Skip to Main Content
Pattern recognition of abnormal control charts can provide clues to reveal potential quality problems in manufacturing process. This paper aims to realize the automatic recognition of abnormal patterns of control charts in a statistical process control (SPC) system. A new neural network model named regional supervised feature mapping (RSFM) network was proposed to recognize the control chart patterns, which include six basic patterns and their mixed patterns. The performance of network was studied, and its parameters were optimized. Euclid-distance-discriminance approach was developed to recognize mixed abnormal patterns. Numerical results show this network possesses advantages of quick training and good recognition performance, which is fit for pattern recognition of control charts in a real time SPC system.