Online deep neural network-based feedback control of a Lutein bioprocess

Pappa, N.; Moghadam, Rohollah; Jagannathan, S.

doi:10.1016/j.jprocont.2020.11.011

Cited by 25 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to identify robustness of the said control paradigm with effect of non-zero signal-to-noise ratio (SNR) value, a variation on the set of process parameters ( k 01 , k 02 , C A , initial ) of the below pattern (presented in Figure 6(a)–(c)) was introduced. Under those significant mismatches, between process and model, the control schemes offer challenges to preserve its process outputs (Masooleh et al, 2022; Natarajan et al, 2021)…”

Section: Resultsmentioning

confidence: 99%

Disturbance-observer-based finite time sliding mode controller with unmatched uncertainties utilizing improved cubature Kalman filter

Sindhuja

Panda

Velappan

et al. 2023

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

Complex reactions are difficult to control as the reactants not only produce desired product but may also further undergo unwanted reactions or the original reactants may degrade through alternate paths. This can be improved by selecting proper measurement and control. In this paper, a robust augmented derivative-free Kalman filter (augmented cubature Kalman filter, ACKF) is propounded for the continuous stirred tank reactor (CSTR) carrying out Van-de-Vusse type complex reactions where the intermediate is the desired product in the midst of consecutive and parallel reactions. Non-isothermal CSTR shows strong non-linearity with inherent challenges as the reaction kinetics depends on process temperature through Arrhenius laws and accompanies non-ideal flow behaviour and unmeasurable disturbances. First, the process exhibits inverse or non-minimum phase behaviour. Second, to control product temperature and concentration, a finite time sliding mode controller (FSMC) is suggested which effectively tracks servo response to the desired set point. Third, a disturbance filter has been proposed in association with FSMC, which constructively eliminates the input disturbances. Realistic simulations for servo-regulatory compliance, elimination of measurement noise, impact on large perturbation, and parametric uncertainty with a state-of-the-art simulator ensure the efficacy of the proposed controller. The results are analysed further with a derivative-free FSMC control approach, considering various performance indices (root mean square error (RMSE), total variation (TV), mean square deviation (MSD)) to assess the goodness of the newly developed control strategy. It has been found that improved control law (improved augmented cubature Kalman filter (IACKF)-FSMC) yields better RMSE (7.2645e–05) than ACKF-FSMC (7.5814e–05).

show abstract

Section: Resultsmentioning

confidence: 99%

Disturbance-observer-based finite time sliding mode controller with unmatched uncertainties utilizing improved cubature Kalman filter

Sindhuja

Panda

Velappan

et al. 2023

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

show abstract

“…Recently, an adaptive neural network technique is devised for tracking control. The method possesses a self-learning capability which gives an added advantage in case of unavailability of prior data [75]. In a similar study, closed loop controller designed with a neural network estimator for a nonlinear process resulted in minimum tracking error when compared to conventional open loop methods even in case of perturbations and parametric uncertainties [39].…”

Section: Neural Network-based Controlmentioning

confidence: 92%

Bioprocess Control: Current Progress and Future Perspectives

Rathore

Mishra

Nikita

et al. 2021

Life

View full text Add to dashboard Cite

Typical bioprocess comprises of different unit operations wherein a near optimal environment is required for cells to grow, divide, and synthesize the desired product. However, bioprocess control caters to unique challenges that arise due to non-linearity, variability, and complexity of biotech processes. This article presents a review of modern control strategies employed in bioprocessing. Conventional control strategies (open loop, closed loop) along with modern control schemes such as fuzzy logic, model predictive control, adaptive control and neural network-based control are illustrated, and their effectiveness is highlighted. Furthermore, it is elucidated that bioprocess control is more than just automation, and includes aspects such as system architecture, software applications, hardware, and interfaces, all of which are optimized and compiled as per demand. This needs to be accomplished while keeping process requirement, production cost, market value of product, regulatory constraints, and data acquisition requirements in our purview. This article aims to offer an overview of the current best practices in bioprocess control, monitoring, and automation.

show abstract

“…For example, neural network-based control has demonstrated its effectiveness under system perturbations and parametric uncertainties. 31,32 Different variations of model predictive control have also shown excellent performance for various unit operations. 29,[33][34][35][36] Additionally, several methodologies for reducing computation burdens are emerging such as model linearization, and reinforcement learning.…”

Section: Quality By Controlmentioning

confidence: 99%

Current challenges and recent advances on the path towards continuous biomanufacturing

Drobnjakovic

Hart²,

Kulvatunyou

et al. 2023

Biotechnology Progress

View full text Add to dashboard Cite

Continuous biopharmaceutical manufacturing is currently a field of intense research due to its potential to make the entire production process more optimal for the modern, ever‐evolving biopharmaceutical market. Compared to traditional batch manufacturing, continuous bioprocessing is more efficient, adjustable, and sustainable and has reduced capital costs. However, despite its clear advantages, continuous bioprocessing is yet to be widely adopted in commercial manufacturing. This article provides an overview of the technological roadblocks for extensive adoptions and points out the recent advances that could help overcome them. In total, three key areas for improvement are identified: Quality by Design (QbD) implementation, integration of upstream and downstream technologies, and data and knowledge management. First, the challenges to QbD implementation are explored. Specifically, process control, process analytical technology (PAT), critical process parameter (CPP) identification, and mathematical models for bioprocess control and design are recognized as crucial for successful QbD realizations. Next, the difficulties of end‐to‐end process integration are examined, with a particular emphasis on downstream processing. Finally, the problem of data and knowledge management and its potential solutions are outlined where ontologies and data standards are pointed out as key drivers of progress.

show abstract

Online deep neural network-based feedback control of a Lutein bioprocess

Cited by 25 publications

References 33 publications

Disturbance-observer-based finite time sliding mode controller with unmatched uncertainties utilizing improved cubature Kalman filter

Disturbance-observer-based finite time sliding mode controller with unmatched uncertainties utilizing improved cubature Kalman filter

Bioprocess Control: Current Progress and Future Perspectives

Current challenges and recent advances on the path towards continuous biomanufacturing

Contact Info

Product

Resources

About