发电技术 ›› 2025, Vol. 46 ›› Issue (3): 627-636.DOI: 10.12096/j.2096-4528.pgt.23135

• 发电及环境保护 • 上一篇    

基于数据驱动的循环流化床机组深度调峰NO x 预测

张鹏新1, 高明明1, 解沛然2, 于浩洋1, 张洪福3, 黄中4   

  1. 1.新能源电力系统国家重点实验室(华北电力大学),北京市 昌平区 102206
    2.天津市普迅电力信息技术有限公司,天津市 东丽区 300308
    3.国家能源集团新能源技术研究院有限公司,北京市 昌平区 102209
    4.清华大学能源与动力工程系,北京市 海淀区 100084
  • 收稿日期:2024-04-03 修回日期:2024-06-27 出版日期:2025-06-30 发布日期:2025-06-16
  • 通讯作者: 高明明
  • 作者简介:张鹏新(2000),男,硕士研究生,研究方向为循环流化床机组智能控制,1912179047@qq.com
    高明明(1979),男,博士,副教授,研究方向为发电过程智能测控技术与应用、人工智能与应用、新能源发电综合测控技术与应用,本文通信作者,gmm1@ncepu.edu.cn
    解沛然(1991),男,博士,研究方向为发电过程智能测控技术与应用、人工智能与应用,peiranxiencepu@163.com
    于浩洋(1996),男,博士研究生,研究方向为发电过程智能测控技术与应用、人工智能与应用,120202127004@ncepu.edu.cn
    张洪福(1995),男,博士,研究方向为循环流化床机组灵活运行与超低排放控制,zhanghongfu0907@126.com
    黄中(1983),男,博士,研究员,研究方向为循环流化床燃烧理论与技术、燃烧过程的污染物控制,huangzhong@mail.tsinghua.edu.cn
  • 基金资助:
    国家重点研发计划项目(2022YFB4100301)

NO x Prediction for Deep Peaking Regulation of Circulating Fluidized Bed Units Based on Data-Driven

Pengxin ZHANG1, Mingming GAO1, Peiran XIE2, Haoyang YU1, Hongfu ZHANG3, Zhong HUANG4   

  1. 1.State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources (North China Electric Power University), Changping District, Beijing 102206, China
    2.Tianjin Puxun Power Information Technology Co. , Ltd. , Dongli District, Tianjin 300308, China
    3.CHN Energy New Energy Technology Research Institute Co. , Ltd. , Changping District, Beijing 102209, China
    4.Department of Energy and Power Engineering, Tsinghua University, Haidian District, Beijing 100084, China
  • Received:2024-04-03 Revised:2024-06-27 Published:2025-06-30 Online:2025-06-16
  • Contact: Mingming GAO
  • Supported by:
    National Key Research and Development Program(2022YFB4100301)

摘要:

目的 在循环流化床(circulating fluidized bed,CFB)机组深度调峰运行状态下,NO x 排放浓度会出现大幅波动,对脱硝控制系统的稳定性与经济性造成严重影响,为此,提出了一种基于数据驱动的循环流化床机组深度调峰运行状态下的NO x 预测模型。 方法 对NO x 的生成机理及影响因素进行了深度分析,结合某300 MW CFB机组现场运行数据,采用鲸鱼优化算法(whale optimization algorithm,WOA)对长短期记忆(long short-term memory,LSTM)神经网络参数进行优化,并建立WOA-LSTM神经网络模型。 结果 该模型实现了深度调峰下的CFB机组NO x 排放质量浓度的在线预测。通过与其他神经网络模型进行对比,表明所提模型具有更好的预测结果,该模型平均绝对误差为2.49 mg/m3,平均绝对百分比误差达到6.8%,模型相关系数达到0.99。 结论 该模型能够准确地反映机组大范围变负荷运行下的NO x 排放变化趋势,对现场脱硝自动控制系统的运行具有良好的指导作用。

关键词: 火电机组, 循环流化床(CFB), NO x 排放, 深度调峰, 人工智能(AI), 鲸鱼优化算法(WOA), 长短期记忆(LSTM)神经网络

Abstract:

Objectives Under the deep peaking regulation operation of circulating fluidized bed (CFB) unit, NO x emission will fluctuate significantly, which will have a serious impact on the stability and economy of the denitrification control system. Therefore, a data-driven NO x prediction model based on the deep peaking regulation of CFB unit is proposed. Methods The generation mechanism and influencing factors of NO x are analyzed in depth. Combined with the field operation data of a 300 MW CFB unit, the whale optimization algorithm (WOA) is used to optimize the parameters of the long short-term memory (LSTM) neural network, and the WOA-LSTM neural network model is established. Results The model realizes the online prediction of NO x emission mass concentration of CFB unit under deep peaking regulation. Compared with other neural network models, the proposed model has better prediction results. The mean absolute error of the model is 2.49 mg/m3, the mean absolute percentage error reaches 6.8%, and the model correlation coefficient reaches 0.99. Conclusions The model can accurately reflect the NO x emission trend under the wide range of variable load operation of the unit. The results of the study are a good guide for the operation of the automatic control system of denitrification in the field.

Key words: coal-fired power unit, circulating fluidized bed (CFB), NO x emission, deep peaking regulation, artificial intelligence (AI), whale optimization algorithm (WOA), long short-term memory (LSTM) neural network

中图分类号: