<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>50750</id>
    <completedYear/>
    <publishedYear>2020</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>4447</pageFirst>
    <pageLast>4459</pageLast>
    <pageNumber/>
    <edition/>
    <issue>18</issue>
    <volume>412</volume>
    <type>article</type>
    <publisherName>Springer</publisherName>
    <publisherPlace>Berlin</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Artificial neural networks for quantitative online NMR spectroscopy</title>
    <abstract language="eng">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.</abstract>
    <parentTitle language="eng">Analytical and bioanalytical chemistry</parentTitle>
    <identifier type="doi">10.1007/s00216-020-02687-5</identifier>
    <identifier type="issn">1618-2642</identifier>
    <identifier type="urn">urn:nbn:de:kobv:b43-507508</identifier>
    <enrichment key="date_peer_review">18.05.2020</enrichment>
    <enrichment key="RelatedIdentifier">https://opus4.kobv.de/opus4-bam/frontdoor/index/index/docId/50456</enrichment>
    <enrichment key="RelatedIdentifier">https://opus4.kobv.de/opus4-bam/frontdoor/index/index/docId/54481</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <author>Simon Kern</author>
    <author>Sascha Liehr</author>
    <author>Lukas Wander</author>
    <author>Martin Bornemann-Pfeiffer</author>
    <author>S. Müller</author>
    <author>Michael Maiwald</author>
    <author>Stefan Kowarik</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Online NMR spectroscopy</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Real-time process monitoring</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Artificial neural networks</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Automation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Process industry</value>
    </subject>
    <collection role="ddc" number="543">Analytische Chemie</collection>
    <collection role="ddc" number="620">Ingenieurwissenschaften und zugeordnete Tätigkeiten</collection>
    <collection role="institutes" number="">1 Analytische Chemie; Referenzmaterialien</collection>
    <collection role="institutes" number="">1.4 Non-Target-Analytik</collection>
    <collection role="institutes" number="">8 Zerstörungsfreie Prüfung</collection>
    <collection role="institutes" number="">8.6 Faseroptische Sensorik</collection>
    <collection role="themenfelder" number="">Umwelt</collection>
    <collection role="themenfelder" number="">Material</collection>
    <collection role="themenfelder" number="">Chemie und Prozesstechnik</collection>
    <collection role="themenfelder" number="">Chemische Charakterisierung und Spurenanalytik</collection>
    <collection role="literaturgattung" number="">Verlagsliteratur</collection>
    <collection role="fulltextaccess" number="">Datei für die Öffentlichkeit verfügbar ("Open Access")</collection>
    <collection role="unnumberedseries" number="">Wissenschaftliche Artikel der BAM</collection>
    <collection role="institutes" number="">8.0 Abteilungsleitung und andere</collection>
    <collection role="themenfelder" number="">Sensorik</collection>
    <thesisPublisher>Bundesanstalt für Materialforschung und -prüfung (BAM)</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-bam/files/50750/AnalBioanalChem_412_2020.pdf</file>
    <file>https://opus4.kobv.de/opus4-bam/files/50750/216_2020_2687_MOESM1_ESM.pdf</file>
  </doc>
  <doc>
    <id>50456</id>
    <completedYear/>
    <publishedYear>2020</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>researchdata</type>
    <publisherName>Zenodo</publisherName>
    <publisherPlace>Geneva</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Training data of quantitative online NMR spectroscopy for artificial neural networks</title>
    <abstract language="eng">Data set of low-field NMR spectra of continuous synthesis of nitro-4’-methyldiphenylamine (MNDPA). 1H spectra (43 MHz) were recorded as single scans.&#13;
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.&#13;
&#13;
Synthetic low-field NMR spectra&#13;
First 4 columns in MAT-files represent component areas of each reactant within the synthetic mixture spectrum.&#13;
Xi (“pure component spectra dataset”)&#13;
Xii (“spectral model dataset”)&#13;
&#13;
Experimental low-field NMR spectra from MNDPA-Synthesis&#13;
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.</abstract>
    <identifier type="doi">10.5281/zenodo.3677139</identifier>
    <enrichment key="ScientificResourceTypeGeneral">Datensatz</enrichment>
    <enrichment key="RelatedIdentifier">http://nbn-resolving.org/urn:nbn:de:kobv:b43-507508</enrichment>
    <enrichment key="RelatedIdentifier">https://opus4.kobv.de/opus4-bam/frontdoor/index/index/docId/54481</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <author>Simon Kern</author>
    <author>Sascha Liehr</author>
    <author>Lukas Wander</author>
    <author>Martin Bornemann-Pfeiffer</author>
    <author>S. Müller</author>
    <author>Michael Maiwald</author>
    <author>Stefan Kowarik</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>NMR spectroscopy</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Real-time process monitoring</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Artificial neural networks</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Online NMR spectroscopy</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Automation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Process industry</value>
    </subject>
    <collection role="ddc" number="543">Analytische Chemie</collection>
    <collection role="ddc" number="620">Ingenieurwissenschaften und zugeordnete Tätigkeiten</collection>
    <collection role="institutes" number="">1 Analytische Chemie; Referenzmaterialien</collection>
    <collection role="institutes" number="">1.4 Non-Target-Analytik</collection>
    <collection role="institutes" number="">8 Zerstörungsfreie Prüfung</collection>
    <collection role="institutes" number="">8.6 Faseroptische Sensorik</collection>
    <collection role="themenfelder" number="">Umwelt</collection>
    <collection role="themenfelder" number="">Material</collection>
    <collection role="themenfelder" number="">Chemie und Prozesstechnik</collection>
    <collection role="themenfelder" number="">Chemische Charakterisierung und Spurenanalytik</collection>
    <collection role="fulltextaccess" number="">Datei für die Öffentlichkeit verfügbar ("Open Access")</collection>
    <collection role="literaturgattung" number="">Graue Literatur</collection>
    <collection role="unnumberedseries" number="">Forschungsdatensätze der BAM</collection>
    <collection role="themenfelder" number="">Sensorik</collection>
    <thesisPublisher>Bundesanstalt für Materialforschung und -prüfung (BAM)</thesisPublisher>
  </doc>
</export-example>
