电动汽车无线充电系统多维度偏移检测技术研究

配备无线充电系统的电动汽车具有便捷、安全等优点。然而，在实际使用场景中，传能线圈之间的偏移会引起功率、效率下降等问题，甚至导致系统无法运行。过往的研究主要关注水平方向上的位置偏移情景，而很少考虑同时包含角度偏移和位置偏移的情景。实际上，在车辆进行对准的过程中一定会存在角度偏移，这会导致偏移检测方法的失效。另外，角度偏移也会影响充电性能，特别是对于使用非圆形传能线圈的充电系统。为了准确地帮助车辆实现传能线圈的偏移对准，本文对偏移检测线圈、检测算法及其稳定性等方面做出了研究。具体完成了以下工作：

本文以使用矩形传能线圈的无线充电系统为例，通过有限元仿真对偏移情境下的空间磁场分布进行分析，并对偏移感应电压进行理论推导，提出了双组协作线圈组设计和搭建了多维度偏移检测系统。通过对不同偏移位置下检测线圈采集的信号进行分析和计算，验证了该线圈组设计能够有效提取多维度偏移信号特征和增强不同偏移信号之间的特征差异。

本文针对偏移信号难以求解的问题，提出了多维度偏移检测算法。该算法核心是通过自适应通道参数再校准机制，以增强残差网络对偏移特征的学习能力。该算法还利用了传能线圈的对称特点，将偏移定位标签和训练样本的数量压缩到原来的1/4。通过大量仿真数据的训练以及与经典算法的对比，验证了该算法的可行性和准确性。

本文还针对高度偏移导致上述算法识别能力下降的问题，提出了基于深度迁移学习的多域网络模型，并通过调整不同迁移任务的参数，提升了各目标域模型的迁移效果。测试结果表明，目标域更密集的融合模型拥有更好的泛化能力，该方法增强了偏移检测算法识别能力的稳定性和可靠性。

本文最后根据所提出的双组协作线圈组设计，搭建了无线充电实验平台和偏移检测装置，并采集了多组实验样本。测试结果表明，在同时发生角度偏移和位置偏移的情境下，多维度偏移检测算法实现了准确的偏移标签识别，且定位误差满足行业标准。当实验平台的传能高度发生变化时，在多域网络模型框架下的偏移检测算法保持了稳定的识别效果。

Electric vehicles featuring wireless charging systems offer benefits such as convenience and safety. However, in practical situations, misalignment between energy transfer coils can lead to issues such as power and efficiency reduction, or even render the system inoperative. Existing misalignment recognition (MR) methods primarily address horizontal or angular misalignment separately, proving insufficient for real-world parking scenarios where multi-type misalignment occur concurrently, resulting in diminished effectiveness. Moreover, angular misalignment also impacts charging performance, particularly for wireless charging systems utilizing non-centrally symmetric energy transfer coils, such as rectangular coils. To facilitate vehicle misalignment recognition, this paper investigates misalignment detection coils, recognition algorithms, and methods for enhancing algorithm stability. The following tasks have been completed:

Focusing on wireless charging systems with rectangular energy transfer coils, this paper analyzes the spatial magnetic field distribution under misalignment scenarios and theoretically derives the relationship between misalignment and induced voltage. A double group cooperative (DGC) coil design is proposed, and a multi-type misalignment recognition system is established. By analyzing and calculating the signals collected by the recognition coils at various misalignment positions, it is demonstrated that this coil group design can effectively extract multi-type misalignment signal features and enhance the differences between distinct signals.

This paper introduces a multi-type misalignment recognition algorithm to address the challenge of interpreting misalignment signals. The core of this algorithm is the enhancement of the residual network's learning ability for misalignment features, through an adaptive channel parameter recalibration (ACPR) mechanism. The algorithm also leverages the center symmetry of energy transfer coils to reduce the number of misalignment positioning labels and training samples to 1/4 of the original. The feasibility and accuracy of this algorithm are verified through training with a large volume of simulation data and comparison with classic algorithms.

