KNN结合PCA在激光诱导荧光光谱识别矿井突水中的应用  

Application of the Identification of Mine Water Inrush with LIF Spectrometry and KNN Algorithm Combined with PCA

作　　者：何晨阳[1] 周孟然[1] 闫鹏程[1] 

机构地区：[1]安徽理工大学电气与信息工程学院,安徽淮南232001

出　　处：《光谱学与光谱分析》2016年第7期2234-2237,共4页Spectroscopy and Spectral Analysis

基　　金：国家"十二五"科技支撑计划重点项目(2013BAK06B01);国家自然科学基金项目(51174258)资助

摘　　要：矿井突水的迅速识别与分类对于井下水灾防治工作有着重要的意义。提出一种KNN结合PCA运用在激光诱导荧光光谱快速识别矿井突水水源中的新方法。利用激光器发射激光通过可浸入式探头射入水样,得到四种突水水样共80组荧光光谱数据,再分别对每组数据进行预处理,处理后的数据中每种水样取15组数据作为训练集,共60组,其余20组作为预测集。利用主成分分析(PCA)对数据进行处理,之后在主成分分析的基础上利用KNN算法进行分类识别。实验过程中,各预处理方法在主成分个数为2的情况下,进行KNN算法分类的正确率都达到100%。Rapid identification and classification of mine water inrush is important for flood prevention work underground .This paper proposed a method of KNN combined with PCA identification of water inrush in mine with the laser induced fluorescence spectrum with an immersion probe laser into water samples .The fluorescence spectra of 4 kinds of water samples were obtained . For each set of data preprocessing ,the processed data in each sample from 15 sets of data as the training setwith a total of 60 groups .The other 20 groups were used as the prediction set .The data were processed by principal component analysis （PCA） , and then the KNN algorithm was used to classify and identify the principal component analysis .During the experiment ,the pre-treatment method in the principal component number is 2 while the correct rate has reached 100% by KNN classification algo-rithm .

关 键 词：KNN算法 PCA 激光诱导荧光 矿井突水 水源识别 

分 类 号：O657.3[理学—分析化学]