发电技术 ›› 2023, Vol. 44 ›› Issue (4): 534-542.DOI: 10.12096/j.2096-4528.pgt.21088

• 发电及环境保护 • 上一篇    下一篇

基于最小二乘支持向量机的火电厂烟气含氧量预测模型优化研究

赵国钦1, 蓝茂蔚2, 李杨3, 周元祥3, 江政纬2, 甘云华2   

  1. 1.广东粤电靖海发电有限公司,广东省 揭阳市 515223
    2.华南理工大学电力学院,广东省 广州市 510640
    3.西安热工研究院有限公司,陕西省 西安市 710054
  • 收稿日期:2022-03-01 出版日期:2023-08-31 发布日期:2023-08-29
  • 通讯作者: 甘云华
  • 作者简介:赵国钦(1976),男,高级工程师,研究方向为热力系统及机械设计,64276748@qq.com
    蓝茂蔚(1996),男,硕士研究生,研究方向为电站系统智能优化,306480034@qq.com
    李杨(1978),男,博士,正高级工程师,研究方向为火电机组节能优化,liyang@tpri.com.cn
    周元祥(1982),男,硕士,高级工程师,研究方向为锅炉及辅助系统节能诊断与运行优化,zhouyuanxiang@tpri.com.cn
    江政纬(1995),男,博士研究生,研究方向为新型燃烧、能源系统智能优化等,928031793@qq.com
    甘云华(1979),男,博士,教授,研究方向为新型燃烧、高效传热、能源系统智能优化等,ganyh@scut.edu.cn
  • 基金资助:
    国家自然科学基金项目(51776077);广东省基础与应用基础研究基金项目(2020B1515020040)

Study on Optimization of Prediction Model of Flue Gas Oxygen Content in Thermal Power Plant Based on Least Squares Support Vector Machine

Guoqin ZHAO1, Maowei LAN2, Yang LI3, Yuanxiang ZHOU3, Zhengwei JIANG2, Yunhua GAN2   

  1. 1.Jinghai Power Generation Co. , Ltd. , Guangdong Energy Group, Jieyang 515223, Guangdong Province, China
    2.School of Electric Power Engineering, South China University of Technology, Guangzhou 510640, Guangdong Province, China
    3.Xi'an Thermal Power Research Institute Co. , Ltd. , Xi'an 710054, Shaanxi Province, China
  • Received:2022-03-01 Published:2023-08-31 Online:2023-08-29
  • Contact: Yunhua GAN
  • Supported by:
    National Natural Science Foundation of China(51776077);Basic and Applied Basic Research Foundation of Guangdong Province(2020B1515020040)

摘要:

烟气含氧量是锅炉运行的重要监控参数,也是反映燃烧设备与锅炉运行完善程度的重要依据。根据运行工况快速、准确地测量烟气含氧量,对于优化锅炉燃烧过程具有重要指导意义。以某电站的1 000 MW超超临界锅炉的运行数据为基础,选取影响烟气排放的31个因素,分别采用交叉验证(cross validation,CV)、粒子群优化(particle swarm optimization,PSO)算法、遗传算法(genetic algorithm,GA)寻找最小二乘支持向量机(least squares support vector machine,LSSVM)模型的最佳参数,建立烟气含氧量预测模型。研究结果表明:相对于PSO-LSSVM和CV-LSSVM模型,GA-LSSVM预测模型对烟气含氧量具有更好的预测能力,具有预测精度高、泛化能力好、鲁棒性强等优点,拟合预测的相对误差、均方误差分别为0.54%、0.23%,泛化预测的相对误差、均方误差分别为1.66%、2.13%,能够比较准确地对火电厂锅炉烟气含氧量进行测量,为锅炉燃烧系统进一步的优化运行奠定了基础。

关键词: 火电厂, 最小二乘支持向量机(LSSVM), 粒子群优化(PSO)算法, 遗传算法(GA), 交叉验证(CV)

Abstract:

The oxygen content in flue gas is an important monitoring parameter of boiler operation, and also an important basis that reflects the perfection of combustion equipment and boiler operation. Quickly and accurately measuring the oxygen content in flue gas according to operating conditions has important guiding significance for optimizing boiler combustion process. Based on the operation data of a 1 000 MW ultra-supercritical boiler in a power station, 31 factors affecting flue gas emission were selected, and cross validation (CV), particle swarm optimization (PSO) algorithm, and genetic algorithm (GA) were used to find the optimal parameters of the least squares support vector machine (LSSVM) model, and the prediction model of flue gas oxygen content was established. The research results show that, compared with PSO-LSSVM and CV-LSSVM models, GA-LSSVM prediction model has better prediction ability for flue gas oxygen content, and has the advantages of high prediction accuracy, good generalization ability, and strong robustness. The relative error and mean square error of fitting prediction are 0.54% and 0.23% respectively, and the relative error and mean square error of generalization prediction are 1.66% and 2.13% respectively. It can accurately measure the oxygen content of boiler flue gas in thermal power plants, which lays a foundation for further optimal operation of boiler combustion system.

Key words: thermal power plant, least squares support vector machine (LSSVM), particle swarm optimization (PSO) algorithm, genetic algorithm (GA), cross validation (CV)

中图分类号: