Parameter optimization of MEWMA control chart based on SVDD

摘要

Statistical Process Control is an important method for production quality control. With the rapid development of machine learning, corresponding classification methods have been applied to the control chart field by researchers. Some scholars have proposed SVDD algorithm based on support vector machines. This algorithm has no process distribution. For small samples, high-dimensional issues are very applicable. Considering MEWMA control chart based on SVDD, this paper proposes the MST-GEN method to improve the selection of parameters. It is expected to improve the performance of control chart.