Effect of Database Generation on Damage Consequences’ Assessment Based on Random Forests

Recently, the application of machine learning has been explored to assess the main damage consequences without employing flooding sensors. This method can be the base of a new generation of onboard decision support systems to help the master during the progressive flooding of the ship. In particular...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Luca Braidotti, Jasna Prpić-Oršić, Marko Valčić
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	damaged ship progressive flooding random forests database generation decision support system Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581
Acceso en línea:	https://doaj.org/article/429fe110130948778068fdb08f9f01ef
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:429fe110130948778068fdb08f9f01ef
record_format	dspace
spelling	oai:doaj.org-article:429fe110130948778068fdb08f9f01ef2021-11-25T18:05:16ZEffect of Database Generation on Damage Consequences’ Assessment Based on Random Forests10.3390/jmse91113032077-1312https://doaj.org/article/429fe110130948778068fdb08f9f01ef2021-11-01T00:00:00Zhttps://www.mdpi.com/2077-1312/9/11/1303https://doaj.org/toc/2077-1312Recently, the application of machine learning has been explored to assess the main damage consequences without employing flooding sensors. This method can be the base of a new generation of onboard decision support systems to help the master during the progressive flooding of the ship. In particular, the application of random forests has been found suitable to assess the <i>final fate</i> of the ship and the damaged compartments’ set and estimate the <i>time-to-flood</i>. Random forests have to be trained using a database of precalculated progressive flooding simulations. In the present work, multiple options for database generation were tested and compared: three based on Monte Carlo (MC) sampling based on different probability distributions of the damage parameters and a parametric one. The methods were tested on a barge geometry to highlight the main effects on the damage consequences’ assessment in order to ease the further development of flooding-sensor-agnostic decision support systems for flooding emergencies.Luca BraidottiJasna Prpić-OršićMarko ValčićMDPI AGarticledamaged shipprogressive floodingrandom forestsdatabase generationdecision support systemNaval architecture. Shipbuilding. Marine engineeringVM1-989OceanographyGC1-1581ENJournal of Marine Science and Engineering, Vol 9, Iss 1303, p 1303 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	damaged ship progressive flooding random forests database generation decision support system Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581
spellingShingle	damaged ship progressive flooding random forests database generation decision support system Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581 Luca Braidotti Jasna Prpić-Oršić Marko Valčić Effect of Database Generation on Damage Consequences’ Assessment Based on Random Forests
description	Recently, the application of machine learning has been explored to assess the main damage consequences without employing flooding sensors. This method can be the base of a new generation of onboard decision support systems to help the master during the progressive flooding of the ship. In particular, the application of random forests has been found suitable to assess the <i>final fate</i> of the ship and the damaged compartments’ set and estimate the <i>time-to-flood</i>. Random forests have to be trained using a database of precalculated progressive flooding simulations. In the present work, multiple options for database generation were tested and compared: three based on Monte Carlo (MC) sampling based on different probability distributions of the damage parameters and a parametric one. The methods were tested on a barge geometry to highlight the main effects on the damage consequences’ assessment in order to ease the further development of flooding-sensor-agnostic decision support systems for flooding emergencies.
format	article
author	Luca Braidotti Jasna Prpić-Oršić Marko Valčić
author_facet	Luca Braidotti Jasna Prpić-Oršić Marko Valčić
author_sort	Luca Braidotti
title	Effect of Database Generation on Damage Consequences’ Assessment Based on Random Forests
title_short	Effect of Database Generation on Damage Consequences’ Assessment Based on Random Forests
title_full	Effect of Database Generation on Damage Consequences’ Assessment Based on Random Forests
title_fullStr	Effect of Database Generation on Damage Consequences’ Assessment Based on Random Forests
title_full_unstemmed	Effect of Database Generation on Damage Consequences’ Assessment Based on Random Forests
title_sort	effect of database generation on damage consequences’ assessment based on random forests
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/429fe110130948778068fdb08f9f01ef
work_keys_str_mv	AT lucabraidotti effectofdatabasegenerationondamageconsequencesassessmentbasedonrandomforests AT jasnaprpicorsic effectofdatabasegenerationondamageconsequencesassessmentbasedonrandomforests AT markovalcic effectofdatabasegenerationondamageconsequencesassessmentbasedonrandomforests
_version_	1718411613212508160

Effect of Database Generation on Damage Consequences’ Assessment Based on Random Forests

Ejemplares similares