641e Successful Industrial Application of Robust Inferential Sensors for NOx Emissions Monitoring

Zdravko Stefanov1, Leo H. Chiang2, Arthur Kordon1, James Edwards3, David Roberts3, Rodney Roubique3, and Charles Harper3. (1) The Dow Chemical Company, Corporate R&D, 2301 Brazosport Blvd., B1463, Freeport, TX 77584, (2) Core R&D, The Dow Chemical Company, 2301 Brazosport Blvd., B1225, Freeport, TX 77584, (3) Energy Systems, The Dow Chemical Company, Plaquemine, LA 70765

As a large chemical company, Dow Chemical uses and maintains multiple power plants. One of the major environmental requirements on power plants is compliance of their NOx emissions with Environmental Protection Agency (EPA) regulations. To satisfy governmental regulation, Dow is obligated to maintain Emission Monitoring Systems. These systems are either hardware based (Continuous CEMS) or software based (Predictive PEMS).

The application of the robust inferential sensors was considered in 2004 when a vendor installed system was to be replaced and in-house solution was determined to be much more cost effective. Two modeling technologies were concurrently evaluated – Partial Least Squares (PLS) which is a linear approach and Genetic Programming (GP) which is a nonlinear approach. As a consequence GP models were proven to be superior and were implemented.

The robust implementation is achieved by sensor validation. Sensor validation provides redundant backup for the inputs of the inferential sensor, so the sensor continues to operate even if some of the inputs fails. This robustness is also an EPA requirement. Due to this implementation and the quality of the models, four years of EPA compliance are recorded as of 2008. Certain details on the inferential sensors maintenance and standardization will be discussed.