控制图异常模式的识别技术研究

质量控制图中所呈现出的异常状态可揭示出加工过程潜在的质量问题。本文提出了一种基于SLFM网络的控制图模式识别模型 ,该模型不仅能够识别控制图的 6种基本模式 ,对混合型的异常模式也能够有效识别。数字仿真表明 ,该模型训练速度快 ,识别精度高 ,并且具有很强的可塑性 ,适用于质量控制图的在线实时模式识别

Abnormal Pattern Recognition Technology for Control Chart

Abnormal control charts can provide clues to reveal potential quality problems in manufacturing process. In this paper, a pattern recognition model based on SLFM network is proposed to recognize the control chart patterns, which include six basic patterns and their mixed patterns. Numerical results show that this model possesses advantages of quick training and satisfactory recognition performance. This model can improve its recognition accuracy because of its flexibility. The above mentioned good performances facilitate the use of the proposed model in an on line real time mode.