Weld penetration identification with deep learning method based on auditory spectrum images of arc sounds
文献类型:期刊论文
作者 | Gao, Yanfeng1,5; Wang, Qisheng2,3; Xiao, Jianhua4; Xiong, Genliang1,5; Zhang, Hua1,5 |
刊名 | WELDING IN THE WORLD |
出版日期 | 2022-09-08 |
ISSN号 | 0043-2288 |
关键词 | Weld penetration Deep learning method Arc sounds Auditory spectrum Convolution neural network |
DOI | 10.1007/s40194-022-01373-7 |
通讯作者 | Gao, Yanfeng(gyf_2672@163.com) ; Wang, Qisheng(wangqisheng@mail.ustc.edu.cn) |
英文摘要 | Penetration states significantly affect the service performance of weld products. For improving welding quality, it is essential to real-timely monitor the penetration states of molten pool during welding process. This study adopts arc sound signals to identify penetration states of weld seam. Firstly, the time-frequency spectrum images of arc sounds are obtained with short-time Fourier transform. And based on a convolution neural network, the penetration states of weld seam are identified. For improving the anti-interference ability of the proposed identification method, a mathematical model that simulates the functions of human auditory system is developed. The auditory spectrum images of arc sounds are acquired with this model. Based on the auditory spectrum images of arc sounds, the penetration states are identified. The experimental results show that the proposed method has high anti-interference ability. When the signal-to-noise ratio is less than 5 dB, the accuracy rate of identification keeps more than 95%. |
WOS关键词 | RECOGNITION |
资助项目 | Natural Science Foundation of Shanghai[21ZR1425900] ; Natural Science Foundation of Shanghai[21010501600] |
WOS研究方向 | Metallurgy & Metallurgical Engineering |
语种 | 英语 |
出版者 | SPRINGER HEIDELBERG |
WOS记录号 | WOS:000852269600001 |
资助机构 | Natural Science Foundation of Shanghai |
源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/128970] |
专题 | 中国科学院合肥物质科学研究院 |
通讯作者 | Gao, Yanfeng; Wang, Qisheng |
作者单位 | 1.Shanghai Univ Engn Sci, Sch Mech & Automot Engn, Shanghai 201620, Peoples R China 2.Chinese Acad Sci, Inst Intelligent Machines, Hefei Inst Phys Sci, Huihong Bldg,Changwu Middle Rd 801, Changzhou 213164, Jiangsu, Peoples R China 3.Univ Sci & Technol China, Dept Sci Isl, Hefei 230026, Anhui, Peoples R China 4.Shanghai Univ Engn Sci, Sch Chem & Chem Engn, Shanghai 201620, Peoples R China 5.Shanghai Collaborat Innovat Ctr Intelligent Mfg R, Shanghai 201620, Peoples R China |
推荐引用方式 GB/T 7714 | Gao, Yanfeng,Wang, Qisheng,Xiao, Jianhua,et al. Weld penetration identification with deep learning method based on auditory spectrum images of arc sounds[J]. WELDING IN THE WORLD,2022. |
APA | Gao, Yanfeng,Wang, Qisheng,Xiao, Jianhua,Xiong, Genliang,&Zhang, Hua.(2022).Weld penetration identification with deep learning method based on auditory spectrum images of arc sounds.WELDING IN THE WORLD. |
MLA | Gao, Yanfeng,et al."Weld penetration identification with deep learning method based on auditory spectrum images of arc sounds".WELDING IN THE WORLD (2022). |
入库方式: OAI收割
来源:合肥物质科学研究院
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。