Simulation-Based Optimization of Robotic Weld Seam Tracking Using Fuzzy C-Means Clustering and PID Control

Abstract

Today, welding automation is a vital technology that boosts efficiency in manufacturing processes while enhancing weld quality by minimizing human intervention. However, deformations caused by high heat and deviations from programming errors in robotic welding can negatively impact welding quality. Existing camera and laser-based seam tracking systems are insufficient in certain scenarios due to factors such as highly reflective surfaces, intense arc radiation, or uneven surface conditions. This article presents a weld seam tracking system based on an angle sensor, called Weld Guide, developed to address the limitations of existing systems. The proposed system features angle sensors that utilize a Contact-based sensor principle to improve the accuracy of the robotic welding torch. The Weld Guide system was designed using SolidWorks software, simulated in RoboDK simulation software, and validated through experimental tests. The prototype was tested on both linear and curved weld seams, and its performance under different control systems was evaluated using an optical microscope. Results from the experiments showed that the Weld Guide system successfully tracked weld seams with a deviation of less than 0.6 mm. The comparison between the trajectories obtained from simulated and actual field tests exhibited a similarity exceeding 97%, demonstrating a high level of accuracy in trajectory-tracking performance. Furthermore, a hybrid approach combining Fuzzy C-Means (FCM) clustering with Proportional Integral Derivative (PID) control was implemented to enable automatic tuning of the PID parameters. By incorporating oscillation levels into the fuzzy logic rules, the optimization was enhanced against sudden changes, thereby preventing error accumulation and excessive oscillations. These findings indicate that the proposed system provides a reliable and cost-effective alternative when optical-based tracking methods fall short.

Keywords

• Angle Sensors
• Contact-Based Sensor
• FCM-PID
• Robodk
• Robotic Welding
• Simulation
• SolidWorks
• Weld Seam Tracking

Bulanık C-Means Kümeleme ve PID Kontrolü Kullanılarak Robotik Kaynak Dikişi Takibinin Simülasyon Tabanlı Optimizasyonu

Abstract

Günümüzde kaynak otomasyonu, imalat süreçlerinde verimliliği artırırken, insan müdahalesini en aza indirerek kaynak kalitesini iyileştiren hayati bir teknolojidir. Ancak, robotik kaynaktaki yüksek ısı kaynaklı deformasyonlar ve programlama hatalarından kaynaklanan sapmalar, kaynak kalitesini olumsuz etkileyebilir. Mevcut kamera ve lazer tabanlı dikiş takip sistemleri, yüksek yansıtıcı yüzeyler, yoğun ark ışınımı veya düzensiz yüzey koşulları gibi faktörler nedeniyle bazı senaryolarda yetersiz kalmaktadır. Bu makalede, mevcut sistemlerin sınırlamalarını aşmak amacıyla geliştirilen, açı sensörüne dayalı bir kaynak dikişi takip sistemi olan Weld Guide sunulmaktadır. Önerilen sistem, robotik kaynak meşalesinin doğruluğunu artırmak için temas bazlı ölçüm prensibini kullanan açı sensörleri içermektedir. Weld Guide sistemi SolidWorks yazılımı ile tasarlanmış, RoboDK simülasyon yazılımında modellenmiş ve deneysel testlerle doğrulanmıştır. Prototip, hem doğrusal hem de eğrisel kaynak dikişlerinde test edilerek çeşitli kaynak koşulları altında performansı değerlendirilmiştir. Deney sonuçları, Weld Guide sisteminin kaynak dikişlerini 0,6 mm’den daha az sapma ile başarılı bir şekilde takip ettiğini göstermiştir. Simülasyon analizlerinin gerçek saha testleriyle karşılaştırılması ise %97’den fazla benzerlik oranı ortaya koymuştur. Ayrıca, Fuzzy C-Means (FCM) kümeleme ve PID kontrolünü birleştiren hibrit bir yöntem uygulanarak PID parametrelerinin otomatik ayarlanması sağlanmış ve ani hata değişikliklerine karşı optimizasyon iyileştirilmiş, böylece hata birikimi ve salınımlar önlenmiştir. Bu bulgular, önerilen sistemin optik tabanlı takip yöntemlerinin yetersiz kaldığı durumlarda güvenilir ve ekonomik bir alternatif sunduğunu göstermektedir.

