تعیین محل اصابت صاعقه به کمک روش معکوس زمانی الکترومغناطیسی(EMTR) و یادگیری ماشین
محورهای موضوعی : مهندسی برق و کامپیوترعباس همدونی اصلی 1 , محمدحسن مرادی 2 *
1 - دانشكده مهندسی برق دانشگاه بوعلی سینا
2 - دانشكده مهندسی برق، دانشگاه بوعلی سینا
کلید واژه: تعیین محل اصابت صاعقه, تفاضل محدود حوزه زمان, روش معکوس زمانی الکترومغناطیسی, یادگیری ماشین,
چکیده مقاله :
تعیین محل اصابت صاعقه (LLS) از چالش‌های امروزی در حوزه‌های مختلف و به‌ویژه حوزه برق و الکترونیک است. برای تعیین محل اصابت صاعقه، استفاده از روش‌های کلاسیک مرسوم بود؛ ولی اخیراً استفاده از روش معکوس زمانی الکترومغناطیسی (EMTR) نیز رواج یافته است. با توجه به محاسبه شکل موج کامل میدان با استفاده از روش EMTR، دقت در تعیین محل اصابت صاعقه به‌طور قابل توجهی نسبت به روش‌های پیشین افزایش یافته است. در روش معکوس زمانی الکترومغناطیسی به کمک تفاضل محدود حوزه زمان (FDTD)، ابتدا میدان الکترومغناطیسی گذرای تولیدشده توسط کانال صاعقه محاسبه شده و پس از معکوس‌کردن زمانی موج، از محل حسگر یا حسگرها به منبع خود بازانتشار می‌گردد و مجدداً با کمک FDTD، میدان الکترومغناطیسی بازانتشاری در محیط مورد نظر محاسبه می‌شود. با داشتن میدان الکترومغناطیسی محیط با استفاده از معیارهایی مانند حداکثر دامنه میدان، حداکثر انرژی و آنتروپی و ...، محل اصابت صاعقه تعیین می‌گردد. در این مقاله روشی بر اساس ترکیب یادگیری ماشین و EMTR برای تعیین محل اصابت صاعقه پیشنهاد شده است. ابتدا روش تفاضل محدود حوزه زمان سه‌بعدی(D-FDTD3) در محاسبه میدان الکترومغناطیسی محیط به‌کار گرفته شد و با استفاده از EMTR میدان الکترومغناطیسی بازانتشاری مجدداً با کمک (D-FDTD3) در کل محیط محاسبه گردید. بدین طریق داده‌های لازم برای تولید پروفایل‌های سه‌بعدی تصاویر RGB آماده گردید. سپس برای یادگیری ماشین از VGG19، یک شبکه عصبی کانولوشنی (CNN) از پیش آموزش‌دیده، برای استخراج ویژگی‌های تصاویر استفاده شد. در آخر برای تعیین محل اصابت صاعقه، لایه برازش‌کننده‌ای به بالای 19VGG اضافه شد. روش پیشنهادی در MATLAB و Python شبیه‌سازی و اجرا گردید که نتایج، کارایی آن را برای تعیین محل اصابت صاعقه در محیط سه‌بعدی نشان می‌دهند.
Determining the location of lightning strikes (LLS) is one of today's challenges in various fields, especially in the fields of electricity and electronics. To determine the location of the lightning strike, classical methods were used previously; however, the use of electromagnetic time reversal (EMTR) method has also become popular recently. According to the calculation of the complete waveform of the field using the EMTR method, the accuracy in determining the location of the lightning strike has significantly increased compared to the traditional methods. In the electromagnetic time reversal method with the help of finite difference time domain (FDTD), the transient electromagnetic field produced by the lightning channel is calculated first. After the time reversal of the wave, it is re-emitted from the sensor or sensors to its source and again with the help of FDTD, The re-emission electromagnetic field in the desired environment is calculated. With the electromagnetic field of the environment, using criteria (such as maximum field amplitude, maximum energy and entropy, etc.), the location of the lightning strike is determined. In traditional methods, it is quite difficult to determine the uniqueness of the final response in environments with different characteristics, and the use of at least three sensors is mandatory. In this paper, to overcome these limitations, a method based on the combination of machine learning and three-dimensional EMTR (3D-FDTD) is proposed to determine the lightning strike location. First, the three-dimensional time domain finite difference method is used to calculate the electromagnetic field of the environment and using EMTR, the back-diffusion electromagnetic field (again with the help of 3D-FDTD) is calculated in the entire environment. In this way, the necessary data for the production of RGB image profiles is prepared. Then VGG19, a pre-trained convolutional neural network (CNN), is used to extract image features. Finally, a fitting layer is used to determine the location of the lightning strike. The proposed method is simulated and implemented in MATLAB and Python, and the results show the effectiveness of the proposed method to determine the location of lightning strikes in a three-dimensional environment without requiring the use of at least three sensors.