This paper also introduces a multi-domain network model based on deep transfer learning to address the issue of decreased recognition ability caused by height misalignment. By adjusting parameters for different transfer tasks, the transfer effect of each target domain model is enhanced. Test results demonstrate that a more densely fused model of target domains exhibits superior generalization ability, and this method bolsters the stability and reliability of the recognition ability for the misalignment recognition algorithm.

Lastly, in accordance with the dual-group cooperative recognition coil group design proposed in this paper, a wireless charging experimental platform and a misalignment recognition device are constructed, and several sets of experimental samples are collected. The test results reveal that, in scenarios where both angular misalignment and horizontal misalignment occur simultaneously, the proposed recognition algorithm accurately classifies position labels with misalignment errors meeting industry standards. The multi-domain network model ensures the proposed algorithm maintains a stable recognition effect, even when the energy transfer distance of the experimental platform varies.

[1] 国务院办公厅关于印发新能源汽车产业发展规划(2021—2035年)的通知[J]. 中华人民共和国国务院公报, 2020(31): 16-23.
[2] WU S, CAI C, LIU X, et al. Compact and Free-Positioning Omnidirectional Wireless Power Transfer System for Unmanned Aerial Vehicle Charging Applications[J]. IEEE Transactions on Power Electronics, 2022(8):37.
[3] ZHANG Z, PANG H L, GEORGIADIS A, et al. Wireless power transfer-an overview[J]. IEEE Transactions on Industrial Electronics, 2019, 66(2): 1044-1058.
[4] LIANG H W R, WANG H W, LEE C K, et al. Analysis and performance enhancement of wireless power transfer systems with intended metallic objects[J]. IEEE Transactions on Power Electronics, 2021, 36(2): 1388-1398.
[5] MAHESH A, BHARATIRAJA C, POPA L M. Review on inductive wireless power transfer charging for electric vehicle—a review[J]. IEEE Access, 2021, 9:137667-137713.
[6] LIU S P, WU Y H, ZHOU L Y, et al. A Misalignment-Tolerant IPT System Based on Dual Decoupled Receiver Coils with Voltage Doubler Rectifier[C]//2022 IEEE Applied Power Electronics Conference and Exposition (APEC), 2022:1104-1109.
[7] SAB A, DW B, CPY A, et al. How driver behaviour and parking alignment affects inductive charging systems for electric vehicles - ScienceDirect[J]. Transportation Research Part C: Emerging Technologies, 2015, 58: 721-731.
[8] SCHNEIDER J M, O'HARE J J. Alignment, verification, and optimization of high power wireless charging systems: US, US09637014B2[P]2017-05-02.
[9] NI W, COLLINGS I B, WANG X, et al. Radio alignment for inductive charging of electric vehicles[J]. IEEE Transactions on Industrial Informatics, 2015, 11(2): 427-440.
[10] XU J, LI Z, ZHANG K, et al. The Principle, Methods and Recent Progress in RFID Positioning Techniques: A Review[J], IEEE Journal of Radio Frequency Identification, 2023, 7: 50-63.
[11] HASHI S, YABUKAMI S, KANETAKA H, et al. Wireless magnetic position-sensing system using optimized pickup coils for higher accuracy[J]. IEEE Transactions on Magnetics, 2011, 47(10): 3542-3545.
[12] KHAN N, MATSUMOTO H, TRESCASES O. Wireless electric vehicle charger with electromagnetic coil-based position correction using impedance and resonant frequency detection[J]. IEEE Transactions on Power Electronics, 2020, 35(8): 7873-7883.
[13] DAHAL A, KUMAR V R, YOGAMANI S, et al. An Online Learning System for Wireless Charging Alignment Using Surround-View Fisheye Cameras[J], IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11): 20553-20562.
