Clark-Park Transformation based Autoencoder for 3-Phase Electrical Signals

During the past decades, significant progress has been made in the field of artificial neural networks to process images (Convolutional Neural Networks), audio signals (Temporal Convolutional Networks), or textual information (Transformers). However, for electrical three-phase signals processing, these network architectures ignore important characteristics and therefore lack of computational efficiency. This can lead to performance problems and limits the application potential of neural networks for a fast and efficient local analysis of three-phase electrical current or voltage waveforms. To address this issue, a novel autoencoder architecture is proposed in this paper, which incorporates Clark-Park transformation to learn the representations of three-phase electrical signals. Using unbalanced and noisy voltage signals, the Clark-Park based autoencoder shows superior performance and computational efficiency compared to recurrent and convolutional benchmark architectures.