On-line post consumer package identification by NIR spectroscopy combined with a FuzzyARTMAP classifier in an industrial environment

被引:38
作者
Feldhoff, R
Wienke, D
Cammann, K
Fuchs, H
机构
[1] CATHOLIC UNIV NIJMEGEN,ANALYT CHEM LAB,NL-6525 ED NIJMEGEN,NETHERLANDS
[2] UNIV MUNSTER,INST PHYS,D-48149 MUNSTER,GERMANY
关键词
NIR spectroscopy; plastics recycling; waste sorting; principal component analysis; neural networks;
D O I
10.1366/0003702971940215
中图分类号
TH7 [仪器、仪表];
学科分类号
0804 ; 080401 ; 081102 ;
摘要
An optical setup consisting of a high-throughput near-IR (NIR) spectrograph with an InGaAs-array detector and specially designed collection optics is used to record spectra from post consumer packages located on an industrial conveyor belt. NIR spectra of packages of different polymers (PE, PET, PP, PS, and PVC) and of a cardboard/plastic compound are recorded between 900 and 1700 nm with 6.3-ms integration time, The visual distinction between the spectra is demonstrated by aid of principal component analysis (PCA) plots. The spectra are further classified by a FuzzyARTMAP neural network. The method is assessed to be suitable for on-line identification under industrial conditions.
引用
收藏
页码:362 / 368
页数:7
相关论文
共 16 条
[1]  
Alam M.K., 1995, NIR NEWS, V6, P10, DOI [10.1255/nirn.287, DOI 10.1255/NIRN.287]
[2]  
ALAM MK, 1994, SPECTROSCOPY, V9, P30
[3]  
COHEN MJ, 1993, P SOC PHOTO-OPT INS, V1946, P436, DOI 10.1117/12.158695
[4]  
Eisenreich N., 1992, 23 INT ANN C ICT KAR
[5]  
FELDHOFF F, 1995, J INFRARED SPECTROSC, V3, P3
[6]   NIR - REMOTE-SENSING AND ARTIFICIAL NEURAL NETWORKS FOR RAPID IDENTIFICATION OF POST CONSUMER PLASTICS [J].
HUTHFEHRE, T ;
FELDHOFF, R ;
KANTIMM, T ;
QUICK, L ;
WINTER, F ;
CAMMANN, K ;
VANDENBROEK, W ;
WIENKE, D ;
MELSSEN, W ;
BUYDENS, L .
JOURNAL OF MOLECULAR STRUCTURE, 1995, 348 :143-146
[7]  
LUCHT H, 1993, UMWELT, V23, P443
[8]  
Michaeli W., 1993, STOFFLICHES KUNSTSTO
[9]  
STAHL I, 1993, GAK, P134
[10]  
Summers J. W., 1990, J VINYL TECHNOL, V12, P161