Analysis of dynamic texture features of floatation froth images based on space-time characteristics of complex networks

MA Ailian; XU Degang; XIE Yongfang; YANG Chunhua; GUI Weihua

doi:10.11949/j.issn.0438-1157.20161632

您当前的位置：

首页 >

文章列表页 >

Analysis of dynamic texture features of floatation froth images based on space-time characteristics of complex networks

更新时间：2025-12-10

- Analysis of dynamic texture features of floatation froth images based on space-time characteristics of complex networks
- CIESC Journal Issue 3, Pages: 1023-1031(2017)
- 作者机构：
  
  中南大学信息科学与工程学院,湖南,长沙,410083
- 作者简介：
- 基金信息：
- DOI：10.11949/j.issn.0438-1157.20161632
  CLC： Q028.8
- Online First：05 March 2017，
  
  Published：05 March 2017
- 稿件说明：
移动端阅览
MA Ailian, XU Degang, XIE Yongfang, et al. Analysis of dynamic texture features of floatation froth images based on space-time characteristics of complex networks[J]. CIESC Journal, 2017, (3): 1023-1031.
DOI：

MA Ailian, XU Degang, XIE Yongfang, et al. Analysis of dynamic texture features of floatation froth images based on space-time characteristics of complex networks[J]. CIESC Journal, 2017, (3): 1023-1031. DOI： 10.11949/j.issn.0438-1157.20161632.

摘要

基于机器视觉的浮选过程监控方法已经被广泛应用于浮选过程中，泡沫表面纹理特征是过程监控的关键视觉特征之一。当前静态纹理特征只能从空间维度描述图像特征，在时间维度上刻画图像序列的内在变化特性存在不足，不能准确反映浮选泡沫浮选过程动态特性。提出了基于复杂网络时空特性的泡沫图像序列动态纹理特征方法。通过将每帧图像的像素点映射到网络各节点，利用邻接矩阵建立复杂网络模型和网络权值动态演化反应不同时刻的图像特征，基于复杂网络时空特性提取泡沫图像序列的动态纹理特征。结合实际生产数据进行仿真验证，实验结果表明该方法可准确识别浮选动态状况，为浮选生产过程的实时调节提供重要的指导信息。

Abstract

Methods for monitoring flotation processes based on machine vision has been widely used

which surface texture feature of froths is one of the key visual parameters in process monitoring. Static texture features can only describe images in space dimensions but do not well describe inherent variation characteristics of the image sequence in time dimension

so they can not accurately reflect dynamic characteristics of froths in flotation process. An extraction and analysis method for dynamic texture features of flotation froth images was proposed on a basis of space-time characteristics of complex networks. After pixels of each image were mapped into nodes of complex networks

a complex network model was established by adjacent matrix. The image characteristics at different time were described by network-weighted dynamic evolution and dynamic texture characteristics of image sequences were obtained by the space-time characteristics of complex networks. Simulation results with actual production data showed that the method could accurately identify flotation dynamic conditions and provide guidance for instant regulation of flotation process.

关键词

Keywords

references

Views

243

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A dual-stream multirate GRU soft sensor modeling based on data chunk strategy

ESO-based action dependent heuristic dynamic programming control and its application in a four-stage CSTR process

TTPA-LSTM soft sensor modeling for multi-sampling rate data

ONLSTM soft sensor modeling based on time series transfer and dual stream weighting

Local time difference constrained neighborhood preserving embedding algorithm for fault detection

Related Author

ZHANG Zhen

SHI Xudong

WANG Fazheng

XIONG Weili

CHEN Xun

LI Dazi

SUI Lin

XIONG Weili

Related Institution

School of Internet of Things Engineering, Jiangnan University

Key Laboratory of Advanced Process Control for Industry (Ministry of Education), Jiangnan University

College of Information Science and Technology, Beijing University of Chemical Technology

Key Laboratory of Advanced Process Control for Industry, Ministry of Education, Jiangnan University

Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology

⁰