Prediksi Kualitas Sambungan Las Robotik Menggunakan Random Forest dan Data Sensor Tegangan
Abstract
Menghadapi tantangan nyata di lini produksi, penelitian ini bertujuan menggantikan metode inspeksi las konvensional yang lambat dan rentan error. Inspeksi manual atau pengujian merusak kerap memakan waktu 2-3 hari per batch, menyumbang 15% biaya produksi, dan mengandung risiko human error 20-30%. Solusinya, kami kembangkan sistem prediksi real-time berbasis kecerdasan buatan yang “mendengarkan” proses pengelasan melalui sensor tegangan. Peneliti menganalisis 1.200 sampel las dari baja AISI 1020, merekam sinyal tegangan 10.000 kali per detik. Dari data ini, diekstraksi 24 “sidik jari digital” ciri statistik dan frekuensi yang mencerminkan kondisi pengelasan. Hasil las dikategorikan sebagai Baik, Porositas, atau Cacat Kritis berdasarkan inspeksi ultrasonik. Setelah menguji tujuh algoritma, Random Forest yang telah dioptimasi menunjukkan performa terbaik dengan akurasi 94,82%, hanya membutuhkan 23,4 milidetik untuk menganalisis satu sambungan. Ini mengungguli algoritma lain seperti Gradient Boosting (92,1%) dan Neural Network (90,7%). Sistem ini berpotensi merevolusi kontrol kualitas: mengurangi ketergantungan inspeksi manual hingga 70%, memangkas waktu inspeksi dari hari menjadi real-time, dan menurunkan biaya kualitas hingga 40%. Dengan demikian, penelitian ini tidak hanya membuktikan keampuhan machine learning, tetapi juga menawarkan solusi praktis yang siap diadopsi industri untuk meningkatkan efisiensi dan daya saing di era otomasi.References
[1] S. W. Campbell, Welding: Principles and Practices, 5th ed. New York, NY, USA: McGraw-Hill, 2017.
[2] P. Kah and J. Martikainen, “Current trends in robotic welding and future challenges,” Int. J. Mech. Mater. Eng., vol. 10, no. 1, p. 13, Dec. 2015.
[3] J. Noruk, “The costs and benefits of nondestructive testing,” Weld. J., vol. 90, no. 5, pp. 46–49, May 2011.
[4] R. Halmshaw, Introduction to the Non-Destructive Testing of Welded Joints, 2nd ed. Abington, U.K.: Woodhead Publishing, 1996.
[5] A. S. R. Silva and J. M. A. Rebello, “The reliability of non-destructive testing in the evaluation of weld defects,” Insight, vol. 45, no. 5, pp. 331–335, May 2003.
[6] C. R. G. de Silva, “Economic aspects of nondestructive evaluation,” in Handbook of Nondestructive Evaluation, C. J. Hellier, Ed. New York, NY, USA: McGraw-Hill, 2001, ch. 2.
[7] H. Wang, J. Zhang, L. Wang, and Q. Wang, “Vision-based monitoring of weld pool geometry in GMAW,” J. Manuf. Process., vol. 56, pp. 1107–1114, Aug. 2020.
[8] M. G. Shibin, S. K. S. M., and S. P. S., “Arc acoustic sensing for quality monitoring in gas tungsten arc welding,” Mech. Syst. Signal Process., vol. 147, Jan. 2021, Art. no. 107127.
[9] P. J. Modenesi, E. R. Apolinário, and I. M. Pereira, “Welding process monitoring and quality control,” in Welding Processes, R. S. Parmar, Ed. London, U.K.: IntechOpen, 2012, ch. 8.
[10] A. Kumar, R. S. Patel, and V. K. Singh, “Deep convolutional neural network for weld defect classification using multisensor fusion,” IEEE Sens. J., vol. 21, no. 16, pp. 18153–18162, Aug. 2021.
