主元分析用于多联式空调系统传感器故障检测和诊断

发布时间：2018-02-24 14:38

本文关键词： 主元分析故障检测及诊断 Q统计量 Q贡献率传感器多联式空调系统　出处：《制冷学报》2017年03期 　论文类型：期刊论文

【摘要】：作为多元数据分析方法之一,主元分析(PCA)被广泛运用于诊断制冷空调系统的传感器故障。本文首先结合热平衡原理以及多联机运行的控制逻辑,筛选系统中常用的18个传感器变量,建立多联机(VRF)传感器的故障分析(FDD)模型。然后结合主元分析的算法原理,给出以Q统计量和Q贡献率为检验标准的传感器故障检测与诊断流程。利用实测数据验证工作,引入不同类型和程度的传感器故障,分析得到不同故障条件下的故障检测和诊断特性。结果表明:总体上,主元分析应用于多联机传感器故障检测与诊断过程是可靠的。具体特征表现为:不同类型的传感器在不同故障类型及程度条件下,故障检测效果差异明显;在小偏差故障条件下,基于主元分析的传感器故障检测方法的故障检测效率较低,并且针对个别传感器而言,其整体故障检测效率偏低。鉴于故障诊断是基于故障检测的结果,因此上述故障检测方法在FDD过程中将起到重要的作用。
[Abstract]:As one of the multivariate data analysis methods, Principal component Analysis (PCA) is widely used to diagnose sensor faults in refrigeration and air conditioning systems. Firstly, this paper combines the principle of heat balance and the control logic of multi-on-line operation. The FDD model of multiple on-line VRFs is established by selecting 18 sensor variables commonly used in the system. Then the principle of principal component analysis (PCA) algorithm is combined. The flow chart of sensor fault detection and diagnosis based on Q statistics and Q contribution rate is given. Different types and degrees of sensor faults are introduced by the verification of measured data. The characteristics of fault detection and diagnosis under different fault conditions are obtained. The results show that, Principal component analysis (PCA) is reliable in the process of fault detection and diagnosis of multi-on-line sensors. The main features are as follows: different types of sensors have different fault detection effects under different fault types and degrees; Under the condition of small deviation fault, the fault detection efficiency of sensor based on principal component analysis is low, and the overall fault detection efficiency is low for individual sensors. In view of the fault diagnosis is based on the result of fault detection. Therefore, the above fault detection methods will play an important role in the FDD process.
【作者单位】：华中科技大学制冷与低温工程系;珠海格力电器有限公司;北京建筑大学供热供燃气通风及空调工程北京市重点实验室;
【基金】：国家自然科学基金(51576074,51328602)资助项目供热供燃气通风及空调工程北京市重点实验室研究基金(NR2013K02)项目资助~~
【分类号】：TB657.2

【参考文献】