توسعه سامانه هوشمند آشکارسازی آنی پاره‌شدن شمش و تختال در ماشین‌های ریخته‌گری پیوسته با استفاده از الگوریتم‌های هوش مصنوعی
حسین علیرضائی
1
(
دانشکده مهندسی برق، واحد نجف‌آباد، دانشگاه آزاد اسلامی، نجف‌آباد، ایران
)
سید محمدعلی زنجانی
2
(
دانشکده مهندسی برق، واحد نجف‌آباد، دانشگاه آزاد اسلامی، نجف‌آباد، ایران
)
کلید واژه: ماشین ریخته‌گری پیوسته, پاره شدن شمش, سامانه الکترونیکی آشکارساز, تشخیص پارگی خط, الگوریتم گرگ خاکستری, ماشین بردار پشتیبانی.,
چکیده مقاله :
در ماشین‌های ریخته‌گری پیوسته، پاره شدن شمش و تختال یکی از چالش‌های عملیاتی مهم است که باعث خسارات سنگین به تجهیزات و توقف تولید می‌شود. این حادثه زمانی رخ می‌دهد که پوسته شمش یا تختال در مراحل اولیه ریخته‌گری پاره شده و مذاب درون آن به اجزای ماشین از جمله غلتک‌ها و بیرینگ‌ها نفوذ می‌کند. در این مقاله، برای کاهش خسارات ناشی از این پدیده، سامانه‌ای بر پایه تکنیک‌های هوشمند ارائه شده است. برای انتخاب بهینه نوع سیم‌های مورد استفاده، از الگوریتم گرگ خاکستری استفاده شده است و سامانه‌ای طراحی شده است که بتواند در دمای بالا و شرایط محیطی سخت مقاومت کند. این سیم‌ها با ویژگی‌های مقاوم به دمای 1000 درجه سانتی‌گراد، تنش و کشش بالا و کمترین خزش، در بین غلتک‌ها نصب می‌شوند. همچنین، برای تشخیص آنی و هوشمند خطاها، از ماشین بردار پشتیبانی استفاده شده است. این سامانه پس از پاره شدن شمش، با تشخیص سیگنال اتصال زمین به‌وسیله ماژول PLC، هشدارهای لازم را به اپراتورها ارسال کرده و از بروز خسارت‌های بیشتر جلوگیری می‌کند. با ترکیب تکنیک‌های هوش مصنوعی و بهینه‌سازی، سامانه پیشنهادی، دقت و کارایی بالایی را در شرایط عملیاتی سخت فراهم می‌آورد.
چکیده انگلیسی :
In continuous casting machines, slab and billet breakout is a significant operational challenge that leads to severe equipment damage and production downtime. This phenomenon occurs when the slab or billet shell ruptures in the early stages of casting, causing the molten metal inside to spill out and adhere to the machine components such as rollers and bearings. This paper proposes a smart system to mitigate the damages caused by this event. The Grey Wolf Optimizer (GWO) algorithm is employed to optimize the selection of wire materials used in the detection system, ensuring resistance to high temperatures and harsh environmental conditions. These wires, with the ability to withstand temperatures up to 1000°C, high tensile strength, and minimal creep, are installed between the rollers. Additionally, for real-time intelligent fault detection, Support Vector Machines (SVM) are used. Upon breakout, the system detects a grounding signal through a PLC module and immediately sends alerts to operators, preventing further damage. The proposed system provides high accuracy and reliability in demanding operational conditions by integrating AI and optimization techniques
[1] R. I. Guthrie and M. M. Isac, "Continuous casting practices for steel: Past, present and future," Metals, vol. 12, no. 5, p. 862, 2022, doi: 10.3390/met12050862.
[2] S. Louhenkilpi, "Continuous casting of steel," in Treatise on Process Metallurgy, Elsevier, 2024, pp. 343–383, doi: 10.1016/B978-0-323-85373-6.00009-0.
[3] W. Wang, C. Ji, S. Luo and M. Zhu, "Modeling of dendritic evolution of continuously cast steel billet with cellular automaton," Metallurgical and Materials Transactions B, vol. 49, pp. 200–212, 2018, doi: 10.1007/s11663-017-1131-5.
[4] A. H. Bui and V. H. Nguyen, "Defects of the steel billet in continuous casting," Journal of Metals, Materials and Minerals, vol. 30, no. 1, 2020, doi: 10.55713/jmmm.v30i1.574.
