基于图像特征的锑浮选矿浆pH值预测控制

Predictive control of slurry pH based on froth characteristics for antimony flotation process

适宜的矿浆pH值是泡沫浮选高效生产的关键.针对浮选矿浆pH值无法在线检测和控制滞后的问题,提取pH关联泡沫表面敏感特征,建立基于仿射传播聚类的多模型最小二乘支持向量机软测量模型,提出一种基于差分进化的在线支持向量回归pH值预测控制方法,离线建立和在线校正pH值预测模型,采用基于差分进化优化方法求解预测控制决策变量,从而实现pH值实时控制.金锑浮选工业数据表明,所提出的控制策略稳定了矿浆pH值,减少了药剂消耗.

A suitable pH value of the slurry is the key for efficient froth flotation. In the industrial process, it is difficult to measure the pH value online, which causes the control delay. To solve this problem, pH-associated sensitive image features of the froth are obtained, and a soft sensor model-multi-model least squares support vector machine（LSSVM） based on affinity propagation clustering（AP） is introduced. Then, a predictive control strategy based on online support vector regression（OSVR） and differential evolution（DE） optimization for the pH is proposed. The prediction model is built offline and corrected online, and a DE optimization method is used to solve the predictive control problem to find the optimal decision variables, so as to achieve the real-time control of the slurry pH value. The industrial test results in antimony flotation show that the proposed control strategy can stabilize the pH value, and reduce the chemical consumption.