光谱学与光谱分析
光譜學與光譜分析
광보학여광보분석
Spectroscopy and Spectral Analysis
2015年
11期
3182-3186
,共5页
高光谱%化学计量学方法%EVA胶膜%层压温度%光伏电池
高光譜%化學計量學方法%EVA膠膜%層壓溫度%光伏電池
고광보%화학계량학방법%EVA효막%층압온도%광복전지
Hyperspectral imaging%Chemometrics%Ethylene-Vinyl Acetate copolymer%Encapsulation temperature%Photovoltaic cells
提出了利用高光谱成像技术结合化学计量学方法实现在线无损预测光伏电池中乙烯‐醋酸乙烯共聚物(EVA)胶膜层压温度的方法。四类EVA胶膜层压的温度控制在128,132,142和148℃。采集的高光谱波段范围在904.58~1700.01 nm之间。每类样本建模集包含90个样本,预测集包含10个样本。从获得的EV A胶膜高光谱图像中选取150×150像素大小的感兴趣区域,并以该区域内所有的像素点包含的光谱反射率平均值作为该样本的光谱特征曲线。分别采用偏最小二乘回归法、多分类支持向量机法和大间隔最邻近法对高光谱薄膜样本层压温度进行建模和预测。权重回归系数图表明短波和长波近红外波段高光谱数据对层压温度预测都有贡献。由于EV A高分子材料反射高光谱数据表现出了较强的非线性性,偏最小二乘法预报性能受到较大影响,为95%,而基于核方法的预测模型在高维特征空间一定程度消除了E V A高分子材料测量光谱非线性特性的影响,较为准确地反映原始EV A高分子材料光谱数据与层压温度之间的关系,比较上述三种模型的预测精度可知,大间隔最邻近模型对EV A胶膜层压温度的预测精度率最高,达到100%。结果表明,应用高光谱成像技术在线无损预测 EVA胶膜层压温度是可行的,为实现光伏电池夹层中EVA高分子材料封装温度自动监测与控制创造了条件。
提齣瞭利用高光譜成像技術結閤化學計量學方法實現在線無損預測光伏電池中乙烯‐醋痠乙烯共聚物(EVA)膠膜層壓溫度的方法。四類EVA膠膜層壓的溫度控製在128,132,142和148℃。採集的高光譜波段範圍在904.58~1700.01 nm之間。每類樣本建模集包含90箇樣本,預測集包含10箇樣本。從穫得的EV A膠膜高光譜圖像中選取150×150像素大小的感興趣區域,併以該區域內所有的像素點包含的光譜反射率平均值作為該樣本的光譜特徵麯線。分彆採用偏最小二乘迴歸法、多分類支持嚮量機法和大間隔最鄰近法對高光譜薄膜樣本層壓溫度進行建模和預測。權重迴歸繫數圖錶明短波和長波近紅外波段高光譜數據對層壓溫度預測都有貢獻。由于EV A高分子材料反射高光譜數據錶現齣瞭較彊的非線性性,偏最小二乘法預報性能受到較大影響,為95%,而基于覈方法的預測模型在高維特徵空間一定程度消除瞭E V A高分子材料測量光譜非線性特性的影響,較為準確地反映原始EV A高分子材料光譜數據與層壓溫度之間的關繫,比較上述三種模型的預測精度可知,大間隔最鄰近模型對EV A膠膜層壓溫度的預測精度率最高,達到100%。結果錶明,應用高光譜成像技術在線無損預測 EVA膠膜層壓溫度是可行的,為實現光伏電池夾層中EVA高分子材料封裝溫度自動鑑測與控製創造瞭條件。
제출료이용고광보성상기술결합화학계량학방법실현재선무손예측광복전지중을희‐작산을희공취물(EVA)효막층압온도적방법。사류EVA효막층압적온도공제재128,132,142화148℃。채집적고광보파단범위재904.58~1700.01 nm지간。매류양본건모집포함90개양본,예측집포함10개양본。종획득적EV A효막고광보도상중선취150×150상소대소적감흥취구역,병이해구역내소유적상소점포함적광보반사솔평균치작위해양본적광보특정곡선。분별채용편최소이승회귀법、다분류지지향량궤법화대간격최린근법대고광보박막양본층압온도진행건모화예측。권중회귀계수도표명단파화장파근홍외파단고광보수거대층압온도예측도유공헌。유우EV A고분자재료반사고광보수거표현출료교강적비선성성,편최소이승법예보성능수도교대영향,위95%,이기우핵방법적예측모형재고유특정공간일정정도소제료E V A고분자재료측량광보비선성특성적영향,교위준학지반영원시EV A고분자재료광보수거여층압온도지간적관계,비교상술삼충모형적예측정도가지,대간격최린근모형대EV A효막층압온도적예측정도솔최고,체도100%。결과표명,응용고광보성상기술재선무손예측 EVA효막층압온도시가행적,위실현광복전지협층중EVA고분자재료봉장온도자동감측여공제창조료조건。
A novel method of combination of the chemometrics and the hyperspectral imaging techniques was presented to detect the temperatures of Ethylene‐Vinyl Acetate copolymer (EVA ) films in photovoltaic cells during the thermal encapsulation process .Four varieties of the EVA films which had been heated at the temperatures of 128 ,132 ,142 and 148 ℃ during the pho‐tovoltaic cells production process were used for investigation in this paper .These copolymer encapsulation films were firstly scanned by the hyperspectral imaging equipment (Spectral Imaging Ltd .Oulu ,Finland) .The scanning band range of hyperspec‐tral equipemnt was set between 904.58 and 1 700.01 nm .The hyperspectral dataset of copolymer films was randomly divided in‐to two parts for the training and test purpose .Each type of the training set and test set contained 90 and 10 instances ,respec‐tively .The obtained hyperspectral images of EVA films were dealt with by using the ENVI (Exelis Visual Information Solu‐tions ,USA) software .The size of region of interest (ROI) of each obtained hyperspectral image of EVA film was set as 150 × 150 pixels .The average of reflectance hyper spectra of all the pixels in the ROI was used as the characteristic curve to represent the instance .There kinds of chemometrics methods including partial least squares regression (PLSR) ,multi‐class support vector machine (SVM) and large margin nearest neighbor (LMNN) were used to correlate the characteristic hyper spectra with the en‐capsulation temperatures of of copolymer films .The plot of weighted regression coefficients illustrated that both bands of short‐and long‐wave near infrared hyperspectral data contributed to enhancing the prediction accuracy of the forecast model .Because the attained reflectance hyperspectral data of EVA materials displayed the strong nonlinearity ,the prediction performance of lin‐ear modeling method of PLSR declined and the prediction precision only reached to 95% .The kernel‐based forecast models were introduced to eliminate the impact of nonlinear hyperspectral data to some extent through mapping the original nonlinear hyper‐spectral data to the high dimensional linear feature space ,so the relationship between the nonlinear hyperspectral data and the encapsulation temperatures of EVA films was fully disclosed finally .Compared with the prediction results of three proposed models ,the prediction performance of LMNN was superior to the other two ,whose final recognition accuracy achieved 100% . The results indicated that the methods of combination of LMNN model with the hyperspectral imaging techniques was the best one for accurately and rapidly determining the encapsulation temperatures of EVA films of photovoltaic cells .In addition ,this paper had created the ideal conditions for automatically monitoring and effectively controlling the encapsulation temperatures of EVA films in the photovoltaic cells production process .