Multi-objective Bayesian optimization of chemical reactor design using computational fluid dynamics

Park, Seongeon; Na, Jonggeol; Kim, Minjun; Lee, Jong Min

doi:10.1016/j.compchemeng.2018.08.005

Cited by 73 publications

(38 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the global and local models are made use of for approximating the objective function and estimating the uncertainty of the approximated fitness, based on which an infill criterion is designed for surrogate management in the federated optimization environment. Federated data-driven optimization has a wide range real-world applications, in such as the design of chemical reactors [36] and the optimization of engineering operation [39], where the entire system contains a large number of sub-systems and the collected data on each sub-system are not allowed to be sent to a central storage. By extending FDD-EA, this work proposes a federated data-driven evolutionary algorithm for multi-objective optimization.…”

Section: Introductionmentioning

confidence: 99%

A federated data-driven evolutionary algorithm for expensive multi-/many-objective optimization

Jin

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Data-driven optimization has found many successful applications in the real world and received increased attention in the field of evolutionary optimization. Most existing algorithms assume that the data used for optimization are always available on a central server for construction of surrogates. This assumption, however, may fail to hold when the data must be collected in a distributed way and are subject to privacy restrictions. This paper aims to propose a federated data-driven evolutionary multi-/many-objective optimization algorithm. To this end, we leverage federated learning for surrogate construction so that multiple clients collaboratively train a radial-basis-function-network as the global surrogate. Then a new federated acquisition function is proposed for the central server to approximate the objective values using the global surrogate and estimate the uncertainty level of the approximated objective values based on the local models. The performance of the proposed algorithm is verified on a series of multi-/many-objective benchmark problems by comparing it with two state-of-the-art surrogate-assisted multi-objective evolutionary algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

A federated data-driven evolutionary algorithm for expensive multi-/many-objective optimization

Jin

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…The optimization of a tube bundle design has not been exploited yet, except for tube arrangements in heat exchangers at low temperatures, e.g., Daróczy et al (2014). Considering multiple objectives, simulation-based optimization can yield a range of optimal solutions as for example Park et al (2018) showed for a stirred tank reactor.…”

Section: Introductionmentioning

confidence: 99%

Optimal Tube Bundle Arrangements in Side-Fired Methane Steam Reforming Furnaces

et al. 2020

View full text Add to dashboard Cite

Steam methane reforming processes represent the economically most competitive processes for the production of synthesis gas and hydrogen despite their high energy costs. Although there is a strong need for highly resource-efficient production, literature on the optimal design of reformers remains scarce due to the inherently high complexity of these processes. This contribution addresses design aspects of reformers for the case study of a side-fired reformer. Based on a two-dimensional furnace representation heat transfer and the optimal tube bundle arrangement for a fixed furnace chamber are investigated using simulation-based parametric study with both a lean radiation-based model and a computational fluid dynamics model that enables the consideration of fuel efficiency. Radiative heat transfer prevails in the reformer on the furnace side and inter-tube distances of at least three diameters are optimal within the investigated design space. The line arrangement of reformer tubes is beneficial in terms of total heat transferred, fuel efficiency as well as the homogeneity of the tube surface temperatures. These findings pave the way for further studies such as three-dimensional design aspects.

show abstract

“…They can address complex black-box problems, such as reactor geometry [16,17] or impeller configuration [18], but require a large number of function evaluations, which leads to a large number of computationally expensive CFD runs. To improve the computational efficiency of direct CFD simulations, hybrid methods have been proposed that replace direct CFD evaluation with simpler data-driven models [21][22][23][24][25], which are then integrated with GA. Successful implementation have been reported in the literature that use neural network [22,23], Gaussian process [24] and radial basis function (RBF) [25].…”

Section: Introductionmentioning

confidence: 99%

“…To improve the computational efficiency of direct CFD simulations, hybrid methods have been proposed that replace direct CFD evaluation with simpler data-driven models [21][22][23][24][25], which are then integrated with GA. Successful implementation have been reported in the literature that use neural network [22,23], Gaussian process [24] and radial basis function (RBF) [25]. However, building confidence in those data-driven models requires large number of CFD runs, and balancing computational efficiency with accuracy is non-trivial [26].…”

Section: Introductionmentioning

confidence: 99%

Optimization of Reaction Selectivity Using CFD-Based Compartmental Modeling and Surrogate-Based Optimization

et al. 2018

View full text Add to dashboard Cite

Mixing is considered as a critical process parameter (CPP) during process development due to its significant influence on reaction selectivity and process safety. Nevertheless, mixing issues are difficult to identify and solve owing to their complexity and dependence on knowledge of kinetics and hydrodynamics. In this paper, we proposed an optimization methodology using Computational Fluid Dynamics (CFD) based compartmental modelling to improve mixing and reaction selectivity. More importantly, we have demonstrated that through the implementation of surrogate-based optimization, the proposed methodology can be used as a computationally non-intensive way for rapid process development of reaction unit operations. For illustration purpose, reaction selectivity of a process with Bourne competitive reaction network is discussed. Results demonstrate that we can improve reaction selectivity by dynamically controlling rates and locations of feeding in the reactor. The proposed methodology incorporates mechanistic understanding of the reaction kinetics together with an efficient optimization algorithm to determine the optimal process operation and thus can serve as a tool for quality-by-design (QbD) during product development stage.

show abstract

Multi-objective Bayesian optimization of chemical reactor design using computational fluid dynamics

Cited by 73 publications

References 33 publications

A federated data-driven evolutionary algorithm for expensive multi-/many-objective optimization

A federated data-driven evolutionary algorithm for expensive multi-/many-objective optimization

Optimal Tube Bundle Arrangements in Side-Fired Methane Steam Reforming Furnaces

Optimization of Reaction Selectivity Using CFD-Based Compartmental Modeling and Surrogate-Based Optimization

Contact Info

Product

Resources

About