Artificial neural networks and data fusion enable concentration predictions for inline process analytics

Sagmeister, Peter; Hierzegger, Robin; Williams, Jason D.; Kappe, C. Oliver; Kowarik, Stefan

doi:10.1039/d2dd00006g

Cited by 7 publications

(6 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANN modeling was performed as a processing approach for inline FTIR spectra data according to the reported literature (Figure S2a). [34] Several groups of MNA and AMA in methanol solution with different concentrations were prepared and their inline FTIR spectra data were collected as training set and validation set. Here the verification set is equivalent to the test set (Table S1).…”

Section: Concentration Determinationmentioning

confidence: 99%

See 1 more Smart Citation

Optimization of heterogeneous continuous flow hydrogenation using FTIR inline analysis: a comparative study of multi-objective Bayesian optimization and kinetic modeling

Chai,

Xia,

Shen

et al. 2024

Preprint

View full text Add to dashboard Cite

The heterogeneous continuous flow hydrogenation is pivotal in chemical research and production, yet its reaction optimization has historically been intricate and labor-intensive. This study introduces a heterogeneous continuous flow hydrogenation system specifically designed for the preparation of 2-amino-3-methylbenzoic acid (AMA), employing FTIR inline analysis coupled with an artificial neural network model for monitoring. We explored two distinct reaction optimization strategies: multi-objective Bayesian optimization (MOBO) and intrinsic kinetic modeling, executed in parallel to optimize the reaction conditions. Remarkably, the MOBO approach achieved an optimal AMA yield of 99% and a productivity of 0.64 g/hour within a limited number of iterations. Conversely, despite requiring extensive experimental data collection and equation fitting, the intrinsic kinetic modeling approach yielded a similar optimal AMA yield but a higher productivity of 1.13 g/hour, attributed to increased catalyst usage. Our findings indicate that while MOBO offers a more efficient route with fewer required experiments, kinetic modeling provides deeper insights into the reaction optimization landscape but is limited by its assumptions.

show abstract

Section: Concentration Determinationmentioning

confidence: 99%

“…[33] Furthermore, they have successfully applied artificial neural networks (ANN) for processing NMR and UV/vis spectra of multiple components. [34] Besides enhancing Bayesian optimization, inline analysis is also anticipated to improve the efficiency of traditional optimization techniques, such as kinetic modeling.…”

Section: Introductionmentioning

confidence: 99%

Optimization of heterogeneous continuous flow hydrogenation using FTIR inline analysis: a comparative study of multi-objective Bayesian optimization and kinetic modeling

Chai,

Xia,

Shen

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Furthermore, Kappe's group demonstrated how to use artificial neural networks (ANN) to complete advanced data processing of NMR and UV/Vis spectra to accurately predict the concentration of intermediates in the production of mesalazine. 19 The creation and utilization of simulated training spectra speed up the training process of ANN and compensate for the lack of experimental data. This strategy encourages more use of low-cost and easy-to-get PAT instruments for multistep reaction monitoring.…”

Section: Process Analytical Technologymentioning

confidence: 99%

A Review of the Applications of Artificial Intelligence in the Process Analysis and Optimization of Chemical Products

Shen,

2023

Pharmaceutical Fronts

View full text Add to dashboard Cite

Continuous flow chemistry is an enabling technology for automated synthesis. Artificial intelligence (AI) is a powerful tool in various areas of automated synthesis in flow chemistry, including process analysis technology and synthesis reaction optimization. The merger of continuous flow chemistry and AI drives chemical production in a more intelligent, automated, and flexible direction. This review discusses the recent application of AI in analyzing and optimizing chemical products produced by continuous flow chemistry with the most innovative equipment and techniques.

show abstract

“…As reliability increases, this information is employed more for closed-loop control rather than the historical open-loop approach, where researchers can view the analysis results to determine if the process control needs to be changed or the data need to be archived for future reference. 13…”

Section: Introductionmentioning

confidence: 99%

A Review of Inline Infrared and Nuclear Magnetic Resonance Applications in Flow Chemistry

Zhang,

2023

Pharmaceutical Fronts

View full text Add to dashboard Cite

As a safe and efficient synthesis technique, flow chemistry has recently gained attention in the pharmaceutical, materials, and environmental protection industries. However, researchers always face challenges in handling samples and selecting sufficiently flexible analytical techniques. Generally, real-time process analysis is crucial for monitoring reactions. The combination of flow chemistry with real-time process analysis can be beneficial for studying reaction kinetics and thermodynamics, monitoring, and control of the chemical synthesis processes, reaction optimization of macro and microreactors, and qualitative and quantitative analyses of compounds. Thus far, studies investigating the combination of flow chemistry with inline monitoring have included ultraviolet–infrared spectroscopy, Raman spectroscopy, gas chromatography, mass spectrometry, liquid chromatography, nuclear magnetic resonance (NMR) spectroscopy, and other automated conventional or unconventional methods. This review sheds light on applying inline infrared and inline NMR spectroscopies in flow chemistry.

show abstract

Artificial neural networks and data fusion enable concentration predictions for inline process analytics

Abstract: Real-time process analytics enable an insight into chemical processes and are essential to implement process optimization and control algorithms. However, the quantification of reaction species in complex mixtures can be...

Cited by 7 publications

References 68 publications

Optimization of heterogeneous continuous flow hydrogenation using FTIR inline analysis: a comparative study of multi-objective Bayesian optimization and kinetic modeling

Optimization of heterogeneous continuous flow hydrogenation using FTIR inline analysis: a comparative study of multi-objective Bayesian optimization and kinetic modeling

A Review of the Applications of Artificial Intelligence in the Process Analysis and Optimization of Chemical Products

A Review of Inline Infrared and Nuclear Magnetic Resonance Applications in Flow Chemistry

Contact Info

Product

Resources

About