• CN:11-2187/TH
  • ISSN:0577-6686

机械工程学报 ›› 2019, Vol. 55 ›› Issue (6): 194-202.doi: 10.3901/JME.2019.06.194

• 可再生能源与工程热物理 • 上一篇    下一篇

变频空调实际运行模式识别及数据挖掘

梁志豪1, 巫江虹1, 谢子立2   

  1. 1. 华南理工大学机械与汽车工程学院 广州 510641;
    2. 多伦多大学文理学院 安大略 M5S 2E8 加拿大
  • 收稿日期:2018-03-06 修回日期:2018-10-28 出版日期:2019-03-20 发布日期:2019-03-20
  • 通讯作者: 巫江虹(通信作者),女,1967年出生,博士,教授,博士研究生导师。主要研究方向为相变蓄热热泵技术、室温磁制冷、移动空调。E-mail:pmjhwu@scut.edu.cn
  • 作者简介:梁志豪,男,1990年出生。主要研究方向为基于数据挖掘的房间空调器长效性能。E-mail:13480204681@139.com;谢子立,男,1995年出生。主要研究方向为大数据挖掘。Email:zili.xie@mail.utoronto.ca
  • 基金资助:
    国家自然科学基金(51776076)和国家重点研发计划“政府间国际科技创新合作”重点专项(2016YFE011810)资助项目。

Variable Frequency Room Air Conditioner Operation Pattern Recognition and Data Mining

LIANG Zhihao1, WU Jianghong1, XIE Zili2   

  1. 1. School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510641;
    2. College of Arts and Sciences, University of Toronto, Ontario, M5S 2E8 Canada
  • Received:2018-03-06 Revised:2018-10-28 Online:2019-03-20 Published:2019-03-20

摘要: 变频空调的长期运行数据是空调在实际环境中运行状态最直接的反映,空调运行的内在规律潜藏在其长期的运行数据中,分析其长期运行数据时,由于数据冗余、存在异常数据等原因,需要采用数据挖掘的方法进行研究。采用聚类算法进行分析,空调的运行模式可总结为三种模式,即上午高负荷模式、下午高负荷模式以及低频平稳模式,三种模式下空调的送风温度都比较接近,但室外温度有所区别。上午(下午)高负荷模式中,室外温度在上午(下午)最高,功率及制冷性能系数(Energy efficiency ratio,EER)分别处于峰值及谷值,低频平稳模式下,室外温度并不高,开机后空调运行比较稳定,运行参数变化不大。此后,采用控制变量法和多项式拟合来分析环境工况参数对空调性能的影响,室外侧环境温度、空调回风温度的升高均导致空调的功率增加,而空调的EER随着回风温度的升高而增加,随着室外温度及空调的功率(运行频率)的增加而下降。采用神经网络算法,研究基于空调送风侧参数预测变频空调性能的方法,并建立神经网络预测模型,该方法的预测误差在15%以内,可以通过控制空调运行时的送风侧参数,达到控制空调性能的目的。最后,根据以上研究成果,提出变频空调控制优化方法,提高空调在线长期运行能效。

关键词: 变频空调, 模式识别, 能耗分析, 数据挖掘, 优化运行

Abstract: The long running data of the variable frequency room air conditioners is the most direct reflection of their operation state in actual surroundings. Since the inherent law of air conditioners is hidden behind the long term operation data with a great quantity of redundancy and outlier data, data mining method is needed to solve this problem. The clustering algorithm is used for the analysis of air conditioners' operation modes. Three modes are concluded:morning high load mode, afternoon high load mode and stable low frequency mode. The temperature of air supply in the three modes is relatively similar, but the outdoor temperature is different. In the morning high load or afternoon high load mode, the outdoor temperature peaks in the morning and afternoon, meanwhile the energy consumption reaches the maximum and the energy efficiency ratio (EER) reaches the minimum respectively. In the stable low frequency mode, the outdoor temperature is not high, the operation is relatively stable after starting, and the operating parameters are relatively stable. Since then, the controlling variables method and polynomial fitting method are applied to analyze the relationships between the operation parameters and the performance of the air conditioners. It shows that air conditioner energy consumption will increase with the increase of outdoor temperature, and the EER will rise as the indoor temperature increases but will decrease as the energy consumption (frequency) increases. Then the neural network algorithm is used to predict the performance of inverter air conditioner based on the air side parameters. And this model has been proved to be effective in predicting air conditioner energy consumption and EER with the error range within 15%, which means it can be used to control air conditioner performance through air conditioner inlet air parameters. Finally, according to the above research results, the optimization method of variable frequency air conditioner control is put forward to improve air conditioners' long term operation energy efficiency.

Key words: data mining, operation optimization, pattern recognition, performance analysis, variable frequency air conditioner

中图分类号: