Filtern
Dokumenttyp
- Beitrag zu einem Tagungsband (4) (entfernen)
Schlagworte
- CONSENS (2)
- Prozessanalytik (2)
- Artificial Neural Networks (1)
- Betriebspunktoptimierung (1)
- Cyber-Physical Systems (1)
- Datenanalyse (1)
- Datenkonzepte (1)
- Echtzeitoptimierungsverfahren (1)
- First Principles (1)
- Indirect Hard Modelling (1)
Organisationseinheit der BAM
- 1.4 Prozessanalytik (4) (entfernen)
Produzieren Sie schon oder kalibrieren Sie noch? – Online-NMR-Spektrometer als Smarte Feldgeräte
(2018)
Der Vortrag zeigt allgemeine Anforderungen an "smarte Feldgeräte" und deren Entwicklung in den vergangenen Jahren. Am Beispiel eines smarten Online-NMR-Sensors, der in einem EU-Projekt von der BAM entwickelt wurde, wird die Umsetzung der Anforderung aufgezeigt. Schließlich werden weitere Technologieanforderungen und Lösungsansätze vorgestellt.
Im Zuge der Digitalisierung der Prozessindustrie werden zunehmend modellbasiere Echtzeitoptimierungsverfahren eingesetzt, sog. „Advanced Process Control“. Mithilfe der sogenannten Modifier-Adaptation ist eine iterative Betriebspunktoptimierung auch mit ungenauen Modellen möglich, sofern zuverlässige Prozessdaten zur Verfügung stehen. Am Beispiel eines smarten Online-NMR-Sensors, der in einem EU-Projekt von der BAM entwickelt wurde, konnte das Konzept in einer modularen Produktionsanlage zur Herstellung eines pharmazeutischen Wirkstoffs erfolgreich getestet werden.
Monitoring chemical reactions is the key to chemical process control. Today, mainly optical online methods are applied, which require excessive calibration effort. NMR spectroscopy has a high potential for direct loop process control while exhibiting short set-up times. Compact NMR instruments make NMR spectroscopy accessible in industrial and harsh environ¬ments for advanced process monitoring and control, as demonstrated within the European Union’s Horizon 2020 project CONSENS.
We present a range of approaches for the automated spectra analysis moving from conventional multivariate statistical approach, (i.e., Partial Least Squares Regression) to physically motivated spectral models (i.e., Indirect Hard Modelling and Quantum Mechanical calculations). By using the benefits of traditional qNMR experiments data analysis models can meet the demands of the PAT community (Process Analytical Technology) regarding low calibration effort/calibration free methods, fast adaptions for new reactants or derivatives and robust automation schemes.
Mass Spectrometry (MS) and Nuclear Magnetic Resonance Spectroscopy (NMR) are critical components of every industrial chemical process as they provide information on the concentrations of individual compounds and by-products. These processes are carried out manually and by a specialist, which takes a substantial amount of time and prevents their utilization for real-time closed-loop process control. This paper presents recent advances from two projects that use Artificial Neural Networks (ANNs) to address the challenges of automation and performance-efficient realizations of MS and NMR. In the first part, a complete toolchain has been developed to develop simulated spectra and train ANNs to identify compounds in MS. In the second part, a limited number of experimental NMR spectra have been augmented by simulated spectra to train an ANN with better prediction performance and speed than state-of-theart analysis. These results suggest that, in the context of the digital transformation of the process industry, we are now on the threshold of a possible strongly simplified use of MS and MRS and the accompanying data evaluation by machine-supported procedures, and can utilize both methods much wider for reaction and process monitoring or quality control.