Dokument-ID Dokumenttyp Autoren/innen Persönliche Herausgeber/innen Haupttitel Abstract Auflage Verlagsort Verlag Herausgeber (Institution) Erscheinungsjahr Titel des übergeordneten Werkes Jahrgang/Band ISBN Veranstaltung Veranstaltungsort Beginndatum der Veranstaltung Enddatum der Veranstaltung Ausgabe/Heft Erste Seite Letzte Seite URN DOI Lizenz Datum der Freischaltung OPUS4-53941 Zeitschriftenartikel Fricke, F.; Brandalero, M.; Liehr, Sascha; Kern, Simon; Meyer, Klas; Kowarik, Stefan; Hierzegger, R.; Westerdick, S.; Maiwald, Michael; Hübner, M. Artificial Intelligence for Mass Spectrometry and Nuclear Magnetic Resonance Spectroscopy Using a Novel Data Augmentation Method 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. IEEE 2021 Transactions on Emerging Topics in Computing 10 1 87 98 urn:nbn:de:kobv:b43-539412 10.1109/TETC.2021.3131371 https://creativecommons.org/licenses/by/4.0/deed.de 2021-12-08 OPUS4-55360 Zeitschriftenartikel Fricke, F.; Mahmood, S.; Hoffmann, J.; Brandalero, M.; Liehr, Sascha; Kern, Simon; Meyer, Klas; Kowarik, S.; Westerdick, S.; Maiwald, Michael; Hübner, M. Artificial Intelligence for Mass Spectrometry and Nuclear Magnetic Resonance Spectroscopy 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. IEEE 2021 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE) 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE) Grenoble, France 01.02.2021 05.02.2021 615 620 10.23919/DATE51398.2021.9473958 2022-07-25 OPUS4-37356 Zeitschriftenartikel Meyer, Klas; Kern, Simon; Zientek, Nicolai; Guthausen, G.; Maiwald, Michael Process control with compact NMR Compact nuclear magnetic resonance (NMR) instruments make NMR spectroscopy and relaxometry accessible in industrial and harsh environments for reaction and process control. An increasing number of applications are reported. To build an interdisciplinary bridge between "process control" and "compact NMR",we give a short overviewon current developments in the field of process Engineering such as modern process design, integrated processes, intensified processes along with requirements to process control, model based control, or soft sensing. Finally, robust field integration of NMR systems into processes environments, facing explosion protection or Integration into process control systems, are briefly discussed. Elsevier 2016 Trends in Analytical Chemistry 83 Part A / SI 39 52 urn:nbn:de:kobv:b43-373562 10.1016/j.trac.2016.03.016 https://creativecommons.org/licenses/by-nc-nd/4.0/deed.de 2016-09-15 OPUS4-36333 Zeitschriftenartikel Zientek, Nicolai; Meyer, Klas; Kern, Simon; Maiwald, Michael Quantitative online NMR spectroscopy in a nutshell Online NMR spectroscopy is an excellent tool to study complex reacting multicomponent mixtures and gain process insight and understanding. For online studies under process conditions, flow NMR probes can be used in a wide range of temperature and pressure. This paper compiles the most important aspects towards quantitative process NMR spectroscopy in complex multicomponent mixtures and provides examples. After NMR spectroscopy is introduced as an online method and for technical samples without sample preparation in deuterated solvents, influences of the residence time distribution, pre-magnetization, and cell design are discussed. NMR acquisition and processing parameters as well as data preparation methods are presented and the most practical data analysis strategies are introduced. Weinheim, Germany Wiley-VCH Verlag GmbH & Co. KGaA 2016 Chemie Ingenieur Technik 88 6 698 709 10.1002/cite.201500120 2016-06-02 OPUS4-44847 Zeitschriftenartikel Kern, Simon; Meyer, Klas; Guhl, Svetlana; Gräßer, Patrick; Paul, Andrea; King, R.; Maiwald, Michael Online low-field NMR spectroscopy for process control of an industrial lithiation reaction—automated data analysis Monitoring specific chemical properties is the key to chemical process control. Today, mainly optical online methods are applied, which require time- and cost-intensive calibration effort. NMR spectroscopy, with its advantage being a direct comparison method without need for calibration, has a high potential for closed-loop process control while exhibiting short set-up times. Compact NMR instruments make NMR spectroscopy accessible in