基于混合建模的蒸汽管道参数计算

doi:10.11930/j.issn.1004-9649.201907190

摘要/Abstract

摘要： 提出一种结合机理建模和数据驱动建模的混合模型用于蒸汽管道的参数计算。在机理模型的基础上，采用向量机算法建立数据驱动误差预测模型，对机理模型计算所造成的机理误差进行预测，并将该模型的误差预测结果用于修正机理模型计算结果。为验证混合建模计算的有效性，通过实例建立机理模型和基于向量机算法的蒸汽参数预测模型计算管道末端蒸汽参数，并与混合模型的计算结果进行比较。结果证明，混合模型具有更高的计算精度，可为供热管道的运行优化提供参考。

关键词: 蒸汽管道, 水力热力耦合, 支持向量机, 混合模型, 误差修正

Abstract: This paper proposes a hybrid model combining mechanism modeling and data-driven modeling together for the calculation of parameters of steam pipelines. Based on the mechanism model, this paper establishes a data-driven error prediction model by virtue of the vector machine algorithm to predict the mechanism error caused by the mechanism model calculation, then uses the error prediction result of the model to correct the mechanism model calculation results. In order to verify the validity of the hybrid modeling calculation, through the case studies, the pipe end steam parameters are calculated by using the mechanism model and the steam parameter prediction model based on vector machine algorithm, and then compared with the mixed model calculation results. The results show that the hybrid model has higher calculation accuracy, which can provide reference for the operation optimization of the heating pipeline.

Key words: steam pipeline, hydraulic thermodynamic coupling, support vector machine, hybrid model, error correction

陈鸿伟, 麻哲瑞, 吕春旺, 刘玉强, 张巍, 王睿坤. 基于混合建模的蒸汽管道参数计算[J]. 中国电力, 2020, 53(9): 195-201.

CHEN Hongwei, MA Zherui, LV Chunwang, LIU Yuqiang, ZHANG Wei, WANG Ruikun. Parameter Calculation of Steam Pipeline Based on Hybrid Modeling[J]. Electric Power, 2020, 53(9): 195-201.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201907190