[5] Y. Han, W. Yan, J. Zhang, W. Chen, J. Chen and Q. Liu, "Optimization of thermal soft reduction on continuous-casting billet," ISIJ International, vol. 60, no. 1, pp. 106–113, 2020, doi: 10.2355/isijinternational.isijint-2019-409.
[6] F. Zhang, M. Liu, Z. Zhou and W. Shen, "An IoT-based online monitoring system for continuous steel casting," IEEE Internet of Things Journal, vol. 3, no. 6, pp. 1355–1363, 2016, doi: 10.1109/jiot.2016.2600630.
[7] A. K. Bhattacharya and D. Sambasivam, "Optimization of oscillation parameters in continuous casting process of steel manufacturing: Genetic algorithms versus differential evolution," Evolutionary Computation, pp. 77–102, 2009, doi: 10.5772/9616.
[8] S. I. Shakhov, Z. K. Kabakov S. M. Gorbatyuk, A. A. Gerasimova and D. S. Shakhov, "Improvements to electromagnetic stirring systems for billet and bloom continuous casting machines. Part 1," Metallurgist, vol. 66, no. 5, pp. 510–517, 2022, doi: 10.1007/s11015-022-01354-7.
[9] Y. Lu, "On the investigation of hot tearing behavior of continuous cast steel," Ph.D. dissertation, Missouri Univ. of Sci. and Technol., 2020.
[10] J. Jakubowski et al., "Artificial intelligence approaches for predictive maintenance in the steel industry: A survey," arXiv preprint arXiv:2405.12785, 2024.
[11] J. E. Kelly, K. P. Michalek, T. G. O’Connor, B. G. Thomas and J. A. Dantzig, "Initial development of thermal and stress fields in continuously cast steel billets," Metallurgical Transactions A, vol. 19, pp. 2589–2602, 1988, doi: 10.1007/bf02645486.
[12] Q. Ouyang, L. Z. Zhang, L. M. Zhao, X. L. Zhang and D. F. Chen, "Experimental study on quantitative surface defect depth detection based on laser scanning technology in continuous casting," Ironmaking & Steelmaking, vol. 38, no. 5, pp. 363–368, 2011, doi: 10.1179/1743281211y.0000000005.
[13] X. Wu, W. Jiang, S. Yuan, H. Kang, Q. Gao and J. Mi, "Automatic casting control method of continuous casting based on improved soft actor–critic algorithm," Metals, vol. 13, no. 4, p. 820, 2023, doi: 10.3390/met13040820.
[14] S. Park, K. Changgyun and S. Youm, "Establishment of an IoT-based smart factory and data analysis model for the quality management of SMEs die-casting companies in Korea," International Journal of Distributed Sensor Networks, vol. 15, no. 10, pp. 1–13, 2019, doi: 10.1177/1550147719879378.
[15] D. Cemernek et al., "Machine learning in continuous casting of steel: A state-of-the-art survey," Journal of Intelligent Manufacturing, pp. 1–19, 2022, doi: 10.1007/s10845-021-01754-7.
[16] B. Mintz and D. N. Crowther, "Hot ductility of steels and its relationship to the problem of transverse cracking in continuous casting," International Materials Reviews, vol. 55, no. 3, pp. 168–196, 2010, doi: 10.1179/095066009x12572530170624.
[17] K. M. Banks, A. Tuling and B. Mintz, "Influence of thermal history on hot ductility of steel and its relationship to the problem of cracking in continuous casting," Materials Science and Technology, vol. 28, no. 5, pp. 536–542, 2012, doi: 10.1179/1743284711y.0000000094.
[18] Y. Jiang et al., "Advance on rock-breaking cutter steels: A review of characteristics, failure modes, molding processes and strengthening technology," Journal of Materials Research and Technology, 2024, doi: 10.1016/j.jmrt.2024.06.195.
[19] J. Li, X. W. Xu, N. Ren, M. X. Xia and J. G. Li, "A review on prediction of casting defects in steel ingots: From macrosegregation to multi-defect model," Journal of Iron and Steel Research International, vol. 29, no. 12, pp. 1901–1914, 2022, doi: 10.1007/s42243-022-00848-7.
[20] B. Chakraborty and B. K. Sinha, "Process-integrated steel ladle monitoring, based on infrared imaging–a robust approach to avoid ladle breakout," Quantitative InfraRed Thermography Journal, vol. 17, no. 3, pp. 169–191, 2020, doi: 10.1080/17686733.2019.1639112.