[11] Y. Li, Y. Li, and G. Wang, “Real-time monitoring of welding stability based on voltage signal,” J. Mater. Process. Technol., vol. 210, no. 14, pp. 2030–2035, Nov. 2010.
[12] L. F. P. de Alcantara, D. F. de Oliveira, and R. T. de Sousa, “Feature extraction methods for welding quality assessment: A systematic review,” J. Nondestruct. Eval., vol. 40, no. 2, p. 46, Jun. 2021.
[13] C. Song, Z. Wu, J. Gray, and Z. Meng, “An RFID-Powered Multisensing Fusion Industrial IoT System for Food Quality Assessment and Sensing,” IEEE Trans. Ind. Informatics, vol. 20, no. 1, 2024, doi: 10.1109/TII.2023.3262197.
[14] S. Ma, W. Ding, Y. Liu, S. Ren, and H. Yang, “Digital twin and big data-driven sustainable smart manufacturing based on information management systems for energy-intensive industries,” Appl. Energy, vol. 326, 2022, doi: 10.1016/j.apenergy.2022.119986.
[15] T. Wang, B. Hu, Y. Feng, X. Gao, C. Yang, and J. Tan, “Data Augmentation-Based Manufacturing Quality Prediction Approach in Human Cyber-Physical Systems,” J. Manuf. Sci. Eng., vol. 145, no. 12, 2023, doi: 10.1115/1.4063269.
[16] H. Zhou, K. M. Yu, Y. C. Chen, and H. P. Hsu, “A Hybrid Feature Selection Method RFSTL for Manufacturing Quality Prediction Based on a High Dimensional Imbalanced Dataset,” IEEE Access, vol. 9, 2021, doi: 10.1109/ACCESS.2021.3059298.
[17] T. Batu, H. G. Lemu, and H. Shimels, “Application of Artificial Intelligence for Surface Roughness Prediction of Additively Manufactured Components,” Materials, 2023, doi: 10.3390/ma16186266.
[18] A. Khdoudi, N. Barka, T. Masrour, I. El-Hassani, and C. El Mazgualdi, “Online prediction of automotive tempered glass quality using machine learning,” Int. J. Adv. Manuf. Technol., vol. 125, no. 3–4, 2023, doi: 10.1007/s00170-022-10649-7.
[19] D. Liu, Y. Du, W. Chai, C. Q. Lu, and M. Cong, “Digital Twin and Data-Driven Quality Prediction of Complex Die-Casting Manufacturing,” IEEE Trans. Ind. Informatics, vol. 18, no. 11, 2022, doi: 10.1109/TII.2022.3168309.
[20] H. Helgers et al., “Towards autonomous operation by advanced process control—process analytical technology for continuous biologics antibody manufacturing,” Processes, vol. 9, no. 1, 2021, doi: 10.3390/pr9010172.
[21] F. Xiang, L. Yang, M. Zhang, Y. Zuo, X. F. Zou, and F. Tao, “Model fusion based product quality prediction for complex manufacturing process,” Scientia Sinica Technologica, vol. 53, no. 7, 2023, doi: 10.1360/SST-2022-0427.
[22] H. Jung, J. Jeon, D. Choi, and A. J. Y. Park, “Application of machine learning techniques in injection molding quality prediction: Implications on sustainable manufacturing industry,” Sustainability, vol. 13, no. 8, 2021, doi: 10.3390/su13084120.
[23] L. P. Zhao, B. H. Li, and Y. Y. Yao, “A novel predict-prevention quality control method of multi-stage manufacturing process towards zero defect manufacturing,” Adv. Manuf., vol. 11, no. 2, 2023, doi: 10.1007/s40436-022-00427-9.
[24] M. Papananias, T. E. McLeay, M. Mahfouf, and V. Kadirkamanathan, “A Bayesian information fusion approach for end product quality estimation using machine learning and on-machine probing,” J. Manuf. Process., vol. 76, 2022, doi: 10.1016/j.jmapro.2022.01.020.
