Multivariable advanced nonlinear controller for bioethanol production in a non-isothermal fermentation bioreactor

Reinforcement learning based temperature control of a fermentation bioreactor for ethanol production

Ethanol production is a significant industrial bioprocess for energy. The primary objective of this study is to control the process reactor temperature to get the desired product, that is, ethanol. Advanced model-based control systems face challenges due to model-process mismatch, but Reinforcement Learning (RL) is a class of machine learning which can help by allowing agents to learn policies directly from the environment. Hence a RL algorithm called twin delayed deep deterministic policy gradient (TD3) is employed. The control of reactor temperature is categorized into two categories namely unconstrained and constrained control approaches. The TD3 with various reward functions are tested on a nonlinear bioreactor model. The results are compared with existing popular RL algorithm, namely, deep deterministic policy gradient (DDPG) algorithm with a performance measure such as mean squared error (MSE). In the unconstrained control of the bioreactor, the TD3 based controller designed with the integral absolute error (IAE) reward yields a lower MSE of 0.22, whereas the DDPG produces an MSE of 0.29. Similarly, in the case of constrained controller, TD3 based controller designed with the IAE reward yields a lower MSE of 0.38, whereas DDPG produces an MSE of 0.48. In addition, the TD3 trained agent successfully rejects the disturbances, namely, input flow rate and inlet temperature in addition to a setpoint change with better performance metrics.

Robust Stabilization for Uncertain Non-Minimum Phase Switched Nonlinear System under Arbitrary Switchings

This paper addresses the problem of stabilization of non-minimum phase switched nonlinear systems where the internal dynamics with symmetries or non-symmetries of each mode may be unstable. The authors initially build a stabilizing Lyapunov controller for each mode in order to stabilize its own unstable internal dynamics. The proposed approach is based on the exact input-output feedback linearization technique and the Lyapunov stability theory. The stability results for non-minimum phase switched nonlinear systems with arbitrary switching rules are then obtained using generalized Gronwall–Bellman inequalities. Finally, numerical examples are provided to demonstrate the efficacy of the achieved results.

A novel cascaded fractional fuzzy approach for control of fermentation process

In this work, a cascaded control strategy based on fractional-order fuzzy PD/PI (FOFPD/PI) is proposed for temperature control of the bioreactor. The FOFPI is used to control the ethanol concentration in the inner loop, while the FOFPD is used for temperature control of the bioreactor in the outer loop. The integer order fuzzy PD/PI (IOFPD/PI), 2DOF FOPID, 2DOF PID, and PID are also designed for comparison purposes. The design parameter of FOFPD/PI and IOFPD/PI are estimated using non-dominated sorting genetic algorithm II (NSGA-II). Results revealed that the proposed cascaded control scheme reduced the IAE by 33.5 %, 40.5%, 47%, and 64% compared to IOFPD/PI, 2DOF FOPID, 2DOF PID, and PID, respectively. Hence, it can be concluded that the proposed FOFPD/PI controller provides precise control of reactor temperature in different operating conditions compared to other controllers.