Fault Identification via Non-parametric Belief Propagation

TL;DR

This paper introduces a non-parametric belief propagation method for fault identification from noisy measurements, outperforming existing algorithms by effectively handling binary and sparse fault patterns.

Contribution

The paper presents a novel non-parametric belief propagation approach that improves fault detection accuracy by considering fault binary states and sparsity, addressing computational challenges.

Findings

Belief propagation outperforms interior point and semidefinite programming methods.

The approach effectively captures fault binary states and sparsity.

Empirical results demonstrate higher accuracy in fault identification.

Abstract

We consider the problem of identifying a pattern of faults from a set of noisy linear measurements. Unfortunately, maximum a posteriori probability estimation of the fault pattern is computationally intractable. To solve the fault identification problem, we propose a non-parametric belief propagation approach. We show empirically that our belief propagation solver is more accurate than recent state-of-the-art algorithms including interior point methods and semidefinite programming. Our superior performance is explained by the fact that we take into account both the binary nature of the individual faults and the sparsity of the fault pattern arising from their rarity.