Thomas Huth-Fehre

Application of a Spectroscopic Infrared Focal Plane Array Sensor for On-Line Identification of Plastic Waste

A spectroscopic near-infrared imaging system, using a focal plane array (FPA) detector, is presented for remote and on-line measurements on a macroscopic scale. On-line spectroscopic imaging requires high-speed sensors and short image processing steps. Therefore, the use of a focal plane array detector in combination with fast chemometric software is investigated. As these new spectroscopic imaging systems generate so much data, multivariate statistical techniques are needed to extract the important information from the multidimensional spectroscopic images. These techniques include principal component analysis (PCA) and linear discriminant analysis (LDA) for supervised classification of spectroscopic image data. Supervised classification is a tedious task in spectroscopic imaging, but a procedure is presented to facilitate this task and to provide more insight into and control over the composition of the datasets. The identification system is constructed, implemented, and tested for a real-world application of plastic identification in municipal solid waste.

Comparison of an adaptive resonance theory based neural network (ART-2a) against other classifiers for rapid sorting of post consumer plastics by remote near-infrared spectroscopic sensing using an InGaAs diode array

An Adaptive Resonance Theory Based Artificial Neural Network (ART-2a) has been compared with Multilayer Feedforward Backpropagation of Error Neural Networks (MLF-BP) and with the SIMCA classifier. All three classifiers were applied to achieve rapid sorting of post-consumer plastics by remote near-infrared (NIR) spectroscopy. A new semiconductor diode array detector based on InGaAs technology has been experimentally tested for measuring the NIR spectra. It has been found by a cross validation scheme that MLF-BP networks show a slightly better discrimination power than ART-2a networks. Both types of artificial neural networks perform significantly better than the SIMCA method. A median sorting purity of better than 98% can be guaranteed for non-black plastics. More than 75 samples per second can be identified by the combination InGaAs diode array/neural network. However, MLF-BP neural networks can definitely not extrapolate. Uninterpretable predictions were observed in case of test samples that truly belong to a particular class but that are located outside the subspace defined by training set.

Adaptive resonance theory based neural network for supervised chemical pattern recognition ( FuzzyARTMAP) Part 2: Classification of post-consumer plastics by remote NIR spectroscopy using an InGaAs diode array

The supervised working FuzzyARTMAP pattern recognition algorithm has been applied to automated identification of post-consumer plastics by near-infrared spectroscopy (NIRS). Experimentally, a remote operating parallel multisensor device, based on a rapid InGaAs diode array detector combined with new collimation optics, has been used. The laboratory setup allows on-line identification of more than 100 spectra per second. Internal parameter settings of FuzzyARTMAP were varied to explore their influence on the classifier’s behavior. Discrimination results obtained were better than those from an optimized multilayer feedforward backpropagation artificial neural network (MLF-BP) and significantly better than those provided by the partial least squares method (PLSZ). Additional advantages of FuzzyARTMAP compared to these two classifiers are a significantly higher speed of calibration, the chemical interpretability of network weight coefficients and a built-in detector against extrapolations.

Detection of inorganic wood preservatives on timber by near infrared spectroscopy

The recycling of waste wood causes great problems due to the variety of toxic wood preservatives, varnishes and paints used. The fast and reliable distinction and sorting of treated and untreated wood on demolition sites could open new ways of wood recycling, e. g. for the production of chip boards. For this purpose, prepared wood samples treated with inorganic wood preservatives (arsenic, boron, copper salts) were investigated by near infrared-spectroscopy. In most cases, treated wood samples could be distinguished from untreated ones. Furthermore the type of wood preservative could be identified. The observed spectral features are electronic absorption bands and changes in the OH–band due to interaction with salt molecules.

Rapid Identification of Plastics from Electronic Devices With Nir-Spectroscopy

ABSTRACT In this study, a NIR- based identification system for recycling purposes of plastics from electronic devices has been constructed and tested with 91 typical samples, such as computer housings. The system consisted of a robust NIR-monochromator with a fast InGaAs-diode array detector, a conventional halogen lamp as light source and a standard PC for signal processing. Spectra have been collected in the wavelength range between 800 and 1700 nm. Chemometric data analysis with appropriate data preprocessing (smoothing, differentiation) led to the desired distinction of the different plastic types. It was shown, that the presented system has, due to its speed, the potential of being applied to high throughput recycling streams.

Fast identification of packaging waste by near infrared spectroscopy with an InGaAs array spectrograph combined with neural networks

An optical set-up consisting of a high-throughput NIR spectrometer with an InGaAs array (800 nm to 1700 nm) and a specially designed collection optics was used to record spectra from post consumer packages (PE, PET, PP, PS and a cardboard–plastic compound) located on an industrial conveyor belt with an integration time of 6.3 milliseconds per sample. The spectra were classified by neural networks with an identification rate of better than 98%. The set-up is, hence, regarded as suitable for the on-line identification of package materials.