FAULT DETECTION AND DIAGNOSIS IN INDUSTRIAL FED-BATCH CELL CULTURE

Multivariate statistical process monitoring techniques are applied to pilot-plant, cell culture data for the purpose of fault detection and diagnosis. Data from 23 batches, 20 normal operating conditions (NOC) and three abnormal, were available. A PCA model was constructed from 19 NOC batches, while the remaining NOC batch was used for model validation. Subsequently, the model was used to successfully detect (both offline and online) abnormal process conditions and to diagnose the root causes.