Prediction of Polyethylene Density by Near-Infrared Spectroscopy Combined with Neural Network Analysis

Abstract

A rapid and intact method has been developed for predicting polyethylene density by near-infrared spectroscopy combined with neural network analysis. Near-infrared spectra in the region of 1.1-2.2 µm wavelength were measured using pellets or powders of twenty-three kinds of polyethylene (PE) with different densities (0.898-0.962 g cm-3). The spectra were used for training a back-propagation neural network after normalized and second-derivative treatments to predict PE density. Although only a small number of spectral data were used for training, a leave-one-out test of neural network analysis has demonstrated good results. In comparison, principal component regression (PCR) analysis and partial least-squares (PLS) regression analysis were applied. The correlation coefficients (R) were calculated to be 1.000, 0.968 and 0.983 for neural network, PCR and PLS analysis, respectively. The root mean square errors of prediction were found to be 0.00026, 0.0043 and 0.0031 g cm-3 , respectively. It is found that near-infrared spectroscopy combined with neural network analysis is useful for the efficient and accurate determination of PE density.

Laser diode sensors for measuring mechanical properties of recycled plastics

“…However, the cost of a spectrometer can be too high and the scanned frequency band can be rather wide. According to the testing scope, plastic of the same type interacts with a specific wavelength, even though the plastics were recycled [8]. Thus, the scanned frequency band can be narrowed down to the corresponding band.…”

On‐line prediction of crystallinity spatial distribution across polymer films using NIR spectral imaging and chemometrics methods

“…They often rely on small sample size and require significant handling time. The most common off‐line method is differential scanning calorimetry (DSC), which relies on the heat associated with melting of small samples, typically less than 20 mg. DSC has been widely used in polymer analysis (Batur et al, 1999; Saeki et al, 2003; Sato et al, 2003; Albano et al, 2003; Watanabe et al, 2006; Pelsoci, 2007). Numerous microscopy methods also exist.…”

“…Nuclear magnetic resonance (NMR) spectroscopy has also been used to obtain physical, chemical and structural information about polymer phases (Bergmann, 1981; Pelsoci, 2007). Application of this method is typically expensive, time consuming and destructive (Vailaya et al, 2001; Saeki et al, 2003). X‐ray scattering methods are a family of non‐destructive methods based on the scattered intensity of a beam hitting a sample and providing information about the average structure and composition (Brown et al, 1973; Polizzi et al, 1991; Albano et al, 2003; Pantani et al, 2005; Pelsoci, 2007; Briskman, 2007).…”

Neural Network-Based Active Learning in Multivariate Calibration

“…For this, one often uses fixed experimental designs [14], where the entire set of training samples is determined in one step. Nonlinear calibration techniques, particularly using NN [3], [7]- [13], try to achieve a faster convergence to a particular accuracy level, basically replacing the linear methods.…”

“…The corresponding calibration model can be linear (e.g., linear regression from standard software like GRAMS/AI [4], Unscrambler [5]), HORIZON MB [6], etc., or nonlinear. In the nonlinear calibration category, neural networks (NNs) have been widely used, as reported in the works [7]- [9], also for particular spectroscopy applications, e.g., prediction of cleaning solution component concentrations [3], identification of amino acid [10], gasoline applications [11], [12], polyethylene density prediction [13], etc.…”