UNNATURAL PATTERN-RECOGNITION ON CONTROL CHARTS USING CORRELATION-ANALYSIS TECHNIQUES

This paper presents analysis and development of a pattern recognition system for identifying unnatural patterns on quality control charts. T he system is based on correlation analysis, where a set of optimal mat ched filters are generated. To illustrate the design methodology and o peration of the system, a set of commonly encountered pattens is utili zed, such as the trend, the systematic, and the cyclic patterns. A tra ining algorithm that minimizes the probabilities of Type I and Type II errors is presented. To evaluate the system performance, a testing al gorithm as well as a set of newly-defined performance measures are int roduced. The obtained results have shown the effectiveness of correlat ion analysis for control chart pattern recognition.