Deep learning based online metallic surface defect detection method for wire and arc additive manufacturing
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...
Saved in:
| Published in | Robotics and computer-integrated manufacturing Vol. 80; p. 102470 |
|---|---|
| Main Authors | , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Ltd
01.04.2023
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | 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.
•Propose a defect detection method in additive manufacturing based on deep learning.•Use attention model, multiple spatial pyramid pooling and exponential moving average.•Establish a wire and arc additive manufacturing defect dataset to verify the effect.•YOLO-attention achieves a mean average precision of 94.5%. |
|---|---|
| AbstractList | 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.
•Propose a defect detection method in additive manufacturing based on deep learning.•Use attention model, multiple spatial pyramid pooling and exponential moving average.•Establish a wire and arc additive manufacturing defect dataset to verify the effect.•YOLO-attention achieves a mean average precision of 94.5%. |
| ArticleNumber | 102470 |
| Author | Zhang, Haiou Li, Runsheng Li, Wenhao Wang, Guilan Xiong, Gang Li, Guokuan Zhao, Meihua |
| Author_xml | – sequence: 1 givenname: Wenhao orcidid: 0000-0002-5428-258X surname: Li fullname: Li, Wenhao organization: School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, 430074, China – sequence: 2 givenname: Haiou surname: Zhang fullname: Zhang, Haiou organization: School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, 430074, China – sequence: 3 givenname: Guilan surname: Wang fullname: Wang, Guilan organization: School of Materials Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, 430074, China – sequence: 4 givenname: Gang surname: Xiong fullname: Xiong, Gang organization: Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China – sequence: 5 givenname: Meihua orcidid: 0000-0003-0108-3752 surname: Zhao fullname: Zhao, Meihua organization: State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China – sequence: 6 givenname: Guokuan surname: Li fullname: Li, Guokuan organization: Wuhan National Laboratory for Optoelectronics, Wuhan, Hubei, 430074, China – sequence: 7 givenname: Runsheng orcidid: 0000-0002-1904-9774 surname: Li fullname: Li, Runsheng email: lirunsheng@hust.edu.cn organization: School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, 430074, China |
| BookMark | eNp9kM1OAyEURlnUxFZ9AVe8wFQGZjo0cWPqb9LEja7JHbgodQoN0BrfXiZ15aKrL-Fyvtx7ZmTig0dCrms2r1m9uNnMo3bbOWeclwfedGxCpqwTi6qVTXtOZiltGCuDVkzJ1z3ijg4I0Tv_QXtIaGjwg_NIt5hhGJymaR8taKQGLepcIpdwwY8_PoOhNkT67SJS8IZC1BSMcdkdSgX4fUHzPpb2S3JmYUh49ZcX5P3x4W31XK1fn15Wd-tKC8ZyZYVgyDpcGt31veiFaZadtFbW7QKltH3fojEIuIQaJQcEbrpGam2YbVhbiwsij706hpQiWqVdhnHhHMENqmZqFKU2ahSlRlHqKKqg_B-6i24L8ec0dHuEsBx1cBhV0g69RlOc6KxMcKfwXxutiTw |
| CitedBy_id | crossref_primary_10_1115_1_4065525 crossref_primary_10_1002_srin_202300369 crossref_primary_10_1088_1361_6501_acfe2f crossref_primary_10_1080_17452759_2023_2266658 crossref_primary_10_1016_j_rcim_2024_102806 crossref_primary_10_1080_17452759_2023_2294336 crossref_primary_10_1080_24725854_2024_2443592 crossref_primary_10_1063_5_0185513 crossref_primary_10_1016_j_eswa_2024_125741 crossref_primary_10_3390_su162310724 crossref_primary_10_1016_j_measurement_2024_114975 crossref_primary_10_1016_j_addma_2023_103547 crossref_primary_10_1016_j_jmapro_2024_07_060 crossref_primary_10_1080_17452759_2024_2409390 crossref_primary_10_1109_ACCESS_2025_3545057 crossref_primary_10_1007_s00170_023_12624_2 crossref_primary_10_1016_j_engappai_2023_106143 crossref_primary_10_1016_j_jii_2023_100484 crossref_primary_10_1088_1361_6501_ad80b5 crossref_primary_10_1145_3715851 crossref_primary_10_1016_j_ijmecsci_2023_108269 crossref_primary_10_1007_s43069_024_00337_5 crossref_primary_10_1108_IR_05_2024_0215 crossref_primary_10_1016_j_jmapro_2023_03_016 crossref_primary_10_1016_j_rcim_2023_102639 crossref_primary_10_1016_j_engappai_2023_107717 crossref_primary_10_1016_j_measurement_2024_114689 crossref_primary_10_1016_j_jmapro_2024_08_033 crossref_primary_10_3390_s24020429 crossref_primary_10_1016_j_optlastec_2023_110243 crossref_primary_10_1016_j_rcim_2023_102581 crossref_primary_10_1016_j_eswa_2023_120959 crossref_primary_10_1080_02670836_2023_2246772 crossref_primary_10_1016_j_rineng_2024_103462 crossref_primary_10_7717_peerj_cs_2224 crossref_primary_10_1177_09544062241283330 crossref_primary_10_1007_s10845_024_02487_z crossref_primary_10_1016_j_amf_2024_200159 crossref_primary_10_1016_j_jmrt_2024_06_018 crossref_primary_10_1002_tee_24158 crossref_primary_10_1007_s10921_024_01107_3 crossref_primary_10_1016_j_rcim_2023_102575 crossref_primary_10_1109_TCSS_2024_3407823 crossref_primary_10_3390_ma17061373 crossref_primary_10_1016_j_compositesb_2023_111006 crossref_primary_10_3390_electronics12163446 crossref_primary_10_1007_s40964_024_00612_1 crossref_primary_10_1080_17452759_2023_2291471 crossref_primary_10_1016_j_compind_2024_104084 crossref_primary_10_1016_j_addma_2024_104323 crossref_primary_10_1007_s13198_024_02472_y