Neural Extended Kalman Filters for Learning and Predicting Dynamics of Structural Systems

by   Wei Liu, et al.

Accurate structural response prediction forms a main driver for structural health monitoring and control applications. This often requires the proposed model to adequately capture the underlying dynamics of complex structural systems. In this work, we utilize a learnable Extended Kalman Filter (EKF), named the Neural Extended Kalman Filter (Neural EKF) throughout this paper, for learning the latent evolution dynamics of complex physical systems. The Neural EKF is a generalized version of the conventional EKF, where the modeling of process dynamics and sensory observations can be parameterized by neural networks, therefore learned by end-to-end training. The method is implemented under the variational inference framework with the EKF conducting inference from sensing measurements. Typically, conventional variational inference models are parameterized by neural networks independent of the latent dynamics models. This characteristic makes the inference and reconstruction accuracy weakly based on the dynamics models and renders the associated training inadequate. We here show how the structure imposed by the Neural EKF is beneficial to the learning process. We demonstrate the efficacy of the framework on both simulated and real-world monitoring datasets, with the results indicating significant predictive capabilities of the proposed scheme.


Neural Augmentation of Kalman Filter with Hypernetwork for Channel Tracking

We propose Hypernetwork Kalman Filter (HKF) for tracking applications wi...

Kalman filter demystified: from intuition to probabilistic graphical model to real case in financial markets

In this paper, we revisit the Kalman filter theory. After giving the int...

A Poisson Kalman filter for disease surveillance

An optimal filter for Poisson observations is developed as a variant of ...

Alleviating Cold-start Problem in CTR Prediction with A Variational Embedding Learning Framework

We propose a general Variational Embedding Learning Framework (VELF) for...

Real-Time Variational Method for Learning Neural Trajectory and its Dynamics

Latent variable models have become instrumental in computational neurosc...

A Poisson Kalman Filter to Control the Dynamics of Neonatal Sepsis and Postinfectious Hydrocephalus

Neonatal sepsis (NS) and resulting complications, such as postinfectious...

Please sign up or login with your details

Forgot password? Click here to reset