TY - JOUR A1 - Kern, Simon A1 - Liehr, Sascha A1 - Wander, Lukas A1 - Bornemann-Pfeiffer, Martin A1 - Müller, S. A1 - Maiwald, Michael A1 - Kowarik, Stefan T1 - Artificial neural networks for quantitative online NMR spectroscopy N2 - Industry 4.0 is all about interconnectivity, sensor-enhanced process control, and data-driven systems. Process analytical technology (PAT) such as online nuclear magnetic resonance (NMR) spectroscopy is gaining in importance, as it increasingly contributes to automation and digitalization in production. In many cases up to now, however, a classical evaluation of process data and their transformation into knowledge is not possible or not economical due to the insufficiently large datasets available. When developing an automated method applicable in process control, sometimes only the basic data of a limited number of batch tests from typical product and process development campaigns are available. However, these datasets are not large enough for training machine-supported procedures. In this work, to overcome this limitation, a new procedure was developed, which allows physically motivated multiplication of the available reference data in order to obtain a sufficiently large dataset for training machine learning algorithms. The underlying example chemical synthesis was measured and analyzed with both application-relevant low-field NMR and high-field NMR spectroscopy as reference method. Artificial neural networks (ANNs) have the potential to infer valuable process information already from relatively limited input data. However, in order to predict the concentration at complex conditions (many reactants and wide concentration ranges), larger ANNs and, therefore, a larger Training dataset are required. We demonstrate that a moderately complex problem with four reactants can be addressed using ANNs in combination with the presented PAT method (low-field NMR) and with the proposed approach to generate meaningful training data. KW - Online NMR spectroscopy KW - Real-time process monitoring KW - Artificial neural networks KW - Automation KW - Process industry PY - 2020 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:b43-507508 SN - 1618-2642 VL - 412 IS - 18 SP - 4447 EP - 4459 PB - Springer CY - Berlin AN - OPUS4-50750 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - GEN A1 - Kern, Simon A1 - Liehr, Sascha A1 - Wander, Lukas A1 - Bornemann-Pfeiffer, Martin A1 - Müller, S. A1 - Maiwald, Michael A1 - Kowarik, Stefan T1 - Training data of quantitative online NMR spectroscopy for artificial neural networks N2 - Data set of low-field NMR spectra of continuous synthesis of nitro-4’-methyldiphenylamine (MNDPA). 1H spectra (43 MHz) were recorded as single scans. Two different approaches for the generation of artificial neural networks training data for the prediction of reactant concentrations were used: (i) Training data based on combinations of measured pure component spectra and (ii) Training data based on a spectral model. Synthetic low-field NMR spectra First 4 columns in MAT-files represent component areas of each reactant within the synthetic mixture spectrum. Xi (“pure component spectra dataset”) Xii (“spectral model dataset”) Experimental low-field NMR spectra from MNDPA-Synthesis This data set represents low-field NMR-spectra recorded during continuous synthesis of nitro-4’-methyldiphenylamine (MNDPA). Reference values from high-field NMR results are included. KW - NMR spectroscopy KW - Real-time process monitoring KW - Artificial neural networks KW - Online NMR spectroscopy KW - Automation KW - Process industry PY - 2020 U6 - https://doi.org/10.5281/zenodo.3677139 PB - Zenodo CY - Geneva AN - OPUS4-50456 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -