A Hidden Markov Model application with Gaussian Mixture emissions for fault detection and diagnosis on a simulated AUV platform

This paper presents an application of a Hidden Markov Model for fault detection and diagnosis on a testbed that emulates an AUV thruster system. The testbed consists in circuit board with two DC motors that represent the thrusters and embedded features to produce malfunctions. We present how the model is learned using the Expectation Maximization algorithm for Gaussian Mixtures and how the testbed is monitored probabilistic inference. Diagnosis is also performed using GMM classifiers. We describe how the framework deals with non-Gaussian data and how it reflects in the accuracy overall.

[1]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[2]  Gilles Louppe,et al.  Independent consultant , 2013 .

[3]  David M. Lane,et al.  Adaptive mission planning: the embedded OODA loop , 2008 .

[4]  David M. Lane,et al.  Online fault detection and model adaptation for Underwater Vehicles in the case of thruster failures , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[5]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[6]  Georgios Papadimitriou,et al.  Semantic based knowledge representation and adaptive mission planning for MCM missions using AUVs , 2014, OCEANS 2014 - TAIPEI.

[7]  M. Perrier,et al.  Fault-diagnosis of subsea robots using neuro-symbolic hybrid systems , 1998, IEEE Oceanic Engineering Society. OCEANS'98. Conference Proceedings (Cat. No.98CH36259).

[8]  Stéphane Robin,et al.  Hidden Markov Models with mixtures as emission distributions , 2012, Statistics and Computing.

[9]  Uri Lerner,et al.  Hybrid Bayesian networks for reasoning about complex systems , 2002 .

[10]  Serafín Moral,et al.  Estimating mixtures of truncated exponentials in hybrid bayesian networks , 2006 .

[11]  José A. Gámez,et al.  Data clustering using hidden variables in hybrid Bayesian networks , 2014, Progress in Artificial Intelligence.

[12]  Peter Krauthausen,et al.  Parameter learning for hybrid Bayesian Networks with Gaussian mixture and Dirac mixture conditional densities , 2010, Proceedings of the 2010 American Control Conference.

[13]  Rafael Rumí,et al.  Parameter learning in hybrid Bayesian networks using prior knowledge , 2015, Data Mining and Knowledge Discovery.

[14]  Prakash P. Shenoy,et al.  Approximating probability density functions in hybrid Bayesian networks with mixtures of truncated exponentials , 2006, Stat. Comput..

[15]  Angelo Alessandri,et al.  Fault detection of actuator faults in unmanned underwater vehicles , 1999 .