CPT磁力仪拖曳式探测系统的深度残差网络磁补偿方法

doi:10.11720/wtyht.2025.1400

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (3218 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract

The traditional Tolles-Lawson (TL) linear model suffers limitations of compensation precision in processing complex magnetic disturbance data obtained using a towed coherent population trapping (CPT)-based atomic magnetometer detection system. This study introduced neural network technology to achieve more precise nonlinear compensation. Given that conventional neural network models encounter issues such as gradient vanishment or overfitting during parameter updates, this study proposed a deep residual network-based magnetic compensation model (MCRNet) to further enhance the compensation effects of magnetic interference within a towed pod. Experimental results demonstrate that compared to the best traditional method—The Residual Backpropagation Network (ResBP), the proposed MCRNet model increased the improvement ratio (IR) to 4.826 from 4.251, increasing by 13.53%, and reduced the root mean square error (RMSE) of compensated residual magnetism to 0.171 from 0.2, representing a reduction of 14.5%. The proposed model enhances the magnetic survey accuracy of towed magnetic anomaly detection systems.

Key words： CPT-based atomic magnetometer towed detection system MCRNet model magnetic interference compensation neural network

Received: 26 September 2024 Published: 23 October 2025

ZTFLH:

TH762

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Qiang-Feng XU
	Xue-Feng WANG
	Yi-Cheng DENG
	Huan-Xue HE
	Hui-Song ZHANG
	Xiang-Dong LU

Cite this article:

Qiang-Feng XU,Xue-Feng WANG,Yi-Cheng DENG, et al. Deep residual network-based magnetic compensation for a towed, CPT-based magnetometer detection system[J]. Geophysical and Geochemical Exploration, 2025, 49(5): 1212-1220.

URL:

https://www.wutanyuhuatan.com/EN/10.11720/wtyht.2025.1400 OR https://www.wutanyuhuatan.com/EN/Y2025/V49/I5/1212

