AUTHOR=Strani Lorenzo , Mantovani Erik , Bonacini Francesco , Marini Federico , Cocchi Marina TITLE=Fusing NIR and Process Sensors Data for Polymer Production Monitoring JOURNAL=Frontiers in Chemistry VOLUME=Volume 9 - 2021 YEAR=2021 URL=https://www.frontiersin.org/journals/chemistry/articles/10.3389/fchem.2021.748723 DOI=10.3389/fchem.2021.748723 ISSN=2296-2646 ABSTRACT=Process Analytical Technology and Multivariate Process Monitoring are nowadays the most effective approaches to achieve real time quality monitoring/control in production. However, their use it is not yet common practice and industries benefit much less than they could from the outcome of the hundreds of sensors that constantly monitor production in industrial plants. The huge amount of sensor data collected is still mostly used to produce univariate control charts, monitoring one compartment at time and product quality variables are generally used to monitor production, despite their low frequency (off-line measurements at analytical laboratory) is not suitable for real time monitoring. On the contrary, it would be extremely advantageous to benefit from predictive models that, based on on-line sensors, will be able to return quality parameters in real time. As a matter of fact, the plant set up influence product quality, and process sensors (flow meters, thermocouples, etc.) implicitly register process variability, correlation trends, drift, etc. When available spectroscopic sensors, reflecting chemical composition and structure, consent to monitor the intermediate products. Coupling process and spectroscopic sensor and extracting/fusing information by multivariate analysis from this data would enhance evaluation of the produced material features allowing production quality to be estimated at a very early stage. The present work, at a pilot plant scale, applied Multivariate Statistical Process Control (MSPC) charts, obtained by data fusion of process sensors data and Near Infrared (NIR) probes, on a continuous styrene-acrylonitrile (SAN) production process. Furthermore, PLS regression was used for the real time prediction of Melt Flow Index (MFI) and percentage of bounded acrylonitrile (%AN). The results, show that the MSPC model was able to detect deviations from normal operative conditions, indicating the variables responsible for the deviation, be they spectral or process. Moreover, predictive regression models obtained using the fused data showed better results than models computed using single datasets in terms of both error of prediction and R2. Thus, the fusion of spectra and process data improved the real time monitoring allowing an easier visualization of the process ongoing, a faster understanding of possible faults and real time assessment of the final product quality.