基于模糊聚类和模糊支持向量机的湿法炼锌净化除钴过程建模

Modeling of cobalt removal purification process in zinc hydrometallurgy based on FCM-SVM

提出了一种基于模糊C-均值(FCM)聚类和模糊支持向量机(SVM)方法相结合的湿法炼锌净化除钴过程建模方法。该方法针对样本空间影响支持向量机泛化性能和样本数量影响计算复杂度的问题,首先采用模糊聚类将学习样本分类,然后在各个类的样本空间内采用模糊支持向量机进行训练,并对各支持向量机模型的输出加权作为过程模型的输出。以净化除钴过程生产数据进行实验验证的结果表明,该方法明显减少了模型的训练时间,模型具有精度高、泛化性能好等特点,可以用于净化过程的优化控制。

A modeling method for cobalt removal purification process in zinc hydrometallurgy based on the combination of fuzzy C-means （FCM） clustering and fuzzy support vector machine （SVM） is proposed. Considering that the sample space influencs the performance of SVM and the number of samples influences the computation complexity, the method divides the original sample space into subspaces by the FCM clustering firstly, then, trains the samples in each subspace by the fuzzy SVM, and finally, establishes the process model and takes the weighted output of each fuzzy SVM model as the output of the process model. The experimental results show that the proposed method greatly reduces the training time. Moreover, the proposed model has the high accuracy and good generalization performance. It can be used for operation optimization of the purification process of cobalt removal.