Please wait a minute...
浙江大学学报(工学版)
J4  2011, Vol. 45 Issue (12): 2115-2119    DOI: 10.3785/j.issn.1008-973X.2011.12.008
自动化技术     
基于泡沫图像特征加权SVM的浮选工况识别
任会峰, 阳春华, 周璇, 桂卫华, 鄢锋
中南大学 信息科学与工程学院,湖南 长沙 410083
Froth image feature weighted SVM based working condition
recognition for flotation process
REN Hui-feng, YANG Chun-hua, ZHOU Xuan, GUI Wei-hua, YAN Feng
School of Information Science and Engineering, Central South University, Changsha 410083, China
 全文: PDF  HTML
摘要：

针对浮选泡沫视觉特征的多样性和重要度差异以及浮选工况样本数分布不平衡等问题,提出一种基于在线泡沫视觉表观特征加权支持向量机的浮选工况识别方法.通过色彩空间变换,在CIE-Lab空间计算泡沫颜色,采用多方向融合的空间灰度共生矩阵提取泡沫纹理特征,以视觉特征的信息增益评价该特征的重要度,再利用不同工况的样本数加权策略消除样本数不平衡的影响,采用支持向量机方法实现了浮选工况的自动识别.工业运行数据测试结果表明：该方法能够在线识别浮选工况,自动识别准确率达98%,比人工识别率高6%,比传统灰度共生矩阵方法高2%.
Abstract:

Considering the diversity and different importance of visual features and the imbalance of sample distribution, a working condition recognition method for froth flotation process was presented. Firstly, froth color was calculated in CIE-Lab according to color space conversion, and texture were extracted based on four-direction fused space gray co-occurrence matrix. Then， information entropy was introduced to evaluate the feature’s importance via information gain. Finally, the working condition recognition model was established based on support vector machines using sample weighted strategy to eliminate the imbalance of sample distribution. The experimental results of industrial operation data show that the proposed method can accomplish on-line monitoring of the flotation working condition automatically with identification accuracy of 98%, which is 6% higher than the manual recognition and 2% higher than the traditional Gray level co-occurrence matrix (GLCM) method.
出版日期: 2011-12-01
:  TP 274.3  
基金资助:

国家自然科学基金资助项目（61071176）；国家“863”高技术研究发展计划资助项目（2009AA04Z124）；国家杰出青年科学基金资助项目（61025015）.
通讯作者: 阳春华,女,教授,博导.     E-mail: ychh@csu.edu.cn
作者简介: 任会峰（1981—）,男,博士生,从事模式识别与图像处理的研究.E-mail: renhf316@163.com
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　

引用本文:

任会峰, 阳春华, 周璇, 桂卫华, 鄢锋. 基于泡沫图像特征加权SVM的浮选工况识别[J]. J4, 2011, 45(12): 2115-2119.

REN Hui-feng, YANG Chun-hua, ZHOU Xuan, GUI Wei-hua, YAN Feng. Froth image feature weighted SVM based working condition
recognition for flotation process. J4, 2011, 45(12): 2115-2119.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2011.12.008    或    https://www.zjujournals.com/eng/CN/Y2011/V45/I12/2115

［1］ 耿增显,柴天佑.基于LSSVM的浮选过程工艺技术指标软测量［J］.系统仿真学报,2008,20(23): 6321-6324.
GENG Zengxian, CHAI Tianyou. Soft sensor of technical indices based on LSSVM for flotation process ［J］. Journal of System Simulation, 2008,20(23): 6321-6324.
［2］ ALDRICH C, MARAIS C, SHEAN B J, et al. Online monitoring and control of froth flotation systems with machine vision: A review［J］.International Journal of Mineral Processing,2010, 96(4): 1-13.
［3］ 阳春华,杨尽英,牟学民,等.基于聚类预分割和高低精度距离重构的彩色浮选泡沫图像分割［J］.电子与信息学报,2008,30(6): 1286-1290.
YANG Chunhua, YANG Jinying, MOU Xuemin, et al. A segmentation method based on clustering presegmentation and highlow scale distance reconstruction for colour froth image ［J］.Journal of Electronics & Information Technology, 2008, 30(6): 1286-1290.
［4］ YANG Chunhua, XU Canhui, MU Xuemin, et al. Bubble size estimation using interfacial morphological information for mineral flotation process monitoring ［J］. Transactions of Nonferrous Metals Society of China, 2009,19(3): 694-699.
［5］ YANG Chunhua, XU Canhui, GUI Weihua, et al. Application of highlight removal and multivariate image analysis to color measurement of flotation bubble images ［J］. International Journal of Imaging Systems and Technology, 2009, 19: 316-322.
［6］ 刘文礼,路迈西,王凡,等.煤泥浮选泡沫图像纹理特征的提取及泡沫状态的识别［J］.化工学报,2003,54(6): 830-835.
LIU Wenli, LU Maixi, WANG Fan, et al. Extraction of textural feature and recognition of coal flotation froth［J］.Journal of Chemical Industry and Engineering (China), 2003,54(6): 830-835.
［7］ FACCO P, TOMBA E, ROSO M, et al. Automatic characterization of nanofiber assemblies by image texture analysis ［J］. Chemometrics and Intelligent Laboratory Systems, 2010, 103(1): 66-75.
［8］ 郑恩辉,许宏,李平,等.基于νSVM的不平衡数据挖掘研究［J］.浙江大学学报：工学版,2006,40(10): 1682-1687.
ZHENG Enhui, XU Hong, LI Ping, et al. Mining knowledge from unbalanced data based on νsupport vector machine［J］. Journal of Zhejiang University: Engineering Science, 2006, 40(10): 1682-1687.
［9］ KARA S, AKSEBZECI B H, KODAZ H, et al. Medical application of information gainbased artificial immune recognition system (IGAIRS): Classification of microorganism species ［J］. Expert System Application, 2009,36: 5168-5172.
［10］ HSU C W, LIN C J. A comparison of methods for multiclass support vector machines ［J］. IEEE Transactions on Neural Networks, 2002, 13(2): 415-425.
No related articles found!