Spectral measurement techniques, such as the near-infrared (NIR) and Raman spectroscopy, have been intensively researched. Nevertheless, even today, these techniques are still sparsely applied in industry due to their unpredictable and unstable measurements. This paper put forward two data fusion strategies (low-level and mid-level fusion) for combining the NIR and Raman spectra to generate fusion spectra or fusion characteristics in order to improve the in-line measurement precision of component content of molten polymer blends. Subsequently, the fusion value was applied to modeling. For evaluating the response of different models to data fusion strategy, partial least squares (PLS) regression, artificial neural network (ANN), and extreme learning machine (ELM) were applied to the modeling of four kinds of spectral data (NIR, Raman, low-level fused data, and mid-level fused data). A system simultaneously acquiring in-line NIR and Raman spectra was built, and the polypropylene/polystyrene (PP/PS) blends, which had different grades and covered different compounding percentages of PP, were prepared for use as a case study. The results show that data fusion strategies improve the ANN and ELM model. In particular, mid-level fusion enables the in-line measurement of component content of molten polymer blends to become more accurate and robust.
At present, there is a widespread phenomenon that product quality is difficult to monitor during the process of polymer melt modification such as blending, filling, and reinforcement. In consideration of this problem, this paper proposes an in-line Raman spectroscopy technique for measuring dispersion uniformity of polystyrene (PS) in polypropylene (PP)/PS blends during melt extrusion. On the basis of the optimal partial least squares (PLS) calibration model for quantitative determination of PS content in PP/PS, the fluctuations of PS content in extruding PP/PS with a mass percentage of 70 : 30 at different screw rotation speeds were predicted. The coefficient of variation (CV) of PS content at each screw rotation speed was obtained to accurately compare the dispersion uniformity, which was in agreement with the PS dispersion result characterized by the scanning electron microscope (SEM). In addition, the sensitivity of the measurement was validated by calculating the CV of PP/PS with mass percentages of 69 : 31 and 71 : 29. All of the above demonstrated that the in-line measurement system of Raman spectroscopy was able to accurately measure the dispersion uniformity of PS during the blending extrusion of PP/PS and demonstrated good sensitivity to minor changes in the blends composition.
Particle filling is a typical method for reinforcing polymer matrix materials, and the properties of particle filler have a significant impact on the performance of polymeric materials. However, there is still a lack of effective in situ measurement and characterization methods of particulate-filled polymer. In this paper, an in-line measurement and characterization method for glass bead-filled polypropylene (GB/PP) based on machine vision was proposed. A visual die was developed, and the polymer melt in the visual area was photographed by a high-speed camera to obtain images for analysis. An improved YOLO target detection algorithm was applied to identify particles in images. The particle size distribution, dispersion, and component content of glass beads in the polypropylene were measured and characterized through statistical analysis, and then verified by other off-line methods. These properties calculated by our method agree well with those measured by other off-line methods. This method can achieve the in-line measurement and characterization for GB/PP extrusion, which is promising for the in-line property monitoring of particulate-filled polymers in the industry.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.