Data driven reaction mechanism estimation via transient kinetics and machine learning

Kunz, M. Ross; Yonge, Adam; Fang, Zongtang; Batchu, Rakesh; Medford, Andrew J.; Constales, Denis; Yablonsky, Gregory S.

doi:10.1016/j.cej.2021.129610

Cited by 18 publications

(6 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PDEs are often used to interpret the complex transport and reactions occurring during TAP experiments 6 . Knudsen diffusion is the dominant driving force of transport, while a series of gas–surface and surface–surface reactions can take place in the catalyst zone at the center of the reactor 24 . Details of the PDEs have been thoroughly outlined elsewhere 6 .…”

Section: Methodsmentioning

confidence: 99%

“…6 Knudsen diffusion is the dominant driving force of transport, while a series of gas-surface and surface-surface reactions can take place in the catalyst zone at the center of the reactor. 24 Details of the PDEs have been thoroughly outlined elsewhere. 6 TAPsolver, a Python package for the processing of TAP experimental data, is used to perform the analyses presented here.…”

Section: Problem Definition and Numerical Toolsmentioning

confidence: 99%

See 1 more Smart Citation

Quantifying the impact of temporal analysis of products reactor initial state uncertainties on kinetic parameters

et al. 2022

Self Cite

View full text Add to dashboard Cite

The temporal analysis of products (TAP) reactor provides a route to extract intrinsic kinetics from transient measurements. Current TAP uncertainty quantification only considers the experimental noise present in the outlet flow signal. Additional sources of uncertainty such as initial surface coverages, catalyst zone location, inert void fraction, gas pulse intensity, and pulse delay, are not included. For this reason, a framework for quantifying initial state uncertainties present in TAP experiments is presented and applied to a carbon monoxide oxidation case study. Two methods for quantifying these sources of uncertainty are introduced. The first utilizes initial state sensitivities to approximate the parameter variances and provide insights into the structural certainty of the model. The second generates parameter confidence distributions through an ensemble-based sampling algorithm. The initial state covariance matrix can ultimately be merged with the experimental noise covariance matrix, providing a unified description of the parameter uncertainties for a TAP experiment.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Problem Definition and Numerical Toolsmentioning

confidence: 99%

Quantifying the impact of temporal analysis of products reactor initial state uncertainties on kinetic parameters

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…(1) The data set from new experiments or a readily available experimental database: Among these researches, ANN is one of the most popular methods used for predicting activation energies and reaction rate constants. − Rizkin et al reported a novel NN-assisted methodology for exploring polymerization reactions based on an automated microreactor in conjunction with in situ infrared thermography. The developed methodology using efficient and high-speed experimentation could map the reaction space of a zirconocene polymerization catalyst to kinetic parameters.…”

Section: Current Status and Challengesmentioning

confidence: 99%

Review of Machine Learning for Hydrodynamics, Transport, and Reactions in Multiphase Flows and Reactors

Zhu

Chen

Ouyang

et al. 2022

Ind. Eng. Chem. Res.

120

View full text Add to dashboard Cite

Artificial intelligence (AI), machine learning (ML), and data science are leading to a promising transformative paradigm. ML, especially deep learning and physics-informed ML, is a valuable toolkit that complements incomplete domain-specific knowledge in conventional experimental and computational methods. ML can provide flexible techniques to facilitate the conceptual development of new robust predictive models for multiphase flows and reactors by finding hidden pattern/information/mechanism in a data set. Due to such emergence, we thereby comprehensively survey, explore, analyze, and discuss key advancements of recent ML applications to hydrodynamics, heat and mass transfer, and reactions in single-phase and multiphase flow systems from different aspects: (1) development of multiphase closure models of drag force, turbulence stresses and heat/mass transfer to improve the accuracy and efficiency of typical CFD simulations; (2) image reconstruction, regime identification, key parameter predictions, and optimization of multiphase flow and transport fields; (3) reaction kinetics modeling (e.g., predictions of reaction networks, kinetic parameters, and species production) and reaction condition optimization. These sections also discuss and analyze the key advantages and weakness of ML for solving the problems in the domain of multiphase flows and reactors. Finally, we summarize the under-solving challenges and opportunities in order to identify future directions that would be useful for the research community. Future development and study of multiphase flows and reactors are envisaged to be accelerated by ML and data science.

show abstract

“…Peter et al 20 used ML and quantum mechanical (QM) in a two‐way synergy and successfully applied this method in the prediction of a small set of organic radical reactions. Kunz et al 21 explained how materials control reaction mechanisms through the combination of transient kinetics with ML, and their methodology formed a new data‐driven approach for dealing with similar problems.…”

Section: Introductionmentioning

confidence: 99%

“…[15][16][17][18][19] Peter et al 20 used ML and quantum mechanical (QM) in a two-way synergy and successfully applied this method in the prediction of a small set of organic radical reactions. Kunz et al 21…”

mentioning

confidence: 99%

Identification of the reaction network for the synthesis of adipic acid using machine learning coupling with target factor analysis

et al. 2022

View full text Add to dashboard Cite

This study investigated the reaction network of the oxidation of cyclohexanone with nitric acid through machine learning (ML) model coupling with target factor analysis (TFA). Experiments for the synthesis of adipic acid (AA) were carefully designed and carried out in a microreactor system. An artificial neural network (ANN) model was applied and optimized by training on experimental data. To assess the established ANN model, a comparison between the predicted concentrations of the products and those calculated with the power law kinetic model was implemented. TFA was then performed on both the experimental data and the data simulated by ANN for identifying the candidate reactions and finding out the temperature boundaries. Based on the identification results of the reaction network, the kinetic characteristics of this oxidation process under various operational conditions were further researched through the incremental approach and simultaneous approach.

show abstract

Data driven reaction mechanism estimation via transient kinetics and machine learning

Cited by 18 publications

References 66 publications

Quantifying the impact of temporal analysis of products reactor initial state uncertainties on kinetic parameters

Quantifying the impact of temporal analysis of products reactor initial state uncertainties on kinetic parameters

Review of Machine Learning for Hydrodynamics, Transport, and Reactions in Multiphase Flows and Reactors

Identification of the reaction network for the synthesis of adipic acid using machine learning coupling with target factor analysis

Contact Info

Product

Resources

About