Model predictive control of air pollution control processes

摘要

A controller (610) for directing operation of an air pollution control system (620) performing a process to control emissions of a pollutant has multiple process parameters (MPPs) (625). One or more of the MPPs (625) is a controllable process parameter (CTPP) (615) and one of the MPPs (625) is an amount of the pollutant (AOP) (640) emitted by the system (620). A defined AOP (640) value (AOPV) represents an objective or limit on an actual value (AV) of the emitted AOP (640). The controller (610) includes either a neural network process model or a non-neural network process model representing a relationship between each CTPP (615) and the emitted AOP (640). A control processor (630) has the logic to predict, based on the model, how changes to the current value of each CTPP (615) will affect a future AV of emitted AOP (640), to select one of the changes in one CTPP (615) based on the predicted affect of that change and on the AOPV, and to direct control of the one CTPP (615) in accordance with the selected change for the CTPP (615).