[1] F. Rachidi, M. Rubinstein, and M. Paolone, Electromagnetic Time Reversal: Application to EMC and Power Systems, Wiley Online Library, 2017.
[2] A. I. Ioannidis, P. N. Mikropoulos, T. E. Tsovilis, and N. D. Kokkinos, "Lightning protection of historical buildings and cultural heritage monuments: a literature review," in Proc. of the 36th Int. Conf. on Lightning Protection, ICLP'22, pp. 479-484, Cape Town, South Africa, 2-7 Oct. 2022.
[3] Y. Baba and V. A. Rakov, Electromagnetic Computation Methods for Lightning Surge Protection Studies, John Wiley & Sons, 2016.
[4] J. An, C. Zhuang, F. Rachidi, and R. Zeng, "An effective EMTR-based high-impedance fault location method for transmission lines," IEEE Trans. on Electromagnetic Compatibility, vol. 63, no. 1, pp. 268-276, Feb. 2021.
[5] R. Razzaghi, et al., "An efficient method based on the electromagnetic time reversal to locate faults in power networks," IEEE Trans. on Power Delivery, vol. 28, no. 3, pp. 1663-1673, Jul. 2013.
[6] Z. Wang, R. Razzaghi, M. Paolone, and F. Rachidi, "Electromagnetic time reversal similarity characteristics and its application to locating faults in power networks," IEEE Trans. on Power Delivery, vol. 35, no. 4, pp. 1735-1748, Aug. 2020.
[7] R. Razzaghi, et al., "Locating lightning strikes and flashovers along overhead power transmission lines using electromagnetic time reversal," Electric Power Systems Research, vol. 160, pp. 282-291, Jul. 2018.
[8] N. Pineda, et al., "Meteorological aspects of self‐initiated upward lightning at the säntis tower (switzerland)," J. of Geophysical Research: Atmospheres, vol. 124, no. 24, pp. 14162-14183, 27 Dec. 2019.
[9] D. Li, et al., "The propagation effects of lightning electromagnetic fields over mountainous terrain in the earth-ionosphere waveguide," J. of Geophysical Research: Atmospheres, vol. 124, no. 24, pp. 14198-14219, 27 Dec. 2019.
[10] M. Azadifar, et al., "Partial discharge localization using electromagnetic time reversal: a performance analysis," IEEE Access, vol. 8, pp. 147507-147515, 020.
[11] H. Karami, M. Azadifar, A. Mostajabi, M. Rubinstein, and F. Rachidi, "Localization of electromagnetic interference source using a time reversal cavity: application of the maximum power criterion," in Proc. of the IEEE Int. Symp. on Electromagnetic Compatibility & Signal/Power Integrity, EMCSI'20, pp. 598-602, Reno, NV, USA, 28 Jul.-28 Aug. 2020.
[12] A. Nag, M. Murphy, W. Schulz, and K. Cummins, "Lightning locating systems: insights on characteristics and validation techniques," Earth and Space Science, vol. 2, no. 4, pp. 65-93, Apr. 2015.
[13] R. Razzaghi, G. Lugrin, F. Rachidi, and M. Paolone, "Assessment of the influence of losses on the performance of the electromagnetic time reversal fault location method," IEEE Trans. on Power Delivery, vol. 32, no. 5, pp. 2303-2312, Oct. 2017.
[14] D. Li, et al., "On lightning electromagnetic field propagation along an irregular terrain," IEEE Trans. on Electromagnetic Compatibility, vol. 58, no. 1, pp. 161-171, Feb. 2016.
[15] H. Karami, et al., "Locating lightning using electromagnetic time reversal: application of the minimum entropy criterion," in Proc. of the Int. Symp. on Lightning Protection, XV SIPDA'19, 4 pp., Sao Paulo, Brazil, 30 Sept.-4 Oct. 2019.
[16] K. S. Kunz and R. J. Luebbers, The Finite Difference Time Domain Method for Electromagnetic, CRC Press, 1993.
[17] D. Li, Q. Zhang, Z. Wang, and T. Liu, "Computation of lightning horizontal field over the two-dimensional rough ground by using the three-dimensional FDTD," IEEE Trans. on Electromagnetic Compatibility, vol. 56, no. 1, pp. 143-148, Feb. 2014.
[18] Y. Liu, R. Mittra, T. Su, X. Yang, and W. Yu, Parallel finite-difference time-domain method: Artech, 2006.
[19] W. Hou, M. Azadifar, M. Rubinstein, F. Rachidi, and Q. Zhang, "The polarity reversal of lightning‐generated sky wave," J. of Geophysical Research: Atmospheres, vol. 125, no. 17, Article ID: e2020JD032448, 16 Sept. 2020.
[20] F. Wu, J. L. Thomas, and M. Fink, "Time reversal of ultrasonic fields. II. experimental results," IEEE Trans. on Ultrasonics, Ferroelectrics, and Frequency Control, vol. 39, no. 5, pp. 567-578, Sept. 1992.