[14] YANG Y, WANG X, LI D, et al. An Improved Indoor 3-D Ultrawideband Positioning Method by Particle Swarm Optimization Algorithm[J], IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-11.
[15] LIU L, NIU P, LUO D, et al. A method for aligning of transmitting and receiving coils of electric vehicle wireless charging based on binocular vision[C]//2017 IEEE Conference on Energy Internet and Energy System Integration (EI2). IEEE, 2018: 1-6.
[16] 日月. 日本研制无人驾驶公共汽车[J]. 航天技术与民品, 2000(6): 38-38.
[17] GAO Y, CHEN D, OLIVEIRA A A, et al. 3-D Coil positioning based on magnetic sensing for wireless EV charging[J]. IEEE Transactions on Transportation Electrification, 2017, 3(3): 578-588.
[18] LIU X, LIU C, HAN W, et al. Design and Implementation of a Multi-Purpose TMR Sensor Matrix for Wireless Electric Vehicle Charging[J]. IEEE Sensors Journal, 2019, 19(5): 1683-1692.
[19] BABU A, GEORGE B. Sensor system to aid the vehicle alignment for inductive ev chargers[J]. IEEE Transactions on Industrial Electronics, 2018, 66(9): 7338-7346.
[20] JESHMA T V, GEORGE B. MR sensor based coil alignment sensing system for wirelessly charged EVs[J]. IEEE Sensors Journal, 2020, 20(99): 5588-5596.
[21] TAN L, LI C, J LI, et al. Mesh-based accurate positioning strategy of EV wireless charging coil with detection coils[J]. IEEE Transactions on Industrial Informatics, 2020, 17(5): 3176-3185.
[22] ZHANG Z, ZHENG S, YAO Z, et al. A Coil Positioning Method Integrated With an Orthogonal Decoupled Transformer for Inductive Power Transfer Systems[J] IEEE Transactions on Power Electronics, 2022, 37(8): 9983-9998.
[23] WANG R, HUANG X. Multi-degree of freedom accurate offset angle measurement for coils based on 3D electronic compasses[J]. IEEE sensors journal, 2021, 21(19): 22038-22046.
[24] WEI Y Q, LUO Q M, MANTOOTH ALAN. A Resonant frequency tracking technique for LLC converter-based DC transformers[J]. IEEE Journal of Emerging and Selected Topics in Industrial Electronics, 2021, 2(4): 579-590.
[25] 曹玲玲, 陈乾宏, 任小永, 等. 电动汽车高效率无线充电技术的研究进展[J]. 电工技术学报, 2012, 27(8): 13.
[26] V. F. -G. TSENG, S. S. BEDAIR, J. J. RADICE, et al. Ultrasonic Lamb Waves for Wireless Power Transfer[J]. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2020, 67(3):664-670.
[27] MATOS D, CORREIA R, CARVALHO N B. Millimeter-wave hybrid rf-dc converter based on a GaAs chip for IOT-WPT applications[J]. IEEE Microwave and Wireless Components Letters, 2021, PP(99):1-1.
[28] CHINTHAVALI M S, ONAR O C, MILLER J M, et al. SiC MOSFET based single phase active boost rectifier with power factor correction for wireless power transfer applications[C]//2013 IEEE Energy Conversion Congress and Exposition (ECCE). IEEE, 2013: 3258-3265.
[29] WU H H, GILCHRIST A, SEALY K D, et al. A high efficiency 5 kw inductive charger for evs using dual side control[J]. IEEE Transactions on Industrial Informatics, 2012, 8(3): 585-595.
[30] AL-KARAKCHI A A, LACEY G, PUTRUS G. A method of electric vehicle charging to improve battery life[C]//2015 IEEE International Universities Power Engineering Conference (UPEC). IEEE, 2015: 1-3.
[31] BOYS J T, COVIC G A, GREEN A W. Stability and control of inductively coupled power transfer systems[J]. IEEE Proceedings-Electric Power Applications, 2000, 147(1): 37-43.
[32] KUMAR P, RITURAJ G. A new magnetic structure of unipolar rectangular coils in WPT systems to minimize the ferrite volume while maintaining maximum coupling[J]. IEEE Transactions on Circuits and Systems, II. Express briefs, 2021(68-6).
[33] INOUE R, UEDA H, KIM S. Study on Low-Loss and high-energy density coil structure of a wireless power transmission system using high temperature superconducting coils for railway vehicle[J]. IEEE Transactions on Applied Superconductivity, 2022, 32(6):1-4.