crossref_primary_10_1016_j_eswa_2024_126212 crossref_primary_10_1007_s10845_024_02387_2 crossref_primary_10_1016_j_compind_2024_104154 crossref_primary_10_3390_s23167291 crossref_primary_10_1080_09507116_2023_2252733 crossref_primary_10_1109_TIM_2023_3302372 crossref_primary_10_1016_j_aei_2025_103138 crossref_primary_10_1016_j_engappai_2024_108075 crossref_primary_10_1109_TPS_2024_3350203 crossref_primary_10_1088_2631_8695_ad777c crossref_primary_10_1177_03019233241296959 crossref_primary_10_1016_j_optlaseng_2024_108369 crossref_primary_10_1016_j_mtcomm_2024_110294 crossref_primary_10_3390_s24227127 crossref_primary_10_32604_cmes_2024_054735 crossref_primary_10_1088_1361_6501_ad26c9 crossref_primary_10_1016_j_compind_2023_103911 crossref_primary_10_1016_j_eswa_2023_121529 crossref_primary_10_1080_10426914_2023_2254386 crossref_primary_10_1016_j_ijmecsci_2024_108963 crossref_primary_10_1016_j_matchar_2024_113985 crossref_primary_10_1016_j_measurement_2024_115193 crossref_primary_10_1016_j_jmapro_2023_12_033 crossref_primary_10_1016_j_jmsy_2023_11_017 crossref_primary_10_3390_jimaging10070164 crossref_primary_10_1007_s00170_023_12798_9 crossref_primary_10_3390_a15120466 crossref_primary_10_3390_app13126898 crossref_primary_10_1016_j_compind_2023_103963 crossref_primary_10_1016_j_jmsy_2023_11_014 crossref_primary_10_3390_ma16103635 crossref_primary_10_1038_s41598_025_88109_x crossref_primary_10_3390_a17120574 crossref_primary_10_1016_j_jmapro_2024_04_024 crossref_primary_10_1007_s11554_025_01656_4 crossref_primary_10_1016_j_eswa_2023_122669 crossref_primary_10_1007_s40747_024_01554_5 crossref_primary_10_1088_1361_6501_ad63c2 crossref_primary_10_3390_s24134397 crossref_primary_10_1007_s00170_024_13641_5 crossref_primary_10_1080_17452759_2023_2210553 crossref_primary_10_12677_MOS_2023_126522 crossref_primary_10_1016_j_sna_2024_115547 crossref_primary_10_3390_app14135576 crossref_primary_10_1109_ACCESS_2023_3271748 crossref_primary_10_1016_j_engappai_2024_109723 crossref_primary_10_1108_RPJ_04_2023_0133 crossref_primary_10_1016_j_optlastec_2025_112413 crossref_primary_10_3390_math12213414 crossref_primary_10_1016_j_jcomc_2024_100451 crossref_primary_10_3390_machines11080834 crossref_primary_10_3390_met13040648 crossref_primary_10_1371_journal_pone_0297059 crossref_primary_10_3390_math12162480 |
| Cites_doi | 10.1109/CVPR.2017.690 10.1016/j.measurement.2020.107546 10.1016/j.ifacol.2018.09.412 10.1016/j.neucom.2014.09.007 10.1108/13552540510612929 10.1109/TCYB.2017.2668395 10.1016/j.neucom.2017.02.021 10.1109/ICCV.2017.324 10.1109/TII.2014.2359416 10.1016/j.jmapro.2018.08.001 10.1016/j.ijleo.2015.04.017 10.1016/j.asoc.2016.10.030 10.1016/j.apsusc.2015.05.033 10.1080/14786451.2013.826223 10.1016/j.imavis.2009.03.007 10.1016/j.polymertesting.2015.04.013 10.1080/17452759.2015.1111519 10.1109/CVPR.2017.106 10.1007/s11665-014-0958-z 10.1108/RPJ-05-2019-0123 10.1016/j.matdes.2006.08.008 10.1109/TII.2015.2417676 10.1109/CVPR.2017.545 10.1016/j.rcim.2019.01.006 10.1109/TIM.2017.2783098 10.1115/1.4042108 10.1016/j.ins.2020.02.067 10.1109/ICCV.2015.123 10.1108/CW-07-2014-0027 10.14743/apem2018.2.281 10.1109/ICCV.2017.593 10.1109/JSEN.2016.2625815 10.1109/CVPR42600.2020.01079 10.1109/TPAMI.2015.2389824 10.1109/CVPR.2018.00745 10.3390/app8091575 10.1109/TPAMI.2016.2587642 10.1109/TIA.1982.4504068 10.1016/S0143-8166(00)00072-5 |
| ContentType | Journal Article |
| Copyright | 2022 Elsevier Ltd |
| Copyright_xml | – notice: 2022 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.rcim.2022.102470 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| ExternalDocumentID | 10_1016_j_rcim_2022_102470 S0736584522001521 |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 123 1B1 1~. 1~5 29P 4.4 457 4G. 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYFN ABBOA ABFSI ABJNI ABMAC ABWVN ABXDB ACDAQ ACGFS ACIWK ACNNM ACRLP ACRPL ADBBV ADEZE ADMUD ADNMO ADTZH AEBSH AECPX AEIPS AEKER AENEX AFFNX AFJKZ AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AIALX AIEXJ AIKHN AITUG AKRWK ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC BNPGV CS3 DU5 E.L EBS EFJIC EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG9 LY7 M41 MO0 MS~ N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PZZ Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SES SET SEW SPC SPCBC SSH SST SSV SSZ T5K UHS WUQ XPP ZMT ~G- AAYWO AAYXX ACVFH ADCNI AEUPX AFPUW AFXIZ AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKYEP APXCP CITATION |
| ID | FETCH-LOGICAL-c300t-f330e07e9dc7bb3b3d4978ff8156e88fbb5eddeae9a1e82aea2d748ccd0f40513 |
| IEDL.DBID | .~1 |
| ISSN | 0736-5845 |
| IngestDate | Tue Jul 01 02:40:47 EDT 2025 Thu Apr 24 22:59:39 EDT 2025 Sun Apr 06 06:53:37 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Wire and arc additive manufacturing Online Defect detection |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c300t-f330e07e9dc7bb3b3d4978ff8156e88fbb5eddeae9a1e82aea2d748ccd0f40513 |
| ORCID | 0000-0002-1904-9774 0000-0002-5428-258X 0000-0003-0108-3752 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_rcim_2022_102470 crossref_primary_10_1016_j_rcim_2022_102470 elsevier_sciencedirect_doi_10_1016_j_rcim_2022_102470 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | April 2023 2023-04-00 |
