Component content soft-sensor based on SVM in rare earth countercurrent extraction process

The problems of small sample, non-linearity, high dimensions and local minimal value can be well solved by support vector machine in soft-sensor modeling. In consideration of the online measurement of the component content in rare earth counter-current extraction separation process, two algorithms of SVM and LS_SVM with RBF kennel was applied to the modeling of the rare-earth extraction separation process. Through comparing the simulations of two models, it shows that the component content soft-sensor model based on LS_SVM has both preferable generalization and high velocity. LS_SVM is an effective method for rare-earth extract process soft-sensor.