Congratulations to Wei Liu
who was awarded one of the best oral presentations at the 5th International Conference on System Reliability and Safety Engineering (SRSE 2023), for his work titled "Model-based Unknown Input Estimation via Partially Observable Markov Decision Processes"
Wei is a member of the SMM group at the Singapore ETH Center and matriculated doctoral student at the National University of Singapore (NUS). His work forms part of Cluster 1 of the Future Resilient Systems (FRS) program on Cyber-Physical Systems Resilience.
Wei's work, in collaboration with Zhilu Lai, Charikleia D. Stoura, Kiran Bacsa, and Eleni Chatzi, proposes a novel method for estimating unknown system inputs, where the objective is to infer those system inputs that will reproduce the actual measured outputs. This can be reformulated as a Partially Observable Markov Decision Process (POMDP) problem and solved with well-established planning algorithms. The proposed method is demonstrated using simulated dynamical systems for structures with known dynamics, as well as a real wind turbine with learned dynamics inferred through a deep learning-based method for learning stochastic dynamics.