An object-oriented dynamic learning method for whole-process fuel control within coal-fired generating units

Abstract

In response to problems during the startup of coal-fired generating units， including intricate equipment operation， an excess of control parameters， limited optimization techniques， and protracted startup time， an object-oriented dynamic learning method for whole-process fuel control within coal-fired generating units is introduced. This method entails the segmentation and objectification of the entire fuel control process， allowing for the dynamic acquisition of the current operational status of each system at every stage. Consequently， adaptive fuel intelligent control directives are generated， facilitating the realization of intelligent fuel control throughout the entire sequence， from unit ignition to coordinated operation. Functional validation has been performed on a 1，050 MW unit， and practical implementation confirms the method’s capacity for efficient and intelligent operation throughout the entire process， significantly reducing unit startup duration， and elevating the unit’s overall level of automation.

Keywords

• coal-fired generating unit
• object-oriented
• whole-process fuel control
• efficiency