基于RBF网络的稀土萃取过程组分含量软测量

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

针对稀土萃取分离过程元素组分含量在线检测的难题,提出稀土萃取过程组分含量的RBF神经网络软测量方法。应用K-均值聚类算法确定软测量模型的结构和参数,并开展所提软测量方法在某公司稀土萃取分离过程组分含量监测中的应用实验研究,结果表明,所提出的软测量方法是可行、有效的,能较好地解决稀土萃取过程中元素组分含量的监测。

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. The parameters of soft--sensor are optimized by the K--means clustering 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 of rare earth in the countercurrent extraction.