A hybrid system for SPC concurrent pattern recognition

Any nonrandom patterns shown in Statistical Process Control (SPC) charts imply possible assignable causes that may deteriorate the process performance. Hence, timely detecting and recognizing Control Chart Patterns (CCPs) for nonrandomness is very important in the implementation of SPC. Due to the limitations of run-rule-based approaches, Artificial Neural Networks (ANNs) have been resorted for detecting CCPs. However, most of the reported ANN approaches are only limited to recognize single basic patterns. Different from these approaches, this paper presents a hybrid approach by integrating wavelet method with ANNs for on-line recognition of CCPs including concurrent patterns. The main advantage of this approach is its capability of recognizing coexisted or concurrent patterns without training by concurrent patterns. The test results using simulated data have demonstrated the improvements and the effectiveness of the methodology with a success rate up to 91.41% in concurrent CCP recognition.

[1]  Peter R. Nelson,et al.  Process Quality Control , 1991 .

[2]  Shing I. Chang,et al.  A two-stage neural network approach for process variance change detection and classification , 1999 .

[3]  J. D. T. Tannock,et al.  A review of neural networks for statistical process control , 1998, J. Intell. Manuf..

[4]  A. K. Kochhar,et al.  Pattern recognition for statistical process control charts , 1998 .

[5]  R Guh.  IntelliSPC: a hybrid intelligent tool for on-line economical statistical process control , 1999 .

[6]  Marc Thuillard.  Wavelets in Soft Computing , 2001, World Scientific Series in Robotics and Intelligent Systems.

[7]  Duc Truong Pham,et al.  Intelligent quality systems , 1996, Advanced manufacturing series.

[8]  Lloyd S. Nelson,et al.  Interpreting Shewhart X̄ Control Charts , 1985 .

[9]  Lloyd S. Nelson,et al.  Column: Technical Aids: The Shewhart Control Chart--Tests for Special Causes , 1984 .

[10]  Margaret J. Robertson,et al.  Design and Analysis of Experiments , 2006, Handbook of statistics.

[11]  Chuen-Sheng Cheng,et al.  A NEURAL NETWORK APPROACH FOR THE ANALYSIS OF CONTROL CHART PATTERNS , 1997 .

[12]  Ruey-Shiang Guh,et al.  Integrating artificial intelligence into on‐line statistical process control , 2003 .

[13]  Amjed M. Al-Ghanim,et al.  An unsupervised learning neural algorithm for identifying process behavior on control charts and a comparison with supervised learning approaches , 1997 .

[14]  J.D.T. Tannock,et al.  Recognition of control chart concurrent patterns using a neural network approach , 1999 .

[15]  Ruey‐Shiang Guh.  Robustness of the neural network based control chart pattern recognition system to non‐normality , 2002 .

[16]  William J. Kolarik,et al.  Creating quality : concepts, systems, strategies, and tools , 1995 .