Search

The aluminum fluoride (AF) addition in aluminum electrolysis process (AEP) can directly influence the current efficiency, energy consumption, and stability of the process. This paper proposes an optimization scheme for AF addition based on pruned sparse fuzzy neural network (PSFNN), aiming at providing an optimal AF addition for aluminum electrolysis cell under normal superheat degree (SD) condition. Firstly, a Gaussian mixture model (GMM) is introduced to identify SD conditions in which the operating modes of AEP are unknown. Then, PSFNN is proposed to establish the AF addition model under normal SD condition identified by GMM. Specifically, a sparse regularization term is designed in loss function of PSFNN to extract the sparse representation from nonlinear process data. A structure optimization strategy based on enhanced optimal brain surgeon (EOBS) algorithm is proposed to prune redundant neurons in the rule layer. Mini-batch gradient descent and AdaBound optimizer are then introduced to optimize the parameters of PSFNN. Finally, the performance is confirmed on the simulated Tennessee Eastman process (TEP) and real-world AEP. Experimental results demonstrate that the proposed scheme provides a satisfactory performance. • A novel pruned sparse fuzzy neural network (PSFNN) is developed to establish the AF addition model under normal SD condition. • A sparse regularization term based on Kullback–Leibler divergence is designed in loss function of PSFNN to obtain the sparse representation. • The parameters of network are learned based on mini-batch gradient descent method with AdaBound optimizer. • An enhanced optimal brain surgeon (EOBS) algorithm is proposed to obtain a compact network structure. • The experimental results demonstrated that our method achieves a satisfactory performance. [ABSTRACT FROM AUTHOR]

Froth flotation is a complicated process which is difficult to establish its first-principle model. Due to the fluctuations in the grade of raw ore, adaptively adjusting the set-points is extremely important in the flotation process. The inappropriate set-points easily lead to the instability of the process. This paper presents a fuzzy association rule-based set-point adaptive optimization and control strategy for the antimony flotation process without knowing the system model. Firstly, a fuzzy neural network is constructed as a soft-sensor to estimate the feed grade online because of the lack of efficient measurement equipment. Then, fuzzy association rule is used to mine the hidden relationship between the feed grade with reagent dosages and the optimal set-points. Through data mining from the quantitative database, the fuzzy inference system generates the optimal set-points. To implement satisfactory tracking performance, predictive controller is used to compute the control inputs. Because the system dynamics is unknown, long short-term memory network model is established to predict the future behaviors of the process. Finally, simulations and experiments are carried out to demonstrate the effectiveness of the proposed strategy. Compared to the manual manipulation, which is widely used in flotation processes, our control strategy achieves a better control performance, and the concentrate grades are more in line with the process requirement. [ABSTRACT FROM AUTHOR]

In this paper, a novel three-layer coordinating optimization and control strategy involving fuzzy neural networks (FNNs) is proposed for industrial plant-wide control. This strategy includes a coordinator (top layer), local optimizers (middle layer), and local controllers (bottom layer). The coordinator determines and coordinates set-points of production indices for each process in the plant, aiming to achieve plant-wide optimal control. The local optimizers optimize individual unit and deliver the information to the coordinator. The controllers calculate optimal control inputs for the processes according to the set-points. Model predictive control (MPC) is used in this layer. Also used are FNNs with a gradient-based learning algorithm, which are trained to represent the models of the processes that are controlled by MPC. By constructing a Lyapunov function, convergence of the FNNs is established. Experiments are carried out in the largest zinc hydrometallurgy plant in China. The results demonstrate performance of our strategy in tracking the set-points and saving processing costs. Moreover, the strategy achieves a more optimal overall plant operation when compared to the same FNN-based MPC scheme that does not use the coordinator. [ABSTRACT FROM AUTHOR]

The analytical structure of fuzzy controller is important for better understanding and effective design of the fuzzy control system, especially for explaining why fuzzy control system work well. In this paper, we develop a three-dimensional fuzzy controller with arbitrary triangular input fuzzy sets. Then, the analytical structure of this fuzzy controller is derived rigorously, and some properties of this controller are given. To determine the parameters of the fuzzy controller, a novel proximal policy optimization algorithm with recall pool (RP-PPO) is proposed. A recall pool is designed in proximal policy optimization algorithm to store the best ten sets of parameters to enhance the optimization results. Finally, simulation studies are carried out on two time-delay systems and a nonlinear chemical process with time-varying time delay to validate the applicability and effectiveness of the proposed fuzzy controller. • A three-dimensional fuzzy controller with arbitrary triangular input fuzzy sets is designed. • We derive the analytical structure of fuzzy controller and analysis its properties. • A proximal policy optimization algorithm with a recall pool is proposed to optimize the parameters of fuzzy controller. • Simulations on time-delay models demonstrate the excellent performance of our proposed fuzzy controller. [ABSTRACT FROM AUTHOR]