基于灰色关联分析的BP神经网络对混流闭式冷却塔出水温度的预测

doi:10.19596/j.cnki.1001-246x.8376

计算物理 ›› 2022, Vol. 39 ›› Issue (1): 53-59.DOI: 10.19596/j.cnki.1001-246x.8376

基于灰色关联分析的BP神经网络对混流闭式冷却塔出水温度的预测

李洪(), 章立新*(), 任燕, 高明, 刘婧楠

上海理工大学能源与动力工程学院, 上海市动力工程多相流动与传热重点实验室, 上海 200093

收稿日期:2021-04-14 出版日期:2022-01-25 发布日期:2022-09-03
通讯作者: 章立新
作者简介:
李洪(1998-)，男，硕士研究生，研究方向为流动与传热传质，E-mail：hongli19_usst@163.com
基金资助:
国家自然科学基金(51976127)

Prediction of Water Temperature of Mixed-flow Closed Cooling Tower Based on BP Neural Network and Grey Correlation Analysis

Hong LI(), Lixin ZHANG*(), Yan REN, Ming GAO, Jingnan LIU

Shanghai Key Laboratory of Multiphase Flow and Heat Transfer in Power Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

Received:2021-04-14 Online:2022-01-25 Published:2022-09-03
Contact: Lixin ZHANG

摘要/Abstract

摘要：

通过控制变量法对混流闭式冷却塔进行测试, 采用灰色关联分析法对影响出水温度的因素进行筛选, 将关联度较大的5个因子作为输入参数, 进而建立灰色_BP神经网络预测模型, 对混流闭式冷却塔的出水温度进行预测。操作参数包括进水温度、湿球温度、补水温度、循环水流量和风量, 输出值为出水温度。网络采用三层结构, 隐含层神经元数为4个, 迭代次数为30 000次, 使用不涉及训练阶段的实验数据来验证所建立的模型。结果表明, 灰色_BP神经网络模型比传统BP神经网络模型的预测结果更加准确, 其预测值与实际值的相关系数、平均相对误差、均方根误差, 分别为0.998 9、0.293 4%和0.152 9, 因而可认为灰色_BP神经网络是预测混流闭式冷却塔出水温度的有效工具。

关键词: 混流闭式冷却塔, 出水温度, 灰色关联分析, BP神经网络

Abstract:

In this study, a mixed flow closed cooling tower was tested with a control variable method. The factors affecting outlet water temperature were screened with a grey correlation analysis method. Five most important factors were taken as input features in a gray_BP neural network which was developed to predict outlet water temperature of the mixed flow closed cooling tower. These factors include inlet water temperature, wet bulb temperature, water refill temperature, circulating water flow rate and air volume, and the prediction output is outlet water temperature. The network adopts a three-layer structure, four-hidden layer neurons, and 30 000 iterations. Experimental data that involve no training set were used to validate the developed model. It shows that the gray neural network model outperforms the traditional BP neural network model. The correlation coefficient, average relative error, root mean square error are 0.998 9, 0.293 4% and 0.152 9, respectively. We concluded that the gray_BP neural network is a promising algorithm for predicting water temperature of a mixed flow closed cooling tower.

Key words: mixed flow closed cooling tower, outlet water temperature, grey correlation analysis, BP neural network

李洪, 章立新, 任燕, 高明, 刘婧楠. 基于灰色关联分析的BP神经网络对混流闭式冷却塔出水温度的预测[J]. 计算物理, 2022, 39(1): 53-59.

Hong LI, Lixin ZHANG, Yan REN, Ming GAO, Jingnan LIU. Prediction of Water Temperature of Mixed-flow Closed Cooling Tower Based on BP Neural Network and Grey Correlation Analysis[J]. Chinese Journal of Computational Physics, 2022, 39(1): 53-59.

图/表 10

图1 测试系统流程图

Fig.1 Flow chart of test system

表1 测试设备参数

Table 1 Test equipment parameters

参数	测量仪器	测试范围	精度
温度/℃	PT100铂电阻	0~100	±0.15
风速/(m·s^-1)	风速仪	0~30	0.1
循环水流量/(m³·h^-1)	电磁流量计	0~300	0.005
喷淋水流量/(m³·h^-1)	超声波流量计	0~500	0.1

表2 实验测试样本参数范围

Table 2 Experimental test sample parameter ranges

参数	范围
干球温度T_d/℃	27.1 ~ 37.3
湿球温度T_w/℃	24.6 ~ 29.5
风量Q_w/(10⁴m³·h^-1)	6.3 ~ 11.4
进水温度T_i/℃	35.7 ~ 55.1
出水温度T_o/℃	32.0 ~ 43.5
循环水流量Q_c/(m³·h^-1)	120.00 ~ 233.00
喷淋水流量Q_s/(m³·h^-1)	33.60 ~ 200.00
补水水温T_a/℃	26.7 ~ 35.3

