Hybrid modeling in bioprocess dynamics: Structural variabilities, implementation strategies, and practical challenges

Mahanty, Biswanath

doi:10.1002/bit.28503

Cited by 12 publications

(2 citation statements)

References 124 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, specialized DNN topologies that automatically satisfy some of the physical constraints for better accuracy, faster training, and improved generalization may be designed. This is in contrast with traditional DNN models that typically allow for good fitting of a system, but their prediction may be inconsistent when performing extrapolation [109].…”

Section: Physics-informed Neural Network (Pinns)mentioning

confidence: 90%

From Shallow to Deep Bioprocess Hybrid Modeling: Advances and Future Perspectives

Agharafeie,

Ramos,

Mendes

et al. 2023

Fermentation

View full text Add to dashboard Cite

Deep learning is emerging in many industrial sectors in hand with big data analytics to streamline production. In the biomanufacturing sector, big data infrastructure is lagging compared to other industries. A promising approach is to combine deep neural networks (DNN) with prior knowledge in hybrid neural network (HNN) workflows that are less dependent on the quality and quantity of data. This paper reviews published articles over the past 30 years on the topic of HNN applications to bioprocesses. It reveals that HNNs have been applied to various bioprocesses, including microbial cultures, animal cells cultures, mixed microbial cultures, and enzyme biocatalysis. HNNs have been applied for process analysis, process monitoring, development of software sensors, open- and closed-loop control, batch-to-batch control, model predictive control, intensified design of experiments, quality-by-design, and recently for the development of digital twins. Most previous HNN studies have combined shallow feedforward neural networks (FFNNs) with physical laws, such as macroscopic material balance equations, following the semiparametric design principle. Only recently, deep HNNs based on deep FFNNs, convolution neural networks (CNN), long short-term memory (LSTM) networks and physics-informed neural networks (PINNs) have been reported. The biopharma sector is currently a major driver but applications to biologics quality attributes, new modalities, and downstream processing are significant research gaps.

show abstract

Section: Physics-informed Neural Network (Pinns)mentioning

confidence: 90%

From Shallow to Deep Bioprocess Hybrid Modeling: Advances and Future Perspectives

Agharafeie,

Ramos,

Mendes

et al. 2023

Fermentation

View full text Add to dashboard Cite

show abstract

“…The hybrid modeling approach may increase the complexity and computational cost of the model while also complicating the model validation process. Ensuring that theoretical and data models are based on consistent assumptions and datasets to maintain data consistency presents a challenge [ 165 , 172 ]. Dynamically adjusting model weights can enhance adaptability, but may also impact model performance.…”

Section: Continuum Robotsmentioning

confidence: 99%

Continuum Robots and Magnetic Soft Robots: From Models to Interdisciplinary Challenges for Medical Applications

Wang,

Mao,

2024

Micromachines

View full text Add to dashboard Cite

This article explores the challenges of continuum and magnetic soft robotics for medical applications, extending from model development to an interdisciplinary perspective. First, we established a unified model framework based on algebra and geometry. The research progress and challenges in principle models, data-driven, and hybrid modeling were then analyzed in depth. Simultaneously, a numerical analysis framework for the principle model was constructed. Furthermore, we expanded the model framework to encompass interdisciplinary research and conducted a comprehensive analysis, including an in-depth case study. Current challenges and the need to address meta-problems were identified through discussion. Overall, this review provides a novel perspective on understanding the challenges and complexities of continuum and magnetic soft robotics in medical applications, paving the way for interdisciplinary researchers to assimilate knowledge in this domain rapidly.

show abstract

Physics‐informed neural networks for biopharmaceutical cultivation processes: Consideration of varying process parameter settings

Adebar,

Arnold,

Herrera

et al. 2024

Biotech & Bioengineering

View full text Add to dashboard Cite

We present a new modeling approach for the study and prediction of important process outcomes of biotechnological cultivation processes under the influence of process parameter variations. Our model is based on physics‐informed neural networks (PINNs) in combination with kinetic growth equations. Using Taylor series, multivariate external process parameter variations for important variables such as temperature, seeding cell density and feeding rates can be integrated into the corresponding kinetic rates and the governing growth equations. In addition to previous approaches, PINNs also allow continuous and differentiable functions as predictions for the process outcomes. Accordingly, our results show that PINNs in combination with Taylor‐series expansions for kinetic growth equations provide a very high prediction accuracy for important process variables such as cell densities and concentrations as well as a detailed study of individual and combined parameter influences. Furthermore, the proposed approach can also be used to evaluate the outcomes of new parameter variations and combinations, which enables a saving of experiments in combination with a model‐driven optimization study of the design space.

show abstract

Hybrid modeling in bioprocess dynamics: Structural variabilities, implementation strategies, and practical challenges

Cited by 12 publications

References 124 publications

From Shallow to Deep Bioprocess Hybrid Modeling: Advances and Future Perspectives

From Shallow to Deep Bioprocess Hybrid Modeling: Advances and Future Perspectives

Continuum Robots and Magnetic Soft Robots: From Models to Interdisciplinary Challenges for Medical Applications

Physics‐informed neural networks for biopharmaceutical cultivation processes: Consideration of varying process parameter settings

Contact Info

Product

Resources

About