New trends on digitisation of complex engineering drawings

Carlos Francisco Moreno-garcía, Eyad Elyan, Chrisina Jayne

Research output: Contribution to journalArticle

117 Downloads (Pure)

Abstract

Engineering drawings are commonly used across different industries such as oil and gas, mechanical engineering and others. Digitising these drawings is becoming increasingly important. This is mainly due to the legacy of drawings and documents that may provide rich source of information for industries. Analysing these drawings often requires applying a set of digital image processing methods to detect and classify symbols and other components. Despite the recent significant advances in image processing, and in particular in deep neural networks, automatic analysis and processing of these engineering drawings is still far from being complete. This paper presents a general framework for complex engineering drawing digitisation. A thorough and critical review of relevant literature, methods and algorithms in machine learning and machine vision is presented. Real-life industrial scenario on how to contextualise the digitised information from specific type of these drawings, namely piping and instrumentation diagrams, is discussed in details. A discussion of how new trends on machine vision such as deep learning could be applied to this domain is presented with conclusions and suggestions for future research directions.
Original languageEnglish
Pages (from-to)1695-1712
JournalNeural Computing and Applications
Volume31
Issue number6
Early online date13 Jun 2018
DOIs
Publication statusPublished - 30 Jun 2019

Fingerprint

Drawing (graphics)
Analog to digital conversion
Computer vision
Image processing
Mechanical engineering
Learning systems
Industry

Cite this

Moreno-garcía, Carlos Francisco ; Elyan, Eyad ; Jayne, Chrisina. / New trends on digitisation of complex engineering drawings. In: Neural Computing and Applications. 2019 ; Vol. 31, No. 6. pp. 1695-1712.
@article{03b12a8173f6455eaa3ee036fd05cca4,
title = "New trends on digitisation of complex engineering drawings",
abstract = "Engineering drawings are commonly used across different industries such as oil and gas, mechanical engineering and others. Digitising these drawings is becoming increasingly important. This is mainly due to the legacy of drawings and documents that may provide rich source of information for industries. Analysing these drawings often requires applying a set of digital image processing methods to detect and classify symbols and other components. Despite the recent significant advances in image processing, and in particular in deep neural networks, automatic analysis and processing of these engineering drawings is still far from being complete. This paper presents a general framework for complex engineering drawing digitisation. A thorough and critical review of relevant literature, methods and algorithms in machine learning and machine vision is presented. Real-life industrial scenario on how to contextualise the digitised information from specific type of these drawings, namely piping and instrumentation diagrams, is discussed in details. A discussion of how new trends on machine vision such as deep learning could be applied to this domain is presented with conclusions and suggestions for future research directions.",
author = "Moreno-garc{\'i}a, {Carlos Francisco} and Eyad Elyan and Chrisina Jayne",
year = "2019",
month = "6",
day = "30",
doi = "10.1007/s00521-018-3583-1",
language = "English",
volume = "31",
pages = "1695--1712",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",
number = "6",

}

New trends on digitisation of complex engineering drawings. / Moreno-garcía, Carlos Francisco; Elyan, Eyad; Jayne, Chrisina.

In: Neural Computing and Applications, Vol. 31, No. 6, 30.06.2019, p. 1695-1712.

Research output: Contribution to journalArticle

TY - JOUR

T1 - New trends on digitisation of complex engineering drawings

AU - Moreno-garcía, Carlos Francisco

AU - Elyan, Eyad

AU - Jayne, Chrisina

PY - 2019/6/30

Y1 - 2019/6/30

N2 - Engineering drawings are commonly used across different industries such as oil and gas, mechanical engineering and others. Digitising these drawings is becoming increasingly important. This is mainly due to the legacy of drawings and documents that may provide rich source of information for industries. Analysing these drawings often requires applying a set of digital image processing methods to detect and classify symbols and other components. Despite the recent significant advances in image processing, and in particular in deep neural networks, automatic analysis and processing of these engineering drawings is still far from being complete. This paper presents a general framework for complex engineering drawing digitisation. A thorough and critical review of relevant literature, methods and algorithms in machine learning and machine vision is presented. Real-life industrial scenario on how to contextualise the digitised information from specific type of these drawings, namely piping and instrumentation diagrams, is discussed in details. A discussion of how new trends on machine vision such as deep learning could be applied to this domain is presented with conclusions and suggestions for future research directions.

AB - Engineering drawings are commonly used across different industries such as oil and gas, mechanical engineering and others. Digitising these drawings is becoming increasingly important. This is mainly due to the legacy of drawings and documents that may provide rich source of information for industries. Analysing these drawings often requires applying a set of digital image processing methods to detect and classify symbols and other components. Despite the recent significant advances in image processing, and in particular in deep neural networks, automatic analysis and processing of these engineering drawings is still far from being complete. This paper presents a general framework for complex engineering drawing digitisation. A thorough and critical review of relevant literature, methods and algorithms in machine learning and machine vision is presented. Real-life industrial scenario on how to contextualise the digitised information from specific type of these drawings, namely piping and instrumentation diagrams, is discussed in details. A discussion of how new trends on machine vision such as deep learning could be applied to this domain is presented with conclusions and suggestions for future research directions.

U2 - 10.1007/s00521-018-3583-1

DO - 10.1007/s00521-018-3583-1

M3 - Article

VL - 31

SP - 1695

EP - 1712

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 6

ER -