[25] C. Ruiz, D. Jafari, V. Venkata, T. H. J. Vaneker, W. Ya, and Q. Huang, “Prediction and Control of Product Shape Quality for Wire and Arc Additive Manufacturing,” J. Manuf. Sci. Eng., vol. 144, no. 11, 2022, doi: 10.1115/1.4054721.
[26] C. H. Chien, P. Y. Chen, A. J. C. Trappey, and C. V. Trappey, “Intelligent Supply Chain Management Modules Enabling Advanced Manufacturing for the Electric-Mechanical Equipment Industry,” Complexity, vol. 2022, 2022, doi: 10.1155/2022/8221706.
[27] J. Gim and L. S. Turng, “A review of current advancements in high surface quality injection molding: Measurement, influencing factors, prediction, and control,” Polymer Testing, 2022, doi: 10.1016/j.polymertesting.2022.107718.
[28] N. Leberruyer, J. Bruch, M. Ahlskog, and S. Afshar, “Toward Zero Defect Manufacturing with the support of Artificial Intelligence—Insights from an industrial application,” Comput. Ind., vol. 147, 2023, doi: 10.1016/j.compind.2023.103877.
[29] J. Takalo-Mattila, M. Heiskanen, V. Kyllonen, L. Maatta, and A. Bogdanoff, “Explainable Steel Quality Prediction System Based on Gradient Boosting Decision Trees,” IEEE Access, vol. 10, 2022, doi: 10.1109/ACCESS.2022.3185607.
[30] X. Li, Z. Huang, and W. Ning, “Intelligent manufacturing quality prediction model and evaluation system based on big data machine learning,” Comput. Electr. Eng., vol. 111, 2023, doi: 10.1016/j.compeleceng.2023.108904.
[31] V. Azamfirei, F. Psarommatis, and Y. Lagrosen, “Application of automation for in-line quality inspection, a zero-defect manufacturing approach,” J. Manuf. Syst., 2023, doi: 10.1016/j.jmsy.2022.12.010.
[32] S. Nannapaneni, S. Mahadevan, A. Dubey, and Y. T. T. Lee, "Online monitoring and control of a cyber-physical manufacturing process under uncertainty," J. Intell. Manuf., vol. 32, no. 5, 2021, doi: 10.1007/s10845-020-01609-7.
[33] M. Papananias, T. E. McLeay, M. Mahfouf, and V. Kadirkamanathan, "A probabilistic framework for product health monitoring in multistage manufacturing using Unsupervised Artificial Neural Networks and Gaussian Processes," Proc. Inst. Mech. Eng. Part B J. Eng. Manuf., vol. 237, no. 9, 2023, doi: 10.1177/09544054221136510.
[2] P. Kah and J. Martikainen, “Current trends in robotic welding and future challenges,” Int. J. Mech. Mater. Eng., vol. 10, no. 1, p. 13, Dec. 2015.
[3] J. Noruk, “The costs and benefits of nondestructive testing,” Weld. J., vol. 90, no. 5, pp. 46–49, May 2011.
[4] R. Halmshaw, Introduction to the Non-Destructive Testing of Welded Joints, 2nd ed. Abington, U.K.: Woodhead Publishing, 1996.
[5] A. S. R. Silva and J. M. A. Rebello, “The reliability of non-destructive testing in the evaluation of weld defects,” Insight, vol. 45, no. 5, pp. 331–335, May 2003.
[6] C. R. G. de Silva, “Economic aspects of nondestructive evaluation,” in Handbook of Nondestructive Evaluation, C. J. Hellier, Ed. New York, NY, USA: McGraw-Hill, 2001, ch. 2.
[7] H. Wang, J. Zhang, L. Wang, and Q. Wang, “Vision-based monitoring of weld pool geometry in GMAW,” J. Manuf. Process., vol. 56, pp. 1107–1114, Aug. 2020.
[8] M. G. Shibin, S. K. S. M., and S. P. S., “Arc acoustic sensing for quality monitoring in gas tungsten arc welding,” Mech. Syst. Signal Process., vol. 147, Jan. 2021, Art. no. 107127.
