东北大学学报(自然科学版) ›› 2024, Vol. 45 ›› Issue (9): 1217-1226.DOI: 10.12068/j.issn.1005-3026.2024.09.001

• 信息与控制 •    

基于多源异构信息的浮选过程运行状态评价

刘炎(), 卜齐杰, 赵红晨, 郭鑫   

  1. 东北大学 信息科学与工程学院,辽宁 沈阳 110819
  • 收稿日期:2023-04-26 出版日期:2024-09-15 发布日期:2024-12-16
  • 通讯作者: 刘炎
  • 基金资助:
    国家重点研发计划项目(2021YFF0602404);国家自然科学基金资助项目(62073060)

Operating Performance Assessment of Flotation Process Based on Multi-source Heterogeneous Information

Yan LIU(), Qi-jie BU, Hong-chen ZHAO, Xin GUO   

  1. School of Information Science & Engineering,Northeastern University,Shenyang 110819,China. cn
  • Received:2023-04-26 Online:2024-09-15 Published:2024-12-16
  • Contact: Yan LIU
  • About author:LIU Yan,E-mail:liuyan@ise.neu.edu.

摘要:

针对浮选过程中图像信息和过程数据信息共存且不同运行状态特征差异度小的问题,以深度学习技术为基础,提出了一种新的基于多源异构信息的浮选过程运行状态评价方法.首先,建立一种残差网络(residual network,ResNet),旨在从不同等级的原始图像中提取更具区分度的深层特征.其次,提出一种堆叠稀疏状态相关自编码器(stacked sparse performance?relevant autoencoders,SSPAE)模型,将状态等级标签引入到模型训练中,克服传统自编码器忽视状态相关特性的问题.再次,建立基于注意力机制(attention mechanism,AM)的图像和数据特征融合模型,实现对多源异构信息的合理有效利用,并将融合后的特征输入SoftMax分类器建立运行状态评价模型.最后,利用浮选过程数据进行仿真验证.结果表明,基于本文提出的ResNet-SSPAE-AM模型的评价结果优于其他几种比较方法,说明所提方法在浮选过程运行状态评价中的优越性.

关键词: 运行状态评价, 多源异构信息, 深度学习, 注意力机制, 浮选过程

Abstract:

In view of the coexistence of image information and process data information in flotation process and small differences among features of different operation state, a novel operating performance assessment method based on multi?source heterogeneous information and deep learning was proposed for flotation process. Firstly, a residual network (ResNet) is established to extract deep features with more discrimination from original images of different performance grades. Secondly, a stacked sparse performance?relevant autoencoders (SSPAE) model is proposed, which introduces the state level label into the model training to overcome the problem that the traditional autoencoder ignores the state?related characteristics. Furthermore, an image and data feature fusion model based on attention mechanism (AM) is established, and then the fused features are used as the inputs of the SoftMax classifier to train the operating performance assessment model, realizing the reasonable and effective utilization of the multi?source heterogeneous information. Finally, the flotation process data is used for simulation verification. The simulation results show that the proposed method is superior to other comparative methods, verifying its superiority in evaluating the operating performance of flotation processes.

Key words: operating performance assessment, multi?source heterogeneous information, deep learning, attention mechanism, flotation process

中图分类号: