Abstract：In this paper, a multiphase orthogonal signal correction modeling and hierarchical statistical analysis strategy is developed for the improvement of process understanding and quality prediction. According to background, hierarchical PLS is used to build regression model of process variables and quality variables. This blocking leads to two model levels: the upper level where the relationships between blocks are modeled and the lower level showing the details of each block. Furthermore, in each lower model, O2-PLS is used to remove the structured noise in both X and Y, which is not contributed to prediction model. The corresponding loading vectors provide good interpretation of the covarying part in X and Y. Simulation of the continuous annealing line demonstrates the efficiency of the proposed algorithm for better process understanding and quality interpretation.
参考文献
- 下载量()
- 访问量()
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%