Operational complexity in batch-operated plants is large and companies struggle to produce at high equipment utilisation. Due to high fixed costs, capacity utilisation is an important operational directive. Many current plants are not in a state that allows the application of rigorous process systems engineering tools due to modelling challenges. This work proposes identifying the right engineering projects based on statistic evidence. In the case of incomplete process monitoring strategies in semi-automated facilities, these analyses are specifically challenging. The power of modern data processing tools in this context is shown at hand of a case study in an industrial pharmaceutical production. This includes the development of a recursive monitoring algorithm as well as plant performance evaluation based on established heuristics.