Case Studies


Case Study: Predicting Stack Emissions - Utilities

This customer wanted another metric on stack emissions.


Company   Utility Company - Name Withheld
Product   Power
Location   Eastern USA

Stack emissions are a critical key performance indicator for power generation. Having redundant mechanisms to quantify emissions increases reliability and awareness.


Objective   A large municipal power generator wishes to estimate stack emissions as a cross-validation to physical sensors with greater than 90% accuracy.
Method   The customer extracted data from a real-time data historian and Process Modeler was used to model boiler conditions vs. physical stack sensor readings.


This virtual sensor plot above shows the estimated (blue) and actual (red) NOx emissions per million BTUs for a gas and oil fired power plant.  Data shown is "out-of-sample" (actual vs. estimated moisture on data not used to build the virtual sensor) and reflects true performance (93% accurate).  This virtual sensor can back up the physical sensor in case of fouling or failure and the difference between the virtual sensor and the physical sensor can be monitored for abnormalcy, leading to alerts for investigation or repair.


Reference Available?