Distributed Bayesian fault diagnosis of jump Markov systems in wireless sensor networks

被引：4
作者：
Snoussi, Hichem [1 ]
Richard, Cédric [1 ]
机构：
[1] ICD, LM2S, University of Technology of Troyes, Troyes, 10000, 12, rue Marie Curie
来源：
International Journal of Sensor Networks | 2007年 / 2卷 / 1-2期
关键词：
Collaborative sensor network; Online change detection; Rao-blackwellised particle filter; RB-CPF;
D O I：
10.1504/IJSNET.2007.012990
中图分类号：
学科分类号：
摘要：
A Bayesian distributed online change detection algorithm is proposed for monitorin a dynamical system by a wireless sensor network. The proposed solution relies on modellin the system dynamics by a jump Markov system with a finite set of states, including the abrup change behaviour. For each discrete state, an observed system is assumed to evolve accordin to a state-space model. The collaborative strategy ensures the efficiency and the robustnes of the data processing, while limiting the required communications bandwith. An efficien Rao-Blackwellised Collaborative Particle Filter (RB-CPF) is proposed to estimate the a posterior probability of the discrete states of the observed systems. The Rao-Blackwellisation procedur combinesaSequential Monte-Carlo (SMC) filter with a bank of distributed Kalman filters. Inorde to prolong the sensor network lifetime, only few active (leader) nodes are selected according to spatio-temporal selection protocol. This protocol is based on a trade-off between error propagation communications constraints and information content complementarity of distributed data. Onl sufficient statistics are communicated between leader nodes and their collaborators. © 2007 Inderscience Enterprises Ltd.
引用
收藏
页码：118 / 127
页数：9
相关论文
共 17 条
  • [1] Andrieu C., Doucet A., Singh S., Tadic V., Particle methods for change detection, system identification, and control, Proceedings of the IEEE, 92, 3, pp. 423-438, (2004)
  • [2] De Freitas N., Rao-Blackwellised particle filtering for fault diagnosis, IEEE Aerospace, (2002)
  • [3] Dempster A.P., Laird N.M., Rubin D.B., Maximum likelihood from incomplete data via the em algorithm, Journal of the Royal Statistical Society, Series B, 39, pp. 1-38, (1977)
  • [4] Doucet A., Godsill S., Andrieu C., On sequential Monte Carlo sampling methods for Bayesian filtering, Statistics and Computing, 10, 3, pp. 197-208, (2000)
  • [5] Doucet A., De Freitas N., Gordon N., Sequential Monte Carlo Methods in Practice, (2001)
  • [6] Doucet A., Vo B., Andrieu C., Davy M., Particle filtering for multitarget tracking and sensor management, Proceedings of the International Conference on Information Fusion, 1, pp. 474-481, (2002)
  • [7] Ihler A., Fisher III J., Willsky A., Using sample-based representations under communications constraints, Technical Report 2601, (2004)
  • [8] Ihler A., Fisher III J., Willsky A., Particle filtering under communications constraints, Proceedings of Statistical Signal Processing (SSP), (2005)
  • [9] Li X., Jilkov V., Survey of maneuvering target tracking. Part i: Dynamic models, IEEE Transactions on AES, 39, 4, pp. 1333-1364, (2003)
  • [10] Li X., Jilkov V., Survey of maneuvering target tracking. Part v: Multiple-model methods, IEEE Transactions AES, 41, 4, pp. 1255-1321, (2005)
12