摘要
电熔镁炉制备电熔镁砂的工艺过程中,会交替出现正常熔炼、加料和欠烧等不同工况,针对不同的工况需要采取相应的处理方式来保证生产过程的正常进行.目前,工况的识别主要依靠人工完成,这种方式存在工人劳动强度大、容易漏检误检等问题.本文依据不同工况下炉口火焰具有不同的动态可视化特征,提出一种基于动态纹理的工况识别技术.首先,建立炉口火焰的线性动态系统模型来刻画纹理的动态特性,然后,设计基于子空间主要角度的核函数来度量火焰动态模型相似度.对比实验表明本文设计的基于子空间主要角度的工况分类器具有更好的分类精度及鲁棒性.
In the process of preparing fused magnesia in fused magnesium furnace,different working conditions such as Smelting condition,Feeding condition and Semi-fused condition alternately occur,and corresponding treatment methods are needed for these conditions to ensure the normal production process.At present,the identification of working conditions mainly relies on workers.This way has some problems such as high labor intensity of workers,detection omission and wrong detection.According to different dynamic visualization characteristics of furnace flame under different working conditions,a working conditions recognition technology based on dynamic texture is proposed.First of all,the dynamic characteristics of the textures are portrayed by establishing a linear dynamic system model of the furnace flame.In the next place,a kernel function based on subspace principal angles is designed to measure the similarity of flame dynamic model.The contrast experiments show that working conditions classifier based on the subspace principal angles designed in this paper has better classification accuracy and robustness.
作者
赵磊
卢绍文
郑秀萍
ZHAO Lei;LU Shao-wen;ZHENG Xiu-ping(State Key Laboratory of Synthetical Automation for Process Industries,Northeastern University,Shenyang Liaoning 110819,China)
出处
《控制理论与应用》
EI
CAS
CSCD
北大核心
2019年第9期1565-1572,共8页
Control Theory & Applications
基金
国家自然科学基金项目(61473071,61833004)资助~~
关键词
电熔镁炉
纹理
工况识别
动态模型
线性动态系统
核函数
fused magnesium furnace
textures
working conditions recognition
dynamic models
linear dynamic system
kernel function
作者简介
赵磊,硕士研究生,主要从事机器学习、图像处理等方面的科研工作,E-mail:15247232416@163.com;通信作者:卢绍文,教授,于2006年获伦敦大学皇后玛丽学院电子工程学博士学位,研究领域为工业过程建模与仿真、机器学习,E-mail:lusw@mail.neu.edu.cn;郑秀萍,教授,主要研究方向为流程工业综合自动化系统研究开发与应用、流程工业制造执行系统MES研究与应用和智能优化与智能控制,E-mail:xiupingzheng@mail.neu.edu.cn.
