基于粒子群优化算法优化BP神经网络模型的间接空冷散热器性能监测

动力工程学报 ›› 2019, Vol. 39 ›› Issue (12) : 973-980.

监测与测量

李昊^1,2, 罗云^3,4, 李瑞东³, 苏永健³, 陈雪林³, 徐义巍³, 郭洪远³, 李鹏竹³

作者信息 +

Performance Monitoring of Indirect Air-cooled Radiators Based on Particle Swarm Optimization BP Neural Network Model

LI Hao^1,2, LUO Yun^3,4, LI Ruidong³, SU Yongjian³, CHEN Xuelin³, XU Yiwei³, GUO Hongyuan³, LI Pengzhu³

Author information +

History +

摘要

为监测间接空冷散热器的换热性能，提出了监测间接空冷塔出水温度的方法。根据间接空冷系统散热器传热量计算和热平衡方程，分析了间接空冷塔出水温度的影响因素，建立了以环境温度、环境风速、大气压力、间接空冷塔循环水进水温度、循环水进水压力、出水压力和百叶窗开度7个主要参数为输入，出水温度为输出的BP神经网络模型。为避免该模型陷入局部最优，采用非线性动态惯性权重的粒子群优化（PSO）算法对BP神经网络模型的初始权值和阈值进行了优化，构建了PSO-BP神经网络预测模型，并根据某660 MW间接空冷机组的运行数据对该模型进行了训练和验证。结果表明：采用PSO算法优化的BP神经网络模型具有较强泛化能力，预测精度高于单纯的BP神经网络模型，预测平均绝对百分比误差为0.55%。

Abstract

To monitor the heat transfer performance of indirect air-cooled radiators, a method was put forward for monitoring the outlet temperature of related indirect air-cooling towers. Based on heat transfer calculation and heat balance equations, an analysis was conducted on the factors influencing the outlet temperature of the indirect air-cooling towers, and subsequently a BP neural network model was established by taking the ambient temperature, wind speed, atmospheric pressure, inlet circulating water temperature of indirect air cooling tower, inlet pressure of circulating water, outlet water pressure and the shutter opening as the input variables, and outlet water temperature as the outlet variable. To avoid obtaining partial optimal solutions only, the particle swarm optimization (PSO) based on nonlinear dynamic inertia weight was used to optimize the initial weight and threshold of the BP neural network model, and then a neural network prediction model of PSO-BP was set up, which was trained and verified using the operation data of a 660 MW unit indirect air cooling system. Results show that the BP neural network model optimized by PSO algorithm has strong generalization ability, with higher prediction accuracy than the pure BP neural network model, and the mean error predicted is 0.55%.

导出引用

李昊, 罗云, 李瑞东, 苏永健, 陈雪林, 徐义巍, 郭洪远, 李鹏竹. 基于粒子群优化算法优化BP神经网络模型的间接空冷散热器性能监测. 动力工程学报. 2019, 39(12): 973-980

LI Hao, LUO Yun, LI Ruidong, SU Yongjian, CHEN Xuelin, XU Yiwei, GUO Hongyuan, LI Pengzhu. Performance Monitoring of Indirect Air-cooled Radiators Based on Particle Swarm Optimization BP Neural Network Model. Journal of Chinese Society of Power Engineering. 2019, 39(12): 973-980

