4.6 Article

A general deep hybrid model for bioreactor systems: Combining first principles with deep neural networks

Related references

Note: Only part of the references are listed.
Article Computer Science, Interdisciplinary Applications

HybridML: Open source platform for hybrid modeling

Kilian Merkelbach et al.

Summary: This paper presents an open-source modeling platform called HybridML, which can train hybrid models by combining data-driven models with mechanistic models. The authors demonstrate the application of HybridML through an industrial case study and a nonlinear application.

COMPUTERS & CHEMICAL ENGINEERING (2022)

Article Engineering, Chemical

Physics-informed neural networks for hybrid modeling of lab-scale batch fermentation for ß-carotene production using Saccharomyces cerevisiae

Mohammed Saad Faizan Bangi et al.

Summary: In this study, a hybrid model was built using the universal differential equations (UDEs) approach to accurately approximate the unknown dynamics of the batch fermentation process, thereby increasing the overall accuracy of the model. Prior knowledge about the process was incorporated during the hybrid model training to ensure faster convergence of its parameters.

CHEMICAL ENGINEERING RESEARCH & DESIGN (2022)

Article Engineering, Environmental

Deep neural network-based hybrid modeling and experimental validation for an industry-scale fermentation process: Identification of time-varying dependencies among parameters

Parth Shah et al.

Summary: Kinetic modeling of fermentation processes is challenging, but data-driven and hybrid models offer potential solutions. In this study, a hybrid model combining kinetic and deep neural network approaches was developed to improve accuracy and robustness, enabling accurate predictions of fermentation processes.

CHEMICAL ENGINEERING JOURNAL (2022)

Article Biotechnology & Applied Microbiology

A hybrid mechanistic-empirical model for in silico mammalian cell bioprocess simulation

Conor M. O'Brien et al.

Summary: The article discusses the construction of a systems model describing the interactions of major players in cell culture and the optimization of parameters to enhance process understanding and robustness. The optimized model captures the dynamics of metabolism and process variability, attributing part of it to the metabolic state of cell inoculum. The model is also used to identify potential mitigation strategies and explore the effect of changing CO2 removal capacity on process performance.

METABOLIC ENGINEERING (2021)

Article Engineering, Chemical

Digital Twin Application for Model-Based DoE to Rapidly Identify Ideal Process Conditions for Space-Time Yield Optimization

Benjamin Bayer et al.

Summary: The rapid identification of optimal process conditions in a design space using model-based design of experiments helps reduce experimental effort and increase process understanding. By repeating experiments and retraining models, the certainty of the optimal conditions is achieved, leading to a significant reduction in experimental effort and improved efficiency.

PROCESSES (2021)

Article Computer Science, Interdisciplinary Applications

Deep hybrid modeling of chemical process: Application to hydraulic fracturing

Mohammed Saad Faizan Bangi et al.

COMPUTERS & CHEMICAL ENGINEERING (2020)

Article Biochemical Research Methods

Adapting machine-learning algorithms to design gene circuits

Tom W. Hiscock

BMC BIOINFORMATICS (2019)

Article Biotechnology & Applied Microbiology

A bootstrap-aggregated hybrid semi-parametric modeling framework for bioprocess development

Jose Pinto et al.

BIOPROCESS AND BIOSYSTEMS ENGINEERING (2019)

Article Mathematics, Applied

Deep vs. shallow networks: An approximation theory perspective

H. N. Mhaskar et al.

ANALYSIS AND APPLICATIONS (2016)

Article Biotechnology & Applied Microbiology

Hybrid modeling as a QbD/PAT tool in process development: an industrial E-coli case study

Moritz von Stosch et al.

BIOPROCESS AND BIOSYSTEMS ENGINEERING (2016)

Article Biotechnology & Applied Microbiology

Fast development of Pichia pastoris GS115 Mut+ cultures employing batch-to-batch control and hybrid semi-parametric modeling

A. R. Ferreira et al.

BIOPROCESS AND BIOSYSTEMS ENGINEERING (2014)

Review Computer Science, Interdisciplinary Applications

Hybrid semi-parametric modeling in process systems engineering: Past, present and future

Moritz von Stosch et al.

COMPUTERS & CHEMICAL ENGINEERING (2014)

Article Computer Science, Artificial Intelligence

A novel identification method for hybrid (N)PLS dynamical systems with application to bioprocesses

M. von Stosch et al.

EXPERT SYSTEMS WITH APPLICATIONS (2011)

Article Biotechnology & Applied Microbiology

Selective expression of the soluble product fraction in Escherichia coli cultures employed in recombinant protein production processes

Stefan Gnoth et al.

APPLIED MICROBIOLOGY AND BIOTECHNOLOGY (2010)

Article Mathematics, Applied

Local identification of scalar hybrid models with tree structure

Bernold Fiedler et al.

IMA JOURNAL OF APPLIED MATHEMATICS (2008)

Article Biotechnology & Applied Microbiology

Product formation kinetics in genetically modified E-coli bacteria: inclusion body formation

Stefan Gnoth et al.

BIOPROCESS AND BIOSYSTEMS ENGINEERING (2008)

Article Biochemical Research Methods

Hybrid elementary flux analysis/nonparametric modeling: application for bioprocess control

Ana P. Teixeira et al.

BMC BIOINFORMATICS (2007)

Article Biotechnology & Applied Microbiology

Bioprocess iterative batch-to-batch optimization based on hybrid parametric/nonparametric models

AP Teixeira et al.

BIOTECHNOLOGY PROGRESS (2006)

Article Biotechnology & Applied Microbiology

Dynamic optimization of bioprocesses: Efficient and robust numerical strategies

JR Banga et al.

JOURNAL OF BIOTECHNOLOGY (2005)

Article Biotechnology & Applied Microbiology

Hybrid process models for process optimisation, monitoring and control

V Galvanauskas et al.

BIOPROCESS AND BIOSYSTEMS ENGINEERING (2004)

Article Computer Science, Interdisciplinary Applications

Combining first principles modelling and artificial neural networks: a general framework

R Oliveira

COMPUTERS & CHEMICAL ENGINEERING (2004)

Article Automation & Control Systems

Model selection for partial least squares regression

BB Li et al.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2002)

Review Microbiology

Heterologous protein expression in the methylotrophic yeast Pichia pastoris

JL Cereghino et al.

FEMS MICROBIOLOGY REVIEWS (2000)