A DRL Unified Interference Suppression Method For MCR-WPT System
DOI:
https://doi.org/10.54097/9staq964Keywords:
MCR-WPT; DRL; Compound interference; Self-adaptation control.Abstract
Magnetic coupling resonant wireless power transfer (MCR-WPT) technology often experiences performance decline due to compound interference, including coil displacement, metal foreign object intrusion, load mutation, and electromagnetic interference (EMI). Existing control methods struggle to suppress such interference uniformly; thus this paper proposes a unified interference suppression method based on deep reinforcement learning (DRL). First, a simulation environment containing the four types of typical interference is constructed in Simulink. Subsequently, a controller based on the deep deterministic policy gradient (DDPG) algorithm is designed, which regards the inverter’s operating frequency and duty cycle as a continuous two-dimensional action space. A reward function is designed, incorporating power tracking, transmission efficiency and electrical safety, guiding the agent to balance multiple objectives in a complex environment. The curriculum learning strategy is also introduced for staged training. The analysis of open-loop characteristics of the system demonstrates nonlinearity and sensitivity under complex disturbances as well as the conflict between optimal power and efficiency goals. These findings emphasize the necessity of the adaptive intelligent control method. The DRL controller designed in this paper provides a complete framework for complex disturbance in MCR-WPT systems, enabling self-adaptation control without relying on an accurate system model, showing strong application potential.
Downloads
References
[1] Buja G, Bertoluzzo M, Mude K N. Design and Experimentation of WPT Charger for Electric City Car[J]. IEEE Transactions on Industrial Electronics, 2015(12). DOI: https://doi.org/10.1109/TIE.2015.2455524
[2] Abu Houran M, Yang X, Chen W. Magnetically Coupled Resonance WPT: Review of Compensation Topologies, Resonator Structures with Misalignment, and EMI Diagnostics[J]. Electronics, 2018(11). DOI: https://doi.org/10.3390/electronics7110296
[3] Li J, Li S, Wang Y, et al. Review on magnetic coupling resonant type wireless power transmission technology[J]. Electrical Measurement & Instrumentation, 2024(8).
[4] Liu F, Yang Y, Ding Z, et al. A Multifrequency Superposition Methodology to Achieve High Efficiency and Targeted Power Distribution for a Multiload MCR WPT System[J]. IEEE Transactions on Power Electronics, 2018, 33(10): 9005-9016. DOI: https://doi.org/10.1109/TPEL.2017.2784566
[5] Liu X, Chao J, Rong C, et al. Compatibility and Performance Improvement of the WPT Systems Based on Q-Learning Algorithm[J]. IEEE Transactions on Power Electronics, 2024(8 Pt.2). DOI: https://doi.org/10.1109/TPEL.2024.3397804
[6] Huang R, Zhang B, Qiu D, et al. Frequency Splitting Phenomena of Magnetic Resonant Coupling Wireless Power Transfer[J]. IEEE Transactions on Magnetics, 2014(11). DOI: https://doi.org/10.1109/TMAG.2014.2331143
[7] Hou J, Chen Q, Wong S C, et al. Analysis and control of series/series-parallel compensated resonant converter for contactless power transfer[J]. IEEE Journal of Emerging and selected topics in Power Electronics, 2014, 3(1): 124-136. DOI: https://doi.org/10.1109/JESTPE.2014.2336811
[8] Sample A P, Meyer D T, Smith J R. Analysis, experimental results, and range adaptation of magnetically coupled resonators for wireless power transfer[J]. IEEE Transactions on industrial electronics, 2010, 58(2): 544-554. DOI: https://doi.org/10.1109/TIE.2010.2046002
[9] Zhang W, Wong S C, Chi K T, et al. Design for efficiency optimization and voltage controllability of series–series compensated inductive power transfer systems[J]. IEEE Transactions on Power Electronics, 2013, 29(1): 191-200. DOI: https://doi.org/10.1109/TPEL.2013.2249112
[10] Hui S Y R, Zhong W, Lee C K. A critical review of recent progress in mid-range wireless power transfer[J]. IEEE transactions on power electronics, 2013, 29(9): 4500-4511. DOI: https://doi.org/10.1109/TPEL.2013.2249670
[11] Puterman M L. Markov decision processes[M]. Handbooks in operations research and management science, 1990, 2: 331-434. DOI: https://doi.org/10.1016/S0927-0507(05)80172-0
[12] Qiu C, Hu Y, Chen Y, et al. Deep deterministic policy gradient (DDPG)-based energy harvesting wireless communications[J]. IEEE Internet of Things Journal, 2019, 6(5): 8577-8588. DOI: https://doi.org/10.1109/JIOT.2019.2921159
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Academic Journal of Science and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
