Abstract
In automatic non-destructive testing (NDT), weld bead tracking is usually performed outside. However, irregular weld boundaries, unconstrained illumination, and rough metal surfaces can cause noise, which increases the difficulty of seam tracking. In this paper, a method of parallel structured light (PSL) sensing based on deep learning and information fusion is proposed to detect weld lines. First, a camera is used to capture the laser stripe image projected by the PSL on the weld bead. Then, a MobileNet-SSD deep learning model is trained to extract the regions of interest (ROIs) to de-noise the laser stripe image. Finally, the weld line is obtained by fusing information from multiple weld boundaries.
Similar content being viewed by others
References
Zhang L, Sun J, Yin G, Zhao J, Han Q (2015) A cross structured light sensor and stripe segmentation method for visual tracking of a wall climbing robot. Sensors 15(6):13725–13751
Zhang L, Ye Q, Yang W, Jiao J (2014) Weld line detection and tracking via spatial-temporal cascaded hidden Markov models and cross structured light. IEEE Trans Instrum Meas 63(4):742–753
Zou Y, Du D, Zeng J, Zhang W (2008) Visual method for weld seam recognition based on multi-feature extraction and information fusion. Trans China Weld Inst 34:33–36
Krämer S, Fiedler W, Drenker A, Abels P (2014) Seam tracking with texture based image processing for laser material processing. In: Proceedings of the International Society for Optics and Photonics, High-Power Laser Materials Processing: Lasers, Beam Delivery, Diagnostics and Applications III, San Francisco, CA, USA; vol 8963, pp 89630P-1-9
Yan T (2016) Research on identification method of pipeline weld and design of weld ultrasonic scanning equipment (in Chinese). Shenzhen University, MA thesis. https://kns.cnki.net/KCMS/detail/detail.aspx?dbname=CMFD201701&filename=1016763844.nh
Liu X, Xu G, Fei Y (2017) Image processing algorithm for intersecting line weld inspection robot. Transducer Microsystem Technol 36(7):146–153
Li X, Li X, Ge S, Khyam MO, Luo C (2017) Automatic welding seam tracking and identification. IEEE Trans Ind Electron (99):1–1
Zeng J, Chang B, Du D, Wang L, Chang S, Peng G et al (2018) A weld position recognition method based on directional and structured light information fusion in multi-layer/multi-pass welding. Sensors:18(1)
Molleda J, Usamentiaga R, Garcia DF, Bulnes FG, Ema L (2011) Shape measurement of steel strips using a laser-based three-dimensional reconstruction technique. IEEE Trans Ind Appl 47(4):1536–1544
Molleda J, Usamentiaga R, Bulnes FG, Granda JC, Ema L (2012) Uncertainty propagation analysis in 3-d shape measurement using laser range finding. IEEE Trans Instrum Meas 61(5):1160–1172
Usamentiaga R, Molleda J, García DF (2012) Fast and robust laser stripe extraction for 3d reconstruction in industrial environments. Mach Vis Appl 23(1):179–196
Duran O, Althoefer K, Seneviratne LD (2007) Automated pipe defect detection and categorization using camera/laser-based profiler and artificial neural network. IEEE Trans Autom Sci Eng 4(1):118–126
Liang L, Ordonez C, Collins EG Jr, Coyle E, Palejiya D (2011) Terrain surface classification with a control mode update rule using a 2d laser stripe-based structured light sensor. Robot Auton Syst 59(11):954–965
Saito K, Miyoshi T, Yoshikawa H (1991) Noncontact 3-d digitizing and machining system for free-form surfaces. CIRP Ann Manuf Technol 40(1):483–486
Li L, Fu L, Zhou X, Li X (2007) Image processing of seam tracking system using laser vision. Robot Weld Intell Autom 362:319–324
Gu W, Xiong Z, Wan W (2013) Autonomous seam acquisition and tracking system for multi-pass welding based on vision sensor. Int J Adv Manuf Technol 69:451–460
Li Y, Li Y, Wang Q, Xu D, Tan M (2010) Measurement and defect detection of the weld bead based on online vision inspection. IEEE Trans Instrum Meas 59:1841–1849
Zeng J, Chang B, Du D, Hong Y, Chang S, Zou Y (2016) A precise visual method for narrow butt detection in specular reflection workpiece welding. Sensors 16:1480
Muhammad J, Altun H, Abo-Serie E (2016) A robust butt welding seam finding technique for intelligent robotic welding system using active laser vision. Int J Adv Manuf Technol 94:1–17
Fang Z, Xu D (2009) Image-based visual seam tracking system for fillet joint. In Proceedings of the IEEE International Conference on Robotics and Biomimetics, Guilin, China, pp 1230–1235
Fang Z, Xu D, Tan M (2010) Visual seam tracking system for butt weld of thin plate. Int J Adv Manuf Technol 49:519–526
Zhang L, Jiao J, Ye Q, Han Z, Yang W (2012) Robust weld line detection with cross structured light and Hidden Markov Model. In: Proceedings of the IEEE International Conference on Mechatronics and Automation, Chengdu, China, pp 1411–1416
Huang W, Kovacevic R (2012) Development of a real-time laser-based machine vision system to monitor and control welding processes. Int J Adv Manuf Technol 63:235–248
Kim J, Bae H (2005) A study on a vision sensor system for tracking the I-butt weld joints. J Mech Sci Technol 19:1856–1863
Sung K, Lee H, Choi YS, Rhee S (2009) Development of a multiline laser vision sensor for joint tracking in welding. Weld J 88:79 s–85 s
Shi Y, Wang G, Li G (2007) Adaptive robotic welding system using laser vision sensing for underwater engineering. In Proceedings of the IEEE International Conference on Control and Automation, Guangzhou, China, pp 1213–1218
Chu H, Wang Z (2017) Study on dimension measurement and defect detection of weld based on active vision. Hot Work Technol 46(21):206–209
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Dong, Z., Mai, Z., Yin, S. et al. A weld line detection robot based on structure light for automatic NDT. Int J Adv Manuf Technol 111, 1831–1845 (2020). https://doi.org/10.1007/s00170-020-05964-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-020-05964-w