[21] J. Sun, Q. Yang, W. Xu, and W. He, "A distribution line fault location estimation algorithm based on electromagnetic time-reversal method calculated in the finite difference time domain," IEEE Trans. on Electromagnetic Compatibility, vol. 64, no. 3, pp. 865-873, Jun. 2022.
[22] H. Karami, F. Rachidi, and M. Rubinstein, "On the use of electromagnetic time reversal for lightning location," in Proc. 1st URSI Atlantic Radio Science Conf., URSI AT-RASC'15, Gran Canaria, Spain, 16-24 May 2015.
[23] G. Lugrin, N. M. Mora, F. Rachidi, M. Rubinstein, and G. Diendorfer, "On the location of lightning discharges using time reversal of electromagnetic fields," IEEE Trans. on Electromagnetic Compatibility, vol. 56, no. 1, pp. 149-158, Feb. 2013.
[24] N. Mora, F. Rachidi, and M. Rubinstein, "Application of the time reversal of electromagnetic fields to locate lightning discharges," Atmospheric Research, vol. 117, pp. 78-85, Nov. 2012.
[25] H. Karami, M. Azadifar, A. Mostajabi, M. Rubinstein, and F. Rachidi, "Numerical and experimental validation of electromagnetic time reversal for geolocation of lightning strikes," IEEE Trans. on Electromagnetic Compatibility, vol. 62, no. 5, pp. 2156-2163, Oct. 2019.
[26] S. Mohammadi, H. Karami, M. Azadifar, and F. Rachidi, "On the efficiency of openACC-aided GPU-based FDTD approach: application to lightning electromagnetic fields," Applied Sciences, vol. 10, no. 7, Article ID: 2359, 2020.
[27] S. Mohammadi, H. Karami, M. Azadifar, M. Rubinstein, and F. Rachidi, "Assessing the efficacy of a GPU-based MW-FDTD method for calculating lightning electromagnetic fields over large-scale terrains," IEEE Letters on Electromagnetic Compatibility Practice and Applications, vol. 2, no. 4, pp. 106-110, Dec. 2020.
[28] T. Wang, S. Qiu, L. H. Shi, and Y. Li, "Broadband VHF localization of lightning radiation sources by EMTR," IEEE Trans. on Electromagnetic Compatibility, vol. 59, no. 6, pp. 1949-1957, Dec. 2017.
[29] L. Chen, et al., "Artificial intelligence-based solutions for climate change: a review," Environmental Chemistry Letters, vol. 21, no. 5, pp. 2525-2557, Oct. 2023.
[30] L. Wang, B. M. Hare, K. Zhou, H. Stöcker, and O. Scholten, "Identifying lightning structures via machine learning," Chaos, Solitons & Fractals, vol. 170, Article ID: 113346, May 2023.
[31] X. Wang, K. Hu, Y. Wu, and W. Zhou, "A Survey of Deep Learning-Based Lightning Prediction," Atmosphere, vol. 14, no. 11, Article ID: 1698, 2023.
[32] J. Leinonen, U. Hamann, I. V. Sideris, and U. Germann, "Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model," Geophysical Research Letters, vol. 50, no. 8, Article ID: e2022GL101626, 28 Apr. 2023.
[33] J. Tavoosi, et al., "A hybrid approach for fault location in power distributed networks: impedance-based and machine learning technique," Electric Power Systems Research, vol. 210, Article ID: 108073, Sept. 2022.
[34] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436-444, 27 May 2015.
[35] T. Chen and C. Guestrin, "Xgboost: a scalable tree boosting system," in Proc. of the 22nd ACM SIGKDD Int. Con. on Knowledge Discovery and Data Mining, pp. 785-794, San Francisco, CA, USA, 13-17 Aug. 2016.
[36] P. W. Holland and R. E. Welsch, "Robust regression using iteratively reweighted least-squares," Communications in Statistics-Theory and Methods, vol. 6, no. 9, pp. 813-827, 1977.
[37] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.
[38] R. Yamashita, M. Nishio, R. K. G. Do, and K. Togashi, "Convolutional neural networks: an overview and application in radiology," Insights into Imaging, vol. 9, pp. 611-629, Aug. 2018.
[39] J. Yosinski, J. Clune, Y. Bengio, and H. Lipson, "How transferable are features in deep neural networks?" in Proc. of the 27th Int. Conf. on Neural Information Processing Systems, NIPs'14, vol. 2, pp. 3320-3328, Montreal, Canada, 8-13 Dec. 2014.
[40] S. J. Pan and Q. Yang, "A survey on transfer learning," IEEE Trans. on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345-1359, Oct. 2010.
[41] A. Mostajabi, et al., "Single-sensor source localization using electromagnetic time reversal and deep transfer learning: application to lightning," Scientific Reports, vol. 9, no. 1, Article ID: 17372, 22 Nov. 2019.
[42] O. Russakovsky, et al., "Imagenet large scale visual recognition challenge," International J. of Computer Vision, vol. 115, pp. 211-252, 11 Apr. 2015.