基于控制图几何特征的制造过程质量诊断方法研究

he Stability of the manufacturing process is a precondition for ensuring product quality. The features which can show their characteristics have been extracted according to the definition of the features from the geometric pattern of the control chart. The extracted methods of control chart have been established. A neural network pattern recognizer based on the features has been designed. The feature extraction from the sample function through defining the feature has been completed. According to the features of different process model, six types of out of control mode are recognized automatically to distinguish whether the process is in a controlled state or out-of-control. In order to test its effectiveness, the method is applied to the manufacturing process of an engine cylinder block.