Pattern recognition and feature selection for the discrimination between grades of commercial plastics

Abstract A new method of polymer classification is described involving thermal analysis of polymer properties as temperature is changed. It is based on the analysis of the damping factor (tan δ) as a function of temperature. In this study four polymer groups, Polypropylene, Low Density Polyethylene, Polystyrene and Acrylonitrile–Butadiene–Styrene, each characterised by different grades, were studied using Dynamic Mechanical Analysis. The aim is to distinguish polymer (plastics) grades. The first steps are to group polymers into semi-crystalline and amorphous and remove outliers. Prior to employing classification algorithms, feature reduction was performed: two methods are compared, namely principal components analysis and parameterization by means of curve fitting using Gaussian end Exponential functions. Three classification methods are then compared, namely k-nearest neighbours method and two methods for discriminant analysis, based on class distances using both Euclidean and Mahalanobis measures. Both methods of feature reduction gave good results; using Nearest Neighbours on PCA scores 97% of samples were correctly classified, whereas parameterisation combined with Euclidean distance gave 94% correct classification.

[1]  Paul D. Garn,et al.  Thermoanalytical methods of investigation , 1965 .

[2]  John W. Sammon,et al.  An Optimal Discriminant Plane , 1970, IEEE Transactions on Computers.

[3]  Oxana Ye. Rodionova,et al.  Hard and soft methods for prediction of antioxidants' activity based on the DSC measurements , 2005 .

[4]  Elfed Lewis,et al.  Combining principal component analysis with an artificial neural network to perform online quality assessment of food as it cooks in a large-scale industrial oven , 2005 .

[5]  Weissberger.  Physical methods of chemistry , 1971 .

[6]  P. Carniti,et al.  Catalytic thermal degradation of polymers: Degradation of polypropylene , 1984 .

[7]  V. K. Jayaraman,et al.  Feature extraction and denoising using kernel PCA , 2003 .

[8]  P. Haines,et al.  Principles of Thermal Analysis and Calorimetry , 2002 .

[9]  D. Coomans,et al.  Optimization by statistical linear discriminant analysis in analytical chemistry , 1979 .

[10]  Gábor E. Veress,et al.  PRIMA: a new pattern recognition method , 1985 .

[11]  Richard G. Brereton,et al.  Chemometrics: Data Analysis for the Laboratory and Chemical Plant , 2003 .

[12]  B. Kowalski,et al.  K-Nearest Neighbor Classification Rule (pattern recognition) applied to nuclear magnetic resonance spectral interpretation , 1972 .

[13]  R. Brereton,et al.  Component detection weighted index of analogy: similarity recognition on liquid chromatographic mass spectral data for the characterization of route/process specific impurities in pharmaceutical tablets. , 2005, Analytical Chemistry.

[14]  Károly Héberger,et al.  Principal component analysis of polymer–solvent and filler–solvent interactions by inverse gas chromatography , 2005 .

[15]  Paul Geladi,et al.  Principal Component Analysis , 1987, Comprehensive Chemometrics.

[16]  S. D. Jong,et al.  Handbook of Chemometrics and Qualimetrics , 1998 .

[17]  Philip H. Ramsey.  Data Fitting in the Chemical Sciences , 1994 .

[18]  G. Dean,et al.  The determination of dynamic properties of polymers and composites , 1978 .

[19]  H. Siesler,et al.  Near-infrared spectroscopy:principles,instruments,applications , 2002 .

[20]  Andrzej Cichocki,et al.  Kernel PCA for Feature Extraction and De-Noising in Nonlinear Regression , 2001, Neural Computing & Applications.

[21]  D. Jones,et al.  Dynamic mechanical analysis of polymeric systems of pharmaceutical and biomedical significance. , 1999, International journal of pharmaceutics.

[22]  G. Dunteman.  Principal Components Analysis , 1989 .

[23]  R. H. Boyd.  Relaxation processes in crystalline polymers: experimental behaviour — a review , 1985 .

[24]  D. Dollimore,et al.  An introduction to thermogravimetry , 1969 .

[25]  R. Brereton,et al.  Pattern recognition for the analysis of polymeric materials. , 2006, The Analyst.

[26]  P. Haines.  Thermal Methods of Analysis , 1995 .

[27]  G. M. Swallowe.  Mechanical Properties and Testing of Polymers , 1999 .

[28]  P. K. Gallagher,et al.  Handbook of thermal analysis and calorimetry , 1998 .

[29]  David G. Stork,et al.  Pattern Classification , 1973 .

[30]  D. Massart,et al.  The Mahalanobis distance , 2000 .

[31]  Desire L. Massart,et al.  Methods for outlier detection in prediction , 2002 .

[32]  Gabriele Reich,et al.  Near-infrared spectroscopy and imaging: basic principles and pharmaceutical applications. , 2005, Advanced drug delivery reviews.