| PublicationDateYYYYMMDD | 2023-04-01 |
| PublicationDate_xml | – month: 04 year: 2023 text: April 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Robotics and computer-integrated manufacturing |
| PublicationYear | 2023 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Redmon, Farhadi (b52) 2018 Tao, Zhang, Ma, Liu, Xu (b46) 2018; 8 Li, Zhang, Dai, Huang, Wang (b5) 2019 S. Ren, K. He, R. Girshick, J. Sun, Faster r-CNN: Towards real-time object detection with region proposal networks, in: Advances in Neural Information Processing Systems, 2015, pp. 91–99. Zheng, Wang, Liu, Li, Ye, Ren (b59) 2019 Cunningham, Flynn, Shokrani, Dhokia, Newman (b2) 2018; 22 Cen, Zhao, Cen, Cui, Miao, Wei (b21) 2015; 149 Li, Su, Geng, Yin (b17) 2018; 51 Li, Wang, Ding, Tang, Chen, Dai, Wang, Song, Zhang (b10) 2020; 36 Wang, Zhao, Zhou, Hao (b34) 2016 Lin, Lin, Chen, Hsu (b47) 2018 Wanjara, Brochu, Jahazi (b7) 2007; 28 Mahmoudi, Ezzat, Elwany (b39) 2019; 141 J. Redmon, A. Farhadi, YOLO9000: Better, faster, stronger, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 7263–7271. Tan, Le (b42) 2019 Bai, Fang, Lin, Wang, Ju (b23) 2014; 10 Misra (b61) 2019 Susan, Sharma (b22) 2017; 239 Tastimur, Yetis, Karaköse, Akin (b27) 2016; 5 Li, Gao, Woo, Tian, Qiu, Gu (b33) 2016; 17 Mak, Peng, Yiu (b29) 2009; 27 Li, Wang, Zhao, Dai, Huang, Zhang, Chen, Song, Zhang (b11) 2021; 46 Everton, Dickens, Tuck, Dutton (b19) 2015; Vol. 9353 Wu, Pan, Ding, Cuiuri, Li, Xu, Norrish (b1) 2018; 35 Loshchilov, Hutter (b58) 2016 A. Diba, V. Sharma, A. Pazandeh, H. Pirsiavash, L. Van Gool, Weakly supervised cascaded convolutional networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 914–922. Jian, Gao, Ao (b28) 2017; 52 Kalaiselvi, Nagaraja (b30) 2015; 1 Chen, Fang, Lin, Vedantam, Gupta, Dollár, Zitnick (b15) 2015 Ren, Hung, Tan (b20) 2017; 48 He, Zhang, Ren, Sun (b56) 2015; 37 Lee (b13) 1982; IA-18 Huang, Wang, Fu, Yu, Guo, Wang (b50) 2020 M. Tan, R. Pang, Q.V. Le, Efficientdet: Scalable and efficient object detection, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10781–10790. Zhang, Gao, Chen, Zeng (b40) 2019; 30 N. Bodla, B. Singh, R. Chellappa, L.S. Davis, Soft-NMS–improving object detection with one line of code, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 5561–5569. Zhang, Ren, Yang, Wen (b41) 2020; 156 Pandiyan, Murugan, Tjahjowidodo, Caesarendra, Manyar, Then (b49) 2019; 57 Chabot, Laroche, Carcreff, Rauch, Hascoët (b37) 2019 Hu (b25) 2015; 126 Ramachandran, Zoph, Le (b62) 2017 Knezović, Dolšak (b35) 2018; 13 T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, S. Belongie, Feature pyramid networks for object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2117–2125. Borwankar, Ludwig (b24) 2018; 67 J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132–7141. Lopez, Bacelar, Pires, Santos, Sousa, Quintino (b36) 2018; 21 Ouyang, Zeng, Wang, Qiu, Luo, Tian, Li, Yang, Wang, Li (b44) 2016; 39 Frazier (b3) 2014; 23 K. He, X. Zhang, S. Ren, J. Sun, Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1026–1034. Joshi, Sheikh (b9) 2015; 10 Liu, Anguelov, Erhan, Szegedy, Reed, Fu, Berg (b16) 2016 Win, Bushroa, Hassan, Hilman, Ide-Ektessabi (b31) 2015; 11 Mazumder, Dutta, Kikuchi, Ghosh (b6) 2000; 34 Gibson, Rosen, Stucker (b4) 2014 T.-Y. Lin, P. Goyal, R. Girshick, K. He, P. Dollár, Focal loss for dense object detection, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2980–2988. Nassar, Spurgeon, Reutzel (b18) 2014 Bochkovskiy, Wang, Liao (b14) 2020 Yuan, Wu, Peng (b32) 2015; 349 Vavilov, Pawar (b38) 2015; 44 Sreenathbabu, Karunakaran, Amarnath (b8) 2005 Tsanakas, Chrysostomou, Botsaris, Gasteratos (b26) 2015; 34 Taşdemir, Nohut (b12) 2020 Vavilov (10.1016/j.rcim.2022.102470_b38) 2015; 44 Ramachandran (10.1016/j.rcim.2022.102470_b62) 2017 Bai (10.1016/j.rcim.2022.102470_b23) 2014; 10 Gibson (10.1016/j.rcim.2022.102470_b4) 2014 Chabot (10.1016/j.rcim.2022.102470_b37) 2019 Lin (10.1016/j.rcim.2022.102470_b47) 2018 Chen (10.1016/j.rcim.2022.102470_b15) 2015 Zheng (10.1016/j.rcim.2022.102470_b59) 2019 Tastimur (10.1016/j.rcim.2022.102470_b27) 2016; 5 10.1016/j.rcim.2022.102470_b60 Mazumder (10.1016/j.rcim.2022.102470_b6) 2000; 34 Pandiyan (10.1016/j.rcim.2022.102470_b49) 2019; 57 Tsanakas (10.1016/j.rcim.2022.102470_b26) 2015; 34 Zhang (10.1016/j.rcim.2022.102470_b41) 2020; 156 Win (10.1016/j.rcim.2022.102470_b31) 2015; 11 Cen (10.1016/j.rcim.2022.102470_b21) 2015; 149 Knezović (10.1016/j.rcim.2022.102470_b35) 2018; 13 Misra (10.1016/j.rcim.2022.102470_b61) 2019 Yuan (10.1016/j.rcim.2022.102470_b32) 2015; 349 Wu (10.1016/j.rcim.2022.102470_b1) 2018; 35 Li (10.1016/j.rcim.2022.102470_b10) 2020; 36 Taşdemir (10.1016/j.rcim.2022.102470_b12) 2020 Wang (10.1016/j.rcim.2022.102470_b34) 2016 Lee (10.1016/j.rcim.2022.102470_b13) 1982; IA-18 Mak (10.1016/j.rcim.2022.102470_b29) 2009; 27 Ren (10.1016/j.rcim.2022.102470_b20) 2017; 48 Tao (10.1016/j.rcim.2022.102470_b46) 2018; 8 10.1016/j.rcim.2022.102470_b48 Li (10.1016/j.rcim.2022.102470_b5) 2019 Joshi (10.1016/j.rcim.2022.102470_b9) 2015; 10 10.1016/j.rcim.2022.102470_b43 10.1016/j.rcim.2022.102470_b45 Wanjara (10.1016/j.rcim.2022.102470_b7) 