Residual network structure

MCRNet magnetic compensation neural network model

MCRNet parameter settings

Flowchart of model training and prediction

Frame of the towed magnetic anomaly detection pod

Test environment for towed pod detection

Magnetometer measured data

Block of the data set production process

Heading error compensation of the CPT atomic magnetometer

Model training and validation process

Test set prediction results

Parameters of the model

Comparison of different algorithms

[20]	彭翔, 郭弘. 光泵原子磁力仪技术[J]. 导航与控制, 2022, 21(S2):101-121,198.
[20]	Peng X, Guo H. Techniques in optically-pumped atomic magnetometer[J]. Navigation and Control, 2022, 21(S2):101-121,198.
[21]	Gnadt A R, Wollaber A B, Nielsen A P. Derivation and extensions of the tolles-lawson model for aeromagnetic compensation[EB/OL]. 2022:2212.09899,2022-12-19. https://arxiv.org/abs/2212.09899v1.
[22]	邱锡鹏. 神经网络与深度学习[M]. 北京: 机械工业出版社, 2020.
[22]	Qiu X P. Neural networks and deep learning[M]. Beijing: China Machine Press, 2020.
[23]	He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),IEEE,2016.
[24]	Wang H, Du C P, Wang H D, et al. Aeromagnetic compensation with suppressing heading error of the scalar atomic magnetometer[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(7):1134-1138.
[25]	Fan S F, Chen S D, Zhang S, et al. An improved Overhauser magnetometer for Earth’s magnetic field observation[C]// Earth Observing Systems XXI,SPIE, 2016.
[26]	Zhang X N, Kou J, Li J, et al. An omnidirectional measurement technology of CPT magnetometer based on coupling of the dark state[C]// Fourth Seminar on Novel Optoelectronic Detection Technology and Application,SPIE, 2018.
[27]	王学锋, 邓意成, 徐强锋, 等. 宇航用原子磁力仪研究与应用进展[J]. 前瞻科技, 2022, 1(1):159-168.
[27]	Wang X F, Deng Y C, Xu Q F, et al. Research and application progress of atomic magnetometers for aerospace[J]. Science and Technology Foresight, 2022, 1(1):159-168.
[28]	Vasconcelos J F, Elkaim G, Silvestre C, et al. Geometric approach to strapdown magnetometer calibration in sensor frame[J]. IEEE Transactions on Aerospace and Electronic Systems, 2011, 47(2):1293-1306.
[29]	Wu Y, Shi W. On calibration of three-axis magnetometer[J]. IEEE Sensors Journal, 2015, 15(11):6424-6431.
[30]	Merayo J M G, Brauer P, Primdahl F, et al. Scalar calibration of vector magnetometers[J]. Measurement Science and Technology, 2000, 11(2):120-132.
[31]	徐强锋, 王学锋, 邓意成, 等. CPT原子磁力仪转向差及其标定补偿[J]. 空间科学与试验学报, 2024, 24(1):95-101.
[31]	Xu Q F, Wang X F, Deng Y C, et al. Heading error calibration and compensation of CPT atomic magnetometer[J]. Journal of Space Science and Experiment, 2024, 24(1):95-101.
[32]	Xu Q F, Wang X F, Deng Y C, et al. Heading error calibration and compensation of CPT atomic magnetometer[J]. Journal of Space Science and Experiment, 2024, 1(1):95-101.
[1]	李晨, 周建军. 航磁探测水下目标关键技术发展及应用[J]. 舰船电子工程, 2023, 43(6):184-188.
[1]	Li C, Zhou J J. Key technology development and application on aeromagnetic detection of target underwater[J]. Ship Electronic Engineering, 2023, 43(6):184-188.
[2]	殷长春, 张博, 刘云鹤, 等. 航空电磁勘查技术发展现状及展望[J]. 地球物理学报, 2015, 58(8):2637-2653.
[2]	Yin C C, Zhang B, Liu Y H, et al. Review on airborne EM technology and developments[J]. Chinese Journal of Geophysics, 2015, 58(8):2637-2653.
[3]	魏征, 杜度, 刘洋, 等. 美国反潜装备技术发展研究[J]. 舰船科学技术, 2019, 41(17):154-157.
[3]	Wei Z, Du D, Liu Y, et al. Research on the development of anti-submarine equipment and technology[J]. Ship Science and Technology, 2019, 41(17):154-157.
[4]	Reeves C. Aeromagnetic surveys: principles, practice and interpretation[M]. Washington:Geosoft, 2005.
[5]	黄岩, 罗丁, 冯自成, 等. 无人直升机航磁测量系统集成及应用[J]. 物探与化探, 2019, 43(2):386-392.
[5]	Huang Y, Luo D, Feng Z C, et al. Unmanned helicopter aeromagnetic measurement system and its application[J]. Geophysical and Geochemical Exploration, 2019, 43(2):386-392.
[6]	西永在, 路宁, 张兰, 等. 基于无人直升机平台的航磁系统集成与应用[J]. 物探与化探, 2019, 43(1):125-131.
[33]	Kingma D P, Ba J. Adam:A method for stochastic optimization[C]// The 3^rd International Conference for Learning Representations, 2015.
[6]	Xi Y Z, Lu N, Zhang L, et al. Integration and application of an aeromagnetic survey system based on unmanned helicopter platform[J]. Geophysical and Geochemical Exploration, 2019, 43(1):125-131.
[7]	Dou Z J, Han Q, Niu X M, et al. An aeromagnetic compensation coefficient-estimating method robust to geomagnetic gradient[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(5):611-615.
[8]	Zheng Y X, Li S Y, Xing K, et al. Unmanned aerial vehicles for magnetic surveys:A review on platform selection and interference suppression[J]. Drones, 2021, 5(3):93.
[9]	Tolles W E, Lawson J D. Magnetic compensation of MAD equipped aircraft[J]. Airborne Instruments Lab.Inc., 1950, 201(1):1-5.
[10]	刘宇欣, 李雯, 魏东岩, 等. 一种顾及舱内OBE干扰的改进航磁补偿方法[J]. 导航定位与授时, 2024, 11(4):38-46.
[10]	Liu Y X, Li W, Wei D Y, et al. A modified aeromagnetic compensation method robust to in-cabin OBE interferences[J]. Navigation Positioning and Timing, 2024, 11(4):38-46.
[11]	Zhang C, Du C P, Peng X, et al. An aeromagnetic compensation method for suppressing the magnetic interference generated by electric current with vector magnetometer[J]. Sensors, 2022, 22(16):6151.
[12]	Li H, Ge J, Dong H B, et al.Aeromagnetic compensation of rotor UAV based on least squares[C]// 2018 37^th Chinese Control Conference (CCC), IEEE,2018.
[13]	Su Z N, Jiao J, Zhou S, et al. Aeromagnetic compensation method based on ridge regression algorithm[J]. Global Geology, 2022, 25(1):41-48.
[14]	Noriega G, Marszalkowski A. Adaptive techniques and other recent developments in aeromagnetic compensation[J]. First Break, 2017, 35(9):31-38.
[15]	Dou Z J, Liu C H, Wang J R, et al. An adaptive aeromagnetic compensation method based on local linear regression[J]. IOP Conference Series:Earth and Environmental Science, 2021, 783(1):012090.
[16]	Williams P M. Aeromagnetic compensation using neural networks[J]. Neural Computing & Applications, 1993, 1(3):207-214.
[17]	Zhou S, Yang C C, Su Z N, et al. An aeromagnetic compensation algorithm based on radial basis function artificial neural network[J]. Applied Sciences, 2023, 13(1):136.
[18]	Yu P, Bi F Y, Jiao J, et al. An aeromagnetic compensation algorithm based on a residual neural network[J]. Applied Sciences, 2022, 12(21):10759.
[19]	Oelsner G, Schultze V, IJsselsteijn R, et al. Sources of heading errors in optically pumped magnetometers operated in the Earth’s magnetic field[J]. Physical Review A, 2019,99:013420.