Component Content Soft-Sensor Based on RBF Neural Network in Rare Earth Countercurrent Extraction Process

In consideration of the difficulty in online measuring the component content in rare earth extraction separation production process, the soft-sensor method based on the radial basis function (RBF) neural networks is proposed to measure the rare earth component content. The parameters of soft-sensor are optimized by the hierarchical genetic algorithms. In addition, application experiment research of this proposed method is carried out in the rare earth separation production process of a corporation. The results show that this method is effective and can realize online measuring for the component content of rare earth in the countercurrent extraction