2007; 28 Jian (10.1016/j.rcim.2022.102470_b28) 2017; 52 Li (10.1016/j.rcim.2022.102470_b17) 2018; 51 He (10.1016/j.rcim.2022.102470_b56) 2015; 37 Everton (10.1016/j.rcim.2022.102470_b19) 2015; Vol. 9353 Ouyang (10.1016/j.rcim.2022.102470_b44) 2016; 39 Zhang (10.1016/j.rcim.2022.102470_b40) 2019; 30 Huang (10.1016/j.rcim.2022.102470_b50) 2020 Redmon (10.1016/j.rcim.2022.102470_b52) 2018 Frazier (10.1016/j.rcim.2022.102470_b3) 2014; 23 Susan (10.1016/j.rcim.2022.102470_b22) 2017; 239 Sreenathbabu (10.1016/j.rcim.2022.102470_b8) 2005 Hu (10.1016/j.rcim.2022.102470_b25) 2015; 126 Kalaiselvi (10.1016/j.rcim.2022.102470_b30) 2015; 1 Li (10.1016/j.rcim.2022.102470_b33) 2016; 17 Lopez (10.1016/j.rcim.2022.102470_b36) 2018; 21 Cunningham (10.1016/j.rcim.2022.102470_b2) 2018; 22 Borwankar (10.1016/j.rcim.2022.102470_b24) 2018; 67 10.1016/j.rcim.2022.102470_b51 Li (10.1016/j.rcim.2022.102470_b11) 2021; 46 Liu (10.1016/j.rcim.2022.102470_b16) 2016 10.1016/j.rcim.2022.102470_b53 10.1016/j.rcim.2022.102470_b54 Loshchilov (10.1016/j.rcim.2022.102470_b58) 2016 10.1016/j.rcim.2022.102470_b55 10.1016/j.rcim.2022.102470_b57 Bochkovskiy (10.1016/j.rcim.2022.102470_b14) 2020 Tan (10.1016/j.rcim.2022.102470_b42) 2019 Nassar (10.1016/j.rcim.2022.102470_b18) 2014 Mahmoudi (10.1016/j.rcim.2022.102470_b39) 2019; 141 |
| References_xml | – year: 2016 ident: b34 article-title: Calculation of flexible printed circuit boards (FPC) global and local defect detection based on computer vision publication-title: Circuit World – volume: 149 start-page: 1206 year: 2015 end-page: 1215 ident: b21 article-title: Defect inspection for TFT-LCD images based on the low-rank matrix reconstruction publication-title: Neurocomputing – reference: S. Ren, K. He, R. Girshick, J. Sun, Faster r-CNN: Towards real-time object detection with region proposal networks, in: Advances in Neural Information Processing Systems, 2015, pp. 91–99. – volume: IA-18 start-page: 246 year: 1982 end-page: 251 ident: b13 article-title: The other electrical hazard: Electric arc blast burns publication-title: IEEE Trans. Ind. Appl. – volume: 126 start-page: 1331 year: 2015 end-page: 1340 ident: b25 article-title: Automated defect detection in textured surfaces using optimal elliptical Gabor filters publication-title: Optik – volume: 349 start-page: 472 year: 2015 end-page: 484 ident: b32 article-title: An improved Otsu method using the weighted object variance for defect detection publication-title: Appl. Surf. Sci. – volume: 28 start-page: 2278 year: 2007 end-page: 2286 ident: b7 article-title: Electron beam freeforming of stainless steel using solid wire feed publication-title: Mater. Des. – volume: 239 start-page: 232 year: 2017 end-page: 237 ident: b22 article-title: Automatic texture defect detection using Gaussian mixture entropy modeling publication-title: Neurocomputing – volume: 156 year: 2020 ident: b41 article-title: Real-time seam defect identification for Al alloys in robotic arc welding using optical spectroscopy and integrating learning publication-title: Measurement – year: 2018 ident: b52 article-title: YOLOv3: An incremental improvement – reference: K. He, X. Zhang, S. Ren, J. Sun, Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1026–1034. – volume: 51 start-page: 76 year: 2018 end-page: 81 ident: b17 article-title: Real-time detection of steel strip surface defects based on improved yolo detection network publication-title: IFAC-PapersOnLine – volume: 52 start-page: 348 year: 2017 end-page: 358 ident: b28 article-title: Automatic surface defect detection for mobile phone screen glass based on machine vision publication-title: Appl. Soft Comput. – year: 2019 ident: b61 article-title: Mish: A self regularized non-monotonic neural activation function – volume: 8 start-page: 1575 year: 2018 ident: b46 article-title: Automatic metallic surface defect detection and recognition with convolutional neural networks publication-title: Appl. Sci. – volume: 67 start-page: 690 year: 2018 end-page: 697 ident: b24 article-title: An optical surface inspection and automatic classification technique using the rotated wavelet transform publication-title: IEEE Trans. Instrum. Meas. – volume: 46 year: 2021 ident: b11 article-title: Effect of path strategy on residual stress and distortion in laser and cold metal transfer hybrid additive manufacturing publication-title: Addit. Manuf. – volume: 27 start-page: 1585 year: 2009 end-page: 1592 ident: b29 article-title: Fabric defect detection using morphological filters publication-title: Image Vis. Comput. – volume: Vol. 9353 year: 2015 ident: b19 article-title: Evaluation of laser ultrasonic testing for inspection of metal additive manufacturing publication-title: Laser 3D Manufacturing II – start-page: 21 year: 2016 end-page: 37 ident: b16 article-title: SSD: Single shot multibox detector publication-title: European Conference on Computer Vision – start-page: 1 year: 2019 end-page: 11 ident: b37 article-title: Towards defect monitoring for metallic additive manufacturing components using phased array ultrasonic testing publication-title: J. Intell. Manuf. – year: 2015 ident: b15 article-title: Microsoft coco captions: Data