Identification and control of power plant de-superheater using soft computing techniques

Tight turbine steam temperature control is a necessity for obtaining long lifetime, high efficiency, high load following capability and high availability in power plants. The present work reports a systematic approach for the control strategy design of power plants with non-linear characteristics. The presented control strategy is developed based on optimized PI control with genetic algorithms (GAs) and investigates performance and robustness of the GA-based PI controller (GAPI). In order to design the controller, an effective neuro-fuzzy model of the de-superheating process is developed based on recorded data. Results indicate a successful identification of the high-order de-superheating process as well as improvements in the performance of the steam temperature controller.