A hybrid representation approach for modelling complex dynamic bioprocesses

Thibault, Jules; Acuña, Gonzalo; Pérez-Correa, Ricardo; Jorquera, Héctor; Molin, Paul; Agosín, Eduardo

doi:10.1007/s004499900110

Cited by 24 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sometimes, ANN was found unreliable for extrapolation and did not lead to better understanding of the system (Shinskey 1998); but this disadvantage may be overcome to some extent by establishing a hybrid neural network (HNN) model. In such a model, prior knowledge is introduced and only a few parameters are represented by neural networks (Thibault et al 2000;Viassides et al 2001). Several deterministic kinetic models were proposed for describing batch cultivations of heterotrophic Chlorella (Zhang et al 1999;Shi et al 2000).…”

Section: Introductionmentioning

confidence: 99%

Optimization for high-density cultivation of heterotrophic Chlorella based on a hybrid neural network model

Shi

2007

Lett Appl Microbiol

106

View full text Add to dashboard Cite

Aims: The purpose of this study was to develop a reliable hybrid neural network (HNN) model for heterotrophic growth of Chlorella, based on which optimization for fed‐batch (FB) cultivation of Chlorella may be successfully realized. Methods and Results: Deterministic kinetic model was preliminarily developed for the optimization of FB cultivation of Chlorella. The highest biomass concentration and the maximum productivity were obtained as: 104·9 g l−1 dry cell weight and 0·613 g l−1 h−1, respectively. After several cultivations had been performed, an HNN model was developed. The efficiency of biomass production was further increased by the optimization using this model. The highest biomass concentration and the maximum productivity attained was: 116·2 g l−1 dry cell weight and 1·020 g l−1 h−1, respectively. Conclusion: The HNN model agreed well with experimental results in different cultivations. Comparison between the HNN model and the deterministic model showed that the former had better generalization ability, which made it a reliable tool in modelling and optimization. Significance and Impact of the Study: The high cell density and productivity of biomass obtained in this study is of significance for the commercial cultivation of Chlorella. The simple and efficient optimization strategy proposed in this paper may be employed in heterotrophic mass culture of Chlorella as well as other similar organisms.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimization for high-density cultivation of heterotrophic Chlorella based on a hybrid neural network model

Shi

2007

Lett Appl Microbiol

106

View full text Add to dashboard Cite

show abstract

“…Such unit operation agents can, with the co‐operation of FP and AI agents, also act as a bridge to link FP and data‐driven models. This integrates the best features of the two different types of models so as to derive a hybrid model (Feyo de Azevedo et al,1997; Martinez and Wilson,1998; Thibault et al,2000; Zorzetto et al,2000) for a more sophisticated and complete process description.…”

Section: Proposed Framework For Agent‐based Plant‐wide Bioprocess Desmentioning

confidence: 99%

Application of agent‐based system for bioprocess description and process improvement

Gao

Kipling

Glassey

et al. 2009

Biotechnology Progress

View full text Add to dashboard Cite

Modeling plays an important role in bioprocess development for design and scale-up. Predictive models can also be used in biopharmaceutical manufacturing to assist decision-making either to maintain process consistency or to identify optimal operating conditions. To predict the whole bioprocess performance, the strong interactions present in a processing sequence must be adequately modeled. Traditionally, bioprocess modeling considers process units separately, which makes it difficult to capture the interactions between units. In this work, a systematic framework is developed to analyze the bioprocesses based on a whole process understanding and considering the interactions between process operations. An agent-based approach is adopted to provide a flexible infrastructure for the necessary integration of process models. This enables the prediction of overall process behavior, which can then be applied during process development or once manufacturing has commenced, in both cases leading to the capacity for fast evaluation of process improvement options. The multi-agent system comprises a process knowledge base, process models, and a group of functional agents. In this system, agent components co-operate with each other in performing their tasks. These include the description of the whole process behavior, evaluating process operating conditions, monitoring of the operating processes, predicting critical process performance, and providing guidance to decision-making when coping with process deviations. During process development, the system can be used to evaluate the design space for process operation. During manufacture, the system can be applied to identify abnormal process operation events and then to provide suggestions as to how best to cope with the deviations. In all cases, the function of the system is to ensure an efficient manufacturing process. The implementation of the agent-based approach is illustrated via selected application scenarios, which demonstrate how such a framework may enable the better integration of process operations by providing a plant-wide process description to facilitate process improvement.

show abstract

“…Lee and Ramirez (1996) and Tholudur and Ramirez (1999) utilized a hybrid model to describe shock and recovery of cell growth with respect to the induction of recombinant protein production. Thibault et al (2000) utilized a hybrid model to describe the activity of a simulated fermentation system that produced gluconic acid. However, both of these models utilized a time-dependent model that required measurements of several state variables, data that may not be available in all historical databases.…”

Section: Introductionmentioning

confidence: 99%

Retrospective optimization of time-dependent fermentation control strategies using time-independent historical data

Block

2006

Biotechnol. Bioeng.

View full text Add to dashboard Cite

We have previously shown the usefulness of historical data for fermentation process optimization. The methodology developed includes identification of important process inputs, training of an artificial neural network (ANN) process model, and ultimately use of the ANN model with a genetic algorithm to find the optimal values of each critical process input. However, this approach ignores the time-dependent nature of the system, and therefore, does not fully utilize the available information within a database. In this work, we propose a method for incorporating time-dependent optimization into our previously developed three-step optimization routine. This is achieved by an additional step that uses a fermentation model (consisting of coupled ordinary differential equations (ODE)) to interpret important time-course features of the collected data through adjustments in model parameters. Important process variables not explicitly included in the model were then identified for each model parameter using automatic relevance determination (ARD) with Gaussian process (GP) models. The developed GP models were then combined with the fermentation model to form a hybrid neural network model that predicted the time-course activity of the cell and protein concentrations of novel fermentation conditions. A hybrid-genetic algorithm was then used in conjunction with the hybrid model to suggest optimal time-dependent control strategies. The presented method was implemented upon an E. coli fermentation database generated in our laboratory. Optimization of two different criteria (final protein yield and a simplified economic criteria) was attempted. While the overall protein yield was not increased using this methodology, we were successful in increasing a simplified economic criterion by 15% compared to what had been previously observed. These process conditions included using 35% less arabinose (the inducer) and 33% less typtone in the media and reducing the time required to reach the maximum protein concentration by 10% while producing approximately the same level of protein as the previous optimum.

show abstract

A hybrid representation approach for modelling complex dynamic bioprocesses

Cited by 24 publications

References 22 publications

Optimization for high-density cultivation of heterotrophic Chlorella based on a hybrid neural network model

Optimization for high-density cultivation of heterotrophic Chlorella based on a hybrid neural network model

Application of agent‐based system for bioprocess description and process improvement

Retrospective optimization of time-dependent fermentation control strategies using time-independent historical data

Contact Info

Product

Resources

About