Ingenieurwissenschaften und zugeordnete Tätigkeiten
Filtern
Dokumenttyp
- Vortrag (2)
- Forschungsdatensatz (2)
- Zeitschriftenartikel (1)
Schlagworte
- Artificial neural networks (5) (entfernen)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (2)
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.
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.
An experimental setup to integrate laser sensor into conventional GMAW setups via a unified control architecture is described. The setup is used to automate and monitor narrow-gap GMAW and control the electrode weaving motion as well as the resulting height of each weld layer. A way to develop GMAW arc-sensors using artificial neural networks using the setup is shown.
The control system is connected to a relational database to store various process measurements. The database can be accessed to filter previous weldments by numerous criteria which allows modelling of process parameter correlation among vast datasets. Such models can be used for process monitoring and control in future applications.
Es wird ein Versuchsstand zum automatisierten MSG-Engspaltschweißen mit integrierter Lasersensorik zur Prozessteuerung und -überwachung vorgestellt. Die Funktion einer Lichtbogensensorik zur automatischen Steuerung der mechanischen Elektrodenauslenkung wird erläutert und verschiedene Anwendungsfälle an Beispielen demonstriert. Die zusätzliche Füllgradregelung beim Mehrlagenschweißen mit veränderlichem Nahtquerschnitt auf Basis der optischen Messtechnik wird zudem vorgestellt.