Optimum Position of Acoustic Emission Sensors for Ship Hull Structural Health Monitoring Based on Deep Machine Learning

Vassilios Kappatos; Petros Karvelis; George Georgoulas; Vasileios Tzitzilonis

doi:10.15224/978-1-63248-140-5-43

Optimum Position of Acoustic Emission Sensors for Ship Hull Structural Health Monitoring Based on Deep Machine Learning

Vassilios Kappatos, Petros Karvelis, George Georgoulas, Vasileios Tzitzilonis

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

In this paper a method for the estimation of the optimum sensor positions for acoustic emission localization on ship hull structures is presented. The optimum sensor positions are treated as a classification (localization) problem based on a deep learning paradigm. In order to avoid complex and time-consuming implementations, the proposed approach uses a simple feature extraction module, which significantly reduces the extremely high dimensionality of the raw signals/data. The optimum sensor position is defined by the maximum localization rate. In simulation experiments, where a stiffened plate model was partially sunk into the water, the localization rate of acoustic emission events in a noise-free environment is greater than 99.5 %, using only a single sensor.

Original language	English
Title of host publication	Sixth International Conference on Advances in Mechanical and Robotics Engineering - AMRE 2017
Publisher	SEEK Digital Library
Publication date	2018
Pages	40-43
ISBN (Electronic)	978-1-63248-140-5
DOIs	https://doi.org/10.15224/978-1-63248-140-5-43
Publication status	Published - 2018
Event	Sixth International Conference on Advances in Mechanical and Robotics Engineering - AMRE 2017 - Hotel Novotel Roma Eur, Rome, Italy Duration: 9. Dec 2017 → 10. Dec 2017 http://amre.theired.org/

Conference

Conference	Sixth International Conference on Advances in Mechanical and Robotics Engineering - AMRE 2017
Location	Hotel Novotel Roma Eur
Country/Territory	Italy
City	Rome
Period	09/12/2017 → 10/12/2017
Internet address	http://amre.theired.org/

Documents & Links

10.15224/978-1-63248-140-5-43

Cite this

@inproceedings{200257445ef84173ab10359819f1a205,

title = "Optimum Position of Acoustic Emission Sensors for Ship Hull Structural Health Monitoring Based on Deep Machine Learning",

abstract = "In this paper a method for the estimation of the optimum sensor positions for acoustic emission localization on ship hull structures is presented. The optimum sensor positions are treated as a classification (localization) problem based on a deep learning paradigm. In order to avoid complex and time-consuming implementations, the proposed approach uses a simple feature extraction module, which significantly reduces the extremely high dimensionality of the raw signals/data. The optimum sensor position is defined by the maximum localization rate. In simulation experiments, where a stiffened plate model was partially sunk into the water, the localization rate of acoustic emission events in a noise-free environment is greater than 99.5 %, using only a single sensor.",

author = "Vassilios Kappatos and Petros Karvelis and George Georgoulas and Vasileios Tzitzilonis",

year = "2018",

doi = "10.15224/978-1-63248-140-5-43",

language = "English",

pages = "40--43",

booktitle = "Sixth International Conference on Advances in Mechanical and Robotics Engineering - AMRE 2017",

publisher = "SEEK Digital Library",

note = "Sixth International Conference on Advances in Mechanical and Robotics Engineering - AMRE 2017 ; Conference date: 09-12-2017 Through 10-12-2017",

url = "http://amre.theired.org/",

}

Kappatos, V, Karvelis, P, Georgoulas, G & Tzitzilonis, V 2018, Optimum Position of Acoustic Emission Sensors for Ship Hull Structural Health Monitoring Based on Deep Machine Learning. in Sixth International Conference on Advances in Mechanical and Robotics Engineering - AMRE 2017. SEEK Digital Library, pp. 40-43, Sixth International Conference on Advances in Mechanical and Robotics Engineering - AMRE 2017, Rome, Italy, 09/12/2017. https://doi.org/10.15224/978-1-63248-140-5-43

Optimum Position of Acoustic Emission Sensors for Ship Hull Structural Health Monitoring Based on Deep Machine Learning. / Kappatos, Vassilios; Karvelis, Petros; Georgoulas, George et al.
Sixth International Conference on Advances in Mechanical and Robotics Engineering - AMRE 2017. SEEK Digital Library, 2018. p. 40-43.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Optimum Position of Acoustic Emission Sensors for Ship Hull Structural Health Monitoring Based on Deep Machine Learning

AU - Kappatos, Vassilios

AU - Karvelis, Petros

AU - Georgoulas, George

AU - Tzitzilonis, Vasileios

PY - 2018

Y1 - 2018

N2 - In this paper a method for the estimation of the optimum sensor positions for acoustic emission localization on ship hull structures is presented. The optimum sensor positions are treated as a classification (localization) problem based on a deep learning paradigm. In order to avoid complex and time-consuming implementations, the proposed approach uses a simple feature extraction module, which significantly reduces the extremely high dimensionality of the raw signals/data. The optimum sensor position is defined by the maximum localization rate. In simulation experiments, where a stiffened plate model was partially sunk into the water, the localization rate of acoustic emission events in a noise-free environment is greater than 99.5 %, using only a single sensor.

AB - In this paper a method for the estimation of the optimum sensor positions for acoustic emission localization on ship hull structures is presented. The optimum sensor positions are treated as a classification (localization) problem based on a deep learning paradigm. In order to avoid complex and time-consuming implementations, the proposed approach uses a simple feature extraction module, which significantly reduces the extremely high dimensionality of the raw signals/data. The optimum sensor position is defined by the maximum localization rate. In simulation experiments, where a stiffened plate model was partially sunk into the water, the localization rate of acoustic emission events in a noise-free environment is greater than 99.5 %, using only a single sensor.

U2 - 10.15224/978-1-63248-140-5-43

DO - 10.15224/978-1-63248-140-5-43

M3 - Article in proceedings

SP - 40

EP - 43

BT - Sixth International Conference on Advances in Mechanical and Robotics Engineering - AMRE 2017

PB - SEEK Digital Library

T2 - Sixth International Conference on Advances in Mechanical and Robotics Engineering - AMRE 2017

Y2 - 9 December 2017 through 10 December 2017

ER -

Optimum Position of Acoustic Emission Sensors for Ship Hull Structural Health Monitoring Based on Deep Machine Learning

Abstract

Conference

Documents & Links

Fingerprint

Cite this