collection and evaluation server – reference: M. Tan, R. Pang, Q.V. Le, Efficientdet: Scalable and efficient object detection, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10781–10790. – volume: 10 start-page: 175 year: 2015 end-page: 185 ident: b9 article-title: 3D printing in aerospace and its long-term sustainability publication-title: Virtual Phys. Prototyp. – year: 2019 ident: b42 article-title: Efficientnet: Rethinking model scaling for convolutional neural networks – volume: 36 year: 2020 ident: b10 article-title: Optimization of the geometry for the end lateral extension path strategy to fabricate intersections using laser and cold metal transfer hybrid additive manufacturing publication-title: Addit. Manuf. – volume: 1 start-page: 77 year: 2015 end-page: 85 ident: b30 article-title: A rapid automatic brain tumor detection method for MRI images using modified minimum error thresholding technique publication-title: Int. J. Imaging Syst. Technol. – volume: 23 start-page: 1917 year: 2014 end-page: 1928 ident: b3 article-title: Metal additive manufacturing: A review publication-title: J. Mater. Eng. Perform. – year: 2014 ident: b4 article-title: Additive Manufacturing Technologies, Vol. 17 – year: 2017 ident: b62 article-title: Searching for activation functions – volume: 21 start-page: 298 year: 2018 end-page: 306 ident: b36 article-title: Non-destructive testing application of radiography and ultrasound for wire and arc additive manufacturing publication-title: Addit. Manuf. – volume: 17 start-page: 412 year: 2016 end-page: 421 ident: b33 article-title: Quantitative surface crack evaluation based on eddy current pulsed thermography publication-title: IEEE Sens. J. – volume: 35 start-page: 127 year: 2018 end-page: 139 ident: b1 article-title: A review of the wire arc additive manufacturing of metals: Properties, defects and quality improvement publication-title: J. Manuf. Process. – year: 2020 ident: b50 article-title: DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection publication-title: Inform. Sci. – year: 2016 ident: b58 article-title: SGDR: Stochastic gradient descent with restarts. CoRR – volume: 44 start-page: 224 year: 2015 end-page: 233 ident: b38 article-title: A novel approach for one-sided thermal nondestructive testing of composites by using infrared thermography publication-title: Polym. Test. – volume: 11 start-page: 642 year: 2015 end-page: 649 ident: b31 article-title: A contrast adjustment thresholding method for surface defect detection based on mesoscopy publication-title: IEEE Trans. Ind. Inf. – volume: 37 start-page: 1904 year: 2015 end-page: 1916 ident: b56 article-title: Spatial pyramid pooling in deep convolutional networks for visual recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 57 start-page: 477 year: 2019 end-page: 487 ident: b49 article-title: In-process virtual verification of weld seam removal in robotic abrasive belt grinding process using deep learning publication-title: Robot. Comput.-Integr. Manuf. – volume: 13 start-page: 158 year: 2018 end-page: 168 ident: b35 article-title: In-process non-destructive ultrasonic testing application during wire plus arc additive manufacturing publication-title: Adv. Produc. Eng. Manag. – reference: T.-Y. Lin, P. Goyal, R. Girshick, K. He, P. Dollár, Focal loss for dense object detection, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2980–2988. – volume: 5 start-page: 283 year: 2016 ident: b27 article-title: Rail defect detection and classification with real time image processing technique publication-title: Int. J. Comput. Sci. Softw. Eng. – year: 2005 ident: b8 article-title: Statistical process design for hybrid adaptive layer manufacturing publication-title: Rapid Prototyp. J. – start-page: 141 year: 2018 end-page: 149 ident: b47 article-title: Steel surface defects detection based on deep learning publication-title: International Conference on Applied Human Factors and Ergonomics – volume: 48 start-page: 929 year: 2017 end-page: 940 ident: b20 article-title: A generic deep-learning-based approach for automated surface inspection publication-title: IEEE Trans. Cybern. – start-page: 278 year: 2014 end-page: 287 ident: b18 article-title: Sensing defects during directed-energy additive manufacturing of metal parts using optical emissions spectroscopy publication-title: Solid Freeform Fabrication Symposium Proceedings – volume: 10 start-page: 2135 year: 2014 end-page: 2145 ident: b23 article-title: Saliency-based defect detection in industrial images by using phase spectrum publication-title: IEEE Trans. Ind. Inf. – reference: J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132–7141. – start-page: 1 year: 2020 end-page: 18 ident: b12 article-title: An overview of wire arc additive manufacturing (WAAM) in shipbuilding industry publication-title: Ships Offshore Struct. – volume: 141 year: 2019 ident: b39 article-title: Layerwise anomaly detection in laser powder-bed fusion metal additive manufacturing publication-title: J. Manuf. Sci. Eng. – reference: A. Diba, V. Sharma, A. Pazandeh, H. Pirsiavash, L. Van Gool, Weakly supervised cascaded convolutional networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 