School of Automation, Central South University, Changsha City, 410083, China.
School of Automation, Central South University, Changsha City, 410083, China; Department of Electrical and Computer Engineering, College of Engineering, Wayne State University, Detroit, 48202, United States.
Neural Netw. 2019 Aug;116:1-10. doi: 10.1016/j.neunet.2019.03.007. Epub 2019 Mar 29.
Outlet ferrous ion concentration is an essential indicator to manipulate the goethite process in the zinc hydrometallurgy plant. However, it cannot be measured on-line, which leads to the delay of this feedback information. In this study, a self-adjusting structure radial basis function neural network (SAS-RBFNN) is developed to predict the outlet ferrous ion concentration on-line. First, a supervised cluster algorithm is proposed to initialize the RBFNN. Then, the network structure is adjusted by the developed self-adjusting structure mechanism. This mechanism can merge or divide the hidden neurons according to the distance of the clusters to achieve the adaptability of the RBFNN. Finally, the connection weights are determined by the gradient-based algorithm. The convergence of the SAS-RBFNN is analyzed by the Lyapunov criterion. A simulation for a benchmark problem shows the effectiveness of the proposed network. The SAS-RBFNN is then applied to predict the outlet ferrous ion concentration in the goethite process. The results demonstrate that this network can provide a more accurate prediction than the mathematical model, even under the fluctuating production condition.
出口亚铁离子浓度是操纵锌湿法冶金厂针铁矿工艺的一个重要指标。然而，它不能在线测量，这导致了这种反馈信息的延迟。在本研究中，开发了一种自调整结构径向基函数神经网络（SAS-RBFNN）来在线预测出口亚铁离子浓度。首先，提出了一种有监督聚类算法来初始化 RBFNN。然后，通过所开发的自调整结构机制来调整网络结构。该机制可以根据聚类的距离合并或划分隐藏神经元，从而实现 RBFNN 的适应性。最后，通过基于梯度的算法确定连接权重。通过 Lyapunov 准则分析了 SAS-RBFNN 的收敛性。基准问题的仿真表明了所提出网络的有效性。然后将 SAS-RBFNN 应用于预测针铁矿工艺中的出口亚铁离子浓度。结果表明，该网络即使在波动的生产条件下，也能提供比数学模型更准确的预测。
