Department of Industrial Management
National Formosa University
Huwei, Yunlin, Taiwan 632, R. O. C.
Department of Information Management
Hufan University
Pattern recognition is a critical issue in Statistical Process Control because unnatural patterns displayed by control charts can be associated with specific causes that adversely impact on the manufacturing process. Recently, neural networks have been widely investigated as an effec-tive approach to control chart pattern (CCP) recognition. However, most of the research in this field has used traditional back propagation networks (BPNs) that cannot deal with pat-terns that vary over time in an on-line CCP recognition scheme. This causes a pattern misclas-sification problem in nearly all neural network-based studies in the field of on-line CCP rec-ognition. The present paper presents a novel application of utilizing a time delay neural net-work (TDNN) based model to address this problem. The TDNN, with its special architecture, can represent relationships between patterns in a time sequence, and is therefore suitable to be trained with dynamic patterns that change over time. Numerical results indicate that the pat-tern misclassification problem has been addressed effectively by the proposed TDNN-based model. When compared with traditional BPNs, the TDNN model has better performance in both recognition accuracy and speed. In comparison with traditional control chart approaches, the proposed model is capable of superior performance of average run length, while the cate-gory of the unnatural CCP can also be accurately identified.
Keywords:time delay neural network, pattern recognition, control chart, statistical process control
(*Contact: E-mail rsguh@nfu.edu.tw )
Cite this article as: Ruey-Shiang Guh and Yeou-Ren Shiue, "FAST AND ACCURATE RECOGNITION OF CONTROL CHART PATTERNS USING A TIME DELAY NEURAL NETWORK," Journal of the Chinese Institute of Industrial Engineers, 27, 61-79 (2010).