基于選擇性模型組合的三維熒光光譜水質(zhì)分析方法

摘要：為提高三維熒光光譜水質(zhì)分析的精度,提出一種選擇性模型組合方法,采用相關(guān)系數(shù)法對(duì)三維熒光光譜激發(fā)波長(zhǎng)進(jìn)行選擇,并將被選中的激發(fā)波長(zhǎng)下的熒光發(fā)射光譜水質(zhì)分析子模型采用嶺回歸法進(jìn)行模型組合,得到對(duì)水質(zhì)指標(biāo)的組合模型.以一組總有機(jī)碳(TOC)范圍在3.41～125.35 mg·L~(-1),化學(xué)需氧量(COD)范圍在22.80～330.60 mg·L~(-1)的32個(gè)地表水和城市生活污水水樣做為研究對(duì)象,對(duì)其三維熒光光譜220～400脅范圍內(nèi)的10個(gè)激發(fā)波長(zhǎng)采用上述方法進(jìn)行選擇,分別針對(duì)TOC和COD指標(biāo)篩選出260,280,400 nm和220,280,400 nm各3個(gè)激發(fā)波長(zhǎng).采用部分最小二乘方法建立上述激發(fā)波長(zhǎng)下熒光發(fā)射光譜水質(zhì)分析子模型,根據(jù)嶺回歸法計(jì)算各子模型的組合系數(shù),分別得到對(duì)TOC和COD指標(biāo)的組合模型.實(shí)驗(yàn)結(jié)果表明:采用該方法得到的組合模型對(duì)TOC和COD兩種指標(biāo)的預(yù)測(cè)誤差均方根(RMSEP)相比精度最高的單一熒光發(fā)射光譜子模型分別減小了15.4%和17.5%,相比未經(jīng)模型選擇的組合模型分別減小了6.1%和10.9%.Abstract：A selective model combination method is proposed in this paper to improve the precision of water quality analysis with three dimensional fluorescence spectra. A correlation coefficient criterion was designed to select effective excitation wavelengths for sub-models building, based on which the ridge regression method was adopted to combine the selected sub-models to get the stacked model Thirty two samples from surface water and urban wastewater were used as research objects with total organic carbon (TOC) index from 3. 41 to 125. 35 mg·L~(-1) , and chemical oxygen demand (COD) index from 22.80 to 330. 60 mg·L~(-1) , and 10 excitation wavelengths in the range of 220-400 nm were adopted to generate three dimensional fluorescence spectra. Following the proposed correlation coefficient criterion, the excitation wavelengths of 260, 280 and 400 nm, and the excitation wavelengths of 220, 280 and 400 nm were selected respectively for TOC analysis and COD analysis, based on which two stacked models were built by using partial least square regression method for sub-models building and ridge regression method for sub-models combination. The experimental results show that, compared with the sub-models with the best prediction precision, the root mean square errors of prediction (RMSEP) of the stacked models decreased by 15.4% for TOC analysis, and 17.5% for COD analysis; and compared with the models without sub-models selection, the RMSEP of the stacked models decreased by 6.1% for TOC analysis and 10.9% for COD analysis. 作者： 武曉莉[1]李艷君[2]吳鐵軍[3] Author： WU Xiao-li[1]  LI Yan-jun[2]  WU Tie-jun[3] 作者單位： 浙江科技學(xué)院,浙江,杭州,310023浙江大學(xué)城市學(xué)院,浙江,杭州,310015浙江大學(xué)工業(yè)控制技術(shù)國(guó)家重點(diǎn)實(shí)驗(yàn)室,浙江,杭州,310027 期 刊： 光譜學(xué)與光譜分析   ISTICEISCIPKU Journal： SPECTROSCOPY AND SPECTRAL ANALYSIS 年，卷(期)： 2010, 30(4) 分類號(hào)： X832 O657.3 關(guān)鍵詞： 三維熒光光譜    模型組合    激發(fā)波長(zhǎng)選擇    模型選擇    總有機(jī)碳    化學(xué)需氧量    Keywords： 3-D fluorescence spectra    Model combination    Excitation wavelength selection    Model selection    Total organic carbon    Chemical oxygen demand    機(jī)標(biāo)分類號(hào)： TN2 O65 機(jī)標(biāo)關(guān)鍵詞： 選擇性    模型組合    三維熒光光譜    水質(zhì)分析    分析方法    Combination    Model    Based    Fluorescence Spectra    quality analysis    regression method    correlation coefficient    激發(fā)波長(zhǎng)    熒光發(fā)射光譜    three dimensional    組合模型    子模型    TOC    fluorescence    COD 基金項(xiàng)目： 國(guó)家(863計(jì)劃)項(xiàng)目

【基于選擇性模型組合的三維熒光光譜水質(zhì)分析方法】相關(guān)文章：

基于三維熒光光譜技術(shù)的多組分分析濃度校準(zhǔn)方法研究04-27

基于葉綠素?zé)晒夤庾V分析的黃瓜霜霉病害預(yù)測(cè)模型05-07

基于Bayes方法的診斷模型分析04-26

石化廢水的三維熒光光譜特征05-07

基于標(biāo)識(shí)指數(shù)法的水質(zhì)灰色動(dòng)態(tài)模型群預(yù)測(cè)分析04-25

藻類的三維熒光光譜辨別及算法研究05-02

三維熒光光譜法分析西寧環(huán)境水樣有機(jī)污染類型04-26

雙交組合農(nóng)藝性狀的ADAA模型及其分析方法05-02

太湖水熒光光譜分析04-30

甲醇和乙醇的三維熒光光譜特性研究05-07