Filtern
Dokumenttyp
- Vortrag (3)
- Zeitschriftenartikel (2)
Sprache
- Englisch (5) (entfernen)
Schlagworte
Organisationseinheit der BAM
- 8.0 Abteilungsleitung und andere (5) (entfernen)
Eingeladener Vortrag
- nein (3)
Mass Spectrometry (MS) and Nuclear Magnetic Resonance Spectroscopy (NMR) are valuable analytical and quality control methods for most industrial chemical processes as they provide information on the concentrations of individual compounds and by-products. These processes are traditionally 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 realized 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-the-art analysis. These results suggest that, in the context of the digital transformation of the process industry, we are now on the threshold of a 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.
Chemical and pharmaceutical companies need to find new ways to survive successfully in a changing environment, while finding more flexible ways of product and process development to bring their products to market faster - especially high-value, high-end products such as fine chemicals or pharmaceuticals. This is complicated by changes in value chains along a potential circular economy.
One current approach is flexible and modular chemical production units that use multi-purpose equipment to produce various high-value products with short downtimes between campaigns and can shorten time-to-market for new products. Online NMR spectroscopy will play an important role for plant automation and quality control, as the method brings very high linearity, matrix independence and thus works almost calibration-free. Moreover, these properties ideally enable automated and machine-aided data analysis for the above-mentioned applications.
Using examples, this presentation will outline a possible more holistic approach to digitalization and the use of machine-based processes in the production of specialty chemicals and pharmaceuticals through the introduction of integrated and networked systems and processes.
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.
The CLEAN ENERGY Flagship is an initiative designed to utilize recent game changing developments in digital, materials and manufacturing technologies to catalyze a radical paradigm shift towards clean, reliable, efficient and cost-optimal energy.
Unifying and drastically accelerating radically new energy material design, processing and integration across the entire value chain addressing energy production, conversion, storage and systems.
CLEAN ENERGY participants are all distinguished research organisations that each benefit from their own industry networks and contacts with regions and state-level activities and have a long history of collaborating with each other (for 10 years now under the umbrella of EERA) within a European collaborative framework.
Through EERA, CLEAN ENERGY aims to become a crucial partner in the SET-Plan, supporting long-lasting approaches through its established networks and internal collaborations.
Chemical and pharmaceutical companies have to find new paths to survive successfully in a changing environment, while also finding more flexible ways of product and process development to bring their products to market more quickly – especially high-quality high-end products like fine chemicals or pharmaceuticals. A current approach uses flexible and modular chemical production units, which can produce different high-quality products using multi-purpose equipment with short downtimes between campaigns and reduce the time to market of new products.
NMR spectroscopy appeared as excellent online analytical tool and allowed a modular data analysis approach, which even served as reliable reference method for further Process Analytical Technology (PAT) applications. Using the available datasets, a second data analysis approach based on artificial neural networks (ANN) was evaluated. Therefore, amount of data was augmented to be sufficient for training. The results show comparable performance, while improving the calculation time tremendously. In future, such fully integrated and interconnecting “smart” systems and processes can increase the efficiency of the production of specialty chemicals and pharmaceuticals.