出厂水泥不同抽样方法误差比较研究  

Research on comparisons among cement sampling methods' error

作　　者：张大康[1] 

机构地区：[1]拉法基瑞安(北京)技术服务有限公司重庆分公司,重庆400010

出　　处：《水泥工程》2009年第3期56-58,共3页Cement Engineering

摘　　要：目前水泥厂对出厂水泥采用的是一种近乎没有限制的"随意"抽样方法,与国家标准采用随机抽样的规定不符。原因主要是随机抽样在水泥厂实际操作中难以实行。应用蒙特卡罗方法模拟了随机抽样、系统抽样、分层抽样、近似系统抽样和分层任意抽样的抽样误差,旨在寻找一种抽样误差不大于随机抽样,而又易于实施的抽样方法。结果表明,五种抽样方法的抽样误差接近。据此,从易于操作的角度提出以近似系统抽样的方法代替随机抽样。At present cement plants use ＂unbending＂ sampling methods which have no limit and are unconformable to the random sampling method in national standard nile. The reason is that the random sampling method is hard to operate in cement real production. To find a right sampling method whose error less than or equal to that of random sampling method and easy to operate, simulated the sampling errors of random sampling, systematic sampling, stratified sampling, approximation systematic sampling and stratified random sampling by Monte Carlo Method. The results show that the five sampling methods have similar errors. Based on that results, suggested replace the random sampling method with approximation systematic sampling method for easy operation.

关 键 词：出厂水泥 抽样方法 抽样误差 蒙特卡罗模拟 

分 类 号：TQ172.66[化学工程—水泥工业]