基于跨域流形正则化特征域适应的浮选工况识别  

Identification of flotation working condition based on feature domain adaptation of cross-domain manifold regularization

作　　者：安迪 王姝[1] 关展旭 刘尧 张林[1] AN Di;WANG Shuy;GUAN Zhan-xu;LIU Yao;ZHANG Lin(College of Information Science and Engineering,Northeastern University,Shenyang 110819,China)

机构地区：[1]东北大学信息科学与工程学院,沈阳110819

出　　处：《控制与决策》2023年第9期2597-2605,共9页Control and Decision

基　　金：国家重点研发计划项目(2021YFF0602404);国家自然科学基金项目(61873053,61621004)。

摘　　要：针对浮选过程的故障工况信息不足难以建立准确识别模型,导致调整浮选生产工况不及时,从而无法正常稳定运行的问题,提出一种基于跨域流形正则化特征域适应方法.该方法将已有相似完备浮选过程积累的丰富工况信息作为源域迁移至未建模的不完备浮选过程的目标域中,首先,通过最大域内类密度和局部流形正则化约束分别保留原始判别信息和维持域内邻域结构信息不变,从而提取完备工况与不完备工况域间的特征并投影至公共子空间;然后,由最大均值差异缩小源域与目标域间分布差异,建立分类识别模型,再结合D-S证据理论,融合浮选过程泡沫的静态特征与动态特征信息,提高对不完备浮选过程工况识别的泛化能力,保证得到较好的识别分类效果;最后,通过仿真实验验证所提出方法的有效性.Aiming at the problem that the flotation process is difficult to establish an accurate identification model due to insufficient fault condition information,which leads to the delay in adjusting the flotation production conditions and the failure to run statically in the normal state,this paper proposes a feature transfer learning method based on cross-domain manifold regularization(CDMRFTL).In this method,the rich and complete working condition information accumulated by the existing similar complete flotation process is transferred as the source domain to the target domain of the incomplete unmodeled flotation process.First,the common features between the complete working conditions and the incomplete working conditions are extracted and are mapped to the common subspace through the largest domain class density and partial manifold regularization,to constraint discriminant information and retain the original unchanged in neighborhood domain structure information.Then,narrowing the difference of distribution between source domain and target domain by the largest average differences,the classification and recognition model is established.Next,D-S evidence theory is combined to fuse the apparent characteristics and depth characteristics of the foam in the flotation process to improve the generalization ability of incomplete flotation process condition recognition and ensure better recognition and classification effect.Finally,the effectiveness of the proposed method is verified by simulation experiments.

关 键 词：铜浮选过程 迁移学习 流形正则化 D-S理论 工况识别 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]