炼铜转炉粗铜成分混沌时间序列的软测量模型及应用  

Soft-Sensing Model of Chaos Time Series of Crude Copper Composition in Copper Convertor and Its Application

作　　者：鄂加强[1] 王耀南[1] 龚金科[2] 李春生[1] 梅炽[3] 

机构地区：[1]湖南大学电气与信息工程学院,湖南长沙410082 [2]湖南大学机械与汽车工程学院,湖南长沙410082 [3]中南大学能源与动力工程学院,湖南长沙410083

出　　处：《华南理工大学学报（自然科学版）》2006年第1期52-56,共5页Journal of South China University of Technology(Natural Science Edition)

基　　金：国家自然科学基金资助项目(60375001)

摘　　要：将转炉产粗铜成分的以往化验数据作为二次变量,化验数据严重滞后的当前炉次粗铜成分作为主导变量,并以延迟时间τ=2(炉次)将转炉粗铜成分时间序列分成两个子时间序列,采用重构相空间理论、最大Lyapunov指数方法和样本及时更新的办法,建立了一种仅对当前炉次的炼铜转炉粗铜成分进行软测量的混沌时间序列软测量模型.实验结果表明,该软测量模型能快速得出转炉当前炉次的粗铜成分数据,具有很高的精度.A new soft-sensing model of current crude copper composition based on the chaos time series of foregone crude copper composition was established by using the phase-space reconstruction theory and the method of maximum Lyapunov exponent and by updating samples in time. In this soft-sensing model, foregoing assay data of crude copper composition were regarded as the secondary variables, the assay data of crude copper composition in current copper convertor were taken as the primary variables because of its great delay, and the chaos time series of foregone crude copper composition was divided into two sub-series via the time lag T = 2 furnace orders. Experimental results indicate that the crude copper composition in current copper convertor can be quickly and precisely determined by the proposed soft-sensing model.

关 键 词：炼铜转炉 成分测量 混沌时间序列 LYAPUNOV指数 软测量 重构相空间理论 

分 类 号：TF811[冶金工程—有色金属冶金] O415.5[理学—理论物理]