Deep convolutional neural network based on self-distillation for tool wear recognition
文献类型:期刊论文
作者 | Pan, Yi1,2; Hao, Ling2; He, Jianliang2; Ding, Kun1; Yu, Qiang1; Wang, Yulin2 |
刊名 | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE |
出版日期 | 2024-06-01 |
卷号 | 132页码:12 |
ISSN号 | 0952-1976 |
关键词 | Tool fault diagnosis Mobile inspection robots Self-distillation Industry 4.0 Deep learning |
DOI | 10.1016/j.engappai.2024.107851 |
通讯作者 | Wang, Yulin(wyl_sjtu@126.com) |
英文摘要 | In the ever-evolving Industry 4.0 landscape, traditional manufacturing constantly merges with cutting-edge AI technology. In manufacturing, Computer Numerical Control (CNC) machine tools heavily depend on cutting tools. Most existing researches on tool fault diagnosis center on machines customized for visual monitoring, overlooking the specific challenges posed by unmodifiable production line equipment. Mobile inspection robots, though versatile, are constrained by resources, limiting the use of large deep learning models. In view of this, we aim to introduce a tailored tool wear recognition solution for resource-constrained mobile inspection robots. To achieve this goal, a lightweight deep learning model with a unique single -stage self -distillation approach is presented. This method efficiently transfers knowledge from deep networks to shallow networks, optimizing performance while minimizing training costs. From our results, we achieve a promising top -1 accuracy of 97.66% after 50 training epochs within 1 h and 20 min of training time. This surpasses the student model obtained through offline distillation by 4.30%, saving 59.39% of training time, and improves recognition accuracy by 2.43% compared to online distillation, while reducing training time by 44.83%. Compared with the state-of-the-art method TinyVit, 12.09% of training time is saved with an accuracy improvement of 1.48%. In conclusion, our model manifests a desirable balance between efficiency and accuracy, rendering it highly suitable for deployment on mobile terminals. Furthermore, ablation experiments confirm the robustness of our method's internal structure in influencing final performance. This research addresses tool fault diagnosis in unmodifiable production line tools and is expected to provide a practical, efficient solution with broad implications for Industry 4.0. |
资助项目 | National Key R&D Program of China[2022YFB3402100] ; National Natural Science Foundation of China[52075267] |
WOS研究方向 | Automation & Control Systems ; Computer Science ; Engineering |
语种 | 英语 |
出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
WOS记录号 | WOS:001164955800001 |
资助机构 | National Key R&D Program of China ; National Natural Science Foundation of China |
源URL | [http://ir.ia.ac.cn/handle/173211/55628] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Wang, Yulin |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Nanjing Univ Sci & Technol, Sch Mech Engn, Xiaolingwei 200, Nanjing 210094, Peoples R China |
推荐引用方式 GB/T 7714 | Pan, Yi,Hao, Ling,He, Jianliang,et al. Deep convolutional neural network based on self-distillation for tool wear recognition[J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE,2024,132:12. |
APA | Pan, Yi,Hao, Ling,He, Jianliang,Ding, Kun,Yu, Qiang,&Wang, Yulin.(2024).Deep convolutional neural network based on self-distillation for tool wear recognition.ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE,132,12. |
MLA | Pan, Yi,et al."Deep convolutional neural network based on self-distillation for tool wear recognition".ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 132(2024):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。