[9] P. J. Modenesi, E. R. Apolinário, and I. M. Pereira, “Welding process monitoring and quality control,” in Welding Processes, R. S. Parmar, Ed. London, U.K.: IntechOpen, 2012, ch. 8.
[10] A. Kumar, R. S. Patel, and V. K. Singh, “Deep convolutional neural network for weld defect classification using multisensor fusion,” IEEE Sens. J., vol. 21, no. 16, pp. 18153–18162, Aug. 2021.
[11] Y. Li, Y. Li, and G. Wang, “Real-time monitoring of welding stability based on voltage signal,” J. Mater. Process. Technol., vol. 210, no. 14, pp. 2030–2035, Nov. 2010.
[12] L. F. P. de Alcantara, D. F. de Oliveira, and R. T. de Sousa, “Feature extraction methods for welding quality assessment: A systematic review,” J. Nondestruct. Eval., vol. 40, no. 2, p. 46, Jun. 2021.
[13] C. Song, Z. Wu, J. Gray, and Z. Meng, “An RFID-Powered Multisensing Fusion Industrial IoT System for Food Quality Assessment and Sensing,” IEEE Trans. Ind. Informatics, vol. 20, no. 1, 2024, doi: 10.1109/TII.2023.3262197.
[14] S. Ma, W. Ding, Y. Liu, S. Ren, and H. Yang, “Digital twin and big data-driven sustainable smart manufacturing based on information management systems for energy-intensive industries,” Appl. Energy, vol. 326, 2022, doi: 10.1016/j.apenergy.2022.119986.
[15] T. Wang, B. Hu, Y. Feng, X. Gao, C. Yang, and J. Tan, “Data Augmentation-Based Manufacturing Quality Prediction Approach in Human Cyber-Physical Systems,” J. Manuf. Sci. Eng., vol. 145, no. 12, 2023, doi: 10.1115/1.4063269.
[16] H. Zhou, K. M. Yu, Y. C. Chen, and H. P. Hsu, “A Hybrid Feature Selection Method RFSTL for Manufacturing Quality Prediction Based on a High Dimensional Imbalanced Dataset,” IEEE Access, vol. 9, 2021, doi: 10.1109/ACCESS.2021.3059298.
[17] T. Batu, H. G. Lemu, and H. Shimels, “Application of Artificial Intelligence for Surface Roughness Prediction of Additively Manufactured Components,” Materials, 2023, doi: 10.3390/ma16186266.
[18] A. Khdoudi, N. Barka, T. Masrour, I. El-Hassani, and C. El Mazgualdi, “Online prediction of automotive tempered glass quality using machine learning,” Int. J. Adv. Manuf. Technol., vol. 125, no. 3–4, 2023, doi: 10.1007/s00170-022-10649-7.
[19] D. Liu, Y. Du, W. Chai, C. Q. Lu, and M. Cong, “Digital Twin and Data-Driven Quality Prediction of Complex Die-Casting Manufacturing,” IEEE Trans. Ind. Informatics, vol. 18, no. 11, 2022, doi: 10.1109/TII.2022.3168309.
[20] H. Helgers et al., “Towards autonomous operation by advanced process control—process analytical technology for continuous biologics antibody manufacturing,” Processes, vol. 9, no. 1, 2021, doi: 10.3390/pr9010172.
[21] F. Xiang, L. Yang, M. Zhang, Y. Zuo, X. F. Zou, and F. Tao, “Model fusion based product quality prediction for complex manufacturing process,” Scientia Sinica Technologica, vol. 53, no. 7, 2023, doi: 10.1360/SST-2022-0427.
[22] H. Jung, J. Jeon, D. Choi, and A. J. Y. Park, “Application of machine learning techniques in injection molding quality prediction: Implications on sustainable manufacturing industry,” Sustainability, vol. 13, no. 8, 2021, doi: 10.3390/su13084120.