[34] BUDHIA M, BOYS J T, COVIC G A, et al. Development of a single-sided flux magnetic coupler for electric vehicle IPT charging systems[J]. IEEE Transactions on Industrial Electronics, 2013, 60(1): 318-328.
[35] 沈锦飞. 磁共振无线充电技术[M]. 北京: 机械工业出版社, 2020.
[36] 戴欣, 孙悦, 唐春森, 等. 无线电能传输技术[M]. 北京: 科学出版社, 2017.
[37] ZHAKSYLYK Y, HANKE U, AZADMEHR M. Single-Sided Interspiraled Inductive Impedance Matching for Magnetic Resonance Wireless Power Transfer[J]. IEEE Transactions on Circuits and Systems I: Regular Papers, 2023, 70(5):2189-2200.
[38] ZHAKSYLYK Y, HALVORSEN E, HANKE U, et al. Analysis of Fundamental Differences between Capacitive and Inductive Impedance Matching for Inductive Wireless Power Transfer[J]. Electronics, 2020, 9(3):476.
[39] BEH T C, IMURA T, KATO M, et al. Explicit Design of Impedance Matching Networks for Robust MHz WPT Systems With Different Features[J]. IEEE Transactions on Power Electronics, 2022, 37(9): 11382-11393.
[40] SHIN Y, WOO S, AHN S. Design of Series Inductors to Reduce EMI and Improve Power Bifurcation Phenomenon in WPT System[C]// 2022 Asia-Pacific Microwave Conference (APMC).
[41] VO T, DUONG Q T, OKADA M. Load-Independent Voltage Control for Multiple-Receiver Inductive Power Transfer Systems[J]. IEEE Access, 2019, 7(99):139450-139461.
[42] LIAO Z J, FENG Q K, JIANG C H, et al. Analysis and Design of EIT-Like Magnetic Coupling Wireless Power Transfer Systems[J]. IEEE Transactions on Circuits and Systems I: Regular Papers, 2021.
[43] VILLA J L, SALLAN J, OSORIO J, et al. High-misalignment tolerant compensation topology for ICPT systems[J]. IEEE Transactions on Industrial Electronics, 2011, 59(2): 945-951.
[44] BI Z, KAN T, MI C C, et al. A review of wireless power transfer for electric vehicles: Prospects to enhance sustainable mobility[J]. Applied Energy, 2016, 179(oct.1): 413-425.
[45] JAMES J E, ROBERTSON D, COVIC G A. Improved AC pickups for IPT systems[J]. IEEE Transactions on Power Electronics, 2014, 29(12): 6361-6374.
[46] HE R, ZHOU J, HU C. A Dual-Source Inductive Power Transfer System Optimized with Large Misalignment Tolerance[C]// IECON 2020 - 46th Annual Conference of the IEEE Industrial Electronics Society. IEEE, 2020.
[47] AUVIGNE C, GERMANO P, LADAS D, et al. A dual-topology ICPT applied to an electric vehicle battery charger[C]//2012 IEEE International Conference on Electrical Machines (ICEM). IEEE, 2012: 2287-2292.
[48] 孙运全, 顾加亭, 陆洋锐, 等. 基于双边LCC补偿槽恒流恒压输出的无线充电系统研究[J]. 电子器件, 2019, 42(06): 1428-1434.
[49] QU X, JING Y, HAN H, et al. Higher order compensation for inductive-power-transfer converters with constant-voltage or constant-current output combating transformer parameter constraints[J]. IEEE Transactions on Power Electronics, 2017, 32(1): 394-405.
[50] NIU S, XU H, SUN Z, et al. The state-of-the-arts of wireless electric vehicle charging via magnetic resonance: principles, standards and core technologies[J]. Renewable & Sustainable Energy Reviews, 2019, 114(OCT.): 109302.1-109302.20.
[51] ZHANG B, CHEN Q, ZHANG L, et al. Triple-coil-structure-based coil positioning system for wireless EV charger[J]. IEEE Transactions on Power Electronics, 2021, 36(12): 13515-13525.
[52] CULLINANE B, SMITH D, GREEN P. Where, when, and how well people park: a phone survey and field measurements[R]. University of Michigan Ann Arbor Transportation Research Institute, 2004.
[53] VEIT A, WILBER M J, BELONGIE S. Residual networks behave like ensembles of relatively shallow networks[C]//Advances in Neural Information Processing Systems. 2016: 550-558.
[54] ORHAN A E, PITKOW X. Skip Connections Eliminate Singularities[J]. International Conference on Learning Representations, 2018.
