Online deep neural network-based feedback control of a Lutein bioprocess. (February 2021)

• Record Type: Journal Article
• Authors: Natarajan, Pappa; Moghadam, Rohollah; Jagannathan, S.
• Is Part Of: Journal of process control. Volume 98(2021)
• Page Start: 41
• Page End: 51
• Publication Date: 2021-02
• Subjects: Deep neural network -- Feedback linearization -- Lutein bioprocess -- Tracking control; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2020.11.011
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: An online adaptive deep neural network (DNN) scheme has been introduced for the tracking control of a nonlinear bioprocess with uncertain internal dynamics. First, a detailed controllability analysis is conducted for the Lutein bioprocess to represent the bioprocess as a nonlinear system in affine form. Next, a controller consisting of a DNN-based function approximator is designed for the nonlinear Lutein production bioprocess. It is demonstrated that closed-loop tracking control of a bioprocess for a desired yield profile is possible only with two inputs. The set point trajectory to yield maximum Lutein production is shown by the proposed online adaptive deep NN controller. The proposed controller exhibits self-learning capability under closed loop condition, due to the online learning phase. In other words, no explicit offline learning phase is required and online learning is preferred due to lack of a priori training data for approximating complex nonlinear functions. Simulation results are provided to confirm the performance of the proposed approach. Highlights: Online deep NN control of a Benchmark nonlinear bioprocess namely Lutein production process with unknown internal dynamics. Detailed mathematical analysis on Controllability of Nonlinear Bioprocess. Exploring the use of deep NN acting as a function approximator for feedback linearization. Ability to track the optimal profile to achieve the required yield.