[1]苏 涛,潘红光,黄向东,等.基于改进PSO-SVM的燃煤电厂烟气含氧量软测量[J].西安科技大学学报,2020,(02):342-348.
 SU Tao,PAN Hong-guang,HUANG Xiang-dong,et al.Soft sensor of flue gas oxygen content based on improved PSO-SVM in coal-fired power plant[J].Journal of Xi'an University of Science and Technology,2020,(02):342-348.
点击复制

基于改进PSO-SVM的燃煤电厂烟气含氧量软测量(/HTML)
分享到:

西安科技大学学报[ISSN:1672-9315/CN:61-1434/N]

卷:
期数:
2020年02期
页码:
342-348
栏目:
出版日期:
2020-03-30

文章信息/Info

Title:
Soft sensor of flue gas oxygen content based on improved PSO-SVM in coal-fired power plant
文章编号:
1672-9315(2020)02-0342-07
作者:
苏 涛1潘红光1黄向东1邵小强1马 彪2
(1.西安科技大学 电气与控制工程学院,陕西 西安 710054; 2.鄂尔多斯市神东工程设计有限公司,新疆 鄂尔多斯 017000)
Author(s):
SU Tao1PAN Hong-guang1HUANG Xiang-dong1SHAO Xiao-qiang1MA Biao2
(1.College of Electrical and Control Engineering,Xi'an University of Science and Technology,Xi'an 710054,China; 2.Ordos Shendong Engineering Design Co.,Ltd.,Ordos 017000,China)
关键词:
烟气含氧量 软测量 支持向量机 改进粒子群算法 参数优化
Keywords:
flue gas oxygen content soft sensor support vector machine improved particle swarm optimization algorithm parameter optimization
分类号:
TP 13
文献标志码:
A
摘要:
针对燃煤电厂烟气含氧量测量成本高、使用过程复杂且精度低等问题,应用软测量的方法来代替氧量传感器估计锅炉烟气含氧量。首先分析烟气含氧量的化学原理和锅炉工艺,初步选取合理的辅助变量,同时引入邓氏关联度分析法对燃煤电厂数据做降维处理,利用支持向量机建立辅助变量与烟气含氧量之间的软测量模型。其次,针对软测量模型参数优化问题,提出一种改进的粒子群优化算法,并对模型中的惩罚参数和核函数参数进行优化,进而利用算法得到的优化值构建改进的烟气含氧量软测量模型。最后,通过仿真验证改进的粒子群优化算法的有效性,并与传统方法进行了对比研究,发现该方法较传统方法预测精度更高、泛化性更好,烟气含氧量预测值的相对误差范围从[0,0.07]降至[0,0.02],均方根误差RMSE为0.060 4.结果表明:所建立的烟气氧含量软测量模型能够满足燃煤电厂对于烟气氧含量测量的精度需求,可以很好地解决烟气含氧量软测量精度低的问题,在燃煤电厂热效率提升和锅炉控制系统性能优化方面具有指导意义。
Abstract:
Aiming at the problems of high cost,complex operation and low accuracy of oxygen content measurement of flue gas in coal-fired power plants,soft sensor is applied to estimate oxygen content of boiler flue gas instead of oxygen sensor.In this paper,the chemical principle and boiler process of flue gas oxygen content are firstly analyzed,and reasonable auxiliary variables are preliminarily selected.At the same time,Deng correlation analysis is introduced to conduct dimensionality reduction processing for data form coal-fired power plants,and the soft sensor model between auxiliary variables and flue gas oxygen content is established by using support vector machine(SVM).Secondly,an improved particle swarm optimization(PSO)algorithm is proposed to solve the problem of soft sensor model parameter optimization,and the penalty parameters and kernel function parameters in the model are optimized.Finally,the effectiveness of the improved particle swarm optimization(PSO)algorithm was verified by simulation,and compared with the traditional method,it was found that the method had higher prediction accuracy and better generalization than the traditional method,and the relative error range of the predicted oxygen content of flue gas decreased from[0,0.07]to[0,0.025],and the root mean square error RMSE was 0.060 4.The results show that the soft sensor model of flue gas oxygen content can meet the requirements of coal burning power plants for the accuracy of flue gas oxygen content measurement,can solve the problem of low accuracy of flue gas oxygen content soft sensor,and has guiding significance in improving thermal efficiency of coal burning power plants and optimizing the performance of boiler control system.

