基于灰色关联分析法及GSA-LSSVM的汽轮机排汽焓预测模型

doi:10.3969/j.issn.1000－7229.2016.11.017

摘要/Abstract

摘要： 排汽焓是汽轮发电机组热经济性诊断必不可少的一个参数。通过汽轮机功率方程与灰色关联分析(grey correlation analysis，GCA)理论确定了模型的输入变量，利用万有引力搜索算法(gravitational search algorithm，GSA)优化了最小二乘支持向量机(least squares support vector machine，LSSVM)的惩罚因子μ以及核径向范围σ 2个参数。通过比较分析，选用RBF_kernel为LSSVM的核函数。以GCA-GSA-LSSVM为基础，建立了预测汽轮机排汽焓的数学模型，并将其与BP神经网络、RBF神经网络进行对比，同时分析了该数学模型的鲁棒性。结果表明基于GCA-GSA-LSSVM的汽轮机排汽焓预测模型具有精度高、泛化能力强、鲁棒性强等优点，该方法为精确预测机组节能潜力提供了一种有力的工具。

关键词: , 最小二乘支持向量机（LSSVM), 万有引力搜索算法（GSA）, 灰色关联分析法（GCA）, 汽轮机排汽焓

Abstract: The steam exhaust enthalpy is an essential parameter for the thermal economic diagnosis of steam turbine generator group. We determine the input variables of the model by steam turbine power equation and grey correlation analysis (GCA) method, and optimize the punishment factor μ and nuclear radial range σ of least square support vector machine (LSSVM) by gravitation search algorithm (GSA). The RBF_kernel is selected as the kernel function of LSSVM through the comparative analysis. Based on the GCA-GSA-LSSVM, this paper establishes the mathematical model to predict the exhaust enthalpy of steam turbine, compares it with the BP neural network and RBF neural network, and analyzes its robustness. The results show that the prediction model of steam turbine exhaust enthalpy based on GCA-GSA-LSSVM has the advantages of high precision, strong generalization ability and strong robustness. This method provides a powerful tool for accurately predicting the energy saving potential of the unit.

Key words: least square support vector machine (LSSVM), gravitation search algorithm(GSA), grey correlation analysis method(GCA), steam turbine exhaust enthalpy

中图分类号:

TM 621

王惠杰，范志愿，许小刚，李鑫鑫. 基于灰色关联分析法及GSA-LSSVM的汽轮机排汽焓预测模型[J]. 电力建设, 2016, 37(11): 115-.

WANG Huijie，FAN Zhiyuan，XU Xiaogang，LI Xinxin. Prediction Model of Steam Turbine Exhaust Enthalpy Based on Grey Correlation Analysis Method and GSA-LSSVM[J]. Electric Power Construction, 2016, 37(11): 115-.

参考文献

［1］〖HJ1.4mm〗张乐乐, 张燕平, 黄树红, 等. 汽轮机湿蒸汽区蒸汽焓值的计算模型研究［J］. 动力工程学报, 2013, 33(4): 272-277, 302.

ZHANG Lele, ZHANG Yanping, HUANG Shuhong, et al. Steam enthalpy calculation model for wet steam region of steam turbines［J］. Journal of Chinese Society of Power Engineering, 2013, 33(4): 272-277, 302.

［2］杨涛, 胥建群, 张赟, 等. 电站汽轮机低压缸排汽焓近似计算模型研究［J］. 热力透平, 2013, 42(1): 30-34.

YANG Tao, XU Jianqun, ZHANG Yun, et al. Research on approximate calculation model of LP steam turbine exhaust enthalpy in power plant ［J］.Thermal Turbine, 2013, 42(1): 30-34.

［3］李勇, 李仁杰, 曹丽华, 等. 凝汽式汽轮机低压缸相对内效率在线监测方法［J］. 化工机械, 2014, 41(3): 316-322.

LI Yong, LI Renjie, CAO Lihua, et al. On-line monitoring method for internal efficiency ratio of low-pressure cylinder in condensing steam turbine［J］.Chemical Engineering & Machinery, 2014, 41(3): 316-322.

［4］闫顺林, 徐鸿, 李永华, 等. 汽轮机排汽焓动态在线计算模型的研究［J］. 动力工程, 2008, 28(2): 181-184, 199.

YAN Shunlin, XU Hong, LI Yonghua, et al. Research on online dynamic model for calculating exhaust enthalpy of steam turbine［J］. Journal of Power Engineering, 2008, 28(2): 181-184, 199.

