Search

To reduce climate impact, switching to carbon-free electrofuels is an interesting option to reduce greenhouse gas emissions from electricity generation. The emission of other pollutants than CO2, such as nitrogen oxides (NOx), however, remains a concern. This research focuses on investigating the impact of transient phases, such as start-up and load change, on the NOx emissions expected from the rich combustion of mixtures of hydrogen and ammonia in gas turbines. Stochastic processes account for the inherent variability and uncertainty on the transient trajectories. The trajectories are simulated using a one-dimensional premixed flame model built in Cantera to compute the levels of pollutant formations, among others. The results indicate significant variations in the equivalence ratio, leading to high NOx emission peaks. The study concludes that the impact of the uncertainties related to the transient trajectories on the NOx emissions is low compared to the overall variations of the equivalence ratio, although they can accentuate observed peaks.

Abstract Individual pitch control has shown great capability of alleviating the oscillating loads experienced by wind turbine blades due to wind shear, atmospheric turbulence, yaw misalignment, or wake impingement. This work presents a novel controller structure that relies on the separation of low‐level control tasks and high‐level ones. It is based on a neural network that modulates basic periodic pitch angle signals. This neural network is trained with reinforcement learning, a trial and error way of acquiring skills, in a low‐fidelity environment exempt from turbulence. The trained controller is further deployed in large eddy simulations to assess its performances in turbulent and waked flows. Results show that the method enables the neural network to learn how to reduce fatigue loads and to exploit that knowledge to complex turbulent flows. When compared to a state‐of‐the‐art individual pitch controller, the one introduced here presents similar load alleviation capacities at reasonable turbulence intensity levels, while displaying very smooth pitching commands by nature.