参考文献/References:

[1] 姜兆宇,贾庆山,管晓宏.多时空尺度的风力发电预测方法综述[J].自动化学报,2019,45(1):51-71. JIANG Zhao-yu,JIA Qing-shan,GUAN Xiao-hong.A review of multi-temporal-and-spatial-scale wind power forecasting method[J].Acta Automatica Sinica,2019,45(1):51-71. [2]李 品.中国能源供给安全影响因素研究[J].西安科技大学学报,2018,38(3):403-410. LI Pin.Influential factors of energy supply security of China[J].Journal of Xi'an University of Science and Technology,2018,38(3):403-410. [3]杨倩鹏,林伟杰,王月明,等.火力发电产业发展与前沿技术路线[J].中国电机工程学报,2017,37(13):3787-3794. YANG Qian-peng,LIN Wei-jie,WANG Yue-ming,et al.Industry development and frontier technology roadmap of thermal power generation[J].Proceedings of the CSEE,2017,37(13):3787-3794. [4]刘长良,李淑娜.基于LS-SVM和单纯形的烟气含氧量软测量[J].热能动力工程,2010,25(3):292-296. LIU Chang-liang,LI Shu-na.Soft measurement of flue gas oxygen content based on LS-SVM and simplex[J].Journal of Engineering for Thermal Energy and Power,2010,25(3):292-296. [5]罗 嘉,吴 乐.电站锅炉主要热工过程参数软测量技术研究进展[J].热力发电,2015,44(11):1-9. LUO Jia,WU Le.Research status of soft measurement technology of typical thermal parameters for utility boilers[J].Thermal Power Generation,2015,44(11):1-9. [6]王 凯,翟小伟,王炜罡.氧浓度与风量对煤热物性参数影响的实验研究[J].西安科技大学学报,2018,38(1):31-36. WANG Kai,ZHAI Xiao-wei,WANG Wei-gang.Influence of oxygen concentration and blowing rate on thermal properties of coal[J].Journal of Xi'an University of Science and Technology,2018,38(1):31-36. [7]刘 千,韩 璞,王东风.基于ANFIS模型的烟气含氧量建模和预测[J].计算机仿真,2014,31(10):437-439. LIU Qian,HAN Pu,WANG Dong-feng.Soft-sensing of oxygen content in flue gas based on ANFIS model[J].Computer,2014,31(10):437-439. [8]李建强,赵 凯,陈星旭,等.600MW燃煤机组最优氧量与配风方式的联合优化[J].中国电机工程学报,2017,37(15):4422-4429. LI Jian-qiang,ZHAO Kai,CHEN Xing-xu,et al.Combined optimization of optimal oxygen content and second air distribution in 600 mw coal-fired unit[J].Proceedings of the CSEE,2017,37(15):4422-4429. [9]李 艳,任 锦.火电厂锅炉烟气氧含量精确测量仿真研究[J].计算机仿真,2017,34(11):58-62. LI Yan,REN Jin.Study on soft-sensors of boiler flue gas oxygen content based on PSO-LSSVM[J].Computer,2017,34(11):58-62. [10]李建强,赵 凯,牛成林,等.基于GA-SVM的电站锅炉烟气含氧量软测量模型[J].热力发电,2017,46(4):63-69. LI Jian-qiang,ZHAO Kai,NIU Cheng-lin,et al.GA-SVM based soft-sensor model for oxygen content in flue gas of utility boilers[J].Thermal Power Generation,2017,46(4):63-69. [11]丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综述[J].电子科技大学学报,2011,40(1):2-10. DING Shi-fei,QI Bing-juan,TAN Hong-yan.An overview on theory and algorithm of support vector machines[J].Journal of University of Electronic Science and Technology of China,2011,40(1):2-10. [12]Sun L,Wang Y.Soft-sensing of oxygen content of flue gas based on mixed model[J].Energy Procedia,2012,17(part-PA):221-226. [13]Chen B J,Chang M,Lin C J.Load forecasting using support vector machines:a study on eunite competition 2001[J].IEEE Transactions on Power Systems,2004,19(4):1821-1830. [14]刘思峰,蔡 华,杨英杰,等.灰色关联分析模型研究进展[J].系统工程理论与实践,2013,33(8):2041-2046. LIU Si-feng,CAI Hua,YANG Ying-jie,et al.Advance in grey incidence analysis modelling[J].Systems Engineering Theory & Practice,2013,33(8):2041-2046. [15]张选平,杜玉平,秦国强,等.一种动态改变惯性权的自适应粒子群算法[J].西安交通大学学报,2005,39(10):1039-1042. ZHANG Xuan-ping,DU Yu-ping,QIN Guo-qiang,et al.Adaptive particle swarm algorithm with dynamically changing inertia weight[J].Journal of Xi'an Jiaotong University,2005,39(10):1039-1042. [16]Zaharis Z D,Gravas I P,Yioultsis T V,et al.Exponential log-periodic antenna design using improved particle swarm optimization with velocity mutation[J].IEEE Transactions on Magnetics,2017,53(6):1-4. [17]Park J B,Jeong Y W,Shin J R,et al.An improved particle swarm optimization for nonconvex economic dispatch problems[J].IEEE Transactions on Power Systems,2010,25(1):156-166. [18]Everson R,Roberts,S.Inferring the eigenvalues of covariance matrices from limited,noisy data[J].IEEE Transactions on Signal Processing,2013,48(7):2083-2091.

备注/Memo

备注/Memo:
收稿日期:2019-10-11 责任编辑:高 佳
基金项目:国家自然科学基金(61603295); 中国博士后基金(2017M623207); 陕西省自然科学基础研究计划项目(2018JM6003); 西安科技大学优秀青年科技基金(2018YQ2-07)
通信作者:潘红光(1983-),男,山东临沂人,博士,讲师,E-mail:hongguangpan@xust.edu.cn
更新日期/Last Update: 2020-03-30