Development of a Reinforcement Learning-Based Control Strategy for Load Following in Supercritical Pulverized Coal (SCPC) Power Plants
Presented by NETL at Clearwater Clean Energy Conference, 06/19
Engineering topics
Publications and source records attributed to Hedrick, Elijah.
Presented by NETL at Clearwater Clean Energy Conference, 06/19
Presented by NETL 2019 Annual Project Review Meeting for Crosscutting, Rare Earth Elements, Gasification and Transformative Power Generation, 04/19
Traditional energy production plants are increasingly forced to cycle their load and operate under low-load conditions in response to growth in intermittent renewable generation. A plant-wide dynamic model of a supercritical pulverized coal (SCPC) power plant has been developed in the Aspen Plus Dynamics® (APD) software environment and the impact of advanced control strategies on the transient responses of the key variables to load-following operation and disturbances can be studied. Models of various key unit operations, such as the steam turbine, are developed in Aspen Custom Modeler® (ACM) and integrated in the APD environment. A coordinated control system (CCS) is developed above the regulatory control layer. Three control configurations are evaluated for the control of the main steam; the reheat steam temperature is also controlled. For studying servo control performance of the CCS, the load is decreased from 100% to 40% at a ramp rate of 3% load per min. The impact of a disturbance due to a change in the coal feed composition is also studied. The CCS is found to yield satisfactory performance for both servo control and disturbance rejection.
Presented by NETL at EPRI Flexible Operations Conference, 6/18
Presented by NETL at AIChE Annual Meeting, 10/18
Presented by NETL at AIChE Annual Meeting, 10/18