基于控制图和神经网络的印刷过程质量智能监控技术  

Intelligent Monitoring Technology of Printing Process Quality Based on Control Chart and Neural Network

作　　者：初红艳[1] 李鹏[1] 蔡力钢[1] 

机构地区：[1]北京工业大学机械工程与应用电子技术学院北京市先进制造技术重点实验室,北京100124

出　　处：《北京工业大学学报》2012年第3期340-344,共5页Journal of Beijing University of Technology

基　　金：国家'十一五'科技支撑计划课题资助项目(2006BAF03B01);北京市教委科研计划资助项目(KM200910005006)

摘　　要：将SPC方法和BP神经网络技术相结合,应用于印刷过程,研究了印刷过程质量智能监控技术.分析影响印刷品质量的因素,设计印刷质量管理数据库;根据印刷过程特点,结合印刷质量的检测方法,确定控制图的绘图方案;通过实验,建立4个BP神经网络模型,实现控制图模式智能识别及异常模式特征参数的估计,并进一步分析异常原因及诊断建议.在分析研究的基础上,开发了印刷过程质量智能监控系统,对提高印刷过程的自动化和智能化水平具有重要的意义.This study applies the SPC method and BP neural network to a printing process, and intelligent monitoring technology of printing process quality is researched. The factors that influence the prints quality are analyzed, and the printing quality management database is established. According tothe characteristics of the control chart for printing models are established printing process and method of printing quality detection, the drawing plan of process is also established. Through the experiments, four BP neural network to realize intelligent recognition of control chart patterns and characteristicparameters estimation of abnormal patterns, and the abnormal causes and suggestions are further obtained. The intelligent monitoring system for printing process quality is developed based on analysis and research, and it is of great significance to improve the degree of automation and intelligence of the printing process.

关 键 词：SPC控制图 BP神经网络 数据库 印刷过程质量 

分 类 号：TS805.3[轻工技术与工程] TH165.4[机械工程—机械制造及自动化]