主成分分析的燃气采暖热水炉运行性能评价

Evaluation of Operation Performance of Gas-fired Heating and Hot Water Combi-boilers Based on Principal Component Analysis

选取燃气采暖热水炉运行过程中额定热输入时供暖热效率、干烟气中O2体积分数、干烟气中CO体积分数、干烟气中CO2体积分数、干烟气中NOx体积分数及排烟温度6个指标,并随机挑选40个样本进行了相关试验。利用主成分分析法建立了燃气采暖热水炉运行性能评价模型。主成分分析结果显示,基于该方法转换后的3个主成分指标能够代替原来6个指标88.9%的信息量,该方法能够将复杂的信息简单化,且能够获得量化的评价指标,可以应用于燃气采暖热水炉运行性能的定量评价。研究中关注到:考虑到特征向量的非唯一性,应注意软件选取的特征向量是否合适的问题,并给出了验证和确定方法。验证结果显示,SPSS数据分析软件选取的特征向量对文中案例的主成分1、主成分2是合适的,对主成分3是不合适的,应乘以-1后再参与运算。

Six indicators including the heating heat efficiency at the rated heat input during the operation of the gas-fired heating and hot water combi-boilers,the O 2 volume fraction in the dry flue gas,the CO volume fraction in the dry flue gas,the CO 2 volume fraction in the dry flue gas,the NO x volume fraction in the dry flue gas and the flue gas exhaust temperature are selected,and 40 samples are randomly selected for related experiments. The operation performance evaluation model of gas-fired heating and hot water combi-boilers is established by principal component analysis. The principal component analysis results show that the three principal component indexes converted by this method can replace 88.9% information of the original six indicators. This method can simplify complex information and obtain quantitative evaluation indicators,which can be applied to quantitative evaluation of the operation performance of gas-fired heating and hot water combi-boilers. Considering the non-uniqueness of the feature vector,it should be paid attention whether the feature vector selected by the software is suitable,and the verification and determination methods are given. The verification results show that the feature vector selected by SPSS data analysis software is suitable for the principal component 1 and principal component 2 in the paper case,is not suitable for the principal component 3,and should be multiplied by -1 before participating in the operation.