A reinforcement learning agent with variational autoencoder state compression and noise-based exploration adaptively tunes active EMI filters, delivering 25-30 dB better attenuation than fixed passive or conventional methods in co-simulation using measured automotive drive-unit spectra.
IEEE Transactions on Power Electronics 20, 523–
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Intelligent Self-tuning Active EMI Filtering for Electrified Automotive Power Systems Using Reinforcement Learning
A reinforcement learning agent with variational autoencoder state compression and noise-based exploration adaptively tunes active EMI filters, delivering 25-30 dB better attenuation than fixed passive or conventional methods in co-simulation using measured automotive drive-unit spectra.