Citation: Ma, H.; Lee, S. Smart
System to Detect Painting Defects in
Shipyards: Vision AI and a
Deep-Learning Approach. Appl. Sci.
2022, 12, 2412. https://doi.org/
10.3390/app12052412
Academic Editor: Manuel Armada
Received: 20 January 2022
Accepted: 23 February 2022
Published: 25 February 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Smart System to Detect Painting Defects in Shipyards: Vision
AI and a Deep-Learning Approach
Hanseok Ma
1
and Sunggeun Lee
2,
*
1
Smart Yard R&D Department, Daewoo Shipbuilding and Marine Engineering, 3370, Geoje-daero,
Geoje-si 53302, Korea; mhs@dsme.co.kr
2
Division of Electronics and Electrical Information Engineering, Korea Maritime and Ocean University, 727,
Taejong-ro, Yeongdo-gu, Busan 49112, Korea
* Correspondence: sglee48@kmou.ac.kr
Abstract:
The shipbuilding industry has recently had to address several problems, such as improving
productivity and overcoming the limitations of existing worker-dependent defect-inspection systems
for painting on large steel plates while meeting the demands for information and smart-factory
systems for quality management. The target shipyard previously used human visual inspection
and there was no system to manage defect frequency, type, or history. This is challenging because
these defects can have different sizes, shapes, and locations. In addition, the shipyard environment
is variable and limits the options for camera placements. To solve these problems, we developed a
new Vision AI deep-learning system for detecting painting defects in an actual shipyard production
line and conducted experiments to optimize and evaluate the performance. We then configured and
installed the Vision AI system to control the actual shipyard production line through a programmable
logic controller interface. The installed system analyzes images in real-time and is expected to improve
productivity by 11% and reduce quality incidents by 2%. This is the first practical application of AI
operating in conjunction with the control unit of the actual shipyard production line. The lessons
learned here can be applied to other industrial systems.
Keywords:
smart factory; deep learning; steel plate painting; painting defect detection; production
line programmable logic controller
1. Introduction
The manufacturing industry values not only preparedness for manpower shortages
but also responsibility in environmental, social, and governance (ESG) management. For
this reason, companies are constantly investing in the construction of smart factories, vision
systems, and smart manufacturing using artificial intelligence (AI).
Recently, most equipment related to manufacturing has been fully connected over
a wireless network, monitored by sensors, and controlled by the manufacturing system.
Computer intelligence reduces costs associated with the improvement of systems and
product quality, thereby promoting productivity and sustainability. It provides various
core technologies to cyber-physical systems (CPS) through the internet of things (IoT),
cloud computing, and smart technologies. These technologies play a role in solving various
problems while developing manufacturing technologies in modern society [1–3].
However, sufficient levels of stability and accuracy in production lines cannot be
guaranteed by introducing such algorithms at many actual production sites including
shipyards. The painting process line of the target shipyard is continuously monitored
through CCTV at places that are difficult for humans to access. Such CCTV monitoring
enables the determination of defects and the operation of the stop switch. It also completely
stops the process line during work breaks or maintenance work. In addition, the absence of
a quality management system decreases work efficiency and productivity. To overcome this,
methods were proposed for process improvement in industrial sites using various methods.
Appl. Sci. 2022, 12, 2412. https://doi.org/10.3390/app12052412 https://www.mdpi.com/journal/applsci