[55] NAIR V, HINTON G E. Rectified Linear Units Improve Restricted Boltzmann Machines Vinod Nair[C]//2010 International Conference on Machine Learning (ICML). JMLR.org, 2010: 807-814
[56] IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]//2015 International Conference on Machine Learning (ICML). JMLR.org, 2015: 448-456.
[57] 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: 770-778.
[58] BALDUZZI D, FREAN M, LEARY L, et al. The shattered gradients problem: If resnets are the answer, then what is the question?[C]//2017 International Conference on Machine Learning (ICML). JMLR.org, 2017: 342-350.
[59] ZHAO M H, ZHONG S S, FU X Y, et al. Deep residual networks with adaptively parametric rectifier linear units for fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2021, 68(3): 2587-2597.
[60] ZHANG X X, WANG J, IEEE. A Method for high-dynamic DS-FH signal simulation based on high-order DDS[C]//2017 International Conference on Systems and Informatics (ICSAI). IEEE, 2017: 1330-1335.
[61] RIFKIN R, KLAUTAU A. In defense of one-vs-all classification[J]. Journal of Machine Learning Research, 2004, 5: 101-141.
[62] DENG X Q, LI W K, LIU X P, et al. One-class remote sensing classification: one-class vs. binary classifiers[J]. International Journal of Remote Sensing, 2018, 39(6): 1890-1910.
[63] CHANG C C, LIN C J. LIBSVM: A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 27: 1-27.
[64] 徐启华, 杨瑞. 一种新的软间隔支持向量机分类算法[J]. 计算机工程与设计, 2005, 26(9): 3.
[65] FENG F, NA W C, JIN J, et al. Artificial neural networks for microwave computer-aided design: the state of the art[J]. IEEE Transactions on Microwave Theory and Techniques, 2022, 70(11): 4597-4619.
[66] ZHAO P, WU K. Homotopy optimization of microwave and millimeter-wave filters based on neural network model[J]. IEEE Transactions on Microwave Theory and Techniques, 2020, 68(4): 1390-1400.
[67] ZHANG W, FENG F, VENU-MADHAV-REDDY G R, et al. Space mapping approach to electromagnetic centric multiphysics parametric modeling of microwave components[J]. IEEE Transactions on Microwave Theory and Techniques, 2018, 66: 3169-3185.
[68] CHAUDHARY V, PANWAR R. FSS derived using a new equivalent circuit model backed deep neural network[J]. IEEE Antennas and Wireless Propagation Letters, 2021(10): 20.
[69] DACHENA C, FEDELI A, FANTI A, et al. Initial experimental tests of an ann-based microwave imaging technique for neck diagnostics[J]. IEEE Microwave and Wireless Components Letters, 2022, 32(12): 1495-1498.
[70] ZHOU P and AUSTIN J. Learning criteria for training neural network classifiers[J]. Neural Computation. Apply., vol. 7, no. 4, pp. 334–342, 1998.
[71] SHALEV-SHWARTZ S, ZHANG T. Stochastic dual coordinate ascent methods for regularized loss minimization[J]. Journal of Machine Learning Research, 2013, 14: 567-599.
[72] MAATEN L J P V D, HINTON G E. Visualizing high-dimensional data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9: 2579-2605.
[73] ZHANG X Y, ZOU J H, HE K M, et al. Accelerating very deep convolutional networks for classification and detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(10): 1943-1955.
[74] CHENG Y W, ZHU H P, WU J, et al. Machine health monitoring using adaptive kernel spectral clustering and deep long short-term memory recurrent neural networks[J]. IEEE Transactions on Industrial Informatics, 2019, 15(2): 987-997.
[75] PAN S J, QIANG Y. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345-1359.
[76] 王晋东, 陈益强. 迁移学习导论[M]. 北京: 电子工业出版社, 2022.
[77] LONG M, WANG J, DING G, et al. Transfer learning with graph co-regularization[J]. IEEE Transactions on Knowledge and Data Engineering, 2014, 26(7): 1805-1818.
[78] ZHANG Y, YANG Q. A survey on multi-task learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(12): 5586-5609.