首页 | 本学科首页   官方微博 | 高级检索  
     

基于差分进化算法的供热节能控制系统
引用本文:闫峰.基于差分进化算法的供热节能控制系统[J].沈阳工业大学学报,2017,39(3):328-332.
作者姓名:闫峰
作者单位:1. 河北工业大学 建筑与艺术设计学院, 天津 300401; 2. 邢台学院 科研处, 河北 邢台 054001
基金项目:河北省科技厅科普专项资助项目(16K576650);河北省社会科学基金资助项目(HB15SH007)
摘    要:针对公共建筑集中供热系统能耗高、自动调节和实时监控难度大的问题,将数字温度传感器、芯片控制技术及CAN总线技术结合到一起,设计了一种基于差分进化算法的神经网络控制的公共建筑集中供热系统.系统具有降低遗传算法复杂性、快速收敛的优势,且自适应能力较强,能够实现供热流量自动调节和网络实时监控.为了验证该系统的节能效果,与传统节能控制系统的供热消耗进行了试验比较,结果表明,该系统最低平均节能10.1%,最高节能16.3%,节能效果更好.

关 键 词:公共建筑  集中供热  传感器  CAN总线  节能控制系统  差分进化算法  神经网络  

Heating energy saving control system based on differential evolution algorithm
YAN Feng.Heating energy saving control system based on differential evolution algorithm[J].Journal of Shenyang University of Technology,2017,39(3):328-332.
Authors:YAN Feng
Affiliation:1. School of Architecture and Art Design, Hebei University of Technology, Tianjin 300401, China; 2. Research Department, Xingtai University, Xingtai 054001, China
Abstract:Aiming at the problem that the energy consumption of central heating system in public buildings is high, and the automatic regulation and real-time monitoring are quite difficult, a central heating system in public buildings based on the neural network control of differential evolution algorithm was designed with the combination of digital temperature sensor, chip control technology and CAN bus technology. The system has the advantages in realizing the fast convergence and reducing the complexity of genetic algorithm, and has strong adaptive ability. The system can realize the automatic regulation and real-time network monitoring of heating flow. In order to verify the energy saving effect of the system, the proposed system was compared with the heating consumption of the traditional energy saving control system. The results show that the minimum average energy saving of the proposed system is 10.1%, and the maximum energy saving is 16.3%. And the proposed system has better energy saving effect.
Keywords:public building  central heating  sensor  CAN bus  energy saving control system  differential evolution algorithm  neural network  
本文献已被 CNKI 等数据库收录!
点击此处可从《沈阳工业大学学报》浏览原始摘要信息
点击此处可从《沈阳工业大学学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号