On-line Quality Intelligent Diagnosis for Multi-variety and Small-batch Dynamic Process Based on MSVM

Abstract

Abstract:

An on-line quality intelligent diagnosis method was proposed based on MSVM. In off-line training, the feature data was extracted using wavelet reconstruction of quality patterns, the MSVM recognition model and estimation model then were trained and tested.In online diagnosis, the abnormal pattern and the parameter of data flow in “monitoring window” were recognized and estimated by the trained recognition model and estimation model, then the dynamic process was diagnosed by the construed diagnosis library. Finally, the proposed method is applied to online diagnosis the precision-axis machining process, and the results of application example show its effectiveness.

Key words: multi-variety and small-batch, quality abnormal pattern, wavelet reconstruction, multi support vector machine(MSVM), on-line intelligent diagnosis

摘要：

提出了基于多分类支持向量机(MSVM)的多品种、小批量动态过程在线质量智能诊断方法。离线训练时，提取异常模式仿真数据的小波重构特征，对 MSVM识别和估计模型进行训练和测试，同时建立异常因素诊断库;在线诊断时，对“监控窗口”数据特征的过程模式及参数进行识别与估计，而后利用异常因素诊断库实现对多品种、小批量动态过程实时在线智能诊断。某精密轴加工过程实例验证了该智能诊断方法的有效性。

关键词: 多品种小批量, 质量异常模式, 小波重构, 分类支持向量机(MSVM), 在线智能诊断

CLC Number:

Liu Yumin, Zhou Haofei. On-line Quality Intelligent Diagnosis for Multi-variety and Small-batch Dynamic Process Based on MSVM[J]. China Mechanical Engineering, 2015, 26(17): 2356-2363.

刘玉敏, 周昊飞. 基于MSVM的多品种小批量动态过程在线质量智能诊断[J]. 中国机械工程, 2015, 26(17): 2356-2363.

References

[1]Gu K,Jia X,You H.A T-chart for Monitoring Multi-variety and Small Batch Production Run[J].Quality and Reliability Engineering International,2013,30(2):287-299.
[2]曹军，尹超，刘飞. 多品种小批量机加工车间关键工序动态SPC研究及应用[J].中国机械工程,2011,22(23):2822-2827.
Cao Jun,Yin Chao,Liu Fei. Research and Application on Dynamic Statistical Process Control of Key Process in Multi-varieties and Small-batch Machining Workshop[J]. China Mechanical Engineering, 2011,22(23):2822-2827.
[3]仲建兰，马义中.面向小批量生产过程的两阶段串联可修系统SPC与维修策略整合优化[J].计算机集成制造系统,2014,20(8):1959-1967.
Zhong Jianlan,Ma Yizhong. Integrated Optimization for SPC and Maintenance Strategy of Two-stage Series Repairable Systems Oriented to Short-run Production[J].Computer Integrated Manufacturing Systems, 2014,20(8):1959-1967.
[4]Petros X, Talayeh R. A Weighted Support Vector Machine Method for Control Chart Pattern Recognition[J]. Computers & Industrial Engineering, 2014, 70 :134-149.
[5]吴常坤，赵丽萍.基于小波分析和SVM 的控制图模式识别[J].中国机械工程，2010, 21(13):1572-1576.
Wu Changkun, Zhao Liping. Control Chart Pattern Recognition Based on Wavelet Analysis and SVM[J]. China Mechanical Engineering, 2010, 21(13):1572-1576.

[6]Shichang D, Delin H. Recognition of Concurrent Control Chart Patterns Using Wavelet Transform Decomposition and Multiclass Support Vector Machines[J].Computers & Industrial Engineering,2013, 66: 683-695.
[7]Ata E, Jalil A,Vahid R. Recognition of Control Chart Patterns Using an Intelligent Technique[J]. Applied Soft Computing,2013, 13: 2970-2980.
[8]Susanta K G, Shankar C. Recognition of Control Chart Patterns Using Improved Selection of Features[J].Computers & Industrial Engineering, 2009, 56:1577-1588.
[9]Vahid R, Ata E. Control Chart Pattern Recognition Using a Novel Hybrid Intelligent Method[J]. Applied Soft Computing, 2011,11: 2676-2686.
[10]Ata E,Vahid R. Control Chart Pattern Recognition Using an Optimized Neural Network and Efficient Features[J].ISA Transactions,2010,49:387-393.
[11]Vahid R,Ata E. Application of the PSO-SVM Model for Recognition of Control Chart Patterns[J]. ISA Transactions, 2010, 49:577-586.
[12]乐清洪，滕霖. 质量控制图在线智能诊断分析系统[J]. 计算机集成制造系统, 2004,10(12):1583-1487.
Le Qinghong, Teng Lin. On-line Intelligent Diagnosis and Analysis System for Quality Control Charts[J]. Computer Integrated Manufacturing Systems, 2004,10(12):1583-1487.
[13]吴少雄. 智能统计工序质量控制的体系研究[J]. 计算机集成制造系统, 2006,12(11):1832-1837.
Wu Shaoxiong. Intelligent Statistical Process Control System[J]. Computer Integrated Manufacturing Systems, 2006,12(11):1832-1837.
[14]王明刚，朱永忠，王峰.SVM 在监控小批量生产中的应用及比较分析[J].重庆大学学报（自然科学版）,2014,28(3):140-144.
Wang Minggang,Zhu Yongzhong,Wang Feng. Comparison Analysis and Application of SVM in the Monitor of Small Batch Production[J].Journal of Chongqing University of Technology(Natural Science), 2014,28 (3):140-144.
[15]刘玉敏，周昊飞.基于多特征的PSO-MSVM动态过程质量异常模式识别[J].计算机应用研究,2015,32(1): 124-129.
Liu Yumin, Zhou Haofei. Recognition of Quality Abnormal Patterns for Dynamic Process Based on Multi-features with PSO-MSVM[J]. Application Research of Computers,2015, 32(3):713-716.
[16]侯世旺，同淑荣.基于小波重构的控制图并发异常模式识别研究[J].计算机工程与应用,2008,44(28):18-21.
Hou Shiwang,Tong Shurong.Wavelet-reconstruction Based Recognition Method for Control Charts Concurrent Abnormal Patterns[J]. Computer Engineering and Applications, 2008,44 (28):18-21.
[17]李诚，张宏烈. 混合智能算法的控制图模式识别仿真研究[J].计算机仿真,2013,10(30):345-349.
Li Cheng，Zhang Honglie. Simulation on Pattern Recognition of Control Chart Based on Hybrid Intelligent Algorithm[J].Computer Simulation, 2013,10(30):345-349.
[18]Liu Yumin, Zhou Haofei. MSVM Recognition Model for Dynamic Process Abnormal Pattern Based on Multi-kernel Functions[J]. Journal of Systems Science and Information, 2014, 2(5):473-480.