机器学习在火电厂NO_(x)减排中的应用综述  

Review of applications of machine learning in nitrogen oxides reduction in thermal power plants

作　　者：张珑慧 林德海 王颖 季广辉[3] 马少丹 曹子雄 刘伟 刘子林 马子然 王宝冬 ZHANG Longhui;LIN Dehai;WANG Ying;JI Guanghui;MA Shaodan;CAO Zixiong;LIU Wei;LIU Zilin;MA Ziran;WANG Baodong(National Institute of Clean and Low Carbon Energy,Beijing 102209,China;North Engineering Design and Research Institute Co.,Ltd.,Shijiazhuang 050000,China;Hebei Guohua Dingzhou Power Generation Co.,Ltd.,Dingzhou 073000,China)

机构地区：[1]北京低碳清洁能源研究院,北京102209 [2]北方工程设计研究院有限公司,河北石家庄050000 [3]河北国华定州发电有限责任公司,河北定州073000

出　　处：《热力发电》2023年第1期7-17,共11页Thermal Power Generation

基　　金：国家重点研发计划项目(2019YFC1907500)。

摘　　要：随着火电厂超低排放改造的完成,产生了成本增加、喷氨超标等问题。通过机器学习对电厂运行数据建模和优化成为解决这一问题的重要手段。综述了NO_(x)减排中常用的机器学习算法及其应用场景。在算法方面,归纳了数据预处理、算法模型和模型参数优化3个过程的研究现状,给出了各个过程多种机器学习算法的应用情况及适用性,提出了变工况数据预处理方法、多目标优化中目标函数的构造方法等未来研究方向。在应用层面,总结了机器学习在炉内低氮燃烧、选择性催化还原(SCR)烟气脱硝系统运行优化、全系统综合节能降耗等过程的实施方法及其运行效果,展望了长周期动态建模控制及多电厂联合建模等未来应用场景。With the completion of ultra-low emission transformation of thermal power plants, problems such as increased costs and excessive ammonia injection have arisen. Modeling and optimization of power plant operation data through machine learning has become an important means to solve the above problems. This article reviews the commonly used machine learning algorithms and their application scenarios in reducing nitrogen oxides. In terms of algorithm, the main algorithms of data preprocessing, modeling prediction and parameter optimization and their applicability to nitrogen oxides removal are summarized. The research directions of multi-operating condition data preprocessing method and the construction method of the objective function in multi-objective optimization are proposed. For the application level of the machine learning methods, such as low nitrogen combustion in the furnace, optimization of SCR denitration system, and comprehensive energy saving and consumption reduction of the whole system, the implementation methods and corresponding effects are summarized. The future research directions of long-period dynamic modeling control and multi-power plant joint modeling have prospected.

关 键 词：NO_(x)排放 SCR 模型预测控制 大数据 机器学习 

分 类 号：X773[环境科学与工程—环境工程] TP181[自动化与计算机技术—控制理论与控制工程]