, MDPI, vol. 13(2), pages 1-13, January.
    20. Li, Yangtao & Khajepour, Amir & Devaud, Cécile, 2018. "Realization of variable Otto-Atkinson cycle using variable timing hydraulic actuated valve train for performance and efficiency improvements in unthrottled gasoline engines," Applied Energy, Elsevier, vol. 222(C), pages 199-215.

    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:gam:jeners:v:14:y:2021:i:2:p:439-:d:480824. 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: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    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.