基于多源信号融合的球磨机负荷预测方法研究
|
摘要
针对单一因素的球磨机负荷预测时存在的局限性问题。分别提取磨矿过程中振动、磨音、电流的特征信息值,采用网格搜索与交叉验证相结合的支持向量机(SVM)磨机负荷预测方法判断磨机负荷的类型,并得到基本信度分配函数(mass函数)。通过改进后的D-S证据融合规则,提出了磨机负荷的多源异类信号特征层融合方法,通过实例验证与不同算法间对比分析,表明该方法应用于磨机负荷预测时,得到的融合结果置信度更高、收敛速度更快、稳定性更强。
For the limitation of the single-factor ball mill load prediction, we extracted the characteristic information values of vibration, grinding and current in the grinding process, and used the support vector machine(SVM) combined with grid search and cross-validation for grinding machine load prediction. By determining the type of mill load, we obtained the basic reliability distribution function(mass function). Through the improved D-S evidence fusion rule, a multi-source heterogeneous signal feature layer fusion method for mill load was proposed. Through the example verification and comparison between different algorithms, we found when the method is applied to the mill load prediction, higher confidence, faster convergence, and greater stability fusion results are obtained.
For the limitation of the single-factor ball mill load prediction, we extracted the characteristic information values of vibration, grinding and current in the grinding process, and used the support vector machine(SVM) combined with grid search and cross-validation for grinding machine load prediction. By determining the type of mill load, we obtained the basic reliability distribution function(mass function). Through the improved D-S evidence fusion rule, a multi-source heterogeneous signal feature layer fusion method for mill load was proposed. Through the example verification and comparison between different algorithms, we found when the method is applied to the mill load prediction, higher confidence, faster convergence, and greater stability fusion results are obtained.
引文
[1]王飞.基于频谱分析的磨机负荷检测方法研究[D].重庆:重庆邮电大学,2016.
[2]沙亚红,常太华,常建平.球磨机负荷检测方法综述[J].现代电力,2006,23(4):66-69.SHA Yahong,CHANG Taihua,CHANG Jianping.Measure methods of ball mill’s load[J].Modern Electric Power,2006,23(4):66-69.
[3]孙景敏,李世厚.基于信息融合技术的球磨机三因素负荷检测研究[J].云南冶金,2008,37(1):16-19.SUN Jingmin,LI Shihou.Research for three factors on load examination of the ball mill based on information fusion techniques[J].Yunnan Metallurgy,2008,37(1):16-19.
[4]罗小燕,陈慧明,卢小江,等.基于网格搜索与交叉验证的SVM磨机负荷预测[J].中国测试,2017,43(1):132-135.LUO Xiaoyan,CHEN Huiming,LU Xiaojiang,et al.Forecast of SVM mill load based on grid search and cross validation[J].China Measurement&Test,2017,43(1):132-135.
[5]刘芳.基于D-S证据理论的冲突证据分析研究[D].济南:山东师范大学,2016.
[6]鹿高娜.基于D-S证据理论的融合事件检测算法研究[D].北京:北京交通大学,2016.
[7]罗小燕,卢小江,熊洋,等.小波分析球磨机轴承振动信号特征提取方法[J].噪声与振动控制,2016,36(1):148-152.LUO Xiaoyan,LU Xiaojiang,XIONG Yang,et al.Feature extraction method for ball-mill bearing’s vibration signals using wavelet analysis[J].Noise and Vibration Control,2016,36(1):148-152.
[8]孙全,叶秀清,顾伟康.一种新的基于证据理论的合成公式[J].电子学报,2000,28(8):178-181.SUN Quan,YE Xiuqing,GU Weikang.A new combination rules of evidence theory[J].Acta Electronica Sinica,2000,28(8):178-181.
[9]邓勇,施文康.一种改进的证据推理组合规则[J].上海交通大学学报,2003,37(8):534-536.DENG Yong,SHI Wenkang.A modified combination rule of evidence theory[J].Journal of Shanghai Jiao Tong University,2003,37(8):534-536.
[10]MURPHY C K.Combining belief functions when evidence conflicts[J].Decision Support Systems,2000,29(1):1-9.
[2]沙亚红,常太华,常建平.球磨机负荷检测方法综述[J].现代电力,2006,23(4):66-69.SHA Yahong,CHANG Taihua,CHANG Jianping.Measure methods of ball mill’s load[J].Modern Electric Power,2006,23(4):66-69.
[3]孙景敏,李世厚.基于信息融合技术的球磨机三因素负荷检测研究[J].云南冶金,2008,37(1):16-19.SUN Jingmin,LI Shihou.Research for three factors on load examination of the ball mill based on information fusion techniques[J].Yunnan Metallurgy,2008,37(1):16-19.
[4]罗小燕,陈慧明,卢小江,等.基于网格搜索与交叉验证的SVM磨机负荷预测[J].中国测试,2017,43(1):132-135.LUO Xiaoyan,CHEN Huiming,LU Xiaojiang,et al.Forecast of SVM mill load based on grid search and cross validation[J].China Measurement&Test,2017,43(1):132-135.
[5]刘芳.基于D-S证据理论的冲突证据分析研究[D].济南:山东师范大学,2016.
[6]鹿高娜.基于D-S证据理论的融合事件检测算法研究[D].北京:北京交通大学,2016.
[7]罗小燕,卢小江,熊洋,等.小波分析球磨机轴承振动信号特征提取方法[J].噪声与振动控制,2016,36(1):148-152.LUO Xiaoyan,LU Xiaojiang,XIONG Yang,et al.Feature extraction method for ball-mill bearing’s vibration signals using wavelet analysis[J].Noise and Vibration Control,2016,36(1):148-152.
[8]孙全,叶秀清,顾伟康.一种新的基于证据理论的合成公式[J].电子学报,2000,28(8):178-181.SUN Quan,YE Xiuqing,GU Weikang.A new combination rules of evidence theory[J].Acta Electronica Sinica,2000,28(8):178-181.
[9]邓勇,施文康.一种改进的证据推理组合规则[J].上海交通大学学报,2003,37(8):534-536.DENG Yong,SHI Wenkang.A modified combination rule of evidence theory[J].Journal of Shanghai Jiao Tong University,2003,37(8):534-536.
[10]MURPHY C K.Combining belief functions when evidence conflicts[J].Decision Support Systems,2000,29(1):1-9.