industrial and rough environments for process monitoring and advanced process control strategies. We present a fully automated data analysis approach which is completely based on physically motivated spectral models as first principles information (Indirect Hard Modelling - IHM) and applied it to a given pharmaceutical lithiation reaction in the framework of the European Union's Horizon 2020 project CONSENS. Online low-field NMR (LF NMR) data was analysed by IHM with low calibration effort, compared to a multivariate PLS-R (Partial Least Squares Regression) approach, and both validated using online high-field NMR (HF NMR) spectroscopy. Berlin, Heidelberg Springer 2018 Analytical and Bioanalytical Chemistry 410 14 3349 3360 10.1007/s00216-018-1020-z 2018-05-07 OPUS4-48062 Zeitschriftenartikel Kern, Simon; Wander, Lukas; Meyer, Klas; Guhl, Svetlana; Gottu Mukkula, A. R.; Holtkamp, M.; Salge, M.; Fleischer, C.; Weber, N.; Engell, S.; Paul, Andrea; Pereira Remelhe, M.; Maiwald, Michael Flexible automation with compact NMR spectroscopy for continuous production of pharmaceuticals Modular plants using intensified continuous processes represent an appealing concept for the production of pharmaceuticals. It can improve quality, safety, sustainability, and profitability compared to batch processes; besides, it enables plug-and-produce reconfiguration for fast product changes. To facilitate this flexibility by real-time quality control, we developed a solution that can be adapted quickly to new processes and is based on a compact nuclear magnetic resonance (NMR) spectrometer. The NMR sensor is a benchtop device enhanced to the requirements of automated chemical production including robust evaluation of sensor data. Beyond monitoring the product quality, online NMR data was used in a new iterative optimization approach to maximize the plant profit and served as a reliable reference for the calibration of a near-infrared (NIR) spectrometer. The overall approach was demonstrated on a commercial-scale pilot plant using a metal-organic reaction with pharmaceutical relevance. Heidelberg Springer Nature 2019 Analytical and Bioanalytical Chemistry 411 14 3037 3046 urn:nbn:de:kobv:b43-480623 10.1007/s00216-019-01752-y https://creativecommons.org/licenses/by/4.0/deed.de 2019-05-27 OPUS4-49041 Zeitschriftenartikel Bornemann-Pfeiffer, Martin; Kern, Simon; Jurtz, N.; Thiede, Tobias; Kraume, M.; Maiwald, Michael Design and validation of an additively manufactured flowCell-static mixer combination for inline NMR spectroscopy There have been an increasing number of publications on flow chemistry applications of compact NMR. Despite this, there is so far no comprehensive workflow for the technical design of flow cells. Here, we present an approach that is suitable for the design of an NMR flow cell with an integrated static mixing unit. This design moves the mixing of reactants to the active NMR detection region within the NMR instrument, presenting a feature that analyses chemical reactions faster (5-120 s region) than other common setups. During the design phase, the targeted mixing homogeneity of the components was evaluated for different types of mixing units based on CFD simulation. Subsequently, the flow cell was additively manufactured from ceramic material and metal tubing. Within the targeted working mass flow range, excellent mixing properties as well as narrow line widths were confirmed in validation experiments, comparable to common glass tubes. Washington American Chemical Society 2019 Industrial & Engineering Chemistry Research 58 42 19562 19570 10.1021/acs.iecr.9b03746 2019-09-23 OPUS4-50750 Zeitschriftenartikel Kern, Simon; Liehr, Sascha; Wander, Lukas; Bornemann-Pfeiffer, Martin; Müller, S.; Maiwald, Michael; Kowarik, Stefan Artificial neural networks for quantitative online NMR spectroscopy 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. Berlin Springer 2020 Analytical and bioanalytical chemistry 412 18 4447 4459 urn:nbn:de:kobv:b43-507508 10.1007/s00216-020-02687-5 https://creativecommons.org/licenses/by/4.0/deed.de 2020-05-11 OPUS4-51726 Zeitschriftenartikel Bornemann-Pfeiffer, Martin; Kern, Simon; Maiwald, Michael; Meyer, Klas Calibration-Free Chemical Process and Quality Control Units