Sort by
Refine Your Search
-
tracking and autoencoders for amplitude and phase noise characterization Bayesian filtering Building experimental set-ups for noise characterization Reinforcement learning strategies for comb generation
-
focus on the following areas: Subspace tracking and autoencoders for amplitude and phase noise characterization Bayesian filtering Building experimental set-ups for noise characterization Reinforcement
-
performance utilizing reliable and computationally efficient numerical structural models. To support the condition (state) assessment, you will also explore the use of advanced estimators (e.g., Kalman Filter
-
(e.g., Kalman Filter) or Machine Learning models. These tools will be integrated with physics-based models of environmental loading (waves and wind) to enhance the accuracy and robustness
-
computationally efficient numerical structural models. To support the condition (state) assessment, the project will also explore the use of advanced estimators (e.g., Kalman Filter) or Machine Learning models
-
chromatograph, FIA and electronic particle counters i.e., Coulter counters also available. As a PhD fellow, you will be associated with the research groups and get access to instrumentation of your main and co