Automatic extraction of cable connection information from 2D drawings for electrical outfittings design in shipyards

This study proposes to automate the analysis of wiring diagrams to generate cable lists by using machine learning for text classification and pre-trained Deep Neural Network (DNN)-based image classification to detect cable routes. In shipyards, many drawings are produced for each ship, and analyzing...

Full description

Saved in:
Bibliographic Details
Main Authors: Adrian Rahmanto Putra, Sol Ha, Kwang-Phil Park
Format: Article
Language:English
Published: Elsevier 2024-01-01
Series:International Journal of Naval Architecture and Ocean Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2092678224000499
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846109760596738048
author Adrian Rahmanto Putra
Sol Ha
Kwang-Phil Park
author_facet Adrian Rahmanto Putra
Sol Ha
Kwang-Phil Park
author_sort Adrian Rahmanto Putra
collection DOAJ
description This study proposes to automate the analysis of wiring diagrams to generate cable lists by using machine learning for text classification and pre-trained Deep Neural Network (DNN)-based image classification to detect cable routes. In shipyards, many drawings are produced for each ship, and analyzing these drawings, especially wiring diagrams, to generate cable lists for the Bill of Materials (BOM) can be a time-consuming and error-prone task. This process is performed manually by reading the cable routes and entering the information into a spreadsheet. To address these challenges, this study aims to automate the information extraction from wiring diagrams. The process involves extracting text from the PDF document and classifying it using machine learning, followed by using DNN-based image classification to trace cable routes and identify the relevant annotations. The developed algorithm was tested on three PDF wiring diagram samples and achieved an average accuracy of about 90%, confirming its effectiveness.
format Article
id doaj-art-0566e41c1e7b4126a6641f8e92ed67df
institution Kabale University
issn 2092-6782
language English
publishDate 2024-01-01
publisher Elsevier
record_format Article
series International Journal of Naval Architecture and Ocean Engineering
spelling doaj-art-0566e41c1e7b4126a6641f8e92ed67df2024-12-25T04:21:14ZengElsevierInternational Journal of Naval Architecture and Ocean Engineering2092-67822024-01-0116100630Automatic extraction of cable connection information from 2D drawings for electrical outfittings design in shipyardsAdrian Rahmanto Putra0Sol Ha1Kwang-Phil Park2Infoget System Co., Ltd., Seoul, Republic of KoreaSchool of Mechanical and Ocean Engineering, Mokpo National University, Jeollanam-do, Republic of Korea; Corresponding author.Department of Autonomous Vehicle System Engineering, Chungnam National University, Daejeon, Republic of Korea; Corresponding author.This study proposes to automate the analysis of wiring diagrams to generate cable lists by using machine learning for text classification and pre-trained Deep Neural Network (DNN)-based image classification to detect cable routes. In shipyards, many drawings are produced for each ship, and analyzing these drawings, especially wiring diagrams, to generate cable lists for the Bill of Materials (BOM) can be a time-consuming and error-prone task. This process is performed manually by reading the cable routes and entering the information into a spreadsheet. To address these challenges, this study aims to automate the information extraction from wiring diagrams. The process involves extracting text from the PDF document and classifying it using machine learning, followed by using DNN-based image classification to trace cable routes and identify the relevant annotations. The developed algorithm was tested on three PDF wiring diagram samples and achieved an average accuracy of about 90%, confirming its effectiveness.http://www.sciencedirect.com/science/article/pii/S2092678224000499Cable connection analysisWiring diagramMachine learningShip design automationText classificationLine detection
spellingShingle Adrian Rahmanto Putra
Sol Ha
Kwang-Phil Park
Automatic extraction of cable connection information from 2D drawings for electrical outfittings design in shipyards
International Journal of Naval Architecture and Ocean Engineering
Cable connection analysis
Wiring diagram
Machine learning
Ship design automation
Text classification
Line detection
title Automatic extraction of cable connection information from 2D drawings for electrical outfittings design in shipyards
title_full Automatic extraction of cable connection information from 2D drawings for electrical outfittings design in shipyards
title_fullStr Automatic extraction of cable connection information from 2D drawings for electrical outfittings design in shipyards
title_full_unstemmed Automatic extraction of cable connection information from 2D drawings for electrical outfittings design in shipyards
title_short Automatic extraction of cable connection information from 2D drawings for electrical outfittings design in shipyards
title_sort automatic extraction of cable connection information from 2d drawings for electrical outfittings design in shipyards
topic Cable connection analysis
Wiring diagram
Machine learning
Ship design automation
Text classification
Line detection
url http://www.sciencedirect.com/science/article/pii/S2092678224000499
work_keys_str_mv AT adrianrahmantoputra automaticextractionofcableconnectioninformationfrom2ddrawingsforelectricaloutfittingsdesigninshipyards
AT solha automaticextractionofcableconnectioninformationfrom2ddrawingsforelectricaloutfittingsdesigninshipyards
AT kwangphilpark automaticextractionofcableconnectioninformationfrom2ddrawingsforelectricaloutfittingsdesigninshipyards