［5］韩中合, 杨昆, 田松峰, 等. 在线确定凝汽式汽轮机排汽焓的热力学方法［J］. 动力工程, 2004, 24(3): 356-359, 374.

HAN Zhonghe, YANG Kun, TIAN Songfeng. A thermodynamics method of online calculation steam turbine exhaust enthalpy［J］. Power Engineering, 2004, 24(3): 356-359, 374.

［6］徐曙. 用Baumman公式估算汽轮机排汽压力对机组经济性的影响［J］. 汽轮机技术, 2016, 58(1): 72-74, 32.

XU Shu. Estimate exhaust pressure of steam turbine on the economic impact with Baumman formula［J］.Turbine Technology, 2016, 58(1): 72-74, 32.

［7］宫唤春. 基于双隐层径向基过程神经网络的汽轮机排汽焓在线预测［J］. 热力发电, 2014, 43(7): 32-35.

GONG Huanchun. Double hidden layer RBF process neural network based online prediction of steam turbine exhaust enthalpy［J］. Thermal Power Generation, 2014, 43(7): 32-35.

［8］吴俊杰, 侯宏娟, 杨勇平. 神经网络算法在汽轮机排汽焓估算中的应用［J］. 热力发电, 2014, 43(8): 125-130.

WU Junjie, HOU Hongjuan, YANG Yongping. Application of neural network algorithm in steam turbine’s exhaust enthalpy estimation［J］.Thermal Power Generation, 2014, 43(8): 125-130.

［9］王建国, 赵帅, 王广雨. 提高汽轮机排汽焓在线预测精度的GA-Elman神经网络算法［J］. 热力发电, 2014, 43(10): 90-94.

WANG Jianguo, ZHAO Shuai, WANG Guangyu. A GA-Elman neural network algorithm which can improve online prediction accuracy of exhaust enthalpy for steam turbines［J］. Thermal Power Generation, 2014, 43(10): 90-94.

［10］蔡杰进, 马晓茜. 支持向量机在电站汽轮机排汽焓在线预测中的应用［J］. 电力系统自动化, 2006, 30(18): 77-82.

CAI Jiejin, MA Xiaoqian. Online forecasting of steam turbine exhaust enthalpy based on support vector machine method［J］. Automation of Electric Power Systems, 2006, 30(18): 77-82.

［11］王绵斌, 李欢欢, 谭忠富,等. 基于支持向量机方法的输电工程造价指标评估体系［J］. 电力建设, 2014, 35(3):102-106.

WANG Mianbin, LI Huanhuan, TAN Zhongfu, et al. Index evaluation system of power transmission project cost based on support vector machine method［J］. Electric Power Construction,2014, 35(3):102-106.

［12］李红玲, 文习山, 舒乃秋. 最小二乘支持向量机在绝缘子污秽放电声发射监测中的应用［J］. 电力建设, 2009, 30(6):25-28.

LI Hongling, WEN Xishan, SHU Naiqiu.Application of least squares support vector machine in acoustic emission monitor of polluted insulator discharge ［J］. Electric Power Construction, 2009, 30(6):25-28.

［13］韩中合, 焦宏超, 朱霄珣,等. 基于EEMD排列组合熵的SVM转子振动故障诊断研究［J］. 电力建设, 2016, 37(1):92-96.

HAN Zhonghe, JIAO Hongchao, ZHU Xiaoxun, et al. SVM rotor vibration fault diagnosis based on EEMD permutation entropy ［J］. Electric Power Construction,2016, 37(1):92-96.

［14］田中大, 高宪文, 石彤. 用于混沌时间序列预测的组合核函数最小二乘支持向量机［J］. 物理学报, 2014, 63(16):66-76.

TIAN Zhongda, GAO Xianwen, SHI Tong. Combination kernel function least squares support vector machine for chaotic time series prediction［J］.Acta Physica Sinica, 2014, 63(16):66-76.

［15］顾燕萍, 赵文杰, 吴占松. 最小二乘支持向量机鲁棒回归算法研究［J］. 清华大学学报(自然科学版), 2015, 55(4):396-402.

GU Yanping, ZHAO Wenjie, WU Zhansong. Investigation of robust least squares-support vector machines［J］.Journal of Tsinghua University (Science and Technology), 2015, 55(4):396-402.

［16］孟银凤, 梁吉业. 基于最小二乘支持向量机的函数型数据回归分析［J］. 模式识别与人工智能, 2014, 27(12):1124-1130.