Keywords

• Açı sensörleri
• FCM-PID
• Kaynak dikiş takibi
• RoboDK
• Robotik kaynak
• Simülasyon
• SolidWorks

References

1. Behrooz, F., Yusof, R., Mariun, N., Khairuddin, U., & Hilmi Ismail, Z. (2019). Designing intelligent MIMO nonlinear controller based on fuzzy cognitive map method for energy reduction of the buildings. Energies, 12(14), Article 2713. https://doi.org/10.3390/en12142713
2. Budde, L., Biester, K., Coors, T., Faqiri, M. Y., Lammers, M., Hermsdorf, J., & Overmeyer, L. (2023). Influence of shielding gas coverage during laser hot-wire cladding with high carbon steel. The International Journal of Advanced Manufacturing Technology, 127(7), 3195-3207. https://doi.org/10.1007/s00170-023-11350-z
3. Bryn, O., Bekhta, P., Sedliačik, J., Forosz, V., & Galysh, V. (2016). The effect of diffusive impregnation of birch veneers with fire retardant on plywood properties. BioResources, 11(4), 9112-9125. https://doi.org/10.15376/biores.11.4.9112-9125
4. Canelas, A., Póvoa, R., Martins, R., Lourenço, N., Guilherme, J., Carvalho, J. P., & Horta, N. (2018). FUZYE: A Fuzzy c-Means Analog IC Yield Optimization Using Evolutionary-Based Algorithms. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 39(1), 1-13. https://doi.org/10.1109/TCAD.2018.2883978
5. Chao, C. T., Sutarna, N., Chiou, J. S., & Wang, C. J. (2019). An optimal fuzzy PID controller design based on conventional PID control and nonlinear factors. Applied Sciences, 9(6), Article 1224. https://doi.org/10.3390/app9061224
6. Cibicik, A., Tingelstad, L., & Egeland, O. (2021). Laser scanning and parametrization of weld grooves with reflective surfaces. Sensors, 21(14), Article 4791. https://doi.org/10.3390/s21144791
7. Corke, P. (2017). Robot arm kinematics. In Robotics, vision and control: Fundamental algorithms in MATLAB® (2nd ed., pp. 193-228). https://doi.org/10.1007/978-3-319-54413-7_7
8. Costa, C. M., Veiga, G., Sousa, A., Rocha, L., Oliveira, E., Cardoso, H. L., & Thomas, U. (2018, April). Automatic generation of disassembly sequences and exploded views from SolidWorks symbolic geometric relationships. In 2018 International Conference on Autonomous Robot Systems and Competitions (ICARSC) (pp. 211-218). IEEE. https://doi.org/10.1109/ICARSC.2018.8374185

