IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v12y2019i13p2585-d245722.html
   My bibliography  Save this article

An Unsupervised Classification Method for Flame Image of Pulverized Coal Combustion Based on Convolutional Auto-Encoder and Hidden Markov Model

Author

Listed:
  • Tian Qiu

    (Beijing Key Laboratory of New Technology and System on Measuring and Control for Industrial Process, North China Electric Power University, Beijing 102206, China)

  • Minjian Liu

    (Beijing Key Laboratory of New Technology and System on Measuring and Control for Industrial Process, North China Electric Power University, Beijing 102206, China)

  • Guiping Zhou

    (State Grid Liaoning Electric Power Supply Co, Ltd., Shenyang 110004, Liaoning Province, China)

  • Li Wang

    (State Grid Liaoning Electric Power Supply Co, Ltd., Shenyang 110004, Liaoning Province, China)

  • Kai Gao

    (State Grid Liaoning Electric Power Supply Co, Ltd., Shenyang 110004, Liaoning Province, China)

Abstract

Combustion condition monitoring is a fundamental and critical issue that needs to be addressed in the wide-load operation of coal-fired boilers. In this paper, an unsupervised classification framework based on the convolutional auto-encoder (CAE), the principal component analysis (PCA), and the hidden Markov model (HMM) is proposed to monitor the combustion condition with the uniformly spaced flame images, which are collected from the furnace combustion monitoring system. First, CAE is adopted to extract the features from the flame images, which obtain the sparse representations in the images. Then, PCA is applied to project the feature vectors into the orthogonal space for robustness and computation efficiency. Finally, a HMM is built to calculate the corresponding optimal states by learning the temporal behaviors in the compressed representations. A coal combustion adjustment experiment was conducted in a 660 MW opposed-firing boiler, and the sequential 14,400 flame images with three different combustion states were obtained to evaluate the effectiveness of the proposed approach. We tested six different compression dimensions of the latent variable z in the CAE model and ensured that the appropriate compress parameter was 1024. The proposed framework is compared with five other methods: the CAE + Gaussian mixture model (GMM), CAE + Kmean, the CAE + fuzzy c-mean method, CAE + HMM, and the traditional handcraft feature extraction method (TH) + HMM. The results show that the proposed framework has the highest classification accuracy (95.25% for the training samples and 97.36% for the testing samples) and has the best performance in recognizing the semi-stable state (85.67% for the training samples and 77.60% for the testing samples), indicating that the proposed framework is capable of identifying the combustion condition, changing when the combustion deteriorates as the coal feed rate falls.

Suggested Citation

  • Tian Qiu & Minjian Liu & Guiping Zhou & Li Wang & Kai Gao, 2019. "An Unsupervised Classification Method for Flame Image of Pulverized Coal Combustion Based on Convolutional Auto-Encoder and Hidden Markov Model," Energies, MDPI, vol. 12(13), pages 1-17, July.
    • Handle: RePEc:gam:jeners:v:12:y:2019:i:13:p:2585-:d:245722
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/12/13/2585/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/12/13/2585/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Roland Winkler & Frank Klawonn & Rudolf Kruse, 2011. "Fuzzy C-Means in High Dimensional Spaces," International Journal of Fuzzy System Applications (IJFSA), IGI Global, vol. 1(1), pages 1-16, January.
    2. Chen, Junghui & Hsu, Tong-Yang & Chen, Chih-Chien & Cheng, Yi-Cheng, 2010. "Monitoring combustion systems using HMM probabilistic reasoning in dynamic flame images," Applied Energy, Elsevier, vol. 87(7), pages 2169-2179, July.
    3. Wang, Zhenyu & Song, Chunfeng & Chen, Tao, 2017. "Deep learning based monitoring of furnace combustion state and measurement of heat release rate," Energy, Elsevier, vol. 131(C), pages 106-112.
    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. Chen, Hua & Yan, Tingting & Zhang, Xiaogang, 2020. "Burning condition recognition of rotary kiln based on spatiotemporal features of flame video," Energy, Elsevier, vol. 211(C).
    2. Han, Zhezhe & Hossain, Md. Moinul & Wang, Yuwei & Li, Jian & Xu, Chuanlong, 2020. "Combustion stability monitoring through flame imaging and stacked sparse autoencoder based deep neural network," Applied Energy, Elsevier, vol. 259(C).
    3. Romina Dastoorian & Lee J. Wells, 2023. "A hybrid off-line/on-line quality control approach for real-time monitoring of high-density datasets," Journal of Intelligent Manufacturing, Springer, vol. 34(2), pages 669-682, February.

    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. Chen, Hua & Yan, Tingting & Zhang, Xiaogang, 2020. "Burning condition recognition of rotary kiln based on spatiotemporal features of flame video," Energy, Elsevier, vol. 211(C).
    2. Han, Zhezhe & Hossain, Md. Moinul & Wang, Yuwei & Li, Jian & Xu, Chuanlong, 2020. "Combustion stability monitoring through flame imaging and stacked sparse autoencoder based deep neural network," Applied Energy, Elsevier, vol. 259(C).
    3. Zhou, Dongdong & Cheng, Shusen, 2019. "Measurement study of the PCI process on the temperature distribution in raceway zone of blast furnace by using digital imaging techniques," Energy, Elsevier, vol. 174(C), pages 814-822.
    4. González-Cencerrado, A. & Peña, B. & Gil, A., 2012. "Coal flame characterization by means of digital image processing in a semi-industrial scale PF swirl burner," Applied Energy, Elsevier, vol. 94(C), pages 375-384.
    5. Jiang, Feifeng & Ma, Jun & Li, Zheng & Ding, Yuexiong, 2022. "Prediction of energy use intensity of urban buildings using the semi-supervised deep learning model," Energy, Elsevier, vol. 249(C).
    6. Dong, Zhe & Liu, Miao & Guo, Zhiwu & Huang, Xiaojin & Zhang, Yajun & Zhang, Zuoyi, 2019. "Adaptive state-observer for monitoring flexible nuclear reactors," Energy, Elsevier, vol. 171(C), pages 893-909.
    7. Yuteng Xiao & Jihang Yin & Yifan Hu & Junzhe Wang & Hongsheng Yin & Honggang Qi, 2019. "Monitoring and Control in Underground Coal Gasification: Current Research Status and Future Perspective," Sustainability, MDPI, vol. 11(1), pages 1-14, January.
    8. Chen, Junghui & Chang, Yu-Hsiang & Cheng, Yi-Cheng & Hsu, Chen-Kai, 2012. "Design of image-based control loops for industrial combustion processes," Applied Energy, Elsevier, vol. 94(C), pages 13-21.
    9. Koziel, Sylvie & Hilber, Patrik & Westerlund, Per & Shayesteh, Ebrahim, 2021. "Investments in data quality: Evaluating impacts of faulty data on asset management in power systems," Applied Energy, Elsevier, vol. 281(C).

    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:12:y:2019:i:13:p:2585-:d:245722. 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.