控制理论与应用2012，Vol.29Issue(2)：183-191,9.
基于振动频谱的磨矿过程球磨机负荷参数集成建模方法
Ensemble modeling for parameters of ballmill load in grinding process based on frequency spectrum of shell vibration
摘要
Abstract
The mill load （ML） of a wet ballmill is generally determined by using the lowsensitivity shaft vibration signal, acoustical signal from mill shell and mill power during the grinding process. The result doesn＇t reflect the status of the load parameters inside the ballmill. To deal with this problem, we propose the ensemble modeling method based on the highsensitivity frequencyspectrum signal from the shell vibration. According to the grinding mechanism, the vibration frequency spectrum is automatically partitioned into several different spectral segments with different physical meanings based on the frequencyspectrum clustering method. The submodel of ML parameters in each spectral segment is built by using the kernel partial leastsquares （KPLS） algorithm. The final ML parameters ensemble prediction model is obtained as the weighed combination of submodels. Each initial weighting coefficient is determined from the information entropy of the training data prediction error of the corresponding submodel. The weighting coefficient can be adaptively updated on line based on the variation of prediction error of the submodel. Simulation results demonstrate the validity of the proposed method关键词
磨矿过程/球磨机负荷/频谱聚类/核偏最小二乘/信息熵/集成建模Key words
grinding process/ball-mill load/frequency-spectrum clustering/kernel partial least squares/informationentropy/ensemble model分类
信息技术与安全科学引用本文复制引用
汤健,柴天佑,赵立杰,岳恒,郑秀萍：..基于振动频谱的磨矿过程球磨机负荷参数集成建模方法[J].控制理论与应用,2012,29(2):183-191,9.基金项目
国家自然科学基金资助项目 （）
中国博士后自然科学基金资助项目 （）
国冢自然科字基金资助项目 （）
国家科技支撑计划资助项目（2008BAB31803）. （）
