A Deep Learning Module Design for Workspace Identification in Manufacturing Industry

被引：1

作者：

Kim, Jeong-Su ^{[1
]}

Lee, Dong Myung ^{[2
]}

机构：

[1] Tongmyong Univ, Grad Sch, Dept Comp & Media Engn, Busan, South Korea

[2] Tongmyong Univ, Dept Comp Engn, Busan, South Korea

来源：

3RD INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE IN INFORMATION AND COMMUNICATION (IEEE ICAIIC 2021) | 2021年

基金：

新加坡国家研究基金会;

关键词：

scene recognition; deep learning; convolutional neural network; datasets; places365; manufacturing workspace;

D O I：

10.1109/ICAIIC51459.2021.9415257

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, in order to solve various problems occurring in the workspace, a deep learning-based workspace identification module was designed, and the performance was analyzed through an experiment on the recognition accuracy according to the configuration of the training dataset and the number of training. The data model of the designed deep learning module is ResNet18, and after setting up three dataset strategies, a dataset using five types of workspaces of the manufacturing industry was selected. In terms of the average top 5 and all training, strategy 2 was 812% and 76.4%, respectivel, confirming that it was the best among the 3 strategies. In the future, after upgrading the designed module, it is planned to implement a module with real-time workspace identification performance level of practical use in a mobile environment with an image input device installed.

引用

页码：390 / 393

页数：4

共 50 条

[31] Real Time Big Data Analytics for Tool Wear Protection with Deep Learning in Manufacturing Industry
Cakir, Altan
Ozkaya, Emre
Akkus, Fatih
Kucukbas, Ezgi
Yilmaz, Okan
INTELLIGENT AND FUZZY SYSTEMS: DIGITAL ACCELERATION AND THE NEW NORMAL, INFUS 2022, VOL 2, 2022, 505 : 148 - 155
[32] Anomaly Detection in Hobbing Tool Images: Using An Unsupervised Deep Learning Approach in Manufacturing Industry
Kiefer, Daniel
Wezel, Stefan
Boettcher, Alexander
Grimm, Florian
Straub, Tim
Bitsch, Gunter
Van Dinther, Clemens
5TH INTERNATIONAL CONFERENCE ON INDUSTRY 4.0 AND SMART MANUFACTURING, ISM 2023, 2024, 232 : 2396 - 2405
[33] Safe Locomotion Within Confined Workspace using Deep Reinforcement Learning
Dastider, Apan
Raza, Sayyed Jaffar Ali
Lin, Mingjie
2021 FIFTH IEEE INTERNATIONAL CONFERENCE ON ROBOTIC COMPUTING (IRC 2021), 2021, : 111 - 114
[34] Design and Manufacturing of High Concentration Reflected Photovoltaic Module
Lin, Yuli
Hsu, Cheng-Yi
Chiang, Yu-De
NEW MATERIALS AND PROCESSES, PTS 1-3, 2012, 476-478 : 1241 - +
[35] The Effects of Module-based Design on Design and Manufacturing of a Complex Product
Ristimaeki, L.
Ojanen, V.
Kaessi, T.
MECHANIKA 2010: PROCEEDINGS OF THE 15TH INTERNATIONAL CONFERENCE, 2010, : 380 - 385
[36] Lean Rules Identification and Classification for Manufacturing Industry
Mourtzis, D.
Papathanasiou, P.
Fotia, S.
26TH CIRP DESIGN CONFERENCE, 2016, 50 : 198 - 203
[37] Design for manufacturing in the semiconductor industry: The litho/design workshops
Schellenberg, FM
TWELFTH INTERNATIONAL CONFERENCE ON VLSI DESIGN, PROCEEDINGS, 1999, : 111 - 119
[38] Identification, characterization, and design of plant genome sequences using deep learning
Wang, Zhenye
Yuan, Hao
Yan, Jianbing
Liu, Jianxiao
PLANT JOURNAL, 2025, 121 (01):
[39] Design and Implementation of Chaetodontidae Fish Identification Algorithms with Deep Learning Methods
Santoso, S. A.
Jaya, I
Iqbal, M.
2021 IEEE OCEAN ENGINEERING TECHNOLOGY AND INNOVATION CONFERENCE: OCEAN OBSERVATION, TECHNOLOGY AND INNOVATION IN SUPPORT OF OCEAN DECADE OF SCIENCE (OETIC), 2021, : 39 - 44
[40] Environmental Art Design Element Identification and Mining Based on Deep Learning
Li W.
Li C.
Computer-Aided Design and Applications, 2024, 21 (S19): : 164 - 178

← 1 2 3 4 5 →