Plastic Classification with X-ray Absorption Spectroscopy Based on Back Propagation Neural Network

2017 ◽  
Vol 71 (11) ◽  
pp. 2538-2548 ◽  
Author(s):  
Qian Wang ◽  
Xiaomei Wu ◽  
Lingcong Chen ◽  
Zheng Yang ◽  
Zheng Fang
Keyword(s):  
Absorption Spectroscopy ◽  
Recognition Rate ◽  
Back Propagation ◽  
Principal Component ◽  
Back Propagation Neural Network ◽  
X Ray ◽  
Analysis Methods ◽  
Average Recognition Rate ◽  
The Stability ◽  
X Ray Absorption

Currently, spectral analysis methods used in the classification of plastics have limitations that do not apply to opaque plastics or the stability of experimental results is not strong. In this paper, X-ray absorption spectroscopy (XAS) has been applied to classify plastics due to its strong penetrability and stability. Fifteen kinds of plastics are selected as specimens. X-ray, which is excited by a voltage of 60 kV, penetrated these specimens. The spectral data acquired by CdTe X-ray detector are processed by principal component analysis (PCA) and other data analysis methods. Then the back propagation neural networks (BPNN) algorithm is used to classify the processed data. The average recognition rate reached 96.95% and classification results of all types of plastic results were analyzed in detail. It indicates that XAS has the potential to classify plastics and that XAS can be used in some fields such as plastic waste sorting and recycling. At the same time, the technology of XAS, in the future, can also be used to classify more substances.

Estimating the number of pure chemical components in a mixture by X-ray absorption spectroscopy

2014 ◽  
Vol 21 (5) ◽  
pp. 1140-1147 ◽  
Author(s):  
Alain Manceau ◽  
Matthew Marcus ◽  
Thomas Lenoir
Keyword(s):  
Data Analysis ◽  
Absorption Spectroscopy ◽  
Principal Component ◽  
Weighted Sums ◽  
Chemical Components ◽  
F Test ◽  
X Ray ◽  
Number Of Components ◽  
Pure Compounds ◽  
X Ray Absorption

Principal component analysis (PCA) is a multivariate data analysis approach commonly used in X-ray absorption spectroscopy to estimate the number of pure compounds in multicomponent mixtures. This approach seeks to describe a large number of multicomponent spectra as weighted sums of a smaller number of component spectra. These component spectra are in turn considered to be linear combinations of the spectra from the actual species present in the system from which the experimental spectra were taken. The dimension of the experimental dataset is given by the number of meaningful abstract components, as estimated by the cascade or variance of the eigenvalues (EVs), the factor indicator function (IND), or the F-test on reduced EVs. It is shown on synthetic and real spectral mixtures that the performance of the IND and F-test critically depends on the amount of noise in the data, and may result in considerable underestimation or overestimation of the number of components even for a signal-to-noise (s/n) ratio of the order of 80 (σ = 20) in a XANES dataset. For a given s/n ratio, the accuracy of the component recovery from a random mixture depends on the size of the dataset and number of components, which is not known in advance, and deteriorates for larger datasets because the analysis picks up more noise components. The scree plot of the EVs for the components yields one or two values close to the significant number of components, but the result can be ambiguous and its uncertainty is unknown. A new estimator, NSS-stat, which includes the experimental error to XANES data analysis, is introduced and tested. It is shown that NSS-stat produces superior results compared with the three traditional forms of PCA-based component-number estimation. A graphical user-friendly interface for the calculation of EVs, IND, F-test and NSS-stat from a XANES dataset has been developed under LabVIEW for Windows and is supplied in the supporting information. Its possible application to EXAFS data is discussed, and several XANES and EXAFS datasets are also included for download.

X-ray absorption spectroscopy in the dispersive mode with synchrotron radiation: optical considerations

1988 ◽  
Vol 21 (1) ◽  
pp. 15-22 ◽  
Author(s):  
H. Tolentino ◽  
E. Dartyge ◽  
A. Fontaine ◽  
G. Tourillon
Keyword(s):  
Absorption Spectroscopy ◽  
Energy Resolution ◽  
Energy Scale ◽  
Source Size ◽  
X Ray ◽  
Size Dependent ◽  
Scale Reliability ◽  
Position Sensitive ◽  
The Stability ◽  
X Ray Absorption

Aspects of the optics of the energy-dispersive scheme for X-ray absorption spectroscopy are discussed. The idea of a set of monochromatic focus points related to a set of local Rowland circles is introduced to account for the source-size effect on the energy resolution. It is shown that there exists an optimized location of the position-sensitive detector where the energy resolution is no longer source-size dependent. In addition, the stability of the dispersive optical system has been estimated and a 10 meV energy-scale reliability is currently achieved.

The Effect of Water on the Stability of Iron Oxide and Iron Carbide Nanoparticles in Hydrogen and Syngas Followed by in Situ X-ray Absorption Spectroscopy

2012 ◽  
Vol 116 (13) ◽  
pp. 7367-7373 ◽  
Author(s):  
Peter Thüne ◽  
Prabashini Moodley ◽  
Freek Scheijen ◽  
Hans Fredriksson ◽  
Remco Lancee ◽  
...  
Keyword(s):  
Iron Oxide ◽  
Absorption Spectroscopy ◽  
Iron Carbide ◽  
X Ray ◽  
Effect Of Water ◽  
The Stability ◽  
X Ray Absorption

Fast and Non-Destructiveness Discrimination of Varieties of Fragrant Mushroom Using Near Infrared Spectroscopy

2011 ◽  
Vol 460-461 ◽  
pp. 159-164
Author(s):  
Peng Cheng Nie ◽  
Weiong Zhang ◽  
Yan Yang ◽  
Di Wu ◽  
Yong He
Keyword(s):  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
High Speed ◽  
Near Infrared ◽  
Recognition Rate ◽  
Back Propagation ◽  
Nir Spectroscopy ◽  
Principal Component ◽  
Back Propagation Neural Network ◽  
Hidden Layer

Visible/near-infrared spectroscopy (NIRS) is the millimeter wave ,It is the high speed and non-destructiveness method, high precision and reliable detection data, is a rapid and non-destructiveness method for discrimination varieties of Fragrant mushrooms by means of VIS/NIR spectroscopy was developed in this study. The relationship between the reflectance spectra and Fragrant mushrooms varieties was established. The spectral data was compressed by the wavelet transform (WT). The features from WT can be visualized in principal component (PC) space, appeared to provide a reasonable clustering of the varieties of Fragrant mushrooms. The fivet principal components computed by PCA had been applied as inputs to a back propagation neural network(BP) with one hidden layer. The 220 samples of four varieties were selected randomly to build BP model. This model was used to predict the varieties of 40 unknown samples. The predict recognition rate has achieved 99.5%. This model was reliable and practicable.

Sign in / Sign up

Export Citation Format

Share Document