发电技术 ›› 2023, Vol. 44 ›› Issue (4): 525-533.DOI: 10.12096/j.2096-4528.pgt.22129

• 发电及环境保护 • 上一篇    下一篇

燃煤电厂SCR脱硝系统精准控氨优化方法研究

罗志刚1, 何成兵2, 孟浩然1, 刘国栋1, 沈鹏1, 张军1, 张浩亮1   

  1. 1.国能龙源环保有限公司, 北京市 海淀区 100039
    2.华北电力大学能源动力与机械工程学院, 北京市 昌平区 102206
  • 收稿日期:2023-01-06 出版日期:2023-08-31 发布日期:2023-08-29
  • 通讯作者: 何成兵
  • 作者简介:罗志刚(1973),男,硕士,高级工程师,研究方向为电力环保科技、大气污染物测量技术,12039692@chnenergy.com.cn
    何成兵(1974),男,博士,副教授,研究方向为燃煤电厂脱硝系统优化控制,hcbyy@126.com
    孟浩然(1996),男,助理工程师,研究方向为大气污染物测量与自动控制,lucktd@qq.com
  • 基金资助:
    国家重点研发计划项目(2022YFC3701503)

Research on Optimization Method of Precise Ammonia Injection in SCR de-NO x System of Coal-fired Power Plant

Zhigang LUO1, Chengbing HE2, Haoran MENG1, Guodong LIU1, Peng SHEN1, Jun ZHANG1, Haoliang ZHANG1   

  1. 1.China Energy Longyuan Environmental Protection Co. , Ltd. , Haidian District, Beijing 100039, China
    2.School of Energy and Power Engineering, North China Electric Power University, Changping District, Beijing 102206, China
  • Received:2023-01-06 Published:2023-08-31 Online:2023-08-29
  • Contact: Chengbing HE
  • Supported by:
    National Key R&D Program of China(2022YFC3701503)

摘要:

针对燃煤电厂选择性催化还原(selective catalytic reduction,SCR)脱硝系统喷氨不均匀的问题,将智能前馈串级控制技术与分区控制技术相结合,提出了一种精准控氨优化方法。在智能前馈环节,采用预测精度更高的改进一维卷积神经网络模型,实现了SCR反应器入口NO x 质量浓度的预测,并将其作为智能前馈控制信号,实现了机组全工况下NO x 质量浓度的快速准确控制。在分区控制环节,采用分区巡测-多点同步取样测量技术与均衡控制策略相结合的方法,实现了各分区喷氨量的精准控制。该优化方法已应用于多个燃煤电厂,运行结果表明,机组全工况下实现了喷氨量的精准控制,SCR反应器出口断面NO x 质量浓度分布均匀,波动范围小,氨耗量降低明显,经济效益显著。

关键词: 燃煤电厂, SCR脱硝, 精准控氨, 改进一维卷积神经网络, 分区控制

Abstract:

In order to solve the problem of uneven ammonia injection in selective catalytic reduction (SCR) de-NO x system of coal-fired power plant, a precise ammonia control optimization method was proposed by combining the intelligent feed-forward cascade control technology with the partition control technology. In the intelligent feed-forward process, the improved one-dimensional convolution neural network model with higher prediction accuracy was used to predict the NO x mass concentration at the inlet of the SCR reactor, which was used as the intelligent feed-forward control signal to realize the fast and accurate control of the NO x mass concentration under the whole working condition of the unit. In the partition control process, the single sub area and multi-point synchronous sampling measurement technology and equalization control strategy were combined to realize the precise control of ammonia injection in each partition. The proposed optimization method has been applied to several coal-fired power plants. The operation results show that the precise control of ammonia injection amount is realized under the whole working conditions of the unit. The NO x mass concentration at the outlet section of SCR reactor is uniformly distributed. The ammonia consumption is obviously reduced and the economic benefit is significant.

Key words: coal-fired power plant, SCR de-NO x, precise ammonia injection, improved one-dimensional convolution neural network, partition control

中图分类号: