Superheater steam temperature control for a 300MW boiler unit with Inverse Dynamic Process Models

Abstract

An Inverse Dynamic Neuro-Controller (IDNC) is developed to improve the superheater steam temperature control of a 300MW boiler unit. A recurrent neural network was used for building the Inverse Dynamic Process Models (IDPMs) for the superheater system. Two inverse dynamic neural network (NN) models referring to the first-stage and the second-stage water-spray attemperators are constructed separately. To achieve highly accurate approximation of the superheater system, the NN models are trained with sufficient historical data in a wide operating range, which consists of both different steady-state conditions and dynamic transients. Then the IDNCs are designed based on the well-trained IDPMs and applied to superheater steam temperature control. In order to eliminate the steady-state control error arisen by the model error, a simple feedback PID compensator is added to an inverse controller. Detailed control tests are carried out on a full-scope simulator for a 300MW coal-fired power generating unit. It is shown that the temperature control is greatly improved with the IDNCs compared to the original cascaded PID control scheme.