On-line Statistical Process Monitoring and Fault Diagnosis in BatchBaker’s Yeast Fermentation

摘要

Despite the fact that many process variables are simultaneously monitored and stored in the industry, theanalysis and interpretation of this abundant amount of interrelated data is rarely made. This study involves realtime monitoring and fault diagnosis in batch baker’s yeast fermentation. A specific Real Time Statistical ProcessAnalysis and Control program (RT-SPAC) was developed to monitor instantaneous reaction conditions. The airflow rate fed to the reactor; temperature, pH and dissolved oxygen concentration in a laboratory size fermenterwere monitored and recorded by means of on-line sensors. Under control of the RT-SPAC program, twenty twobatch baker’s yeast fermentation operations were carried out. In the first twenty of them, ordinary process wasfollowed under previously defined nominal conditions. Historical data collected from these batches was then usedfor on-line dynamic PCA analysis in the course of the following two batches. The last two batches wereimplemented such that some deliberate faults (in temperature and pH) were introduced during the operation. Theresults indicated that the software was capable of capturing the process faults, and furthermore the possible causesof these faults were identified by contribution plots.