Mahuizi Lu, Kelin Jia, Rajib Goswami et al. · Apr 30, 2026
A reinforcement learning approach is used to develop an intelligent self-tuning active EMI filtering system for electrified automotive power systems. The system reduces electromagnetic interference by 25-30 dB across a wide frequency range compared to conventional control strategies and passive filtering solutions, and uses variational autoencoders and noise-based exploration mechanisms to improve robustness and generalization. This approach enables lightweight, energy-efficient, and reliable power-electronic systems for intelligent and green transportation applications.
Why This Matters
This paper matters for power industry professionals as it proposes a novel EMI filtering approach that can improve the reliability and adaptability of electrified automotive power systems, which is a critical component in modern grid operations, particularly in regions with high penetration of electric vehicles. By mitigating EMI, this solution can enhance the overall resilience of the grid and support the integration of renewable energy sources.