Enhanced process development using automated continuous reactors by self-optimisation algorithms and statistical empirical modelling

Jeraal, Mohammed I.; Holmes, Nicholas P.; Akien, Geoffrey R.; Bourne, Richard A.

doi:10.1016/j.tet.2018.02.061

Cited by 40 publications

(34 citation statements)

References 29 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each node has a value for each data point 4,2 , which is computed to be used as operator arguments on the layer above. Consequently, by using the tree structure and the index assignment given (Tables 1-3), the optimization problem was formulated with the objective to minimize the sum of squared errors (SSE) between the values computed by the model and the experimental data, Eq.…”

Section: Minlp Formulationmentioning

confidence: 99%

See 1 more Smart Citation

Identifying Physico-Chemical Laws from the Robotically Collected Data

Cao¹,

Russo²,

Vassiliadis³

et al. 2019

Preprint

View full text Add to dashboard Cite

A mixed-integer nonlinear programming (MINLP) formulation for symbolic regression was proposed to identify physical models from noisy experimental data. The formulation was tested using numerical models and was found to be more efficient than the previous literature example with respect to the number of predictor variables and training data points. The globally optimal search was extended to identify physical models and to cope with noise in the experimental data predictor variable. The methodology was coupled with the collection of experimental data in an automated fashion, and was proven to be successful in identifying the correct physical models describing the relationship between the shear stress and shear rate for both Newtonian and non-Newtonian fluids, and simple kinetic laws of reactions. Future work will focus on addressing the limitations of the formulation presented in this work, by extending it to be able to address larger complex physical models.

show abstract

Section: Minlp Formulationmentioning

confidence: 99%

“…It is evident by the increasing number of publications in which synthetic and computational chemistry, or materials development are mixed with machine learning (ML), robotics and artificial intelligence (AI), for example in Refs. [1][2][3][4][5][6]. DMT is promising less suitable models than possible.…”

Section: Introductionmentioning

confidence: 99%

Identifying Physico-Chemical Laws from the Robotically Collected Data

Cao¹,

Russo²,

Vassiliadis³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…This is evident by the increasing number of publications in which synthetic and computational chemistry, or materials development, are mixed with machine learning (ML), robotics and artificial intelligence (AI), for example in Refs. [1][2][3][4][5][6]. DMT promises to significantly expand the accessible chemical space, and to reduce the price of access to new functional molecules and materials.…”

Section: Introductionmentioning

confidence: 99%

A new formulation for symbolic regression to identify physico-chemical laws from experimental data

Neumann

Cao

Russo

et al. 2020

Chemical Engineering Journal

View full text Add to dashboard Cite

A modification to the mixed-integer nonlinear programming (MINLP) formulation for symbolic regression was proposed with the aim of identification of physical models from noisy experimental data. In the proposed formulation, a binary tree in which equations are represented as directed, acyclic graphs, is fully constructed for a pre-defined number of layers. The introduced modification results in the reduction in the number of required binary variables and removal of redundancy due to possible symmetry of the tree formulation. The formulation was tested using numerical models and was found to be more efficient than the previous literature example with respect to the numbers of predictor variables and training data points. The globally optimal search was extended to identify physical models and to cope with noise in the experimental data predictor variable. The methodology was proven to be successful in identifying the correct physical models describing the relationship between shear stress and shear rate for both Newtonian and non-Newtonian fluids, and simple kinetic laws of chemical reactions. Future work will focus on addressing the limitations of the present formulation and solver to enable extension of target problems to larger, more complex physical models.

show abstract

“…Automated flow reactors offer great opportunities for conducting rapid kinetic studies, as they can be combined with a variety of design of experiment algorithms in closed loop systems, where the reactor platform designs each experiment based on information collected from previously conducted experiments, all without user supervision. These closed loop systems have already shown much success for "self-optimising" reactors where the reactor platform autonomously finds the optimum operating conditions to maximise or minimise given criteria, such as yield or E-factor 14,[18][19][20][21][22][23][24][25][26][27][28][29] , by using response surfaces and optimisation algorithms, such as the SIMPLEX or SNOBFIT algorithms. Similar closed loop systems can also be used for making kinetic studies more efficient, by using Model-Based Design of Experiments (MBDoE), which designs experiments in the most efficient way possible in order to improve model understanding 3 .…”

Section: Introductionmentioning

confidence: 99%

Closed-Loop Model-Based Design of Experiments for Kinetic Model Discrimination and Parameter Estimation: Benzoic Acid Esterification on a Heterogeneous Catalyst

Waldron

Pankajakshan

Quaglio

et al. 2019

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

An autonomous reactor platform was developed to rapidly identify a kinetic model for the esterification of benzoic acid and ethanol with the heterogeneous Amberlyst-15 catalyst. A five-step methodology for kinetic studies was employed to systematically reduce the number of experiments required to identify a practical kinetic model. This included i) initial screening using traditional factorial designed steady-state experiments, ii) proposing and testing candidate kinetic models, iii) performing an identifiability analysis to reject models whose model parameters cannot be estimated for a given experimental budget, iv) performing online Model-Based Design of Experiments (MBDoE) for model discrimination to identify the best model from a list of candidates and v) performing online MBDoE for improving parameter precision for the chosen model. This methodology, combined with the reactor platform which conducted all kinetic experiments unattended, reduces the number of experiments and time required to identify kinetic models, significantly increasing lab productivity.

show abstract

Enhanced process development using automated continuous reactors by self-optimisation algorithms and statistical empirical modelling

Abstract: This is a repository copy of Enhanced process development using automated continuous reactors by self-optimisation algorithms and statistical empirical modelling.

Cited by 40 publications

References 29 publications

Identifying Physico-Chemical Laws from the Robotically Collected Data

Identifying Physico-Chemical Laws from the Robotically Collected Data

A new formulation for symbolic regression to identify physico-chemical laws from experimental data

Closed-Loop Model-Based Design of Experiments for Kinetic Model Discrimination and Parameter Estimation: Benzoic Acid Esterification on a Heterogeneous Catalyst

Contact Info

Product

Resources

About