Machine learning-based adaptive model identification of systems: Application to a chemical process

Bhadriraju, Bhavana; Narasingam, Abhinav; Kwon, Joseph

doi:10.1016/j.cherd.2019.09.009

Cited by 81 publications

(24 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The current study aims to modify this strategy and adopt it into photo‐production bioprocess hybrid modelling. More mathematical theory background of model structure detection and sparse optimisation can be found in (Bhadriraju, Narasingam, & Kwon, 2019). Detailed implementation of this strategy is explained below.…”

Section: Methodsmentioning

confidence: 99%

Combining model structure identification and hybrid modelling for photo‐production process predictive simulation and optimisation

Zhang

Savage

Cho

2020

Biotech & Bioengineering

View full text Add to dashboard Cite

Integrating physical knowledge and machine learning is a critical aspect of developing industrially focused digital twins for monitoring, optimisation, and design of microalgal and cyanobacterial photo-production processes. However, identifying the correct model structure to quantify the complex biological mechanism poses a severe challenge for the construction of kinetic models, while the lack of data due to the time-consuming experiments greatly impedes applications of most data-driven models. This study proposes the use of an innovative hybrid modelling approach that consists of a simple kinetic model to govern the overall process dynamic trajectory and a data-driven model to estimate mismatch between the kinetic equations and the real process. An advanced automatic model structure identification strategy is adopted to simultaneously identify the most physically probable kinetic model structure and minimum number of data-driven model parameters that can accurately represent multiple data sets over a broad spectrum of process operating conditions. Through this hybrid modelling and automatic structure identification framework, a highly accurate mathematical model was constructed to simulate and optimise an algal lutein production process. Performance of this hybrid model for long-term predictive modelling, optimisation, and online self-calibration is demonstrated and thoroughly discussed, indicating its significant potential for future industrial application.

show abstract

Section: Methodsmentioning

confidence: 99%

Combining model structure identification and hybrid modelling for photo‐production process predictive simulation and optimisation

Zhang

Savage

Cho

2020

Biotech & Bioengineering

View full text Add to dashboard Cite

show abstract

“…However, the functional form of H is usually unknown a priori. Although there are some methods proposed in the literature to identify functional forms from the data, inferring functional forms usually requires a large amount of data and can be computationally expensive [49][50][51][52][53][54]. Instead, we assume H to be an ANN model.…”

Section: Development Of Artificial Neural Network Modelsmentioning

confidence: 99%

Development of a hybrid model for a partially known intracellular signaling pathway through correction term estimation and neural network modeling

2020

Self Cite

View full text Add to dashboard Cite

Developing an accurate first-principle model is an important step in employing systems biology approaches to analyze an intracellular signaling pathway. However, an accurate first-principle model is difficult to be developed since it requires in-depth mechanistic understandings of the signaling pathway. Since underlying mechanisms such as the reaction network structure are not fully understood, significant discrepancy exists between predicted and actual signaling dynamics. Motivated by these considerations, this work proposes a hybrid modeling approach that combines a first-principle model and an artificial neural network (ANN) model so that predictions of the hybrid model surpass those of the original model. First, the proposed approach determines an optimal subset of model states whose dynamics should be corrected by the ANN by examining the correlation between each state and outputs through relative order. Second, an L2-regularized least-squares problem is solved to infer values of the correction terms that are necessary to minimize the discrepancy between the model predictions and available measurements. Third, an ANN is developed to generalize relationships between the values of the correction terms and the system dynamics. Lastly, the original first-principle model is coupled with the developed ANN to finalize the hybrid model development so that the model will possess generalized prediction capabilities while retaining the model interpretability. We have successfully validated the proposed methodology with two case studies, simplified apoptosis and lipopolysaccharide-induced NFκB signaling pathways, to develop hybrid models with in silico and in vitro measurements, respectively.

show abstract

“…Therefore, it is challenging to use SINDy for model‐based control, especially in the presence of any parameter uncertainties or changing process dynamics, because recovering the model by solving a sparse regression problem online is computationally expensive. To address this, we previously proposed an adaptive model identification framework that utilizes a small amount of data to identify and recover the model in real time 22 . Though the method provides a direction to apply SINDy for adaptive modeling, it is useful to have a robust framework that guarantees to adapt well with the changing process dynamics.…”

Section: Introductionmentioning

confidence: 99%

Operable adaptive sparse identification of systems: Application to chemical processes

et al. 2020

Self Cite

View full text Add to dashboard Cite

Over the past few decades, several data-driven methods have been developed for identifying a model that accurately describes the process dynamics. Lately, sparse identification of nonlinear dynamics (SINDy) has delivered promising results for various nonlinear processes. However, at any instance of plant-model mismatch or process upset, retraining the model using SINDy is computationally expensive and cannot guarantee to catch up with rapidly changing dynamics. Hence, we propose operable adaptive sparse identification of systems (OASIS) framework that extends the capabilities of SINDy for accurate, automatic, and adaptive approximation of process models. First, we use SINDy to obtain multiple models from historical data for varying input settings. Next, using these models and their training data, we build a deep neural network that is incorporated in a model predictive control framework for closed-loop operation. We demonstrate the OASIS methodology on the identification and control of a continuous stirred tank reactor.

show abstract

Machine learning-based adaptive model identification of systems: Application to a chemical process

Cited by 81 publications

References 47 publications

Combining model structure identification and hybrid modelling for photo‐production process predictive simulation and optimisation

Combining model structure identification and hybrid modelling for photo‐production process predictive simulation and optimisation

Development of a hybrid model for a partially known intracellular signaling pathway through correction term estimation and neural network modeling

Operable adaptive sparse identification of systems: Application to chemical processes

Contact Info

Product

Resources

About