图2 各影响因子所占权重

Fig.2 Weights of influencing factors

图3 BP神经网络结构示意图

Fig.3 A schematic of BP neural network structure

表3 不同隐含层神经元个数测试结果

Table 3 Test result of the number of neurons in different hidden layers

隐含层节点数	r	MRE/%	RMSE
2	0.993 8	0.711 9	0.539 1
3	0.986 1	1.217 0	0.593 1
4	0.998 9	0.293 4	0.152 9
5	0.998 8	0.357 9	0.191 5
6	0.977 0	0.887 4	0.758 1

图4 平均相对误差随迭代次数的变化

Fig.4 Mean relative error as a function of number of iteration

图5 BP神经网络出水温度预测结果

Fig.5 Predictions of effluent temperature with BP neural network

图6 灰色_BP神经网络出水温度预测结果

Fig.6 Predictions of effluent temperature with grey BP neural network

图7 实际出水温度与预测出水温度的偏差

Fig.7 Degree of actual effluent temperatures deviate from predicted values

参考文献 18

1	赵顺安. 冷却塔工艺原理[M]. 北京: 中国建筑工业出版社, 2015: 3- 11.
2	史美中. 热交换器原理与设计[M]. 南京: 东南大学出版社, 2009: 7- 8.
3	宋嘉梁, 阮圣奇, 陈永东, 等. 基于神经网络模型的自然通风逆流湿式冷却塔热力性能研究[J]. 流体机械, 2019, 47 (3): 88- 92.
4	ZHOU Qian , WEI Duqu . Firing activity of memristor neural network under field coupling[J]. Chinese Journal of Computational Physics, 2020, 37 (6): 750- 756.
5	靳藩. 神经计算智能基础原理·方法[M]. 成都: 西南交通大学出版社, 2000: 135- 136.
6	朱大奇, 史慧. 人工神经网络原理及应用[M]. 北京: 科学出版社, 2006: 5- 6.
7	GAO Ming , SUN Fengzhong , ZHOU Shoujun , et al. Performance prediction of wet cooling tower using artificial neural network under cross-wind conditions[J]. International Journal of Thermal Sciences, 2009, 48 (3): 583- 589. DOI
8	GAO Ming , SHI Yuetao , WANG Nini , et al. Artificial neural network model research on effects of cross-wind to performance parameters of wet cooling tower based on level Froude number[J]. Applied Thermal Engineering, 2013, 51 (1-2): 1226- 1234. DOI
9	刚文杰, 王劲柏. 基于神经网络的冷却塔出水温度的预测[C]. 全国暖通空调制冷2010年学术年会, 2010.
10	段小容, 陈友明, 赵云峰, 等. 基于神经网络的冷却塔性能预测与评估[C]. 全国暖通空调制冷学术年会, 2010.
11	刘鹏飞, 李锐, 王岩. 基于灰色神经网络模型的区域供热负荷预测研究[J]. 暖通空调, 2019, 49 (5): 124- 128.
12	李玉云, 王永骥. 人工神经网络在暖通空调领域的应用研究发展[J]. 暖通空调, 2001, 31 (1): 38- 41. DOI
13	WU Jiasheng , ZHANG Guoqiang , ZHANG Quan , et al. Artificial neural network analysis of the performance characteristics of a reversibly used cooling tower under cross flow conditions for heat pump heating system in winter[J]. Energy and Buildings, 2011, 43 (7): 1685- 1693. DOI
14	QI Xiaoni , LIU Yongqi , GUO Qianjian , et al. Performance prediction of a shower cooling tower using wavelet neural network[J]. Applied Thermal Engineering, 2016, 108 (5): 475- 485.
15	ZHOU Yuhao , LIU Huiqing , QI Peng , et al. Forecast of oil production in fractured-vuggy reservoir by using recurrent neural networks[J]. Chinese Journal of Computational Physics, 2018, 35 (6): 668- 674.
16	孙国营, 孙新杰, 陕振沛, 等. 基于灰色关联和BP神经网络的地下水PH值预测研究[J]. 数学的实践与认识, 2020, 50 (14): 147- 154.
17	邱微, 樊庆锌. 寒冷地区城市水资源承载力模型[M]. 哈尔滨: 哈尔滨工业大学出版社, 2013: 67- 68.
18	FENG Cunfeng , KONG Fanmin , ZHANG Xueyao , et al. Identification of primary proton component at the knee with artificial neural networks[J]. Chinese Journal of Computational Physics, 1999, 16 (6): 568- 572.

基于灰色关联分析的BP神经网络对混流闭式冷却塔出水温度的预测

Prediction of Water Temperature of Mixed-flow Closed Cooling Tower Based on BP Neural Network and Grey Correlation Analysis

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 18

相关文章 0

编辑推荐

Metrics

作者中心

审稿中心

期刊浏览

期刊介绍