Weighted Semi-supervised Orthogonal Factor Analysis Model for Quality-Related Process Monitoring

Probabilistic model has already been widely used for process monitoring. However, the obtained factors may contain quality-unrelated information, which is harmful to the quality-related process monitoring. Meanwhile, considering the situation of unequal sample rates of process and quality variables, a semi-supervised orthogonal factor analysis (Semi-SOFA) model is presented, further, to improve robustness, Semi-SOFA is extended to weighted form (WSemi-SOFA). This paper performs orthogonal decomposition on the obtained factors, which divides them into two parts: quality-related one and quality-unrelated one. Based on it, the corresponding T-2 statistics are designed to offer quality-related process monitoring, respectively. Besides, SPE statistics are constructed as supplement to monitor residuals. For effectiveness demonstration of the proposed method, TE benchmark is utilized.