Nonlinear model predictive control for the ALSTOM gasifier

Abstract

In this work a nonlinear model predictive control based on Wiener model has been developed and used to control the ALSTOM gasifier. The 0% load condition was identified as the most difficult case to control among three operating conditions. A linear model of the plant at 0% load is adopted as a base model for prediction. A nonlinear static gain represented by a feedforward neural network was identified for a particular output channel-namely, fuel gas pressure, to compensate its strong nonlinear behaviour observed in open loop simulations. By linearising the neural network at each sampling time, the static nonlinear model provides certain adaptation to the linear base model at all other load conditions. The resulting controller showed noticeable performance improvement when compared with pure linear model based predictive control. 2006 Elsevier Ltd. All rights reserved.

Neural network based nonlinear model predictive control for an intensified continuous reactor

“…(19), the NMPC with nonlinear optimization (NMPC-NO) based on nonlinear neural network model in Eq. (23), and the NMPC with nonlinear prediction and linearization (NMPC-NPL) that is described by Eq.…”

“…Such as developing a neural network model, it is easy to make a large number of simulations to feed the neural network whereas it is more difficult to make the experiments that will also lack the same reproducibility. The empirical approaches include polynomial approximations (e.g., autoregressive moving average model with exogenous inputs, ARMAX) [13][14][15], artificial neural networks [16][17][18][19][20][21][22][23], piecewise linear models [24], Volterra series [25], Wiener and Hammerstein models [19][20][21], etc. In the above empirical models, neural network models have found wide applicability because of their inherent capability of handling complex and nonlinear problems and reducing the engineering effort required in controller model development.…”

Performance evaluation of optimal PI controller for ALSTOM gasifier during coal quality variations

“…Researchers have attempted to design controllers and/or retuned the baseline controller to meet the performance objectives at 100%, 50% and 0% load conditions. While many researchers have attempted these challenges [3][4][5][6][7][8][9][10][11][12][13][14][15][16], meeting the desired gasifier performance due to variation in calorific value under step and sinusoidal pressure disturbance remains unsolved. The ultimate requirement is to design an optimal controller such that all the constraints are met for disturbances around all load conditions and coal quality variations.…”

“…In order to compare the performance of the proposed optimal PI controller with some of the other works published [2,6] and [10] so far, Maximum Absolute Error (MAE) and Integral of Absolute Error (IAE) obtained in each method corresponding to six pressure disturbance tests (step and sinusoidal disturbances around three operating loads) are consolidated and shown in Table 3. The obtained results for the above six pressure disturbance tests (step and sinusoidal disturbances around three operating loads) are consolidated and shown in Table 3.…”

Adaptive hybrid predictive control for a combined cycle power plant optimization

“…To tackle the real-time optimization of a CCPP in [4,5] an optimizing supervisory algorithm based on predictive control is used, and in [6] predictive control is used on gasification units employing linearized neuronal models. In all these examples the CCPP operation is optimized in an economical way, but the prediction models do not consider the start up and shut down procedures or any other logic condition.…”