A receptive field transfer strategy using layer-aligned distillation learning for multivariate fault signal denoising

To improve fault diagnosis performance in complex noise environments, effective signal denoising techniques are necessary. However, traditional denoising methods have proven inadequate for multivariate fault signal denoising, neglecting the correlation between these signals. To address this, we propose a novel denoising module, inspired by traditional signal decomposition and reconstruction methods. To further enhance the performance of our denoising modules, we analyze the influence of the receptive field and develop a receptive field transfer strategy using layer-aligned distillation learning. Our experiments demonstrate that the proposal effectively balances the receptive field and computational load, offering a new approach for developing high-performance denoising networks.