OpenFields

Fault diagnosis over wireless sensor networks using distributed Kalman and distributed Particle Filtering

The paper considers the problem of distributed fault detection for continuous time nonlinear dynamical systems.

Year of Publication2011

The paper considers the problem of distributed fault detection for continuous time nonlinear dynamical systems. Such a fault diagnosis procedure involves the transmission of measurements to local processing units over a wireless sensor network and the fusion of local state estimates with the use of distributed filtering algorithms.The paper proposes the Extended Information Filter (EIF), the Unscented Information Filter (UIF) and the Distributed Particle Filter (DPF) as possible approaches for fusing the state estimates obtained by local monitoring stations, under the assumption of Gaussian noises. As far as the fault diagnosis part is concerned the FDI method can be based on the combination of the Kalman or the Particle Filtering algorithm with the likelihood ratio test. As an application example the paper considers failure diagnosis for a GPS receiver which is mounted on a UAV.

This item is categorised as follows

Additional keywords/tags

generalized likelihood ratiounscented information filterextended information filterdistributed fault diagnosisdistributed particle filter
Organisation Logo for Harper Adams University

Supporting the development of the national rural economy.

Website

What Next...?

This is a brief summary of an item in the OpenFields Library. This free online library contains items of interest to practitioners and researchers in the agricultural and landbased industries.