吸收式制冷机组逆神经网络设定优化

王亚昆; 吴爱国; 董娜

doi:10.7652/xjtuxb201801018

您当前的位置：

首页 >

文章列表页 >

吸收式制冷机组逆神经网络设定优化

更新时间：2025-07-09

- 吸收式制冷机组逆神经网络设定优化
- A Set Point Optimization Method for Absorption Chiller Based on Inverse Neural Network
- 西安交通大学学报 2018年52卷第1期页码：123-128+142
- 作者机构：
  
  天津大学电气自动化与信息工程学院,天津,300072
- 作者简介：
- 基金信息：
  
  : 2017-05-22。作者简介: 王亚昆(1993—),女,硕士生;吴爱国(通信作者),男,教授,博士生导师。基金项目: 国家自然科学基金资助项目(61403274);天津市智能制造科技重大专项资助项目(15ZXZNGX00160)
- DOI：10.7652/xjtuxb201801018
  中图分类号： TB651;TP273
- 网络首发：2018-01-10，
  
  纸质出版：2018
- 稿件说明：
移动端阅览
王亚昆, 吴爱国, 董娜. 吸收式制冷机组逆神经网络设定优化[J]. 西安交通大学学报, 2018,52(1):123-128+142.

A Set Point Optimization Method for Absorption Chiller Based on Inverse Neural Network[J]. 2018, 52(1): 123-128+142.
王亚昆, 吴爱国, 董娜. 吸收式制冷机组逆神经网络设定优化[J]. 西安交通大学学报, 2018,52(1):123-128+142. DOI： 10.7652/xjtuxb201801018.

A Set Point Optimization Method for Absorption Chiller Based on Inverse Neural Network[J]. 2018, 52(1): 123-128+142. DOI： 10.7652/xjtuxb201801018.

摘要

针对吸收式制冷机组非线性、难以控制的特点

提出了一种基于逆神经网络模型的设定点优化方案。首先

以11.5 kW单效溴化锂吸收式制冷机组为对象

使用人工神经网络方法建立了机组模型

通过对溴冷机制冷原理的分析

建立了系统结构为5-6-2的网络模型

该神经网络模型的相关系数大于0.99且方均根误差小于0.2%

与实验数据取得了良好的拟合效果; 然后

利用该模型对溴冷机的各个输入参数进行灵敏度分析

并据此选择热水供水温度与冷却水流量作为优化方法的控制输入参数; 最后

以冷冻水输出温度作为系统控制输出

对其进行优化计算

并采用改进的粒子群优化算法与逆神经网络相结合的方法

计算制冷机组的最优控制输入参数。通过实验与仿真分析

可知该算法的计算时间在30 s以内

低于吸收式制冷机组的稳定时间; 溴冷机的目标输出与仿真计算结果间的误差小于0.02%

表明该方案可以应用于吸收式制冷机组的在线控制。

Abstract

In view of the nonlinearity and difficulty in control of absorption chiller

a set point optimization method based on inverse neural network model is proposed. Firstly

taking an 11.5 kW single-effect lithium bromide absorption chiller as the research object

an artificial neural network method is used to establish a model of the unit. Through the analysis of the chiller

a network model with a 5-6-2 structure is established. The correlation coefficient of the neural network model is more than 0.99 and the root mean square error is less than 0.2%

so the experimental data are well fitted. Subsequently

the sensitivity analysis of each input parameter of the chiller is conducted to select the hot water supply temperature and the cooling water flow rate as the control input parameters to be estimated. Finally

as the control output of the system

the chilled water output temperature is optimized. The optimal control input parameters of the chilling system are estimated by combination of an improved particle swarm optimization and the inverse neural network algorithm. Through the analysis of experiment and simulation

the calculation time of this method is within 30 s

which is shorter than the stable time of absorption chiller. Moreover

the error between target output and simulation calculation is less than 0.02%. These results show that the proposed scheme is suitable for online control of absorption chiller.

关键词

Keywords

references

KAYNAKLI O, KILIC M. Theoretical study on the effect of operating conditions on performance of absorption refrigeration system [J]. Energy Conversion and Management, 2007, 48: 599-607.

EICKER U, PIETRUSCHKA D. Design and performance of solar powered absorption cooling systems in office buildings [J]. Energy and Buildings, 2009, 41: 81-91.

王永涛, 吴裕远, 禹志强, 等. NH3-H2O-LiBr吸收式制冷机吸收和蒸发性能的实验研究 [J]. 西安交通大学学报, 2011, 45(3): 40-43.

