Smart Firing Control System

摘要

When pulverized coal is fed to a utility boiler a phenomenon sometimes referred to as "roping" occurs. Roping impacts the distribution of coal flow to the coal pipes supplying the burners. The roping characteristics are unique mill to mill, change with mill wear and are dependent on primary air flow and coal type. Coal maldistribution in turn causes some regions of the furnace to have more fuel and some to have less fuel. Typically the secondary air flow control is configured to be evenly distributed to the burners via the respective registers. Thus, these coal flow imbalances result in O_2 imbalances with regions of high CO and unburned carbon in oxygen depleted areas and high NO_x in regions of higher O_2. Advanced Process Control (APC) applications such as multivariable model predictive control and neural networks are frequently applied to bias furnace air flow distribution and address O_2 imbalances and regions of high CO. However, coal roping and other phenomena creates a need for a recalibration of the APC models of the air register positions related to the higher level variables such as excess O_2, CO, NO_x, and even heat rate. A novel solution, Smart Firing Control System, has been developed for periodically testing the APC system on line without operator intervention and gradually adapting the models to capture the characteristics of these shifting relationships. This solution has contributed to significant additional boiler efficiency improvements above and beyond the original APC application.