914–922. – reference: N. Bodla, B. Singh, R. Chellappa, L.S. Davis, Soft-NMS–improving object detection with one line of code, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 5561–5569. – volume: 30 year: 2019 ident: b40 article-title: Spectral diagnosis of wire arc additive manufacturing of Al alloys publication-title: Addit. Manuf. – year: 2020 ident: b14 article-title: YOLOv4: Optimal speed and accuracy of object detection – volume: 39 start-page: 1320 year: 2016 end-page: 1334 ident: b44 article-title: DeepID-Net: Object detection with deformable part based convolutional neural networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 22 start-page: 672 year: 2018 end-page: 686 ident: b2 article-title: Invited review article: Strategies and processes for high quality wire arc additive manufacturing publication-title: Addit. Manuf. – year: 2019 ident: b5 article-title: End lateral extension path strategy for intersection in wire and arc additive manufactured 2319 aluminum alloy publication-title: Rapid Prototyp. J. – year: 2019 ident: b59 article-title: Distance-IoU loss: Faster and better learning for bounding box regression – reference: J. Redmon, A. Farhadi, YOLO9000: Better, faster, stronger, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 7263–7271. – reference: T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, S. Belongie, Feature pyramid networks for object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2117–2125. – volume: 34 start-page: 397 year: 2000 end-page: 414 ident: b6 article-title: Closed loop direct metal deposition: Art to part publication-title: Opt. Lasers Eng. – volume: 34 start-page: 351 year: 2015 end-page: 372 ident: b26 article-title: Fault diagnosis of photovoltaic modules through image processing and canny edge detection on field thermographic measurements publication-title: Int. J. Sustain. Energy – ident: 10.1016/j.rcim.2022.102470_b51 doi: 10.1109/CVPR.2017.690 – start-page: 1 year: 2020 ident: 10.1016/j.rcim.2022.102470_b12 article-title: An overview of wire arc additive manufacturing (WAAM) in shipbuilding industry publication-title: Ships Offshore Struct. – volume: 156 year: 2020 ident: 10.1016/j.rcim.2022.102470_b41 article-title: Real-time seam defect identification for Al alloys in robotic arc welding using optical spectroscopy and integrating learning publication-title: Measurement doi: 10.1016/j.measurement.2020.107546 – volume: 51 start-page: 76 year: 2018 ident: 10.1016/j.rcim.2022.102470_b17 article-title: Real-time detection of steel strip surface defects based on improved yolo detection network publication-title: IFAC-PapersOnLine doi: 10.1016/j.ifacol.2018.09.412 – start-page: 1 year: 2019 ident: 10.1016/j.rcim.2022.102470_b37 article-title: Towards defect monitoring for metallic additive manufacturing components using phased array ultrasonic testing publication-title: J. Intell. Manuf. – year: 2015 ident: 10.1016/j.rcim.2022.102470_b15 – volume: 149 start-page: 1206 year: 2015 ident: 10.1016/j.rcim.2022.102470_b21 article-title: Defect inspection for TFT-LCD images based on the low-rank matrix reconstruction publication-title: Neurocomputing doi: 10.1016/j.neucom.2014.09.007 – volume: 30 year: 2019 ident: 10.1016/j.rcim.2022.102470_b40 article-title: Spectral diagnosis of wire arc additive manufacturing of Al alloys publication-title: Addit. Manuf. – year: 2016 ident: 10.1016/j.rcim.2022.102470_b58 – year: 2005 ident: 10.1016/j.rcim.2022.102470_b8 article-title: Statistical process design for hybrid adaptive layer manufacturing publication-title: Rapid Prototyp. J. doi: 10.1108/13552540510612929 – volume: 48 start-page: 929 year: 2017 ident: 10.1016/j.rcim.2022.102470_b20 article-title: A generic deep-learning-based approach for automated surface inspection publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2017.2668395 – volume: 239 start-page: 232 year: 2017 ident: 10.1016/j.rcim.2022.102470_b22 article-title: Automatic texture defect detection using Gaussian mixture entropy modeling publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.02.021 – ident: 10.1016/j.rcim.2022.102470_b60 doi: 10.1109/ICCV.2017.324 – volume: 10 start-page: 2135 year: 2014 ident: 10.1016/j.rcim.2022.102470_b23 article-title: Saliency-based defect detection in industrial images by using phase spectrum publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2014.2359416 – year: 2018 ident: 10.1016/j.rcim.2022.102470_b52 – volume: 35 start-page: 127 year: 2018 ident: 10.1016/j.rcim.2022.102470_b1 article-title: A review of the wire arc additive manufacturing of metals: Properties, defects and quality improvement publication-title: J. Manuf. Process. doi: 10.1016/j.jmapro.2018.08.001 – start-page: 21 year: 2016 ident: 10.1016/j.rcim.2022.102470_b16 article-title: SSD: Single shot multibox detector – volume: 126 start-page: 1331 year: 2015 ident: 10.1016/j.rcim.2022.102470_b25 article-title: Automated defect detection in textured surfaces using optimal elliptical Gabor filters publication-title: Optik doi: 10.1016/j.ijleo.2015.04.017 – volume: 52 start-page: 348 year: 2017 ident: 10.1016/j.rcim.2022.102470_b28 article-title: Automatic