Manufacturing process multivariate quality diagnosis classifier based on chi-square value

Abstract

The present invention provides a manufacturing process multivariate quality diagnosis classifier based on a chi-square value. Original data of quality features is collected in the manufacturing process, data preprocessing is performed, a hybrid algorithm is applied to perform process analysis of multivariate quality features of key operations, the stability is determined and it is determined whether there is an exception phenomenon or not according to the data recorded in a control graph, and searching process anomaly sources based on a chi-square value method. In order to allow a classification result to be more accurate, the chi-square value, weight proportion between the chi-square value and the data and a similarity stability determination are introduced. The manufacturing process multivariate quality diagnosis classifier based on the chi-square value is strict in process capability coefficient condition, accurate in determination state, low in algorithm complexity and fast in processing time, integrates multivariate quality, misjudgement factors and principal component factors, is higher in applicability, standard in parameter processing and complete in data processing, reduces the misjudgement probability, solves the problems of data offset and non-uniform unit, is higher in accuracy than a support vector machine and can achieve an exception diagnosis technology.

Description

technical field [0001] The invention relates to the technical field of quality diagnosis in the processing and manufacturing process of mechanical products, in particular to a chi-square value-based multivariate quality diagnosis classifier in the manufacturing process. Background technique [0002] The modern manufacturing process is multivariate and highly correlated, and the process monitoring of this kind of production process is called multivariate quality control (MQC) or multivariate statistical process control (MSPC). The process of finding the cause of the loss of control is known as MSPC diagnosis or anomaly identification. There are two main types of methods: one is statistical decomposition techniques; the other is techniques based on machine learning. Mainstream decomposition techniques include principal component analysis (PCA), feature space comparison method, MTY method, step-down method, and multi-directional kernel principal component analysis method. How...

AI Technical Summary

Problems solved by technology

However, these methods usually involve complex statistical procedures, which are not conducive to the application

Images