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

Mariela De Lucas Alvarez; David M. Lane

doi:10.1109/OCEANS.2016.7761280

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

Mariela De Lucas Alvarez
, David M. Lane

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

8 Citations (Scopus)

Abstract

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.

Original language	English
Title of host publication	OCEANS 2016 MTS/IEEE Monterey
Publisher	IEEE
ISBN (Electronic)	9781509015375
DOIs	https://doi.org/10.1109/OCEANS.2016.7761280
Publication status	Published - 1 Dec 2016
Event	2016 OCEANS MTS/IEEE Monterey - Monterey, United States Duration: 19 Sept 2016 → 23 Sept 2016

Conference

Conference	2016 OCEANS MTS/IEEE Monterey
Country/Territory	United States
City	Monterey
Period	19/09/16 → 23/09/16

Keywords

Fault detection and diagnosis
Gaussian mixtures
Hidden markov models
Underwater long-term autonomy

ASJC Scopus subject areas

Instrumentation
Oceanography
Ocean Engineering

Access to Document

10.1109/OCEANS.2016.7761280

Cite this

@inproceedings{dd24ccac0d194ad0be1936195fac2794,

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

abstract = "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.",

keywords = "Fault detection and diagnosis, Gaussian mixtures, Hidden markov models, Underwater long-term autonomy",

author = "\{De Lucas Alvarez\}, Mariela and Lane, \{David M.\}",

year = "2016",

month = dec,

day = "1",

doi = "10.1109/OCEANS.2016.7761280",

language = "English",

booktitle = "OCEANS 2016 MTS/IEEE Monterey",

publisher = "IEEE",

address = "United States",

note = "2016 OCEANS MTS/IEEE Monterey ; Conference date: 19-09-2016 Through 23-09-2016",

}

TY - GEN

T1 - A Hidden Markov Model application with Gaussian Mixture emissions for fault detection and diagnosis on a simulated AUV platform

AU - De Lucas Alvarez, Mariela

AU - Lane, David M.

PY - 2016/12/1

Y1 - 2016/12/1

N2 - 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.

AB - 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.

KW - Fault detection and diagnosis

KW - Gaussian mixtures

KW - Hidden markov models

KW - Underwater long-term autonomy

UR - https://www.scopus.com/pages/publications/85006922678

U2 - 10.1109/OCEANS.2016.7761280

DO - 10.1109/OCEANS.2016.7761280

M3 - Conference contribution

AN - SCOPUS:85006922678

BT - OCEANS 2016 MTS/IEEE Monterey

PB - IEEE

T2 - 2016 OCEANS MTS/IEEE Monterey

Y2 - 19 September 2016 through 23 September 2016

ER -

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

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this