<scp>Pyomo.DOE</scp>: An open‐source package for model‐based design of experiments in Python

Wang, Jialu; Dowling, Alexander W.

doi:10.1002/aic.17813

Cited by 24 publications

(7 citation statements)

References 124 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PARSEC (PARameter SEnsitivity driven Clustering based DoE) framework represents a MBDoE rooted in four key ideas (Figure 1). Firstly, it employs the parameter sensitivity of a variable as an indicator of its informativeness towards the estimation of a parameter value [35, 10]. The information content profile of a measurement is, thus, approximated using a vector of its parameter sensitivity indices (PSI) (Step 1, Figure 1).…”

Section: Resultsmentioning

confidence: 99%

“…Fisher’s Information Matrix (FIM) is a popular framework for designing experiments aimed at estimating model parameter values [3, 4, 5, 6, 7, 8]. It is based on the concept of the expected information gain from an experiment, which is calculated by taking the expected value of the second derivative of the log-likelihood function with respect to the model parameters [9, 10]. If changes in the values of the parameters have a major effect on the output of the model, it implies that the output is useful in providing information about the parameters.…”

Section: Introductionmentioning

confidence: 99%

“…The complexity of matrix inversion and the need for a large experimental sample size to achieve the desired accuracy and a Gaussian noise distribution present additional difficulties that restrict the use of FIM-MBDoE [11]. Recently, new approaches have been proposed to address some of these issues [8, 12, 11, 10, 13, 14, 9]. For example, design space discretization can be employed to handle non-linear models, and the average information content and risk can be calculated for a large uncertainty to identify robust and reliable designs [14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Rationalised experiment design for parameter estimation with sensitivity clustering

Chhajer,

Roy

2023

Preprint

View full text Add to dashboard Cite

Quantitative experiments are essential for investigating, uncovering and confirming our understanding of complex systems, necessitating the use of effective and robust experimental designs. Despite generally outperforming other approaches, the broader adoption of model-based design of experiments (MBDoE) has been hindered by oversimplified assumptions and computational overhead. To address this, we present PARameter SEnsitivity Clustering (PARSEC), an MBDoE framework that identifies informative measurable combinations through parameter sensitivity (PS) clustering. We combined PARSEC with a new variant of Approximate Bayesian Computation for rapid, automated assessment and ranking of designs. By inherent design, PARSEC can take into account experimental restrictions and parameter variability. We show that PARSEC improves parameter estimation for two different types of biological models. Importantly, PARSEC can determine the optimal sample size for information gain, which we show correlates well with the optimal number of PS clusters. This supports our rationale for PARSEC and demonstrates the potential to harness both model structure and system behaviour to efficiently navigate the experiment design space.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Rationalised experiment design for parameter estimation with sensitivity clustering

Chhajer,

Roy

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…While not essential for preliminary HFC separation process design and IL entrainer screening, ternary data is useful in the further validation and refinement of predictions made with models parametrized with binary data and can provide additional enrichment of a data set. Furthermore, we found several opportunities for utilizing model-based design of experiments (MBDoE) to inform the minimum required data set for screening at each step of the framework. Finally, a SAFT-based , or machine learning method may be implemented to predict ILs for HFC separations.…”

Section: Discussionmentioning

confidence: 99%

What Data Are Most Valuable to Screen Ionic Liquid Entrainers for Hydrofluorocarbon Refrigerant Reuse and Recycling?

Garciadiego

Befort

Franco

et al. 2022

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

Separating azeotropic mixtures of hydrofluorocarbons (HFCs) for reuse and recycle is environmentally and economically imperative. While ionic liquid (IL)-enabled HFC separations show promise, Edisonian trial-and-error screening for the optimal IL entrainer is intractable and expensive. Here, we propose an open-source, equation-oriented modeling framework to rapidly translate HFC/IL solubility data into regressed thermodynamic models which can be used for process design under uncertainty and rapid IL screening. Moreover, we use data science and process systems engineering tools to contemplate which data are the most valuable for IL screening. We find that binary solubility data collected at multiple temperatures is adequate for separation process design, and newly available ternary solubility measurements should be reserved for validation. Additionally, we use uncertainty quantification analyses to show up to 10% experimental error is acceptable for IL screening decisions. Informed by these results, we recommend a multistep workflow for IL screening.

show abstract

“…These calculations are performed using the Pyomo.DOE package (Wang and Dowling, 2022). We approximate the TABLE 1 | Kinetic model library.…”

Section: Model Identifiabilitymentioning

confidence: 99%

Nonlinear Reactor Design Optimization With Embedded Microkinetic Model Information

2022

Self Cite

View full text Add to dashboard Cite

Despite the success of multiscale modeling in science and engineering, embedding molecular-level information into nonlinear reactor design and control optimization problems remains challenging. In this work, we propose a computationally tractable scale-bridging approach that incorporates information from multi-product microkinetic (MK) models with thousands of rates and chemical species into nonlinear reactor design optimization problems. We demonstrate reduced-order kinetic (ROK) modeling approaches for catalytic oligomerization in shale gas processing. We assemble a library of six candidate ROK models based on literature and MK model structure. We find that three metrics—quality of fit (e.g., mean squared logarithmic error), thermodynamic consistency (e.g., low conversion of exothermic reactions at high temperatures), and model identifiability—are all necessary to train and select ROK models. The ROK models that closely mimic the structure of the MK model offer the best compromise to emulate the product distribution. Using the four best ROK models, we optimize the temperature profiles in staged reactors to maximize conversions to heavier oligomerization products. The optimal temperature starts at 630–900K and monotonically decreases to approximately 560 K in the final stage, depending on the choice of ROK model. For all models, staging increases heavier olefin production by 2.5% and there is minimal benefit to more than four stages. The choice of ROK model, i.e., model-form uncertainty, results in a 22% difference in the objective function, which is twice the impact of parametric uncertainty; we demonstrate sequential eigendecomposition of the Fisher information matrix to identify and fix sloppy model parameters, which allows for more reliable estimation of the covariance of the identifiable calibrated model parameters. First-order uncertainty propagation determines this parametric uncertainty induces less than a 10% variability in the reactor optimization objective function. This result highlights the importance of quantifying model-form uncertainty, in addition to parametric uncertainty, in multi-scale reactor and process design and optimization. Moreover, the fast dynamic optimization solution times suggest the ROK strategy is suitable for incorporating molecular information in sequential modular or equation-oriented process simulation and optimization frameworks.

show abstract

Pyomo.DOE: An open‐source package for model‐based design of experiments in Python

Cited by 24 publications

References 124 publications

Rationalised experiment design for parameter estimation with sensitivity clustering

Rationalised experiment design for parameter estimation with sensitivity clustering

What Data Are Most Valuable to Screen Ionic Liquid Entrainers for Hydrofluorocarbon Refrigerant Reuse and Recycling?

Nonlinear Reactor Design Optimization With Embedded Microkinetic Model Information

Contact Info

Product

Resources

About