|Table of Contents|

Citation:
　Ao Zhou,Yadong Zhang,Wentie Yang,et al.Ship Magnetic Field Modeling and Extrapolation Based on a Convolutional Neural Network[J].Journal of Marine Science and Application,2026,(2):536-549.[doi:10.1007/s11804-025-00783-5]
Click and Copy

Ship Magnetic Field Modeling and Extrapolation Based on a Convolutional Neural Network

Info

Title:
Ship Magnetic Field Modeling and Extrapolation Based on a Convolutional Neural Network
Author(s):
Ao Zhou1; 2;  Yadong Zhang1; 2;  Wentie Yang3;  Zuoshuai Wang3;  Jianxun Wang3;  Zhiwei Chen3
Affilations:
Author(s):
Ao Zhou1; 2;  Yadong Zhang1; 2;  Wentie Yang3;  Zuoshuai Wang3;  Jianxun Wang3;  Zhiwei Chen3
1. School of Electrical Engineering, Wuhan University, Wuhan, 430072, China;
2. State Key Laboratory of Power Grid Environmental Protection, School of Electrical Engineering and Automation, Wuhan University, Wuhan, 430072, China;
3. The 719th Research Institute of China Shipbuilding Industry Corporation, Wuhan, 442000, China
Keywords:
Shipboard magnetic field|Convolutional neural network|Genetic algorithm|Equivalent source method|Magnetic field extrapolation
分类号:
-
DOI:
10.1007/s11804-025-00783-5
Abstract:
Accurate modeling of ship magnetic fields is important for predicting their spatial distribution to improve the magnetic stealth effect of ships. This study proposes an extrapolation model for ship magnetic fields based on genetic algorithms and convolutional neural networks (CNNs). The magnetic probe position matrix of the traditional equivalent source is utilized as input, and the three-directional components of the magnetic field measured by the probes are employed as output. The extrapolation model for ship magnetic fields is obtained through iterative training and fitting with CNNs. Variables such as the number of magnetic dipoles, the distance between magnetic dipoles, the size and quantity of convolutional kernels, batch size, learning rate, and L2 regularization coefficient are optimized to boost the accuracy of the extrapolation model for magnetic fields. The fitting accuracy of the extrapolation model for ship magnetic fields is used as the optimization objective. Based on a finite element simulation model of ship magnetic fields, the accuracy and robustness of the CNN algorithm under different magnetic field conditions are validated using the known standard depth plane, the unknown depth at 1.125 times the standard depth plane, and the unknown depth at 1.25 times the standard depth plane. Results show that, after optimization, the fitting error for the magnetic field extrapolation model based on CNN is 1.50% for the standard depth plane, 1.63% for the unknown depth at 1.125 times the standard depth plane, and 2.36% for the unknown depth at 1.25 times the standard depth plane. The error remains below 5% under varying magnetic field conditions. When a random measurement error of 0%-5% is introduced for the magnetic probes, the prediction error at 1.25 times the standard depth plane is 2.30%; with a random error of 0%-10%, the prediction error is 4.95%. This approach significantly improves the accuracy and robustness of magnetic field extrapolation, which makes it an effective and feasible method for ship magnetic field modeling.

References:

[1] Birsan M (2021) Simulation of a ship’s deperming process using the Jiles-Atherton model. IEEE Transactions on Magnetics 57(6): 7300407. DOI: 10.1109/tmag.2021.3068555
[2] Chen YF, Yang QX, Li YJ, Zhang H, Zhang CG (2024) Data-driven deep convolutional neural networks for electromagnetic field estimation of transformers. IEEE Transactions on Applied Superconductivity 34(8): 5500805. DOI: 10.1109/tasc.2024.3420184
[3] Dai ZH, Zhou SH, Zhang XB (2021) Multi-objective optimization of ship magnetic field modeling method. Acta Physica Sinica 70(16): 164101. DOI: 10.7498/aps.70.20210334
[4] Deng B, Wang J, Xu X, Yi G (2024) Individual prediction of electric field induced by deep-brain magnetic stimulation with CNN-Transformer. IEEE Transactions on Neural Systems and Rehabilitation Engineering 32: 2143-2152. DOI: 10.1109/TNSRE.2024.3408902
[5] Gao JJ, Liu DM, Yao QH, Zhou GH, Yan HC (2006) Verifying the mathematics model of submarine magnetic field extrapolation with boundary element method through experiment. Acta Armamentarii 27(5): 869-872
[6] Gao JJ, Wang PZ, Zhu XL (2021) Calculation and verification of ship magnetic field based on boundary integral-iterative method. 2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 1-5. DOI: 10.1109/ICECCME52200.2021.9590861
[7] Han ZX, Hu JC, Li ZN, Ma PC, Peng QJ, Wang Q, Zheng ZZ, Zhu HW (2023) Magnetic field simulation of reactor based on deep neural networks. IEEE Transactions on Power Delivery 38(3): 2224-2227. DOI: 10.1109/tpwrd.2023.3256122
[8] Hua C, Huang C, Zuo Y, Wang W, Yang J (2020) Research on low frequency magnetic field test and equivalent modeling method of ship equipment. 6th Global Electromagnetic Compatibility Conference (GEMCCON), 1-3. DOI: 10.1109/GEMCCON50979.2020.9456684
[9] Hui Y, Xi C, Ye KQ (2010) The application of recursive algorithm on ship’s magnetic field extrapolation. Acta Armamentarii 31: 1200-1203
[10] Jakubiuk K, Zimny P, Wolszyn M (2012) Multidipoles model of ship’s magnetic field. 15th International Symposium on Applied Eleetromagneties and Meehanies, 45
[11] Jia W, Lin C (2018) Improved Euler method for preventing failure of positioning magnetic target magnetic Gradiometer. Journal of Navigation University of Engineering 30(3): 37-42
[12] Jin HH, Wang H, Zhuang ZH (2022) A new simple method to design degaussing coils using magnetic dipoles. Journal of Marine Science and Engineering 10(10): 1495. DOI: 10.3390/jmse10101495
[13] Khan A, Ghorbanian V, Lowther D (2019) Deep learning for magnetic field estimation. IEEE Transactions on Magnetics 55(6): 7202304. DOI: 10.1109/tmag.2019.2899304
[14] Lin PF, Zhang N, Chang M, Xu L (2020) Research on the model and the location method of ship shaft-rate magnetic field based on rotating magnetic dipole. IEEE Access 8: 162999-163005. DOI: 10.1109/access.2020.3021206
[15] Liu Q, Sun Z, Jiang R, Wu X, Lei Y (2022) A signal reconstruction and conversion method for magnetic field under a ship. Journal of Electrical Engineering 37(15): 3723-3732
[16] Menana H (2021) 3D FEM-BEM coupling for the magnetic field computation in thin shells: Application to the evaluation of ship magnetic signature. IEEE Transactions on Magnetics 57(6): 7402206. DOI: 10.1109/TMAG.2021.3062563
[17] Peng QJ, Sima WX, Sun JQ, Wang JS, Yang M, Zou DX (2025) Calculation method of transformer space dynamic magnetic field acceleration taking into account core nonlinearity. Journal of Electrotechnology 40(5): 1559-1574
[18] Sasaki H, Iwata K, Sato T, Sato Y (2024) Prediction of motor characteristic maps via deep operator networks for topology optimization. IEEE Transactions on Magnetics 60(12): 8206205. DOI: 10.1109/tmag.2024.3477448
[19] Sheinker A, Ginzburg B, Salomonski N, Yaniv A, Persky E (2021) Estimation of ship’s magnetic signature using multi-dipole modeling method. IEEE Transactions on Magnetics 57(5): 6500408. DOI: 10.1109/tmag.2021.3062998
[20] Synnes SA (2008) Representing elongated magnetic sources by prolate spheroidal harmonics developed on an optimized coordinate system. IEEE Transactions on Magnetics 44(10): 2277-2282. DOI: 10.1109/tmag.2008.2001917
[21] Tarnawski J, Cichocki A, Rutkowski TA, Buszman K, Woloszyn M (2020) Improving the quality of magnetic signature reproduction by increasing flexibility of multi-dipole model structure and enriching measurement information. IEEE Access 8: 190448-190462. DOI: 10.1109/access.2020.3031740
[22] Tarnawski J, Rutkowski TA, Woloszyn M, Cichocki A, Buszman K (2022) Magnetic signature description of ellipsoid-shape vessel using 3D multi-dipole model fitted on cardinal directions. IEEE Access 10: 16906-16930. DOI: 10.1109/access.2022.3147138
[23] Wang Y, Wang D, Chi C, Yu ZT, Li JW, Yu L (2024) Ship shaft-rate electric field signal denoising method based on VMD-MSS. Journal of Marine Science and Engineering 12(4): 544. DOI: 10.3390/jmse12040544
[24] Woloszyn M, Jankowski P (2017) Simulation of ship’s deperming process using Opera 3D. 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering (ISEF) Book of Abstracts, 1-2. DOI: 10.1109/ISEF.2017.8090680
[25] Yan J (2020) Research on magnetic modeling simulation technology of marine target. Master thesis, Harbin Institute of Technology, Harbin, 41-46
[26] Zateev AA, Ivanov YM, Semenov VG (2021) Enhancing the precision of measurements of a ship’s magnetic moment in the far field. Measurement Techniques 64(8): 681-688. DOI: 10.1007/s11018-021-01989-z
[27] Zhang Z, Yu W, Yi J (2018) Equivalent source forecast method for bad points’ field on ship’s magnetic field measuring. Journal of Huazhong University of Science and Technology (Natural Science Edition) 46(4): 63-67
[28] Zhou G, Xiao C, Liu S, Gao J (2009) 3D Magnetostatic Field Computation With Hexahedral Surface Integral Equation Method. Diangong Jishu Xuebao 24(3): 1-7

Memo

Memo:
Received date:2025-1-13;Accepted date:2025-6-16。<br>Corresponding author:Ao Zhou,E-mail:654449727@qq.com
Last Update: 2026-06-08