Deep learning based online metallic surface defect detection method for wire and arc additive manufacturing
文献类型:期刊论文
作者 | Li, Wenhao7; Zhang, Haiou7; Wang, Guilan1; Xiong, Gang5,6; Zhao, Meihua3,4; Li, Guokuan2; Li, Runsheng7 |
刊名 | ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING |
出版日期 | 2023-04-01 |
卷号 | 80页码:12 |
ISSN号 | 0736-5845 |
关键词 | Wire and arc additive manufacturing Defect detection Online Deep learning |
DOI | 10.1016/j.rcim.2022.102470 |
通讯作者 | Li, Runsheng(lirunsheng@hust.edu.cn) |
英文摘要 | Wire and arc additive manufacturing (WAAM) is an emerging manufacturing technology that is widely used in different manufacturing industries. To achieve fully automated production, WAAM requires a dependable, efficient, and automatic defect detection system. Although machine learning is dominant in the object detection domain, classic algorithms have defect detection difficulty in WAAM due to complex defect types and noisy detection environments. This paper presents a deep learning-based novel automatic defect detection solution, you only look once (YOLO)-attention, based on YOLOv4, which achieves both fast and accurate defect detection for WAAM. YOLO-attention makes improvements on three existing object detection models: the channel-wise attention mechanism, multiple spatial pyramid pooling, and exponential moving average. The evaluation on the WAAM defect dataset shows that our model obtains a 94.5 mean average precision (mAP) with at least 42 frames per second. This method has been applied to additive manufacturing of single-pass, multi-pass deposition and parts. It demonstrates its feasibility in practical industrial applications and has potential as a vision-based methodology that can be implemented in real-time defect detection systems. |
WOS关键词 | TESTING APPLICATION ; IMAGES ; INSPECTION ; YOLO |
资助项目 | National Natural Science Foundation of China[U1909218] ; National Natural Science Foundation of China[61872365] ; Research and Development of Laser Repair Technology and Equipment, China for Landing Gear and Other Key Metal Parts of Transport Aircraft, Hubei Province Technology Innovation Special Key Project[2019AAA003] ; Scientific Instrument Developing Project of the Chinese Academy of Sciences (CAS)[YZQT014] ; Guangdong Basic and Applied Basic Research Foundation[2021B1515140034] |
WOS研究方向 | Computer Science ; Engineering ; Robotics |
语种 | 英语 |
出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
WOS记录号 | WOS:000869978400003 |
资助机构 | National Natural Science Foundation of China ; Research and Development of Laser Repair Technology and Equipment, China for Landing Gear and Other Key Metal Parts of Transport Aircraft, Hubei Province Technology Innovation Special Key Project ; Scientific Instrument Developing Project of the Chinese Academy of Sciences (CAS) ; Guangdong Basic and Applied Basic Research Foundation |
源URL | [http://ir.ia.ac.cn/handle/173211/50299] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队 |
通讯作者 | Li, Runsheng |
作者单位 | 1.Huazhong Univ Sci & Technol, Sch Mat Sci & Engn, Wuhan 430074, Hubei, Peoples R China 2.Wuhan Natl Lab Optoelect, Wuhan 430074, Hubei, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 5.Chinese Acad Sci, Guangdong Engn Res Ctr 3D Printing & Intelligent M, Cloud Comp Ctr, Donggguan 523808, Peoples R China 6.Chinese Acad Sci, Inst Automat, Beijing Engn Res Ctr Intelligent Syst & Technol, Beijing 100190, Peoples R China 7.Huazhong Univ Sci & Technol, Sch Mech Sci & Engn, Wuhan 430074, Hubei, Peoples R China |
推荐引用方式 GB/T 7714 | Li, Wenhao,Zhang, Haiou,Wang, Guilan,et al. Deep learning based online metallic surface defect detection method for wire and arc additive manufacturing[J]. ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING,2023,80:12. |
APA | Li, Wenhao.,Zhang, Haiou.,Wang, Guilan.,Xiong, Gang.,Zhao, Meihua.,...&Li, Runsheng.(2023).Deep learning based online metallic surface defect detection method for wire and arc additive manufacturing.ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING,80,12. |
MLA | Li, Wenhao,et al."Deep learning based online metallic surface defect detection method for wire and arc additive manufacturing".ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING 80(2023):12. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。