[21] R. Emadi, A. Hajipoor and H. Emadi, "Investigation the causes of corrosion and failure of the submerged entry nozzle for continuous casting of steel," Journal of Advanced Processes in Materials Engineering, vol. 10, no. 2, pp. 193–203, 2016.
[22] M. Khodaei, A. Hajipour and M. Meratian, "Numerical simulation on melt flow in steel continuous casting and inclusion tracing," Journal of Advanced Processes in Materials Engineering, vol. 9, no. 4, pp. 43–51, 2017, doi: 10.3724/sp.j.1037.2010.00479.
[23] B. G. Thomas, "Review on modeling and simulation of continuous casting," Steel Research International, vol. 89, no. 1, p. 1700312, 2018, doi: 10.1002/srin.201700312.
[24] A. J. Moshayedi, A. S. Khan, S. Yang and S. M. Zanjani, "Personal image classifier based handy pipe defect recognizer (hpd): Design and test," in 2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP), Apr. 2022, pp. 1721–1728, doi: 10.1109/icsp54964.2022.9778676.
[25] B. Eghtedari, M. Meratian, A. Maleki and M. Khodaei, "The effect of pressure on the Mg alloy-Alumina composite properties fabricated by infiltration casting," Advanced Processes in Materials Engineering, vol. 10, no. 1, pp. 115–124, 2016, dor: 20.1001.1.24233226.1395.10.1.10.5.
[26] H. Shahinzadeh et al., "Deep learning: A overview of theory and architectures," in 20th CSI International Symposium on Artificial Intelligence and Signal Processing (AISP), Feb. 2024, pp. 1–11, doi: 10.1109/aisp61396.2024.10475265.
[27] C. Yao, M. Wang, M. Zhang, L. Xing, H. Zhang and Y. Bao, "Effects of mold electromagnetic stirring on heat transfer, species transfer and solidification characteristics of continuous casting round billet," Journal of Materials Research and Technology, vol. 19, pp. 1766–1776, 2022, doi: 10.1016/j.jmrt.2022.05.167.
[28] A. Asilian and S. M. Zanjani, "Application of Levenberg-Marquardt backpropagation algorithm in artificial neural network for self-calibration of deflection type Wheatstone bridge circuit in CO electrochemical gas sensor," Majlesi Journal of Electrical Engineering, vol. 18, no. 1, pp. 21–32, 2024, doi: 10.30486/mjee.2023.1988651.1157.
[29] M. Khurram, S. Iqbal, S. M. Fahad and A. Quddoos, "The effect of temperature, cooling rate and casting speed on quality of continuous cast steel billets," Advanced Materials Research, vol. 1171, pp. 61–72, 2022, doi: 10.4028/p-3955cb.
[30] K. B. Nagashanmugam et al., "Iron making in induction furnace for casting steel billets," Materials Today: Proceedings, 2023, doi: 10.1016/j.matpr.2023.06.253.
[31] S. J. A. D. Hosseini, M. Moazzami, H. Shahinzadeh, G. B. Gharehpetian and J. Moradi, "SCUC considering loads and wind power forecasting uncertainties using binary gray wolf optimization method," Majlesi Journal of Electrical Engineering, vol. 12, no. 4, p. 15, 2018.
[32] S. M. Zanjani, H. Shahinzadeh, J. Moradi, M. H. Fayaz-Dastgerdi, W. Yaïci and M. Benbouzid, "Short-term load forecasting using the combined method of wavelet transform and neural networks tuned by the gray wolf optimization algorithm," in Global Energy Conference (GEC), Oct. 2022, pp. 294–299, doi: 10.1109/gec55014.2022.9986711.
[33] T. Han, L. Zhang, Z. Yin and A. C. Tan, "Rolling bearing fault diagnosis with combined convolutional neural networks and support vector machine," Measurement, vol. 177, p. 109022, 2021, doi: 10.1016/j.measurement.2021.109022.
[34] A. Mangal, T. Vyas, R. Gupta, S. Tanwar and H. Shahinzadeh, "Neurosymbolic AI-based framework for sports ball identification concerning toddlers," in 20th CSI International Symposium on Artificial Intelligence and Signal Processing (AISP), Feb. 2024, pp. 1–6, doi: 10.1109/aisp61396.2024.10475201.
[35] M. Cui, Y. Wang, X. Lin and M. Zhong, "Fault diagnosis of rolling bearings based on an improved stack autoencoder and support vector machine," IEEE Sensors Journal, vol. 21, no. 4, pp. 4927–4935, 2020, doi: 10.1109/jsen.2020.3030910.