基于QPSO优化RBF网络的稀土萃取组分含量软测量

Component Content Soft-sensor by RBF Based on QPSO in Rare Earth Extraction

径向基函数用于软测量模型建立,具有最佳非线性逼近性能力和全局最优特性,其结构简单,训练速度快。本文是为了解决稀土萃取过程中组分含量在线检测的问题,将RBF网络应用于此过程中建立软测量模型,采用量子粒子群优化RBF网络参数提高模型的精度和泛化能力。仿真结果表明,基于粒子群优化RBF软测量方法用于稀土萃取过程中组分含量在线估计,是一种有效的方法。

With the best nonlinear approximation and global optimum characteristic capability,simple structure and quickly trained Speed,radial basis function is better chioce for the modeling of the soft-sensor.In consideration of the online measurement of the component content in rare earth extraction separation process,algorithm of RBF neural network is applied to the modeling of the rare earth extraction separation process.Particle Swarm Optimizatiom algorithm was proposed to select the parameters of RBF.This method contributed to the distinct improvement of precision and generalization ability of the soft sensor model based on RBF.It shows that the proposed method had good approximation and well generalization ability,the method based on QPOS-RBF is more effective to realize online prediction of the component content in the rare earth extraction process than the mathod based on RBF.