surface defect detection for mobile phone screen glass based on machine vision publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2016.10.030 – volume: 349 start-page: 472 year: 2015 ident: 10.1016/j.rcim.2022.102470_b32 article-title: An improved Otsu method using the weighted object variance for defect detection publication-title: Appl. Surf. Sci. doi: 10.1016/j.apsusc.2015.05.033 – volume: 34 start-page: 351 year: 2015 ident: 10.1016/j.rcim.2022.102470_b26 article-title: Fault diagnosis of photovoltaic modules through image processing and canny edge detection on field thermographic measurements publication-title: Int. J. Sustain. Energy doi: 10.1080/14786451.2013.826223 – volume: 27 start-page: 1585 year: 2009 ident: 10.1016/j.rcim.2022.102470_b29 article-title: Fabric defect detection using morphological filters publication-title: Image Vis. Comput. doi: 10.1016/j.imavis.2009.03.007 – volume: 1 start-page: 77 year: 2015 ident: 10.1016/j.rcim.2022.102470_b30 article-title: A rapid automatic brain tumor detection method for MRI images using modified minimum error thresholding technique publication-title: Int. J. Imaging Syst. Technol. – year: 2020 ident: 10.1016/j.rcim.2022.102470_b14 – volume: 44 start-page: 224 year: 2015 ident: 10.1016/j.rcim.2022.102470_b38 article-title: A novel approach for one-sided thermal nondestructive testing of composites by using infrared thermography publication-title: Polym. Test. doi: 10.1016/j.polymertesting.2015.04.013 – year: 2017 ident: 10.1016/j.rcim.2022.102470_b62 – volume: 10 start-page: 175 year: 2015 ident: 10.1016/j.rcim.2022.102470_b9 article-title: 3D printing in aerospace and its long-term sustainability publication-title: Virtual Phys. Prototyp. doi: 10.1080/17452759.2015.1111519 – ident: 10.1016/j.rcim.2022.102470_b54 doi: 10.1109/CVPR.2017.106 – volume: 23 start-page: 1917 year: 2014 ident: 10.1016/j.rcim.2022.102470_b3 article-title: Metal additive manufacturing: A review publication-title: J. Mater. Eng. Perform. doi: 10.1007/s11665-014-0958-z – year: 2019 ident: 10.1016/j.rcim.2022.102470_b5 article-title: End lateral extension path strategy for intersection in wire and arc additive manufactured 2319 aluminum alloy publication-title: Rapid Prototyp. J. doi: 10.1108/RPJ-05-2019-0123 – start-page: 278 year: 2014 ident: 10.1016/j.rcim.2022.102470_b18 article-title: Sensing defects during directed-energy additive manufacturing of metal parts using optical emissions spectroscopy – volume: 28 start-page: 2278 year: 2007 ident: 10.1016/j.rcim.2022.102470_b7 article-title: Electron beam freeforming of stainless steel using solid wire feed publication-title: Mater. Des. doi: 10.1016/j.matdes.2006.08.008 – volume: 46 year: 2021 ident: 10.1016/j.rcim.2022.102470_b11 article-title: Effect of path strategy on residual stress and distortion in laser and cold metal transfer hybrid additive manufacturing publication-title: Addit. Manuf. – volume: 5 start-page: 283 year: 2016 ident: 10.1016/j.rcim.2022.102470_b27 article-title: Rail defect detection and classification with real time image processing technique publication-title: Int. J. Comput. Sci. Softw. Eng. – volume: 11 start-page: 642 year: 2015 ident: 10.1016/j.rcim.2022.102470_b31 article-title: A contrast adjustment thresholding method for surface defect detection based on mesoscopy publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2015.2417676 – ident: 10.1016/j.rcim.2022.102470_b45 doi: 10.1109/CVPR.2017.545 – volume: 57 start-page: 477 year: 2019 ident: 10.1016/j.rcim.2022.102470_b49 article-title: In-process virtual verification of weld seam removal in robotic abrasive belt grinding process using deep learning publication-title: Robot. Comput.-Integr. Manuf. doi: 10.1016/j.rcim.2019.01.006 – volume: 67 start-page: 690 year: 2018 ident: 10.1016/j.rcim.2022.102470_b24 article-title: An optical surface inspection and automatic classification technique using the rotated wavelet transform publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2017.2783098 – volume: 141 year: 2019 ident: 10.1016/j.rcim.2022.102470_b39 article-title: Layerwise anomaly detection in laser powder-bed fusion metal additive manufacturing publication-title: J. Manuf. Sci. Eng. doi: 10.1115/1.4042108 – ident: 10.1016/j.rcim.2022.102470_b48 – volume: 36 year: 2020 ident: 10.1016/j.rcim.2022.102470_b10 article-title: Optimization of the geometry for the end lateral extension path strategy to fabricate intersections using laser and cold metal transfer hybrid additive manufacturing publication-title: Addit. Manuf. – year: 2020 ident: 10.1016/j.rcim.2022.102470_b50 article-title: DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection publication-title: Inform. Sci. doi: 10.1016/j.ins.2020.02.067 – ident: 10.1016/j.rcim.2022.102470_b53 doi: 10.1109/ICCV.2015.123 – start-page: 141 year: 2018 ident: 10.1016/j.rcim.2022.102470_b47 article-title: Steel surface defects detection based on deep learning – volume: 22 start-page: 672 year: 2018 ident: 10.1016/j.rcim.2022.102470_b2 article-title: Invited review article: Strategies and processes for high quality wire arc additive manufacturing publication-title: Addit. Manuf. – volume: Vol. 