Adaptive and Predictive Control of Liquid‐Liquid Extractors Using Neural‐Based Instantaneous Linearization Technique

Abstract

Nonlinearity of the extraction process is addressed via the application of instantaneous linearization to control the extract and raffinate concentrations. Two feed-forward neural networks with delayed inputs and outputs were trained and validated to capture the dynamics of the extraction process. These nonlinear models were then adopted in an instantaneous linearization algorithm into two control algorithms. The self-tuning adaptive control strategy was compared to an approximate model predictive control in terms of set point tracking capability, efficiency and stability. For the case of large, abrupt set point changes, the performance of the self-tuning algorithm was poor, especially for the raffinate control. The approximate model predictive control strategy was superior to the self-tuning control in terms of its ability to force the output to following the set point trajectory efficiently with smooth controller moves.

Nonlinear model identification and adaptive model predictive control using neural networks

“…The minimization of (14) using (16) is based on an iterative procedure which starts with a randomly initialized θ (k) = θ 0 (k) andθ (k) is updated iteratively according to the following typical updating rule…”

“…Several techniques for solving (14) exist in the literature [10,12,45]; and different methods for adjusting and updating θ (k) have also been reported in [9,11,21]. Following the discussion in Section 1, the NN technique is proposed in this paper for solving (14) on the basis of its approximation capabilities [10,19,33].…”

“…The generalized predictive control algorithm (GPC) is a class of MPC originally proposed by Clarke et al [41] in the context of adaptive control and has been widely used for industrial system control based on linear model [1][2][3][4]8,[14][15][16][17][18]24,28]. The proposed NN-based GPC scheme is shown in Fig.…”

“…Following the discussion in Section 1, the NN technique is proposed in this paper for solving (14) on the basis of its approximation capabilities [10,19,33].…”

“…The application of neural networks (NN) for model identification and the adaptive control of dynamic systems has been studied extensively [8][9][10][11][12][13][14][15][16][17][18]. NNs can approximate any nonlinear function to an arbitrarily high degree of accuracy [10][11][12][13][19][20][21].…”