9. Elsisi, M., Zaini, H. G., Mahmoud, K., Bergies, S., & Ghoneim, S. S. (2021). Improvement of trajectory tracking by robot manipulator based on a new co-operative optimization algorithm. Mathematics, 9(24), Article 3231. https://doi.org/10.3390/math9243231
10. Ferdaus, M. M., Anavatti, S. G., Garratt, M. A., & Pratama, M. (2019). Development of c-means clustering based adaptive fuzzy controller for a flapping wing micro air vehicle. Journal of Artificial Intelligence and Soft Computing Research, 9(2), 99-109. https://doi.org/10.2478/jaiscr-2018-0027
11. Garbev, A., & Atanassov, A. (2020, October). Comparative analysis of RoboDK and robot operating system for solving diagnostics tasks in off-line programming. In 2020 International Conference Automatics and Informatics (ICAI) (pp. 1-5). IEEE. https://doi.org/10.1109/ICAI50593.2020.9311332
12. Haeri, H., Talehjerdi, A. G., Sarfarazi, V., Moayer, A., & Marji, M. F. (2024). A finite element analysis of the effects of TADAS dampers on the frame members’ performances in concrete structures under Cyclic and monotonic loadings. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 49(2), 1133-1156. https://doi.org/10.1007/s40996-024-01540-4
13. Han, J., Shan, X., Liu, H., Xiao, J., & Huang, T. (2023). Fuzzy gain scheduling PID control of a hybrid robot based on dynamic characteristics. Mechanism and Machine Theory, 184, Article 105283. https://doi.org/10.1016/j.mechmachtheory.2023.105283
14. Henriques, J. P. C., Neto, E. R., de Paula Paiva, J. P. M., de Souza, L. C., Lugli, A. B., Florentino, F. M., & de Andrade Carvalho, G. C. (2023, November). Trajectory generation using RoboDK for a Staubli SCARA TS 60 robot. In 2023 11th International Conference on Control, Mechatronics and Automation (ICCMA) (pp. 121-126). IEEE. https://doi.org/10.1109/ICCMA59762.2023.10374649
15. Hong, L., Wang, B., Xu, Z., & Lv, D. (2018, August). Algorithm and application of inverse kinematics for 6-DOF welding robot based on screw theory. In 2018 International Conference on Information Technology and Management Engineering (ICITME 2018) (pp. 159-163). Atlantis Press. https://doi.org/10.2991/icitme-18.2018.32
16. Huang, Y., Abu-Dakka, F. J., Silvério, J., & Caldwell, D. G. (2020). Toward orientation learning and adaptation in cartesian space. Transactions on Robotics, 37(1), 82-98. https://doi.org/10.1109/TRO.2020.3010633
17. Huynh, C. T., & Phung, T. C. (2024). Research on welding seam tracking algorithm for automatic welding process of X-shaped tip of concrete piles using laser distance sensor. Robotica, 42(6), 1796-1815. https://doi.org/10.1017/S0263574724000535
18. Ibrahim, I. N., & Al Akkad, M. A. (2017). Studying the disturbances of robotic arm movement in space using the compound-pendulum method. Bulletin of IzhSTU named after MT Kalashnikov, 20(2), 156-159. https://doi.org/10.22213/2413-1172-2017-2-156-159
19. Keles, A. E., Haznedar, B., Kaya Keles, M., & Arslan, M. T. (2023). The effect of adaptive neuro-fuzzy inference system (ANFIS) on determining the leadership perceptions of construction employees. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 47(6), 4145-4157. https://doi.org/10.1007/s40996-023-01146-2
20. Li, G., Hong, Y., Gao, J., Hong, B., & Li, X. (2020). Welding seam trajectory recognition for automated skip welding guidance of a spatially intermittent welding seam based on laser vision sensor. Sensors, 20(13), Article 3657. https://doi.org/10.3390/s20133657
21. Li Sr, B., Qin, X., Lei, J., Zeng, Y., Zhang, J., Jia, B., Li, H., & Li, Z. (2021, November). Detection method of power line under uneven lightness for flying-walking power line inspection robot. In Proceedings of the 2021 International Conference on Image, Video Processing, and Artificial Intelligence (Vol. 12076, pp. 46-52). SPIE. https://doi.org/10.1117/12.2611653
22. Lin, C. H., Wang, K. J., Tadesse, A. A., & Woldegiorgis, B. H. (2022). Human-robot collaboration empowered by hidden semi-Markov model for operator behaviour prediction in a smart assembly system. Journal of Manufacturing Systems, 62, 317-333. https://doi.org/10.1016/j.jmsy.2021.12.001
23. Liu, F., Wang, Z., & Ji, Y. (2018). Precise initial weld position identification of a fillet weld seam using laser vision technology. The International Journal of Advanced Manufacturing Technology, 99(5), 2059-2068. https://doi.org/10.1007/s00170-018-2574-9
24. Lu, S., Zhou, J., & Zhang, J. (2015). Optimization of welding thickness on casting-steel surface for production of forging die. The International Journal of Advanced Manufacturing Technology, 76 (5), 1411-1419. https://doi.org/10.1007/s00170-014-6371-9
25. Luo, J., Zhu, L., Wu, N., Chen, M., Liu, D., Zhang, Z., & Liu, J. (2022). Adaptive neural-PID visual servoing tracking control via extreme learning machine. Machines, 10(9), Article 782. https://doi.org/10.3390/machines10090782
26. Morsi, N. M. (2024). Feasibility testing of robotics inspection by advanced simulation for aerospace structures (Doctoral thesis, Glasgow Caledonian University).