9353 year: 2015 ident: 10.1016/j.rcim.2022.102470_b19 article-title: Evaluation of laser ultrasonic testing for inspection of metal additive manufacturing – volume: 21 start-page: 298 year: 2018 ident: 10.1016/j.rcim.2022.102470_b36 article-title: Non-destructive testing application of radiography and ultrasound for wire and arc additive manufacturing publication-title: Addit. Manuf. – year: 2014 ident: 10.1016/j.rcim.2022.102470_b4 – year: 2016 ident: 10.1016/j.rcim.2022.102470_b34 article-title: Calculation of flexible printed circuit boards (FPC) global and local defect detection based on computer vision publication-title: Circuit World doi: 10.1108/CW-07-2014-0027 – volume: 13 start-page: 158 year: 2018 ident: 10.1016/j.rcim.2022.102470_b35 article-title: In-process non-destructive ultrasonic testing application during wire plus arc additive manufacturing publication-title: Adv. Produc. Eng. Manag. doi: 10.14743/apem2018.2.281 – ident: 10.1016/j.rcim.2022.102470_b57 doi: 10.1109/ICCV.2017.593 – volume: 17 start-page: 412 year: 2016 ident: 10.1016/j.rcim.2022.102470_b33 article-title: Quantitative surface crack evaluation based on eddy current pulsed thermography publication-title: IEEE Sens. J. doi: 10.1109/JSEN.2016.2625815 – ident: 10.1016/j.rcim.2022.102470_b55 doi: 10.1109/CVPR42600.2020.01079 – volume: 37 start-page: 1904 year: 2015 ident: 10.1016/j.rcim.2022.102470_b56 article-title: Spatial pyramid pooling in deep convolutional networks for visual recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2015.2389824 – ident: 10.1016/j.rcim.2022.102470_b43 doi: 10.1109/CVPR.2018.00745 – volume: 8 start-page: 1575 year: 2018 ident: 10.1016/j.rcim.2022.102470_b46 article-title: Automatic metallic surface defect detection and recognition with convolutional neural networks publication-title: Appl. Sci. doi: 10.3390/app8091575 – year: 2019 ident: 10.1016/j.rcim.2022.102470_b59 – year: 2019 ident: 10.1016/j.rcim.2022.102470_b42 – volume: 39 start-page: 1320 year: 2016 ident: 10.1016/j.rcim.2022.102470_b44 article-title: DeepID-Net: Object detection with deformable part based convolutional neural networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2016.2587642 – volume: IA-18 start-page: 246 year: 1982 ident: 10.1016/j.rcim.2022.102470_b13 article-title: The other electrical hazard: Electric arc blast burns publication-title: IEEE Trans. Ind. Appl. doi: 10.1109/TIA.1982.4504068 – year: 2019 ident: 10.1016/j.rcim.2022.102470_b61 – volume: 34 start-page: 397 year: 2000 ident: 10.1016/j.rcim.2022.102470_b6 article-title: Closed loop direct metal deposition: Art to part publication-title: Opt. Lasers Eng. doi: 10.1016/S0143-8166(00)00072-5 |
| SSID | ssj0002453 |
| Score | 2.6542494 |
| Snippet | Wire and arc additive manufacturing (WAAM) is an emerging manufacturing technology that is widely used in different manufacturing industries. To achieve fully... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 102470 |
| SubjectTerms | Deep learning Defect detection Online Wire and arc additive manufacturing |
| Title | Deep learning based online metallic surface defect detection method for wire and arc additive manufacturing |
| URI | https://dx.doi.org/10.1016/j.rcim.2022.102470 |
| Volume | 80 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEF6KXvTgoyrWR9mDN4ndJpsmPZZqqa8iaqG3sI-JRNtYanv1t7uT3WgF6cHTQtiFMJmd-SDffB8hZ6H2pYpDgXraLQ8htSe0uVcMFJM4yGj_mN4PWv0hvxmFowrplrMwSKt0td_W9KJauycNF83GNMsaTyY5sX0aAIGNvxgm5zzCLL_4_KF5-NwqUZrNHu52gzOW4zVTGU6j-z4qGHA0LP6rOS01nN4O2XJIkXbsy-ySCuRVsl26MFB3Katkc0lScI-8XQJMqfOCeKHYpDS1chh0AgZpjzNFPxazVCigGpDMYZZ5QcjKqfWTpgbIUtQwpiLX1NwEiqwjrIt0IvIFzkIUw437ZNi7eu72PWeo4KmAsbmXBgEDFkFbq0jKQAYa_eXSFBVjII5TKUMw5U5AWzQh9gUIX0c8Vkqz1AC7ZnBA1vL3HA4JjVuhH8YmAQxi4SAiiX3fwDfOlGRRGtVIs4xkopzaOJpejJOSVvaaYPQTjH5io18j599nplZrY-XusPxAya-MSUwzWHHu6J_njskGWs1b1s4JWZvPFnBqAMlc1ouMq5P1Tvfx7gHX69v-4AvnnuHg |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3LTsJAFJ0QXKgLH6gRn7NwZypDH7QsDUpQgY2QsGvmcWuqUAmWrd_u3M5UMTEsXJE0M0lzuY-T9NxzCLkKlCtkFHDU0245CKkdrnRdMZBM4CKj-WI6GLZ6Y_9xEkwqpFPuwiCt0vZ-09OLbm2fNGw0G_M0bTzr5MTxqQEEDn5cJt_wdfmijcHN5w_Pw_WNFKU-7eBxuzljSF4LmeI6uuuihIGPjsV_TaeVidPdIzsWKtJb8zb7pAJZjeyWNgzUVmWNbK9oCh6QtzuAObVmEC8Up5SiRg-DzkBD7Wkq6cdykXAJVAGyOfRPXjCyMmoMpalGshRFjCnPFNWlQJF2hI2Rzni2xGWIYrvxkIy796NOz7GOCo70GMudxPMYsBDaSoZCeMJTaDCXJCgZA1GUCBGA7ncc2rwJkcuBuyr0IykVSzSya3pHpJq9Z3BMaNQK3CDSGaAhiw88FDj4NX7zmRQsTMI6aZaRjKWVG0fXi2lc8speY4x-jNGPTfTr5Pr7ztyIbaw9HZR_UPwrZWI9DdbcO_nnvUuy2RsN-nH_Yfh0SrbQd95QeM5INV8s4Vyjk1xcFNn3BRfT4dk |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Deep+learning+based+online+metallic+surface+defect+detection+method+for+wire+and+arc+additive+manufacturing&rft.jtitle=Robotics+and+computer-integrated+manufacturing&rft.au=Li%2C+Wenhao&rft.au=Zhang%2C+Haiou&rft.au=Wang%2C+Guilan&rft.au=Xiong%2C+Gang&rft.date=2023-04-01&rft.pub=Elsevier+Ltd&rft.issn=0736-5845&rft.volume=80&rft_id=info:doi/10.1016%2Fj.rcim.2022.102470&rft.externalDocID=S0736584522001521 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0736-5845&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0736-5845&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0736-5845&client=summon |