摘要
SPC控制图(如EWMA和CUSUM控制图)常用来监控过程均值的漂移,特别是对微小漂移具有较好的敏感性,但对于复杂数据无法进行有效的智能分析和内部规律总结,不能及时报告有失控趋势的样本点。针对上述问题提出一种对监控过程漂移更加敏感、智能化的方法——基于支持向量机(SVM)的分析模式,并对该模型的精度做了相关分析。仿真结果显示:与EWMA和CUSUM控制图相比,该模型能更加及时地发现有失控趋势或失控的样本点。
SPC control chart （such as EWMA and CUSUM control chart） can be used to monitor the process mean,which especially has good sensitivity to small shift.But because these control charts for complex data could not have effective intelligent analysis and internal regularity,and no report of trend of sample points in time,this paper presents a new method for monitoring the process shift more sensitively and intelligently—based on support vector machine （SVM） analysis model,and the precision of the model makes the correlation analysis.Through the simulation,and compared with EWMA and CUSUM control chart methods,results show that the model is better than EWMA and CUSUM control charts can more timely find out trends or out of sample points.
出处
《重庆理工大学学报（自然科学）》
CAS
2014年第3期140-144,共5页
Journal of Chongqing University of Technology：Natural Science
基金
国家自然科学基金资助项目(50979029)
河海大学自然科学基金资助项目(2008431111)
