Measurement of parameters in the process industry is key for optimizing process control and to increase OEE. To achieve this, sensors are one of the most common methods. A virtual sensor allows new cost effective ways to generate this data.

The example of the customer Münzing Chemie GmbH shows how production optimization using BCAP (Bilfinger Connected Asset Performance) can be carried out solely on the basis of sensor data while maintaining full plant availability.

Virtual Sensor: This moisture estimation and prediction example shows how process industry operators can automate data collection from blind spots within their production line.

Learn from this customer case study how product quality and productivity can be increased using plant intelligence based on data insights.

This use case demonstrates how we provided insight into variation in batch duration, and duration of steps within batches, for a pharmaceutical customer’s filter dryer.

Anyone who is well acquainted with industrial systems will hear immediately if equipment is running differently than normal. But changes in the machine condition cannot always be detected efficiently with regular inspection rounds. Machine Learning can give an answer.

PIDGraph enables a cost-efficient and fast conversion and digitalization of legacy P&IDs. This use case describes how PIDGraph’ s Deep Graph Analysis is applied for equipment isolation in an oil & gas plant.

Read in this use case how module engineering based on a deep graph analysis of a P&ID enables a time- and cost-effective way to create e.g. asset hierarchies, and then extract valuable information from the data obtained.