The Observability in Unobservable Systems

TL;DR

This paper proposes a new approach to assess and improve the estimation of specific state variables in systems that are not fully observable, using a neural network-based deep filter and a quantitative observability measure.

Contribution

It introduces a novel concept of targeted observability and a deep neural filter for estimating specific states without full system observability, along with a quantitative observability metric.

Findings

Deep filter effectively estimates targeted state variables.

Quantitative observability measure allows comparison of sensor configurations.

Method enables estimation in unobservable systems.

Abstract

In this paper, we introduce the concept of observability of targeted state variables for systems that may not be fully observable. For their estimation, we introduce and exemplify a deep filter, which is a neural network specifically designed for the estimation of targeted state variables without computing the trajectory of the entire system. The observability definition is quantitative rather than a yes or no answer so that one can compare the level of observability between different sensor locations.