Neurodynamics-Driven Model Predictive Control With Soft-Measurement for Desulfurization System

Sulfur dioxide ( $\mathrm {SO_{2}}$ ) emissions are the main problems causing the air pollution and respiratory disease, which makes desulfurization important in the coal combustion and chemical industry processes. The wet-flue-gas desulfurization (WFGD) is currently an effective method to deal with this issue. However, the WFGD system is actually a complex process with multi-variable coupling, high nonlinearity and large time-delay, which brings great challenges for the traditional mechanism-based modeling and control. In this paper, a neurodynamics-driven model predictive control (NDMPC) with soft-measurement is proposed to predict and control the dynamics of $\mathrm {SO_{2}}$ to improve the operational performance of the WFGD system. First, we design a self-organizing fuzzy neural network (SOFNN) as the soft-measuring model, which is driven by the data and neurodynamics to adaptively predict $\mathrm {SO_{2}}$ in the WFGD system. Second, the designed SOFNN is considered as a predictive model that can give the predicted values for the future moments. Third, we also design a loss function where the one-step output of the predictive model and the control law are the independent variables. The resulting rolling optimization can give the optimal control law sequence by minimizing the loss function. Finally, simulation experiments on the practical data from the WFDG system show that the NDMPC outperforms the other methods in terms of the soft-measurement and control performance, especially generally reducing the $\mathrm {SO_{2}}$ emission and economic cost by 60.25% and 22.27%, respectively. Note to Practitioners—The proposed NDMPC framework presents an effective method to solve the optimal feedstock. which can reduce costs while maintaining the operational efficiency of WFGD system. The optimal solution of NDMPC is dominated by soft-measuring model (SOFNN) to some extent. In the practical applications of WFGD systems, it is better for practitioners to obtain more historical data so that the more accurate soft-measuring model is available for the optimal solution of NDMPC.