基于模糊聚类方法的制冷系统性能分析

摘要

A new method is proposed to analyze the operating performance of chiller system by using Fuzzy C-means (FCM) cluster method. A simulation model of chiller system is built based on Trnsys simulation software. Among all of the operating parameters of chiller system over a year, 5 main operating parameters are chosen for the cluster analysis. Three cluster centers are obtained by FCM cluster method, which represent three typical operating conditions of chiller system over a year. It is also found that the calculated error between the Operation Energy Efficiency Ratio (OEER) of each chiller over a year and the weighted average value of the Coefficient of Performance (COP) of the chiller in different cluster centers is small. The result illustrates that the OEER of a chiller over a year can be represented by the COP of the chiller in different cluster centers.%提出一种采用模糊聚类方法来分析制冷机组运行性能的方法。本文基于Trnsys仿真软件建立了制冷系统仿真模型，根据某制冷系统的全年运行数据，选取了影响制冷系统运行性能的5种运行参数进行聚类分析。结果表明：制冷系统的全年运行工况分成3类，这3类聚类数据的聚类中心可以用来表征制冷系统在全年运行中的3种典型运行工况。通过计算制冷系统各台制冷机组全年能效比和3个聚类中心工况下各台制冷机组运行能效比的加权平均值，发现二者之间的误差很小，说明可以通过基于聚类中心计算所获得的各台制冷机组的运行能效比来表征制冷机组全年运行的性能。