Chinese Science Citation Database Core Library(CSCD)Source Journals
Chinese Core Journals
Chinese Core Science and Technology Journals
RCCSE China Authoritative Academic Journal(A+)
Dutch Digest and Citation Database (Scopus)

Current situation and prospect of machine learning-driven boilercombustion optimization technology

2024 No. 02
341
307
OnlineView
Download
Authors:
YAO Shunchun
LI Longqian
LU Zhimin
LI Zhenghui
Unit:
School of Electric Power,South China University of Technology
Key Laboratory of Energy Efficiency and Clean Utilization in Guangdong Province
Abstract:

With the rapid increase of installed capacity of renewable energy power generation,unstable conditions such as variable load andunstable combustion during deep peak regulation put forward higher requirements for combustion optimization control of thermal powerunits. The rapidly developing artificial intelligence technology and deep learning algorithm provides an important means for boiler parameterprediction modeling and optimization. In terms of machine learning algorithms, this paper summarized the research status of feature screening and modeling algorithms, and pointed out that traditional statistical methods and linear dimensionality reduction methods had poor scientific interpretation and can not identify high-dimensional data well, and feature screening methods combined with deep learning algorithms had more obvious advantages in processing complex thermal power unit data. The advantages and disadvantages of various neuralnetworks in NOx emission concentration modeling were compared. Among them, long short-term memory neural network and convolutionalneural network have better effects in processing time series data, and the integrated model can improve the generalization ability and robustness of the whole model by combining the advantages of different learners. In the application of prediction model, the establishment ofprediction model for SCR denitration system can facilitate operators to simulate and modify adjustable parameters, and at the same time,it can be used as a soft measurement method to monitor the operating state of the combustion system. Advanced control methods, such asfeedforward control and model predictive control, which introduce NOx emission concentration prediction model, can effectively improvethe poor effect of traditional PID control for thermal power units. In multi-objective optimization, NOx removal efficiency and boiler efficiency or denitrification cost are usually used as optimization objectives, in order to achieve the harmonious unity of economic and social benefits.

Keywords:
machine learning
NOx emission
deep peak shaving
prediction model
multi-objective optimization control
Citation format:
姚顺春(1983—),男,浙江龙游人,教授,博士生导师,博士。E-mail:epscyao@scut.edu.cn
Chart:
Articles:
--
Citation format:
YAO Shunchun,LI Longqian,LU Zhimin,et al.Current situation and prospect of machine learning-driven boiler com-bustion optimization technology[J].Clean Coal Technology,2024,30(2):228-243.

About Journal

  • Executive director

    China Coal Science and Industry Group Co., Ltd

  • Sponsored by

    Coal Science Research Institute Co., Ltd
    Coal Industry Clean Coal Engineering
    Technology Research Center

  • Editor in Chief

    XIE Qiang

  • Vice Editor-in-Chief

    YU Chang
    SHI Yixiang
    ZHAO Yongchun
    DUAN Linbo
    CAO Jingpei
    ZENG Jie

  • Publication Frequencies

    Monthly

  • ISSN

    1006-6772

  • CN

    11-3676/TD

Covered by

  • CSTPCD
  • RCCSE(A+)
  • AJ
  • EBSCO host
  • Ulrichsweb
  • JST
  • Scopus

Contact us

New Media

  • Meichuanmei
    Meichuanmei
  • Clean Coal Technology
    Clean Coal Technology
  • Online Journals
    Online Journals
Website Copyright © {year} Clean Coal Technology
京ICP备05086979号-19
地址:Coal Tower, Hepingli, Chaoyang District, Beijing, China.
邮编:100013
Tel:86-10-87986452 / 010-87986451
E-mail:jjmjs@263.net