This article presents a comparative study on the development and application of two distinct adaptive control algorithms for biomass specific growth rate control in fed-batch biotechnological processes. A typical fed-batch process using Escherichia coli for recombinant protein production was selected for this research. Numerical simulation results show that both developed controllers, an adaptive PI controller based on the gain scheduling technique and a model-free adaptive controller based on the artificial neural network, delivered a comparable control performance and are suitable for application when using the substrate limitation approach and substrate feeding rate manipulation. The controller performance was tested within the realistic ranges of the feedback signal sampling intervals and measurement noise intensities. Considering the efforts for controller design and tuning, including development of the adaptation/learning algorithms, the model-free adaptive control algorithm proves to be more attractive for industrial applications, especially when only limited knowledge of the process and its mathematical model is available. The investigated model-free adaptive controller also tended to deliver better control quality under low specific growth rate conditions that prevail during the recombinant protein production phase. In the investigated simulation runs, the average tracking error did not exceed 0.01 (1/h). The temporary overshoots caused by the maximal disturbances stayed within the range of 0.025–0.11 (1/h). Application of the algorithm can be further extended to specific growth rate control in other bacterial and mammalian cell cultivations that run under substrate limitation conditions.

In this paper, we propose examining Heterogeneous Autoregressive (HAR) models using five different estimation techniques and four different estimation horizons to decide which performs better in terms of forecasting accuracy. Several different estimators are used to determine the coefficients of three selected HAR-type models. Furthermore, model lags, calculated using 5 min intraday data from the Standard & Poor’s 500 (SPX) index and the Chicago Board Options Exchange Volatility (VIX) index as the sole exogenous variable, enrich the models. For comparison and evaluation of the experimental results, we use three metrics: Quasi-Likelihood (QLIKE), Mean Absolute Error (MAE), and Mean Squared Error (MSE). An empirical study reveals that the Entropy Loss Function consistently achieves the best QLIKE results in all the horizons, especially in the weekly horizon. On the other hand, the performance of the Robust Linear Model implies that it can provide an alternative to the Entropy Loss Function when considering the results of the MAE and MSE metrics. Moreover, research shows that adding more informative lags, such as Realized Quarticity for the Heterogeneous Autoregressive model yielding the Realized Quarticity (HARQ) model, and incorporating the VIX index further improve the general results of the models. The results of the proposed Entropy Loss Function and Robust Linear Model suggest that they successfully achieve significant forecasting accuracy for HAR models across multiple forecasting horizons.

Pharmaceutical industries widely use Escherichia coli cell strain to synthesize various target products. The main goal is to reach the highest possible product yield. However, the formation of by-products is inevitable throughout the cell growth stage. Metabolic compounds such as acetates cause inhibition, particularly in later bioprocess stages. Therefore, the acetate accumulation model is necessary for planning bioprocesses to maximize cell biomass growth. The decision tree method was in possession to replicate the approach. Specific biomass growth at induction, broth weight, oxygen uptake rate, and consumed substrate weight were the inputs of model training. Broth and consumed substrate weight had additional aging-related information incorporated as separate inputs to introduce the cumulative regularization.

Accurate estimations of the concentrations of soluble compounds are crucial for optimizing bioprocesses involving Escherichia coli (E. coli). This study proposes a hybrid model structure that leverages off-gas analysis data and physiological parameters, including the average biomass age and specific growth rate, to estimate soluble compounds such as acetate and glutamate in fed-batch cultivations We used a hybrid recurrent neural network to establish the relationships between these parameters. To enhance the precision of the estimates, the model incorporates ensemble averaging and information gain. Ensemble averaging combines varying model inputs, leading to more robust representations of the underlying dynamics in E. coli bioprocesses. Our hybrid model estimates acetates with 1% and 8% system precision using data from the first site and the second site at GSK plc, respectively. Using the data from the second site, the precision of the approach for other solutes was as fallows: isoleucine −8%, lactate and glutamate −9%, and a 13% error for glutamine., These results, demonstrate its practical potential.