Articles

Machining Quality Monitoring of Blades and Source Tracing Based on Dynamic Bayesian Network

Expand
  • Key Laboratory of Contemporary Design and Integrated Manufacturing Technology, Ministry of Education, Northwestern Polytechnical University, Xi'an 710072, China

Received date: 2011-05-06

  Revised date: 2010-08-22

  Online published: 2012-01-16

Abstract

A methodology of monitoring the machining quality of blades and tracing the error source based on dynamic Bayesian network is proposed for solving the low accuracy of blade machining quality. Dynamic Bayesian network is used to establish the relationship between blade machining operations to realize the control of the whole machining process. The causal relation between the elements in the main process factor set that affects blade machining operations is built by Bayesian network. The control chart T2 is used to monitor the factor set of each operation to judge whether the operation is out of control or not. While tracing error sources, the T2 statistics of the samples out of control are decomposed according to causal variables described by aforementioned causal relation, and the decomposed variable control limits are built as error source judgment conditions are built. A simulation study on a blade machining process is carried out, which demonstrates that the proposed method is reasonable.

Cite this article

WANG Pei, ZHANG Dinghua, CHEN Bing, LI Shan, WANG Mingwei . Machining Quality Monitoring of Blades and Source Tracing Based on Dynamic Bayesian Network[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2012 , 33(1) : 170 -181 . DOI: CNKI:11-1929/V.20111107.1019.001

References

[1] Chiang L H, Russell E L, Braatz R D. Fault detection and diagnosis in industrial systems. New York:Springer-Verlag, 2001.

[2] Venkatasubramanian V, Rengaswamy R, Yin K, et al. A review of process fault detection and diagnosis part I: quantitative model-based methods. Computers and Chemical Engineering, 2003, 27(3): 293-311.

[3] Chen W D, Miao R, Zhao Y Z, et al. Multivariate statistical process diagnosis based on path diagram. Journal of Shanghai Jiaotong University, 2010, 44(12): 1758-1762. (in Chinese) 陈文多, 苗瑞, 赵言正, 等. 基于路径图的多元统计过程诊断. 上海交通大学学报, 2010, 44(12): 1758-1762.

[4] Chan F T. Application of a hybrid case-based reasoning approach in electroplating industry. Expert Systems with Applications, 2005, 29(1): 121-130.

[5] Patton R J, Frank P M, Clark R N. Issues of fault diagnosis for dynamic systems. New York: Springer, 2000.

[6] Du S C, Xi L F, Pan E S. Modeling & controlling of product quality in serial-parallel hybrid multi-stage manufacturing systems. Computer Integrated Manufacturing Systems, 2006, 12(7): 1068-1073. (in Chinese) 杜世昌, 奚立峰, 潘尔顺. 串并联混合式多阶段制造系统产品质量建模与控制. 计算机集成制造系统, 2006, 12(7): 1068-1073.

[7] Liu D Y, Jiang P Y. Fluctuation analysis of process flow based on error propagation network. Chinese Journal of Mechanical Engineering, 2010, 46(2): 14-21. (in Chinese) 刘道玉, 江平宇, 基于误差传递网络的工序流波动分析. 机械工程学报, 2010, 46(2): 14-21.

[8] Jin M, Tsung F. A chart allocation strategy for multistage processes. IIE Transactions, 2008, 41(9): 790-803.

[9] Li Y, Tsung F. False discovery rate-adjusted charting schemes for multistage process fault diagnosis and isolation. Technometrics, 2008, 51(2): 186-205.

[10] Du F Z, Tang X Q, Sun J. ARL computation and parameters optimization for MEWMA control chart based on the Markov chain. Journal of Beijing University of Aeronautics and Astronautics, 2006, 32(8): 974-978. (in Chinese) 杜福洲, 唐晓青, 孙静. MEWMA控制图 ARL计算及参数优化. 北京航空航天大学学报, 2006, 32 (8): 974-978.

[11] Du F Z, Sun J, Tang X Q. Run length analysis for multivariate cumulative sum control chart based on Markov chains. Journal of Tsinghua University: Science and Technology, 2007, 47(2): 169-172. (in Chinese) 杜福洲, 孙静, 唐晓青. 基于Markov 链的MCUSUM控制图链长分析. 清华大学学报:自然科学版, 2007, 47(2): 169-172.

[12] Xiang L, Tsung F. Statistical monitoring of multistage processes based on engineering models. IIE Transactions, 2008, 40(10): 957-970.

[13] Zantek P F, Li S, Chen Y. Detecting multiple special causes from multivariate data with applications to fault detection in manufacturing. IIE Transactions, 2007, 39(8): 771-782.

[14] Kamal H, Meisam P, Hosein M. Fault diagnosis and classification based on wavelet transform and neural network. Progress in Nuclear Energy, 2011, 53(1): 41-47.

[15] Doganaksoy N, Faltin F W. Tucker W T. Identification of out of control multivariate characteristic in a multivariable manufacturing environment. Communications in Statistics, 1991, 20(9): 2775-2790.

[16] Cui X, Guo W, Lin L, et al. Covariate-adjusted nonlinear regression. Annals of Statistics, 2009, 37(4): 1839-1870.

[17] Senturk D. Covariate-adjusted varying coefficient models. Biostatistics, 2006, 7(2): 235-251.

[18] Maravelakis P E, Bersimis S, Panaretos J, et al. Identifying the out of control variable in a multivariate control chart. Journal of Quality Technology, 2002, 31(12): 2391-2408.

[19] Aparisi F, Avendano G, Sanz J. Techniques to interpret T2 control chart signals. IIE Transactions, 2006, 38(8): 647-657.

[20] Sun H C, Yan Z Y, Xie L Y. Recognition based on wavelet neural network for sucker rod's defects. Journal of Northeastern University: Natural Science, 2008, 29(2): 258-261. (in Chinese) 孙红春,阎志颖,谢里阳. 基于小波神经网络的抽油杆缺陷识别. 东北大学学报:自然科学版, 2008, 29(2): 258-261.

[21] Nie S C, Tang X Q. Research on quality fault diagnosis in mechanical machining process based on genetic algorithm. Acta Aeronautica et Astronautica Sinica, 2001, 22(6): 521-524. (in Chinese) 聂胜才, 唐晓青. 基于基因算法的加工质量故障诊断研究与实现. 航空学报, 2001, 22(6): 521-524.

[22] Niaki S T A, Abbasi B. Fault diagnosis in multivariate control chart using artificial neural networks. Quality Reliability Engineering International, 2005, 21(8): 825-840.

[23] Zeng L, Zhou S. Variability monitoring of multistage manufacturing processes using regression adjustment methods. IIE Transactions, 2008, 40(2): 109-121.

[24] Bersimis S, Psarakis S, Panaretos J. Multivariate statistical process control charts: an overview. Quality Reliability Engineering International, 2007, 23(5): 517-543.

[25] Mason R L, Tracy N D, Young J C. Decomposition of T2 for multivariate control chart interpretation. Journal of Quality Technology, 1995, 27(2): 109-119.

[26] Li J, Jin J, Shi J. Causation-based T2 decomposition for multivariate process monitoring and diagnosis. Journal of Quality Technology, 2008, 40(1): 46-58.
Outlines

/