as Enablers for Modular Production Modular chemical production is a tangible translation of the digital transformation of the process industry for specialty chemicals. In particular, it enables the speeding-up of process development and thus a quicker time to market by flexibly connecting and orchestrating standardised physical modules and bringing them to life (i.e., parameterising them) with digitally accumulated process knowledge. We focus on the specific challenges of chemical process and quality control, which in its current form is not well suited for modular production and provide possible approaches and examples of the change towards direct analytical methods, analytical model transfer or machine-supported processes. Weinheim Wiley-VCH 2021 Chemie Ingenieur Technik 93 1-2 62 70 urn:nbn:de:kobv:b43-517264 10.1002/cite.202000150 https://creativecommons.org/licenses/by/4.0/deed.de 2020-12-03 OPUS4-52453 Zeitschriftenartikel Gottu Mukkula, A. R.; Kern, Simon; Salge, M.; Holtkamp, M.; Guhl, Svetlana; Fleischer, C.; Meyer, Klas; Remelhe, M.; Maiwald, Michael; Engell, S. An Application of Modifier Adaptation with Quadratic Approximation on a Pilot Scale Plant in Industrial Environment The goal of this work is to identify the optimal operating input for a lithiation reaction that is performed in a highly innovative pilot scale continuous flow chemical plant in an industrial environment, taking into account the process and safety constraints. The main challenge is to identify the optimum operation in the absence of information about the reaction mechanism and the reaction kinetics. We employ an iterative real-time optimization scheme called modifier adaptation with quadratic approximation (MAWQA) to identify the plant optimum in the presence of plant-model mismatch and measurement noise. A novel NMR PAT-sensor is used to measure the concentration of the reactants and of the product at the reactor outlet. The experiment results demonstrate the capabilities of the iterative optimization using the MAWQA algorithm in driving a complex real plant to an economically optimal operating point in the presence of plant-model mismatch and of process and measurement uncertainties. Amsterdam Elsevier 2020 IFAC-PapersOnLine 53 2 11773 11779 urn:nbn:de:kobv:b43-524531 10.1016/j.ifacol.2020.12.685 https://creativecommons.org/licenses/by-nc-nd/4.0/deed.de 2021-04-19 OPUS4-39323 Zeitschriftenartikel Michalik-Onichimowska, Aleksandra; Kern, Simon; Riedel, Jens; Panne, Ulrich; King, R.; Maiwald, Michael ''Click" analytics for ''click" chemistry - A simple method for calibration-free evaluation of online NMR spectra Driven mostly by the search for chemical syntheses under biocompatible conditions, so called "click" chemistry rapidly became a growing field of research. The resulting simple one-pot reactions are so far only scarcely accompanied by an adequate optimization via comparably straightforward and robust analysis techniques possessing short set-up times. Here, we report on a fast and reliable calibration-free online NMR monitoring approach for technical mixtures. It combines a versatile fluidic system, continuous-flow measurement of 1H spectra with a time interval of 20 s per spectrum, and a robust, fully automated algorithm to interpret the obtained data. As a proof-of-concept, the thiol-ene coupling between N-boc cysteine methyl ester and allyl alcohol was conducted in a variety of non-deuterated solvents while its time-resolved behaviour was characterized with step tracer experiments. Overlapping signals in online spectra during thiol-ene coupling could be deconvoluted with a spectral model using indirect hard modeling and were subsequently converted to either molar ratios (using a calibrationfree approach) or absolute concentrations (using 1-point calibration). For various solvents the kinetic constant k for pseudo-first order reaction was estimated to be 3.9 h-1 at 25 °C. The obtained results were compared with direct integration of non-overlapping signals and showed good agreement with the implemented mass balance. Oxford Elsevier Inc. 2017 Journal of Magnetic Resonance 277 154 161 urn:nbn:de:kobv:b43-393232 10.1016/j.jmr.2017.02.018 https://creativecommons.org/licenses/by-nc-nd/4.0/deed.de 2017-03-13