Simultaneous Process Mean and Variance Monitoring Using Wavelet Transform and Probabilistic Neural Network

Abstract:

A real-time WPNN-based model was present for the simultaneous recognition of both mean and variance CCPs. In the modeling of structure for patterns recognition, the combined wavelet transform with probabilistic neural network (WPNN) was proposed. Input data was decomposed by wavelet transform into several detail coefficients and approximations. The approximation obtained and energy of every lever detail coefficients was for the input of PNN. The simulation results shows that it can recognize each pattern of the mean and variance CCPs accurately, which can be used in simultaneous process mean and variance monitoring.

• Periodical: Applied Mechanics and Materials (Volumes 157-158)
• Pages: 11-15
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.157-158.11
• Online since: February 2012
• Authors: Shao Xiong Wu
• Keywords: Control Chart, Pattern Recognition, Probabilistic Neural Network, Statistical Process Control (SPC), Wavelet Transform (WT)

References

[1] Pharm, D. T. and E. Oztemel. Control chart pattern recognition using neural networks. J. Syst. Eng., 2, 256-262(1992).

[2] Hwarng, H. B. and N. F. Hubele. Back-propagation pattern recognizers for X control charts. Methodology and performance. Computers ind. Engng., 24, 219-235(1993).

DOI: 10.1016/0360-8352(93)90010-u

[3] Smith, A. E. X-bar and R control chart interpretation using neural computing. Int. J. Prod. Res., 32, 309-320(1994).

[4] Pham, D. T. and E. Oztemel. Control chart pattern recognition using learning vector quantization networks. Int. J. Prod Res., 32, 721-729(1994).

DOI: 10.1080/00207549408956963

[5] Cheng C. S. A multi-layer neural network model for detecting changes in the process mean. Computers ind. Engng., 28, 51-61(1995).

DOI: 10.1016/0360-8352(94)00024-h

[6] Ruey-shiang Guh. Intergrating Artificial Intelligence into On-line statistical Process Control. Quality and reliability engineering international. 19, 1-20(2003).

[7] Pacella M., Semeraro Q. Using recurrent neural networks to detect changes in auto-correlated processes for quality monitoring. Computers & Industrial Engineering. 52, 502-520(2007).

DOI: 10.1016/j.cie.2007.03.003

[8] Niaki S. T. A., Abbasi B. Detection and classification mean-shifts in multi-attribute processes by artificial neural networks. International Journal of Production Research. 46, 2945-2963(2008).

DOI: 10.1080/00207540601039809

[9] Guh, R. S. Real-time recognition of control chart patterns in auto-correlated processes using a learning vector quantization network-based approach. International Journal of Production Research. 46, 3959-3991(2008).

DOI: 10.1080/00207540601011501

[10] Shaoxiong W. Study on On-line Detection and Analysis System of Control Chart Based on Wavelet Packet and Probabilistic Neural Network. Transactions of the Chinese society for agricultural machinery, vol. 39, 211-215, (2008).

[11] Cook D. R., Zobel, C. W. Nottingham, Q. J. Utilization of neural networks for the recognition of variance shifts in correlated manufacturing process parameters. International Journal of Production Research. 39, 3881-3887. (2001).

DOI: 10.1080/00207540110071750

[12] Ruey-shiang Guh. Simultaneous process mean and variance monitoring using artificial neural networks. Computers ind. Engng. 58, 739-753(2010).

DOI: 10.1016/j.cie.2010.02.004