Pattern Recognition for Printing Quality Control Chart Based on MC Method and BP Neural Network
-
摘要: 建立了印刷质量控制图模式的数学模型,基于Monte Carlo(MC)方法模拟印刷质量数据,生成仿真样本,并使用标准变换和线性编码方法进行预处理,既不失样本数据的内在特征,又大大降低了数据复杂度.通过实验确定了结构为24-18-16-4的4层反向传播(back propagation,BP)网络模型,并采用比例共轭梯度训练算法,提高了网络的稳定性和收敛速度.在对控制图模式识别时,采用不同训练样本容量的实验方案,模式识别正确率达95.87%.结果表明,该方法可以提高印刷企业的质量控制水平和自动化程度.
-
关键词:
- 印刷质量控制图 /
- 模式识别 /
- Monte Carlo方法 /
- 反向传播神经网络
Abstract: A mathematical model for patterns of the printing quality control chart is established,and the data of printing quality is simulated based on Monte Carlo method,Then the complexity of the sample data is reduced by using the method of standard transformation and linear encoding.A 4-layer BP neural network model,as 24-18-16-4,is established through the experiments,and a scaled conjugated gradient training algorithm is adopted to enhance the stability and convergence of the network.The paper uses different capacity of training samples in pattern recognition for control chart,and the recognition accuracy achieves 95.87%.Results of experiments show that this method can improve the level of quality control and degree of automation for printing enterprise. -
-
[1] 王毓芳,郝凤.过程控制与统计技术[M].北京:中国计量出版社,2001. [2] 赵艳东.统计过程控制(SPC)方法在印刷质量管理中的应用研究[D].武汉:武汉大学印刷与包装系,2005.ZHAO Yan-dong.Study of statistical process control(SPC)application in printing quality management[D].Wuhan:Schoolof Printing and Packing,Wuhan University,2005.(in Chinese) [3] 李刚,王霄,蔡兰.基于神经网络的控制图模式识别技术研究[J].制造业自动化,2000,22(5):31-34.LI Gang,WANG Xiao,CAI Lan.Research of control charts pattern Recognition using neural network[J].ManufacturingAutomation,2000,22(5):31-34.(in Chinese) [4] 李孟清,陈志祥.质量控制图中趋势模式的综合识别方法[J].华中理工大学学报,2000,28(5):24-26.LI Meng-qing,CHEN Zhi-xiang.A synthetical approach of fuzzy logic and neural network for trend pattern recognition incontrol charts[J].Journal of Huazhong University of Science and Technology,2000,28(5):24-26.(in Chinese) [5] CHENG C S.A neural network approach for the analysis of control chart pattern[J].International Journal of ProductionResearch,1997,35(3):667-697.
[6] 昝涛,费仁元,王民.基于神经网络的控制图异常模式识别研究[J].北京:北京工业大学学报,2006,32(8):673-676.ZAN Tao,FEI Ren-yuan,WANG Min.Research on abnormal pattern recognition for control chart based on neural network[J].Beijing:Journal of Beijing University of Technology,2006,32(8):673-676.(in Chinese) [7] YANG J H,YANG M S.A control chart pattern recognition system using a statistical correlation coefficient method[J].Computers&Industrial Engineering,2005,48(2):205-221.
[8] 乐清洪.智能工序质量控制的理论与方法研究[D].西安:西北工业大学机电工程学院,2002.LE Qing-hong.Research on the theory and methodology of intelligent quality control for machining operations[D].Xi'an:School of Mechatronics Engineering,Northwestern Polytechnical University,2002.(in Chinese) [9] 高清,陈平,马玉林.基于神经网络的质量控制图自动识别技术的研究[J].哈尔滨工业大学学报,1995,27(6):121-124.GAO Qing,CHEN Ping,MA Yu-lin.Artificial neural networks for the identification of quality control charts[J].Journal ofHarbin Institute of Technology,1995,27(6):121-124.(in Chinese) [10] 徐钟济.蒙特卡洛方法[M].上海:上海科学技术出版社,1985. [11] 殷显安.试验模拟的蒙特卡洛方法[J].测试技术学报,1994,8(2):49-51.YIN Xian-an.Monte Carlo method for test simulation[J].Journal of Test and Measurement Technique,1994,8(2):49-51.(in Chinese) [12] 闻新,周露,李翔,等.Matlab神经网络仿真与应用[M].北京:科学出版社,2003:258-284. [13] 初红艳,蔡力钢,郑刚,等.基于Intellitrax的印刷色彩检测与控制系统[J].包装工程,2007,28(10):94-97.CHU Hong-yan,CAI Li-gang,ZHENG Gang,et al.Printing color detection and control system based on intellitrax[J].Packaging Engineering,2007,28(10):94-97.(in Chinese)
计量
- 文章访问数: 22
- HTML全文浏览量: 0
- PDF下载量: 8
下载:
