An improved RNN modeling algorithm for flotation process of copper-silver ore
Kang Wang, Liwei Pang, Xiaoli Li, Xin Zhao
Abstract
Concentrate grade is an important evaluation index in the flotation process, which reflects the rich degree of specific recovery components in the concentrate. In this paper, the copper and silver ore grades in LinXi Mining Co., Ltd are taken as the research object. Given the difficulty in identifying the flotation process through mechanism modeling, the recurrent neural network model of the flotation process is established by using the idea of data-driven. Considering that the learning parameters are randomly selected, an improved RNN model is proposed by introducing the index function which optimizes the model parameters to obtain better modeling performance. The simulation results show that the improved recurrent neural network model can effectively identify the flotation process compared with the traditional RNN model and ARMAX model. Key Words: Flotation process, Recurrent neural network, Concentrate grade, Data driven, Model optimization