基于相关向量机的硫泡沫浮选液位软测量

Soft Sensor of Sulfur Flotation Froth Level Based on Relevance Vector Machine

针对硫浮选过程中常规检测方法难以准确检测浮选槽液位的缺陷,提出一种基于相关向量机(RVM)的浮选液位软测量方法。该方法基于采集的浮选泡沫表层图像,通过提取硫浮选泡沫溢流速度和泡沫稳定度动态图像特征,融合浮选过程充气量、矿浆流量等过程参数,结合RVM建模思想,实现硫浮选过程中浮选槽液位的预测。工业数据仿真结果验证了所提方法的有效性、可行性。

As conventional froth level detect method in the sulfur flotation process is not reliable, a new modeling method based on rele- vance vector machine is proposed. This method makes use of the froth flotation surface imagines. By extracting froth overflow rate and foam stability dynamic characteristics, combined with the air rate and the slurry flow rate parameters of the flotation process and using the relevance vector machine modeling idea, this model can predict the froth level of the sulfur flotation. The results of industrial data simulation indicate that the proposed method is effective and feasible.