[23] L. P. Zhao, B. H. Li, and Y. Y. Yao, “A novel predict-prevention quality control method of multi-stage manufacturing process towards zero defect manufacturing,” Adv. Manuf., vol. 11, no. 2, 2023, doi: 10.1007/s40436-022-00427-9.
[24] M. Papananias, T. E. McLeay, M. Mahfouf, and V. Kadirkamanathan, “A Bayesian information fusion approach for end product quality estimation using machine learning and on-machine probing,” J. Manuf. Process., vol. 76, 2022, doi: 10.1016/j.jmapro.2022.01.020.
[25] C. Ruiz, D. Jafari, V. Venkata, T. H. J. Vaneker, W. Ya, and Q. Huang, “Prediction and Control of Product Shape Quality for Wire and Arc Additive Manufacturing,” J. Manuf. Sci. Eng., vol. 144, no. 11, 2022, doi: 10.1115/1.4054721.
[26] C. H. Chien, P. Y. Chen, A. J. C. Trappey, and C. V. Trappey, “Intelligent Supply Chain Management Modules Enabling Advanced Manufacturing for the Electric-Mechanical Equipment Industry,” Complexity, vol. 2022, 2022, doi: 10.1155/2022/8221706.
[27] J. Gim and L. S. Turng, “A review of current advancements in high surface quality injection molding: Measurement, influencing factors, prediction, and control,” Polymer Testing, 2022, doi: 10.1016/j.polymertesting.2022.107718.
[28] N. Leberruyer, J. Bruch, M. Ahlskog, and S. Afshar, “Toward Zero Defect Manufacturing with the support of Artificial Intelligence—Insights from an industrial application,” Comput. Ind., vol. 147, 2023, doi: 10.1016/j.compind.2023.103877.
[29] J. Takalo-Mattila, M. Heiskanen, V. Kyllonen, L. Maatta, and A. Bogdanoff, “Explainable Steel Quality Prediction System Based on Gradient Boosting Decision Trees,” IEEE Access, vol. 10, 2022, doi: 10.1109/ACCESS.2022.3185607.
[30] X. Li, Z. Huang, and W. Ning, “Intelligent manufacturing quality prediction model and evaluation system based on big data machine learning,” Comput. Electr. Eng., vol. 111, 2023, doi: 10.1016/j.compeleceng.2023.108904.
[31] V. Azamfirei, F. Psarommatis, and Y. Lagrosen, “Application of automation for in-line quality inspection, a zero-defect manufacturing approach,” J. Manuf. Syst., 2023, doi: 10.1016/j.jmsy.2022.12.010.
[32] S. Nannapaneni, S. Mahadevan, A. Dubey, and Y. T. T. Lee, "Online monitoring and control of a cyber-physical manufacturing process under uncertainty," J. Intell. Manuf., vol. 32, no. 5, 2021, doi: 10.1007/s10845-020-01609-7.
[33] M. Papananias, T. E. McLeay, M. Mahfouf, and V. Kadirkamanathan, "A probabilistic framework for product health monitoring in multistage manufacturing using Unsupervised Artificial Neural Networks and Gaussian Processes," Proc. Inst. Mech. Eng. Part B J. Eng. Manuf., vol. 237, no. 9, 2023, doi: 10.1177/09544054221136510.
Published
2025-12-19
How to Cite
HIDAYAT, RAHMAT.
Prediksi Kualitas Sambungan Las Robotik Menggunakan Random Forest dan Data Sensor Tegangan.
INFORMATION SYSTEM FOR EDUCATORS AND PROFESSIONALS : Journal of Information System, [S.l.], v. 10, n. 2, p. 159-170, dec. 2025.
ISSN 2548-3587.
Available at: <https://ejournal-binainsani.ac.id/index.php/ISBI/article/view/3778>. Date accessed: 15 july 2026.
doi: https://doi.org/10.51211/isbi.v10i2.3778.
Section
Articles