WANG Yongtao, WU Yuyuan, YU Zhiqiang, et al. Experiment on absorption and evaporation performance of a NH3-H2O-LiBr absorption chiller [J]. Journal of Xi'an Jiaotong University, 2011, 45(3): 40-43.

CHOW T T, ZHANG Q, LIN Z, et al. Global optimization of absorption chiller system by genetic algorithm and neural network [J]. Energy and Buildings, 2002, 34: 103-109.

许玉杰, 张士杰, 肖云汉. 单效溴化锂吸收式制冷机动态特性及控制分析 [J]. 中国电机工程学报, 2015, 35(s1): 105-112.

XU Yujie, ZHANG Shijie, XIAO Yunhan. Dynamic performance and control system analysis of the single-effect absorption chiller [J]. Proceeding of the CSEE, 2015, 35(s1): 105-112.

田健, 朱瑞琪, 冯全科. 风冷制冷机组的多变量模糊控制研究 [J]. 西安交通大学学报, 2006, 40(5): 514-517.

TIAN Jian, ZHU Ruiqi, FENG Quanke. Study on multi variable fuzzy neural control for air cooled refrigeration system [J]. Journal of Xi'an Jiaotong University, 2006, 40(5): 514-517.

ROSIEK S, BATLLES F J. Modelling a solar-assisted air-conditioning system installed in CIESOL building using an artificial neural network [J]. Renewable Energy, 2010, 35: 2894-2901.

ESCOBEDO-TRUJILLO B A, COLORADO D, RIVERA W, et al. Neural network and polynomial model to improve the coefficient of performance prediction for solar intermittent refrigeration system [J]. Solar Energy, 2016, 129: 28-37.

COLORADO D, HERNÁNDEZ JA, RIVERA W, et al. Optimal operation conditions for a single-stage heat transformer by means of an artificial neural network inverse [J]. Applied Energy, 2011, 88: 1281-1290.

LABUS J, MARIMON M A, CORONAS A. Experimental evaluation of small capacity H2O-LiBr absorption heat pump in cooling and heating modes [J]. International Journal of Air-Conditioning and Refrigeration, 2010, 18(4): 317-325.

吴小华,杨俊玲,越云凯,等.一种新型热压缩机运行特性实验研究.2017,51(11):144-149.[doi:10.7652/xjtuxb201711 020]

刘展,张少华,张晓屿,等.地面热力学排气系统实验研究.2017,51(7):8-15.[doi:10.7652/xjtuxb201707002]

武晓昆,陈文卿,周明龙,等.双螺杆制冷压缩机气流脉动衰减器的研究与开发.2017,51(4):23-29.[doi:10.7652/xjtuxb 201704004]

薛洪武,吴爱国,董娜.制冷系统自抗扰解耦控制.2016,50(9):85-90.[doi:10.7652/xjtuxb201609014]

王哲,厉彦忠,李正宇,等.液氦/超流氦制冷系统负压换热器仿真及优化设计.2016,50(8):143.[doi:10.7652/xjtuxb 201608023]

赖欢,陈振华,高荣,等.大型高速低温风洞冷量回收的方法研究.2016,50(6):136-142.[doi:10.7652/xjtuxb201606021]

钟兵,洪伟,苏岩,等.控制参数对增压缸内直喷汽油机部分负荷下微粒排放特性的影响.2016,50(5):95-100.[doi:10.7652/xjtuxb201605014]

乔亦圆,杨东方,曹锋,等.R134a/R23复叠制冷系统级间容量比的优化分析.2016,50(2):104-110.[doi:10.7652/xjtuxb 201602018]

宋明毅,吴伟烽,李直.汽车空调压缩机气阀运动规律模拟.2015,49(12):144-150.[doi:10.7652/xjtuxb201512023]

吴毅,王旭荣,杨翼,等.以液化天然气为冷源的超临界CO2-跨临界CO2冷电联供系统.2015,49(9):58-62.[doi:10.7652/xjtuxb201509011]

何丽娟,梁晶晶,张少华.CO2-[emim][Tf2N]二元混合体系超额混合焓的预测.2015,49(9):99-104.[doi:10.7652/xjtuxb201509017]

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

相变冷却换热器动态热响应降阶预测方法研究

采用动力学模态分解和长短期记忆网络的压缩空气储气装置流场动态预测方法

新能源汽车热管理系统协同优化策略

高超声速飞行器干扰补偿与解耦最优反步控制策略

语义区分和子图整合驱动的知识图谱表示学习方法