27. Nguyen, H. C., & Lee, B. R. (2014). Laser-vision-based quality inspection system for small-bead laser welding. International Journal of Precision Engineering and Manufacturing, 15(3), 415-423. https://doi.org/10.1007/s12541-014-0352-7
28. Petschnigg, C., Breitenhuber, G., Breiling, B., Dieber, B., & Brandstötter, M. (2018, March). Online simulation for flexible robotic manufacturing. In Proceedings of the International Conference on Industrial Technology and Management (pp. 88-92). IEEE. https://doi.org/10.1109/ICITM.2018.8333925
29. Ramalingam, S., Rasool Mohideen, S., Manigandan, S., & Prem Anand, T. P. (2021). Hybrid polymer composite material for robotic manipulator subject to single link flexibility. International Journal of Ambient Energy, 42(5), 514-521. https://doi.org/10.1080/01430750.2018.1557551
30. Reddy, J., Dutta, A., Mukherjee, A., & Pal, S. K. (2024). A low-cost vision-based weld-line detection and measurement technique for robotic welding. International Journal of Computer Integrated Manufacturing, 37(12), 1538-1558. https://doi.org/10.1080/0951192X.2024.2314784
31. Ružbarský, J. (2023). The difficulty of measuring the roughness of glossy surfaces using the triangulation principle. Applied Sciences, 13(8), Article 5155. https://doi.org/10.3390/app13085155.
32. Seefried, J., Mahr, A., Weigelt, M., Kühl, A., & Franke, J. (2021, December). Challenges of contacting processes for thin copper flat wires in the context of electromechanical engineering. In Proceedings of the 2021 11th International Electric Drives Production Conference (EDPC) (pp. 1-8). IEEE. https://doi.org/10.1109/EDPC53547.2021.9684202
33. Sharkawy, A. N., & Khairullah, S. S. (2023). Forward and inverse kinematics solution of a 3-DOF articulated robotic manipulator using artificial neural network. International Journal of Robotics and Control Systems, 3(2), 330-353. https://doi.org/10.31763/ijrcs.v3i2.1017
34. Sharma, A., Sharma, K., Islam, A., & Roy, D. (2020). Effect of welding parameters on automated robotic arc welding process. Materials Today: Proceedings, 26, 2363-2367. https://doi.org/10.1016/j.matpr.2020.02.507
35. Shyju, T., Saravanan, C., Kumar, T. S., & Kumaragurubaran, B. (2016). Static analysis of tube to header weld joint configurations. International Journal of Engineering Research, 5(5), 440-446.
36. Skála, J., Svantner, M., Tesar, J., & Franc, A. (2016). Active thermography inspection of protective glass contamination on laser scanning heads. Applied Optics, 55(34), 60-66. https://doi.org/10.1364/AO.55.000D60
37. Soltani, A., & Vahidi Bajestani, A. (2024). Linear quadratic Gaussian control for a liquid-carrying quadrotor. Iranian Journal of Science and Technology, Transactions of Electrical Engineering, 48(1), 395-408. https://doi.org/10.1007/s40998-023-00657-y
38. Suoranta, I. (2021). Implementation of a laser sensor system in a multi-robot welding cell (Master’s thesis, LUT University, School of Mechanical Engineering). LUTPub. https://lutpub.lut.fi/handle/10024/162891
39. Wang, B., Hu, S. J., Sun, L., & Freiheit, T. (2020). Intelligent welding system technologies: State-of-the-art review and perspectives. Journal of Manufacturing Systems, 56, 373-391. https://doi.org/10.1016/j.jmsy.2020.06.020
40. Xue, K., Wang, Z., Shen, J., Hu, S., Zhen, Y., Liu, J., & Yang, H. (2021). Robotic seam tracking system based on vision sensing and human-machine interaction for multi-pass MAG welding. Journal of Manufacturing Processes, 63, 48-59. https://doi.org/10.1016/j.jmapro.2020.02.026
41. Vacharakornrawut, N., Thepmanee, T., Rerkratn, A., & Pongswatd, S. (2016, June). Converting TCP to joints value of 6-DOF robot based on forward and inverse kinematic analysis. In 2016 13th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON) (pp. 1-6). IEEE. https://doi.org/10.1109/ECTICon.2016.7561348
42. Vocetka, M., Huňady, R., Hagara, M., Bobovský, Z., Kot, T., & Krys, V. (2020). Influence of the approach direction on the repeatability of an industrial robot. Applied Sciences, 10(23), Article 8714. https://doi.org/10.3390/app10238714
43. Vesović, M., Jovanović, R., & Zarić, V. (2024). Hybrid GA-ANFIS and PSO-ANFIS techniques for nonlinear DC motor system modeling. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science. https://doi.org/10.1177/09544062251350800
44. Yang, L., Pan, Y., Lin, J., Liu, Y., Shang, Y., Yang, S., & Cao, H. (2020). Automatic guidance method for laser tracker based on rotary-laser scanning angle measurement. Sensors, 20(15), Article 4168. https://doi.org/10.3390/s20154168
45. Zhang, Z., Wan, Y., Wang, Y., Guan, X., Ren, W., & Li, G. (2021). Improved hybrid A* path planning method for spherical mobile robot based on pendulum. International Journal of Advanced Robotic Systems, 18(1). https://doi.org/10.1177/1729881421992958
46. Zou, Y., Wei, X., & Chen, J. (2020). Conditional generative adversarial network-based training image inpainting for laser vision seam tracking. Optics and Lasers in Engineering, 134, Article 106140. https://doi.org/10.1016/j.optlaseng.2020.106140