本文關(guān)鍵詞：小波變換和連續(xù)投影算法在火龍果總酸無(wú)損檢測(cè)中的應(yīng)用　出處：《光譜學(xué)與光譜分析》2016年05期 　論文類型：期刊論文

  更多相關(guān)文章： 可見/近紅外光譜技術(shù) 無(wú)損檢測(cè) 小波變換(WT) 連續(xù)投影算法(SPA) 火龍果 總酸(TA)

【摘要】：應(yīng)用可見/近紅外光譜技術(shù)、小波變換(WT)和連續(xù)投影算法(SPA),對(duì)火龍果總酸含量(TA)進(jìn)行精確、快速的無(wú)損檢測(cè),為火龍果內(nèi)部品質(zhì)無(wú)損檢測(cè)提供科學(xué)依據(jù)。利用Maya2000光纖光譜儀采集380~1 099nm范圍的火龍果漫反射光譜數(shù)據(jù),通過(guò)WT消噪、SPA優(yōu)選波長(zhǎng)和偏最小二乘回歸(PLSR)分析方法,建立了火龍果總酸的定量預(yù)測(cè)模型。試驗(yàn)結(jié)果表明:經(jīng)過(guò)WT消噪聯(lián)合SPA優(yōu)選波長(zhǎng)壓縮光譜變量后建立的WT-SPA-PLSR模型,預(yù)測(cè)精度都高于全譜PLSR模型。由全部樣本的原始光譜變量作為輸入變量建立PLSR模型的預(yù)測(cè)相關(guān)系數(shù)(R_p)為0.851 394,預(yù)測(cè)均方根誤差(RMSEP)為0.086 848;全部樣本的原始光譜數(shù)據(jù)使用dbN(N=2,3,…,10)小波進(jìn)行分解消噪,其中消噪效果最優(yōu)的是db4小波2層分解(db4-2),WT-PLSR模型的Rp為0.915 635,RMSEP為0.066 752,小波變換消噪后的光譜預(yù)測(cè)模型精度明顯提高;原始光譜經(jīng)過(guò)db10-3小波消噪聯(lián)合SPA算法,從570個(gè)光譜變量中優(yōu)選出530,545,604,626,648,676,685,695,730,897,972,1 016nm共12個(gè)變量作為輸入變量,建立WT-SPA-PLSR預(yù)測(cè)模型,模型的RP為0.882 83,RMSEP為0.077 39。SPA算法適合火龍果TA模型的光譜變量選擇,能夠有效提取與總酸相關(guān)度高的波長(zhǎng)變量,增加了預(yù)測(cè)模型的精度和穩(wěn)定性。研究結(jié)果表明小波變換技術(shù)聯(lián)合連續(xù)投影算法的漫反射近紅外光譜無(wú)損檢測(cè)火龍果總酸含量具有可行性。
[Abstract]:The visible / near infrared spectroscopy, wavelet transform (WT) and continuous projection algorithm (SPA) are applied to detect the total acid content (TA) of Pitaya accurately and quickly, so as to provide a scientific basis for pitaya's internal quality nondestructive testing. Using Maya2000 optical fiber spectrometer to collect pitaya diffuse reflectance data in 380~1 099nm range, we established a quantitative prediction model of Pitaya total acid by WT denoising, SPA preferred wavelength and partial least squares regression (PLSR) analysis method. The experimental results show that the prediction accuracy of the WT-SPA-PLSR model is higher than that of the full spectrum PLSR model after the WT denoising combined with the SPA optimization of the wavelength compression spectrum variable. The predicted correlation coefficient (R_p) of PLSR model was 0.851394 and the root mean square error (RMSEP) of all models was 0.086848. The original spectral data of all samples were dbN (N=2,3,...). 10), wavelet decomposition denoising, the denoising effect is the optimal DB4 wavelet decomposition level 2 (db4-2), WT-PLSR model Rp was 0.915635, RMSEP was 0.066752. The wavelet transform de noised spectral prediction model accuracy is obviously improved; the original spectra by db10-3 wavelet denoising combined SPA algorithm optimized 530545604626648676685695730897972,1 016nm total of 12 variables as input variables from 570 spectral variables, establish WT-SPA-PLSR prediction model, model RP was 0.88283, RMSEP was 0.07739. SPA algorithm is suitable for spectral variable selection of Pitaya TA model. It can effectively extract wavelength variables with high total acid correlation and increase the accuracy and stability of prediction models. The results show the feasibility of nondestructive detection of total acid content of Pitaya by wavelet transform combined with continuous projection method.
【作者單位】： 華南農(nóng)業(yè)大學(xué)電子工程學(xué)院;華南農(nóng)業(yè)大學(xué)南方農(nóng)業(yè)機(jī)械與裝備關(guān)鍵技術(shù)教育部重點(diǎn)實(shí)驗(yàn)室;國(guó)家柑橘產(chǎn)業(yè)技術(shù)體系機(jī)械研究室;華南農(nóng)業(yè)大學(xué)工程學(xué)院;
【基金】：國(guó)家現(xiàn)代農(nóng)業(yè)產(chǎn)業(yè)技術(shù)體系建設(shè)專項(xiàng)項(xiàng)目(CARS-27) 教育部高等學(xué)校博士學(xué)科點(diǎn)專項(xiàng)科研基金項(xiàng)目(20124404120006)資助
【分類號(hào)】：O657.33;TS255.7
【正文快照】： 1.華南農(nóng)業(yè)大學(xué)電子工程學(xué)院,廣東廣州5106422.華南農(nóng)業(yè)大學(xué)南方農(nóng)業(yè)機(jī)械與裝備關(guān)鍵技術(shù)教育部重點(diǎn)實(shí)驗(yàn)室,廣東廣州5106423.國(guó)家柑橘產(chǎn)業(yè)技術(shù)體系機(jī)械研究室,廣東廣州5106424.華南農(nóng)業(yè)大學(xué)工程學(xué)院,廣東廣州510642引言水果品質(zhì)無(wú)損檢測(cè)一直是農(nóng)業(yè)工程領(lǐng)域重要的研究課題[1]。

【相似文獻(xiàn)】

相關(guān)期刊論文 前5條

1 甘秀海;梁志遠(yuǎn);王道平;胡外英;王瑞;;固相微萃取-氣相色譜-質(zhì)譜法分析火龍果果肉中揮發(fā)性成分[J];理化檢驗(yàn)(化學(xué)分冊(cè));2012年06期

2 劉小玲,許時(shí)嬰,王璋;火龍果色素的基本性質(zhì)及結(jié)構(gòu)鑒定[J];無(wú)錫輕工大學(xué)學(xué)報(bào);2003年03期

3 胡力川;蘭佳玉;董海英;王秀峰;;火龍果中微量元素Fe Mn Zn含量測(cè)定[J];微量元素與健康研究;2012年01期

4 袁亞芳;趙珍珍;王威;陳清西;余志雄;;紅肉火龍果果皮色素的分離、純化和HPLC-MS分析[J];福建農(nóng)林大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年06期

5 ;[J];;年期

，

本文編號(hào)：1340144