https://www.electricpower.com.cn/CN/Y2020/V53/I9/195

参考文献

[1] WANG H, MENG H, ZHU T. New model for onsite heat loss state estimation of general district heating network with hourly measurements[J]. Energy Conversion and Management, 2018, 157: 71–85.
[2] WANG H, WANG H Y, ZHU T, et al. A novel model for steam transportation considering drainage loss in pipeline networks[J]. Applied Energy, 2017, 188: 178–189.
[3] TALER D, KACZMARSKI K. A numerical model of steam pipeline[J]. Procedia Engineering, 2016, 157: 158–162.
[4] 郭永强. 蒸汽供热管网水力计算的简易算法[J]. 节能, 2008, 27(9): 16–18
GUO Yongqiang. Simplified calculation of hydraulic calculation in steam heating pipe network[J]. Energy Conservation, 2008, 27(9): 16–18
[5] 孙玉宝, 李恩山, 田贯三, 等. 蒸汽热力状态参数计算方法的研究[J]. 煤气与热力, 2006, 26(10): 49–51
SUN Yubao, LI Enshan, TIAN Guansan, et al. Study on calculation method of steam thermal state parameters[J]. Gas & Heat, 2006, 26(10): 49–51
[6] 王威, 罗先喜. 蒸汽管网的热力计算数学模型[J]. 中国设备工程, 2017(15): 199–201
[7] LUO X X, YUAN M Z, WANG H, et al. On steam pipe network modeling and flow rate calculation[J]. Procedia Engineering, 2012, 29: 1897–1903.
[8] 吴空. 合肥市供热管网现状及发展分析研究[D]. 合肥: 合肥工业大学, 2010.
WU Kong. The research of Hefei heating pipe network current situation and development[D]. Hefei: Hefei University of Technology, 2010.
[9] 周游, 李成乐. Excel在蒸汽管网水力计算的应用[J]. 煤气与热力, 2010, 30(5): 17–20
ZHOU You, LI Chengle. Application of excel to hydraulic calculation of steam network[J]. Gas & Heat, 2010, 30(5): 17–20
[10] 殷戈, 葛斌, 王培红. 蒸汽管网热力系统的建模与软件开发[J]. 热力发电, 2008, 37(5): 24–28
YIN Ge, GE Bin, WANG Peihong. Model-establishing and software-developing for thermodynamic system of steam pipe network[J]. Thermal Power Generation, 2008, 37(5): 24–28
[11] 阿拉木斯, 范世东. 架空蒸汽管道水力热力联合计算模型研究及应用[J]. 北京石油化工学院学报, 2018, 26(2): 65–70
A Lamusi, FAN Shidong. Research and application of the combined calculation model of hydraulic and steam power for overhead steam pipeline[J]. Journal of Beijing Institute of Petrochemical Technology, 2018, 26(2): 65–70
[12] KUMARI A, DAS S K, SRIVASTAVA P K. Data-driven modeling of fireside corrosion rate[J]. Anti-Corrosion Methods and Materials, 2017, 64(4): 397–404.
[13] AYHAN-SARAC B, KARLIK B, BALI T, et al. Neural network methodology for heat transfer enhancement data[J]. International Journal of Numerical Methods for Heat & Fluid Flow, 2007, 17(8): 788–798.
[14] LIU T X, LIU S Z, HENG J N, et al. A new hybrid approach for wind speed forecasting applying support vector machine with ensemble empirical mode decomposition and cuckoo search algorithm[J]. Applied Sciences, 2018, 8(10): 1754.
[15] 马修元, 段钰锋, 刘猛, 等. 基于PSO-BP神经网络的水焦浆管道压降预测[J]. 中国电机工程学报, 2012, 32(5): 54–60
MA Xiuyuan, DUAN Yufeng, LIU Meng, et al. Prediction of pressure drop of coke water slurry flowing in pipeline by PSO-BP neural network[J]. Proceedings of the CSEE, 2012, 32(5): 54–60
[16] NAFEY A S. Neural network based correlation for critical heat flux in steam-water flows in pipes[J]. International Journal of Thermal Sciences, 2009, 48(12): 2264–2270.
[17] 马钢, 李俊飞, 白瑞, 等. 基于PSO-SVM模型的油气管道内腐蚀速率预测[J]. 表面技术, 2019, 48(5): 43–48
MA Gang, LI Junfei, BAI Rui, et al. Prediction of corrosion rate in oil and gas pipelines based on PSO-SVM model[J]. Surface Technology, 2019, 48(5): 43–48
[18] 汪国山, 朱晓星, 谭锐, 等. 水和水蒸汽热力性质国际工业标准IAPWS-IF97和计算程序编制[J]. 汽轮机技术, 2005, 47(3): 161–164, 167
WANG Guoshan, ZHU Xiaoxing, TAN Rui, et al. Introduction to the international standard for properties of water and steam IAPWS-IF97 and programming[J]. Turbine Technology, 2005, 47(3): 161–164, 167
[19] HOFMANN R, LINZNER P, WALTER H, et al. New approximation algorithms for the state functions of water and steam for the application of transient processes and fast on-line applications[J]. Energy, 2018, 164: 1079–1096.
[20] TIEN BUI D, SHAHABI H, SHIRZADI A, et al. Landslide detection and susceptibility mapping by AIRSAR data using support vector machine and index of entropy models in Cameron Highlands, Malaysia[J]. Remote Sensing, 2018, 10(10): 1527.
[21] 刘荣海, 豆龙江, 万书亭, 等. 基于EEMD样本熵和支持向量机的高压断路器故障诊断[J]. 华北电力大学学报(自然科学版), 2018, 45(2): 82–88
LIU Ronghai, DOU Longjiang, WAN Shuting, et al. Fault diagnosis of high voltage circuit breaker based on EEMD sample entropy and support vector machine[J]. Journal of North China Electric Power University (Natural Science Edition), 2018, 45(2): 82–88
[22] 祝晓燕, 张金会, 付士鹏, 等. 基于集合经验模态分解和支持向量机的短期风速预测模型[J]. 华北电力大学学报(自然科学版), 2013, 40(5): 60–64
ZHU Xiaoyan, ZHANG Jinhui, FU Shipeng, et al. Short-term wind speed prediction model based on EEMD and SVM[J]. Journal of North China Electric Power University (Natural Science Edition), 2013, 40(5): 60–64
[23] CAI J J, MA X Q, LI Q. On-line monitoring the performance of coal-fired power unit: a method based on support vector machine[J]. Applied Thermal Engineering, 2009, 29(11/12): 2308–2319.
[24] 秦天牧, 吕游, 杨婷婷, 等. SCR烟气脱硝系统自适应混合动态模型[J]. 仪器仪表学报, 2016, 37(12): 2844–2850
QIN Tianmu, LV You, YANG Tingting, et al. Self-adaptive hybrid dynamic model of SCR flue gas denitration system[J]. Chinese Journal of Scientific Instrument, 2016, 37(12): 2844–2850