MENG Yinfeng, LIANG Jiye. Regression analysis for functional data based on least squares support vector machine［J］. Pattern Recognition and Artificial Intelligence, 2014, 27(12):1124-1130.

［17］潘宇雄, 任章, 李清东. 动态贝叶斯最小二乘支持向量机［J］. 控制与决策, 2014, 29(12): 2297-2300.

PAN Yuxiong, REN Zhang, LI Qingdong. Dynamic Bayesian least squares support vector machine［J］. Control and Decision,2014, 29(12): 2297-2300.

［18］RASHEDI E, NEZAMABADI-POUR H, SARYAZDI S. GSA: a gravitational search algorithm ［J］. Information Sciences, 2009, 179(13): 2232-2248.

［19］张春发, 张素香,崔映红，等. 现行电力系统热经济性状态方程［J］. 工程热物理学报, 2001, 22(6): 665-667.

ZHANG Chunfa, ZHANG Suxiang, CUI Yinghong, et al. Thermo-economy state equation of modern power system［J］. Journal of Engineering Thermophysics, 2001, 22(6): 665-667.

［20］刘超, 牛培峰, 游霞. 反向建模方法在汽轮机热耗率建模中的应用［J］. 动力工程学报, 2014, 34(11): 867-872, 902.

LIU Chao, NIU Peifeng, YOU Xia. Application of reversed modeling method in prediction of steam turbine heat rate［J］.Journal of Chinese Society of Power Engineering, 2014, 34(11): 867-872, 902.

[1]	汤吉鸿, 章德, 丛凡超, 田国梁, 吴贵烘, 李宇骏, 禹海峰. 基于线性二次型最优控制的多端直流最优功率调制方案[J]. 电力建设, 2020, 41(8): 32-39.
[2]	赵洱岽, 王浩, 林弘杨. 现货市场中基于演化博弈的火电企业阶梯报价策略[J]. 电力建设, 2020, 41(8): 68-71.
[3]	宋建，束洪春，董俊，梁雨婷，李雨龙，杨博. 基于GM(1，1)与BP神经网络的综合负荷预测[J]. 电力建设, 2020, 41(5): 75-80.
[4]	祁兵，叶欣，李彬，陈宋宋，李源非，石坤. 考虑IEC标准的用户侧电力物联网体系架构研究[J]. 电力建设, 2020, 41(5): 92-99.
[5]	钟永洁，谢东亮，孙永辉，翟苏巍，常福刚，张明理. 考虑能源子系统与储能的综合能源系统优化分析[J]. 电力建设, 2019, 40(8): 59-68.
[6]	杨军，林洋佳，陈杰军，李逸欣，詹祥澎. 未来城市共享电动汽车发展模式[J]. 电力建设, 2019, 40(4): 49-59.
[7]	江帆，杨洪耕. 基于选择性贝叶斯分类的非侵入式负荷识别方法[J]. 电力建设, 2019, 40(2): 94-.
[8]	刘中原，王维庆，王海云，袁成玉，王亮，李永钦，丁文彬. 基于VSG技术的VSC-HVDC输电系统受端换流器控制策略[J]. 电力建设, 2019, 40(2): 100-.
[9]	林伟芳，易俊，贾俊川，王安斯，余芳芳，方诗卉. 故障后半波长输电线路的稳态过电压控制措施[J]. 电力建设, 2019, 40(2): 109-.
[10]	崔树银，陆奕，常啸. 考虑信用评分机制的电力碳排放交易区块链模型[J]. 电力建设, 2019, 40(1): 104-111.
[11]	黄裕春，王宏，王珂，文福拴. 考虑电动汽车充电设施接入的居民配电系统供电容量最优规划[J]. 电力建设, 2018, 39(6): 1-.
[12]	常巩, 邓友均, 杨洪明, 文福拴, 赖明勇. 充换电站模式下电动汽车参与物流配送的电能补给方式规划[J]. 电力建设, 2018, 39(6): 7-.
[13]	刘洵源, 齐峰, 文福拴, 冯昌森, 王蕾，邹波，张西竹. 光伏不平衡接入的配电系统中电动汽车有序充电策略[J]. 电力建设, 2018, 39(6): 21-.
[14]	杨文涛, 王蕾, 邹波, 张西竹, 文福拴, 程敏 . 基于大数据服务平台的电动汽车有序充放电管理[J]. 电力建设, 2018, 39(6): 28-.
[15]	郑涛，张滋行. 基于半桥子模块的模块化多电平换流器内部故障诊断及对策[J]. 电力建设, 2018, 39(6): 42-.