摘要
利用时间序列预测,针对某进口铁矿石卸载时的在线粒度检测结果,应用MATLAB语言,分别采用自回归移动预测模型、特征点聚类法、双窗口贝叶斯后验检验法3种模型,利用小波分解的高通软阈值和相关特征参数预测其品位波动情况,然后根据预测的品位波动情况按相关标准规定制订取样方案。该方法简单易用,可以节省大量的人力财力。
Based on the on-stream particle-size analysis results of some imported iron ore during unloading,variation in the grade of iron ore was predicted by using time series prediction technofogy and MATLAB through three models （autoregressive integrated moving average model, feature points clustering method and the double window Bayesian posterior estimation ）,respectively, based on the high-pass soft-threshofd and related parameters of wavelet decomposition. This prediction was then taken as a basis for developing a sampling scheme. This method,being simple and easy to operate,can save both manpower and material resources.
出处
《矿冶工程》
CSCD
北大核心
2017年第1期96-99,102,共5页
Mining and Metallurgical Engineering
基金
国家质检总局计划科研项目(2012IK045)
关键词
小波分析
时间序列
铁矿
品位波动
预测
wavelet analysis
time series
iron ore
quality variation
prediction