参考文献

[1] 吕凯, 雷彦荣, 彭鹏, 等. 间接空冷机组冷端系统节能改造方案[J]. 热力发电, 2016, 45(12):89-94, 123. LÜ Kai, LEI Yanrong, PENG Peng, et al. Study on energy-saving reconstruction plans for cold end system of indirect air cooling units[J]. Thermal Power Generation, 2016, 45(12):89-94, 123.
[2] 韩中合, 张垚鹏, 李恒凡. 侧风环境下间接空冷塔百叶窗开度调节方案[J]. 汽轮机技术, 2018, 60(1):41-44, 48. HAN Zhonghe, ZHANG Yaopeng, LI Hengfan. Adjustment scheme of louver opening degree under crosswind environment of indirect air cooling tower[J]. Turbine Technology, 2018, 60(1):41-44, 48.
[3] 田松峰, 戴文鹏, 向同琼, 等. 间接空冷塔防侧风影响的数值模拟及优化[J]. 汽轮机技术, 2016, 58(2):101-104. TIAN Songfeng,DAI Wenpeng,XIANG Tongqiong, et al. Numerical simulation and optimization on anti-crosswind of indirect air cooling tower[J]. Turbine Technology, 2016, 58(2):101-104.
[4] 田松峰, 刘会阳, 柴艳琴. 散热器热负荷分配对间接空冷系统运行的影响[J]. 动力工程学报, 2015, 35(3):224-229. TIAN Songfeng, LIU Huiyang, CHAI Yanqin. Effects of radiator heat load distribution on operation performance of the indirect air-cooling system[J]. Journal of Chinese Society of Power Engineering, 2015, 35(3):224-229.
[5] 刘培忠, 杨志军. 高寒地区间接空冷机组散热器防冻预暖措施[J]. 中国电力, 2013, 46(5):18-22. LIU Peizhong, YANG Zhijun. Anti-freezing and pre-heating measures for radiator in indirect air-cooling units in cold areas[J]. Electric Power, 2013, 46(5):18-22.
[6] 李彦军, 伍小林, 安健雄, 等. 高寒、高海拔地区间接空冷系统防冻技术研究[J]. 华北电力技术, 2013(8):22-26. LI Yanjun, WU Xiaolin, AN Jianxiong, et al. Study on anti-freezing technology of indirect air cooling condenser system in cold and high altitude region[J]. North China Electric Power, 2013(8):22-26.
[7] 葛晓霞, 肖洪闯, 嵇卫, 等. 基于果蝇算法优化广义回归神经网络的凝汽器真空预测[J]. 汽轮机技术, 2018, 60(3):208-212. GE Xiaoxia, XIAO Hongchuang, JI Wei, et al. Vacuum pediction of condenser based on generalized regression neural network optimized by fruit fly algorithm[J]. Turbine Technology, 2018, 60(3):208-212.
[8] 张利平, 陈浩天, 王伟峰, 等. 应用PSO算法改进Elman神经网络的双压凝汽器真空预测[J]. 热力发电, 2015, 44(3):53-57. ZHANG Liping, CHEN Haotian, WANG Weifeng, et al. Application of PSO algorithm-modified Elman neural network in vacuum prediction for dual-pressure condensers[J]. Thermal Power Generation, 2015, 44(3):53-57.
[9] 王建国, 林乐平. 粒子群算法与径向神经网络相结合的凝汽器真空预测模型[J]. 热力发电, 2015, 44(10):72-76. WANG Jianguo, LIN Leping. A vacuum value prediction method for steam condensers using RBF neural network optimized by particle swarm algorithm[J]. Thermal Power Generation, 2015, 44(10):72-76.
[10] 张维蔚, 王甲斌, 田瑞, 等. 表面式间接空冷散热器传热特性分析[J]. 汽轮机技术, 2018, 60(3):189-192. ZHANG Weiwei, WANG Jiabin, TIAN Rui, et al. Analysis of heat transfer characteristics of surface indirect air cooled radiators[J]. Turbine Technology, 2018, 60(3):189-192.
[11] 洪文鹏, 陈重. 基于自适应粒子群优化BP神经网络的氨法烟气脱硫效率预测[J]. 动力工程学报, 2013, 33(4):290-295. HONG Wenpeng, CHEN Zhong. Efficiency prediction of ammonia flue gas desulfurization based on adaptive PSO-BP model[J]. Journal of Chinese society of Power Engineering, 2013, 33(4):290-295.
[12] 肖文平, 叶家玮. 混沌粒子群优化神经网络算法应用于SRG建模[J]. 计算机工程与应用, 2010, 46(27):238-241. XIAO Wenping, YE Jiawei. CPSO-BPNN algorithm and its application of SRG modeling[J]. Computer Engineering and Applications, 2010, 46(27):238-241.
[13] 邓博, 徐鸿, 郭鹏, 等. 变负荷下超(超)临界机组过热器壁温预测[J]. 中国电力, 2018, 51(3):13-20. DENG Bo, XU Hong, GUO Peng, et al. Prediction of superheater tube wall temperature in supercritical/ultra-supercritical boilers for different loading[J]. Electric Power, 2018, 51(3):13-20.
[14] 周志华. 机器学习[M]. 北京:清华大学出版社, 2016:104-105.
[15] 李劲柏,刘复平.汽轮机阀门流量特性函数优化和对机组安全性经济性的影响[J]. 中国电力, 2008, 41(12):50-53. LI Jinbai, LIU Fuping. Optimization for the flow characteristic function of turbine valves and the influences on safe and economic operation[J]. Electric Power, 2008, 41(12):50-53.
[16] 王东风, 孟丽. 粒子群优化算法的性能分析和参数选择[J]. 自动化学报, 2016, 42(10):1552-1561. WANG Dongfeng, MENG Li. Performance analysis and parameter selection of PSO algorithms[J]. Acta Automatica Sinica, 2016, 42(10):1552-1561.
[17] 李丽, 牛奔. 粒子群优化算法[M]. 北京:冶金工业出版社, 2010:34-35.
[18] 王建国, 孟娜, 殷鑫. 基于粒子群优化算法的凝汽器真空预测模型[J]. 动力工程学报, 2012, 32(10):815-819. WANG Jianguo, MENG Na, YIN Xin. Prediction model of condenser vacuum degree based on particle swarm optimization algorithm[J]. Journal of Chinese Society of Power Engineering, 2012, 32(10):815-819.
[19] 孙保民, 信晶, 杨斌, 等. 基于独立成分分析预测电站锅炉NO_x排放量[J]. 中国电力, 2013, 46(9):39-43. SUN Baomin, XIN Jing, YANG Bin, et al. Forecasting the NO_x emissions from utility boilers based on independent component analysis[J]. Electric Power, 2013, 46(9):39-43.
[20] BOOSTANI M, KARIMI H, AZIZI S. Heat transfer to oil-water flow in horizontal and inclined pipes:experimental investigation and ANN modeling[J]. International Journal of Thermal Sciences, 2017, 111:340-350.

PDF(1127 KB)

Accesses

Citation

Detail

段落导航

摘要
Abstract
关键词
Key words
引用本文
参考文献

Received	Published
2019-01-04	2019-12-15
Issue Date
2019-12-15

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

{{custom_fnGroup.title_cn}}

脚注