Search

An adaptive generalized predictive control (GPC) scheme for an industrial process is designed based on a neuron adaptive splitting and merging radial basis function neural network (NASM-RBFNN) in this paper. The NASM-RBFNN is developed to identify the dynamic behaviors of the industrial process. In order to provide an accurate prediction model for the GPC, a neuron adaptive splitting and merging strategy and a weighted parameters adaptive correction approach are proposed. The neuron adaptive splitting and merging strategy can automatically add or delete the hidden neurons on-line, and the weighted parameters adaptive correction approach can update the weights based on the error of the neural network. The proposed approaches can enable the NASM-RBFNN to be adapted to the time-varying production condition and stochastic disturbance. The stability analysis and convergence of neuron adaptive splitting and merging strategy and weighted parameters adaptive correction approach are given. Finally, the NASM-RBFNN-based GPC (NASM-RBFNN-GPC) is applied to control the iron removal process in the largest zinc hydrometallurgy plant in China. The industrial experiments demonstrate that the NASM-RBFNN-GPC has a satisfactory tracking and control performance. [ABSTRACT FROM AUTHOR]

Antimony flotation is a complicated industrial process with an unknown system structure. Manual manipulation is still widely used by observing the froth appearance, which relies on operators' experience. Therefore, this paper proposes a reagent predictive control strategy for the antimony flotation process based on machine vision, which is an optional replacement of manual control. Froth image is a good indicator to reflect the working conditions of the process. A shape-weighted bubble size distribution (SWBSD) is developed to characterize the froth image feature. The SWBSD combines the bubble size and bubble shape, which differs from the separate use of froth features. Since lots of the froth images can be obtained, a random selection of an image from a froth video as the indicator of the working conditions is not advisable. A typical froth image selection method is proposed to choose the froth image which can best characterize the current working conditions. Due to the unknown system model, multi-output least square support vector regressor (LS-SVR) is used to predict the future image feature according to the current image feature and reagent dosages. Based on the above methods, predictive control technique is employed to calculate the optimal control inputs of the reagents. Simulations using the real-world production data verify the effectiveness of the proposed control strategy. In further, industrial experiments in the antimony flotation plant of China demonstrate that our control strategy improved the tracking performance and decreased the tailing grade, compared with the manual manipulation. [ABSTRACT FROM AUTHOR]