A novel analysis and design of a neural network assisted nonlinear controller for a bioreactor

A comparison of networked approximators in parallel mode identification of a bioreactor

“…This figure stipulates that when the steady state is reached, the cell mass cannot assume values larger than 1þb 4 ¼ 0:255. This practical constraint was also highlighted in Puskorius and Feldkamp [23] and Efe et al [8]. The right subplot of Fig.…”

“…It is important to note that, for small a, (8) becomes the standard Gauss-Newton method, and for large a, the tuning law becomes the standard Error Backpropagation (EBP) algorithm. Therefore, LM method establishes a good balance between EBP and Gauss-Newton strategies.…”

MIMO variable structure controller design for a bioreactor benchmark process

“…According to the above discussion, we exploitĉ 1 (t) and c 2 (t) as the state variables in constructing the control signals in (8) and (9).…”

“…Larger values of η i s deteriorate the tracking performance significantly too. In fact, the choice of ζ i s is tightly dependent upon the quantity supĉ 1 ,c 2 ∈Ω |Σ 1 | and supĉ 1 ,c 2 ∈Ω |Σ 2 |, where Σ 1 and Σ 2 denote the collective form of uncertainties when the control laws in (8) and (9) are substituted into the dynamics in (18)-(21). This would yielḋ…”

A comparative study on a novel model‐based PID tuning and control mechanism for nonlinear systems

“…where c 1 (t) is the cell concentration that is considered as the output of the process (y(t) = c 1 (t)), c 2 (t) is the amount of nutrients per unit volume and u(t) is the flow rate as the control signal [28]. For this system, = 0.48 and = 0.02.…”