A fault diagnosis method for polymeric reaction process based on soft measuring hybrid model

This paper presented a fault diagnostic method for polymeric reaction process by means of the technique of adopted fuzzy pattern recognition. Based on soft measuring hybrid model, a threshold value principle and maximum membership degree principle are combined to diagnose faults. The fault diagnostic method is used for a typical polymeric reaction productive process - Polyacrylonitrile productive process, and it is proved that it can not only get accurate diagnosis results but also rectify the output of the hybrid model with the help of the information from morbid symptom set.